diff --git a/adapter_model.bin b/adapter_model.bin
index 881c929ef6feee8884c6c40245ae107a561cf26b..5de3f3e6c9e61b9bd3e08f609bbd9ec5373788b9 100644
--- a/adapter_model.bin
+++ b/adapter_model.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834da4210cbe02d35ef0db3b3658d8c7275dda5e4c2e20ff5a4d8f2c935cd877
+oid sha256:beeedc987a15ea2421995f369107f9b533b5d424088562667fdc59e9d36e27f2
 size 113314765
diff --git a/checkpoint-600/README.md b/checkpoint-600/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b32efe7366f05d1d90816d2ad9e4b06ccca46bea
--- /dev/null
+++ b/checkpoint-600/README.md
@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-600/adapter_config.json b/checkpoint-600/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e108f2da037ef6250457c67a4bedd308d97303c
--- /dev/null
+++ b/checkpoint-600/adapter_config.json
@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-600/adapter_model.bin b/checkpoint-600/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1c98e4dc10d4397572ad2233bf1f2ae5d0a10fcb
--- /dev/null
+++ b/checkpoint-600/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e89ebdd6587ad945d5187588bd36ac4fd4361c7ed1a2e67c15bf52aafd5e3b98
+size 113314765
diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1ae7df044a47da4d59810d802b04d0388f367571
--- /dev/null
+++ b/checkpoint-600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e961eee9681942c9b315a838e8c3305c3384b8c6dbacb3b820d1779f6e573c23
+size 226653957
diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e0eac287fe6aaa4f5ead2a49c7c4f92cbe6cc9e4
--- /dev/null
+++ b/checkpoint-600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3bd16cf2784e27d887ba26f43636be027528577198ffa7914b576e44c1fd6ad
+size 14575
diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b8b78778de95ad4ef2d142354e507dc82c66b32c
--- /dev/null
+++ b/checkpoint-600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f7cf85b820e7f67d841ddbeab7ac10af6e481bc637d729f2badec258f8130b
+size 627
diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b0c37d1b93b481e094b45de6ce15c0e2f4f92d7c
--- /dev/null
+++ b/checkpoint-600/trainer_state.json
@@ -0,0 +1,3619 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1559754483090625,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6869,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8396,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7489,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7252,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8022,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.6524,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6981,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7488,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6891,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7968,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6912,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8452,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 0.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6685,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5469,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7915,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.6e-05,
+      "loss": 0.7744,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.6804,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.4e-05,
+      "loss": 0.7796,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.706,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6798,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6333,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 0.6012,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.52,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6583,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.7354,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000116,
+      "loss": 0.6296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 0.6352,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000124,
+      "loss": 0.6007,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5659,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000132,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6639,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 0.5934,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000144,
+      "loss": 0.5233,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000148,
+      "loss": 0.5307,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000152,
+      "loss": 0.5928,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5908,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000164,
+      "loss": 0.5972,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000168,
+      "loss": 0.4825,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000172,
+      "loss": 0.6783,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 0.7633,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5988,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000188,
+      "loss": 0.6658,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000192,
+      "loss": 0.5945,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000196,
+      "loss": 0.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.6057,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.601,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.5566,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.5911,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.7636,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.5537,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000232,
+      "loss": 0.6474,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000236,
+      "loss": 0.6483,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00024,
+      "loss": 0.5021,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000244,
+      "loss": 0.5347,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000248,
+      "loss": 0.5791,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000252,
+      "loss": 0.5407,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.5298,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5685,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000264,
+      "loss": 0.5108,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000268,
+      "loss": 0.526,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6843,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000276,
+      "loss": 0.6608,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00028,
+      "loss": 0.5866,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000284,
+      "loss": 0.6422,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000288,
+      "loss": 0.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000292,
+      "loss": 0.5319,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000296,
+      "loss": 0.5977,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.5805,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000304,
+      "loss": 0.5209,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000308,
+      "loss": 0.6098,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.4665,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6882,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00032,
+      "loss": 0.5427,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000324,
+      "loss": 0.5345,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000328,
+      "loss": 0.663,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000332,
+      "loss": 0.5393,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000336,
+      "loss": 0.5711,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00034,
+      "loss": 0.5261,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000344,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000348,
+      "loss": 0.6329,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.4425,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6837,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00036,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000364,
+      "loss": 0.5615,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5434,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000376,
+      "loss": 0.5583,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00038,
+      "loss": 0.5299,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000384,
+      "loss": 0.532,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000388,
+      "loss": 0.5227,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000392,
+      "loss": 0.5275,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.4541,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004,
+      "loss": 0.6485,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003999995350775973,
+      "loss": 0.5438,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999814031255063,
+      "loss": 0.5997,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999581571134455,
+      "loss": 0.5322,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003999925612847867,
+      "loss": 0.484,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998837704800766,
+      "loss": 0.5961,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998326302046085,
+      "loss": 0.7405,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997721922592255,
+      "loss": 0.5802,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997024569249167,
+      "loss": 0.769,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999623424525898,
+      "loss": 0.5598,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999535095429608,
+      "loss": 0.6143,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039994374700467095,
+      "loss": 0.5766,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039993305488310836,
+      "loss": 0.7695,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999214332279831,
+      "loss": 0.7153,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999088820933269,
+      "loss": 0.5835,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039989540153749286,
+      "loss": 0.6634,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000399880991623155,
+      "loss": 0.6069,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998656524173082,
+      "loss": 0.7224,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000399849383991268,
+      "loss": 0.5884,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998321864206699,
+      "loss": 0.5122,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039981405978546924,
+      "loss": 0.6453,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997950041699408,
+      "loss": 0.4665,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997750196626785,
+      "loss": 0.5428,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039975410635659464,
+      "loss": 0.4365,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039973226434891995,
+      "loss": 0.5978,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039970949374120286,
+      "loss": 0.7729,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000399685794639309,
+      "loss": 0.6212,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039966116715342066,
+      "loss": 0.5426,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00039963561139803676,
+      "loss": 0.5782,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003996091274919716,
+      "loss": 0.6701,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995817155583548,
+      "loss": 0.6314,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995533757246307,
+      "loss": 0.6662,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995241081225573,
+      "loss": 0.5192,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994939128882065,
+      "loss": 0.5591,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994627901619625,
+      "loss": 0.5809,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994307400885219,
+      "loss": 0.4871,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993977628168928,
+      "loss": 0.6666,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993638585003938,
+      "loss": 0.6469,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039932902729665357,
+      "loss": 0.5727,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039929326936761036,
+      "loss": 0.6715,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039925658487951067,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039921897400290894,
+      "loss": 0.501,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039918043691266665,
+      "loss": 0.5795,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039914097378795124,
+      "loss": 0.6287,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039910058481223564,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039905927017329726,
+      "loss": 0.6232,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039901703006321715,
+      "loss": 0.5291,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039897386467837903,
+      "loss": 0.5297,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039892977421946844,
+      "loss": 0.5784,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988847588914718,
+      "loss": 0.5714,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988388189036754,
+      "loss": 0.5044,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987919544696646,
+      "loss": 0.8246,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987441658073226,
+      "loss": 0.5048,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003986954531388297,
+      "loss": 0.5433,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039864581669066186,
+      "loss": 0.5251,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003985952566935902,
+      "loss": 0.5708,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039854377338267936,
+      "loss": 0.6276,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039849136699728684,
+      "loss": 0.4915,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003984380377810617,
+      "loss": 0.6389,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039838378598194325,
+      "loss": 0.6067,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039832861185216045,
+      "loss": 0.6136,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003982725156482301,
+      "loss": 0.5597,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000398215497630956,
+      "loss": 0.5957,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003981575580654278,
+      "loss": 0.5853,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980986972210194,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980389153713881,
+      "loss": 0.5302,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039797821279447307,
+      "loss": 0.5395,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039791658977249425,
+      "loss": 0.7004,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039785404659195084,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039779058354362013,
+      "loss": 0.5759,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000397726200922556,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003976608990280877,
+      "loss": 0.5488,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975946781638183,
+      "loss": 0.6162,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975275386376236,
+      "loss": 0.558,
+      "step": 173
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003974594807616502,
+      "loss": 0.519,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003973905048523144,
+      "loss": 0.6195,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039732061123030064,
+      "loss": 0.5991,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003972498002205601,
+      "loss": 0.5428,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039717807215230896,
+      "loss": 0.5323,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039710542735902705,
+      "loss": 0.5307,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003970318661784564,
+      "loss": 0.5783,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003969573889525993,
+      "loss": 0.5924,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039688199602771714,
+      "loss": 0.5902,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039680568775432855,
+      "loss": 0.6291,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003967284644872077,
+      "loss": 0.5942,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003966503265853829,
+      "loss": 0.4878,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003965712744121347,
+      "loss": 0.6487,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003964913083349945,
+      "loss": 0.6111,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039641042872574233,
+      "loss": 0.6072,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039632863596040575,
+      "loss": 0.716,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039624593041925763,
+      "loss": 0.6178,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003961623124868145,
+      "loss": 0.6323,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039607778255183485,
+      "loss": 0.5821,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959923410073174,
+      "loss": 0.6738,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959059882504989,
+      "loss": 0.6203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039581872468285277,
+      "loss": 0.632,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003957305507100868,
+      "loss": 0.5857,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039564146674214164,
+      "loss": 0.6311,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003955514731931885,
+      "loss": 0.5889,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039546057048162763,
+      "loss": 0.5201,
+      "step": 199
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039536875903008607,
+      "loss": 0.5581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039527603926541586,
+      "loss": 0.5104,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039518241161869193,
+      "loss": 0.5978,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039508787652521013,
+      "loss": 0.6244,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039499243442448536,
+      "loss": 0.589,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003948960857602493,
+      "loss": 0.575,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947988309804485,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947006705372422,
+      "loss": 0.4895,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039460160488700036,
+      "loss": 0.5479,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039450163449030124,
+      "loss": 0.5893,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003944007598119297,
+      "loss": 0.5451,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003942989813208747,
+      "loss": 0.5582,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003941962994903273,
+      "loss": 0.5121,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039409271479767826,
+      "loss": 0.6324,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000393988227724516,
+      "loss": 0.6118,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003938828387566244,
+      "loss": 0.6303,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003937765483839804,
+      "loss": 0.7705,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003936693571007517,
+      "loss": 0.6224,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935612654052946,
+      "loss": 0.5664,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039345227380015163,
+      "loss": 0.66,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039334238279204906,
+      "loss": 0.5582,
+      "step": 220
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039323159289189505,
+      "loss": 0.6087,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003931199046147764,
+      "loss": 0.5566,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039300731847995716,
+      "loss": 0.5775,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039289383501087534,
+      "loss": 0.5081,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277945473514104,
+      "loss": 0.5218,
+      "step": 225
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003926641781845338,
+      "loss": 0.6655,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003925480058950002,
+      "loss": 0.5735,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039243093840665114,
+      "loss": 0.6609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003923129762637596,
+      "loss": 0.7323,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000392194120014758,
+      "loss": 0.5703,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039207437021223583,
+      "loss": 0.6545,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003919537274129366,
+      "loss": 0.521,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039183219217775564,
+      "loss": 0.5257,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003917097650717377,
+      "loss": 0.5487,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039158644666407365,
+      "loss": 0.4861,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039146223752809845,
+      "loss": 0.4928,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003913371382412883,
+      "loss": 0.5253,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039121114938525756,
+      "loss": 0.6155,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039108427154575684,
+      "loss": 0.55,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039095650531266967,
+      "loss": 0.6617,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039082785128000976,
+      "loss": 0.5198,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039069831004591866,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003905678822126625,
+      "loss": 0.5347,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039043656838662946,
+      "loss": 0.531,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039030436917832697,
+      "loss": 0.4884,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039017128520237883,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003900373170775222,
+      "loss": 0.5537,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038990246542660494,
+      "loss": 0.5753,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038976673087658256,
+      "loss": 0.5059,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038963011405851537,
+      "loss": 0.5118,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038949261560756565,
+      "loss": 0.5645,
+      "step": 251
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003893542361629944,
+      "loss": 0.5623,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038921497636815866,
+      "loss": 0.5216,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003890748368705085,
+      "loss": 0.4501,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003889338183215838,
+      "loss": 0.48,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038879192137701135,
+      "loss": 0.5218,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003886491466965018,
+      "loss": 0.5858,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038850549494384685,
+      "loss": 0.6124,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038836096678691536,
+      "loss": 0.4645,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038821556289765136,
+      "loss": 0.474,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038806928395207003,
+      "loss": 0.4364,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038792213063025484,
+      "loss": 0.5821,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003877741036163547,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003876252035985804,
+      "loss": 0.5373,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003874754312692013,
+      "loss": 0.6021,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003873247873245426,
+      "loss": 0.4549,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003871732724649817,
+      "loss": 0.5994,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003870208873949453,
+      "loss": 0.4764,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038686763282290556,
+      "loss": 0.4311,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003867135094613774,
+      "loss": 0.5462,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003865585180269148,
+      "loss": 0.5006,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003864026592401076,
+      "loss": 0.5347,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038624593382557835,
+      "loss": 0.5242,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038608834251197856,
+      "loss": 0.5005,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038592988603198554,
+      "loss": 0.5436,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000385770565122299,
+      "loss": 0.4658,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003856103805236375,
+      "loss": 0.5273,
+      "step": 277
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038544933298073516,
+      "loss": 0.436,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038528742324233804,
+      "loss": 0.4785,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038512465206120086,
+      "loss": 0.5366,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038496102019408324,
+      "loss": 0.4448,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038479652840174637,
+      "loss": 0.5132,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038463117744894955,
+      "loss": 0.7918,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038446496810444627,
+      "loss": 0.5309,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038429790114098114,
+      "loss": 0.5316,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038412997733528576,
+      "loss": 0.4611,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038396119746807563,
+      "loss": 0.4609,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038379156232404613,
+      "loss": 0.5821,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003836210726918691,
+      "loss": 0.5883,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003834497293641889,
+      "loss": 0.5012,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038327753313761913,
+      "loss": 0.4457,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038310448481273867,
+      "loss": 0.4851,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038293058519408787,
+      "loss": 0.5622,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038275583509016507,
+      "loss": 0.5703,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038258023531342265,
+      "loss": 0.5718,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003824037866802632,
+      "loss": 0.5183,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038222649001103614,
+      "loss": 0.5085,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038204834613003323,
+      "loss": 0.5388,
+      "step": 298
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038186935586548537,
+      "loss": 0.5425,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003816895200495584,
+      "loss": 0.447,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003815088395183493,
+      "loss": 0.5541,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038132731511188227,
+      "loss": 0.5518,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000381144947674105,
+      "loss": 0.5074,
+      "step": 303
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003809617380528847,
+      "loss": 0.5134,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003807776871000037,
+      "loss": 0.4599,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003805927956711562,
+      "loss": 0.5838,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038040706462594395,
+      "loss": 0.5216,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038022049482787216,
+      "loss": 0.5323,
+      "step": 308
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003800330871443456,
+      "loss": 0.5681,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00037984484244666446,
+      "loss": 0.4172,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003796557616100207,
+      "loss": 0.4958,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003794658455134934,
+      "loss": 0.662,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003792750950400451,
+      "loss": 0.5832,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003790835110765174,
+      "loss": 0.4271,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003788910945136271,
+      "loss": 0.4842,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037869784624596186,
+      "loss": 0.4656,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037850376717197626,
+      "loss": 0.4981,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037830885819398733,
+      "loss": 0.5162,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037811312021817067,
+      "loss": 0.652,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003779165541545558,
+      "loss": 0.5104,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003777191609170225,
+      "loss": 0.4971,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003775209414232962,
+      "loss": 0.4871,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003773218965949436,
+      "loss": 0.5226,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00037712202735736884,
+      "loss": 0.4823,
+      "step": 324
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003769213346398087,
+      "loss": 0.497,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003767198193753286,
+      "loss": 0.5976,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003765174825008181,
+      "loss": 0.4532,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003763143249569868,
+      "loss": 0.5236,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00037611034768835947,
+      "loss": 0.6513,
+      "step": 329
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037590555164327224,
+      "loss": 0.5686,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037569993777386774,
+      "loss": 0.456,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003754935070360909,
+      "loss": 0.5181,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003752862603896846,
+      "loss": 0.4765,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037507819879818477,
+      "loss": 0.5363,
+      "step": 334
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037486932322891646,
+      "loss": 0.4584,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037465963465298886,
+      "loss": 0.5428,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003744491340452913,
+      "loss": 0.3927,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003742378223844882,
+      "loss": 0.5478,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003740257006530147,
+      "loss": 0.469,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037381276983707246,
+      "loss": 0.5169,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037359903092662434,
+      "loss": 0.4797,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037338448491539054,
+      "loss": 0.5315,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037316913280084353,
+      "loss": 0.4422,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003729529755842035,
+      "loss": 0.4426,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003727360142704337,
+      "loss": 0.4718,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003725182498682361,
+      "loss": 0.5585,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003722996833900459,
+      "loss": 0.4775,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003720803158520279,
+      "loss": 0.6014,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00037186014827407076,
+      "loss": 0.5117,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003716391816797829,
+      "loss": 0.5404,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003714174170964876,
+      "loss": 0.527,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037119485555521796,
+      "loss": 0.4555,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037097149809071255,
+      "loss": 0.5372,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037074734574141016,
+      "loss": 0.5377,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003705223995494454,
+      "loss": 0.4925,
+      "step": 355
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037029666056064345,
+      "loss": 0.482,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037007012982451546,
+      "loss": 0.5235,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00036984280839425356,
+      "loss": 0.4957,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000369614697326726,
+      "loss": 0.5379,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003693857976824721,
+      "loss": 0.4653,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036915611052569785,
+      "loss": 0.469,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003689256369242702,
+      "loss": 0.5618,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003686943779497124,
+      "loss": 0.4459,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003684623346771995,
+      "loss": 0.5606,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003682295081855524,
+      "loss": 0.4368,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036799589955723375,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036776150987834243,
+      "loss": 0.4664,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036752634023860846,
+      "loss": 0.4737,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003672903917313883,
+      "loss": 0.4247,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036705366545365935,
+      "loss": 0.5677,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036681616250601505,
+      "loss": 0.5441,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003665778839926599,
+      "loss": 0.6247,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00036633883102140405,
+      "loss": 0.5217,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003660990047036584,
+      "loss": 0.4651,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003658584061544291,
+      "loss": 0.4648,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003656170364923128,
+      "loss": 0.6048,
+      "step": 376
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036537489683949114,
+      "loss": 0.4515,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003651319883217255,
+      "loss": 0.5096,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036488831206835207,
+      "loss": 0.4231,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036464386921227637,
+      "loss": 0.4903,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036439866088996796,
+      "loss": 0.5131,
+      "step": 381
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003641526882414553,
+      "loss": 0.5986,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003639059524103203,
+      "loss": 0.6,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003636584545436931,
+      "loss": 0.5216,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003634101957922468,
+      "loss": 0.5144,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00036316117731019184,
+      "loss": 0.4963,
+      "step": 386
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003629114002552711,
+      "loss": 0.5657,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036266086578875384,
+      "loss": 0.5028,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003624095750754311,
+      "loss": 0.573,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036215752928360967,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003619047295851068,
+      "loss": 0.656,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036165117715524506,
+      "loss": 0.5129,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036139687317284647,
+      "loss": 0.3945,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003611418188202271,
+      "loss": 0.5318,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036088601528319196,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036062946375102885,
+      "loss": 0.5407,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003603721654165034,
+      "loss": 0.5364,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00036011412147585306,
+      "loss": 0.5407,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003598553331287821,
+      "loss": 0.5999,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003595958015784555,
+      "loss": 0.624,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00035933552803149354,
+      "loss": 0.5351,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003590745136979662,
+      "loss": 0.5196,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035881275979138765,
+      "loss": 0.5447,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003585502675287104,
+      "loss": 0.4908,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035828703813031986,
+      "loss": 0.5172,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035802307282002834,
+      "loss": 0.5923,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003577583728250699,
+      "loss": 0.568,
+      "step": 407
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035749293937609395,
+      "loss": 0.4618,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003572267737071601,
+      "loss": 0.5351,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003569598770557322,
+      "loss": 0.5285,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035669225066267256,
+      "loss": 0.4571,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035642389577223625,
+      "loss": 0.4214,
+      "step": 412
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003561548136320653,
+      "loss": 0.5393,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003558850054931828,
+      "loss": 0.549,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035561447260998714,
+      "loss": 0.4824,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035534321624024656,
+      "loss": 0.6244,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035507123764509245,
+      "loss": 0.5436,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003547985380890144,
+      "loss": 0.5198,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035452511883985366,
+      "loss": 0.5979,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035425098116879754,
+      "loss": 0.4158,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035397612635037356,
+      "loss": 0.5125,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035370055566244334,
+      "loss": 0.4699,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003534242703861966,
+      "loss": 0.5553,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035314727180614573,
+      "loss": 0.5969,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035286956121011897,
+      "loss": 0.456,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003525911398892552,
+      "loss": 0.5195,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003523120091379975,
+      "loss": 0.5187,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035203217025408726,
+      "loss": 0.5443,
+      "step": 428
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003517516245385582,
+      "loss": 0.4476,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003514703732957301,
+      "loss": 0.5757,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035118841783320304,
+      "loss": 0.5129,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035090575946185114,
+      "loss": 0.6354,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035062239949581645,
+      "loss": 0.4065,
+      "step": 433
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000350338339252503,
+      "loss": 0.5472,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00035005358005257045,
+      "loss": 0.5424,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034976812321992816,
+      "loss": 0.6127,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034948197008172877,
+      "loss": 0.63,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003491951219683625,
+      "loss": 0.413,
+      "step": 438
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034890758021345034,
+      "loss": 0.5435,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034861934615383844,
+      "loss": 0.5433,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034833042112959153,
+      "loss": 0.4763,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034804080648398667,
+      "loss": 0.5727,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034775050356350727,
+      "loss": 0.5392,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034745951371783666,
+      "loss": 0.4981,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003471678382998518,
+      "loss": 0.5516,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00034687547866561703,
+      "loss": 0.4965,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003465824361743779,
+      "loss": 0.4982,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003462887121885544,
+      "loss": 0.5619,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003459943080737353,
+      "loss": 0.5273,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034569922519867133,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034540346493526876,
+      "loss": 0.4874,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003451070286585833,
+      "loss": 0.5966,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003448099177468137,
+      "loss": 0.4487,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003445121335812951,
+      "loss": 0.5091,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003442136775464929,
+      "loss": 0.407,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003439145510299958,
+      "loss": 0.6327,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00034361475542251025,
+      "loss": 0.4217,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003433142921178531,
+      "loss": 0.6102,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003430131625129456,
+      "loss": 0.5556,
+      "step": 459
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034271136800780673,
+      "loss": 0.4986,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003424089100055467,
+      "loss": 0.5406,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034210578991236056,
+      "loss": 0.5881,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034180200913752157,
+      "loss": 0.4869,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034149756909337454,
+      "loss": 0.5626,
+      "step": 464
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003411924711953295,
+      "loss": 0.564,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00034088671686185486,
+      "loss": 0.6272,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003405803075144711,
+      "loss": 0.4643,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003402732445777438,
+      "loss": 0.5435,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00033996552947927744,
+      "loss": 0.5844,
+      "step": 469
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003396571636497084,
+      "loss": 0.5362,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033934814852269865,
+      "loss": 0.5607,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003390384855349285,
+      "loss": 0.4836,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033872817612609065,
+      "loss": 0.6555,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033841722173888315,
+      "loss": 0.4784,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033810562381900253,
+      "loss": 0.5583,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033779338381513736,
+      "loss": 0.4679,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003374805031789613,
+      "loss": 0.5325,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033716698336512654,
+      "loss": 0.6601,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000336852825831257,
+      "loss": 0.4838,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003365380320379414,
+      "loss": 0.5588,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033622260344872665,
+      "loss": 0.4596,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003359065415301108,
+      "loss": 0.5228,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033558984775153663,
+      "loss": 0.5316,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033527252358538437,
+      "loss": 0.4761,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003349545705069653,
+      "loss": 0.5254,
+      "step": 485
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003346359899945144,
+      "loss": 0.4786,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033431678352918384,
+      "loss": 0.4302,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003339969525950361,
+      "loss": 0.4914,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033367649867903663,
+      "loss": 0.4102,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003333554232710477,
+      "loss": 0.4698,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003330337278638207,
+      "loss": 0.4454,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033271141395298964,
+      "loss": 0.4648,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033238848303706415,
+      "loss": 0.4616,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033206493661742237,
+      "loss": 0.4861,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033174077619830416,
+      "loss": 0.4797,
+      "step": 495
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033141600328680373,
+      "loss": 0.5104,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033109061939286336,
+      "loss": 0.5712,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033076462602926553,
+      "loss": 0.5425,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033043802471162636,
+      "loss": 0.6156,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003301108169583887,
+      "loss": 0.4282,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003297830042908146,
+      "loss": 0.4088,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032945458823297857,
+      "loss": 0.4866,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003291255703117605,
+      "loss": 0.5045,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003287959520568384,
+      "loss": 0.491,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032846573500068136,
+      "loss": 0.458,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032813492067854246,
+      "loss": 0.4508,
+      "step": 506
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003278035106284516,
+      "loss": 0.4294,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032747150639120834,
+      "loss": 0.4834,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032713890951037477,
+      "loss": 0.3857,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032680572153226834,
+      "loss": 0.4072,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003264719440059545,
+      "loss": 0.4028,
+      "step": 511
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032613757848323977,
+      "loss": 0.3789,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032580262651866446,
+      "loss": 0.4944,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003254670896694952,
+      "loss": 0.4259,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032513096949571805,
+      "loss": 0.5037,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032479426756003093,
+      "loss": 0.5857,
+      "step": 516
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003244569854278366,
+      "loss": 0.5407,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032411912466723524,
+      "loss": 0.499,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003237806868490172,
+      "loss": 0.4359,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032344167354665573,
+      "loss": 0.4374,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003231020863362997,
+      "loss": 0.4172,
+      "step": 521
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000322761926796766,
+      "loss": 0.4451,
+      "step": 522
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003224211965095326,
+      "loss": 0.4,
+      "step": 523
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003220798970587309,
+      "loss": 0.4009,
+      "step": 524
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003217380300311386,
+      "loss": 0.3966,
+      "step": 525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000321395597016172,
+      "loss": 0.4255,
+      "step": 526
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00032105259960587895,
+      "loss": 0.4707,
+      "step": 527
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00032070903939493124,
+      "loss": 0.5313,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003203649179806172,
+      "loss": 0.3596,
+      "step": 529
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003200202369628345,
+      "loss": 0.5223,
+      "step": 530
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031967499794408234,
+      "loss": 0.4146,
+      "step": 531
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031932920252945423,
+      "loss": 0.4328,
+      "step": 532
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003189828523266306,
+      "loss": 0.4258,
+      "step": 533
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031863594894587105,
+      "loss": 0.4457,
+      "step": 534
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003182884940000072,
+      "loss": 0.5249,
+      "step": 535
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003179404891044348,
+      "loss": 0.4751,
+      "step": 536
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031759193587710676,
+      "loss": 0.5378,
+      "step": 537
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031724283593852497,
+      "loss": 0.634,
+      "step": 538
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031689319091173326,
+      "loss": 0.4298,
+      "step": 539
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031654300242230977,
+      "loss": 0.5469,
+      "step": 540
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031619227209835917,
+      "loss": 0.5153,
+      "step": 541
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003158410015705053,
+      "loss": 0.4144,
+      "step": 542
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003154891924718837,
+      "loss": 0.6041,
+      "step": 543
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003151368464381335,
+      "loss": 0.4891,
+      "step": 544
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003147839651073904,
+      "loss": 0.5258,
+      "step": 545
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00031443055012027874,
+      "loss": 0.4351,
+      "step": 546
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000314076603119904,
+      "loss": 0.4556,
+      "step": 547
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031372212575184514,
+      "loss": 0.5445,
+      "step": 548
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031336711966414675,
+      "loss": 0.5585,
+      "step": 549
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003130115865073117,
+      "loss": 0.367,
+      "step": 550
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003126555279342933,
+      "loss": 0.4877,
+      "step": 551
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003122989456004876,
+      "loss": 0.4335,
+      "step": 552
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003119418411637258,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003115842162842663,
+      "loss": 0.4508,
+      "step": 554
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00031122607262478743,
+      "loss": 0.4631,
+      "step": 555
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003108674118503793,
+      "loss": 0.3496,
+      "step": 556
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003105082356285361,
+      "loss": 0.4108,
+      "step": 557
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003101485456291486,
+      "loss": 0.4877,
+      "step": 558
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030978834352449614,
+      "loss": 0.3696,
+      "step": 559
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030942763098923913,
+      "loss": 0.5138,
+      "step": 560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030906640970041084,
+      "loss": 0.5961,
+      "step": 561
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003087046813374099,
+      "loss": 0.3824,
+      "step": 562
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030834244758199276,
+      "loss": 0.4925,
+      "step": 563
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000307979710118265,
+      "loss": 0.4511,
+      "step": 564
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030761647063267457,
+      "loss": 0.4306,
+      "step": 565
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003072527308140031,
+      "loss": 0.468,
+      "step": 566
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030688849235335856,
+      "loss": 0.4842,
+      "step": 567
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003065237569441671,
+      "loss": 0.4332,
+      "step": 568
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030615852628216537,
+      "loss": 0.4637,
+      "step": 569
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003057928020653925,
+      "loss": 0.6193,
+      "step": 570
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003054265859941824,
+      "loss": 0.5033,
+      "step": 571
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030505987977115555,
+      "loss": 0.4185,
+      "step": 572
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003046926851012114,
+      "loss": 0.4211,
+      "step": 573
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003043250036915201,
+      "loss": 0.5089,
+      "step": 574
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00030395683725151505,
+      "loss": 0.517,
+      "step": 575
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003035881874928845,
+      "loss": 0.492,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003032190561295636,
+      "loss": 0.4535,
+      "step": 577
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003028494448777269,
+      "loss": 0.3947,
+      "step": 578
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030247935545577986,
+      "loss": 0.3125,
+      "step": 579
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003021087895843511,
+      "loss": 0.3882,
+      "step": 580
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003017377489862845,
+      "loss": 0.4802,
+      "step": 581
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030136623538663083,
+      "loss": 0.4652,
+      "step": 582
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030099425051263994,
+      "loss": 0.3816,
+      "step": 583
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003006217960937529,
+      "loss": 0.4583,
+      "step": 584
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00030024887386159385,
+      "loss": 0.4568,
+      "step": 585
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029987548554996174,
+      "loss": 0.3908,
+      "step": 586
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002995016328948225,
+      "loss": 0.4235,
+      "step": 587
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029912731763430075,
+      "loss": 0.4138,
+      "step": 588
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029875254150867216,
+      "loss": 0.5838,
+      "step": 589
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002983773062603548,
+      "loss": 0.462,
+      "step": 590
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029800161363390145,
+      "loss": 0.4632,
+      "step": 591
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029762546537599125,
+      "loss": 0.5898,
+      "step": 592
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002972488632354218,
+      "loss": 0.4742,
+      "step": 593
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029687180896310065,
+      "loss": 0.4579,
+      "step": 594
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002964943043120378,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029611635103733675,
+      "loss": 0.4304,
+      "step": 596
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002957379508961871,
+      "loss": 0.4383,
+      "step": 597
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029535910564785584,
+      "loss": 0.5327,
+      "step": 598
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029497981705367933,
+      "loss": 0.4781,
+      "step": 599
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029460008687705525,
+      "loss": 0.4178,
+      "step": 600
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1557,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 8.028786781032284e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbdf20491848d40e9a89bca19c6229b4b2b55e5d
--- /dev/null
+++ b/checkpoint-600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07819caee47f45203545f962678d52b5954ff1fd4afe1d5152fad48004402099
+size 4155
diff --git a/checkpoint-650/README.md b/checkpoint-650/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b32efe7366f05d1d90816d2ad9e4b06ccca46bea
--- /dev/null
+++ b/checkpoint-650/README.md
@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-650/adapter_config.json b/checkpoint-650/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e108f2da037ef6250457c67a4bedd308d97303c
--- /dev/null
+++ b/checkpoint-650/adapter_config.json
@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-650/adapter_model.bin b/checkpoint-650/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8f8773f20e472b1a46a60e0be925fbbb40c5e878
--- /dev/null
+++ b/checkpoint-650/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4d4a963234d5b145db85e44f623296620990066a8818059db46bfb6fdae142
+size 113314765
diff --git a/checkpoint-650/optimizer.pt b/checkpoint-650/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7a11a97b2ead753daf7f1a52bc6f49d8da251144
--- /dev/null
+++ b/checkpoint-650/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319fe643298cda15dc43201f86c588932cbb2e8ba93d626062a50a30db8ec3f8
+size 226653957
diff --git a/checkpoint-650/rng_state.pth b/checkpoint-650/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0e0b6d57634584c89d5063aad9e41133446d7286
--- /dev/null
+++ b/checkpoint-650/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bcc6c883b3a4f7fb228632aa870378c86b9dd9a19866e7d6f881e4815d9a9b1
+size 14575
diff --git a/checkpoint-650/scheduler.pt b/checkpoint-650/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2778d642a4ba0b823d14b608547f22e597c683f3
--- /dev/null
+++ b/checkpoint-650/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6161499fb6777bbd8c4173364b8988e53a62d1e88cad4a1841153cca0b12c9b6
+size 627
diff --git a/checkpoint-650/trainer_state.json b/checkpoint-650/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..47453fa63c302f0a585790aa69958c381fb05e9e
--- /dev/null
+++ b/checkpoint-650/trainer_state.json
@@ -0,0 +1,3919 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2522565892405826,
+  "eval_steps": 500,
+  "global_step": 650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6869,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8396,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7489,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7252,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8022,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.6524,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6981,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7488,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6891,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7968,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6912,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8452,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 0.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6685,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5469,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7915,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.6e-05,
+      "loss": 0.7744,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.6804,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.4e-05,
+      "loss": 0.7796,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.706,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6798,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6333,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 0.6012,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.52,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6583,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.7354,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000116,
+      "loss": 0.6296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 0.6352,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000124,
+      "loss": 0.6007,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5659,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000132,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6639,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 0.5934,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000144,
+      "loss": 0.5233,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000148,
+      "loss": 0.5307,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000152,
+      "loss": 0.5928,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5908,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000164,
+      "loss": 0.5972,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000168,
+      "loss": 0.4825,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000172,
+      "loss": 0.6783,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 0.7633,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5988,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000188,
+      "loss": 0.6658,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000192,
+      "loss": 0.5945,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000196,
+      "loss": 0.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.6057,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.601,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.5566,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.5911,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.7636,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.5537,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000232,
+      "loss": 0.6474,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000236,
+      "loss": 0.6483,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00024,
+      "loss": 0.5021,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000244,
+      "loss": 0.5347,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000248,
+      "loss": 0.5791,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000252,
+      "loss": 0.5407,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.5298,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5685,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000264,
+      "loss": 0.5108,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000268,
+      "loss": 0.526,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6843,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000276,
+      "loss": 0.6608,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00028,
+      "loss": 0.5866,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000284,
+      "loss": 0.6422,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000288,
+      "loss": 0.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000292,
+      "loss": 0.5319,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000296,
+      "loss": 0.5977,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.5805,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000304,
+      "loss": 0.5209,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000308,
+      "loss": 0.6098,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.4665,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6882,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00032,
+      "loss": 0.5427,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000324,
+      "loss": 0.5345,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000328,
+      "loss": 0.663,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000332,
+      "loss": 0.5393,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000336,
+      "loss": 0.5711,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00034,
+      "loss": 0.5261,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000344,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000348,
+      "loss": 0.6329,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.4425,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6837,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00036,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000364,
+      "loss": 0.5615,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5434,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000376,
+      "loss": 0.5583,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00038,
+      "loss": 0.5299,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000384,
+      "loss": 0.532,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000388,
+      "loss": 0.5227,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000392,
+      "loss": 0.5275,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.4541,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004,
+      "loss": 0.6485,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003999995350775973,
+      "loss": 0.5438,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999814031255063,
+      "loss": 0.5997,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999581571134455,
+      "loss": 0.5322,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003999925612847867,
+      "loss": 0.484,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998837704800766,
+      "loss": 0.5961,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998326302046085,
+      "loss": 0.7405,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997721922592255,
+      "loss": 0.5802,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997024569249167,
+      "loss": 0.769,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999623424525898,
+      "loss": 0.5598,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999535095429608,
+      "loss": 0.6143,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039994374700467095,
+      "loss": 0.5766,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039993305488310836,
+      "loss": 0.7695,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999214332279831,
+      "loss": 0.7153,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999088820933269,
+      "loss": 0.5835,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039989540153749286,
+      "loss": 0.6634,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000399880991623155,
+      "loss": 0.6069,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998656524173082,
+      "loss": 0.7224,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000399849383991268,
+      "loss": 0.5884,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998321864206699,
+      "loss": 0.5122,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039981405978546924,
+      "loss": 0.6453,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997950041699408,
+      "loss": 0.4665,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997750196626785,
+      "loss": 0.5428,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039975410635659464,
+      "loss": 0.4365,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039973226434891995,
+      "loss": 0.5978,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039970949374120286,
+      "loss": 0.7729,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000399685794639309,
+      "loss": 0.6212,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039966116715342066,
+      "loss": 0.5426,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00039963561139803676,
+      "loss": 0.5782,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003996091274919716,
+      "loss": 0.6701,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995817155583548,
+      "loss": 0.6314,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995533757246307,
+      "loss": 0.6662,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995241081225573,
+      "loss": 0.5192,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994939128882065,
+      "loss": 0.5591,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994627901619625,
+      "loss": 0.5809,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994307400885219,
+      "loss": 0.4871,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993977628168928,
+      "loss": 0.6666,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993638585003938,
+      "loss": 0.6469,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039932902729665357,
+      "loss": 0.5727,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039929326936761036,
+      "loss": 0.6715,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039925658487951067,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039921897400290894,
+      "loss": 0.501,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039918043691266665,
+      "loss": 0.5795,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039914097378795124,
+      "loss": 0.6287,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039910058481223564,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039905927017329726,
+      "loss": 0.6232,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039901703006321715,
+      "loss": 0.5291,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039897386467837903,
+      "loss": 0.5297,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039892977421946844,
+      "loss": 0.5784,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988847588914718,
+      "loss": 0.5714,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988388189036754,
+      "loss": 0.5044,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987919544696646,
+      "loss": 0.8246,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987441658073226,
+      "loss": 0.5048,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003986954531388297,
+      "loss": 0.5433,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039864581669066186,
+      "loss": 0.5251,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003985952566935902,
+      "loss": 0.5708,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039854377338267936,
+      "loss": 0.6276,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039849136699728684,
+      "loss": 0.4915,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003984380377810617,
+      "loss": 0.6389,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039838378598194325,
+      "loss": 0.6067,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039832861185216045,
+      "loss": 0.6136,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003982725156482301,
+      "loss": 0.5597,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000398215497630956,
+      "loss": 0.5957,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003981575580654278,
+      "loss": 0.5853,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980986972210194,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980389153713881,
+      "loss": 0.5302,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039797821279447307,
+      "loss": 0.5395,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039791658977249425,
+      "loss": 0.7004,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039785404659195084,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039779058354362013,
+      "loss": 0.5759,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000397726200922556,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003976608990280877,
+      "loss": 0.5488,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975946781638183,
+      "loss": 0.6162,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975275386376236,
+      "loss": 0.558,
+      "step": 173
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003974594807616502,
+      "loss": 0.519,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003973905048523144,
+      "loss": 0.6195,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039732061123030064,
+      "loss": 0.5991,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003972498002205601,
+      "loss": 0.5428,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039717807215230896,
+      "loss": 0.5323,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039710542735902705,
+      "loss": 0.5307,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003970318661784564,
+      "loss": 0.5783,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003969573889525993,
+      "loss": 0.5924,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039688199602771714,
+      "loss": 0.5902,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039680568775432855,
+      "loss": 0.6291,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003967284644872077,
+      "loss": 0.5942,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003966503265853829,
+      "loss": 0.4878,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003965712744121347,
+      "loss": 0.6487,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003964913083349945,
+      "loss": 0.6111,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039641042872574233,
+      "loss": 0.6072,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039632863596040575,
+      "loss": 0.716,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039624593041925763,
+      "loss": 0.6178,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003961623124868145,
+      "loss": 0.6323,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039607778255183485,
+      "loss": 0.5821,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959923410073174,
+      "loss": 0.6738,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959059882504989,
+      "loss": 0.6203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039581872468285277,
+      "loss": 0.632,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003957305507100868,
+      "loss": 0.5857,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039564146674214164,
+      "loss": 0.6311,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003955514731931885,
+      "loss": 0.5889,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039546057048162763,
+      "loss": 0.5201,
+      "step": 199
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039536875903008607,
+      "loss": 0.5581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039527603926541586,
+      "loss": 0.5104,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039518241161869193,
+      "loss": 0.5978,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039508787652521013,
+      "loss": 0.6244,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039499243442448536,
+      "loss": 0.589,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003948960857602493,
+      "loss": 0.575,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947988309804485,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947006705372422,
+      "loss": 0.4895,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039460160488700036,
+      "loss": 0.5479,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039450163449030124,
+      "loss": 0.5893,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003944007598119297,
+      "loss": 0.5451,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003942989813208747,
+      "loss": 0.5582,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003941962994903273,
+      "loss": 0.5121,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039409271479767826,
+      "loss": 0.6324,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000393988227724516,
+      "loss": 0.6118,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003938828387566244,
+      "loss": 0.6303,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003937765483839804,
+      "loss": 0.7705,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003936693571007517,
+      "loss": 0.6224,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935612654052946,
+      "loss": 0.5664,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039345227380015163,
+      "loss": 0.66,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039334238279204906,
+      "loss": 0.5582,
+      "step": 220
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039323159289189505,
+      "loss": 0.6087,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003931199046147764,
+      "loss": 0.5566,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039300731847995716,
+      "loss": 0.5775,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039289383501087534,
+      "loss": 0.5081,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277945473514104,
+      "loss": 0.5218,
+      "step": 225
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003926641781845338,
+      "loss": 0.6655,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003925480058950002,
+      "loss": 0.5735,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039243093840665114,
+      "loss": 0.6609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003923129762637596,
+      "loss": 0.7323,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000392194120014758,
+      "loss": 0.5703,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039207437021223583,
+      "loss": 0.6545,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003919537274129366,
+      "loss": 0.521,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039183219217775564,
+      "loss": 0.5257,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003917097650717377,
+      "loss": 0.5487,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039158644666407365,
+      "loss": 0.4861,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039146223752809845,
+      "loss": 0.4928,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003913371382412883,
+      "loss": 0.5253,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039121114938525756,
+      "loss": 0.6155,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039108427154575684,
+      "loss": 0.55,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039095650531266967,
+      "loss": 0.6617,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039082785128000976,
+      "loss": 0.5198,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039069831004591866,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003905678822126625,
+      "loss": 0.5347,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039043656838662946,
+      "loss": 0.531,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039030436917832697,
+      "loss": 0.4884,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039017128520237883,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003900373170775222,
+      "loss": 0.5537,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038990246542660494,
+      "loss": 0.5753,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038976673087658256,
+      "loss": 0.5059,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038963011405851537,
+      "loss": 0.5118,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038949261560756565,
+      "loss": 0.5645,
+      "step": 251
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003893542361629944,
+      "loss": 0.5623,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038921497636815866,
+      "loss": 0.5216,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003890748368705085,
+      "loss": 0.4501,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003889338183215838,
+      "loss": 0.48,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038879192137701135,
+      "loss": 0.5218,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003886491466965018,
+      "loss": 0.5858,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038850549494384685,
+      "loss": 0.6124,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038836096678691536,
+      "loss": 0.4645,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038821556289765136,
+      "loss": 0.474,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038806928395207003,
+      "loss": 0.4364,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038792213063025484,
+      "loss": 0.5821,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003877741036163547,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003876252035985804,
+      "loss": 0.5373,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003874754312692013,
+      "loss": 0.6021,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003873247873245426,
+      "loss": 0.4549,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003871732724649817,
+      "loss": 0.5994,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003870208873949453,
+      "loss": 0.4764,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038686763282290556,
+      "loss": 0.4311,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003867135094613774,
+      "loss": 0.5462,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003865585180269148,
+      "loss": 0.5006,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003864026592401076,
+      "loss": 0.5347,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038624593382557835,
+      "loss": 0.5242,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038608834251197856,
+      "loss": 0.5005,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038592988603198554,
+      "loss": 0.5436,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000385770565122299,
+      "loss": 0.4658,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003856103805236375,
+      "loss": 0.5273,
+      "step": 277
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038544933298073516,
+      "loss": 0.436,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038528742324233804,
+      "loss": 0.4785,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038512465206120086,
+      "loss": 0.5366,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038496102019408324,
+      "loss": 0.4448,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038479652840174637,
+      "loss": 0.5132,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038463117744894955,
+      "loss": 0.7918,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038446496810444627,
+      "loss": 0.5309,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038429790114098114,
+      "loss": 0.5316,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038412997733528576,
+      "loss": 0.4611,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038396119746807563,
+      "loss": 0.4609,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038379156232404613,
+      "loss": 0.5821,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003836210726918691,
+      "loss": 0.5883,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003834497293641889,
+      "loss": 0.5012,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038327753313761913,
+      "loss": 0.4457,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038310448481273867,
+      "loss": 0.4851,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038293058519408787,
+      "loss": 0.5622,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038275583509016507,
+      "loss": 0.5703,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038258023531342265,
+      "loss": 0.5718,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003824037866802632,
+      "loss": 0.5183,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038222649001103614,
+      "loss": 0.5085,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038204834613003323,
+      "loss": 0.5388,
+      "step": 298
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038186935586548537,
+      "loss": 0.5425,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003816895200495584,
+      "loss": 0.447,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003815088395183493,
+      "loss": 0.5541,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038132731511188227,
+      "loss": 0.5518,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000381144947674105,
+      "loss": 0.5074,
+      "step": 303
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003809617380528847,
+      "loss": 0.5134,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003807776871000037,
+      "loss": 0.4599,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003805927956711562,
+      "loss": 0.5838,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038040706462594395,
+      "loss": 0.5216,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038022049482787216,
+      "loss": 0.5323,
+      "step": 308
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003800330871443456,
+      "loss": 0.5681,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00037984484244666446,
+      "loss": 0.4172,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003796557616100207,
+      "loss": 0.4958,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003794658455134934,
+      "loss": 0.662,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003792750950400451,
+      "loss": 0.5832,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003790835110765174,
+      "loss": 0.4271,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003788910945136271,
+      "loss": 0.4842,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037869784624596186,
+      "loss": 0.4656,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037850376717197626,
+      "loss": 0.4981,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037830885819398733,
+      "loss": 0.5162,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037811312021817067,
+      "loss": 0.652,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003779165541545558,
+      "loss": 0.5104,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003777191609170225,
+      "loss": 0.4971,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003775209414232962,
+      "loss": 0.4871,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003773218965949436,
+      "loss": 0.5226,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00037712202735736884,
+      "loss": 0.4823,
+      "step": 324
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003769213346398087,
+      "loss": 0.497,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003767198193753286,
+      "loss": 0.5976,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003765174825008181,
+      "loss": 0.4532,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003763143249569868,
+      "loss": 0.5236,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00037611034768835947,
+      "loss": 0.6513,
+      "step": 329
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037590555164327224,
+      "loss": 0.5686,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037569993777386774,
+      "loss": 0.456,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003754935070360909,
+      "loss": 0.5181,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003752862603896846,
+      "loss": 0.4765,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037507819879818477,
+      "loss": 0.5363,
+      "step": 334
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037486932322891646,
+      "loss": 0.4584,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037465963465298886,
+      "loss": 0.5428,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003744491340452913,
+      "loss": 0.3927,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003742378223844882,
+      "loss": 0.5478,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003740257006530147,
+      "loss": 0.469,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037381276983707246,
+      "loss": 0.5169,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037359903092662434,
+      "loss": 0.4797,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037338448491539054,
+      "loss": 0.5315,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037316913280084353,
+      "loss": 0.4422,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003729529755842035,
+      "loss": 0.4426,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003727360142704337,
+      "loss": 0.4718,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003725182498682361,
+      "loss": 0.5585,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003722996833900459,
+      "loss": 0.4775,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003720803158520279,
+      "loss": 0.6014,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00037186014827407076,
+      "loss": 0.5117,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003716391816797829,
+      "loss": 0.5404,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003714174170964876,
+      "loss": 0.527,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037119485555521796,
+      "loss": 0.4555,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037097149809071255,
+      "loss": 0.5372,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037074734574141016,
+      "loss": 0.5377,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003705223995494454,
+      "loss": 0.4925,
+      "step": 355
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037029666056064345,
+      "loss": 0.482,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037007012982451546,
+      "loss": 0.5235,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00036984280839425356,
+      "loss": 0.4957,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000369614697326726,
+      "loss": 0.5379,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003693857976824721,
+      "loss": 0.4653,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036915611052569785,
+      "loss": 0.469,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003689256369242702,
+      "loss": 0.5618,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003686943779497124,
+      "loss": 0.4459,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003684623346771995,
+      "loss": 0.5606,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003682295081855524,
+      "loss": 0.4368,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036799589955723375,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036776150987834243,
+      "loss": 0.4664,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036752634023860846,
+      "loss": 0.4737,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003672903917313883,
+      "loss": 0.4247,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036705366545365935,
+      "loss": 0.5677,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036681616250601505,
+      "loss": 0.5441,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003665778839926599,
+      "loss": 0.6247,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00036633883102140405,
+      "loss": 0.5217,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003660990047036584,
+      "loss": 0.4651,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003658584061544291,
+      "loss": 0.4648,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003656170364923128,
+      "loss": 0.6048,
+      "step": 376
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036537489683949114,
+      "loss": 0.4515,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003651319883217255,
+      "loss": 0.5096,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036488831206835207,
+      "loss": 0.4231,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036464386921227637,
+      "loss": 0.4903,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036439866088996796,
+      "loss": 0.5131,
+      "step": 381
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003641526882414553,
+      "loss": 0.5986,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003639059524103203,
+      "loss": 0.6,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003636584545436931,
+      "loss": 0.5216,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003634101957922468,
+      "loss": 0.5144,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00036316117731019184,
+      "loss": 0.4963,
+      "step": 386
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003629114002552711,
+      "loss": 0.5657,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036266086578875384,
+      "loss": 0.5028,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003624095750754311,
+      "loss": 0.573,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036215752928360967,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003619047295851068,
+      "loss": 0.656,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036165117715524506,
+      "loss": 0.5129,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036139687317284647,
+      "loss": 0.3945,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003611418188202271,
+      "loss": 0.5318,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036088601528319196,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036062946375102885,
+      "loss": 0.5407,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003603721654165034,
+      "loss": 0.5364,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00036011412147585306,
+      "loss": 0.5407,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003598553331287821,
+      "loss": 0.5999,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003595958015784555,
+      "loss": 0.624,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00035933552803149354,
+      "loss": 0.5351,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003590745136979662,
+      "loss": 0.5196,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035881275979138765,
+      "loss": 0.5447,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003585502675287104,
+      "loss": 0.4908,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035828703813031986,
+      "loss": 0.5172,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035802307282002834,
+      "loss": 0.5923,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003577583728250699,
+      "loss": 0.568,
+      "step": 407
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035749293937609395,
+      "loss": 0.4618,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003572267737071601,
+      "loss": 0.5351,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003569598770557322,
+      "loss": 0.5285,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035669225066267256,
+      "loss": 0.4571,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035642389577223625,
+      "loss": 0.4214,
+      "step": 412
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003561548136320653,
+      "loss": 0.5393,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003558850054931828,
+      "loss": 0.549,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035561447260998714,
+      "loss": 0.4824,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035534321624024656,
+      "loss": 0.6244,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035507123764509245,
+      "loss": 0.5436,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003547985380890144,
+      "loss": 0.5198,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035452511883985366,
+      "loss": 0.5979,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035425098116879754,
+      "loss": 0.4158,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035397612635037356,
+      "loss": 0.5125,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035370055566244334,
+      "loss": 0.4699,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003534242703861966,
+      "loss": 0.5553,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035314727180614573,
+      "loss": 0.5969,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035286956121011897,
+      "loss": 0.456,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003525911398892552,
+      "loss": 0.5195,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003523120091379975,
+      "loss": 0.5187,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035203217025408726,
+      "loss": 0.5443,
+      "step": 428
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003517516245385582,
+      "loss": 0.4476,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003514703732957301,
+      "loss": 0.5757,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035118841783320304,
+      "loss": 0.5129,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035090575946185114,
+      "loss": 0.6354,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035062239949581645,
+      "loss": 0.4065,
+      "step": 433
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000350338339252503,
+      "loss": 0.5472,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00035005358005257045,
+      "loss": 0.5424,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034976812321992816,
+      "loss": 0.6127,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034948197008172877,
+      "loss": 0.63,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003491951219683625,
+      "loss": 0.413,
+      "step": 438
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034890758021345034,
+      "loss": 0.5435,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034861934615383844,
+      "loss": 0.5433,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034833042112959153,
+      "loss": 0.4763,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034804080648398667,
+      "loss": 0.5727,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034775050356350727,
+      "loss": 0.5392,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034745951371783666,
+      "loss": 0.4981,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003471678382998518,
+      "loss": 0.5516,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00034687547866561703,
+      "loss": 0.4965,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003465824361743779,
+      "loss": 0.4982,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003462887121885544,
+      "loss": 0.5619,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003459943080737353,
+      "loss": 0.5273,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034569922519867133,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034540346493526876,
+      "loss": 0.4874,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003451070286585833,
+      "loss": 0.5966,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003448099177468137,
+      "loss": 0.4487,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003445121335812951,
+      "loss": 0.5091,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003442136775464929,
+      "loss": 0.407,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003439145510299958,
+      "loss": 0.6327,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00034361475542251025,
+      "loss": 0.4217,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003433142921178531,
+      "loss": 0.6102,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003430131625129456,
+      "loss": 0.5556,
+      "step": 459
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034271136800780673,
+      "loss": 0.4986,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003424089100055467,
+      "loss": 0.5406,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034210578991236056,
+      "loss": 0.5881,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034180200913752157,
+      "loss": 0.4869,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034149756909337454,
+      "loss": 0.5626,
+      "step": 464
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003411924711953295,
+      "loss": 0.564,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00034088671686185486,
+      "loss": 0.6272,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003405803075144711,
+      "loss": 0.4643,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003402732445777438,
+      "loss": 0.5435,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00033996552947927744,
+      "loss": 0.5844,
+      "step": 469
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003396571636497084,
+      "loss": 0.5362,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033934814852269865,
+      "loss": 0.5607,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003390384855349285,
+      "loss": 0.4836,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033872817612609065,
+      "loss": 0.6555,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033841722173888315,
+      "loss": 0.4784,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033810562381900253,
+      "loss": 0.5583,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033779338381513736,
+      "loss": 0.4679,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003374805031789613,
+      "loss": 0.5325,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033716698336512654,
+      "loss": 0.6601,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000336852825831257,
+      "loss": 0.4838,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003365380320379414,
+      "loss": 0.5588,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033622260344872665,
+      "loss": 0.4596,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003359065415301108,
+      "loss": 0.5228,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033558984775153663,
+      "loss": 0.5316,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033527252358538437,
+      "loss": 0.4761,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003349545705069653,
+      "loss": 0.5254,
+      "step": 485
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003346359899945144,
+      "loss": 0.4786,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033431678352918384,
+      "loss": 0.4302,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003339969525950361,
+      "loss": 0.4914,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033367649867903663,
+      "loss": 0.4102,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003333554232710477,
+      "loss": 0.4698,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003330337278638207,
+      "loss": 0.4454,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033271141395298964,
+      "loss": 0.4648,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033238848303706415,
+      "loss": 0.4616,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033206493661742237,
+      "loss": 0.4861,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033174077619830416,
+      "loss": 0.4797,
+      "step": 495
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033141600328680373,
+      "loss": 0.5104,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033109061939286336,
+      "loss": 0.5712,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033076462602926553,
+      "loss": 0.5425,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033043802471162636,
+      "loss": 0.6156,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003301108169583887,
+      "loss": 0.4282,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003297830042908146,
+      "loss": 0.4088,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032945458823297857,
+      "loss": 0.4866,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003291255703117605,
+      "loss": 0.5045,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003287959520568384,
+      "loss": 0.491,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032846573500068136,
+      "loss": 0.458,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032813492067854246,
+      "loss": 0.4508,
+      "step": 506
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003278035106284516,
+      "loss": 0.4294,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032747150639120834,
+      "loss": 0.4834,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032713890951037477,
+      "loss": 0.3857,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032680572153226834,
+      "loss": 0.4072,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003264719440059545,
+      "loss": 0.4028,
+      "step": 511
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032613757848323977,
+      "loss": 0.3789,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032580262651866446,
+      "loss": 0.4944,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003254670896694952,
+      "loss": 0.4259,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032513096949571805,
+      "loss": 0.5037,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032479426756003093,
+      "loss": 0.5857,
+      "step": 516
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003244569854278366,
+      "loss": 0.5407,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032411912466723524,
+      "loss": 0.499,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003237806868490172,
+      "loss": 0.4359,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032344167354665573,
+      "loss": 0.4374,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003231020863362997,
+      "loss": 0.4172,
+      "step": 521
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000322761926796766,
+      "loss": 0.4451,
+      "step": 522
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003224211965095326,
+      "loss": 0.4,
+      "step": 523
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003220798970587309,
+      "loss": 0.4009,
+      "step": 524
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003217380300311386,
+      "loss": 0.3966,
+      "step": 525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000321395597016172,
+      "loss": 0.4255,
+      "step": 526
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00032105259960587895,
+      "loss": 0.4707,
+      "step": 527
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00032070903939493124,
+      "loss": 0.5313,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003203649179806172,
+      "loss": 0.3596,
+      "step": 529
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003200202369628345,
+      "loss": 0.5223,
+      "step": 530
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031967499794408234,
+      "loss": 0.4146,
+      "step": 531
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031932920252945423,
+      "loss": 0.4328,
+      "step": 532
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003189828523266306,
+      "loss": 0.4258,
+      "step": 533
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031863594894587105,
+      "loss": 0.4457,
+      "step": 534
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003182884940000072,
+      "loss": 0.5249,
+      "step": 535
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003179404891044348,
+      "loss": 0.4751,
+      "step": 536
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031759193587710676,
+      "loss": 0.5378,
+      "step": 537
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031724283593852497,
+      "loss": 0.634,
+      "step": 538
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031689319091173326,
+      "loss": 0.4298,
+      "step": 539
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031654300242230977,
+      "loss": 0.5469,
+      "step": 540
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031619227209835917,
+      "loss": 0.5153,
+      "step": 541
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003158410015705053,
+      "loss": 0.4144,
+      "step": 542
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003154891924718837,
+      "loss": 0.6041,
+      "step": 543
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003151368464381335,
+      "loss": 0.4891,
+      "step": 544
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003147839651073904,
+      "loss": 0.5258,
+      "step": 545
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00031443055012027874,
+      "loss": 0.4351,
+      "step": 546
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000314076603119904,
+      "loss": 0.4556,
+      "step": 547
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031372212575184514,
+      "loss": 0.5445,
+      "step": 548
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031336711966414675,
+      "loss": 0.5585,
+      "step": 549
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003130115865073117,
+      "loss": 0.367,
+      "step": 550
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003126555279342933,
+      "loss": 0.4877,
+      "step": 551
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003122989456004876,
+      "loss": 0.4335,
+      "step": 552
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003119418411637258,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003115842162842663,
+      "loss": 0.4508,
+      "step": 554
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00031122607262478743,
+      "loss": 0.4631,
+      "step": 555
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003108674118503793,
+      "loss": 0.3496,
+      "step": 556
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003105082356285361,
+      "loss": 0.4108,
+      "step": 557
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003101485456291486,
+      "loss": 0.4877,
+      "step": 558
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030978834352449614,
+      "loss": 0.3696,
+      "step": 559
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030942763098923913,
+      "loss": 0.5138,
+      "step": 560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030906640970041084,
+      "loss": 0.5961,
+      "step": 561
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003087046813374099,
+      "loss": 0.3824,
+      "step": 562
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030834244758199276,
+      "loss": 0.4925,
+      "step": 563
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000307979710118265,
+      "loss": 0.4511,
+      "step": 564
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030761647063267457,
+      "loss": 0.4306,
+      "step": 565
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003072527308140031,
+      "loss": 0.468,
+      "step": 566
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030688849235335856,
+      "loss": 0.4842,
+      "step": 567
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003065237569441671,
+      "loss": 0.4332,
+      "step": 568
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030615852628216537,
+      "loss": 0.4637,
+      "step": 569
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003057928020653925,
+      "loss": 0.6193,
+      "step": 570
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003054265859941824,
+      "loss": 0.5033,
+      "step": 571
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030505987977115555,
+      "loss": 0.4185,
+      "step": 572
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003046926851012114,
+      "loss": 0.4211,
+      "step": 573
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003043250036915201,
+      "loss": 0.5089,
+      "step": 574
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00030395683725151505,
+      "loss": 0.517,
+      "step": 575
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003035881874928845,
+      "loss": 0.492,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003032190561295636,
+      "loss": 0.4535,
+      "step": 577
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003028494448777269,
+      "loss": 0.3947,
+      "step": 578
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030247935545577986,
+      "loss": 0.3125,
+      "step": 579
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003021087895843511,
+      "loss": 0.3882,
+      "step": 580
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003017377489862845,
+      "loss": 0.4802,
+      "step": 581
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030136623538663083,
+      "loss": 0.4652,
+      "step": 582
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030099425051263994,
+      "loss": 0.3816,
+      "step": 583
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003006217960937529,
+      "loss": 0.4583,
+      "step": 584
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00030024887386159385,
+      "loss": 0.4568,
+      "step": 585
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029987548554996174,
+      "loss": 0.3908,
+      "step": 586
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002995016328948225,
+      "loss": 0.4235,
+      "step": 587
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029912731763430075,
+      "loss": 0.4138,
+      "step": 588
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029875254150867216,
+      "loss": 0.5838,
+      "step": 589
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002983773062603548,
+      "loss": 0.462,
+      "step": 590
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029800161363390145,
+      "loss": 0.4632,
+      "step": 591
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029762546537599125,
+      "loss": 0.5898,
+      "step": 592
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002972488632354218,
+      "loss": 0.4742,
+      "step": 593
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029687180896310065,
+      "loss": 0.4579,
+      "step": 594
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002964943043120378,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029611635103733675,
+      "loss": 0.4304,
+      "step": 596
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002957379508961871,
+      "loss": 0.4383,
+      "step": 597
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029535910564785584,
+      "loss": 0.5327,
+      "step": 598
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029497981705367933,
+      "loss": 0.4781,
+      "step": 599
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029460008687705525,
+      "loss": 0.4178,
+      "step": 600
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002942199168834342,
+      "loss": 0.3987,
+      "step": 601
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029383930884031183,
+      "loss": 0.3861,
+      "step": 602
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029345826451722005,
+      "loss": 0.5322,
+      "step": 603
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029307678568571936,
+      "loss": 0.3997,
+      "step": 604
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002926948741193903,
+      "loss": 0.4121,
+      "step": 605
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029231253159382514,
+      "loss": 0.4931,
+      "step": 606
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029192975988662017,
+      "loss": 0.4626,
+      "step": 607
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029154656077736666,
+      "loss": 0.4441,
+      "step": 608
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002911629360476432,
+      "loss": 0.3863,
+      "step": 609
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029077888748100703,
+      "loss": 0.36,
+      "step": 610
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029039441686298594,
+      "loss": 0.4246,
+      "step": 611
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002900095259810702,
+      "loss": 0.4916,
+      "step": 612
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028962421662470346,
+      "loss": 0.4896,
+      "step": 613
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028923849058527535,
+      "loss": 0.4237,
+      "step": 614
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028885234965611274,
+      "loss": 0.5727,
+      "step": 615
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028846579563247116,
+      "loss": 0.5681,
+      "step": 616
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002880788303115269,
+      "loss": 0.4383,
+      "step": 617
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028769145549236845,
+      "loss": 0.4962,
+      "step": 618
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002873036729759881,
+      "loss": 0.5472,
+      "step": 619
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002869154845652738,
+      "loss": 0.5431,
+      "step": 620
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002865268920650003,
+      "loss": 0.4152,
+      "step": 621
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002861378972818211,
+      "loss": 0.3922,
+      "step": 622
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002857485020242602,
+      "loss": 0.5129,
+      "step": 623
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002853587081027034,
+      "loss": 0.4328,
+      "step": 624
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00028496851732938997,
+      "loss": 0.4431,
+      "step": 625
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002845779315184042,
+      "loss": 0.4968,
+      "step": 626
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.000284186952485667,
+      "loss": 0.5301,
+      "step": 627
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002837955820489276,
+      "loss": 0.4332,
+      "step": 628
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002834038220277546,
+      "loss": 0.4245,
+      "step": 629
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00028301167424352836,
+      "loss": 0.5057,
+      "step": 630
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028261914051943166,
+      "loss": 0.4623,
+      "step": 631
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028222622268044174,
+      "loss": 0.5452,
+      "step": 632
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028183292255332164,
+      "loss": 0.5238,
+      "step": 633
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028143924196661176,
+      "loss": 0.3966,
+      "step": 634
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002810451827506214,
+      "loss": 0.35,
+      "step": 635
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00028065074673742007,
+      "loss": 0.4325,
+      "step": 636
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0002802559357608292,
+      "loss": 0.4854,
+      "step": 637
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027986075165641343,
+      "loss": 0.4254,
+      "step": 638
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027946519626147225,
+      "loss": 0.4614,
+      "step": 639
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027906927141503125,
+      "loss": 0.3798,
+      "step": 640
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027867297895783373,
+      "loss": 0.4742,
+      "step": 641
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002782763207323322,
+      "loss": 0.4007,
+      "step": 642
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002778792985826795,
+      "loss": 0.4383,
+      "step": 643
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002774819143547206,
+      "loss": 0.4298,
+      "step": 644
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00027708416989598387,
+      "loss": 0.5178,
+      "step": 645
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002766860670556722,
+      "loss": 0.3434,
+      "step": 646
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002762876076846551,
+      "loss": 0.3862,
+      "step": 647
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027588879363545934,
+      "loss": 0.4459,
+      "step": 648
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002754896267622608,
+      "loss": 0.3934,
+      "step": 649
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027509010892087565,
+      "loss": 0.4349,
+      "step": 650
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1557,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 8.708683022784922e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-650/training_args.bin b/checkpoint-650/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbdf20491848d40e9a89bca19c6229b4b2b55e5d
--- /dev/null
+++ b/checkpoint-650/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07819caee47f45203545f962678d52b5954ff1fd4afe1d5152fad48004402099
+size 4155
diff --git a/checkpoint-700/README.md b/checkpoint-700/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b32efe7366f05d1d90816d2ad9e4b06ccca46bea
--- /dev/null
+++ b/checkpoint-700/README.md
@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-700/adapter_config.json b/checkpoint-700/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e108f2da037ef6250457c67a4bedd308d97303c
--- /dev/null
+++ b/checkpoint-700/adapter_config.json
@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-700/adapter_model.bin b/checkpoint-700/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..08eb8ab92eac85b0939c839125d2b4f48d21b12f
--- /dev/null
+++ b/checkpoint-700/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05dcbf6a0eb6c227daf79f403826fb96f696f78fcae8997c0788ae630aaa6df
+size 113314765
diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a040176b68cd02a9f4c6cfce7960b00a349cd284
--- /dev/null
+++ b/checkpoint-700/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aaf4be3170088c5a633ea2b98b4000542a6eedfdbccc39f40e2a0aa8908411c
+size 226653957
diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f25b5c4bb8b1f73efa158f82884219b4cc6d7e4a
--- /dev/null
+++ b/checkpoint-700/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d644493925e965e20b39de9c3711211259f8396a94a62986c092fb2026af3821
+size 14575
diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f50d708a9f9dbe99cc2ec182ae711957ff05d6d3
--- /dev/null
+++ b/checkpoint-700/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fae75956dfc9e7cb641e5a21ef9ab176011d3b4ea29c8e3c08de7f701c6c44
+size 627
diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c7e65333074953684fc1cedec6c9c9cdfe9d454b
--- /dev/null
+++ b/checkpoint-700/trainer_state.json
@@ -0,0 +1,4219 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3485377301721027,
+  "eval_steps": 500,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6869,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8396,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7489,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7252,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8022,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.6524,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6981,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7488,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6891,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7968,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6912,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8452,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 0.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6685,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5469,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7915,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.6e-05,
+      "loss": 0.7744,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.6804,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.4e-05,
+      "loss": 0.7796,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.706,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6798,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6333,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 0.6012,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.52,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6583,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.7354,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000116,
+      "loss": 0.6296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 0.6352,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000124,
+      "loss": 0.6007,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5659,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000132,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6639,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 0.5934,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000144,
+      "loss": 0.5233,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000148,
+      "loss": 0.5307,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000152,
+      "loss": 0.5928,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5908,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000164,
+      "loss": 0.5972,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000168,
+      "loss": 0.4825,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000172,
+      "loss": 0.6783,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 0.7633,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5988,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000188,
+      "loss": 0.6658,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000192,
+      "loss": 0.5945,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000196,
+      "loss": 0.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.6057,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.601,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.5566,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.5911,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.7636,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.5537,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000232,
+      "loss": 0.6474,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000236,
+      "loss": 0.6483,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00024,
+      "loss": 0.5021,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000244,
+      "loss": 0.5347,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000248,
+      "loss": 0.5791,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000252,
+      "loss": 0.5407,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.5298,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5685,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000264,
+      "loss": 0.5108,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000268,
+      "loss": 0.526,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6843,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000276,
+      "loss": 0.6608,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00028,
+      "loss": 0.5866,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000284,
+      "loss": 0.6422,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000288,
+      "loss": 0.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000292,
+      "loss": 0.5319,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000296,
+      "loss": 0.5977,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.5805,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000304,
+      "loss": 0.5209,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000308,
+      "loss": 0.6098,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.4665,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6882,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00032,
+      "loss": 0.5427,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000324,
+      "loss": 0.5345,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000328,
+      "loss": 0.663,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000332,
+      "loss": 0.5393,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000336,
+      "loss": 0.5711,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00034,
+      "loss": 0.5261,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000344,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000348,
+      "loss": 0.6329,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.4425,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6837,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00036,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000364,
+      "loss": 0.5615,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5434,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000376,
+      "loss": 0.5583,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00038,
+      "loss": 0.5299,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000384,
+      "loss": 0.532,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000388,
+      "loss": 0.5227,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000392,
+      "loss": 0.5275,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.4541,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004,
+      "loss": 0.6485,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003999995350775973,
+      "loss": 0.5438,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999814031255063,
+      "loss": 0.5997,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999581571134455,
+      "loss": 0.5322,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003999925612847867,
+      "loss": 0.484,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998837704800766,
+      "loss": 0.5961,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998326302046085,
+      "loss": 0.7405,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997721922592255,
+      "loss": 0.5802,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997024569249167,
+      "loss": 0.769,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999623424525898,
+      "loss": 0.5598,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999535095429608,
+      "loss": 0.6143,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039994374700467095,
+      "loss": 0.5766,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039993305488310836,
+      "loss": 0.7695,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999214332279831,
+      "loss": 0.7153,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999088820933269,
+      "loss": 0.5835,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039989540153749286,
+      "loss": 0.6634,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000399880991623155,
+      "loss": 0.6069,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998656524173082,
+      "loss": 0.7224,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000399849383991268,
+      "loss": 0.5884,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998321864206699,
+      "loss": 0.5122,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039981405978546924,
+      "loss": 0.6453,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997950041699408,
+      "loss": 0.4665,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997750196626785,
+      "loss": 0.5428,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039975410635659464,
+      "loss": 0.4365,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039973226434891995,
+      "loss": 0.5978,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039970949374120286,
+      "loss": 0.7729,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000399685794639309,
+      "loss": 0.6212,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039966116715342066,
+      "loss": 0.5426,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00039963561139803676,
+      "loss": 0.5782,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003996091274919716,
+      "loss": 0.6701,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995817155583548,
+      "loss": 0.6314,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995533757246307,
+      "loss": 0.6662,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995241081225573,
+      "loss": 0.5192,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994939128882065,
+      "loss": 0.5591,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994627901619625,
+      "loss": 0.5809,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994307400885219,
+      "loss": 0.4871,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993977628168928,
+      "loss": 0.6666,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993638585003938,
+      "loss": 0.6469,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039932902729665357,
+      "loss": 0.5727,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039929326936761036,
+      "loss": 0.6715,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039925658487951067,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039921897400290894,
+      "loss": 0.501,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039918043691266665,
+      "loss": 0.5795,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039914097378795124,
+      "loss": 0.6287,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039910058481223564,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039905927017329726,
+      "loss": 0.6232,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039901703006321715,
+      "loss": 0.5291,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039897386467837903,
+      "loss": 0.5297,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039892977421946844,
+      "loss": 0.5784,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988847588914718,
+      "loss": 0.5714,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988388189036754,
+      "loss": 0.5044,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987919544696646,
+      "loss": 0.8246,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987441658073226,
+      "loss": 0.5048,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003986954531388297,
+      "loss": 0.5433,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039864581669066186,
+      "loss": 0.5251,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003985952566935902,
+      "loss": 0.5708,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039854377338267936,
+      "loss": 0.6276,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039849136699728684,
+      "loss": 0.4915,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003984380377810617,
+      "loss": 0.6389,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039838378598194325,
+      "loss": 0.6067,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039832861185216045,
+      "loss": 0.6136,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003982725156482301,
+      "loss": 0.5597,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000398215497630956,
+      "loss": 0.5957,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003981575580654278,
+      "loss": 0.5853,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980986972210194,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980389153713881,
+      "loss": 0.5302,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039797821279447307,
+      "loss": 0.5395,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039791658977249425,
+      "loss": 0.7004,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039785404659195084,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039779058354362013,
+      "loss": 0.5759,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000397726200922556,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003976608990280877,
+      "loss": 0.5488,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975946781638183,
+      "loss": 0.6162,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975275386376236,
+      "loss": 0.558,
+      "step": 173
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003974594807616502,
+      "loss": 0.519,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003973905048523144,
+      "loss": 0.6195,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039732061123030064,
+      "loss": 0.5991,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003972498002205601,
+      "loss": 0.5428,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039717807215230896,
+      "loss": 0.5323,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039710542735902705,
+      "loss": 0.5307,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003970318661784564,
+      "loss": 0.5783,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003969573889525993,
+      "loss": 0.5924,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039688199602771714,
+      "loss": 0.5902,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039680568775432855,
+      "loss": 0.6291,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003967284644872077,
+      "loss": 0.5942,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003966503265853829,
+      "loss": 0.4878,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003965712744121347,
+      "loss": 0.6487,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003964913083349945,
+      "loss": 0.6111,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039641042872574233,
+      "loss": 0.6072,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039632863596040575,
+      "loss": 0.716,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039624593041925763,
+      "loss": 0.6178,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003961623124868145,
+      "loss": 0.6323,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039607778255183485,
+      "loss": 0.5821,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959923410073174,
+      "loss": 0.6738,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959059882504989,
+      "loss": 0.6203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039581872468285277,
+      "loss": 0.632,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003957305507100868,
+      "loss": 0.5857,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039564146674214164,
+      "loss": 0.6311,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003955514731931885,
+      "loss": 0.5889,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039546057048162763,
+      "loss": 0.5201,
+      "step": 199
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039536875903008607,
+      "loss": 0.5581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039527603926541586,
+      "loss": 0.5104,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039518241161869193,
+      "loss": 0.5978,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039508787652521013,
+      "loss": 0.6244,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039499243442448536,
+      "loss": 0.589,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003948960857602493,
+      "loss": 0.575,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947988309804485,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947006705372422,
+      "loss": 0.4895,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039460160488700036,
+      "loss": 0.5479,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039450163449030124,
+      "loss": 0.5893,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003944007598119297,
+      "loss": 0.5451,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003942989813208747,
+      "loss": 0.5582,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003941962994903273,
+      "loss": 0.5121,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039409271479767826,
+      "loss": 0.6324,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000393988227724516,
+      "loss": 0.6118,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003938828387566244,
+      "loss": 0.6303,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003937765483839804,
+      "loss": 0.7705,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003936693571007517,
+      "loss": 0.6224,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935612654052946,
+      "loss": 0.5664,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039345227380015163,
+      "loss": 0.66,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039334238279204906,
+      "loss": 0.5582,
+      "step": 220
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039323159289189505,
+      "loss": 0.6087,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003931199046147764,
+      "loss": 0.5566,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039300731847995716,
+      "loss": 0.5775,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039289383501087534,
+      "loss": 0.5081,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277945473514104,
+      "loss": 0.5218,
+      "step": 225
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003926641781845338,
+      "loss": 0.6655,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003925480058950002,
+      "loss": 0.5735,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039243093840665114,
+      "loss": 0.6609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003923129762637596,
+      "loss": 0.7323,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000392194120014758,
+      "loss": 0.5703,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039207437021223583,
+      "loss": 0.6545,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003919537274129366,
+      "loss": 0.521,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039183219217775564,
+      "loss": 0.5257,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003917097650717377,
+      "loss": 0.5487,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039158644666407365,
+      "loss": 0.4861,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039146223752809845,
+      "loss": 0.4928,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003913371382412883,
+      "loss": 0.5253,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039121114938525756,
+      "loss": 0.6155,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039108427154575684,
+      "loss": 0.55,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039095650531266967,
+      "loss": 0.6617,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039082785128000976,
+      "loss": 0.5198,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039069831004591866,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003905678822126625,
+      "loss": 0.5347,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039043656838662946,
+      "loss": 0.531,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039030436917832697,
+      "loss": 0.4884,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039017128520237883,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003900373170775222,
+      "loss": 0.5537,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038990246542660494,
+      "loss": 0.5753,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038976673087658256,
+      "loss": 0.5059,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038963011405851537,
+      "loss": 0.5118,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038949261560756565,
+      "loss": 0.5645,
+      "step": 251
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003893542361629944,
+      "loss": 0.5623,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038921497636815866,
+      "loss": 0.5216,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003890748368705085,
+      "loss": 0.4501,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003889338183215838,
+      "loss": 0.48,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038879192137701135,
+      "loss": 0.5218,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003886491466965018,
+      "loss": 0.5858,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038850549494384685,
+      "loss": 0.6124,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038836096678691536,
+      "loss": 0.4645,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038821556289765136,
+      "loss": 0.474,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038806928395207003,
+      "loss": 0.4364,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038792213063025484,
+      "loss": 0.5821,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003877741036163547,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003876252035985804,
+      "loss": 0.5373,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003874754312692013,
+      "loss": 0.6021,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003873247873245426,
+      "loss": 0.4549,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003871732724649817,
+      "loss": 0.5994,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003870208873949453,
+      "loss": 0.4764,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038686763282290556,
+      "loss": 0.4311,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003867135094613774,
+      "loss": 0.5462,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003865585180269148,
+      "loss": 0.5006,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003864026592401076,
+      "loss": 0.5347,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038624593382557835,
+      "loss": 0.5242,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038608834251197856,
+      "loss": 0.5005,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038592988603198554,
+      "loss": 0.5436,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000385770565122299,
+      "loss": 0.4658,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003856103805236375,
+      "loss": 0.5273,
+      "step": 277
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038544933298073516,
+      "loss": 0.436,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038528742324233804,
+      "loss": 0.4785,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038512465206120086,
+      "loss": 0.5366,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038496102019408324,
+      "loss": 0.4448,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038479652840174637,
+      "loss": 0.5132,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038463117744894955,
+      "loss": 0.7918,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038446496810444627,
+      "loss": 0.5309,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038429790114098114,
+      "loss": 0.5316,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038412997733528576,
+      "loss": 0.4611,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038396119746807563,
+      "loss": 0.4609,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038379156232404613,
+      "loss": 0.5821,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003836210726918691,
+      "loss": 0.5883,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003834497293641889,
+      "loss": 0.5012,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038327753313761913,
+      "loss": 0.4457,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038310448481273867,
+      "loss": 0.4851,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038293058519408787,
+      "loss": 0.5622,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038275583509016507,
+      "loss": 0.5703,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038258023531342265,
+      "loss": 0.5718,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003824037866802632,
+      "loss": 0.5183,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038222649001103614,
+      "loss": 0.5085,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038204834613003323,
+      "loss": 0.5388,
+      "step": 298
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038186935586548537,
+      "loss": 0.5425,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003816895200495584,
+      "loss": 0.447,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003815088395183493,
+      "loss": 0.5541,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038132731511188227,
+      "loss": 0.5518,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000381144947674105,
+      "loss": 0.5074,
+      "step": 303
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003809617380528847,
+      "loss": 0.5134,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003807776871000037,
+      "loss": 0.4599,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003805927956711562,
+      "loss": 0.5838,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038040706462594395,
+      "loss": 0.5216,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038022049482787216,
+      "loss": 0.5323,
+      "step": 308
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003800330871443456,
+      "loss": 0.5681,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00037984484244666446,
+      "loss": 0.4172,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003796557616100207,
+      "loss": 0.4958,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003794658455134934,
+      "loss": 0.662,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003792750950400451,
+      "loss": 0.5832,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003790835110765174,
+      "loss": 0.4271,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003788910945136271,
+      "loss": 0.4842,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037869784624596186,
+      "loss": 0.4656,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037850376717197626,
+      "loss": 0.4981,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037830885819398733,
+      "loss": 0.5162,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037811312021817067,
+      "loss": 0.652,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003779165541545558,
+      "loss": 0.5104,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003777191609170225,
+      "loss": 0.4971,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003775209414232962,
+      "loss": 0.4871,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003773218965949436,
+      "loss": 0.5226,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00037712202735736884,
+      "loss": 0.4823,
+      "step": 324
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003769213346398087,
+      "loss": 0.497,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003767198193753286,
+      "loss": 0.5976,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003765174825008181,
+      "loss": 0.4532,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003763143249569868,
+      "loss": 0.5236,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00037611034768835947,
+      "loss": 0.6513,
+      "step": 329
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037590555164327224,
+      "loss": 0.5686,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037569993777386774,
+      "loss": 0.456,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003754935070360909,
+      "loss": 0.5181,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003752862603896846,
+      "loss": 0.4765,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037507819879818477,
+      "loss": 0.5363,
+      "step": 334
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037486932322891646,
+      "loss": 0.4584,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037465963465298886,
+      "loss": 0.5428,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003744491340452913,
+      "loss": 0.3927,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003742378223844882,
+      "loss": 0.5478,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003740257006530147,
+      "loss": 0.469,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037381276983707246,
+      "loss": 0.5169,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037359903092662434,
+      "loss": 0.4797,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037338448491539054,
+      "loss": 0.5315,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037316913280084353,
+      "loss": 0.4422,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003729529755842035,
+      "loss": 0.4426,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003727360142704337,
+      "loss": 0.4718,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003725182498682361,
+      "loss": 0.5585,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003722996833900459,
+      "loss": 0.4775,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003720803158520279,
+      "loss": 0.6014,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00037186014827407076,
+      "loss": 0.5117,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003716391816797829,
+      "loss": 0.5404,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003714174170964876,
+      "loss": 0.527,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037119485555521796,
+      "loss": 0.4555,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037097149809071255,
+      "loss": 0.5372,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037074734574141016,
+      "loss": 0.5377,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003705223995494454,
+      "loss": 0.4925,
+      "step": 355
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037029666056064345,
+      "loss": 0.482,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037007012982451546,
+      "loss": 0.5235,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00036984280839425356,
+      "loss": 0.4957,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000369614697326726,
+      "loss": 0.5379,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003693857976824721,
+      "loss": 0.4653,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036915611052569785,
+      "loss": 0.469,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003689256369242702,
+      "loss": 0.5618,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003686943779497124,
+      "loss": 0.4459,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003684623346771995,
+      "loss": 0.5606,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003682295081855524,
+      "loss": 0.4368,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036799589955723375,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036776150987834243,
+      "loss": 0.4664,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036752634023860846,
+      "loss": 0.4737,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003672903917313883,
+      "loss": 0.4247,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036705366545365935,
+      "loss": 0.5677,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036681616250601505,
+      "loss": 0.5441,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003665778839926599,
+      "loss": 0.6247,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00036633883102140405,
+      "loss": 0.5217,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003660990047036584,
+      "loss": 0.4651,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003658584061544291,
+      "loss": 0.4648,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003656170364923128,
+      "loss": 0.6048,
+      "step": 376
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036537489683949114,
+      "loss": 0.4515,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003651319883217255,
+      "loss": 0.5096,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036488831206835207,
+      "loss": 0.4231,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036464386921227637,
+      "loss": 0.4903,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036439866088996796,
+      "loss": 0.5131,
+      "step": 381
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003641526882414553,
+      "loss": 0.5986,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003639059524103203,
+      "loss": 0.6,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003636584545436931,
+      "loss": 0.5216,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003634101957922468,
+      "loss": 0.5144,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00036316117731019184,
+      "loss": 0.4963,
+      "step": 386
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003629114002552711,
+      "loss": 0.5657,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036266086578875384,
+      "loss": 0.5028,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003624095750754311,
+      "loss": 0.573,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036215752928360967,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003619047295851068,
+      "loss": 0.656,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036165117715524506,
+      "loss": 0.5129,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036139687317284647,
+      "loss": 0.3945,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003611418188202271,
+      "loss": 0.5318,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036088601528319196,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036062946375102885,
+      "loss": 0.5407,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003603721654165034,
+      "loss": 0.5364,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00036011412147585306,
+      "loss": 0.5407,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003598553331287821,
+      "loss": 0.5999,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003595958015784555,
+      "loss": 0.624,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00035933552803149354,
+      "loss": 0.5351,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003590745136979662,
+      "loss": 0.5196,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035881275979138765,
+      "loss": 0.5447,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003585502675287104,
+      "loss": 0.4908,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035828703813031986,
+      "loss": 0.5172,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035802307282002834,
+      "loss": 0.5923,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003577583728250699,
+      "loss": 0.568,
+      "step": 407
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035749293937609395,
+      "loss": 0.4618,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003572267737071601,
+      "loss": 0.5351,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003569598770557322,
+      "loss": 0.5285,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035669225066267256,
+      "loss": 0.4571,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035642389577223625,
+      "loss": 0.4214,
+      "step": 412
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003561548136320653,
+      "loss": 0.5393,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003558850054931828,
+      "loss": 0.549,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035561447260998714,
+      "loss": 0.4824,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035534321624024656,
+      "loss": 0.6244,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035507123764509245,
+      "loss": 0.5436,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003547985380890144,
+      "loss": 0.5198,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035452511883985366,
+      "loss": 0.5979,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035425098116879754,
+      "loss": 0.4158,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035397612635037356,
+      "loss": 0.5125,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035370055566244334,
+      "loss": 0.4699,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003534242703861966,
+      "loss": 0.5553,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035314727180614573,
+      "loss": 0.5969,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035286956121011897,
+      "loss": 0.456,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003525911398892552,
+      "loss": 0.5195,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003523120091379975,
+      "loss": 0.5187,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035203217025408726,
+      "loss": 0.5443,
+      "step": 428
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003517516245385582,
+      "loss": 0.4476,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003514703732957301,
+      "loss": 0.5757,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035118841783320304,
+      "loss": 0.5129,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035090575946185114,
+      "loss": 0.6354,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035062239949581645,
+      "loss": 0.4065,
+      "step": 433
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000350338339252503,
+      "loss": 0.5472,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00035005358005257045,
+      "loss": 0.5424,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034976812321992816,
+      "loss": 0.6127,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034948197008172877,
+      "loss": 0.63,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003491951219683625,
+      "loss": 0.413,
+      "step": 438
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034890758021345034,
+      "loss": 0.5435,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034861934615383844,
+      "loss": 0.5433,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034833042112959153,
+      "loss": 0.4763,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034804080648398667,
+      "loss": 0.5727,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034775050356350727,
+      "loss": 0.5392,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034745951371783666,
+      "loss": 0.4981,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003471678382998518,
+      "loss": 0.5516,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00034687547866561703,
+      "loss": 0.4965,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003465824361743779,
+      "loss": 0.4982,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003462887121885544,
+      "loss": 0.5619,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003459943080737353,
+      "loss": 0.5273,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034569922519867133,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034540346493526876,
+      "loss": 0.4874,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003451070286585833,
+      "loss": 0.5966,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003448099177468137,
+      "loss": 0.4487,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003445121335812951,
+      "loss": 0.5091,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003442136775464929,
+      "loss": 0.407,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003439145510299958,
+      "loss": 0.6327,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00034361475542251025,
+      "loss": 0.4217,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003433142921178531,
+      "loss": 0.6102,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003430131625129456,
+      "loss": 0.5556,
+      "step": 459
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034271136800780673,
+      "loss": 0.4986,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003424089100055467,
+      "loss": 0.5406,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034210578991236056,
+      "loss": 0.5881,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034180200913752157,
+      "loss": 0.4869,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034149756909337454,
+      "loss": 0.5626,
+      "step": 464
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003411924711953295,
+      "loss": 0.564,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00034088671686185486,
+      "loss": 0.6272,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003405803075144711,
+      "loss": 0.4643,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003402732445777438,
+      "loss": 0.5435,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00033996552947927744,
+      "loss": 0.5844,
+      "step": 469
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003396571636497084,
+      "loss": 0.5362,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033934814852269865,
+      "loss": 0.5607,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003390384855349285,
+      "loss": 0.4836,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033872817612609065,
+      "loss": 0.6555,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033841722173888315,
+      "loss": 0.4784,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033810562381900253,
+      "loss": 0.5583,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033779338381513736,
+      "loss": 0.4679,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003374805031789613,
+      "loss": 0.5325,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033716698336512654,
+      "loss": 0.6601,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000336852825831257,
+      "loss": 0.4838,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003365380320379414,
+      "loss": 0.5588,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033622260344872665,
+      "loss": 0.4596,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003359065415301108,
+      "loss": 0.5228,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033558984775153663,
+      "loss": 0.5316,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033527252358538437,
+      "loss": 0.4761,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003349545705069653,
+      "loss": 0.5254,
+      "step": 485
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003346359899945144,
+      "loss": 0.4786,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033431678352918384,
+      "loss": 0.4302,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003339969525950361,
+      "loss": 0.4914,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033367649867903663,
+      "loss": 0.4102,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003333554232710477,
+      "loss": 0.4698,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003330337278638207,
+      "loss": 0.4454,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033271141395298964,
+      "loss": 0.4648,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033238848303706415,
+      "loss": 0.4616,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033206493661742237,
+      "loss": 0.4861,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033174077619830416,
+      "loss": 0.4797,
+      "step": 495
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033141600328680373,
+      "loss": 0.5104,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033109061939286336,
+      "loss": 0.5712,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033076462602926553,
+      "loss": 0.5425,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033043802471162636,
+      "loss": 0.6156,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003301108169583887,
+      "loss": 0.4282,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003297830042908146,
+      "loss": 0.4088,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032945458823297857,
+      "loss": 0.4866,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003291255703117605,
+      "loss": 0.5045,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003287959520568384,
+      "loss": 0.491,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032846573500068136,
+      "loss": 0.458,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032813492067854246,
+      "loss": 0.4508,
+      "step": 506
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003278035106284516,
+      "loss": 0.4294,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032747150639120834,
+      "loss": 0.4834,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032713890951037477,
+      "loss": 0.3857,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032680572153226834,
+      "loss": 0.4072,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003264719440059545,
+      "loss": 0.4028,
+      "step": 511
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032613757848323977,
+      "loss": 0.3789,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032580262651866446,
+      "loss": 0.4944,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003254670896694952,
+      "loss": 0.4259,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032513096949571805,
+      "loss": 0.5037,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032479426756003093,
+      "loss": 0.5857,
+      "step": 516
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003244569854278366,
+      "loss": 0.5407,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032411912466723524,
+      "loss": 0.499,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003237806868490172,
+      "loss": 0.4359,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032344167354665573,
+      "loss": 0.4374,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003231020863362997,
+      "loss": 0.4172,
+      "step": 521
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000322761926796766,
+      "loss": 0.4451,
+      "step": 522
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003224211965095326,
+      "loss": 0.4,
+      "step": 523
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003220798970587309,
+      "loss": 0.4009,
+      "step": 524
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003217380300311386,
+      "loss": 0.3966,
+      "step": 525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000321395597016172,
+      "loss": 0.4255,
+      "step": 526
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00032105259960587895,
+      "loss": 0.4707,
+      "step": 527
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00032070903939493124,
+      "loss": 0.5313,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003203649179806172,
+      "loss": 0.3596,
+      "step": 529
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003200202369628345,
+      "loss": 0.5223,
+      "step": 530
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031967499794408234,
+      "loss": 0.4146,
+      "step": 531
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031932920252945423,
+      "loss": 0.4328,
+      "step": 532
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003189828523266306,
+      "loss": 0.4258,
+      "step": 533
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031863594894587105,
+      "loss": 0.4457,
+      "step": 534
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003182884940000072,
+      "loss": 0.5249,
+      "step": 535
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003179404891044348,
+      "loss": 0.4751,
+      "step": 536
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031759193587710676,
+      "loss": 0.5378,
+      "step": 537
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031724283593852497,
+      "loss": 0.634,
+      "step": 538
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031689319091173326,
+      "loss": 0.4298,
+      "step": 539
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031654300242230977,
+      "loss": 0.5469,
+      "step": 540
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031619227209835917,
+      "loss": 0.5153,
+      "step": 541
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003158410015705053,
+      "loss": 0.4144,
+      "step": 542
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003154891924718837,
+      "loss": 0.6041,
+      "step": 543
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003151368464381335,
+      "loss": 0.4891,
+      "step": 544
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003147839651073904,
+      "loss": 0.5258,
+      "step": 545
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00031443055012027874,
+      "loss": 0.4351,
+      "step": 546
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000314076603119904,
+      "loss": 0.4556,
+      "step": 547
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031372212575184514,
+      "loss": 0.5445,
+      "step": 548
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031336711966414675,
+      "loss": 0.5585,
+      "step": 549
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003130115865073117,
+      "loss": 0.367,
+      "step": 550
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003126555279342933,
+      "loss": 0.4877,
+      "step": 551
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003122989456004876,
+      "loss": 0.4335,
+      "step": 552
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003119418411637258,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003115842162842663,
+      "loss": 0.4508,
+      "step": 554
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00031122607262478743,
+      "loss": 0.4631,
+      "step": 555
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003108674118503793,
+      "loss": 0.3496,
+      "step": 556
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003105082356285361,
+      "loss": 0.4108,
+      "step": 557
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003101485456291486,
+      "loss": 0.4877,
+      "step": 558
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030978834352449614,
+      "loss": 0.3696,
+      "step": 559
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030942763098923913,
+      "loss": 0.5138,
+      "step": 560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030906640970041084,
+      "loss": 0.5961,
+      "step": 561
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003087046813374099,
+      "loss": 0.3824,
+      "step": 562
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030834244758199276,
+      "loss": 0.4925,
+      "step": 563
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000307979710118265,
+      "loss": 0.4511,
+      "step": 564
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030761647063267457,
+      "loss": 0.4306,
+      "step": 565
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003072527308140031,
+      "loss": 0.468,
+      "step": 566
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030688849235335856,
+      "loss": 0.4842,
+      "step": 567
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003065237569441671,
+      "loss": 0.4332,
+      "step": 568
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030615852628216537,
+      "loss": 0.4637,
+      "step": 569
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003057928020653925,
+      "loss": 0.6193,
+      "step": 570
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003054265859941824,
+      "loss": 0.5033,
+      "step": 571
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030505987977115555,
+      "loss": 0.4185,
+      "step": 572
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003046926851012114,
+      "loss": 0.4211,
+      "step": 573
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003043250036915201,
+      "loss": 0.5089,
+      "step": 574
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00030395683725151505,
+      "loss": 0.517,
+      "step": 575
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003035881874928845,
+      "loss": 0.492,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003032190561295636,
+      "loss": 0.4535,
+      "step": 577
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003028494448777269,
+      "loss": 0.3947,
+      "step": 578
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030247935545577986,
+      "loss": 0.3125,
+      "step": 579
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003021087895843511,
+      "loss": 0.3882,
+      "step": 580
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003017377489862845,
+      "loss": 0.4802,
+      "step": 581
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030136623538663083,
+      "loss": 0.4652,
+      "step": 582
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030099425051263994,
+      "loss": 0.3816,
+      "step": 583
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003006217960937529,
+      "loss": 0.4583,
+      "step": 584
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00030024887386159385,
+      "loss": 0.4568,
+      "step": 585
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029987548554996174,
+      "loss": 0.3908,
+      "step": 586
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002995016328948225,
+      "loss": 0.4235,
+      "step": 587
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029912731763430075,
+      "loss": 0.4138,
+      "step": 588
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029875254150867216,
+      "loss": 0.5838,
+      "step": 589
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002983773062603548,
+      "loss": 0.462,
+      "step": 590
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029800161363390145,
+      "loss": 0.4632,
+      "step": 591
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029762546537599125,
+      "loss": 0.5898,
+      "step": 592
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002972488632354218,
+      "loss": 0.4742,
+      "step": 593
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029687180896310065,
+      "loss": 0.4579,
+      "step": 594
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002964943043120378,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029611635103733675,
+      "loss": 0.4304,
+      "step": 596
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002957379508961871,
+      "loss": 0.4383,
+      "step": 597
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029535910564785584,
+      "loss": 0.5327,
+      "step": 598
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029497981705367933,
+      "loss": 0.4781,
+      "step": 599
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029460008687705525,
+      "loss": 0.4178,
+      "step": 600
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002942199168834342,
+      "loss": 0.3987,
+      "step": 601
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029383930884031183,
+      "loss": 0.3861,
+      "step": 602
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029345826451722005,
+      "loss": 0.5322,
+      "step": 603
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029307678568571936,
+      "loss": 0.3997,
+      "step": 604
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002926948741193903,
+      "loss": 0.4121,
+      "step": 605
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029231253159382514,
+      "loss": 0.4931,
+      "step": 606
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029192975988662017,
+      "loss": 0.4626,
+      "step": 607
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029154656077736666,
+      "loss": 0.4441,
+      "step": 608
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002911629360476432,
+      "loss": 0.3863,
+      "step": 609
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029077888748100703,
+      "loss": 0.36,
+      "step": 610
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029039441686298594,
+      "loss": 0.4246,
+      "step": 611
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002900095259810702,
+      "loss": 0.4916,
+      "step": 612
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028962421662470346,
+      "loss": 0.4896,
+      "step": 613
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028923849058527535,
+      "loss": 0.4237,
+      "step": 614
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028885234965611274,
+      "loss": 0.5727,
+      "step": 615
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028846579563247116,
+      "loss": 0.5681,
+      "step": 616
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002880788303115269,
+      "loss": 0.4383,
+      "step": 617
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028769145549236845,
+      "loss": 0.4962,
+      "step": 618
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002873036729759881,
+      "loss": 0.5472,
+      "step": 619
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002869154845652738,
+      "loss": 0.5431,
+      "step": 620
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002865268920650003,
+      "loss": 0.4152,
+      "step": 621
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002861378972818211,
+      "loss": 0.3922,
+      "step": 622
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002857485020242602,
+      "loss": 0.5129,
+      "step": 623
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002853587081027034,
+      "loss": 0.4328,
+      "step": 624
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00028496851732938997,
+      "loss": 0.4431,
+      "step": 625
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002845779315184042,
+      "loss": 0.4968,
+      "step": 626
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.000284186952485667,
+      "loss": 0.5301,
+      "step": 627
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002837955820489276,
+      "loss": 0.4332,
+      "step": 628
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002834038220277546,
+      "loss": 0.4245,
+      "step": 629
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00028301167424352836,
+      "loss": 0.5057,
+      "step": 630
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028261914051943166,
+      "loss": 0.4623,
+      "step": 631
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028222622268044174,
+      "loss": 0.5452,
+      "step": 632
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028183292255332164,
+      "loss": 0.5238,
+      "step": 633
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028143924196661176,
+      "loss": 0.3966,
+      "step": 634
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002810451827506214,
+      "loss": 0.35,
+      "step": 635
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00028065074673742007,
+      "loss": 0.4325,
+      "step": 636
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0002802559357608292,
+      "loss": 0.4854,
+      "step": 637
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027986075165641343,
+      "loss": 0.4254,
+      "step": 638
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027946519626147225,
+      "loss": 0.4614,
+      "step": 639
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027906927141503125,
+      "loss": 0.3798,
+      "step": 640
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027867297895783373,
+      "loss": 0.4742,
+      "step": 641
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002782763207323322,
+      "loss": 0.4007,
+      "step": 642
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002778792985826795,
+      "loss": 0.4383,
+      "step": 643
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002774819143547206,
+      "loss": 0.4298,
+      "step": 644
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00027708416989598387,
+      "loss": 0.5178,
+      "step": 645
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002766860670556722,
+      "loss": 0.3434,
+      "step": 646
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002762876076846551,
+      "loss": 0.3862,
+      "step": 647
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027588879363545934,
+      "loss": 0.4459,
+      "step": 648
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002754896267622608,
+      "loss": 0.3934,
+      "step": 649
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027509010892087565,
+      "loss": 0.4349,
+      "step": 650
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000274690241968752,
+      "loss": 0.4178,
+      "step": 651
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002742900277649607,
+      "loss": 0.4151,
+      "step": 652
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002738894681701874,
+      "loss": 0.3888,
+      "step": 653
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027348856504672323,
+      "loss": 0.4214,
+      "step": 654
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002730873202584567,
+      "loss": 0.519,
+      "step": 655
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027268573567086477,
+      "loss": 0.5463,
+      "step": 656
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027228381315100417,
+      "loss": 0.3367,
+      "step": 657
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027188155456750256,
+      "loss": 0.4629,
+      "step": 658
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027147896179055043,
+      "loss": 0.4456,
+      "step": 659
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002710760366918917,
+      "loss": 0.4348,
+      "step": 660
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002706727811448153,
+      "loss": 0.4505,
+      "step": 661
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002702691970241468,
+      "loss": 0.5028,
+      "step": 662
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026986528620623904,
+      "loss": 0.5257,
+      "step": 663
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026946105056896403,
+      "loss": 0.4977,
+      "step": 664
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026905649199170377,
+      "loss": 0.421,
+      "step": 665
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002686516123553417,
+      "loss": 0.4931,
+      "step": 666
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026824641354225397,
+      "loss": 0.5818,
+      "step": 667
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002678408974363005,
+      "loss": 0.4211,
+      "step": 668
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026743506592281674,
+      "loss": 0.5182,
+      "step": 669
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026702892088860413,
+      "loss": 0.5591,
+      "step": 670
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002666224642219221,
+      "loss": 0.5363,
+      "step": 671
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002662156978124786,
+      "loss": 0.5866,
+      "step": 672
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002658086235514218,
+      "loss": 0.422,
+      "step": 673
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002654012433313312,
+      "loss": 0.5375,
+      "step": 674
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002649935590462087,
+      "loss": 0.4752,
+      "step": 675
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00026458557259146986,
+      "loss": 0.4271,
+      "step": 676
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002641772858639351,
+      "loss": 0.4843,
+      "step": 677
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026376870076182086,
+      "loss": 0.4827,
+      "step": 678
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026335981918473086,
+      "loss": 0.47,
+      "step": 679
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002629506430336472,
+      "loss": 0.368,
+      "step": 680
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026254117421092133,
+      "loss": 0.481,
+      "step": 681
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002621314146202656,
+      "loss": 0.4153,
+      "step": 682
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002617213661667443,
+      "loss": 0.4397,
+      "step": 683
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002613110307567643,
+      "loss": 0.4052,
+      "step": 684
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026090041029806695,
+      "loss": 0.4652,
+      "step": 685
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026048950669971884,
+      "loss": 0.3826,
+      "step": 686
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026007832187210277,
+      "loss": 0.5639,
+      "step": 687
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025966685772690906,
+      "loss": 0.3917,
+      "step": 688
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025925511617712685,
+      "loss": 0.5248,
+      "step": 689
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002588430991370347,
+      "loss": 0.3796,
+      "step": 690
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002584308085221922,
+      "loss": 0.4391,
+      "step": 691
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025801824624943084,
+      "loss": 0.4514,
+      "step": 692
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025760541423684496,
+      "loss": 0.5046,
+      "step": 693
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002571923144037831,
+      "loss": 0.4578,
+      "step": 694
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002567789486708389,
+      "loss": 0.4681,
+      "step": 695
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025636531895984236,
+      "loss": 0.4501,
+      "step": 696
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002559514271938506,
+      "loss": 0.4411,
+      "step": 697
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025553727529713916,
+      "loss": 0.401,
+      "step": 698
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025512286519519293,
+      "loss": 0.4911,
+      "step": 699
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002547081988146974,
+      "loss": 0.3754,
+      "step": 700
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1557,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 9.390244643843604e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbdf20491848d40e9a89bca19c6229b4b2b55e5d
--- /dev/null
+++ b/checkpoint-700/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07819caee47f45203545f962678d52b5954ff1fd4afe1d5152fad48004402099
+size 4155
diff --git a/checkpoint-750/README.md b/checkpoint-750/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b32efe7366f05d1d90816d2ad9e4b06ccca46bea
--- /dev/null
+++ b/checkpoint-750/README.md
@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-750/adapter_config.json b/checkpoint-750/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e108f2da037ef6250457c67a4bedd308d97303c
--- /dev/null
+++ b/checkpoint-750/adapter_config.json
@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-750/adapter_model.bin b/checkpoint-750/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6265a5c9e72d2291284a737f0f39272f8d16567b
--- /dev/null
+++ b/checkpoint-750/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5997c00f5e8f6eccdb56e961f1f52738da6811b9e1f8f7db68cc06d230fa63e6
+size 113314765
diff --git a/checkpoint-750/optimizer.pt b/checkpoint-750/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0eb309fead5ea47a366d9047225f99eb279814eb
--- /dev/null
+++ b/checkpoint-750/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d035f8f714d8f59687635c261f0c44aa27f208c4f133ed451e6712f921d9a7a2
+size 226653957
diff --git a/checkpoint-750/rng_state.pth b/checkpoint-750/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b84d89f04526af3df117562115ac4f6cf91ccc53
--- /dev/null
+++ b/checkpoint-750/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e71c190b39ebb7d181ccf3ca246501e0db9c691f3efccf8fad4d44e71dde25
+size 14575
diff --git a/checkpoint-750/scheduler.pt b/checkpoint-750/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d2cc3cd20e5bad09df20e8bfa79447b0e0afad6f
--- /dev/null
+++ b/checkpoint-750/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a877afe6d21b07682330f27e66aabc1b0aa1dfc72a9aa997eb4a4f2512ca27
+size 627
diff --git a/checkpoint-750/trainer_state.json b/checkpoint-750/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cb1819cc48fbb76128230079b75c48ee5a39307
--- /dev/null
+++ b/checkpoint-750/trainer_state.json
@@ -0,0 +1,4519 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4448188711036225,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6869,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8396,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7489,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7252,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8022,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.6524,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6981,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7488,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6891,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7968,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6912,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8452,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 0.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6685,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5469,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7915,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.6e-05,
+      "loss": 0.7744,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.6804,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.4e-05,
+      "loss": 0.7796,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.706,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6798,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6333,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 0.6012,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.52,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6583,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.7354,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000116,
+      "loss": 0.6296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 0.6352,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000124,
+      "loss": 0.6007,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5659,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000132,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6639,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 0.5934,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000144,
+      "loss": 0.5233,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000148,
+      "loss": 0.5307,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000152,
+      "loss": 0.5928,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5908,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000164,
+      "loss": 0.5972,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000168,
+      "loss": 0.4825,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000172,
+      "loss": 0.6783,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 0.7633,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5988,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000188,
+      "loss": 0.6658,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000192,
+      "loss": 0.5945,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000196,
+      "loss": 0.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.6057,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.601,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.5566,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.5911,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.7636,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.5537,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000232,
+      "loss": 0.6474,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000236,
+      "loss": 0.6483,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00024,
+      "loss": 0.5021,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000244,
+      "loss": 0.5347,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000248,
+      "loss": 0.5791,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000252,
+      "loss": 0.5407,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.5298,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5685,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000264,
+      "loss": 0.5108,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000268,
+      "loss": 0.526,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6843,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000276,
+      "loss": 0.6608,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00028,
+      "loss": 0.5866,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000284,
+      "loss": 0.6422,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000288,
+      "loss": 0.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000292,
+      "loss": 0.5319,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000296,
+      "loss": 0.5977,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.5805,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000304,
+      "loss": 0.5209,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000308,
+      "loss": 0.6098,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.4665,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6882,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00032,
+      "loss": 0.5427,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000324,
+      "loss": 0.5345,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000328,
+      "loss": 0.663,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000332,
+      "loss": 0.5393,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000336,
+      "loss": 0.5711,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00034,
+      "loss": 0.5261,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000344,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000348,
+      "loss": 0.6329,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.4425,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6837,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00036,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000364,
+      "loss": 0.5615,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5434,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000376,
+      "loss": 0.5583,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00038,
+      "loss": 0.5299,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000384,
+      "loss": 0.532,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000388,
+      "loss": 0.5227,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000392,
+      "loss": 0.5275,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.4541,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004,
+      "loss": 0.6485,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003999995350775973,
+      "loss": 0.5438,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999814031255063,
+      "loss": 0.5997,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999581571134455,
+      "loss": 0.5322,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003999925612847867,
+      "loss": 0.484,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998837704800766,
+      "loss": 0.5961,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998326302046085,
+      "loss": 0.7405,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997721922592255,
+      "loss": 0.5802,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997024569249167,
+      "loss": 0.769,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999623424525898,
+      "loss": 0.5598,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999535095429608,
+      "loss": 0.6143,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039994374700467095,
+      "loss": 0.5766,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039993305488310836,
+      "loss": 0.7695,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999214332279831,
+      "loss": 0.7153,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999088820933269,
+      "loss": 0.5835,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039989540153749286,
+      "loss": 0.6634,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000399880991623155,
+      "loss": 0.6069,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998656524173082,
+      "loss": 0.7224,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000399849383991268,
+      "loss": 0.5884,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998321864206699,
+      "loss": 0.5122,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039981405978546924,
+      "loss": 0.6453,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997950041699408,
+      "loss": 0.4665,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997750196626785,
+      "loss": 0.5428,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039975410635659464,
+      "loss": 0.4365,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039973226434891995,
+      "loss": 0.5978,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039970949374120286,
+      "loss": 0.7729,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000399685794639309,
+      "loss": 0.6212,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039966116715342066,
+      "loss": 0.5426,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00039963561139803676,
+      "loss": 0.5782,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003996091274919716,
+      "loss": 0.6701,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995817155583548,
+      "loss": 0.6314,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995533757246307,
+      "loss": 0.6662,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995241081225573,
+      "loss": 0.5192,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994939128882065,
+      "loss": 0.5591,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994627901619625,
+      "loss": 0.5809,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994307400885219,
+      "loss": 0.4871,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993977628168928,
+      "loss": 0.6666,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993638585003938,
+      "loss": 0.6469,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039932902729665357,
+      "loss": 0.5727,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039929326936761036,
+      "loss": 0.6715,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039925658487951067,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039921897400290894,
+      "loss": 0.501,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039918043691266665,
+      "loss": 0.5795,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039914097378795124,
+      "loss": 0.6287,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039910058481223564,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039905927017329726,
+      "loss": 0.6232,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039901703006321715,
+      "loss": 0.5291,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039897386467837903,
+      "loss": 0.5297,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039892977421946844,
+      "loss": 0.5784,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988847588914718,
+      "loss": 0.5714,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988388189036754,
+      "loss": 0.5044,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987919544696646,
+      "loss": 0.8246,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987441658073226,
+      "loss": 0.5048,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003986954531388297,
+      "loss": 0.5433,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039864581669066186,
+      "loss": 0.5251,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003985952566935902,
+      "loss": 0.5708,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039854377338267936,
+      "loss": 0.6276,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039849136699728684,
+      "loss": 0.4915,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003984380377810617,
+      "loss": 0.6389,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039838378598194325,
+      "loss": 0.6067,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039832861185216045,
+      "loss": 0.6136,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003982725156482301,
+      "loss": 0.5597,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000398215497630956,
+      "loss": 0.5957,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003981575580654278,
+      "loss": 0.5853,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980986972210194,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980389153713881,
+      "loss": 0.5302,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039797821279447307,
+      "loss": 0.5395,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039791658977249425,
+      "loss": 0.7004,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039785404659195084,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039779058354362013,
+      "loss": 0.5759,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000397726200922556,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003976608990280877,
+      "loss": 0.5488,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975946781638183,
+      "loss": 0.6162,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975275386376236,
+      "loss": 0.558,
+      "step": 173
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003974594807616502,
+      "loss": 0.519,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003973905048523144,
+      "loss": 0.6195,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039732061123030064,
+      "loss": 0.5991,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003972498002205601,
+      "loss": 0.5428,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039717807215230896,
+      "loss": 0.5323,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039710542735902705,
+      "loss": 0.5307,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003970318661784564,
+      "loss": 0.5783,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003969573889525993,
+      "loss": 0.5924,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039688199602771714,
+      "loss": 0.5902,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039680568775432855,
+      "loss": 0.6291,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003967284644872077,
+      "loss": 0.5942,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003966503265853829,
+      "loss": 0.4878,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003965712744121347,
+      "loss": 0.6487,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003964913083349945,
+      "loss": 0.6111,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039641042872574233,
+      "loss": 0.6072,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039632863596040575,
+      "loss": 0.716,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039624593041925763,
+      "loss": 0.6178,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003961623124868145,
+      "loss": 0.6323,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039607778255183485,
+      "loss": 0.5821,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959923410073174,
+      "loss": 0.6738,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959059882504989,
+      "loss": 0.6203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039581872468285277,
+      "loss": 0.632,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003957305507100868,
+      "loss": 0.5857,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039564146674214164,
+      "loss": 0.6311,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003955514731931885,
+      "loss": 0.5889,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039546057048162763,
+      "loss": 0.5201,
+      "step": 199
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039536875903008607,
+      "loss": 0.5581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039527603926541586,
+      "loss": 0.5104,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039518241161869193,
+      "loss": 0.5978,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039508787652521013,
+      "loss": 0.6244,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039499243442448536,
+      "loss": 0.589,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003948960857602493,
+      "loss": 0.575,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947988309804485,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947006705372422,
+      "loss": 0.4895,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039460160488700036,
+      "loss": 0.5479,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039450163449030124,
+      "loss": 0.5893,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003944007598119297,
+      "loss": 0.5451,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003942989813208747,
+      "loss": 0.5582,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003941962994903273,
+      "loss": 0.5121,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039409271479767826,
+      "loss": 0.6324,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000393988227724516,
+      "loss": 0.6118,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003938828387566244,
+      "loss": 0.6303,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003937765483839804,
+      "loss": 0.7705,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003936693571007517,
+      "loss": 0.6224,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935612654052946,
+      "loss": 0.5664,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039345227380015163,
+      "loss": 0.66,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039334238279204906,
+      "loss": 0.5582,
+      "step": 220
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039323159289189505,
+      "loss": 0.6087,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003931199046147764,
+      "loss": 0.5566,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039300731847995716,
+      "loss": 0.5775,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039289383501087534,
+      "loss": 0.5081,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277945473514104,
+      "loss": 0.5218,
+      "step": 225
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003926641781845338,
+      "loss": 0.6655,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003925480058950002,
+      "loss": 0.5735,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039243093840665114,
+      "loss": 0.6609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003923129762637596,
+      "loss": 0.7323,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000392194120014758,
+      "loss": 0.5703,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039207437021223583,
+      "loss": 0.6545,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003919537274129366,
+      "loss": 0.521,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039183219217775564,
+      "loss": 0.5257,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003917097650717377,
+      "loss": 0.5487,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039158644666407365,
+      "loss": 0.4861,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039146223752809845,
+      "loss": 0.4928,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003913371382412883,
+      "loss": 0.5253,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039121114938525756,
+      "loss": 0.6155,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039108427154575684,
+      "loss": 0.55,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039095650531266967,
+      "loss": 0.6617,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039082785128000976,
+      "loss": 0.5198,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039069831004591866,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003905678822126625,
+      "loss": 0.5347,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039043656838662946,
+      "loss": 0.531,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039030436917832697,
+      "loss": 0.4884,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039017128520237883,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003900373170775222,
+      "loss": 0.5537,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038990246542660494,
+      "loss": 0.5753,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038976673087658256,
+      "loss": 0.5059,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038963011405851537,
+      "loss": 0.5118,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038949261560756565,
+      "loss": 0.5645,
+      "step": 251
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003893542361629944,
+      "loss": 0.5623,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038921497636815866,
+      "loss": 0.5216,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003890748368705085,
+      "loss": 0.4501,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003889338183215838,
+      "loss": 0.48,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038879192137701135,
+      "loss": 0.5218,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003886491466965018,
+      "loss": 0.5858,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038850549494384685,
+      "loss": 0.6124,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038836096678691536,
+      "loss": 0.4645,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038821556289765136,
+      "loss": 0.474,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038806928395207003,
+      "loss": 0.4364,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038792213063025484,
+      "loss": 0.5821,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003877741036163547,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003876252035985804,
+      "loss": 0.5373,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003874754312692013,
+      "loss": 0.6021,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003873247873245426,
+      "loss": 0.4549,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003871732724649817,
+      "loss": 0.5994,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003870208873949453,
+      "loss": 0.4764,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038686763282290556,
+      "loss": 0.4311,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003867135094613774,
+      "loss": 0.5462,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003865585180269148,
+      "loss": 0.5006,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003864026592401076,
+      "loss": 0.5347,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038624593382557835,
+      "loss": 0.5242,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038608834251197856,
+      "loss": 0.5005,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038592988603198554,
+      "loss": 0.5436,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000385770565122299,
+      "loss": 0.4658,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003856103805236375,
+      "loss": 0.5273,
+      "step": 277
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038544933298073516,
+      "loss": 0.436,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038528742324233804,
+      "loss": 0.4785,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038512465206120086,
+      "loss": 0.5366,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038496102019408324,
+      "loss": 0.4448,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038479652840174637,
+      "loss": 0.5132,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038463117744894955,
+      "loss": 0.7918,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038446496810444627,
+      "loss": 0.5309,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038429790114098114,
+      "loss": 0.5316,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038412997733528576,
+      "loss": 0.4611,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038396119746807563,
+      "loss": 0.4609,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038379156232404613,
+      "loss": 0.5821,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003836210726918691,
+      "loss": 0.5883,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003834497293641889,
+      "loss": 0.5012,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038327753313761913,
+      "loss": 0.4457,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038310448481273867,
+      "loss": 0.4851,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038293058519408787,
+      "loss": 0.5622,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038275583509016507,
+      "loss": 0.5703,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038258023531342265,
+      "loss": 0.5718,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003824037866802632,
+      "loss": 0.5183,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038222649001103614,
+      "loss": 0.5085,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038204834613003323,
+      "loss": 0.5388,
+      "step": 298
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038186935586548537,
+      "loss": 0.5425,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003816895200495584,
+      "loss": 0.447,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003815088395183493,
+      "loss": 0.5541,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038132731511188227,
+      "loss": 0.5518,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000381144947674105,
+      "loss": 0.5074,
+      "step": 303
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003809617380528847,
+      "loss": 0.5134,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003807776871000037,
+      "loss": 0.4599,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003805927956711562,
+      "loss": 0.5838,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038040706462594395,
+      "loss": 0.5216,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038022049482787216,
+      "loss": 0.5323,
+      "step": 308
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003800330871443456,
+      "loss": 0.5681,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00037984484244666446,
+      "loss": 0.4172,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003796557616100207,
+      "loss": 0.4958,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003794658455134934,
+      "loss": 0.662,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003792750950400451,
+      "loss": 0.5832,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003790835110765174,
+      "loss": 0.4271,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003788910945136271,
+      "loss": 0.4842,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037869784624596186,
+      "loss": 0.4656,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037850376717197626,
+      "loss": 0.4981,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037830885819398733,
+      "loss": 0.5162,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037811312021817067,
+      "loss": 0.652,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003779165541545558,
+      "loss": 0.5104,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003777191609170225,
+      "loss": 0.4971,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003775209414232962,
+      "loss": 0.4871,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003773218965949436,
+      "loss": 0.5226,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00037712202735736884,
+      "loss": 0.4823,
+      "step": 324
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003769213346398087,
+      "loss": 0.497,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003767198193753286,
+      "loss": 0.5976,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003765174825008181,
+      "loss": 0.4532,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003763143249569868,
+      "loss": 0.5236,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00037611034768835947,
+      "loss": 0.6513,
+      "step": 329
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037590555164327224,
+      "loss": 0.5686,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037569993777386774,
+      "loss": 0.456,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003754935070360909,
+      "loss": 0.5181,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003752862603896846,
+      "loss": 0.4765,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037507819879818477,
+      "loss": 0.5363,
+      "step": 334
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037486932322891646,
+      "loss": 0.4584,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037465963465298886,
+      "loss": 0.5428,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003744491340452913,
+      "loss": 0.3927,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003742378223844882,
+      "loss": 0.5478,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003740257006530147,
+      "loss": 0.469,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037381276983707246,
+      "loss": 0.5169,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037359903092662434,
+      "loss": 0.4797,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037338448491539054,
+      "loss": 0.5315,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037316913280084353,
+      "loss": 0.4422,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003729529755842035,
+      "loss": 0.4426,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003727360142704337,
+      "loss": 0.4718,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003725182498682361,
+      "loss": 0.5585,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003722996833900459,
+      "loss": 0.4775,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003720803158520279,
+      "loss": 0.6014,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00037186014827407076,
+      "loss": 0.5117,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003716391816797829,
+      "loss": 0.5404,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003714174170964876,
+      "loss": 0.527,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037119485555521796,
+      "loss": 0.4555,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037097149809071255,
+      "loss": 0.5372,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037074734574141016,
+      "loss": 0.5377,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003705223995494454,
+      "loss": 0.4925,
+      "step": 355
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037029666056064345,
+      "loss": 0.482,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037007012982451546,
+      "loss": 0.5235,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00036984280839425356,
+      "loss": 0.4957,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000369614697326726,
+      "loss": 0.5379,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003693857976824721,
+      "loss": 0.4653,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036915611052569785,
+      "loss": 0.469,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003689256369242702,
+      "loss": 0.5618,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003686943779497124,
+      "loss": 0.4459,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003684623346771995,
+      "loss": 0.5606,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003682295081855524,
+      "loss": 0.4368,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036799589955723375,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036776150987834243,
+      "loss": 0.4664,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036752634023860846,
+      "loss": 0.4737,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003672903917313883,
+      "loss": 0.4247,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036705366545365935,
+      "loss": 0.5677,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036681616250601505,
+      "loss": 0.5441,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003665778839926599,
+      "loss": 0.6247,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00036633883102140405,
+      "loss": 0.5217,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003660990047036584,
+      "loss": 0.4651,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003658584061544291,
+      "loss": 0.4648,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003656170364923128,
+      "loss": 0.6048,
+      "step": 376
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036537489683949114,
+      "loss": 0.4515,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003651319883217255,
+      "loss": 0.5096,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036488831206835207,
+      "loss": 0.4231,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036464386921227637,
+      "loss": 0.4903,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036439866088996796,
+      "loss": 0.5131,
+      "step": 381
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003641526882414553,
+      "loss": 0.5986,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003639059524103203,
+      "loss": 0.6,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003636584545436931,
+      "loss": 0.5216,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003634101957922468,
+      "loss": 0.5144,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00036316117731019184,
+      "loss": 0.4963,
+      "step": 386
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003629114002552711,
+      "loss": 0.5657,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036266086578875384,
+      "loss": 0.5028,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003624095750754311,
+      "loss": 0.573,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036215752928360967,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003619047295851068,
+      "loss": 0.656,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036165117715524506,
+      "loss": 0.5129,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036139687317284647,
+      "loss": 0.3945,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003611418188202271,
+      "loss": 0.5318,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036088601528319196,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036062946375102885,
+      "loss": 0.5407,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003603721654165034,
+      "loss": 0.5364,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00036011412147585306,
+      "loss": 0.5407,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003598553331287821,
+      "loss": 0.5999,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003595958015784555,
+      "loss": 0.624,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00035933552803149354,
+      "loss": 0.5351,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003590745136979662,
+      "loss": 0.5196,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035881275979138765,
+      "loss": 0.5447,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003585502675287104,
+      "loss": 0.4908,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035828703813031986,
+      "loss": 0.5172,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035802307282002834,
+      "loss": 0.5923,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003577583728250699,
+      "loss": 0.568,
+      "step": 407
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035749293937609395,
+      "loss": 0.4618,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003572267737071601,
+      "loss": 0.5351,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003569598770557322,
+      "loss": 0.5285,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035669225066267256,
+      "loss": 0.4571,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035642389577223625,
+      "loss": 0.4214,
+      "step": 412
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003561548136320653,
+      "loss": 0.5393,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003558850054931828,
+      "loss": 0.549,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035561447260998714,
+      "loss": 0.4824,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035534321624024656,
+      "loss": 0.6244,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035507123764509245,
+      "loss": 0.5436,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003547985380890144,
+      "loss": 0.5198,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035452511883985366,
+      "loss": 0.5979,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035425098116879754,
+      "loss": 0.4158,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035397612635037356,
+      "loss": 0.5125,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035370055566244334,
+      "loss": 0.4699,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003534242703861966,
+      "loss": 0.5553,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035314727180614573,
+      "loss": 0.5969,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035286956121011897,
+      "loss": 0.456,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003525911398892552,
+      "loss": 0.5195,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003523120091379975,
+      "loss": 0.5187,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035203217025408726,
+      "loss": 0.5443,
+      "step": 428
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003517516245385582,
+      "loss": 0.4476,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003514703732957301,
+      "loss": 0.5757,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035118841783320304,
+      "loss": 0.5129,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035090575946185114,
+      "loss": 0.6354,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035062239949581645,
+      "loss": 0.4065,
+      "step": 433
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000350338339252503,
+      "loss": 0.5472,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00035005358005257045,
+      "loss": 0.5424,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034976812321992816,
+      "loss": 0.6127,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034948197008172877,
+      "loss": 0.63,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003491951219683625,
+      "loss": 0.413,
+      "step": 438
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034890758021345034,
+      "loss": 0.5435,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034861934615383844,
+      "loss": 0.5433,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034833042112959153,
+      "loss": 0.4763,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034804080648398667,
+      "loss": 0.5727,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034775050356350727,
+      "loss": 0.5392,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034745951371783666,
+      "loss": 0.4981,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003471678382998518,
+      "loss": 0.5516,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00034687547866561703,
+      "loss": 0.4965,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003465824361743779,
+      "loss": 0.4982,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003462887121885544,
+      "loss": 0.5619,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003459943080737353,
+      "loss": 0.5273,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034569922519867133,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034540346493526876,
+      "loss": 0.4874,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003451070286585833,
+      "loss": 0.5966,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003448099177468137,
+      "loss": 0.4487,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003445121335812951,
+      "loss": 0.5091,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003442136775464929,
+      "loss": 0.407,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003439145510299958,
+      "loss": 0.6327,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00034361475542251025,
+      "loss": 0.4217,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003433142921178531,
+      "loss": 0.6102,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003430131625129456,
+      "loss": 0.5556,
+      "step": 459
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034271136800780673,
+      "loss": 0.4986,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003424089100055467,
+      "loss": 0.5406,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034210578991236056,
+      "loss": 0.5881,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034180200913752157,
+      "loss": 0.4869,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034149756909337454,
+      "loss": 0.5626,
+      "step": 464
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003411924711953295,
+      "loss": 0.564,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00034088671686185486,
+      "loss": 0.6272,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003405803075144711,
+      "loss": 0.4643,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003402732445777438,
+      "loss": 0.5435,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00033996552947927744,
+      "loss": 0.5844,
+      "step": 469
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003396571636497084,
+      "loss": 0.5362,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033934814852269865,
+      "loss": 0.5607,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003390384855349285,
+      "loss": 0.4836,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033872817612609065,
+      "loss": 0.6555,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033841722173888315,
+      "loss": 0.4784,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033810562381900253,
+      "loss": 0.5583,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033779338381513736,
+      "loss": 0.4679,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003374805031789613,
+      "loss": 0.5325,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033716698336512654,
+      "loss": 0.6601,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000336852825831257,
+      "loss": 0.4838,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003365380320379414,
+      "loss": 0.5588,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033622260344872665,
+      "loss": 0.4596,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003359065415301108,
+      "loss": 0.5228,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033558984775153663,
+      "loss": 0.5316,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033527252358538437,
+      "loss": 0.4761,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003349545705069653,
+      "loss": 0.5254,
+      "step": 485
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003346359899945144,
+      "loss": 0.4786,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033431678352918384,
+      "loss": 0.4302,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003339969525950361,
+      "loss": 0.4914,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033367649867903663,
+      "loss": 0.4102,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003333554232710477,
+      "loss": 0.4698,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003330337278638207,
+      "loss": 0.4454,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033271141395298964,
+      "loss": 0.4648,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033238848303706415,
+      "loss": 0.4616,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033206493661742237,
+      "loss": 0.4861,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033174077619830416,
+      "loss": 0.4797,
+      "step": 495
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033141600328680373,
+      "loss": 0.5104,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033109061939286336,
+      "loss": 0.5712,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033076462602926553,
+      "loss": 0.5425,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033043802471162636,
+      "loss": 0.6156,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003301108169583887,
+      "loss": 0.4282,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003297830042908146,
+      "loss": 0.4088,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032945458823297857,
+      "loss": 0.4866,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003291255703117605,
+      "loss": 0.5045,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003287959520568384,
+      "loss": 0.491,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032846573500068136,
+      "loss": 0.458,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032813492067854246,
+      "loss": 0.4508,
+      "step": 506
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003278035106284516,
+      "loss": 0.4294,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032747150639120834,
+      "loss": 0.4834,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032713890951037477,
+      "loss": 0.3857,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032680572153226834,
+      "loss": 0.4072,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003264719440059545,
+      "loss": 0.4028,
+      "step": 511
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032613757848323977,
+      "loss": 0.3789,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032580262651866446,
+      "loss": 0.4944,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003254670896694952,
+      "loss": 0.4259,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032513096949571805,
+      "loss": 0.5037,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032479426756003093,
+      "loss": 0.5857,
+      "step": 516
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003244569854278366,
+      "loss": 0.5407,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032411912466723524,
+      "loss": 0.499,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003237806868490172,
+      "loss": 0.4359,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032344167354665573,
+      "loss": 0.4374,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003231020863362997,
+      "loss": 0.4172,
+      "step": 521
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000322761926796766,
+      "loss": 0.4451,
+      "step": 522
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003224211965095326,
+      "loss": 0.4,
+      "step": 523
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003220798970587309,
+      "loss": 0.4009,
+      "step": 524
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003217380300311386,
+      "loss": 0.3966,
+      "step": 525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000321395597016172,
+      "loss": 0.4255,
+      "step": 526
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00032105259960587895,
+      "loss": 0.4707,
+      "step": 527
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00032070903939493124,
+      "loss": 0.5313,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003203649179806172,
+      "loss": 0.3596,
+      "step": 529
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003200202369628345,
+      "loss": 0.5223,
+      "step": 530
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031967499794408234,
+      "loss": 0.4146,
+      "step": 531
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031932920252945423,
+      "loss": 0.4328,
+      "step": 532
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003189828523266306,
+      "loss": 0.4258,
+      "step": 533
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031863594894587105,
+      "loss": 0.4457,
+      "step": 534
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003182884940000072,
+      "loss": 0.5249,
+      "step": 535
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003179404891044348,
+      "loss": 0.4751,
+      "step": 536
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031759193587710676,
+      "loss": 0.5378,
+      "step": 537
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031724283593852497,
+      "loss": 0.634,
+      "step": 538
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031689319091173326,
+      "loss": 0.4298,
+      "step": 539
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031654300242230977,
+      "loss": 0.5469,
+      "step": 540
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031619227209835917,
+      "loss": 0.5153,
+      "step": 541
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003158410015705053,
+      "loss": 0.4144,
+      "step": 542
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003154891924718837,
+      "loss": 0.6041,
+      "step": 543
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003151368464381335,
+      "loss": 0.4891,
+      "step": 544
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003147839651073904,
+      "loss": 0.5258,
+      "step": 545
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00031443055012027874,
+      "loss": 0.4351,
+      "step": 546
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000314076603119904,
+      "loss": 0.4556,
+      "step": 547
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031372212575184514,
+      "loss": 0.5445,
+      "step": 548
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031336711966414675,
+      "loss": 0.5585,
+      "step": 549
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003130115865073117,
+      "loss": 0.367,
+      "step": 550
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003126555279342933,
+      "loss": 0.4877,
+      "step": 551
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003122989456004876,
+      "loss": 0.4335,
+      "step": 552
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003119418411637258,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003115842162842663,
+      "loss": 0.4508,
+      "step": 554
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00031122607262478743,
+      "loss": 0.4631,
+      "step": 555
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003108674118503793,
+      "loss": 0.3496,
+      "step": 556
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003105082356285361,
+      "loss": 0.4108,
+      "step": 557
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003101485456291486,
+      "loss": 0.4877,
+      "step": 558
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030978834352449614,
+      "loss": 0.3696,
+      "step": 559
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030942763098923913,
+      "loss": 0.5138,
+      "step": 560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030906640970041084,
+      "loss": 0.5961,
+      "step": 561
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003087046813374099,
+      "loss": 0.3824,
+      "step": 562
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030834244758199276,
+      "loss": 0.4925,
+      "step": 563
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000307979710118265,
+      "loss": 0.4511,
+      "step": 564
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030761647063267457,
+      "loss": 0.4306,
+      "step": 565
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003072527308140031,
+      "loss": 0.468,
+      "step": 566
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030688849235335856,
+      "loss": 0.4842,
+      "step": 567
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003065237569441671,
+      "loss": 0.4332,
+      "step": 568
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030615852628216537,
+      "loss": 0.4637,
+      "step": 569
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003057928020653925,
+      "loss": 0.6193,
+      "step": 570
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003054265859941824,
+      "loss": 0.5033,
+      "step": 571
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030505987977115555,
+      "loss": 0.4185,
+      "step": 572
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003046926851012114,
+      "loss": 0.4211,
+      "step": 573
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003043250036915201,
+      "loss": 0.5089,
+      "step": 574
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00030395683725151505,
+      "loss": 0.517,
+      "step": 575
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003035881874928845,
+      "loss": 0.492,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003032190561295636,
+      "loss": 0.4535,
+      "step": 577
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003028494448777269,
+      "loss": 0.3947,
+      "step": 578
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030247935545577986,
+      "loss": 0.3125,
+      "step": 579
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003021087895843511,
+      "loss": 0.3882,
+      "step": 580
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003017377489862845,
+      "loss": 0.4802,
+      "step": 581
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030136623538663083,
+      "loss": 0.4652,
+      "step": 582
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030099425051263994,
+      "loss": 0.3816,
+      "step": 583
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003006217960937529,
+      "loss": 0.4583,
+      "step": 584
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00030024887386159385,
+      "loss": 0.4568,
+      "step": 585
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029987548554996174,
+      "loss": 0.3908,
+      "step": 586
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002995016328948225,
+      "loss": 0.4235,
+      "step": 587
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029912731763430075,
+      "loss": 0.4138,
+      "step": 588
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029875254150867216,
+      "loss": 0.5838,
+      "step": 589
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002983773062603548,
+      "loss": 0.462,
+      "step": 590
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029800161363390145,
+      "loss": 0.4632,
+      "step": 591
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029762546537599125,
+      "loss": 0.5898,
+      "step": 592
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002972488632354218,
+      "loss": 0.4742,
+      "step": 593
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029687180896310065,
+      "loss": 0.4579,
+      "step": 594
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002964943043120378,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029611635103733675,
+      "loss": 0.4304,
+      "step": 596
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002957379508961871,
+      "loss": 0.4383,
+      "step": 597
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029535910564785584,
+      "loss": 0.5327,
+      "step": 598
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029497981705367933,
+      "loss": 0.4781,
+      "step": 599
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029460008687705525,
+      "loss": 0.4178,
+      "step": 600
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002942199168834342,
+      "loss": 0.3987,
+      "step": 601
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029383930884031183,
+      "loss": 0.3861,
+      "step": 602
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029345826451722005,
+      "loss": 0.5322,
+      "step": 603
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029307678568571936,
+      "loss": 0.3997,
+      "step": 604
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002926948741193903,
+      "loss": 0.4121,
+      "step": 605
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029231253159382514,
+      "loss": 0.4931,
+      "step": 606
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029192975988662017,
+      "loss": 0.4626,
+      "step": 607
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029154656077736666,
+      "loss": 0.4441,
+      "step": 608
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002911629360476432,
+      "loss": 0.3863,
+      "step": 609
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029077888748100703,
+      "loss": 0.36,
+      "step": 610
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029039441686298594,
+      "loss": 0.4246,
+      "step": 611
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002900095259810702,
+      "loss": 0.4916,
+      "step": 612
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028962421662470346,
+      "loss": 0.4896,
+      "step": 613
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028923849058527535,
+      "loss": 0.4237,
+      "step": 614
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028885234965611274,
+      "loss": 0.5727,
+      "step": 615
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028846579563247116,
+      "loss": 0.5681,
+      "step": 616
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002880788303115269,
+      "loss": 0.4383,
+      "step": 617
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028769145549236845,
+      "loss": 0.4962,
+      "step": 618
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002873036729759881,
+      "loss": 0.5472,
+      "step": 619
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002869154845652738,
+      "loss": 0.5431,
+      "step": 620
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002865268920650003,
+      "loss": 0.4152,
+      "step": 621
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002861378972818211,
+      "loss": 0.3922,
+      "step": 622
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002857485020242602,
+      "loss": 0.5129,
+      "step": 623
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002853587081027034,
+      "loss": 0.4328,
+      "step": 624
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00028496851732938997,
+      "loss": 0.4431,
+      "step": 625
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002845779315184042,
+      "loss": 0.4968,
+      "step": 626
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.000284186952485667,
+      "loss": 0.5301,
+      "step": 627
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002837955820489276,
+      "loss": 0.4332,
+      "step": 628
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002834038220277546,
+      "loss": 0.4245,
+      "step": 629
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00028301167424352836,
+      "loss": 0.5057,
+      "step": 630
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028261914051943166,
+      "loss": 0.4623,
+      "step": 631
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028222622268044174,
+      "loss": 0.5452,
+      "step": 632
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028183292255332164,
+      "loss": 0.5238,
+      "step": 633
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028143924196661176,
+      "loss": 0.3966,
+      "step": 634
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002810451827506214,
+      "loss": 0.35,
+      "step": 635
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00028065074673742007,
+      "loss": 0.4325,
+      "step": 636
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0002802559357608292,
+      "loss": 0.4854,
+      "step": 637
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027986075165641343,
+      "loss": 0.4254,
+      "step": 638
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027946519626147225,
+      "loss": 0.4614,
+      "step": 639
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027906927141503125,
+      "loss": 0.3798,
+      "step": 640
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027867297895783373,
+      "loss": 0.4742,
+      "step": 641
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002782763207323322,
+      "loss": 0.4007,
+      "step": 642
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002778792985826795,
+      "loss": 0.4383,
+      "step": 643
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002774819143547206,
+      "loss": 0.4298,
+      "step": 644
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00027708416989598387,
+      "loss": 0.5178,
+      "step": 645
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002766860670556722,
+      "loss": 0.3434,
+      "step": 646
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002762876076846551,
+      "loss": 0.3862,
+      "step": 647
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027588879363545934,
+      "loss": 0.4459,
+      "step": 648
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002754896267622608,
+      "loss": 0.3934,
+      "step": 649
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027509010892087565,
+      "loss": 0.4349,
+      "step": 650
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000274690241968752,
+      "loss": 0.4178,
+      "step": 651
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002742900277649607,
+      "loss": 0.4151,
+      "step": 652
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002738894681701874,
+      "loss": 0.3888,
+      "step": 653
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027348856504672323,
+      "loss": 0.4214,
+      "step": 654
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002730873202584567,
+      "loss": 0.519,
+      "step": 655
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027268573567086477,
+      "loss": 0.5463,
+      "step": 656
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027228381315100417,
+      "loss": 0.3367,
+      "step": 657
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027188155456750256,
+      "loss": 0.4629,
+      "step": 658
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027147896179055043,
+      "loss": 0.4456,
+      "step": 659
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002710760366918917,
+      "loss": 0.4348,
+      "step": 660
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002706727811448153,
+      "loss": 0.4505,
+      "step": 661
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002702691970241468,
+      "loss": 0.5028,
+      "step": 662
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026986528620623904,
+      "loss": 0.5257,
+      "step": 663
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026946105056896403,
+      "loss": 0.4977,
+      "step": 664
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026905649199170377,
+      "loss": 0.421,
+      "step": 665
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002686516123553417,
+      "loss": 0.4931,
+      "step": 666
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026824641354225397,
+      "loss": 0.5818,
+      "step": 667
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002678408974363005,
+      "loss": 0.4211,
+      "step": 668
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026743506592281674,
+      "loss": 0.5182,
+      "step": 669
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026702892088860413,
+      "loss": 0.5591,
+      "step": 670
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002666224642219221,
+      "loss": 0.5363,
+      "step": 671
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002662156978124786,
+      "loss": 0.5866,
+      "step": 672
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002658086235514218,
+      "loss": 0.422,
+      "step": 673
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002654012433313312,
+      "loss": 0.5375,
+      "step": 674
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002649935590462087,
+      "loss": 0.4752,
+      "step": 675
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00026458557259146986,
+      "loss": 0.4271,
+      "step": 676
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002641772858639351,
+      "loss": 0.4843,
+      "step": 677
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026376870076182086,
+      "loss": 0.4827,
+      "step": 678
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026335981918473086,
+      "loss": 0.47,
+      "step": 679
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002629506430336472,
+      "loss": 0.368,
+      "step": 680
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026254117421092133,
+      "loss": 0.481,
+      "step": 681
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002621314146202656,
+      "loss": 0.4153,
+      "step": 682
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002617213661667443,
+      "loss": 0.4397,
+      "step": 683
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002613110307567643,
+      "loss": 0.4052,
+      "step": 684
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026090041029806695,
+      "loss": 0.4652,
+      "step": 685
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026048950669971884,
+      "loss": 0.3826,
+      "step": 686
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026007832187210277,
+      "loss": 0.5639,
+      "step": 687
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025966685772690906,
+      "loss": 0.3917,
+      "step": 688
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025925511617712685,
+      "loss": 0.5248,
+      "step": 689
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002588430991370347,
+      "loss": 0.3796,
+      "step": 690
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002584308085221922,
+      "loss": 0.4391,
+      "step": 691
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025801824624943084,
+      "loss": 0.4514,
+      "step": 692
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025760541423684496,
+      "loss": 0.5046,
+      "step": 693
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002571923144037831,
+      "loss": 0.4578,
+      "step": 694
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002567789486708389,
+      "loss": 0.4681,
+      "step": 695
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025636531895984236,
+      "loss": 0.4501,
+      "step": 696
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002559514271938506,
+      "loss": 0.4411,
+      "step": 697
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025553727529713916,
+      "loss": 0.401,
+      "step": 698
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025512286519519293,
+      "loss": 0.4911,
+      "step": 699
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002547081988146974,
+      "loss": 0.3754,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025429327808352946,
+      "loss": 0.3807,
+      "step": 701
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002538781049307486,
+      "loss": 0.4193,
+      "step": 702
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002534626812865876,
+      "loss": 0.5259,
+      "step": 703
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00025304700908244433,
+      "loss": 0.3684,
+      "step": 704
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002526310902508718,
+      "loss": 0.5423,
+      "step": 705
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002522149267255699,
+      "loss": 0.4288,
+      "step": 706
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.000251798520441376,
+      "loss": 0.5046,
+      "step": 707
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002513818733342564,
+      "loss": 0.3777,
+      "step": 708
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025096498734129667,
+      "loss": 0.5171,
+      "step": 709
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0002505478644006932,
+      "loss": 0.3785,
+      "step": 710
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025013050645174414,
+      "loss": 0.5413,
+      "step": 711
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024971291543483994,
+      "loss": 0.5018,
+      "step": 712
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024929509329145477,
+      "loss": 0.5212,
+      "step": 713
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024887704196413746,
+      "loss": 0.483,
+      "step": 714
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002484587633965023,
+      "loss": 0.3684,
+      "step": 715
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024804025953322005,
+      "loss": 0.3782,
+      "step": 716
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024762153232000877,
+      "loss": 0.4995,
+      "step": 717
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002472025837036253,
+      "loss": 0.4324,
+      "step": 718
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002467834156318555,
+      "loss": 0.5203,
+      "step": 719
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002463640300535057,
+      "loss": 0.423,
+      "step": 720
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002459444289183933,
+      "loss": 0.4537,
+      "step": 721
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00024552461417733817,
+      "loss": 0.4124,
+      "step": 722
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002451045877821528,
+      "loss": 0.4865,
+      "step": 723
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002446843516856343,
+      "loss": 0.4845,
+      "step": 724
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024426390784155425,
+      "loss": 0.4174,
+      "step": 725
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024384325820465033,
+      "loss": 0.4456,
+      "step": 726
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002434224047306169,
+      "loss": 0.4429,
+      "step": 727
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002430013493760961,
+      "loss": 0.363,
+      "step": 728
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024258009409866853,
+      "loss": 0.4769,
+      "step": 729
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024215864085684442,
+      "loss": 0.4597,
+      "step": 730
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024173699161005429,
+      "loss": 0.366,
+      "step": 731
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024131514831863995,
+      "loss": 0.4746,
+      "step": 732
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0002408931129438453,
+      "loss": 0.5608,
+      "step": 733
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024047088744780744,
+      "loss": 0.4292,
+      "step": 734
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00024004847379354726,
+      "loss": 0.4743,
+      "step": 735
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023962587394496038,
+      "loss": 0.3855,
+      "step": 736
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023920308986680834,
+      "loss": 0.4573,
+      "step": 737
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023878012352470892,
+      "loss": 0.3937,
+      "step": 738
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0002383569768851274,
+      "loss": 0.4371,
+      "step": 739
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023793365191536735,
+      "loss": 0.5432,
+      "step": 740
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023751015058356135,
+      "loss": 0.4803,
+      "step": 741
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.000237086474858662,
+      "loss": 0.4281,
+      "step": 742
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023666262671043263,
+      "loss": 0.4031,
+      "step": 743
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023623860810943826,
+      "loss": 0.4725,
+      "step": 744
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0002358144210270364,
+      "loss": 0.4644,
+      "step": 745
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023539006743536774,
+      "loss": 0.4848,
+      "step": 746
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023496554930734718,
+      "loss": 0.4084,
+      "step": 747
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023454086861665472,
+      "loss": 0.4322,
+      "step": 748
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023411602733772595,
+      "loss": 0.4847,
+      "step": 749
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023369102744574312,
+      "loss": 0.4298,
+      "step": 750
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1557,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 1.0028969008307896e+18,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-750/training_args.bin b/checkpoint-750/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbdf20491848d40e9a89bca19c6229b4b2b55e5d
--- /dev/null
+++ b/checkpoint-750/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07819caee47f45203545f962678d52b5954ff1fd4afe1d5152fad48004402099
+size 4155
diff --git a/checkpoint-800/README.md b/checkpoint-800/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b32efe7366f05d1d90816d2ad9e4b06ccca46bea
--- /dev/null
+++ b/checkpoint-800/README.md
@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-800/adapter_config.json b/checkpoint-800/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e108f2da037ef6250457c67a4bedd308d97303c
--- /dev/null
+++ b/checkpoint-800/adapter_config.json
@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-800/adapter_model.bin b/checkpoint-800/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7befcae362857d17a14c827481a23f31fbca9141
--- /dev/null
+++ b/checkpoint-800/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3301ab4b78b8591003f6fa1b7f17c88567d3174caaac84f4f8070f236f32f1
+size 113314765
diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f4d39305f658175907dc3a842d7a3e66c73174c7
--- /dev/null
+++ b/checkpoint-800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0debffdaf52926aebb9acfd67cb9e51dd2e73647f5a198ae6a54038b017ee81a
+size 226653957
diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..79ff41d4f75c9c761b8d216f548088000567ba5d
--- /dev/null
+++ b/checkpoint-800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67ada9a2f7ba8a9056551a898e8d4dffa8326b6a4cc89d38d13d12d8d808021
+size 14575
diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..97f1b41efe321c456bbbba2f102b8b77225b6631
--- /dev/null
+++ b/checkpoint-800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f308f58f5d6fd593a960d76cee3a327399d8ab47d316d9f148d9ef0c6dd55e26
+size 627
diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..f422e5050d1ff6a6b51a7358f7676aa3fd506a0f
--- /dev/null
+++ b/checkpoint-800/trainer_state.json
@@ -0,0 +1,4819 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5411000120351426,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6869,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8396,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7489,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7252,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8022,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.6524,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6981,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7488,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6891,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7968,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6912,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8452,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 0.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6685,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5469,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7915,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.6e-05,
+      "loss": 0.7744,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.6804,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.4e-05,
+      "loss": 0.7796,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.706,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6798,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6333,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 0.6012,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.52,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6583,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.7354,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000116,
+      "loss": 0.6296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 0.6352,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000124,
+      "loss": 0.6007,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5659,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000132,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6639,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 0.5934,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000144,
+      "loss": 0.5233,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000148,
+      "loss": 0.5307,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000152,
+      "loss": 0.5928,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5908,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000164,
+      "loss": 0.5972,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000168,
+      "loss": 0.4825,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000172,
+      "loss": 0.6783,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 0.7633,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5988,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000188,
+      "loss": 0.6658,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000192,
+      "loss": 0.5945,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000196,
+      "loss": 0.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.6057,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.601,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.5566,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.5911,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.7636,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.5537,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000232,
+      "loss": 0.6474,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000236,
+      "loss": 0.6483,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00024,
+      "loss": 0.5021,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000244,
+      "loss": 0.5347,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000248,
+      "loss": 0.5791,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000252,
+      "loss": 0.5407,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.5298,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5685,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000264,
+      "loss": 0.5108,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000268,
+      "loss": 0.526,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6843,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000276,
+      "loss": 0.6608,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00028,
+      "loss": 0.5866,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000284,
+      "loss": 0.6422,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000288,
+      "loss": 0.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000292,
+      "loss": 0.5319,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000296,
+      "loss": 0.5977,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.5805,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000304,
+      "loss": 0.5209,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000308,
+      "loss": 0.6098,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.4665,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6882,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00032,
+      "loss": 0.5427,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000324,
+      "loss": 0.5345,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000328,
+      "loss": 0.663,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000332,
+      "loss": 0.5393,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000336,
+      "loss": 0.5711,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00034,
+      "loss": 0.5261,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000344,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000348,
+      "loss": 0.6329,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.4425,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6837,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00036,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000364,
+      "loss": 0.5615,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5434,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000376,
+      "loss": 0.5583,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00038,
+      "loss": 0.5299,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000384,
+      "loss": 0.532,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000388,
+      "loss": 0.5227,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000392,
+      "loss": 0.5275,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.4541,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004,
+      "loss": 0.6485,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003999995350775973,
+      "loss": 0.5438,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999814031255063,
+      "loss": 0.5997,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999581571134455,
+      "loss": 0.5322,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003999925612847867,
+      "loss": 0.484,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998837704800766,
+      "loss": 0.5961,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998326302046085,
+      "loss": 0.7405,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997721922592255,
+      "loss": 0.5802,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997024569249167,
+      "loss": 0.769,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999623424525898,
+      "loss": 0.5598,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999535095429608,
+      "loss": 0.6143,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039994374700467095,
+      "loss": 0.5766,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039993305488310836,
+      "loss": 0.7695,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999214332279831,
+      "loss": 0.7153,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999088820933269,
+      "loss": 0.5835,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039989540153749286,
+      "loss": 0.6634,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000399880991623155,
+      "loss": 0.6069,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998656524173082,
+      "loss": 0.7224,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000399849383991268,
+      "loss": 0.5884,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998321864206699,
+      "loss": 0.5122,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039981405978546924,
+      "loss": 0.6453,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997950041699408,
+      "loss": 0.4665,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997750196626785,
+      "loss": 0.5428,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039975410635659464,
+      "loss": 0.4365,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039973226434891995,
+      "loss": 0.5978,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039970949374120286,
+      "loss": 0.7729,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000399685794639309,
+      "loss": 0.6212,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039966116715342066,
+      "loss": 0.5426,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00039963561139803676,
+      "loss": 0.5782,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003996091274919716,
+      "loss": 0.6701,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995817155583548,
+      "loss": 0.6314,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995533757246307,
+      "loss": 0.6662,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995241081225573,
+      "loss": 0.5192,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994939128882065,
+      "loss": 0.5591,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994627901619625,
+      "loss": 0.5809,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994307400885219,
+      "loss": 0.4871,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993977628168928,
+      "loss": 0.6666,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993638585003938,
+      "loss": 0.6469,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039932902729665357,
+      "loss": 0.5727,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039929326936761036,
+      "loss": 0.6715,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039925658487951067,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039921897400290894,
+      "loss": 0.501,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039918043691266665,
+      "loss": 0.5795,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039914097378795124,
+      "loss": 0.6287,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039910058481223564,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039905927017329726,
+      "loss": 0.6232,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039901703006321715,
+      "loss": 0.5291,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039897386467837903,
+      "loss": 0.5297,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039892977421946844,
+      "loss": 0.5784,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988847588914718,
+      "loss": 0.5714,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988388189036754,
+      "loss": 0.5044,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987919544696646,
+      "loss": 0.8246,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987441658073226,
+      "loss": 0.5048,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003986954531388297,
+      "loss": 0.5433,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039864581669066186,
+      "loss": 0.5251,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003985952566935902,
+      "loss": 0.5708,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039854377338267936,
+      "loss": 0.6276,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039849136699728684,
+      "loss": 0.4915,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003984380377810617,
+      "loss": 0.6389,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039838378598194325,
+      "loss": 0.6067,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039832861185216045,
+      "loss": 0.6136,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003982725156482301,
+      "loss": 0.5597,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000398215497630956,
+      "loss": 0.5957,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003981575580654278,
+      "loss": 0.5853,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980986972210194,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980389153713881,
+      "loss": 0.5302,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039797821279447307,
+      "loss": 0.5395,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039791658977249425,
+      "loss": 0.7004,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039785404659195084,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039779058354362013,
+      "loss": 0.5759,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000397726200922556,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003976608990280877,
+      "loss": 0.5488,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975946781638183,
+      "loss": 0.6162,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975275386376236,
+      "loss": 0.558,
+      "step": 173
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003974594807616502,
+      "loss": 0.519,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003973905048523144,
+      "loss": 0.6195,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039732061123030064,
+      "loss": 0.5991,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003972498002205601,
+      "loss": 0.5428,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039717807215230896,
+      "loss": 0.5323,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039710542735902705,
+      "loss": 0.5307,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003970318661784564,
+      "loss": 0.5783,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003969573889525993,
+      "loss": 0.5924,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039688199602771714,
+      "loss": 0.5902,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039680568775432855,
+      "loss": 0.6291,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003967284644872077,
+      "loss": 0.5942,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003966503265853829,
+      "loss": 0.4878,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003965712744121347,
+      "loss": 0.6487,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003964913083349945,
+      "loss": 0.6111,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039641042872574233,
+      "loss": 0.6072,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039632863596040575,
+      "loss": 0.716,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039624593041925763,
+      "loss": 0.6178,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003961623124868145,
+      "loss": 0.6323,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039607778255183485,
+      "loss": 0.5821,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959923410073174,
+      "loss": 0.6738,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959059882504989,
+      "loss": 0.6203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039581872468285277,
+      "loss": 0.632,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003957305507100868,
+      "loss": 0.5857,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039564146674214164,
+      "loss": 0.6311,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003955514731931885,
+      "loss": 0.5889,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039546057048162763,
+      "loss": 0.5201,
+      "step": 199
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039536875903008607,
+      "loss": 0.5581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039527603926541586,
+      "loss": 0.5104,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039518241161869193,
+      "loss": 0.5978,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039508787652521013,
+      "loss": 0.6244,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039499243442448536,
+      "loss": 0.589,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003948960857602493,
+      "loss": 0.575,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947988309804485,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947006705372422,
+      "loss": 0.4895,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039460160488700036,
+      "loss": 0.5479,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039450163449030124,
+      "loss": 0.5893,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003944007598119297,
+      "loss": 0.5451,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003942989813208747,
+      "loss": 0.5582,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003941962994903273,
+      "loss": 0.5121,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039409271479767826,
+      "loss": 0.6324,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000393988227724516,
+      "loss": 0.6118,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003938828387566244,
+      "loss": 0.6303,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003937765483839804,
+      "loss": 0.7705,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003936693571007517,
+      "loss": 0.6224,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935612654052946,
+      "loss": 0.5664,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039345227380015163,
+      "loss": 0.66,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039334238279204906,
+      "loss": 0.5582,
+      "step": 220
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039323159289189505,
+      "loss": 0.6087,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003931199046147764,
+      "loss": 0.5566,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039300731847995716,
+      "loss": 0.5775,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039289383501087534,
+      "loss": 0.5081,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277945473514104,
+      "loss": 0.5218,
+      "step": 225
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003926641781845338,
+      "loss": 0.6655,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003925480058950002,
+      "loss": 0.5735,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039243093840665114,
+      "loss": 0.6609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003923129762637596,
+      "loss": 0.7323,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000392194120014758,
+      "loss": 0.5703,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039207437021223583,
+      "loss": 0.6545,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003919537274129366,
+      "loss": 0.521,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039183219217775564,
+      "loss": 0.5257,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003917097650717377,
+      "loss": 0.5487,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039158644666407365,
+      "loss": 0.4861,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039146223752809845,
+      "loss": 0.4928,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003913371382412883,
+      "loss": 0.5253,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039121114938525756,
+      "loss": 0.6155,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039108427154575684,
+      "loss": 0.55,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039095650531266967,
+      "loss": 0.6617,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039082785128000976,
+      "loss": 0.5198,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039069831004591866,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003905678822126625,
+      "loss": 0.5347,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039043656838662946,
+      "loss": 0.531,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039030436917832697,
+      "loss": 0.4884,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039017128520237883,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003900373170775222,
+      "loss": 0.5537,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038990246542660494,
+      "loss": 0.5753,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038976673087658256,
+      "loss": 0.5059,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038963011405851537,
+      "loss": 0.5118,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038949261560756565,
+      "loss": 0.5645,
+      "step": 251
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003893542361629944,
+      "loss": 0.5623,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038921497636815866,
+      "loss": 0.5216,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003890748368705085,
+      "loss": 0.4501,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003889338183215838,
+      "loss": 0.48,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038879192137701135,
+      "loss": 0.5218,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003886491466965018,
+      "loss": 0.5858,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038850549494384685,
+      "loss": 0.6124,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038836096678691536,
+      "loss": 0.4645,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038821556289765136,
+      "loss": 0.474,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038806928395207003,
+      "loss": 0.4364,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038792213063025484,
+      "loss": 0.5821,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003877741036163547,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003876252035985804,
+      "loss": 0.5373,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003874754312692013,
+      "loss": 0.6021,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003873247873245426,
+      "loss": 0.4549,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003871732724649817,
+      "loss": 0.5994,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003870208873949453,
+      "loss": 0.4764,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038686763282290556,
+      "loss": 0.4311,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003867135094613774,
+      "loss": 0.5462,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003865585180269148,
+      "loss": 0.5006,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003864026592401076,
+      "loss": 0.5347,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038624593382557835,
+      "loss": 0.5242,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038608834251197856,
+      "loss": 0.5005,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038592988603198554,
+      "loss": 0.5436,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000385770565122299,
+      "loss": 0.4658,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003856103805236375,
+      "loss": 0.5273,
+      "step": 277
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038544933298073516,
+      "loss": 0.436,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038528742324233804,
+      "loss": 0.4785,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038512465206120086,
+      "loss": 0.5366,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038496102019408324,
+      "loss": 0.4448,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038479652840174637,
+      "loss": 0.5132,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038463117744894955,
+      "loss": 0.7918,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038446496810444627,
+      "loss": 0.5309,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038429790114098114,
+      "loss": 0.5316,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038412997733528576,
+      "loss": 0.4611,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038396119746807563,
+      "loss": 0.4609,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038379156232404613,
+      "loss": 0.5821,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003836210726918691,
+      "loss": 0.5883,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003834497293641889,
+      "loss": 0.5012,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038327753313761913,
+      "loss": 0.4457,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038310448481273867,
+      "loss": 0.4851,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038293058519408787,
+      "loss": 0.5622,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038275583509016507,
+      "loss": 0.5703,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038258023531342265,
+      "loss": 0.5718,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003824037866802632,
+      "loss": 0.5183,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038222649001103614,
+      "loss": 0.5085,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038204834613003323,
+      "loss": 0.5388,
+      "step": 298
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038186935586548537,
+      "loss": 0.5425,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003816895200495584,
+      "loss": 0.447,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003815088395183493,
+      "loss": 0.5541,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038132731511188227,
+      "loss": 0.5518,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000381144947674105,
+      "loss": 0.5074,
+      "step": 303
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003809617380528847,
+      "loss": 0.5134,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003807776871000037,
+      "loss": 0.4599,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003805927956711562,
+      "loss": 0.5838,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038040706462594395,
+      "loss": 0.5216,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038022049482787216,
+      "loss": 0.5323,
+      "step": 308
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003800330871443456,
+      "loss": 0.5681,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00037984484244666446,
+      "loss": 0.4172,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003796557616100207,
+      "loss": 0.4958,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003794658455134934,
+      "loss": 0.662,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003792750950400451,
+      "loss": 0.5832,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003790835110765174,
+      "loss": 0.4271,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003788910945136271,
+      "loss": 0.4842,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037869784624596186,
+      "loss": 0.4656,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037850376717197626,
+      "loss": 0.4981,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037830885819398733,
+      "loss": 0.5162,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037811312021817067,
+      "loss": 0.652,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003779165541545558,
+      "loss": 0.5104,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003777191609170225,
+      "loss": 0.4971,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003775209414232962,
+      "loss": 0.4871,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003773218965949436,
+      "loss": 0.5226,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00037712202735736884,
+      "loss": 0.4823,
+      "step": 324
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003769213346398087,
+      "loss": 0.497,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003767198193753286,
+      "loss": 0.5976,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003765174825008181,
+      "loss": 0.4532,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003763143249569868,
+      "loss": 0.5236,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00037611034768835947,
+      "loss": 0.6513,
+      "step": 329
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037590555164327224,
+      "loss": 0.5686,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037569993777386774,
+      "loss": 0.456,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003754935070360909,
+      "loss": 0.5181,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003752862603896846,
+      "loss": 0.4765,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037507819879818477,
+      "loss": 0.5363,
+      "step": 334
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037486932322891646,
+      "loss": 0.4584,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037465963465298886,
+      "loss": 0.5428,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003744491340452913,
+      "loss": 0.3927,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003742378223844882,
+      "loss": 0.5478,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003740257006530147,
+      "loss": 0.469,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037381276983707246,
+      "loss": 0.5169,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037359903092662434,
+      "loss": 0.4797,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037338448491539054,
+      "loss": 0.5315,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037316913280084353,
+      "loss": 0.4422,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003729529755842035,
+      "loss": 0.4426,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003727360142704337,
+      "loss": 0.4718,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003725182498682361,
+      "loss": 0.5585,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003722996833900459,
+      "loss": 0.4775,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003720803158520279,
+      "loss": 0.6014,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00037186014827407076,
+      "loss": 0.5117,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003716391816797829,
+      "loss": 0.5404,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003714174170964876,
+      "loss": 0.527,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037119485555521796,
+      "loss": 0.4555,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037097149809071255,
+      "loss": 0.5372,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037074734574141016,
+      "loss": 0.5377,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003705223995494454,
+      "loss": 0.4925,
+      "step": 355
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037029666056064345,
+      "loss": 0.482,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037007012982451546,
+      "loss": 0.5235,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00036984280839425356,
+      "loss": 0.4957,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000369614697326726,
+      "loss": 0.5379,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003693857976824721,
+      "loss": 0.4653,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036915611052569785,
+      "loss": 0.469,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003689256369242702,
+      "loss": 0.5618,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003686943779497124,
+      "loss": 0.4459,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003684623346771995,
+      "loss": 0.5606,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003682295081855524,
+      "loss": 0.4368,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036799589955723375,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036776150987834243,
+      "loss": 0.4664,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036752634023860846,
+      "loss": 0.4737,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003672903917313883,
+      "loss": 0.4247,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036705366545365935,
+      "loss": 0.5677,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036681616250601505,
+      "loss": 0.5441,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003665778839926599,
+      "loss": 0.6247,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00036633883102140405,
+      "loss": 0.5217,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003660990047036584,
+      "loss": 0.4651,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003658584061544291,
+      "loss": 0.4648,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003656170364923128,
+      "loss": 0.6048,
+      "step": 376
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036537489683949114,
+      "loss": 0.4515,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003651319883217255,
+      "loss": 0.5096,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036488831206835207,
+      "loss": 0.4231,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036464386921227637,
+      "loss": 0.4903,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036439866088996796,
+      "loss": 0.5131,
+      "step": 381
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003641526882414553,
+      "loss": 0.5986,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003639059524103203,
+      "loss": 0.6,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003636584545436931,
+      "loss": 0.5216,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003634101957922468,
+      "loss": 0.5144,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00036316117731019184,
+      "loss": 0.4963,
+      "step": 386
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003629114002552711,
+      "loss": 0.5657,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036266086578875384,
+      "loss": 0.5028,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003624095750754311,
+      "loss": 0.573,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036215752928360967,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003619047295851068,
+      "loss": 0.656,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036165117715524506,
+      "loss": 0.5129,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036139687317284647,
+      "loss": 0.3945,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003611418188202271,
+      "loss": 0.5318,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036088601528319196,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036062946375102885,
+      "loss": 0.5407,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003603721654165034,
+      "loss": 0.5364,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00036011412147585306,
+      "loss": 0.5407,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003598553331287821,
+      "loss": 0.5999,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003595958015784555,
+      "loss": 0.624,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00035933552803149354,
+      "loss": 0.5351,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003590745136979662,
+      "loss": 0.5196,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035881275979138765,
+      "loss": 0.5447,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003585502675287104,
+      "loss": 0.4908,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035828703813031986,
+      "loss": 0.5172,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035802307282002834,
+      "loss": 0.5923,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003577583728250699,
+      "loss": 0.568,
+      "step": 407
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035749293937609395,
+      "loss": 0.4618,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003572267737071601,
+      "loss": 0.5351,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003569598770557322,
+      "loss": 0.5285,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035669225066267256,
+      "loss": 0.4571,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035642389577223625,
+      "loss": 0.4214,
+      "step": 412
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003561548136320653,
+      "loss": 0.5393,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003558850054931828,
+      "loss": 0.549,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035561447260998714,
+      "loss": 0.4824,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035534321624024656,
+      "loss": 0.6244,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035507123764509245,
+      "loss": 0.5436,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003547985380890144,
+      "loss": 0.5198,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035452511883985366,
+      "loss": 0.5979,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035425098116879754,
+      "loss": 0.4158,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035397612635037356,
+      "loss": 0.5125,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035370055566244334,
+      "loss": 0.4699,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003534242703861966,
+      "loss": 0.5553,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035314727180614573,
+      "loss": 0.5969,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035286956121011897,
+      "loss": 0.456,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003525911398892552,
+      "loss": 0.5195,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003523120091379975,
+      "loss": 0.5187,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035203217025408726,
+      "loss": 0.5443,
+      "step": 428
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003517516245385582,
+      "loss": 0.4476,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003514703732957301,
+      "loss": 0.5757,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035118841783320304,
+      "loss": 0.5129,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035090575946185114,
+      "loss": 0.6354,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035062239949581645,
+      "loss": 0.4065,
+      "step": 433
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000350338339252503,
+      "loss": 0.5472,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00035005358005257045,
+      "loss": 0.5424,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034976812321992816,
+      "loss": 0.6127,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034948197008172877,
+      "loss": 0.63,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003491951219683625,
+      "loss": 0.413,
+      "step": 438
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034890758021345034,
+      "loss": 0.5435,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034861934615383844,
+      "loss": 0.5433,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034833042112959153,
+      "loss": 0.4763,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034804080648398667,
+      "loss": 0.5727,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034775050356350727,
+      "loss": 0.5392,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034745951371783666,
+      "loss": 0.4981,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003471678382998518,
+      "loss": 0.5516,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00034687547866561703,
+      "loss": 0.4965,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003465824361743779,
+      "loss": 0.4982,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003462887121885544,
+      "loss": 0.5619,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003459943080737353,
+      "loss": 0.5273,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034569922519867133,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034540346493526876,
+      "loss": 0.4874,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003451070286585833,
+      "loss": 0.5966,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003448099177468137,
+      "loss": 0.4487,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003445121335812951,
+      "loss": 0.5091,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003442136775464929,
+      "loss": 0.407,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003439145510299958,
+      "loss": 0.6327,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00034361475542251025,
+      "loss": 0.4217,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003433142921178531,
+      "loss": 0.6102,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003430131625129456,
+      "loss": 0.5556,
+      "step": 459
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034271136800780673,
+      "loss": 0.4986,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003424089100055467,
+      "loss": 0.5406,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034210578991236056,
+      "loss": 0.5881,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034180200913752157,
+      "loss": 0.4869,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034149756909337454,
+      "loss": 0.5626,
+      "step": 464
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003411924711953295,
+      "loss": 0.564,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00034088671686185486,
+      "loss": 0.6272,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003405803075144711,
+      "loss": 0.4643,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003402732445777438,
+      "loss": 0.5435,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00033996552947927744,
+      "loss": 0.5844,
+      "step": 469
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003396571636497084,
+      "loss": 0.5362,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033934814852269865,
+      "loss": 0.5607,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003390384855349285,
+      "loss": 0.4836,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033872817612609065,
+      "loss": 0.6555,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033841722173888315,
+      "loss": 0.4784,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033810562381900253,
+      "loss": 0.5583,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033779338381513736,
+      "loss": 0.4679,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003374805031789613,
+      "loss": 0.5325,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033716698336512654,
+      "loss": 0.6601,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000336852825831257,
+      "loss": 0.4838,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003365380320379414,
+      "loss": 0.5588,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033622260344872665,
+      "loss": 0.4596,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003359065415301108,
+      "loss": 0.5228,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033558984775153663,
+      "loss": 0.5316,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033527252358538437,
+      "loss": 0.4761,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003349545705069653,
+      "loss": 0.5254,
+      "step": 485
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003346359899945144,
+      "loss": 0.4786,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033431678352918384,
+      "loss": 0.4302,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003339969525950361,
+      "loss": 0.4914,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033367649867903663,
+      "loss": 0.4102,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003333554232710477,
+      "loss": 0.4698,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003330337278638207,
+      "loss": 0.4454,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033271141395298964,
+      "loss": 0.4648,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033238848303706415,
+      "loss": 0.4616,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033206493661742237,
+      "loss": 0.4861,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033174077619830416,
+      "loss": 0.4797,
+      "step": 495
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033141600328680373,
+      "loss": 0.5104,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033109061939286336,
+      "loss": 0.5712,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033076462602926553,
+      "loss": 0.5425,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033043802471162636,
+      "loss": 0.6156,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003301108169583887,
+      "loss": 0.4282,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003297830042908146,
+      "loss": 0.4088,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032945458823297857,
+      "loss": 0.4866,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003291255703117605,
+      "loss": 0.5045,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003287959520568384,
+      "loss": 0.491,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032846573500068136,
+      "loss": 0.458,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032813492067854246,
+      "loss": 0.4508,
+      "step": 506
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003278035106284516,
+      "loss": 0.4294,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032747150639120834,
+      "loss": 0.4834,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032713890951037477,
+      "loss": 0.3857,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032680572153226834,
+      "loss": 0.4072,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003264719440059545,
+      "loss": 0.4028,
+      "step": 511
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032613757848323977,
+      "loss": 0.3789,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032580262651866446,
+      "loss": 0.4944,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003254670896694952,
+      "loss": 0.4259,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032513096949571805,
+      "loss": 0.5037,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032479426756003093,
+      "loss": 0.5857,
+      "step": 516
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003244569854278366,
+      "loss": 0.5407,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032411912466723524,
+      "loss": 0.499,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003237806868490172,
+      "loss": 0.4359,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032344167354665573,
+      "loss": 0.4374,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003231020863362997,
+      "loss": 0.4172,
+      "step": 521
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000322761926796766,
+      "loss": 0.4451,
+      "step": 522
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003224211965095326,
+      "loss": 0.4,
+      "step": 523
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003220798970587309,
+      "loss": 0.4009,
+      "step": 524
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003217380300311386,
+      "loss": 0.3966,
+      "step": 525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000321395597016172,
+      "loss": 0.4255,
+      "step": 526
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00032105259960587895,
+      "loss": 0.4707,
+      "step": 527
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00032070903939493124,
+      "loss": 0.5313,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003203649179806172,
+      "loss": 0.3596,
+      "step": 529
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003200202369628345,
+      "loss": 0.5223,
+      "step": 530
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031967499794408234,
+      "loss": 0.4146,
+      "step": 531
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031932920252945423,
+      "loss": 0.4328,
+      "step": 532
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003189828523266306,
+      "loss": 0.4258,
+      "step": 533
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031863594894587105,
+      "loss": 0.4457,
+      "step": 534
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003182884940000072,
+      "loss": 0.5249,
+      "step": 535
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003179404891044348,
+      "loss": 0.4751,
+      "step": 536
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031759193587710676,
+      "loss": 0.5378,
+      "step": 537
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031724283593852497,
+      "loss": 0.634,
+      "step": 538
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031689319091173326,
+      "loss": 0.4298,
+      "step": 539
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031654300242230977,
+      "loss": 0.5469,
+      "step": 540
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031619227209835917,
+      "loss": 0.5153,
+      "step": 541
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003158410015705053,
+      "loss": 0.4144,
+      "step": 542
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003154891924718837,
+      "loss": 0.6041,
+      "step": 543
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003151368464381335,
+      "loss": 0.4891,
+      "step": 544
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003147839651073904,
+      "loss": 0.5258,
+      "step": 545
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00031443055012027874,
+      "loss": 0.4351,
+      "step": 546
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000314076603119904,
+      "loss": 0.4556,
+      "step": 547
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031372212575184514,
+      "loss": 0.5445,
+      "step": 548
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031336711966414675,
+      "loss": 0.5585,
+      "step": 549
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003130115865073117,
+      "loss": 0.367,
+      "step": 550
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003126555279342933,
+      "loss": 0.4877,
+      "step": 551
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003122989456004876,
+      "loss": 0.4335,
+      "step": 552
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003119418411637258,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003115842162842663,
+      "loss": 0.4508,
+      "step": 554
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00031122607262478743,
+      "loss": 0.4631,
+      "step": 555
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003108674118503793,
+      "loss": 0.3496,
+      "step": 556
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003105082356285361,
+      "loss": 0.4108,
+      "step": 557
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003101485456291486,
+      "loss": 0.4877,
+      "step": 558
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030978834352449614,
+      "loss": 0.3696,
+      "step": 559
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030942763098923913,
+      "loss": 0.5138,
+      "step": 560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030906640970041084,
+      "loss": 0.5961,
+      "step": 561
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003087046813374099,
+      "loss": 0.3824,
+      "step": 562
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030834244758199276,
+      "loss": 0.4925,
+      "step": 563
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000307979710118265,
+      "loss": 0.4511,
+      "step": 564
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030761647063267457,
+      "loss": 0.4306,
+      "step": 565
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003072527308140031,
+      "loss": 0.468,
+      "step": 566
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030688849235335856,
+      "loss": 0.4842,
+      "step": 567
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003065237569441671,
+      "loss": 0.4332,
+      "step": 568
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030615852628216537,
+      "loss": 0.4637,
+      "step": 569
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003057928020653925,
+      "loss": 0.6193,
+      "step": 570
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003054265859941824,
+      "loss": 0.5033,
+      "step": 571
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030505987977115555,
+      "loss": 0.4185,
+      "step": 572
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003046926851012114,
+      "loss": 0.4211,
+      "step": 573
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003043250036915201,
+      "loss": 0.5089,
+      "step": 574
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00030395683725151505,
+      "loss": 0.517,
+      "step": 575
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003035881874928845,
+      "loss": 0.492,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003032190561295636,
+      "loss": 0.4535,
+      "step": 577
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003028494448777269,
+      "loss": 0.3947,
+      "step": 578
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030247935545577986,
+      "loss": 0.3125,
+      "step": 579
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003021087895843511,
+      "loss": 0.3882,
+      "step": 580
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003017377489862845,
+      "loss": 0.4802,
+      "step": 581
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030136623538663083,
+      "loss": 0.4652,
+      "step": 582
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030099425051263994,
+      "loss": 0.3816,
+      "step": 583
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003006217960937529,
+      "loss": 0.4583,
+      "step": 584
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00030024887386159385,
+      "loss": 0.4568,
+      "step": 585
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029987548554996174,
+      "loss": 0.3908,
+      "step": 586
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002995016328948225,
+      "loss": 0.4235,
+      "step": 587
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029912731763430075,
+      "loss": 0.4138,
+      "step": 588
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029875254150867216,
+      "loss": 0.5838,
+      "step": 589
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002983773062603548,
+      "loss": 0.462,
+      "step": 590
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029800161363390145,
+      "loss": 0.4632,
+      "step": 591
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029762546537599125,
+      "loss": 0.5898,
+      "step": 592
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002972488632354218,
+      "loss": 0.4742,
+      "step": 593
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029687180896310065,
+      "loss": 0.4579,
+      "step": 594
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002964943043120378,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029611635103733675,
+      "loss": 0.4304,
+      "step": 596
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002957379508961871,
+      "loss": 0.4383,
+      "step": 597
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029535910564785584,
+      "loss": 0.5327,
+      "step": 598
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029497981705367933,
+      "loss": 0.4781,
+      "step": 599
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029460008687705525,
+      "loss": 0.4178,
+      "step": 600
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002942199168834342,
+      "loss": 0.3987,
+      "step": 601
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029383930884031183,
+      "loss": 0.3861,
+      "step": 602
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029345826451722005,
+      "loss": 0.5322,
+      "step": 603
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029307678568571936,
+      "loss": 0.3997,
+      "step": 604
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002926948741193903,
+      "loss": 0.4121,
+      "step": 605
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029231253159382514,
+      "loss": 0.4931,
+      "step": 606
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029192975988662017,
+      "loss": 0.4626,
+      "step": 607
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029154656077736666,
+      "loss": 0.4441,
+      "step": 608
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002911629360476432,
+      "loss": 0.3863,
+      "step": 609
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029077888748100703,
+      "loss": 0.36,
+      "step": 610
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029039441686298594,
+      "loss": 0.4246,
+      "step": 611
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002900095259810702,
+      "loss": 0.4916,
+      "step": 612
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028962421662470346,
+      "loss": 0.4896,
+      "step": 613
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028923849058527535,
+      "loss": 0.4237,
+      "step": 614
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028885234965611274,
+      "loss": 0.5727,
+      "step": 615
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028846579563247116,
+      "loss": 0.5681,
+      "step": 616
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002880788303115269,
+      "loss": 0.4383,
+      "step": 617
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028769145549236845,
+      "loss": 0.4962,
+      "step": 618
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002873036729759881,
+      "loss": 0.5472,
+      "step": 619
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002869154845652738,
+      "loss": 0.5431,
+      "step": 620
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002865268920650003,
+      "loss": 0.4152,
+      "step": 621
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002861378972818211,
+      "loss": 0.3922,
+      "step": 622
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002857485020242602,
+      "loss": 0.5129,
+      "step": 623
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002853587081027034,
+      "loss": 0.4328,
+      "step": 624
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00028496851732938997,
+      "loss": 0.4431,
+      "step": 625
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002845779315184042,
+      "loss": 0.4968,
+      "step": 626
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.000284186952485667,
+      "loss": 0.5301,
+      "step": 627
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002837955820489276,
+      "loss": 0.4332,
+      "step": 628
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002834038220277546,
+      "loss": 0.4245,
+      "step": 629
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00028301167424352836,
+      "loss": 0.5057,
+      "step": 630
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028261914051943166,
+      "loss": 0.4623,
+      "step": 631
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028222622268044174,
+      "loss": 0.5452,
+      "step": 632
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028183292255332164,
+      "loss": 0.5238,
+      "step": 633
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028143924196661176,
+      "loss": 0.3966,
+      "step": 634
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002810451827506214,
+      "loss": 0.35,
+      "step": 635
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00028065074673742007,
+      "loss": 0.4325,
+      "step": 636
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0002802559357608292,
+      "loss": 0.4854,
+      "step": 637
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027986075165641343,
+      "loss": 0.4254,
+      "step": 638
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027946519626147225,
+      "loss": 0.4614,
+      "step": 639
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027906927141503125,
+      "loss": 0.3798,
+      "step": 640
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027867297895783373,
+      "loss": 0.4742,
+      "step": 641
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002782763207323322,
+      "loss": 0.4007,
+      "step": 642
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002778792985826795,
+      "loss": 0.4383,
+      "step": 643
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002774819143547206,
+      "loss": 0.4298,
+      "step": 644
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00027708416989598387,
+      "loss": 0.5178,
+      "step": 645
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002766860670556722,
+      "loss": 0.3434,
+      "step": 646
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002762876076846551,
+      "loss": 0.3862,
+      "step": 647
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027588879363545934,
+      "loss": 0.4459,
+      "step": 648
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002754896267622608,
+      "loss": 0.3934,
+      "step": 649
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027509010892087565,
+      "loss": 0.4349,
+      "step": 650
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000274690241968752,
+      "loss": 0.4178,
+      "step": 651
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002742900277649607,
+      "loss": 0.4151,
+      "step": 652
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002738894681701874,
+      "loss": 0.3888,
+      "step": 653
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027348856504672323,
+      "loss": 0.4214,
+      "step": 654
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002730873202584567,
+      "loss": 0.519,
+      "step": 655
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027268573567086477,
+      "loss": 0.5463,
+      "step": 656
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027228381315100417,
+      "loss": 0.3367,
+      "step": 657
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027188155456750256,
+      "loss": 0.4629,
+      "step": 658
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027147896179055043,
+      "loss": 0.4456,
+      "step": 659
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002710760366918917,
+      "loss": 0.4348,
+      "step": 660
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002706727811448153,
+      "loss": 0.4505,
+      "step": 661
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002702691970241468,
+      "loss": 0.5028,
+      "step": 662
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026986528620623904,
+      "loss": 0.5257,
+      "step": 663
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026946105056896403,
+      "loss": 0.4977,
+      "step": 664
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026905649199170377,
+      "loss": 0.421,
+      "step": 665
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002686516123553417,
+      "loss": 0.4931,
+      "step": 666
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026824641354225397,
+      "loss": 0.5818,
+      "step": 667
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002678408974363005,
+      "loss": 0.4211,
+      "step": 668
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026743506592281674,
+      "loss": 0.5182,
+      "step": 669
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026702892088860413,
+      "loss": 0.5591,
+      "step": 670
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002666224642219221,
+      "loss": 0.5363,
+      "step": 671
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002662156978124786,
+      "loss": 0.5866,
+      "step": 672
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002658086235514218,
+      "loss": 0.422,
+      "step": 673
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002654012433313312,
+      "loss": 0.5375,
+      "step": 674
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002649935590462087,
+      "loss": 0.4752,
+      "step": 675
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00026458557259146986,
+      "loss": 0.4271,
+      "step": 676
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002641772858639351,
+      "loss": 0.4843,
+      "step": 677
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026376870076182086,
+      "loss": 0.4827,
+      "step": 678
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026335981918473086,
+      "loss": 0.47,
+      "step": 679
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002629506430336472,
+      "loss": 0.368,
+      "step": 680
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026254117421092133,
+      "loss": 0.481,
+      "step": 681
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002621314146202656,
+      "loss": 0.4153,
+      "step": 682
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002617213661667443,
+      "loss": 0.4397,
+      "step": 683
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002613110307567643,
+      "loss": 0.4052,
+      "step": 684
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026090041029806695,
+      "loss": 0.4652,
+      "step": 685
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026048950669971884,
+      "loss": 0.3826,
+      "step": 686
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026007832187210277,
+      "loss": 0.5639,
+      "step": 687
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025966685772690906,
+      "loss": 0.3917,
+      "step": 688
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025925511617712685,
+      "loss": 0.5248,
+      "step": 689
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002588430991370347,
+      "loss": 0.3796,
+      "step": 690
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002584308085221922,
+      "loss": 0.4391,
+      "step": 691
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025801824624943084,
+      "loss": 0.4514,
+      "step": 692
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025760541423684496,
+      "loss": 0.5046,
+      "step": 693
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002571923144037831,
+      "loss": 0.4578,
+      "step": 694
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002567789486708389,
+      "loss": 0.4681,
+      "step": 695
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025636531895984236,
+      "loss": 0.4501,
+      "step": 696
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002559514271938506,
+      "loss": 0.4411,
+      "step": 697
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025553727529713916,
+      "loss": 0.401,
+      "step": 698
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025512286519519293,
+      "loss": 0.4911,
+      "step": 699
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002547081988146974,
+      "loss": 0.3754,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025429327808352946,
+      "loss": 0.3807,
+      "step": 701
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002538781049307486,
+      "loss": 0.4193,
+      "step": 702
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002534626812865876,
+      "loss": 0.5259,
+      "step": 703
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00025304700908244433,
+      "loss": 0.3684,
+      "step": 704
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002526310902508718,
+      "loss": 0.5423,
+      "step": 705
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002522149267255699,
+      "loss": 0.4288,
+      "step": 706
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.000251798520441376,
+      "loss": 0.5046,
+      "step": 707
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002513818733342564,
+      "loss": 0.3777,
+      "step": 708
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025096498734129667,
+      "loss": 0.5171,
+      "step": 709
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0002505478644006932,
+      "loss": 0.3785,
+      "step": 710
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025013050645174414,
+      "loss": 0.5413,
+      "step": 711
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024971291543483994,
+      "loss": 0.5018,
+      "step": 712
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024929509329145477,
+      "loss": 0.5212,
+      "step": 713
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024887704196413746,
+      "loss": 0.483,
+      "step": 714
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002484587633965023,
+      "loss": 0.3684,
+      "step": 715
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024804025953322005,
+      "loss": 0.3782,
+      "step": 716
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024762153232000877,
+      "loss": 0.4995,
+      "step": 717
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002472025837036253,
+      "loss": 0.4324,
+      "step": 718
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002467834156318555,
+      "loss": 0.5203,
+      "step": 719
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002463640300535057,
+      "loss": 0.423,
+      "step": 720
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002459444289183933,
+      "loss": 0.4537,
+      "step": 721
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00024552461417733817,
+      "loss": 0.4124,
+      "step": 722
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002451045877821528,
+      "loss": 0.4865,
+      "step": 723
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002446843516856343,
+      "loss": 0.4845,
+      "step": 724
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024426390784155425,
+      "loss": 0.4174,
+      "step": 725
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024384325820465033,
+      "loss": 0.4456,
+      "step": 726
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002434224047306169,
+      "loss": 0.4429,
+      "step": 727
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002430013493760961,
+      "loss": 0.363,
+      "step": 728
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024258009409866853,
+      "loss": 0.4769,
+      "step": 729
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024215864085684442,
+      "loss": 0.4597,
+      "step": 730
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024173699161005429,
+      "loss": 0.366,
+      "step": 731
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024131514831863995,
+      "loss": 0.4746,
+      "step": 732
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0002408931129438453,
+      "loss": 0.5608,
+      "step": 733
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024047088744780744,
+      "loss": 0.4292,
+      "step": 734
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00024004847379354726,
+      "loss": 0.4743,
+      "step": 735
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023962587394496038,
+      "loss": 0.3855,
+      "step": 736
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023920308986680834,
+      "loss": 0.4573,
+      "step": 737
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023878012352470892,
+      "loss": 0.3937,
+      "step": 738
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0002383569768851274,
+      "loss": 0.4371,
+      "step": 739
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023793365191536735,
+      "loss": 0.5432,
+      "step": 740
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023751015058356135,
+      "loss": 0.4803,
+      "step": 741
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.000237086474858662,
+      "loss": 0.4281,
+      "step": 742
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023666262671043263,
+      "loss": 0.4031,
+      "step": 743
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023623860810943826,
+      "loss": 0.4725,
+      "step": 744
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0002358144210270364,
+      "loss": 0.4644,
+      "step": 745
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023539006743536774,
+      "loss": 0.4848,
+      "step": 746
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023496554930734718,
+      "loss": 0.4084,
+      "step": 747
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023454086861665472,
+      "loss": 0.4322,
+      "step": 748
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023411602733772595,
+      "loss": 0.4847,
+      "step": 749
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023369102744574312,
+      "loss": 0.4298,
+      "step": 750
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023326587091662603,
+      "loss": 0.4268,
+      "step": 751
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023284055972702254,
+      "loss": 0.4089,
+      "step": 752
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0002324150958542997,
+      "loss": 0.4214,
+      "step": 753
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023198948127653446,
+      "loss": 0.5576,
+      "step": 754
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023156371797250418,
+      "loss": 0.4377,
+      "step": 755
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00023113780792167785,
+      "loss": 0.4934,
+      "step": 756
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002307117531042068,
+      "loss": 0.3698,
+      "step": 757
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00023028555550091536,
+      "loss": 0.4722,
+      "step": 758
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00022985921709329157,
+      "loss": 0.3837,
+      "step": 759
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00022943273986347822,
+      "loss": 0.5132,
+      "step": 760
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002290061257942635,
+      "loss": 0.487,
+      "step": 761
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022857937686907183,
+      "loss": 0.3857,
+      "step": 762
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022815249507195445,
+      "loss": 0.4135,
+      "step": 763
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022772548238758064,
+      "loss": 0.4639,
+      "step": 764
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022729834080122791,
+      "loss": 0.5297,
+      "step": 765
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022687107229877324,
+      "loss": 0.4485,
+      "step": 766
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022644367886668357,
+      "loss": 0.467,
+      "step": 767
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022601616249200675,
+      "loss": 0.4304,
+      "step": 768
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022558852516236217,
+      "loss": 0.5531,
+      "step": 769
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022516076886593158,
+      "loss": 0.5021,
+      "step": 770
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022473289559144988,
+      "loss": 0.433,
+      "step": 771
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022430490732819566,
+      "loss": 0.505,
+      "step": 772
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022387680606598235,
+      "loss": 0.4677,
+      "step": 773
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022344859379514858,
+      "loss": 0.4421,
+      "step": 774
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022302027250654905,
+      "loss": 0.4282,
+      "step": 775
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0002225918441915456,
+      "loss": 0.366,
+      "step": 776
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022216331084199724,
+      "loss": 0.4147,
+      "step": 777
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022173467445025158,
+      "loss": 0.586,
+      "step": 778
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022130593700913522,
+      "loss": 0.5285,
+      "step": 779
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022087710051194463,
+      "loss": 0.4484,
+      "step": 780
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0002204481669524367,
+      "loss": 0.4063,
+      "step": 781
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002200191383248197,
+      "loss": 0.4751,
+      "step": 782
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021959001662374373,
+      "loss": 0.3936,
+      "step": 783
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021916080384429184,
+      "loss": 0.4433,
+      "step": 784
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002187315019819703,
+      "loss": 0.4883,
+      "step": 785
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021830211303269965,
+      "loss": 0.4925,
+      "step": 786
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021787263899280537,
+      "loss": 0.4597,
+      "step": 787
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021744308185900848,
+      "loss": 0.4954,
+      "step": 788
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021701344362841626,
+      "loss": 0.4025,
+      "step": 789
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021658372629851318,
+      "loss": 0.5734,
+      "step": 790
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021615393186715128,
+      "loss": 0.3779,
+      "step": 791
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021572406233254116,
+      "loss": 0.4994,
+      "step": 792
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021529411969324275,
+      "loss": 0.5359,
+      "step": 793
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021486410594815554,
+      "loss": 0.4738,
+      "step": 794
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021443402309650979,
+      "loss": 0.4915,
+      "step": 795
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021400387313785704,
+      "loss": 0.4991,
+      "step": 796
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021357365807206087,
+      "loss": 0.4503,
+      "step": 797
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0002131433798992874,
+      "loss": 0.4887,
+      "step": 798
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021271304061999633,
+      "loss": 0.4279,
+      "step": 799
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021228264223493139,
+      "loss": 0.5367,
+      "step": 800
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1557,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 1.0713923068693709e+18,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbdf20491848d40e9a89bca19c6229b4b2b55e5d
--- /dev/null
+++ b/checkpoint-800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07819caee47f45203545f962678d52b5954ff1fd4afe1d5152fad48004402099
+size 4155
diff --git a/checkpoint-850/README.md b/checkpoint-850/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b32efe7366f05d1d90816d2ad9e4b06ccca46bea
--- /dev/null
+++ b/checkpoint-850/README.md
@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-850/adapter_config.json b/checkpoint-850/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e108f2da037ef6250457c67a4bedd308d97303c
--- /dev/null
+++ b/checkpoint-850/adapter_config.json
@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-850/adapter_model.bin b/checkpoint-850/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a1a5b6b7fe927689d66fc8724b5a5d06cf9c7607
--- /dev/null
+++ b/checkpoint-850/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f834c68c70315b5fce9b1dc11afe9e89264c74d708a40b82ee8eea83de9b37f7
+size 113314765
diff --git a/checkpoint-850/optimizer.pt b/checkpoint-850/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..388fb19977c5ad24dd58b9a0fc1afd4b15610f91
--- /dev/null
+++ b/checkpoint-850/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b5c5aea4dee5474f182bc612310d2a53e1f96beba93053df1b1b96348ae641
+size 226653957
diff --git a/checkpoint-850/rng_state.pth b/checkpoint-850/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5079e140bc6f3bee99ea24435ba209cd8c7305fd
--- /dev/null
+++ b/checkpoint-850/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515e6d64496266b6c21c0d830c6738ebd8fcdfe672c3416d33ba0ae2c7eaa603
+size 14575
diff --git a/checkpoint-850/scheduler.pt b/checkpoint-850/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..66e71dbbf1209b1a1626639ebaad37283b8ac3d8
--- /dev/null
+++ b/checkpoint-850/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42c783ab5a07507f0b1f8628363ba986357d070d6f9196f44a6f8c605489906
+size 627
diff --git a/checkpoint-850/trainer_state.json b/checkpoint-850/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..0e8f913a77ddc6013eeadb47d4c64c93aa387212
--- /dev/null
+++ b/checkpoint-850/trainer_state.json
@@ -0,0 +1,5119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6373811529666626,
+  "eval_steps": 500,
+  "global_step": 850,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6869,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8396,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7489,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7252,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8022,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.6524,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6981,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7488,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6891,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7968,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6912,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8452,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 0.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6685,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5469,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7915,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.6e-05,
+      "loss": 0.7744,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.6804,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.4e-05,
+      "loss": 0.7796,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.706,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6798,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6333,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 0.6012,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.52,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6583,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.7354,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000116,
+      "loss": 0.6296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 0.6352,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000124,
+      "loss": 0.6007,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5659,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000132,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6639,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 0.5934,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000144,
+      "loss": 0.5233,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000148,
+      "loss": 0.5307,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000152,
+      "loss": 0.5928,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5908,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000164,
+      "loss": 0.5972,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000168,
+      "loss": 0.4825,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000172,
+      "loss": 0.6783,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 0.7633,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5988,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000188,
+      "loss": 0.6658,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000192,
+      "loss": 0.5945,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000196,
+      "loss": 0.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.6057,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.601,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.5566,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.5911,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.7636,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.5537,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000232,
+      "loss": 0.6474,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000236,
+      "loss": 0.6483,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00024,
+      "loss": 0.5021,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000244,
+      "loss": 0.5347,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000248,
+      "loss": 0.5791,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000252,
+      "loss": 0.5407,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.5298,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5685,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000264,
+      "loss": 0.5108,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000268,
+      "loss": 0.526,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6843,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000276,
+      "loss": 0.6608,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00028,
+      "loss": 0.5866,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000284,
+      "loss": 0.6422,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000288,
+      "loss": 0.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000292,
+      "loss": 0.5319,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000296,
+      "loss": 0.5977,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.5805,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000304,
+      "loss": 0.5209,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000308,
+      "loss": 0.6098,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.4665,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6882,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00032,
+      "loss": 0.5427,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000324,
+      "loss": 0.5345,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000328,
+      "loss": 0.663,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000332,
+      "loss": 0.5393,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000336,
+      "loss": 0.5711,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00034,
+      "loss": 0.5261,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000344,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000348,
+      "loss": 0.6329,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.4425,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6837,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00036,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000364,
+      "loss": 0.5615,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5434,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000376,
+      "loss": 0.5583,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00038,
+      "loss": 0.5299,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000384,
+      "loss": 0.532,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000388,
+      "loss": 0.5227,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000392,
+      "loss": 0.5275,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.4541,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004,
+      "loss": 0.6485,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003999995350775973,
+      "loss": 0.5438,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999814031255063,
+      "loss": 0.5997,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999581571134455,
+      "loss": 0.5322,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003999925612847867,
+      "loss": 0.484,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998837704800766,
+      "loss": 0.5961,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998326302046085,
+      "loss": 0.7405,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997721922592255,
+      "loss": 0.5802,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997024569249167,
+      "loss": 0.769,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999623424525898,
+      "loss": 0.5598,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999535095429608,
+      "loss": 0.6143,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039994374700467095,
+      "loss": 0.5766,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039993305488310836,
+      "loss": 0.7695,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999214332279831,
+      "loss": 0.7153,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999088820933269,
+      "loss": 0.5835,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039989540153749286,
+      "loss": 0.6634,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000399880991623155,
+      "loss": 0.6069,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998656524173082,
+      "loss": 0.7224,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000399849383991268,
+      "loss": 0.5884,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998321864206699,
+      "loss": 0.5122,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039981405978546924,
+      "loss": 0.6453,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997950041699408,
+      "loss": 0.4665,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997750196626785,
+      "loss": 0.5428,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039975410635659464,
+      "loss": 0.4365,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039973226434891995,
+      "loss": 0.5978,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039970949374120286,
+      "loss": 0.7729,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000399685794639309,
+      "loss": 0.6212,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039966116715342066,
+      "loss": 0.5426,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00039963561139803676,
+      "loss": 0.5782,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003996091274919716,
+      "loss": 0.6701,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995817155583548,
+      "loss": 0.6314,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995533757246307,
+      "loss": 0.6662,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995241081225573,
+      "loss": 0.5192,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994939128882065,
+      "loss": 0.5591,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994627901619625,
+      "loss": 0.5809,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994307400885219,
+      "loss": 0.4871,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993977628168928,
+      "loss": 0.6666,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993638585003938,
+      "loss": 0.6469,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039932902729665357,
+      "loss": 0.5727,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039929326936761036,
+      "loss": 0.6715,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039925658487951067,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039921897400290894,
+      "loss": 0.501,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039918043691266665,
+      "loss": 0.5795,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039914097378795124,
+      "loss": 0.6287,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039910058481223564,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039905927017329726,
+      "loss": 0.6232,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039901703006321715,
+      "loss": 0.5291,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039897386467837903,
+      "loss": 0.5297,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039892977421946844,
+      "loss": 0.5784,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988847588914718,
+      "loss": 0.5714,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988388189036754,
+      "loss": 0.5044,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987919544696646,
+      "loss": 0.8246,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987441658073226,
+      "loss": 0.5048,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003986954531388297,
+      "loss": 0.5433,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039864581669066186,
+      "loss": 0.5251,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003985952566935902,
+      "loss": 0.5708,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039854377338267936,
+      "loss": 0.6276,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039849136699728684,
+      "loss": 0.4915,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003984380377810617,
+      "loss": 0.6389,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039838378598194325,
+      "loss": 0.6067,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039832861185216045,
+      "loss": 0.6136,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003982725156482301,
+      "loss": 0.5597,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000398215497630956,
+      "loss": 0.5957,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003981575580654278,
+      "loss": 0.5853,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980986972210194,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980389153713881,
+      "loss": 0.5302,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039797821279447307,
+      "loss": 0.5395,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039791658977249425,
+      "loss": 0.7004,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039785404659195084,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039779058354362013,
+      "loss": 0.5759,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000397726200922556,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003976608990280877,
+      "loss": 0.5488,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975946781638183,
+      "loss": 0.6162,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975275386376236,
+      "loss": 0.558,
+      "step": 173
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003974594807616502,
+      "loss": 0.519,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003973905048523144,
+      "loss": 0.6195,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039732061123030064,
+      "loss": 0.5991,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003972498002205601,
+      "loss": 0.5428,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039717807215230896,
+      "loss": 0.5323,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039710542735902705,
+      "loss": 0.5307,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003970318661784564,
+      "loss": 0.5783,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003969573889525993,
+      "loss": 0.5924,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039688199602771714,
+      "loss": 0.5902,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039680568775432855,
+      "loss": 0.6291,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003967284644872077,
+      "loss": 0.5942,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003966503265853829,
+      "loss": 0.4878,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003965712744121347,
+      "loss": 0.6487,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003964913083349945,
+      "loss": 0.6111,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039641042872574233,
+      "loss": 0.6072,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039632863596040575,
+      "loss": 0.716,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039624593041925763,
+      "loss": 0.6178,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003961623124868145,
+      "loss": 0.6323,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039607778255183485,
+      "loss": 0.5821,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959923410073174,
+      "loss": 0.6738,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959059882504989,
+      "loss": 0.6203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039581872468285277,
+      "loss": 0.632,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003957305507100868,
+      "loss": 0.5857,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039564146674214164,
+      "loss": 0.6311,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003955514731931885,
+      "loss": 0.5889,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039546057048162763,
+      "loss": 0.5201,
+      "step": 199
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039536875903008607,
+      "loss": 0.5581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039527603926541586,
+      "loss": 0.5104,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039518241161869193,
+      "loss": 0.5978,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039508787652521013,
+      "loss": 0.6244,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039499243442448536,
+      "loss": 0.589,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003948960857602493,
+      "loss": 0.575,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947988309804485,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947006705372422,
+      "loss": 0.4895,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039460160488700036,
+      "loss": 0.5479,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039450163449030124,
+      "loss": 0.5893,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003944007598119297,
+      "loss": 0.5451,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003942989813208747,
+      "loss": 0.5582,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003941962994903273,
+      "loss": 0.5121,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039409271479767826,
+      "loss": 0.6324,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000393988227724516,
+      "loss": 0.6118,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003938828387566244,
+      "loss": 0.6303,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003937765483839804,
+      "loss": 0.7705,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003936693571007517,
+      "loss": 0.6224,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935612654052946,
+      "loss": 0.5664,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039345227380015163,
+      "loss": 0.66,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039334238279204906,
+      "loss": 0.5582,
+      "step": 220
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039323159289189505,
+      "loss": 0.6087,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003931199046147764,
+      "loss": 0.5566,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039300731847995716,
+      "loss": 0.5775,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039289383501087534,
+      "loss": 0.5081,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277945473514104,
+      "loss": 0.5218,
+      "step": 225
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003926641781845338,
+      "loss": 0.6655,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003925480058950002,
+      "loss": 0.5735,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039243093840665114,
+      "loss": 0.6609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003923129762637596,
+      "loss": 0.7323,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000392194120014758,
+      "loss": 0.5703,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039207437021223583,
+      "loss": 0.6545,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003919537274129366,
+      "loss": 0.521,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039183219217775564,
+      "loss": 0.5257,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003917097650717377,
+      "loss": 0.5487,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039158644666407365,
+      "loss": 0.4861,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039146223752809845,
+      "loss": 0.4928,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003913371382412883,
+      "loss": 0.5253,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039121114938525756,
+      "loss": 0.6155,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039108427154575684,
+      "loss": 0.55,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039095650531266967,
+      "loss": 0.6617,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039082785128000976,
+      "loss": 0.5198,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039069831004591866,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003905678822126625,
+      "loss": 0.5347,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039043656838662946,
+      "loss": 0.531,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039030436917832697,
+      "loss": 0.4884,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039017128520237883,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003900373170775222,
+      "loss": 0.5537,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038990246542660494,
+      "loss": 0.5753,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038976673087658256,
+      "loss": 0.5059,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038963011405851537,
+      "loss": 0.5118,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038949261560756565,
+      "loss": 0.5645,
+      "step": 251
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003893542361629944,
+      "loss": 0.5623,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038921497636815866,
+      "loss": 0.5216,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003890748368705085,
+      "loss": 0.4501,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003889338183215838,
+      "loss": 0.48,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038879192137701135,
+      "loss": 0.5218,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003886491466965018,
+      "loss": 0.5858,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038850549494384685,
+      "loss": 0.6124,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038836096678691536,
+      "loss": 0.4645,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038821556289765136,
+      "loss": 0.474,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038806928395207003,
+      "loss": 0.4364,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038792213063025484,
+      "loss": 0.5821,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003877741036163547,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003876252035985804,
+      "loss": 0.5373,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003874754312692013,
+      "loss": 0.6021,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003873247873245426,
+      "loss": 0.4549,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003871732724649817,
+      "loss": 0.5994,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003870208873949453,
+      "loss": 0.4764,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038686763282290556,
+      "loss": 0.4311,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003867135094613774,
+      "loss": 0.5462,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003865585180269148,
+      "loss": 0.5006,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003864026592401076,
+      "loss": 0.5347,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038624593382557835,
+      "loss": 0.5242,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038608834251197856,
+      "loss": 0.5005,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038592988603198554,
+      "loss": 0.5436,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000385770565122299,
+      "loss": 0.4658,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003856103805236375,
+      "loss": 0.5273,
+      "step": 277
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038544933298073516,
+      "loss": 0.436,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038528742324233804,
+      "loss": 0.4785,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038512465206120086,
+      "loss": 0.5366,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038496102019408324,
+      "loss": 0.4448,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038479652840174637,
+      "loss": 0.5132,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038463117744894955,
+      "loss": 0.7918,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038446496810444627,
+      "loss": 0.5309,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038429790114098114,
+      "loss": 0.5316,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038412997733528576,
+      "loss": 0.4611,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038396119746807563,
+      "loss": 0.4609,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038379156232404613,
+      "loss": 0.5821,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003836210726918691,
+      "loss": 0.5883,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003834497293641889,
+      "loss": 0.5012,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038327753313761913,
+      "loss": 0.4457,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038310448481273867,
+      "loss": 0.4851,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038293058519408787,
+      "loss": 0.5622,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038275583509016507,
+      "loss": 0.5703,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038258023531342265,
+      "loss": 0.5718,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003824037866802632,
+      "loss": 0.5183,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038222649001103614,
+      "loss": 0.5085,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038204834613003323,
+      "loss": 0.5388,
+      "step": 298
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038186935586548537,
+      "loss": 0.5425,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003816895200495584,
+      "loss": 0.447,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003815088395183493,
+      "loss": 0.5541,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038132731511188227,
+      "loss": 0.5518,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000381144947674105,
+      "loss": 0.5074,
+      "step": 303
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003809617380528847,
+      "loss": 0.5134,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003807776871000037,
+      "loss": 0.4599,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003805927956711562,
+      "loss": 0.5838,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038040706462594395,
+      "loss": 0.5216,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038022049482787216,
+      "loss": 0.5323,
+      "step": 308
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003800330871443456,
+      "loss": 0.5681,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00037984484244666446,
+      "loss": 0.4172,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003796557616100207,
+      "loss": 0.4958,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003794658455134934,
+      "loss": 0.662,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003792750950400451,
+      "loss": 0.5832,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003790835110765174,
+      "loss": 0.4271,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003788910945136271,
+      "loss": 0.4842,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037869784624596186,
+      "loss": 0.4656,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037850376717197626,
+      "loss": 0.4981,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037830885819398733,
+      "loss": 0.5162,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037811312021817067,
+      "loss": 0.652,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003779165541545558,
+      "loss": 0.5104,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003777191609170225,
+      "loss": 0.4971,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003775209414232962,
+      "loss": 0.4871,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003773218965949436,
+      "loss": 0.5226,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00037712202735736884,
+      "loss": 0.4823,
+      "step": 324
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003769213346398087,
+      "loss": 0.497,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003767198193753286,
+      "loss": 0.5976,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003765174825008181,
+      "loss": 0.4532,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003763143249569868,
+      "loss": 0.5236,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00037611034768835947,
+      "loss": 0.6513,
+      "step": 329
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037590555164327224,
+      "loss": 0.5686,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037569993777386774,
+      "loss": 0.456,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003754935070360909,
+      "loss": 0.5181,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003752862603896846,
+      "loss": 0.4765,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037507819879818477,
+      "loss": 0.5363,
+      "step": 334
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037486932322891646,
+      "loss": 0.4584,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037465963465298886,
+      "loss": 0.5428,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003744491340452913,
+      "loss": 0.3927,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003742378223844882,
+      "loss": 0.5478,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003740257006530147,
+      "loss": 0.469,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037381276983707246,
+      "loss": 0.5169,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037359903092662434,
+      "loss": 0.4797,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037338448491539054,
+      "loss": 0.5315,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037316913280084353,
+      "loss": 0.4422,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003729529755842035,
+      "loss": 0.4426,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003727360142704337,
+      "loss": 0.4718,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003725182498682361,
+      "loss": 0.5585,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003722996833900459,
+      "loss": 0.4775,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003720803158520279,
+      "loss": 0.6014,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00037186014827407076,
+      "loss": 0.5117,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003716391816797829,
+      "loss": 0.5404,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003714174170964876,
+      "loss": 0.527,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037119485555521796,
+      "loss": 0.4555,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037097149809071255,
+      "loss": 0.5372,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037074734574141016,
+      "loss": 0.5377,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003705223995494454,
+      "loss": 0.4925,
+      "step": 355
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037029666056064345,
+      "loss": 0.482,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037007012982451546,
+      "loss": 0.5235,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00036984280839425356,
+      "loss": 0.4957,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000369614697326726,
+      "loss": 0.5379,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003693857976824721,
+      "loss": 0.4653,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036915611052569785,
+      "loss": 0.469,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003689256369242702,
+      "loss": 0.5618,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003686943779497124,
+      "loss": 0.4459,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003684623346771995,
+      "loss": 0.5606,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003682295081855524,
+      "loss": 0.4368,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036799589955723375,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036776150987834243,
+      "loss": 0.4664,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036752634023860846,
+      "loss": 0.4737,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003672903917313883,
+      "loss": 0.4247,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036705366545365935,
+      "loss": 0.5677,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036681616250601505,
+      "loss": 0.5441,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003665778839926599,
+      "loss": 0.6247,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00036633883102140405,
+      "loss": 0.5217,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003660990047036584,
+      "loss": 0.4651,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003658584061544291,
+      "loss": 0.4648,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003656170364923128,
+      "loss": 0.6048,
+      "step": 376
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036537489683949114,
+      "loss": 0.4515,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003651319883217255,
+      "loss": 0.5096,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036488831206835207,
+      "loss": 0.4231,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036464386921227637,
+      "loss": 0.4903,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036439866088996796,
+      "loss": 0.5131,
+      "step": 381
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003641526882414553,
+      "loss": 0.5986,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003639059524103203,
+      "loss": 0.6,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003636584545436931,
+      "loss": 0.5216,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003634101957922468,
+      "loss": 0.5144,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00036316117731019184,
+      "loss": 0.4963,
+      "step": 386
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003629114002552711,
+      "loss": 0.5657,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036266086578875384,
+      "loss": 0.5028,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003624095750754311,
+      "loss": 0.573,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036215752928360967,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003619047295851068,
+      "loss": 0.656,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036165117715524506,
+      "loss": 0.5129,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036139687317284647,
+      "loss": 0.3945,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003611418188202271,
+      "loss": 0.5318,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036088601528319196,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036062946375102885,
+      "loss": 0.5407,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003603721654165034,
+      "loss": 0.5364,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00036011412147585306,
+      "loss": 0.5407,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003598553331287821,
+      "loss": 0.5999,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003595958015784555,
+      "loss": 0.624,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00035933552803149354,
+      "loss": 0.5351,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003590745136979662,
+      "loss": 0.5196,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035881275979138765,
+      "loss": 0.5447,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003585502675287104,
+      "loss": 0.4908,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035828703813031986,
+      "loss": 0.5172,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035802307282002834,
+      "loss": 0.5923,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003577583728250699,
+      "loss": 0.568,
+      "step": 407
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035749293937609395,
+      "loss": 0.4618,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003572267737071601,
+      "loss": 0.5351,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003569598770557322,
+      "loss": 0.5285,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035669225066267256,
+      "loss": 0.4571,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035642389577223625,
+      "loss": 0.4214,
+      "step": 412
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003561548136320653,
+      "loss": 0.5393,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003558850054931828,
+      "loss": 0.549,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035561447260998714,
+      "loss": 0.4824,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035534321624024656,
+      "loss": 0.6244,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035507123764509245,
+      "loss": 0.5436,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003547985380890144,
+      "loss": 0.5198,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035452511883985366,
+      "loss": 0.5979,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035425098116879754,
+      "loss": 0.4158,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035397612635037356,
+      "loss": 0.5125,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035370055566244334,
+      "loss": 0.4699,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003534242703861966,
+      "loss": 0.5553,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035314727180614573,
+      "loss": 0.5969,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035286956121011897,
+      "loss": 0.456,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003525911398892552,
+      "loss": 0.5195,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003523120091379975,
+      "loss": 0.5187,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035203217025408726,
+      "loss": 0.5443,
+      "step": 428
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003517516245385582,
+      "loss": 0.4476,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003514703732957301,
+      "loss": 0.5757,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035118841783320304,
+      "loss": 0.5129,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035090575946185114,
+      "loss": 0.6354,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035062239949581645,
+      "loss": 0.4065,
+      "step": 433
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000350338339252503,
+      "loss": 0.5472,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00035005358005257045,
+      "loss": 0.5424,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034976812321992816,
+      "loss": 0.6127,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034948197008172877,
+      "loss": 0.63,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003491951219683625,
+      "loss": 0.413,
+      "step": 438
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034890758021345034,
+      "loss": 0.5435,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034861934615383844,
+      "loss": 0.5433,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034833042112959153,
+      "loss": 0.4763,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034804080648398667,
+      "loss": 0.5727,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034775050356350727,
+      "loss": 0.5392,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034745951371783666,
+      "loss": 0.4981,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003471678382998518,
+      "loss": 0.5516,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00034687547866561703,
+      "loss": 0.4965,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003465824361743779,
+      "loss": 0.4982,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003462887121885544,
+      "loss": 0.5619,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003459943080737353,
+      "loss": 0.5273,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034569922519867133,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034540346493526876,
+      "loss": 0.4874,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003451070286585833,
+      "loss": 0.5966,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003448099177468137,
+      "loss": 0.4487,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003445121335812951,
+      "loss": 0.5091,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003442136775464929,
+      "loss": 0.407,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003439145510299958,
+      "loss": 0.6327,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00034361475542251025,
+      "loss": 0.4217,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003433142921178531,
+      "loss": 0.6102,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003430131625129456,
+      "loss": 0.5556,
+      "step": 459
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034271136800780673,
+      "loss": 0.4986,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003424089100055467,
+      "loss": 0.5406,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034210578991236056,
+      "loss": 0.5881,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034180200913752157,
+      "loss": 0.4869,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034149756909337454,
+      "loss": 0.5626,
+      "step": 464
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003411924711953295,
+      "loss": 0.564,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00034088671686185486,
+      "loss": 0.6272,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003405803075144711,
+      "loss": 0.4643,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003402732445777438,
+      "loss": 0.5435,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00033996552947927744,
+      "loss": 0.5844,
+      "step": 469
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003396571636497084,
+      "loss": 0.5362,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033934814852269865,
+      "loss": 0.5607,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003390384855349285,
+      "loss": 0.4836,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033872817612609065,
+      "loss": 0.6555,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033841722173888315,
+      "loss": 0.4784,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033810562381900253,
+      "loss": 0.5583,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033779338381513736,
+      "loss": 0.4679,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003374805031789613,
+      "loss": 0.5325,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033716698336512654,
+      "loss": 0.6601,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000336852825831257,
+      "loss": 0.4838,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003365380320379414,
+      "loss": 0.5588,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033622260344872665,
+      "loss": 0.4596,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003359065415301108,
+      "loss": 0.5228,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033558984775153663,
+      "loss": 0.5316,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033527252358538437,
+      "loss": 0.4761,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003349545705069653,
+      "loss": 0.5254,
+      "step": 485
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003346359899945144,
+      "loss": 0.4786,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033431678352918384,
+      "loss": 0.4302,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003339969525950361,
+      "loss": 0.4914,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033367649867903663,
+      "loss": 0.4102,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003333554232710477,
+      "loss": 0.4698,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003330337278638207,
+      "loss": 0.4454,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033271141395298964,
+      "loss": 0.4648,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033238848303706415,
+      "loss": 0.4616,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033206493661742237,
+      "loss": 0.4861,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033174077619830416,
+      "loss": 0.4797,
+      "step": 495
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033141600328680373,
+      "loss": 0.5104,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033109061939286336,
+      "loss": 0.5712,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033076462602926553,
+      "loss": 0.5425,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033043802471162636,
+      "loss": 0.6156,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003301108169583887,
+      "loss": 0.4282,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003297830042908146,
+      "loss": 0.4088,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032945458823297857,
+      "loss": 0.4866,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003291255703117605,
+      "loss": 0.5045,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003287959520568384,
+      "loss": 0.491,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032846573500068136,
+      "loss": 0.458,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032813492067854246,
+      "loss": 0.4508,
+      "step": 506
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003278035106284516,
+      "loss": 0.4294,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032747150639120834,
+      "loss": 0.4834,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032713890951037477,
+      "loss": 0.3857,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032680572153226834,
+      "loss": 0.4072,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003264719440059545,
+      "loss": 0.4028,
+      "step": 511
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032613757848323977,
+      "loss": 0.3789,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032580262651866446,
+      "loss": 0.4944,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003254670896694952,
+      "loss": 0.4259,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032513096949571805,
+      "loss": 0.5037,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032479426756003093,
+      "loss": 0.5857,
+      "step": 516
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003244569854278366,
+      "loss": 0.5407,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032411912466723524,
+      "loss": 0.499,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003237806868490172,
+      "loss": 0.4359,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032344167354665573,
+      "loss": 0.4374,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003231020863362997,
+      "loss": 0.4172,
+      "step": 521
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000322761926796766,
+      "loss": 0.4451,
+      "step": 522
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003224211965095326,
+      "loss": 0.4,
+      "step": 523
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003220798970587309,
+      "loss": 0.4009,
+      "step": 524
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003217380300311386,
+      "loss": 0.3966,
+      "step": 525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000321395597016172,
+      "loss": 0.4255,
+      "step": 526
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00032105259960587895,
+      "loss": 0.4707,
+      "step": 527
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00032070903939493124,
+      "loss": 0.5313,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003203649179806172,
+      "loss": 0.3596,
+      "step": 529
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003200202369628345,
+      "loss": 0.5223,
+      "step": 530
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031967499794408234,
+      "loss": 0.4146,
+      "step": 531
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031932920252945423,
+      "loss": 0.4328,
+      "step": 532
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003189828523266306,
+      "loss": 0.4258,
+      "step": 533
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031863594894587105,
+      "loss": 0.4457,
+      "step": 534
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003182884940000072,
+      "loss": 0.5249,
+      "step": 535
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003179404891044348,
+      "loss": 0.4751,
+      "step": 536
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031759193587710676,
+      "loss": 0.5378,
+      "step": 537
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031724283593852497,
+      "loss": 0.634,
+      "step": 538
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031689319091173326,
+      "loss": 0.4298,
+      "step": 539
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031654300242230977,
+      "loss": 0.5469,
+      "step": 540
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031619227209835917,
+      "loss": 0.5153,
+      "step": 541
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003158410015705053,
+      "loss": 0.4144,
+      "step": 542
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003154891924718837,
+      "loss": 0.6041,
+      "step": 543
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003151368464381335,
+      "loss": 0.4891,
+      "step": 544
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003147839651073904,
+      "loss": 0.5258,
+      "step": 545
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00031443055012027874,
+      "loss": 0.4351,
+      "step": 546
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000314076603119904,
+      "loss": 0.4556,
+      "step": 547
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031372212575184514,
+      "loss": 0.5445,
+      "step": 548
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031336711966414675,
+      "loss": 0.5585,
+      "step": 549
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003130115865073117,
+      "loss": 0.367,
+      "step": 550
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003126555279342933,
+      "loss": 0.4877,
+      "step": 551
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003122989456004876,
+      "loss": 0.4335,
+      "step": 552
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003119418411637258,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003115842162842663,
+      "loss": 0.4508,
+      "step": 554
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00031122607262478743,
+      "loss": 0.4631,
+      "step": 555
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003108674118503793,
+      "loss": 0.3496,
+      "step": 556
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003105082356285361,
+      "loss": 0.4108,
+      "step": 557
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003101485456291486,
+      "loss": 0.4877,
+      "step": 558
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030978834352449614,
+      "loss": 0.3696,
+      "step": 559
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030942763098923913,
+      "loss": 0.5138,
+      "step": 560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030906640970041084,
+      "loss": 0.5961,
+      "step": 561
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003087046813374099,
+      "loss": 0.3824,
+      "step": 562
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030834244758199276,
+      "loss": 0.4925,
+      "step": 563
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000307979710118265,
+      "loss": 0.4511,
+      "step": 564
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030761647063267457,
+      "loss": 0.4306,
+      "step": 565
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003072527308140031,
+      "loss": 0.468,
+      "step": 566
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030688849235335856,
+      "loss": 0.4842,
+      "step": 567
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003065237569441671,
+      "loss": 0.4332,
+      "step": 568
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030615852628216537,
+      "loss": 0.4637,
+      "step": 569
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003057928020653925,
+      "loss": 0.6193,
+      "step": 570
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003054265859941824,
+      "loss": 0.5033,
+      "step": 571
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030505987977115555,
+      "loss": 0.4185,
+      "step": 572
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003046926851012114,
+      "loss": 0.4211,
+      "step": 573
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003043250036915201,
+      "loss": 0.5089,
+      "step": 574
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00030395683725151505,
+      "loss": 0.517,
+      "step": 575
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003035881874928845,
+      "loss": 0.492,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003032190561295636,
+      "loss": 0.4535,
+      "step": 577
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003028494448777269,
+      "loss": 0.3947,
+      "step": 578
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030247935545577986,
+      "loss": 0.3125,
+      "step": 579
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003021087895843511,
+      "loss": 0.3882,
+      "step": 580
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003017377489862845,
+      "loss": 0.4802,
+      "step": 581
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030136623538663083,
+      "loss": 0.4652,
+      "step": 582
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030099425051263994,
+      "loss": 0.3816,
+      "step": 583
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003006217960937529,
+      "loss": 0.4583,
+      "step": 584
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00030024887386159385,
+      "loss": 0.4568,
+      "step": 585
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029987548554996174,
+      "loss": 0.3908,
+      "step": 586
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002995016328948225,
+      "loss": 0.4235,
+      "step": 587
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029912731763430075,
+      "loss": 0.4138,
+      "step": 588
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029875254150867216,
+      "loss": 0.5838,
+      "step": 589
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002983773062603548,
+      "loss": 0.462,
+      "step": 590
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029800161363390145,
+      "loss": 0.4632,
+      "step": 591
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029762546537599125,
+      "loss": 0.5898,
+      "step": 592
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002972488632354218,
+      "loss": 0.4742,
+      "step": 593
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029687180896310065,
+      "loss": 0.4579,
+      "step": 594
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002964943043120378,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029611635103733675,
+      "loss": 0.4304,
+      "step": 596
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002957379508961871,
+      "loss": 0.4383,
+      "step": 597
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029535910564785584,
+      "loss": 0.5327,
+      "step": 598
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029497981705367933,
+      "loss": 0.4781,
+      "step": 599
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029460008687705525,
+      "loss": 0.4178,
+      "step": 600
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002942199168834342,
+      "loss": 0.3987,
+      "step": 601
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029383930884031183,
+      "loss": 0.3861,
+      "step": 602
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029345826451722005,
+      "loss": 0.5322,
+      "step": 603
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029307678568571936,
+      "loss": 0.3997,
+      "step": 604
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002926948741193903,
+      "loss": 0.4121,
+      "step": 605
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029231253159382514,
+      "loss": 0.4931,
+      "step": 606
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029192975988662017,
+      "loss": 0.4626,
+      "step": 607
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029154656077736666,
+      "loss": 0.4441,
+      "step": 608
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002911629360476432,
+      "loss": 0.3863,
+      "step": 609
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029077888748100703,
+      "loss": 0.36,
+      "step": 610
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029039441686298594,
+      "loss": 0.4246,
+      "step": 611
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002900095259810702,
+      "loss": 0.4916,
+      "step": 612
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028962421662470346,
+      "loss": 0.4896,
+      "step": 613
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028923849058527535,
+      "loss": 0.4237,
+      "step": 614
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028885234965611274,
+      "loss": 0.5727,
+      "step": 615
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028846579563247116,
+      "loss": 0.5681,
+      "step": 616
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002880788303115269,
+      "loss": 0.4383,
+      "step": 617
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028769145549236845,
+      "loss": 0.4962,
+      "step": 618
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002873036729759881,
+      "loss": 0.5472,
+      "step": 619
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002869154845652738,
+      "loss": 0.5431,
+      "step": 620
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002865268920650003,
+      "loss": 0.4152,
+      "step": 621
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002861378972818211,
+      "loss": 0.3922,
+      "step": 622
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002857485020242602,
+      "loss": 0.5129,
+      "step": 623
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002853587081027034,
+      "loss": 0.4328,
+      "step": 624
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00028496851732938997,
+      "loss": 0.4431,
+      "step": 625
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002845779315184042,
+      "loss": 0.4968,
+      "step": 626
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.000284186952485667,
+      "loss": 0.5301,
+      "step": 627
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002837955820489276,
+      "loss": 0.4332,
+      "step": 628
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002834038220277546,
+      "loss": 0.4245,
+      "step": 629
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00028301167424352836,
+      "loss": 0.5057,
+      "step": 630
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028261914051943166,
+      "loss": 0.4623,
+      "step": 631
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028222622268044174,
+      "loss": 0.5452,
+      "step": 632
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028183292255332164,
+      "loss": 0.5238,
+      "step": 633
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028143924196661176,
+      "loss": 0.3966,
+      "step": 634
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002810451827506214,
+      "loss": 0.35,
+      "step": 635
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00028065074673742007,
+      "loss": 0.4325,
+      "step": 636
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0002802559357608292,
+      "loss": 0.4854,
+      "step": 637
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027986075165641343,
+      "loss": 0.4254,
+      "step": 638
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027946519626147225,
+      "loss": 0.4614,
+      "step": 639
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027906927141503125,
+      "loss": 0.3798,
+      "step": 640
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027867297895783373,
+      "loss": 0.4742,
+      "step": 641
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002782763207323322,
+      "loss": 0.4007,
+      "step": 642
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002778792985826795,
+      "loss": 0.4383,
+      "step": 643
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002774819143547206,
+      "loss": 0.4298,
+      "step": 644
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00027708416989598387,
+      "loss": 0.5178,
+      "step": 645
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002766860670556722,
+      "loss": 0.3434,
+      "step": 646
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002762876076846551,
+      "loss": 0.3862,
+      "step": 647
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027588879363545934,
+      "loss": 0.4459,
+      "step": 648
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002754896267622608,
+      "loss": 0.3934,
+      "step": 649
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027509010892087565,
+      "loss": 0.4349,
+      "step": 650
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000274690241968752,
+      "loss": 0.4178,
+      "step": 651
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002742900277649607,
+      "loss": 0.4151,
+      "step": 652
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002738894681701874,
+      "loss": 0.3888,
+      "step": 653
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027348856504672323,
+      "loss": 0.4214,
+      "step": 654
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002730873202584567,
+      "loss": 0.519,
+      "step": 655
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027268573567086477,
+      "loss": 0.5463,
+      "step": 656
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027228381315100417,
+      "loss": 0.3367,
+      "step": 657
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027188155456750256,
+      "loss": 0.4629,
+      "step": 658
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027147896179055043,
+      "loss": 0.4456,
+      "step": 659
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002710760366918917,
+      "loss": 0.4348,
+      "step": 660
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002706727811448153,
+      "loss": 0.4505,
+      "step": 661
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002702691970241468,
+      "loss": 0.5028,
+      "step": 662
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026986528620623904,
+      "loss": 0.5257,
+      "step": 663
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026946105056896403,
+      "loss": 0.4977,
+      "step": 664
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026905649199170377,
+      "loss": 0.421,
+      "step": 665
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002686516123553417,
+      "loss": 0.4931,
+      "step": 666
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026824641354225397,
+      "loss": 0.5818,
+      "step": 667
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002678408974363005,
+      "loss": 0.4211,
+      "step": 668
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026743506592281674,
+      "loss": 0.5182,
+      "step": 669
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026702892088860413,
+      "loss": 0.5591,
+      "step": 670
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002666224642219221,
+      "loss": 0.5363,
+      "step": 671
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002662156978124786,
+      "loss": 0.5866,
+      "step": 672
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002658086235514218,
+      "loss": 0.422,
+      "step": 673
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002654012433313312,
+      "loss": 0.5375,
+      "step": 674
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002649935590462087,
+      "loss": 0.4752,
+      "step": 675
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00026458557259146986,
+      "loss": 0.4271,
+      "step": 676
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002641772858639351,
+      "loss": 0.4843,
+      "step": 677
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026376870076182086,
+      "loss": 0.4827,
+      "step": 678
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026335981918473086,
+      "loss": 0.47,
+      "step": 679
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002629506430336472,
+      "loss": 0.368,
+      "step": 680
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026254117421092133,
+      "loss": 0.481,
+      "step": 681
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002621314146202656,
+      "loss": 0.4153,
+      "step": 682
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002617213661667443,
+      "loss": 0.4397,
+      "step": 683
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002613110307567643,
+      "loss": 0.4052,
+      "step": 684
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026090041029806695,
+      "loss": 0.4652,
+      "step": 685
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026048950669971884,
+      "loss": 0.3826,
+      "step": 686
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026007832187210277,
+      "loss": 0.5639,
+      "step": 687
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025966685772690906,
+      "loss": 0.3917,
+      "step": 688
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025925511617712685,
+      "loss": 0.5248,
+      "step": 689
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002588430991370347,
+      "loss": 0.3796,
+      "step": 690
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002584308085221922,
+      "loss": 0.4391,
+      "step": 691
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025801824624943084,
+      "loss": 0.4514,
+      "step": 692
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025760541423684496,
+      "loss": 0.5046,
+      "step": 693
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002571923144037831,
+      "loss": 0.4578,
+      "step": 694
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002567789486708389,
+      "loss": 0.4681,
+      "step": 695
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025636531895984236,
+      "loss": 0.4501,
+      "step": 696
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002559514271938506,
+      "loss": 0.4411,
+      "step": 697
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025553727529713916,
+      "loss": 0.401,
+      "step": 698
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025512286519519293,
+      "loss": 0.4911,
+      "step": 699
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002547081988146974,
+      "loss": 0.3754,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025429327808352946,
+      "loss": 0.3807,
+      "step": 701
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002538781049307486,
+      "loss": 0.4193,
+      "step": 702
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002534626812865876,
+      "loss": 0.5259,
+      "step": 703
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00025304700908244433,
+      "loss": 0.3684,
+      "step": 704
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002526310902508718,
+      "loss": 0.5423,
+      "step": 705
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002522149267255699,
+      "loss": 0.4288,
+      "step": 706
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.000251798520441376,
+      "loss": 0.5046,
+      "step": 707
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002513818733342564,
+      "loss": 0.3777,
+      "step": 708
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025096498734129667,
+      "loss": 0.5171,
+      "step": 709
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0002505478644006932,
+      "loss": 0.3785,
+      "step": 710
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025013050645174414,
+      "loss": 0.5413,
+      "step": 711
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024971291543483994,
+      "loss": 0.5018,
+      "step": 712
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024929509329145477,
+      "loss": 0.5212,
+      "step": 713
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024887704196413746,
+      "loss": 0.483,
+      "step": 714
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002484587633965023,
+      "loss": 0.3684,
+      "step": 715
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024804025953322005,
+      "loss": 0.3782,
+      "step": 716
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024762153232000877,
+      "loss": 0.4995,
+      "step": 717
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002472025837036253,
+      "loss": 0.4324,
+      "step": 718
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002467834156318555,
+      "loss": 0.5203,
+      "step": 719
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002463640300535057,
+      "loss": 0.423,
+      "step": 720
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002459444289183933,
+      "loss": 0.4537,
+      "step": 721
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00024552461417733817,
+      "loss": 0.4124,
+      "step": 722
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002451045877821528,
+      "loss": 0.4865,
+      "step": 723
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002446843516856343,
+      "loss": 0.4845,
+      "step": 724
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024426390784155425,
+      "loss": 0.4174,
+      "step": 725
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024384325820465033,
+      "loss": 0.4456,
+      "step": 726
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002434224047306169,
+      "loss": 0.4429,
+      "step": 727
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002430013493760961,
+      "loss": 0.363,
+      "step": 728
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024258009409866853,
+      "loss": 0.4769,
+      "step": 729
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024215864085684442,
+      "loss": 0.4597,
+      "step": 730
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024173699161005429,
+      "loss": 0.366,
+      "step": 731
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024131514831863995,
+      "loss": 0.4746,
+      "step": 732
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0002408931129438453,
+      "loss": 0.5608,
+      "step": 733
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024047088744780744,
+      "loss": 0.4292,
+      "step": 734
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00024004847379354726,
+      "loss": 0.4743,
+      "step": 735
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023962587394496038,
+      "loss": 0.3855,
+      "step": 736
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023920308986680834,
+      "loss": 0.4573,
+      "step": 737
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023878012352470892,
+      "loss": 0.3937,
+      "step": 738
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0002383569768851274,
+      "loss": 0.4371,
+      "step": 739
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023793365191536735,
+      "loss": 0.5432,
+      "step": 740
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023751015058356135,
+      "loss": 0.4803,
+      "step": 741
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.000237086474858662,
+      "loss": 0.4281,
+      "step": 742
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023666262671043263,
+      "loss": 0.4031,
+      "step": 743
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023623860810943826,
+      "loss": 0.4725,
+      "step": 744
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0002358144210270364,
+      "loss": 0.4644,
+      "step": 745
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023539006743536774,
+      "loss": 0.4848,
+      "step": 746
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023496554930734718,
+      "loss": 0.4084,
+      "step": 747
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023454086861665472,
+      "loss": 0.4322,
+      "step": 748
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023411602733772595,
+      "loss": 0.4847,
+      "step": 749
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023369102744574312,
+      "loss": 0.4298,
+      "step": 750
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023326587091662603,
+      "loss": 0.4268,
+      "step": 751
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023284055972702254,
+      "loss": 0.4089,
+      "step": 752
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0002324150958542997,
+      "loss": 0.4214,
+      "step": 753
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023198948127653446,
+      "loss": 0.5576,
+      "step": 754
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023156371797250418,
+      "loss": 0.4377,
+      "step": 755
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00023113780792167785,
+      "loss": 0.4934,
+      "step": 756
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002307117531042068,
+      "loss": 0.3698,
+      "step": 757
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00023028555550091536,
+      "loss": 0.4722,
+      "step": 758
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00022985921709329157,
+      "loss": 0.3837,
+      "step": 759
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00022943273986347822,
+      "loss": 0.5132,
+      "step": 760
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002290061257942635,
+      "loss": 0.487,
+      "step": 761
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022857937686907183,
+      "loss": 0.3857,
+      "step": 762
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022815249507195445,
+      "loss": 0.4135,
+      "step": 763
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022772548238758064,
+      "loss": 0.4639,
+      "step": 764
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022729834080122791,
+      "loss": 0.5297,
+      "step": 765
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022687107229877324,
+      "loss": 0.4485,
+      "step": 766
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022644367886668357,
+      "loss": 0.467,
+      "step": 767
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022601616249200675,
+      "loss": 0.4304,
+      "step": 768
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022558852516236217,
+      "loss": 0.5531,
+      "step": 769
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022516076886593158,
+      "loss": 0.5021,
+      "step": 770
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022473289559144988,
+      "loss": 0.433,
+      "step": 771
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022430490732819566,
+      "loss": 0.505,
+      "step": 772
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022387680606598235,
+      "loss": 0.4677,
+      "step": 773
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022344859379514858,
+      "loss": 0.4421,
+      "step": 774
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022302027250654905,
+      "loss": 0.4282,
+      "step": 775
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0002225918441915456,
+      "loss": 0.366,
+      "step": 776
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022216331084199724,
+      "loss": 0.4147,
+      "step": 777
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022173467445025158,
+      "loss": 0.586,
+      "step": 778
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022130593700913522,
+      "loss": 0.5285,
+      "step": 779
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022087710051194463,
+      "loss": 0.4484,
+      "step": 780
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0002204481669524367,
+      "loss": 0.4063,
+      "step": 781
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002200191383248197,
+      "loss": 0.4751,
+      "step": 782
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021959001662374373,
+      "loss": 0.3936,
+      "step": 783
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021916080384429184,
+      "loss": 0.4433,
+      "step": 784
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002187315019819703,
+      "loss": 0.4883,
+      "step": 785
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021830211303269965,
+      "loss": 0.4925,
+      "step": 786
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021787263899280537,
+      "loss": 0.4597,
+      "step": 787
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021744308185900848,
+      "loss": 0.4954,
+      "step": 788
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021701344362841626,
+      "loss": 0.4025,
+      "step": 789
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021658372629851318,
+      "loss": 0.5734,
+      "step": 790
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021615393186715128,
+      "loss": 0.3779,
+      "step": 791
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021572406233254116,
+      "loss": 0.4994,
+      "step": 792
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021529411969324275,
+      "loss": 0.5359,
+      "step": 793
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021486410594815554,
+      "loss": 0.4738,
+      "step": 794
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021443402309650979,
+      "loss": 0.4915,
+      "step": 795
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021400387313785704,
+      "loss": 0.4991,
+      "step": 796
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021357365807206087,
+      "loss": 0.4503,
+      "step": 797
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0002131433798992874,
+      "loss": 0.4887,
+      "step": 798
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021271304061999633,
+      "loss": 0.4279,
+      "step": 799
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021228264223493139,
+      "loss": 0.5367,
+      "step": 800
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021185218674511097,
+      "loss": 0.3212,
+      "step": 801
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021142167615181915,
+      "loss": 0.493,
+      "step": 802
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002109911124565962,
+      "loss": 0.3635,
+      "step": 803
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00021056049766122916,
+      "loss": 0.3494,
+      "step": 804
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00021012983376774254,
+      "loss": 0.3536,
+      "step": 805
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002096991227783895,
+      "loss": 0.4335,
+      "step": 806
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00020926836669564168,
+      "loss": 0.4673,
+      "step": 807
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020883756752218075,
+      "loss": 0.5269,
+      "step": 808
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0002084067272608886,
+      "loss": 0.4365,
+      "step": 809
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020797584791483806,
+      "loss": 0.2998,
+      "step": 810
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020754493148728375,
+      "loss": 0.4318,
+      "step": 811
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020711397998165264,
+      "loss": 0.3205,
+      "step": 812
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020668299540153493,
+      "loss": 0.5026,
+      "step": 813
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020625197975067438,
+      "loss": 0.3923,
+      "step": 814
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0002058209350329594,
+      "loss": 0.3026,
+      "step": 815
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020538986325241342,
+      "loss": 0.4729,
+      "step": 816
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020495876641318567,
+      "loss": 0.3236,
+      "step": 817
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0002045276465195419,
+      "loss": 0.4934,
+      "step": 818
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020409650557585523,
+      "loss": 0.3791,
+      "step": 819
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020366534558659635,
+      "loss": 0.3879,
+      "step": 820
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020323416855632477,
+      "loss": 0.3807,
+      "step": 821
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020280297648967897,
+      "loss": 0.415,
+      "step": 822
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020237177139136758,
+      "loss": 0.3824,
+      "step": 823
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0002019405552661596,
+      "loss": 0.3854,
+      "step": 824
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020150933011887543,
+      "loss": 0.3781,
+      "step": 825
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020107809795437745,
+      "loss": 0.3904,
+      "step": 826
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020064686077756057,
+      "loss": 0.3213,
+      "step": 827
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00020021562059334302,
+      "loss": 0.4888,
+      "step": 828
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019978437940665702,
+      "loss": 0.3375,
+      "step": 829
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001993531392224394,
+      "loss": 0.4325,
+      "step": 830
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019892190204562257,
+      "loss": 0.2865,
+      "step": 831
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001984906698811246,
+      "loss": 0.3984,
+      "step": 832
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019805944473384038,
+      "loss": 0.3011,
+      "step": 833
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019762822860863247,
+      "loss": 0.4063,
+      "step": 834
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019719702351032105,
+      "loss": 0.4489,
+      "step": 835
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019676583144367525,
+      "loss": 0.3991,
+      "step": 836
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019633465441340367,
+      "loss": 0.2736,
+      "step": 837
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019590349442414484,
+      "loss": 0.3842,
+      "step": 838
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0001954723534804581,
+      "loss": 0.346,
+      "step": 839
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0001950412335868144,
+      "loss": 0.3435,
+      "step": 840
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019461013674758668,
+      "loss": 0.4139,
+      "step": 841
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019417906496704064,
+      "loss": 0.4031,
+      "step": 842
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019374802024932567,
+      "loss": 0.352,
+      "step": 843
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019331700459846517,
+      "loss": 0.332,
+      "step": 844
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019288602001834735,
+      "loss": 0.3822,
+      "step": 845
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019245506851271632,
+      "loss": 0.3912,
+      "step": 846
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.000192024152085162,
+      "loss": 0.4028,
+      "step": 847
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019159327273911145,
+      "loss": 0.3625,
+      "step": 848
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00019116243247781927,
+      "loss": 0.392,
+      "step": 849
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00019073163330435842,
+      "loss": 0.3687,
+      "step": 850
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1557,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 1.1381421486723564e+18,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-850/training_args.bin b/checkpoint-850/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4843df7aa1383a371fb28dea27d303b1a1145e1
--- /dev/null
+++ b/checkpoint-850/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637e0437b5818f76ea2fea2aa5b87010fc39a85bdfc12277d436c72e69d11811
+size 4155
diff --git a/checkpoint-900/README.md b/checkpoint-900/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b32efe7366f05d1d90816d2ad9e4b06ccca46bea
--- /dev/null
+++ b/checkpoint-900/README.md
@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-900/adapter_config.json b/checkpoint-900/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e108f2da037ef6250457c67a4bedd308d97303c
--- /dev/null
+++ b/checkpoint-900/adapter_config.json
@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-900/adapter_model.bin b/checkpoint-900/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b6aa9a248091ec8f16fffc872e10a7464bb96f4e
--- /dev/null
+++ b/checkpoint-900/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc5bb6d2dca558111c7797c47c4ff80cfc300763019d10afd07349ed4c4e7c2
+size 113314765
diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dd5a0d885972b9a095f4de24f891cc01bd808b5e
--- /dev/null
+++ b/checkpoint-900/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409911090683a3164a6f094e871c2ec66d7845a881e203a0c6a8accccd39d49a
+size 226653957
diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d8ac1e9824eadc10d5ab36b9f1e4f5b11bed815c
--- /dev/null
+++ b/checkpoint-900/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5316df01292faa701fefb2dbf38969222c4d35108e40f06ea0b5b51d1ebb790f
+size 14575
diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..29da9fabb05fa99da84ff222f0dd6768751b4ea1
--- /dev/null
+++ b/checkpoint-900/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e40400b355c64557f8d6f8ceef4b48a2f1b102c17edff2c48b8bb46663570c3
+size 627
diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..edbefbc12c210531da10262ffecc1d30baab6db5
--- /dev/null
+++ b/checkpoint-900/trainer_state.json
@@ -0,0 +1,5419 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7336622938981827,
+  "eval_steps": 500,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6869,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8396,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7489,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7252,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8022,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.6524,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6981,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7488,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6891,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7968,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6912,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8452,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 0.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6685,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5469,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7915,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.6e-05,
+      "loss": 0.7744,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.6804,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.4e-05,
+      "loss": 0.7796,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.706,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6798,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6333,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 0.6012,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.52,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6583,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.7354,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000116,
+      "loss": 0.6296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 0.6352,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000124,
+      "loss": 0.6007,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5659,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000132,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6639,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 0.5934,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000144,
+      "loss": 0.5233,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000148,
+      "loss": 0.5307,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000152,
+      "loss": 0.5928,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5908,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000164,
+      "loss": 0.5972,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000168,
+      "loss": 0.4825,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000172,
+      "loss": 0.6783,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 0.7633,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5988,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000188,
+      "loss": 0.6658,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000192,
+      "loss": 0.5945,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000196,
+      "loss": 0.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.6057,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.601,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.5566,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.5911,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.7636,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.5537,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000232,
+      "loss": 0.6474,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000236,
+      "loss": 0.6483,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00024,
+      "loss": 0.5021,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000244,
+      "loss": 0.5347,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000248,
+      "loss": 0.5791,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000252,
+      "loss": 0.5407,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.5298,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5685,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000264,
+      "loss": 0.5108,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000268,
+      "loss": 0.526,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6843,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000276,
+      "loss": 0.6608,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00028,
+      "loss": 0.5866,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000284,
+      "loss": 0.6422,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000288,
+      "loss": 0.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000292,
+      "loss": 0.5319,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000296,
+      "loss": 0.5977,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.5805,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000304,
+      "loss": 0.5209,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000308,
+      "loss": 0.6098,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.4665,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6882,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00032,
+      "loss": 0.5427,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000324,
+      "loss": 0.5345,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000328,
+      "loss": 0.663,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000332,
+      "loss": 0.5393,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000336,
+      "loss": 0.5711,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00034,
+      "loss": 0.5261,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000344,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000348,
+      "loss": 0.6329,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.4425,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6837,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00036,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000364,
+      "loss": 0.5615,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5434,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000376,
+      "loss": 0.5583,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00038,
+      "loss": 0.5299,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000384,
+      "loss": 0.532,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000388,
+      "loss": 0.5227,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000392,
+      "loss": 0.5275,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.4541,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004,
+      "loss": 0.6485,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003999995350775973,
+      "loss": 0.5438,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999814031255063,
+      "loss": 0.5997,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999581571134455,
+      "loss": 0.5322,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003999925612847867,
+      "loss": 0.484,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998837704800766,
+      "loss": 0.5961,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998326302046085,
+      "loss": 0.7405,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997721922592255,
+      "loss": 0.5802,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997024569249167,
+      "loss": 0.769,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999623424525898,
+      "loss": 0.5598,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999535095429608,
+      "loss": 0.6143,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039994374700467095,
+      "loss": 0.5766,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039993305488310836,
+      "loss": 0.7695,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999214332279831,
+      "loss": 0.7153,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999088820933269,
+      "loss": 0.5835,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039989540153749286,
+      "loss": 0.6634,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000399880991623155,
+      "loss": 0.6069,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998656524173082,
+      "loss": 0.7224,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000399849383991268,
+      "loss": 0.5884,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998321864206699,
+      "loss": 0.5122,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039981405978546924,
+      "loss": 0.6453,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997950041699408,
+      "loss": 0.4665,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997750196626785,
+      "loss": 0.5428,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039975410635659464,
+      "loss": 0.4365,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039973226434891995,
+      "loss": 0.5978,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039970949374120286,
+      "loss": 0.7729,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000399685794639309,
+      "loss": 0.6212,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039966116715342066,
+      "loss": 0.5426,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00039963561139803676,
+      "loss": 0.5782,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003996091274919716,
+      "loss": 0.6701,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995817155583548,
+      "loss": 0.6314,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995533757246307,
+      "loss": 0.6662,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995241081225573,
+      "loss": 0.5192,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994939128882065,
+      "loss": 0.5591,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994627901619625,
+      "loss": 0.5809,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994307400885219,
+      "loss": 0.4871,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993977628168928,
+      "loss": 0.6666,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993638585003938,
+      "loss": 0.6469,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039932902729665357,
+      "loss": 0.5727,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039929326936761036,
+      "loss": 0.6715,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039925658487951067,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039921897400290894,
+      "loss": 0.501,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039918043691266665,
+      "loss": 0.5795,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039914097378795124,
+      "loss": 0.6287,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039910058481223564,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039905927017329726,
+      "loss": 0.6232,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039901703006321715,
+      "loss": 0.5291,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039897386467837903,
+      "loss": 0.5297,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039892977421946844,
+      "loss": 0.5784,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988847588914718,
+      "loss": 0.5714,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988388189036754,
+      "loss": 0.5044,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987919544696646,
+      "loss": 0.8246,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987441658073226,
+      "loss": 0.5048,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003986954531388297,
+      "loss": 0.5433,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039864581669066186,
+      "loss": 0.5251,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003985952566935902,
+      "loss": 0.5708,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039854377338267936,
+      "loss": 0.6276,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039849136699728684,
+      "loss": 0.4915,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003984380377810617,
+      "loss": 0.6389,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039838378598194325,
+      "loss": 0.6067,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039832861185216045,
+      "loss": 0.6136,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003982725156482301,
+      "loss": 0.5597,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000398215497630956,
+      "loss": 0.5957,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003981575580654278,
+      "loss": 0.5853,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980986972210194,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980389153713881,
+      "loss": 0.5302,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039797821279447307,
+      "loss": 0.5395,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039791658977249425,
+      "loss": 0.7004,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039785404659195084,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039779058354362013,
+      "loss": 0.5759,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000397726200922556,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003976608990280877,
+      "loss": 0.5488,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975946781638183,
+      "loss": 0.6162,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975275386376236,
+      "loss": 0.558,
+      "step": 173
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003974594807616502,
+      "loss": 0.519,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003973905048523144,
+      "loss": 0.6195,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039732061123030064,
+      "loss": 0.5991,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003972498002205601,
+      "loss": 0.5428,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039717807215230896,
+      "loss": 0.5323,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039710542735902705,
+      "loss": 0.5307,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003970318661784564,
+      "loss": 0.5783,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003969573889525993,
+      "loss": 0.5924,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039688199602771714,
+      "loss": 0.5902,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039680568775432855,
+      "loss": 0.6291,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003967284644872077,
+      "loss": 0.5942,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003966503265853829,
+      "loss": 0.4878,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003965712744121347,
+      "loss": 0.6487,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003964913083349945,
+      "loss": 0.6111,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039641042872574233,
+      "loss": 0.6072,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039632863596040575,
+      "loss": 0.716,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039624593041925763,
+      "loss": 0.6178,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003961623124868145,
+      "loss": 0.6323,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039607778255183485,
+      "loss": 0.5821,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959923410073174,
+      "loss": 0.6738,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959059882504989,
+      "loss": 0.6203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039581872468285277,
+      "loss": 0.632,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003957305507100868,
+      "loss": 0.5857,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039564146674214164,
+      "loss": 0.6311,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003955514731931885,
+      "loss": 0.5889,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039546057048162763,
+      "loss": 0.5201,
+      "step": 199
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039536875903008607,
+      "loss": 0.5581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039527603926541586,
+      "loss": 0.5104,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039518241161869193,
+      "loss": 0.5978,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039508787652521013,
+      "loss": 0.6244,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039499243442448536,
+      "loss": 0.589,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003948960857602493,
+      "loss": 0.575,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947988309804485,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947006705372422,
+      "loss": 0.4895,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039460160488700036,
+      "loss": 0.5479,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039450163449030124,
+      "loss": 0.5893,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003944007598119297,
+      "loss": 0.5451,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003942989813208747,
+      "loss": 0.5582,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003941962994903273,
+      "loss": 0.5121,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039409271479767826,
+      "loss": 0.6324,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000393988227724516,
+      "loss": 0.6118,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003938828387566244,
+      "loss": 0.6303,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003937765483839804,
+      "loss": 0.7705,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003936693571007517,
+      "loss": 0.6224,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935612654052946,
+      "loss": 0.5664,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039345227380015163,
+      "loss": 0.66,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039334238279204906,
+      "loss": 0.5582,
+      "step": 220
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039323159289189505,
+      "loss": 0.6087,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003931199046147764,
+      "loss": 0.5566,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039300731847995716,
+      "loss": 0.5775,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039289383501087534,
+      "loss": 0.5081,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277945473514104,
+      "loss": 0.5218,
+      "step": 225
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003926641781845338,
+      "loss": 0.6655,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003925480058950002,
+      "loss": 0.5735,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039243093840665114,
+      "loss": 0.6609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003923129762637596,
+      "loss": 0.7323,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000392194120014758,
+      "loss": 0.5703,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039207437021223583,
+      "loss": 0.6545,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003919537274129366,
+      "loss": 0.521,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039183219217775564,
+      "loss": 0.5257,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003917097650717377,
+      "loss": 0.5487,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039158644666407365,
+      "loss": 0.4861,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039146223752809845,
+      "loss": 0.4928,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003913371382412883,
+      "loss": 0.5253,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039121114938525756,
+      "loss": 0.6155,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039108427154575684,
+      "loss": 0.55,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039095650531266967,
+      "loss": 0.6617,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039082785128000976,
+      "loss": 0.5198,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039069831004591866,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003905678822126625,
+      "loss": 0.5347,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039043656838662946,
+      "loss": 0.531,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039030436917832697,
+      "loss": 0.4884,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039017128520237883,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003900373170775222,
+      "loss": 0.5537,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038990246542660494,
+      "loss": 0.5753,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038976673087658256,
+      "loss": 0.5059,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038963011405851537,
+      "loss": 0.5118,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038949261560756565,
+      "loss": 0.5645,
+      "step": 251
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003893542361629944,
+      "loss": 0.5623,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038921497636815866,
+      "loss": 0.5216,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003890748368705085,
+      "loss": 0.4501,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003889338183215838,
+      "loss": 0.48,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038879192137701135,
+      "loss": 0.5218,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003886491466965018,
+      "loss": 0.5858,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038850549494384685,
+      "loss": 0.6124,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038836096678691536,
+      "loss": 0.4645,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038821556289765136,
+      "loss": 0.474,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038806928395207003,
+      "loss": 0.4364,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038792213063025484,
+      "loss": 0.5821,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003877741036163547,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003876252035985804,
+      "loss": 0.5373,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003874754312692013,
+      "loss": 0.6021,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003873247873245426,
+      "loss": 0.4549,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003871732724649817,
+      "loss": 0.5994,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003870208873949453,
+      "loss": 0.4764,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038686763282290556,
+      "loss": 0.4311,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003867135094613774,
+      "loss": 0.5462,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003865585180269148,
+      "loss": 0.5006,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003864026592401076,
+      "loss": 0.5347,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038624593382557835,
+      "loss": 0.5242,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038608834251197856,
+      "loss": 0.5005,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038592988603198554,
+      "loss": 0.5436,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000385770565122299,
+      "loss": 0.4658,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003856103805236375,
+      "loss": 0.5273,
+      "step": 277
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038544933298073516,
+      "loss": 0.436,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038528742324233804,
+      "loss": 0.4785,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038512465206120086,
+      "loss": 0.5366,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038496102019408324,
+      "loss": 0.4448,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038479652840174637,
+      "loss": 0.5132,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038463117744894955,
+      "loss": 0.7918,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038446496810444627,
+      "loss": 0.5309,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038429790114098114,
+      "loss": 0.5316,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038412997733528576,
+      "loss": 0.4611,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038396119746807563,
+      "loss": 0.4609,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038379156232404613,
+      "loss": 0.5821,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003836210726918691,
+      "loss": 0.5883,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003834497293641889,
+      "loss": 0.5012,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038327753313761913,
+      "loss": 0.4457,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038310448481273867,
+      "loss": 0.4851,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038293058519408787,
+      "loss": 0.5622,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038275583509016507,
+      "loss": 0.5703,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038258023531342265,
+      "loss": 0.5718,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003824037866802632,
+      "loss": 0.5183,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038222649001103614,
+      "loss": 0.5085,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038204834613003323,
+      "loss": 0.5388,
+      "step": 298
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038186935586548537,
+      "loss": 0.5425,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003816895200495584,
+      "loss": 0.447,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003815088395183493,
+      "loss": 0.5541,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038132731511188227,
+      "loss": 0.5518,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000381144947674105,
+      "loss": 0.5074,
+      "step": 303
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003809617380528847,
+      "loss": 0.5134,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003807776871000037,
+      "loss": 0.4599,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003805927956711562,
+      "loss": 0.5838,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038040706462594395,
+      "loss": 0.5216,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038022049482787216,
+      "loss": 0.5323,
+      "step": 308
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003800330871443456,
+      "loss": 0.5681,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00037984484244666446,
+      "loss": 0.4172,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003796557616100207,
+      "loss": 0.4958,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003794658455134934,
+      "loss": 0.662,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003792750950400451,
+      "loss": 0.5832,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003790835110765174,
+      "loss": 0.4271,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003788910945136271,
+      "loss": 0.4842,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037869784624596186,
+      "loss": 0.4656,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037850376717197626,
+      "loss": 0.4981,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037830885819398733,
+      "loss": 0.5162,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037811312021817067,
+      "loss": 0.652,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003779165541545558,
+      "loss": 0.5104,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003777191609170225,
+      "loss": 0.4971,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003775209414232962,
+      "loss": 0.4871,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003773218965949436,
+      "loss": 0.5226,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00037712202735736884,
+      "loss": 0.4823,
+      "step": 324
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003769213346398087,
+      "loss": 0.497,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003767198193753286,
+      "loss": 0.5976,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003765174825008181,
+      "loss": 0.4532,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003763143249569868,
+      "loss": 0.5236,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00037611034768835947,
+      "loss": 0.6513,
+      "step": 329
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037590555164327224,
+      "loss": 0.5686,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037569993777386774,
+      "loss": 0.456,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003754935070360909,
+      "loss": 0.5181,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003752862603896846,
+      "loss": 0.4765,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037507819879818477,
+      "loss": 0.5363,
+      "step": 334
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037486932322891646,
+      "loss": 0.4584,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037465963465298886,
+      "loss": 0.5428,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003744491340452913,
+      "loss": 0.3927,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003742378223844882,
+      "loss": 0.5478,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003740257006530147,
+      "loss": 0.469,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037381276983707246,
+      "loss": 0.5169,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037359903092662434,
+      "loss": 0.4797,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037338448491539054,
+      "loss": 0.5315,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037316913280084353,
+      "loss": 0.4422,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003729529755842035,
+      "loss": 0.4426,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003727360142704337,
+      "loss": 0.4718,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003725182498682361,
+      "loss": 0.5585,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003722996833900459,
+      "loss": 0.4775,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003720803158520279,
+      "loss": 0.6014,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00037186014827407076,
+      "loss": 0.5117,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003716391816797829,
+      "loss": 0.5404,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003714174170964876,
+      "loss": 0.527,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037119485555521796,
+      "loss": 0.4555,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037097149809071255,
+      "loss": 0.5372,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037074734574141016,
+      "loss": 0.5377,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003705223995494454,
+      "loss": 0.4925,
+      "step": 355
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037029666056064345,
+      "loss": 0.482,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037007012982451546,
+      "loss": 0.5235,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00036984280839425356,
+      "loss": 0.4957,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000369614697326726,
+      "loss": 0.5379,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003693857976824721,
+      "loss": 0.4653,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036915611052569785,
+      "loss": 0.469,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003689256369242702,
+      "loss": 0.5618,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003686943779497124,
+      "loss": 0.4459,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003684623346771995,
+      "loss": 0.5606,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003682295081855524,
+      "loss": 0.4368,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036799589955723375,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036776150987834243,
+      "loss": 0.4664,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036752634023860846,
+      "loss": 0.4737,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003672903917313883,
+      "loss": 0.4247,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036705366545365935,
+      "loss": 0.5677,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036681616250601505,
+      "loss": 0.5441,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003665778839926599,
+      "loss": 0.6247,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00036633883102140405,
+      "loss": 0.5217,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003660990047036584,
+      "loss": 0.4651,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003658584061544291,
+      "loss": 0.4648,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003656170364923128,
+      "loss": 0.6048,
+      "step": 376
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036537489683949114,
+      "loss": 0.4515,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003651319883217255,
+      "loss": 0.5096,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036488831206835207,
+      "loss": 0.4231,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036464386921227637,
+      "loss": 0.4903,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036439866088996796,
+      "loss": 0.5131,
+      "step": 381
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003641526882414553,
+      "loss": 0.5986,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003639059524103203,
+      "loss": 0.6,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003636584545436931,
+      "loss": 0.5216,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003634101957922468,
+      "loss": 0.5144,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00036316117731019184,
+      "loss": 0.4963,
+      "step": 386
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003629114002552711,
+      "loss": 0.5657,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036266086578875384,
+      "loss": 0.5028,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003624095750754311,
+      "loss": 0.573,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036215752928360967,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003619047295851068,
+      "loss": 0.656,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036165117715524506,
+      "loss": 0.5129,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036139687317284647,
+      "loss": 0.3945,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003611418188202271,
+      "loss": 0.5318,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036088601528319196,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036062946375102885,
+      "loss": 0.5407,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003603721654165034,
+      "loss": 0.5364,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00036011412147585306,
+      "loss": 0.5407,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003598553331287821,
+      "loss": 0.5999,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003595958015784555,
+      "loss": 0.624,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00035933552803149354,
+      "loss": 0.5351,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003590745136979662,
+      "loss": 0.5196,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035881275979138765,
+      "loss": 0.5447,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003585502675287104,
+      "loss": 0.4908,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035828703813031986,
+      "loss": 0.5172,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035802307282002834,
+      "loss": 0.5923,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003577583728250699,
+      "loss": 0.568,
+      "step": 407
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035749293937609395,
+      "loss": 0.4618,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003572267737071601,
+      "loss": 0.5351,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003569598770557322,
+      "loss": 0.5285,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035669225066267256,
+      "loss": 0.4571,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035642389577223625,
+      "loss": 0.4214,
+      "step": 412
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003561548136320653,
+      "loss": 0.5393,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003558850054931828,
+      "loss": 0.549,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035561447260998714,
+      "loss": 0.4824,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035534321624024656,
+      "loss": 0.6244,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035507123764509245,
+      "loss": 0.5436,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003547985380890144,
+      "loss": 0.5198,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035452511883985366,
+      "loss": 0.5979,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035425098116879754,
+      "loss": 0.4158,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035397612635037356,
+      "loss": 0.5125,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035370055566244334,
+      "loss": 0.4699,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003534242703861966,
+      "loss": 0.5553,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035314727180614573,
+      "loss": 0.5969,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035286956121011897,
+      "loss": 0.456,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003525911398892552,
+      "loss": 0.5195,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003523120091379975,
+      "loss": 0.5187,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035203217025408726,
+      "loss": 0.5443,
+      "step": 428
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003517516245385582,
+      "loss": 0.4476,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003514703732957301,
+      "loss": 0.5757,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035118841783320304,
+      "loss": 0.5129,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035090575946185114,
+      "loss": 0.6354,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035062239949581645,
+      "loss": 0.4065,
+      "step": 433
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000350338339252503,
+      "loss": 0.5472,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00035005358005257045,
+      "loss": 0.5424,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034976812321992816,
+      "loss": 0.6127,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034948197008172877,
+      "loss": 0.63,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003491951219683625,
+      "loss": 0.413,
+      "step": 438
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034890758021345034,
+      "loss": 0.5435,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034861934615383844,
+      "loss": 0.5433,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034833042112959153,
+      "loss": 0.4763,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034804080648398667,
+      "loss": 0.5727,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034775050356350727,
+      "loss": 0.5392,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034745951371783666,
+      "loss": 0.4981,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003471678382998518,
+      "loss": 0.5516,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00034687547866561703,
+      "loss": 0.4965,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003465824361743779,
+      "loss": 0.4982,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003462887121885544,
+      "loss": 0.5619,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003459943080737353,
+      "loss": 0.5273,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034569922519867133,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034540346493526876,
+      "loss": 0.4874,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003451070286585833,
+      "loss": 0.5966,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003448099177468137,
+      "loss": 0.4487,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003445121335812951,
+      "loss": 0.5091,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003442136775464929,
+      "loss": 0.407,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003439145510299958,
+      "loss": 0.6327,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00034361475542251025,
+      "loss": 0.4217,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003433142921178531,
+      "loss": 0.6102,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003430131625129456,
+      "loss": 0.5556,
+      "step": 459
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034271136800780673,
+      "loss": 0.4986,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003424089100055467,
+      "loss": 0.5406,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034210578991236056,
+      "loss": 0.5881,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034180200913752157,
+      "loss": 0.4869,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034149756909337454,
+      "loss": 0.5626,
+      "step": 464
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003411924711953295,
+      "loss": 0.564,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00034088671686185486,
+      "loss": 0.6272,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003405803075144711,
+      "loss": 0.4643,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003402732445777438,
+      "loss": 0.5435,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00033996552947927744,
+      "loss": 0.5844,
+      "step": 469
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003396571636497084,
+      "loss": 0.5362,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033934814852269865,
+      "loss": 0.5607,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003390384855349285,
+      "loss": 0.4836,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033872817612609065,
+      "loss": 0.6555,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033841722173888315,
+      "loss": 0.4784,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033810562381900253,
+      "loss": 0.5583,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033779338381513736,
+      "loss": 0.4679,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003374805031789613,
+      "loss": 0.5325,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033716698336512654,
+      "loss": 0.6601,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000336852825831257,
+      "loss": 0.4838,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003365380320379414,
+      "loss": 0.5588,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033622260344872665,
+      "loss": 0.4596,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003359065415301108,
+      "loss": 0.5228,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033558984775153663,
+      "loss": 0.5316,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033527252358538437,
+      "loss": 0.4761,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003349545705069653,
+      "loss": 0.5254,
+      "step": 485
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003346359899945144,
+      "loss": 0.4786,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033431678352918384,
+      "loss": 0.4302,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003339969525950361,
+      "loss": 0.4914,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033367649867903663,
+      "loss": 0.4102,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003333554232710477,
+      "loss": 0.4698,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003330337278638207,
+      "loss": 0.4454,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033271141395298964,
+      "loss": 0.4648,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033238848303706415,
+      "loss": 0.4616,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033206493661742237,
+      "loss": 0.4861,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033174077619830416,
+      "loss": 0.4797,
+      "step": 495
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033141600328680373,
+      "loss": 0.5104,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033109061939286336,
+      "loss": 0.5712,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033076462602926553,
+      "loss": 0.5425,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033043802471162636,
+      "loss": 0.6156,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003301108169583887,
+      "loss": 0.4282,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003297830042908146,
+      "loss": 0.4088,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032945458823297857,
+      "loss": 0.4866,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003291255703117605,
+      "loss": 0.5045,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003287959520568384,
+      "loss": 0.491,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032846573500068136,
+      "loss": 0.458,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032813492067854246,
+      "loss": 0.4508,
+      "step": 506
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003278035106284516,
+      "loss": 0.4294,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032747150639120834,
+      "loss": 0.4834,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032713890951037477,
+      "loss": 0.3857,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032680572153226834,
+      "loss": 0.4072,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003264719440059545,
+      "loss": 0.4028,
+      "step": 511
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032613757848323977,
+      "loss": 0.3789,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032580262651866446,
+      "loss": 0.4944,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003254670896694952,
+      "loss": 0.4259,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032513096949571805,
+      "loss": 0.5037,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032479426756003093,
+      "loss": 0.5857,
+      "step": 516
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003244569854278366,
+      "loss": 0.5407,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032411912466723524,
+      "loss": 0.499,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003237806868490172,
+      "loss": 0.4359,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032344167354665573,
+      "loss": 0.4374,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003231020863362997,
+      "loss": 0.4172,
+      "step": 521
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000322761926796766,
+      "loss": 0.4451,
+      "step": 522
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003224211965095326,
+      "loss": 0.4,
+      "step": 523
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003220798970587309,
+      "loss": 0.4009,
+      "step": 524
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003217380300311386,
+      "loss": 0.3966,
+      "step": 525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000321395597016172,
+      "loss": 0.4255,
+      "step": 526
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00032105259960587895,
+      "loss": 0.4707,
+      "step": 527
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00032070903939493124,
+      "loss": 0.5313,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003203649179806172,
+      "loss": 0.3596,
+      "step": 529
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003200202369628345,
+      "loss": 0.5223,
+      "step": 530
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031967499794408234,
+      "loss": 0.4146,
+      "step": 531
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031932920252945423,
+      "loss": 0.4328,
+      "step": 532
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003189828523266306,
+      "loss": 0.4258,
+      "step": 533
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031863594894587105,
+      "loss": 0.4457,
+      "step": 534
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003182884940000072,
+      "loss": 0.5249,
+      "step": 535
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003179404891044348,
+      "loss": 0.4751,
+      "step": 536
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031759193587710676,
+      "loss": 0.5378,
+      "step": 537
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031724283593852497,
+      "loss": 0.634,
+      "step": 538
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031689319091173326,
+      "loss": 0.4298,
+      "step": 539
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031654300242230977,
+      "loss": 0.5469,
+      "step": 540
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031619227209835917,
+      "loss": 0.5153,
+      "step": 541
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003158410015705053,
+      "loss": 0.4144,
+      "step": 542
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003154891924718837,
+      "loss": 0.6041,
+      "step": 543
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003151368464381335,
+      "loss": 0.4891,
+      "step": 544
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003147839651073904,
+      "loss": 0.5258,
+      "step": 545
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00031443055012027874,
+      "loss": 0.4351,
+      "step": 546
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000314076603119904,
+      "loss": 0.4556,
+      "step": 547
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031372212575184514,
+      "loss": 0.5445,
+      "step": 548
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031336711966414675,
+      "loss": 0.5585,
+      "step": 549
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003130115865073117,
+      "loss": 0.367,
+      "step": 550
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003126555279342933,
+      "loss": 0.4877,
+      "step": 551
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003122989456004876,
+      "loss": 0.4335,
+      "step": 552
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003119418411637258,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003115842162842663,
+      "loss": 0.4508,
+      "step": 554
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00031122607262478743,
+      "loss": 0.4631,
+      "step": 555
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003108674118503793,
+      "loss": 0.3496,
+      "step": 556
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003105082356285361,
+      "loss": 0.4108,
+      "step": 557
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003101485456291486,
+      "loss": 0.4877,
+      "step": 558
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030978834352449614,
+      "loss": 0.3696,
+      "step": 559
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030942763098923913,
+      "loss": 0.5138,
+      "step": 560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030906640970041084,
+      "loss": 0.5961,
+      "step": 561
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003087046813374099,
+      "loss": 0.3824,
+      "step": 562
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030834244758199276,
+      "loss": 0.4925,
+      "step": 563
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000307979710118265,
+      "loss": 0.4511,
+      "step": 564
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030761647063267457,
+      "loss": 0.4306,
+      "step": 565
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003072527308140031,
+      "loss": 0.468,
+      "step": 566
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030688849235335856,
+      "loss": 0.4842,
+      "step": 567
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003065237569441671,
+      "loss": 0.4332,
+      "step": 568
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030615852628216537,
+      "loss": 0.4637,
+      "step": 569
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003057928020653925,
+      "loss": 0.6193,
+      "step": 570
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003054265859941824,
+      "loss": 0.5033,
+      "step": 571
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030505987977115555,
+      "loss": 0.4185,
+      "step": 572
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003046926851012114,
+      "loss": 0.4211,
+      "step": 573
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003043250036915201,
+      "loss": 0.5089,
+      "step": 574
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00030395683725151505,
+      "loss": 0.517,
+      "step": 575
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003035881874928845,
+      "loss": 0.492,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003032190561295636,
+      "loss": 0.4535,
+      "step": 577
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003028494448777269,
+      "loss": 0.3947,
+      "step": 578
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030247935545577986,
+      "loss": 0.3125,
+      "step": 579
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003021087895843511,
+      "loss": 0.3882,
+      "step": 580
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003017377489862845,
+      "loss": 0.4802,
+      "step": 581
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030136623538663083,
+      "loss": 0.4652,
+      "step": 582
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030099425051263994,
+      "loss": 0.3816,
+      "step": 583
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003006217960937529,
+      "loss": 0.4583,
+      "step": 584
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00030024887386159385,
+      "loss": 0.4568,
+      "step": 585
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029987548554996174,
+      "loss": 0.3908,
+      "step": 586
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002995016328948225,
+      "loss": 0.4235,
+      "step": 587
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029912731763430075,
+      "loss": 0.4138,
+      "step": 588
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029875254150867216,
+      "loss": 0.5838,
+      "step": 589
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002983773062603548,
+      "loss": 0.462,
+      "step": 590
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029800161363390145,
+      "loss": 0.4632,
+      "step": 591
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029762546537599125,
+      "loss": 0.5898,
+      "step": 592
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002972488632354218,
+      "loss": 0.4742,
+      "step": 593
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029687180896310065,
+      "loss": 0.4579,
+      "step": 594
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002964943043120378,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029611635103733675,
+      "loss": 0.4304,
+      "step": 596
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002957379508961871,
+      "loss": 0.4383,
+      "step": 597
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029535910564785584,
+      "loss": 0.5327,
+      "step": 598
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029497981705367933,
+      "loss": 0.4781,
+      "step": 599
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029460008687705525,
+      "loss": 0.4178,
+      "step": 600
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002942199168834342,
+      "loss": 0.3987,
+      "step": 601
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029383930884031183,
+      "loss": 0.3861,
+      "step": 602
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029345826451722005,
+      "loss": 0.5322,
+      "step": 603
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029307678568571936,
+      "loss": 0.3997,
+      "step": 604
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002926948741193903,
+      "loss": 0.4121,
+      "step": 605
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029231253159382514,
+      "loss": 0.4931,
+      "step": 606
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029192975988662017,
+      "loss": 0.4626,
+      "step": 607
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029154656077736666,
+      "loss": 0.4441,
+      "step": 608
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002911629360476432,
+      "loss": 0.3863,
+      "step": 609
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029077888748100703,
+      "loss": 0.36,
+      "step": 610
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029039441686298594,
+      "loss": 0.4246,
+      "step": 611
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002900095259810702,
+      "loss": 0.4916,
+      "step": 612
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028962421662470346,
+      "loss": 0.4896,
+      "step": 613
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028923849058527535,
+      "loss": 0.4237,
+      "step": 614
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028885234965611274,
+      "loss": 0.5727,
+      "step": 615
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028846579563247116,
+      "loss": 0.5681,
+      "step": 616
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002880788303115269,
+      "loss": 0.4383,
+      "step": 617
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028769145549236845,
+      "loss": 0.4962,
+      "step": 618
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002873036729759881,
+      "loss": 0.5472,
+      "step": 619
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002869154845652738,
+      "loss": 0.5431,
+      "step": 620
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002865268920650003,
+      "loss": 0.4152,
+      "step": 621
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002861378972818211,
+      "loss": 0.3922,
+      "step": 622
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002857485020242602,
+      "loss": 0.5129,
+      "step": 623
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002853587081027034,
+      "loss": 0.4328,
+      "step": 624
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00028496851732938997,
+      "loss": 0.4431,
+      "step": 625
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002845779315184042,
+      "loss": 0.4968,
+      "step": 626
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.000284186952485667,
+      "loss": 0.5301,
+      "step": 627
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002837955820489276,
+      "loss": 0.4332,
+      "step": 628
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002834038220277546,
+      "loss": 0.4245,
+      "step": 629
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00028301167424352836,
+      "loss": 0.5057,
+      "step": 630
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028261914051943166,
+      "loss": 0.4623,
+      "step": 631
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028222622268044174,
+      "loss": 0.5452,
+      "step": 632
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028183292255332164,
+      "loss": 0.5238,
+      "step": 633
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028143924196661176,
+      "loss": 0.3966,
+      "step": 634
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002810451827506214,
+      "loss": 0.35,
+      "step": 635
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00028065074673742007,
+      "loss": 0.4325,
+      "step": 636
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0002802559357608292,
+      "loss": 0.4854,
+      "step": 637
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027986075165641343,
+      "loss": 0.4254,
+      "step": 638
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027946519626147225,
+      "loss": 0.4614,
+      "step": 639
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027906927141503125,
+      "loss": 0.3798,
+      "step": 640
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027867297895783373,
+      "loss": 0.4742,
+      "step": 641
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002782763207323322,
+      "loss": 0.4007,
+      "step": 642
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002778792985826795,
+      "loss": 0.4383,
+      "step": 643
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002774819143547206,
+      "loss": 0.4298,
+      "step": 644
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00027708416989598387,
+      "loss": 0.5178,
+      "step": 645
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002766860670556722,
+      "loss": 0.3434,
+      "step": 646
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002762876076846551,
+      "loss": 0.3862,
+      "step": 647
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027588879363545934,
+      "loss": 0.4459,
+      "step": 648
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002754896267622608,
+      "loss": 0.3934,
+      "step": 649
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027509010892087565,
+      "loss": 0.4349,
+      "step": 650
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000274690241968752,
+      "loss": 0.4178,
+      "step": 651
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002742900277649607,
+      "loss": 0.4151,
+      "step": 652
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002738894681701874,
+      "loss": 0.3888,
+      "step": 653
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027348856504672323,
+      "loss": 0.4214,
+      "step": 654
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002730873202584567,
+      "loss": 0.519,
+      "step": 655
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027268573567086477,
+      "loss": 0.5463,
+      "step": 656
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027228381315100417,
+      "loss": 0.3367,
+      "step": 657
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027188155456750256,
+      "loss": 0.4629,
+      "step": 658
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027147896179055043,
+      "loss": 0.4456,
+      "step": 659
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002710760366918917,
+      "loss": 0.4348,
+      "step": 660
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002706727811448153,
+      "loss": 0.4505,
+      "step": 661
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002702691970241468,
+      "loss": 0.5028,
+      "step": 662
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026986528620623904,
+      "loss": 0.5257,
+      "step": 663
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026946105056896403,
+      "loss": 0.4977,
+      "step": 664
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026905649199170377,
+      "loss": 0.421,
+      "step": 665
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002686516123553417,
+      "loss": 0.4931,
+      "step": 666
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026824641354225397,
+      "loss": 0.5818,
+      "step": 667
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002678408974363005,
+      "loss": 0.4211,
+      "step": 668
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026743506592281674,
+      "loss": 0.5182,
+      "step": 669
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026702892088860413,
+      "loss": 0.5591,
+      "step": 670
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002666224642219221,
+      "loss": 0.5363,
+      "step": 671
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002662156978124786,
+      "loss": 0.5866,
+      "step": 672
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002658086235514218,
+      "loss": 0.422,
+      "step": 673
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002654012433313312,
+      "loss": 0.5375,
+      "step": 674
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002649935590462087,
+      "loss": 0.4752,
+      "step": 675
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00026458557259146986,
+      "loss": 0.4271,
+      "step": 676
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002641772858639351,
+      "loss": 0.4843,
+      "step": 677
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026376870076182086,
+      "loss": 0.4827,
+      "step": 678
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026335981918473086,
+      "loss": 0.47,
+      "step": 679
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002629506430336472,
+      "loss": 0.368,
+      "step": 680
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026254117421092133,
+      "loss": 0.481,
+      "step": 681
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002621314146202656,
+      "loss": 0.4153,
+      "step": 682
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002617213661667443,
+      "loss": 0.4397,
+      "step": 683
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002613110307567643,
+      "loss": 0.4052,
+      "step": 684
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026090041029806695,
+      "loss": 0.4652,
+      "step": 685
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026048950669971884,
+      "loss": 0.3826,
+      "step": 686
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026007832187210277,
+      "loss": 0.5639,
+      "step": 687
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025966685772690906,
+      "loss": 0.3917,
+      "step": 688
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025925511617712685,
+      "loss": 0.5248,
+      "step": 689
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002588430991370347,
+      "loss": 0.3796,
+      "step": 690
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002584308085221922,
+      "loss": 0.4391,
+      "step": 691
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025801824624943084,
+      "loss": 0.4514,
+      "step": 692
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025760541423684496,
+      "loss": 0.5046,
+      "step": 693
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002571923144037831,
+      "loss": 0.4578,
+      "step": 694
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002567789486708389,
+      "loss": 0.4681,
+      "step": 695
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025636531895984236,
+      "loss": 0.4501,
+      "step": 696
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002559514271938506,
+      "loss": 0.4411,
+      "step": 697
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025553727529713916,
+      "loss": 0.401,
+      "step": 698
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025512286519519293,
+      "loss": 0.4911,
+      "step": 699
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002547081988146974,
+      "loss": 0.3754,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025429327808352946,
+      "loss": 0.3807,
+      "step": 701
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002538781049307486,
+      "loss": 0.4193,
+      "step": 702
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002534626812865876,
+      "loss": 0.5259,
+      "step": 703
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00025304700908244433,
+      "loss": 0.3684,
+      "step": 704
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002526310902508718,
+      "loss": 0.5423,
+      "step": 705
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002522149267255699,
+      "loss": 0.4288,
+      "step": 706
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.000251798520441376,
+      "loss": 0.5046,
+      "step": 707
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002513818733342564,
+      "loss": 0.3777,
+      "step": 708
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025096498734129667,
+      "loss": 0.5171,
+      "step": 709
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0002505478644006932,
+      "loss": 0.3785,
+      "step": 710
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025013050645174414,
+      "loss": 0.5413,
+      "step": 711
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024971291543483994,
+      "loss": 0.5018,
+      "step": 712
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024929509329145477,
+      "loss": 0.5212,
+      "step": 713
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024887704196413746,
+      "loss": 0.483,
+      "step": 714
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002484587633965023,
+      "loss": 0.3684,
+      "step": 715
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024804025953322005,
+      "loss": 0.3782,
+      "step": 716
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024762153232000877,
+      "loss": 0.4995,
+      "step": 717
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002472025837036253,
+      "loss": 0.4324,
+      "step": 718
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002467834156318555,
+      "loss": 0.5203,
+      "step": 719
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002463640300535057,
+      "loss": 0.423,
+      "step": 720
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002459444289183933,
+      "loss": 0.4537,
+      "step": 721
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00024552461417733817,
+      "loss": 0.4124,
+      "step": 722
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002451045877821528,
+      "loss": 0.4865,
+      "step": 723
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002446843516856343,
+      "loss": 0.4845,
+      "step": 724
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024426390784155425,
+      "loss": 0.4174,
+      "step": 725
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024384325820465033,
+      "loss": 0.4456,
+      "step": 726
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002434224047306169,
+      "loss": 0.4429,
+      "step": 727
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002430013493760961,
+      "loss": 0.363,
+      "step": 728
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024258009409866853,
+      "loss": 0.4769,
+      "step": 729
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024215864085684442,
+      "loss": 0.4597,
+      "step": 730
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024173699161005429,
+      "loss": 0.366,
+      "step": 731
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024131514831863995,
+      "loss": 0.4746,
+      "step": 732
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0002408931129438453,
+      "loss": 0.5608,
+      "step": 733
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024047088744780744,
+      "loss": 0.4292,
+      "step": 734
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00024004847379354726,
+      "loss": 0.4743,
+      "step": 735
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023962587394496038,
+      "loss": 0.3855,
+      "step": 736
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023920308986680834,
+      "loss": 0.4573,
+      "step": 737
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023878012352470892,
+      "loss": 0.3937,
+      "step": 738
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0002383569768851274,
+      "loss": 0.4371,
+      "step": 739
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023793365191536735,
+      "loss": 0.5432,
+      "step": 740
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023751015058356135,
+      "loss": 0.4803,
+      "step": 741
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.000237086474858662,
+      "loss": 0.4281,
+      "step": 742
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023666262671043263,
+      "loss": 0.4031,
+      "step": 743
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023623860810943826,
+      "loss": 0.4725,
+      "step": 744
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0002358144210270364,
+      "loss": 0.4644,
+      "step": 745
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023539006743536774,
+      "loss": 0.4848,
+      "step": 746
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023496554930734718,
+      "loss": 0.4084,
+      "step": 747
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023454086861665472,
+      "loss": 0.4322,
+      "step": 748
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023411602733772595,
+      "loss": 0.4847,
+      "step": 749
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023369102744574312,
+      "loss": 0.4298,
+      "step": 750
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023326587091662603,
+      "loss": 0.4268,
+      "step": 751
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023284055972702254,
+      "loss": 0.4089,
+      "step": 752
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0002324150958542997,
+      "loss": 0.4214,
+      "step": 753
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023198948127653446,
+      "loss": 0.5576,
+      "step": 754
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023156371797250418,
+      "loss": 0.4377,
+      "step": 755
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00023113780792167785,
+      "loss": 0.4934,
+      "step": 756
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002307117531042068,
+      "loss": 0.3698,
+      "step": 757
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00023028555550091536,
+      "loss": 0.4722,
+      "step": 758
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00022985921709329157,
+      "loss": 0.3837,
+      "step": 759
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00022943273986347822,
+      "loss": 0.5132,
+      "step": 760
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002290061257942635,
+      "loss": 0.487,
+      "step": 761
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022857937686907183,
+      "loss": 0.3857,
+      "step": 762
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022815249507195445,
+      "loss": 0.4135,
+      "step": 763
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022772548238758064,
+      "loss": 0.4639,
+      "step": 764
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022729834080122791,
+      "loss": 0.5297,
+      "step": 765
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022687107229877324,
+      "loss": 0.4485,
+      "step": 766
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022644367886668357,
+      "loss": 0.467,
+      "step": 767
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022601616249200675,
+      "loss": 0.4304,
+      "step": 768
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022558852516236217,
+      "loss": 0.5531,
+      "step": 769
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022516076886593158,
+      "loss": 0.5021,
+      "step": 770
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022473289559144988,
+      "loss": 0.433,
+      "step": 771
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022430490732819566,
+      "loss": 0.505,
+      "step": 772
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022387680606598235,
+      "loss": 0.4677,
+      "step": 773
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022344859379514858,
+      "loss": 0.4421,
+      "step": 774
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022302027250654905,
+      "loss": 0.4282,
+      "step": 775
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0002225918441915456,
+      "loss": 0.366,
+      "step": 776
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022216331084199724,
+      "loss": 0.4147,
+      "step": 777
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022173467445025158,
+      "loss": 0.586,
+      "step": 778
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022130593700913522,
+      "loss": 0.5285,
+      "step": 779
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022087710051194463,
+      "loss": 0.4484,
+      "step": 780
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0002204481669524367,
+      "loss": 0.4063,
+      "step": 781
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002200191383248197,
+      "loss": 0.4751,
+      "step": 782
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021959001662374373,
+      "loss": 0.3936,
+      "step": 783
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021916080384429184,
+      "loss": 0.4433,
+      "step": 784
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002187315019819703,
+      "loss": 0.4883,
+      "step": 785
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021830211303269965,
+      "loss": 0.4925,
+      "step": 786
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021787263899280537,
+      "loss": 0.4597,
+      "step": 787
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021744308185900848,
+      "loss": 0.4954,
+      "step": 788
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021701344362841626,
+      "loss": 0.4025,
+      "step": 789
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021658372629851318,
+      "loss": 0.5734,
+      "step": 790
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021615393186715128,
+      "loss": 0.3779,
+      "step": 791
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021572406233254116,
+      "loss": 0.4994,
+      "step": 792
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021529411969324275,
+      "loss": 0.5359,
+      "step": 793
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021486410594815554,
+      "loss": 0.4738,
+      "step": 794
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021443402309650979,
+      "loss": 0.4915,
+      "step": 795
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021400387313785704,
+      "loss": 0.4991,
+      "step": 796
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021357365807206087,
+      "loss": 0.4503,
+      "step": 797
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0002131433798992874,
+      "loss": 0.4887,
+      "step": 798
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021271304061999633,
+      "loss": 0.4279,
+      "step": 799
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021228264223493139,
+      "loss": 0.5367,
+      "step": 800
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021185218674511097,
+      "loss": 0.3212,
+      "step": 801
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021142167615181915,
+      "loss": 0.493,
+      "step": 802
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002109911124565962,
+      "loss": 0.3635,
+      "step": 803
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00021056049766122916,
+      "loss": 0.3494,
+      "step": 804
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00021012983376774254,
+      "loss": 0.3536,
+      "step": 805
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002096991227783895,
+      "loss": 0.4335,
+      "step": 806
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00020926836669564168,
+      "loss": 0.4673,
+      "step": 807
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020883756752218075,
+      "loss": 0.5269,
+      "step": 808
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0002084067272608886,
+      "loss": 0.4365,
+      "step": 809
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020797584791483806,
+      "loss": 0.2998,
+      "step": 810
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020754493148728375,
+      "loss": 0.4318,
+      "step": 811
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020711397998165264,
+      "loss": 0.3205,
+      "step": 812
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020668299540153493,
+      "loss": 0.5026,
+      "step": 813
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020625197975067438,
+      "loss": 0.3923,
+      "step": 814
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0002058209350329594,
+      "loss": 0.3026,
+      "step": 815
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020538986325241342,
+      "loss": 0.4729,
+      "step": 816
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020495876641318567,
+      "loss": 0.3236,
+      "step": 817
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0002045276465195419,
+      "loss": 0.4934,
+      "step": 818
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020409650557585523,
+      "loss": 0.3791,
+      "step": 819
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020366534558659635,
+      "loss": 0.3879,
+      "step": 820
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020323416855632477,
+      "loss": 0.3807,
+      "step": 821
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020280297648967897,
+      "loss": 0.415,
+      "step": 822
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020237177139136758,
+      "loss": 0.3824,
+      "step": 823
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0002019405552661596,
+      "loss": 0.3854,
+      "step": 824
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020150933011887543,
+      "loss": 0.3781,
+      "step": 825
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020107809795437745,
+      "loss": 0.3904,
+      "step": 826
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020064686077756057,
+      "loss": 0.3213,
+      "step": 827
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00020021562059334302,
+      "loss": 0.4888,
+      "step": 828
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019978437940665702,
+      "loss": 0.3375,
+      "step": 829
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001993531392224394,
+      "loss": 0.4325,
+      "step": 830
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019892190204562257,
+      "loss": 0.2865,
+      "step": 831
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001984906698811246,
+      "loss": 0.3984,
+      "step": 832
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019805944473384038,
+      "loss": 0.3011,
+      "step": 833
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019762822860863247,
+      "loss": 0.4063,
+      "step": 834
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019719702351032105,
+      "loss": 0.4489,
+      "step": 835
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019676583144367525,
+      "loss": 0.3991,
+      "step": 836
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019633465441340367,
+      "loss": 0.2736,
+      "step": 837
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019590349442414484,
+      "loss": 0.3842,
+      "step": 838
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0001954723534804581,
+      "loss": 0.346,
+      "step": 839
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0001950412335868144,
+      "loss": 0.3435,
+      "step": 840
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019461013674758668,
+      "loss": 0.4139,
+      "step": 841
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019417906496704064,
+      "loss": 0.4031,
+      "step": 842
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019374802024932567,
+      "loss": 0.352,
+      "step": 843
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019331700459846517,
+      "loss": 0.332,
+      "step": 844
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019288602001834735,
+      "loss": 0.3822,
+      "step": 845
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019245506851271632,
+      "loss": 0.3912,
+      "step": 846
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.000192024152085162,
+      "loss": 0.4028,
+      "step": 847
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019159327273911145,
+      "loss": 0.3625,
+      "step": 848
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00019116243247781927,
+      "loss": 0.392,
+      "step": 849
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00019073163330435842,
+      "loss": 0.3687,
+      "step": 850
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00019030087722161055,
+      "loss": 0.3794,
+      "step": 851
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00018987016623225747,
+      "loss": 0.4095,
+      "step": 852
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00018943950233877094,
+      "loss": 0.3665,
+      "step": 853
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00018900888754340382,
+      "loss": 0.3826,
+      "step": 854
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001885783238481809,
+      "loss": 0.4903,
+      "step": 855
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00018814781325488905,
+      "loss": 0.3174,
+      "step": 856
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00018771735776506866,
+      "loss": 0.3987,
+      "step": 857
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001872869593800037,
+      "loss": 0.4488,
+      "step": 858
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00018685662010071261,
+      "loss": 0.3298,
+      "step": 859
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001864263419279392,
+      "loss": 0.3385,
+      "step": 860
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00018599612686214304,
+      "loss": 0.4442,
+      "step": 861
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00018556597690349023,
+      "loss": 0.3132,
+      "step": 862
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001851358940518445,
+      "loss": 0.5051,
+      "step": 863
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001847058803067573,
+      "loss": 0.3919,
+      "step": 864
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00018427593766745884,
+      "loss": 0.4193,
+      "step": 865
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001838460681328488,
+      "loss": 0.3196,
+      "step": 866
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00018341627370148692,
+      "loss": 0.6047,
+      "step": 867
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00018298655637158376,
+      "loss": 0.3741,
+      "step": 868
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00018255691814099157,
+      "loss": 0.4033,
+      "step": 869
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018212736100719465,
+      "loss": 0.422,
+      "step": 870
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018169788696730034,
+      "loss": 0.3358,
+      "step": 871
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018126849801802976,
+      "loss": 0.3295,
+      "step": 872
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018083919615570823,
+      "loss": 0.4859,
+      "step": 873
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018040998337625627,
+      "loss": 0.2917,
+      "step": 874
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00017998086167518034,
+      "loss": 0.3505,
+      "step": 875
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00017955183304756332,
+      "loss": 0.5962,
+      "step": 876
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0001791228994880554,
+      "loss": 0.3097,
+      "step": 877
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00017869406299086482,
+      "loss": 0.4547,
+      "step": 878
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0001782653255497485,
+      "loss": 0.4567,
+      "step": 879
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0001778366891580028,
+      "loss": 0.3815,
+      "step": 880
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00017740815580845446,
+      "loss": 0.5061,
+      "step": 881
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00017697972749345094,
+      "loss": 0.3729,
+      "step": 882
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0001765514062048515,
+      "loss": 0.3626,
+      "step": 883
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00017612319393401772,
+      "loss": 0.4256,
+      "step": 884
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00017569509267180433,
+      "loss": 0.4114,
+      "step": 885
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017526710440855017,
+      "loss": 0.3554,
+      "step": 886
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017483923113406844,
+      "loss": 0.4741,
+      "step": 887
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017441147483763785,
+      "loss": 0.4472,
+      "step": 888
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017398383750799327,
+      "loss": 0.4325,
+      "step": 889
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017355632113331648,
+      "loss": 0.4184,
+      "step": 890
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00017312892770122678,
+      "loss": 0.468,
+      "step": 891
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0001727016591987721,
+      "loss": 0.3996,
+      "step": 892
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00017227451761241938,
+      "loss": 0.4718,
+      "step": 893
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00017184750492804554,
+      "loss": 0.4076,
+      "step": 894
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00017142062313092824,
+      "loss": 0.337,
+      "step": 895
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00017099387420573656,
+      "loss": 0.3534,
+      "step": 896
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0001705672601365218,
+      "loss": 0.4757,
+      "step": 897
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00017014078290670848,
+      "loss": 0.4629,
+      "step": 898
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00016971444449908474,
+      "loss": 0.4999,
+      "step": 899
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0001692882468957932,
+      "loss": 0.4404,
+      "step": 900
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1557,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 1.2058110331294188e+18,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4843df7aa1383a371fb28dea27d303b1a1145e1
--- /dev/null
+++ b/checkpoint-900/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637e0437b5818f76ea2fea2aa5b87010fc39a85bdfc12277d436c72e69d11811
+size 4155
diff --git a/checkpoint-950/README.md b/checkpoint-950/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b32efe7366f05d1d90816d2ad9e4b06ccca46bea
--- /dev/null
+++ b/checkpoint-950/README.md
@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-950/adapter_config.json b/checkpoint-950/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e108f2da037ef6250457c67a4bedd308d97303c
--- /dev/null
+++ b/checkpoint-950/adapter_config.json
@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-950/adapter_model.bin b/checkpoint-950/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5de3f3e6c9e61b9bd3e08f609bbd9ec5373788b9
--- /dev/null
+++ b/checkpoint-950/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beeedc987a15ea2421995f369107f9b533b5d424088562667fdc59e9d36e27f2
+size 113314765
diff --git a/checkpoint-950/optimizer.pt b/checkpoint-950/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b9a2adbd936e4e5164b8b782b00f4dd32ac8ac4b
--- /dev/null
+++ b/checkpoint-950/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f291998fa6fdd299a4b6a2daf74ba021219c7af0a4c81a473fecf5f70351cc8
+size 226653957
diff --git a/checkpoint-950/rng_state.pth b/checkpoint-950/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5d897fb7deed86b4ea7454db56275119d91fad93
--- /dev/null
+++ b/checkpoint-950/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7403abf508f51b347013a05e6d43ff6eebbe64a861e58d2f63602d8fb86d8c62
+size 14575
diff --git a/checkpoint-950/scheduler.pt b/checkpoint-950/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bedc35738530bf6c63f435291f87d9c1e18bdd7e
--- /dev/null
+++ b/checkpoint-950/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0eb2a89b97372834b870845c6014b3a93146e0ed69632269d8d4bad9b0c7744
+size 627
diff --git a/checkpoint-950/trainer_state.json b/checkpoint-950/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..17b02232b2fa8afa8fc7e49e39ea063dc98db121
--- /dev/null
+++ b/checkpoint-950/trainer_state.json
@@ -0,0 +1,5719 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8299434348297028,
+  "eval_steps": 500,
+  "global_step": 950,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6869,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8396,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7489,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7252,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.6548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8022,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.6524,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6981,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7488,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6891,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7968,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6912,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8452,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 0.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6685,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5469,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7915,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.6e-05,
+      "loss": 0.7744,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.6804,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.4e-05,
+      "loss": 0.7796,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.706,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6798,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6333,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 0.6012,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.52,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6583,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.7354,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000116,
+      "loss": 0.6296,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 0.6352,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000124,
+      "loss": 0.6007,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5659,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000132,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6639,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00014,
+      "loss": 0.5934,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000144,
+      "loss": 0.5233,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000148,
+      "loss": 0.5307,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000152,
+      "loss": 0.5928,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5908,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00016,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000164,
+      "loss": 0.5972,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000168,
+      "loss": 0.4825,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000172,
+      "loss": 0.6783,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018,
+      "loss": 0.7633,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5988,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000188,
+      "loss": 0.6658,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000192,
+      "loss": 0.5945,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000196,
+      "loss": 0.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.6057,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.601,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.5566,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.5911,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.7636,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.5537,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000232,
+      "loss": 0.6474,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000236,
+      "loss": 0.6483,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00024,
+      "loss": 0.5021,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000244,
+      "loss": 0.5347,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000248,
+      "loss": 0.5791,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000252,
+      "loss": 0.5407,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.5298,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5685,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000264,
+      "loss": 0.5108,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000268,
+      "loss": 0.526,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6843,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000276,
+      "loss": 0.6608,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00028,
+      "loss": 0.5866,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000284,
+      "loss": 0.6422,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000288,
+      "loss": 0.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000292,
+      "loss": 0.5319,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000296,
+      "loss": 0.5977,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.5805,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000304,
+      "loss": 0.5209,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000308,
+      "loss": 0.6098,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.4665,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6882,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00032,
+      "loss": 0.5427,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000324,
+      "loss": 0.5345,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000328,
+      "loss": 0.663,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000332,
+      "loss": 0.5393,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000336,
+      "loss": 0.5711,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00034,
+      "loss": 0.5261,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000344,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000348,
+      "loss": 0.6329,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.4425,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6837,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00036,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000364,
+      "loss": 0.5615,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5434,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000376,
+      "loss": 0.5583,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00038,
+      "loss": 0.5299,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000384,
+      "loss": 0.532,
+      "step": 96
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000388,
+      "loss": 0.5227,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000392,
+      "loss": 0.5275,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.4541,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004,
+      "loss": 0.6485,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003999995350775973,
+      "loss": 0.5438,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999814031255063,
+      "loss": 0.5997,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039999581571134455,
+      "loss": 0.5322,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003999925612847867,
+      "loss": 0.484,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998837704800766,
+      "loss": 0.5961,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00039998326302046085,
+      "loss": 0.7405,
+      "step": 106
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997721922592255,
+      "loss": 0.5802,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039997024569249167,
+      "loss": 0.769,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999623424525898,
+      "loss": 0.5598,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003999535095429608,
+      "loss": 0.6143,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00039994374700467095,
+      "loss": 0.5766,
+      "step": 111
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039993305488310836,
+      "loss": 0.7695,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999214332279831,
+      "loss": 0.7153,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003999088820933269,
+      "loss": 0.5835,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00039989540153749286,
+      "loss": 0.6634,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000399880991623155,
+      "loss": 0.6069,
+      "step": 116
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998656524173082,
+      "loss": 0.7224,
+      "step": 117
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000399849383991268,
+      "loss": 0.5884,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003998321864206699,
+      "loss": 0.5122,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039981405978546924,
+      "loss": 0.6453,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997950041699408,
+      "loss": 0.4665,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003997750196626785,
+      "loss": 0.5428,
+      "step": 122
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039975410635659464,
+      "loss": 0.4365,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039973226434891995,
+      "loss": 0.5978,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039970949374120286,
+      "loss": 0.7729,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000399685794639309,
+      "loss": 0.6212,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039966116715342066,
+      "loss": 0.5426,
+      "step": 127
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00039963561139803676,
+      "loss": 0.5782,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003996091274919716,
+      "loss": 0.6701,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995817155583548,
+      "loss": 0.6314,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995533757246307,
+      "loss": 0.6662,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003995241081225573,
+      "loss": 0.5192,
+      "step": 132
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994939128882065,
+      "loss": 0.5591,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994627901619625,
+      "loss": 0.5809,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003994307400885219,
+      "loss": 0.4871,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993977628168928,
+      "loss": 0.6666,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003993638585003938,
+      "loss": 0.6469,
+      "step": 137
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039932902729665357,
+      "loss": 0.5727,
+      "step": 138
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039929326936761036,
+      "loss": 0.6715,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039925658487951067,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039921897400290894,
+      "loss": 0.501,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00039918043691266665,
+      "loss": 0.5795,
+      "step": 142
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039914097378795124,
+      "loss": 0.6287,
+      "step": 143
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039910058481223564,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039905927017329726,
+      "loss": 0.6232,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039901703006321715,
+      "loss": 0.5291,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039897386467837903,
+      "loss": 0.5297,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039892977421946844,
+      "loss": 0.5784,
+      "step": 148
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988847588914718,
+      "loss": 0.5714,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003988388189036754,
+      "loss": 0.5044,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987919544696646,
+      "loss": 0.8246,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003987441658073226,
+      "loss": 0.5048,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003986954531388297,
+      "loss": 0.5433,
+      "step": 153
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039864581669066186,
+      "loss": 0.5251,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003985952566935902,
+      "loss": 0.5708,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039854377338267936,
+      "loss": 0.6276,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039849136699728684,
+      "loss": 0.4915,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003984380377810617,
+      "loss": 0.6389,
+      "step": 158
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039838378598194325,
+      "loss": 0.6067,
+      "step": 159
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039832861185216045,
+      "loss": 0.6136,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003982725156482301,
+      "loss": 0.5597,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000398215497630956,
+      "loss": 0.5957,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003981575580654278,
+      "loss": 0.5853,
+      "step": 163
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980986972210194,
+      "loss": 0.5462,
+      "step": 164
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003980389153713881,
+      "loss": 0.5302,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039797821279447307,
+      "loss": 0.5395,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039791658977249425,
+      "loss": 0.7004,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039785404659195084,
+      "loss": 0.5622,
+      "step": 168
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039779058354362013,
+      "loss": 0.5759,
+      "step": 169
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000397726200922556,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003976608990280877,
+      "loss": 0.5488,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975946781638183,
+      "loss": 0.6162,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003975275386376236,
+      "loss": 0.558,
+      "step": 173
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003974594807616502,
+      "loss": 0.519,
+      "step": 174
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003973905048523144,
+      "loss": 0.6195,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039732061123030064,
+      "loss": 0.5991,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003972498002205601,
+      "loss": 0.5428,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039717807215230896,
+      "loss": 0.5323,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039710542735902705,
+      "loss": 0.5307,
+      "step": 179
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003970318661784564,
+      "loss": 0.5783,
+      "step": 180
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003969573889525993,
+      "loss": 0.5924,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039688199602771714,
+      "loss": 0.5902,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039680568775432855,
+      "loss": 0.6291,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003967284644872077,
+      "loss": 0.5942,
+      "step": 184
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003966503265853829,
+      "loss": 0.4878,
+      "step": 185
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003965712744121347,
+      "loss": 0.6487,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003964913083349945,
+      "loss": 0.6111,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039641042872574233,
+      "loss": 0.6072,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039632863596040575,
+      "loss": 0.716,
+      "step": 189
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039624593041925763,
+      "loss": 0.6178,
+      "step": 190
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003961623124868145,
+      "loss": 0.6323,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039607778255183485,
+      "loss": 0.5821,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959923410073174,
+      "loss": 0.6738,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003959059882504989,
+      "loss": 0.6203,
+      "step": 194
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039581872468285277,
+      "loss": 0.632,
+      "step": 195
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003957305507100868,
+      "loss": 0.5857,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039564146674214164,
+      "loss": 0.6311,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003955514731931885,
+      "loss": 0.5889,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039546057048162763,
+      "loss": 0.5201,
+      "step": 199
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039536875903008607,
+      "loss": 0.5581,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039527603926541586,
+      "loss": 0.5104,
+      "step": 201
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039518241161869193,
+      "loss": 0.5978,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039508787652521013,
+      "loss": 0.6244,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039499243442448536,
+      "loss": 0.589,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003948960857602493,
+      "loss": 0.575,
+      "step": 205
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947988309804485,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003947006705372422,
+      "loss": 0.4895,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039460160488700036,
+      "loss": 0.5479,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039450163449030124,
+      "loss": 0.5893,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003944007598119297,
+      "loss": 0.5451,
+      "step": 210
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003942989813208747,
+      "loss": 0.5582,
+      "step": 211
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003941962994903273,
+      "loss": 0.5121,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039409271479767826,
+      "loss": 0.6324,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000393988227724516,
+      "loss": 0.6118,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003938828387566244,
+      "loss": 0.6303,
+      "step": 215
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003937765483839804,
+      "loss": 0.7705,
+      "step": 216
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003936693571007517,
+      "loss": 0.6224,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935612654052946,
+      "loss": 0.5664,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039345227380015163,
+      "loss": 0.66,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039334238279204906,
+      "loss": 0.5582,
+      "step": 220
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039323159289189505,
+      "loss": 0.6087,
+      "step": 221
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003931199046147764,
+      "loss": 0.5566,
+      "step": 222
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039300731847995716,
+      "loss": 0.5775,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039289383501087534,
+      "loss": 0.5081,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277945473514104,
+      "loss": 0.5218,
+      "step": 225
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003926641781845338,
+      "loss": 0.6655,
+      "step": 226
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003925480058950002,
+      "loss": 0.5735,
+      "step": 227
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039243093840665114,
+      "loss": 0.6609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003923129762637596,
+      "loss": 0.7323,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000392194120014758,
+      "loss": 0.5703,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039207437021223583,
+      "loss": 0.6545,
+      "step": 231
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003919537274129366,
+      "loss": 0.521,
+      "step": 232
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039183219217775564,
+      "loss": 0.5257,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003917097650717377,
+      "loss": 0.5487,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039158644666407365,
+      "loss": 0.4861,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039146223752809845,
+      "loss": 0.4928,
+      "step": 236
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003913371382412883,
+      "loss": 0.5253,
+      "step": 237
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039121114938525756,
+      "loss": 0.6155,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039108427154575684,
+      "loss": 0.55,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039095650531266967,
+      "loss": 0.6617,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039082785128000976,
+      "loss": 0.5198,
+      "step": 241
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039069831004591866,
+      "loss": 0.5302,
+      "step": 242
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003905678822126625,
+      "loss": 0.5347,
+      "step": 243
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039043656838662946,
+      "loss": 0.531,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039030436917832697,
+      "loss": 0.4884,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00039017128520237883,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003900373170775222,
+      "loss": 0.5537,
+      "step": 247
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038990246542660494,
+      "loss": 0.5753,
+      "step": 248
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038976673087658256,
+      "loss": 0.5059,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038963011405851537,
+      "loss": 0.5118,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038949261560756565,
+      "loss": 0.5645,
+      "step": 251
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003893542361629944,
+      "loss": 0.5623,
+      "step": 252
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038921497636815866,
+      "loss": 0.5216,
+      "step": 253
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003890748368705085,
+      "loss": 0.4501,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003889338183215838,
+      "loss": 0.48,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038879192137701135,
+      "loss": 0.5218,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003886491466965018,
+      "loss": 0.5858,
+      "step": 257
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038850549494384685,
+      "loss": 0.6124,
+      "step": 258
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038836096678691536,
+      "loss": 0.4645,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038821556289765136,
+      "loss": 0.474,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038806928395207003,
+      "loss": 0.4364,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038792213063025484,
+      "loss": 0.5821,
+      "step": 262
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003877741036163547,
+      "loss": 0.5393,
+      "step": 263
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003876252035985804,
+      "loss": 0.5373,
+      "step": 264
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003874754312692013,
+      "loss": 0.6021,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003873247873245426,
+      "loss": 0.4549,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003871732724649817,
+      "loss": 0.5994,
+      "step": 267
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003870208873949453,
+      "loss": 0.4764,
+      "step": 268
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038686763282290556,
+      "loss": 0.4311,
+      "step": 269
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003867135094613774,
+      "loss": 0.5462,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003865585180269148,
+      "loss": 0.5006,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003864026592401076,
+      "loss": 0.5347,
+      "step": 272
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038624593382557835,
+      "loss": 0.5242,
+      "step": 273
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038608834251197856,
+      "loss": 0.5005,
+      "step": 274
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038592988603198554,
+      "loss": 0.5436,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000385770565122299,
+      "loss": 0.4658,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003856103805236375,
+      "loss": 0.5273,
+      "step": 277
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038544933298073516,
+      "loss": 0.436,
+      "step": 278
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038528742324233804,
+      "loss": 0.4785,
+      "step": 279
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038512465206120086,
+      "loss": 0.5366,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038496102019408324,
+      "loss": 0.4448,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038479652840174637,
+      "loss": 0.5132,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00038463117744894955,
+      "loss": 0.7918,
+      "step": 283
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038446496810444627,
+      "loss": 0.5309,
+      "step": 284
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038429790114098114,
+      "loss": 0.5316,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038412997733528576,
+      "loss": 0.4611,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038396119746807563,
+      "loss": 0.4609,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00038379156232404613,
+      "loss": 0.5821,
+      "step": 288
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003836210726918691,
+      "loss": 0.5883,
+      "step": 289
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003834497293641889,
+      "loss": 0.5012,
+      "step": 290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038327753313761913,
+      "loss": 0.4457,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038310448481273867,
+      "loss": 0.4851,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00038293058519408787,
+      "loss": 0.5622,
+      "step": 293
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038275583509016507,
+      "loss": 0.5703,
+      "step": 294
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038258023531342265,
+      "loss": 0.5718,
+      "step": 295
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003824037866802632,
+      "loss": 0.5183,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038222649001103614,
+      "loss": 0.5085,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00038204834613003323,
+      "loss": 0.5388,
+      "step": 298
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038186935586548537,
+      "loss": 0.5425,
+      "step": 299
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003816895200495584,
+      "loss": 0.447,
+      "step": 300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003815088395183493,
+      "loss": 0.5541,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00038132731511188227,
+      "loss": 0.5518,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000381144947674105,
+      "loss": 0.5074,
+      "step": 303
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003809617380528847,
+      "loss": 0.5134,
+      "step": 304
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003807776871000037,
+      "loss": 0.4599,
+      "step": 305
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003805927956711562,
+      "loss": 0.5838,
+      "step": 306
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038040706462594395,
+      "loss": 0.5216,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00038022049482787216,
+      "loss": 0.5323,
+      "step": 308
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003800330871443456,
+      "loss": 0.5681,
+      "step": 309
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00037984484244666446,
+      "loss": 0.4172,
+      "step": 310
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003796557616100207,
+      "loss": 0.4958,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003794658455134934,
+      "loss": 0.662,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003792750950400451,
+      "loss": 0.5832,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003790835110765174,
+      "loss": 0.4271,
+      "step": 314
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003788910945136271,
+      "loss": 0.4842,
+      "step": 315
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037869784624596186,
+      "loss": 0.4656,
+      "step": 316
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037850376717197626,
+      "loss": 0.4981,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037830885819398733,
+      "loss": 0.5162,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00037811312021817067,
+      "loss": 0.652,
+      "step": 319
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003779165541545558,
+      "loss": 0.5104,
+      "step": 320
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003777191609170225,
+      "loss": 0.4971,
+      "step": 321
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003775209414232962,
+      "loss": 0.4871,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003773218965949436,
+      "loss": 0.5226,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00037712202735736884,
+      "loss": 0.4823,
+      "step": 324
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003769213346398087,
+      "loss": 0.497,
+      "step": 325
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003767198193753286,
+      "loss": 0.5976,
+      "step": 326
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003765174825008181,
+      "loss": 0.4532,
+      "step": 327
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003763143249569868,
+      "loss": 0.5236,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00037611034768835947,
+      "loss": 0.6513,
+      "step": 329
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037590555164327224,
+      "loss": 0.5686,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037569993777386774,
+      "loss": 0.456,
+      "step": 331
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003754935070360909,
+      "loss": 0.5181,
+      "step": 332
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003752862603896846,
+      "loss": 0.4765,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00037507819879818477,
+      "loss": 0.5363,
+      "step": 334
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037486932322891646,
+      "loss": 0.4584,
+      "step": 335
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037465963465298886,
+      "loss": 0.5428,
+      "step": 336
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003744491340452913,
+      "loss": 0.3927,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003742378223844882,
+      "loss": 0.5478,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003740257006530147,
+      "loss": 0.469,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00037381276983707246,
+      "loss": 0.5169,
+      "step": 340
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037359903092662434,
+      "loss": 0.4797,
+      "step": 341
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037338448491539054,
+      "loss": 0.5315,
+      "step": 342
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00037316913280084353,
+      "loss": 0.4422,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003729529755842035,
+      "loss": 0.4426,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003727360142704337,
+      "loss": 0.4718,
+      "step": 345
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003725182498682361,
+      "loss": 0.5585,
+      "step": 346
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003722996833900459,
+      "loss": 0.4775,
+      "step": 347
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003720803158520279,
+      "loss": 0.6014,
+      "step": 348
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00037186014827407076,
+      "loss": 0.5117,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003716391816797829,
+      "loss": 0.5404,
+      "step": 350
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003714174170964876,
+      "loss": 0.527,
+      "step": 351
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037119485555521796,
+      "loss": 0.4555,
+      "step": 352
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037097149809071255,
+      "loss": 0.5372,
+      "step": 353
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00037074734574141016,
+      "loss": 0.5377,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003705223995494454,
+      "loss": 0.4925,
+      "step": 355
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037029666056064345,
+      "loss": 0.482,
+      "step": 356
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00037007012982451546,
+      "loss": 0.5235,
+      "step": 357
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00036984280839425356,
+      "loss": 0.4957,
+      "step": 358
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000369614697326726,
+      "loss": 0.5379,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003693857976824721,
+      "loss": 0.4653,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036915611052569785,
+      "loss": 0.469,
+      "step": 361
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003689256369242702,
+      "loss": 0.5618,
+      "step": 362
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003686943779497124,
+      "loss": 0.4459,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003684623346771995,
+      "loss": 0.5606,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003682295081855524,
+      "loss": 0.4368,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00036799589955723375,
+      "loss": 0.4168,
+      "step": 366
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036776150987834243,
+      "loss": 0.4664,
+      "step": 367
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036752634023860846,
+      "loss": 0.4737,
+      "step": 368
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003672903917313883,
+      "loss": 0.4247,
+      "step": 369
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036705366545365935,
+      "loss": 0.5677,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00036681616250601505,
+      "loss": 0.5441,
+      "step": 371
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003665778839926599,
+      "loss": 0.6247,
+      "step": 372
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00036633883102140405,
+      "loss": 0.5217,
+      "step": 373
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003660990047036584,
+      "loss": 0.4651,
+      "step": 374
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003658584061544291,
+      "loss": 0.4648,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003656170364923128,
+      "loss": 0.6048,
+      "step": 376
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036537489683949114,
+      "loss": 0.4515,
+      "step": 377
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003651319883217255,
+      "loss": 0.5096,
+      "step": 378
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036488831206835207,
+      "loss": 0.4231,
+      "step": 379
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036464386921227637,
+      "loss": 0.4903,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00036439866088996796,
+      "loss": 0.5131,
+      "step": 381
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003641526882414553,
+      "loss": 0.5986,
+      "step": 382
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003639059524103203,
+      "loss": 0.6,
+      "step": 383
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003636584545436931,
+      "loss": 0.5216,
+      "step": 384
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003634101957922468,
+      "loss": 0.5144,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00036316117731019184,
+      "loss": 0.4963,
+      "step": 386
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003629114002552711,
+      "loss": 0.5657,
+      "step": 387
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036266086578875384,
+      "loss": 0.5028,
+      "step": 388
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003624095750754311,
+      "loss": 0.573,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036215752928360967,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003619047295851068,
+      "loss": 0.656,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00036165117715524506,
+      "loss": 0.5129,
+      "step": 392
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036139687317284647,
+      "loss": 0.3945,
+      "step": 393
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003611418188202271,
+      "loss": 0.5318,
+      "step": 394
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036088601528319196,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00036062946375102885,
+      "loss": 0.5407,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003603721654165034,
+      "loss": 0.5364,
+      "step": 397
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00036011412147585306,
+      "loss": 0.5407,
+      "step": 398
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003598553331287821,
+      "loss": 0.5999,
+      "step": 399
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003595958015784555,
+      "loss": 0.624,
+      "step": 400
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00035933552803149354,
+      "loss": 0.5351,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003590745136979662,
+      "loss": 0.5196,
+      "step": 402
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035881275979138765,
+      "loss": 0.5447,
+      "step": 403
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003585502675287104,
+      "loss": 0.4908,
+      "step": 404
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035828703813031986,
+      "loss": 0.5172,
+      "step": 405
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00035802307282002834,
+      "loss": 0.5923,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003577583728250699,
+      "loss": 0.568,
+      "step": 407
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035749293937609395,
+      "loss": 0.4618,
+      "step": 408
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003572267737071601,
+      "loss": 0.5351,
+      "step": 409
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003569598770557322,
+      "loss": 0.5285,
+      "step": 410
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035669225066267256,
+      "loss": 0.4571,
+      "step": 411
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035642389577223625,
+      "loss": 0.4214,
+      "step": 412
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003561548136320653,
+      "loss": 0.5393,
+      "step": 413
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003558850054931828,
+      "loss": 0.549,
+      "step": 414
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035561447260998714,
+      "loss": 0.4824,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035534321624024656,
+      "loss": 0.6244,
+      "step": 416
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035507123764509245,
+      "loss": 0.5436,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003547985380890144,
+      "loss": 0.5198,
+      "step": 418
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035452511883985366,
+      "loss": 0.5979,
+      "step": 419
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035425098116879754,
+      "loss": 0.4158,
+      "step": 420
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035397612635037356,
+      "loss": 0.5125,
+      "step": 421
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035370055566244334,
+      "loss": 0.4699,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003534242703861966,
+      "loss": 0.5553,
+      "step": 423
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035314727180614573,
+      "loss": 0.5969,
+      "step": 424
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035286956121011897,
+      "loss": 0.456,
+      "step": 425
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003525911398892552,
+      "loss": 0.5195,
+      "step": 426
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003523120091379975,
+      "loss": 0.5187,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00035203217025408726,
+      "loss": 0.5443,
+      "step": 428
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003517516245385582,
+      "loss": 0.4476,
+      "step": 429
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003514703732957301,
+      "loss": 0.5757,
+      "step": 430
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035118841783320304,
+      "loss": 0.5129,
+      "step": 431
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035090575946185114,
+      "loss": 0.6354,
+      "step": 432
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00035062239949581645,
+      "loss": 0.4065,
+      "step": 433
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000350338339252503,
+      "loss": 0.5472,
+      "step": 434
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00035005358005257045,
+      "loss": 0.5424,
+      "step": 435
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034976812321992816,
+      "loss": 0.6127,
+      "step": 436
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00034948197008172877,
+      "loss": 0.63,
+      "step": 437
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003491951219683625,
+      "loss": 0.413,
+      "step": 438
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034890758021345034,
+      "loss": 0.5435,
+      "step": 439
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034861934615383844,
+      "loss": 0.5433,
+      "step": 440
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034833042112959153,
+      "loss": 0.4763,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034804080648398667,
+      "loss": 0.5727,
+      "step": 442
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034775050356350727,
+      "loss": 0.5392,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00034745951371783666,
+      "loss": 0.4981,
+      "step": 444
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003471678382998518,
+      "loss": 0.5516,
+      "step": 445
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00034687547866561703,
+      "loss": 0.4965,
+      "step": 446
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003465824361743779,
+      "loss": 0.4982,
+      "step": 447
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003462887121885544,
+      "loss": 0.5619,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003459943080737353,
+      "loss": 0.5273,
+      "step": 449
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034569922519867133,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00034540346493526876,
+      "loss": 0.4874,
+      "step": 451
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003451070286585833,
+      "loss": 0.5966,
+      "step": 452
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003448099177468137,
+      "loss": 0.4487,
+      "step": 453
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003445121335812951,
+      "loss": 0.5091,
+      "step": 454
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003442136775464929,
+      "loss": 0.407,
+      "step": 455
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003439145510299958,
+      "loss": 0.6327,
+      "step": 456
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00034361475542251025,
+      "loss": 0.4217,
+      "step": 457
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003433142921178531,
+      "loss": 0.6102,
+      "step": 458
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003430131625129456,
+      "loss": 0.5556,
+      "step": 459
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034271136800780673,
+      "loss": 0.4986,
+      "step": 460
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003424089100055467,
+      "loss": 0.5406,
+      "step": 461
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034210578991236056,
+      "loss": 0.5881,
+      "step": 462
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034180200913752157,
+      "loss": 0.4869,
+      "step": 463
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00034149756909337454,
+      "loss": 0.5626,
+      "step": 464
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003411924711953295,
+      "loss": 0.564,
+      "step": 465
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00034088671686185486,
+      "loss": 0.6272,
+      "step": 466
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003405803075144711,
+      "loss": 0.4643,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003402732445777438,
+      "loss": 0.5435,
+      "step": 468
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00033996552947927744,
+      "loss": 0.5844,
+      "step": 469
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003396571636497084,
+      "loss": 0.5362,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033934814852269865,
+      "loss": 0.5607,
+      "step": 471
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003390384855349285,
+      "loss": 0.4836,
+      "step": 472
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033872817612609065,
+      "loss": 0.6555,
+      "step": 473
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033841722173888315,
+      "loss": 0.4784,
+      "step": 474
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00033810562381900253,
+      "loss": 0.5583,
+      "step": 475
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033779338381513736,
+      "loss": 0.4679,
+      "step": 476
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003374805031789613,
+      "loss": 0.5325,
+      "step": 477
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00033716698336512654,
+      "loss": 0.6601,
+      "step": 478
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000336852825831257,
+      "loss": 0.4838,
+      "step": 479
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003365380320379414,
+      "loss": 0.5588,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033622260344872665,
+      "loss": 0.4596,
+      "step": 481
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003359065415301108,
+      "loss": 0.5228,
+      "step": 482
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033558984775153663,
+      "loss": 0.5316,
+      "step": 483
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033527252358538437,
+      "loss": 0.4761,
+      "step": 484
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003349545705069653,
+      "loss": 0.5254,
+      "step": 485
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003346359899945144,
+      "loss": 0.4786,
+      "step": 486
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033431678352918384,
+      "loss": 0.4302,
+      "step": 487
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003339969525950361,
+      "loss": 0.4914,
+      "step": 488
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033367649867903663,
+      "loss": 0.4102,
+      "step": 489
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003333554232710477,
+      "loss": 0.4698,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003330337278638207,
+      "loss": 0.4454,
+      "step": 491
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033271141395298964,
+      "loss": 0.4648,
+      "step": 492
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033238848303706415,
+      "loss": 0.4616,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033206493661742237,
+      "loss": 0.4861,
+      "step": 494
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00033174077619830416,
+      "loss": 0.4797,
+      "step": 495
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033141600328680373,
+      "loss": 0.5104,
+      "step": 496
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033109061939286336,
+      "loss": 0.5712,
+      "step": 497
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033076462602926553,
+      "loss": 0.5425,
+      "step": 498
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00033043802471162636,
+      "loss": 0.6156,
+      "step": 499
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003301108169583887,
+      "loss": 0.4282,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003297830042908146,
+      "loss": 0.4088,
+      "step": 501
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032945458823297857,
+      "loss": 0.4866,
+      "step": 502
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003291255703117605,
+      "loss": 0.5045,
+      "step": 503
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003287959520568384,
+      "loss": 0.491,
+      "step": 504
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032846573500068136,
+      "loss": 0.458,
+      "step": 505
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00032813492067854246,
+      "loss": 0.4508,
+      "step": 506
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003278035106284516,
+      "loss": 0.4294,
+      "step": 507
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032747150639120834,
+      "loss": 0.4834,
+      "step": 508
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032713890951037477,
+      "loss": 0.3857,
+      "step": 509
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00032680572153226834,
+      "loss": 0.4072,
+      "step": 510
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003264719440059545,
+      "loss": 0.4028,
+      "step": 511
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032613757848323977,
+      "loss": 0.3789,
+      "step": 512
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032580262651866446,
+      "loss": 0.4944,
+      "step": 513
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003254670896694952,
+      "loss": 0.4259,
+      "step": 514
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032513096949571805,
+      "loss": 0.5037,
+      "step": 515
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00032479426756003093,
+      "loss": 0.5857,
+      "step": 516
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003244569854278366,
+      "loss": 0.5407,
+      "step": 517
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032411912466723524,
+      "loss": 0.499,
+      "step": 518
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003237806868490172,
+      "loss": 0.4359,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00032344167354665573,
+      "loss": 0.4374,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003231020863362997,
+      "loss": 0.4172,
+      "step": 521
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000322761926796766,
+      "loss": 0.4451,
+      "step": 522
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003224211965095326,
+      "loss": 0.4,
+      "step": 523
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003220798970587309,
+      "loss": 0.4009,
+      "step": 524
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003217380300311386,
+      "loss": 0.3966,
+      "step": 525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000321395597016172,
+      "loss": 0.4255,
+      "step": 526
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00032105259960587895,
+      "loss": 0.4707,
+      "step": 527
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00032070903939493124,
+      "loss": 0.5313,
+      "step": 528
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003203649179806172,
+      "loss": 0.3596,
+      "step": 529
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003200202369628345,
+      "loss": 0.5223,
+      "step": 530
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031967499794408234,
+      "loss": 0.4146,
+      "step": 531
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00031932920252945423,
+      "loss": 0.4328,
+      "step": 532
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003189828523266306,
+      "loss": 0.4258,
+      "step": 533
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031863594894587105,
+      "loss": 0.4457,
+      "step": 534
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003182884940000072,
+      "loss": 0.5249,
+      "step": 535
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003179404891044348,
+      "loss": 0.4751,
+      "step": 536
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00031759193587710676,
+      "loss": 0.5378,
+      "step": 537
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031724283593852497,
+      "loss": 0.634,
+      "step": 538
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031689319091173326,
+      "loss": 0.4298,
+      "step": 539
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031654300242230977,
+      "loss": 0.5469,
+      "step": 540
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00031619227209835917,
+      "loss": 0.5153,
+      "step": 541
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003158410015705053,
+      "loss": 0.4144,
+      "step": 542
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003154891924718837,
+      "loss": 0.6041,
+      "step": 543
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003151368464381335,
+      "loss": 0.4891,
+      "step": 544
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0003147839651073904,
+      "loss": 0.5258,
+      "step": 545
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00031443055012027874,
+      "loss": 0.4351,
+      "step": 546
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000314076603119904,
+      "loss": 0.4556,
+      "step": 547
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031372212575184514,
+      "loss": 0.5445,
+      "step": 548
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00031336711966414675,
+      "loss": 0.5585,
+      "step": 549
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003130115865073117,
+      "loss": 0.367,
+      "step": 550
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003126555279342933,
+      "loss": 0.4877,
+      "step": 551
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003122989456004876,
+      "loss": 0.4335,
+      "step": 552
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003119418411637258,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003115842162842663,
+      "loss": 0.4508,
+      "step": 554
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00031122607262478743,
+      "loss": 0.4631,
+      "step": 555
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003108674118503793,
+      "loss": 0.3496,
+      "step": 556
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003105082356285361,
+      "loss": 0.4108,
+      "step": 557
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003101485456291486,
+      "loss": 0.4877,
+      "step": 558
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030978834352449614,
+      "loss": 0.3696,
+      "step": 559
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030942763098923913,
+      "loss": 0.5138,
+      "step": 560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030906640970041084,
+      "loss": 0.5961,
+      "step": 561
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003087046813374099,
+      "loss": 0.3824,
+      "step": 562
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00030834244758199276,
+      "loss": 0.4925,
+      "step": 563
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000307979710118265,
+      "loss": 0.4511,
+      "step": 564
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030761647063267457,
+      "loss": 0.4306,
+      "step": 565
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003072527308140031,
+      "loss": 0.468,
+      "step": 566
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00030688849235335856,
+      "loss": 0.4842,
+      "step": 567
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003065237569441671,
+      "loss": 0.4332,
+      "step": 568
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030615852628216537,
+      "loss": 0.4637,
+      "step": 569
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003057928020653925,
+      "loss": 0.6193,
+      "step": 570
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003054265859941824,
+      "loss": 0.5033,
+      "step": 571
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00030505987977115555,
+      "loss": 0.4185,
+      "step": 572
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003046926851012114,
+      "loss": 0.4211,
+      "step": 573
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003043250036915201,
+      "loss": 0.5089,
+      "step": 574
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00030395683725151505,
+      "loss": 0.517,
+      "step": 575
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003035881874928845,
+      "loss": 0.492,
+      "step": 576
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003032190561295636,
+      "loss": 0.4535,
+      "step": 577
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003028494448777269,
+      "loss": 0.3947,
+      "step": 578
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030247935545577986,
+      "loss": 0.3125,
+      "step": 579
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003021087895843511,
+      "loss": 0.3882,
+      "step": 580
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003017377489862845,
+      "loss": 0.4802,
+      "step": 581
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030136623538663083,
+      "loss": 0.4652,
+      "step": 582
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00030099425051263994,
+      "loss": 0.3816,
+      "step": 583
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003006217960937529,
+      "loss": 0.4583,
+      "step": 584
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00030024887386159385,
+      "loss": 0.4568,
+      "step": 585
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029987548554996174,
+      "loss": 0.3908,
+      "step": 586
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002995016328948225,
+      "loss": 0.4235,
+      "step": 587
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029912731763430075,
+      "loss": 0.4138,
+      "step": 588
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00029875254150867216,
+      "loss": 0.5838,
+      "step": 589
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002983773062603548,
+      "loss": 0.462,
+      "step": 590
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029800161363390145,
+      "loss": 0.4632,
+      "step": 591
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029762546537599125,
+      "loss": 0.5898,
+      "step": 592
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002972488632354218,
+      "loss": 0.4742,
+      "step": 593
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00029687180896310065,
+      "loss": 0.4579,
+      "step": 594
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002964943043120378,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029611635103733675,
+      "loss": 0.4304,
+      "step": 596
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0002957379508961871,
+      "loss": 0.4383,
+      "step": 597
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029535910564785584,
+      "loss": 0.5327,
+      "step": 598
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029497981705367933,
+      "loss": 0.4781,
+      "step": 599
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029460008687705525,
+      "loss": 0.4178,
+      "step": 600
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002942199168834342,
+      "loss": 0.3987,
+      "step": 601
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029383930884031183,
+      "loss": 0.3861,
+      "step": 602
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029345826451722005,
+      "loss": 0.5322,
+      "step": 603
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029307678568571936,
+      "loss": 0.3997,
+      "step": 604
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002926948741193903,
+      "loss": 0.4121,
+      "step": 605
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029231253159382514,
+      "loss": 0.4931,
+      "step": 606
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029192975988662017,
+      "loss": 0.4626,
+      "step": 607
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029154656077736666,
+      "loss": 0.4441,
+      "step": 608
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002911629360476432,
+      "loss": 0.3863,
+      "step": 609
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029077888748100703,
+      "loss": 0.36,
+      "step": 610
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029039441686298594,
+      "loss": 0.4246,
+      "step": 611
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002900095259810702,
+      "loss": 0.4916,
+      "step": 612
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028962421662470346,
+      "loss": 0.4896,
+      "step": 613
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028923849058527535,
+      "loss": 0.4237,
+      "step": 614
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00028885234965611274,
+      "loss": 0.5727,
+      "step": 615
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028846579563247116,
+      "loss": 0.5681,
+      "step": 616
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002880788303115269,
+      "loss": 0.4383,
+      "step": 617
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00028769145549236845,
+      "loss": 0.4962,
+      "step": 618
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002873036729759881,
+      "loss": 0.5472,
+      "step": 619
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002869154845652738,
+      "loss": 0.5431,
+      "step": 620
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002865268920650003,
+      "loss": 0.4152,
+      "step": 621
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002861378972818211,
+      "loss": 0.3922,
+      "step": 622
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002857485020242602,
+      "loss": 0.5129,
+      "step": 623
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002853587081027034,
+      "loss": 0.4328,
+      "step": 624
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00028496851732938997,
+      "loss": 0.4431,
+      "step": 625
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002845779315184042,
+      "loss": 0.4968,
+      "step": 626
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.000284186952485667,
+      "loss": 0.5301,
+      "step": 627
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002837955820489276,
+      "loss": 0.4332,
+      "step": 628
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002834038220277546,
+      "loss": 0.4245,
+      "step": 629
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00028301167424352836,
+      "loss": 0.5057,
+      "step": 630
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028261914051943166,
+      "loss": 0.4623,
+      "step": 631
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028222622268044174,
+      "loss": 0.5452,
+      "step": 632
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028183292255332164,
+      "loss": 0.5238,
+      "step": 633
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00028143924196661176,
+      "loss": 0.3966,
+      "step": 634
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002810451827506214,
+      "loss": 0.35,
+      "step": 635
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00028065074673742007,
+      "loss": 0.4325,
+      "step": 636
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0002802559357608292,
+      "loss": 0.4854,
+      "step": 637
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027986075165641343,
+      "loss": 0.4254,
+      "step": 638
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027946519626147225,
+      "loss": 0.4614,
+      "step": 639
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027906927141503125,
+      "loss": 0.3798,
+      "step": 640
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00027867297895783373,
+      "loss": 0.4742,
+      "step": 641
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002782763207323322,
+      "loss": 0.4007,
+      "step": 642
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002778792985826795,
+      "loss": 0.4383,
+      "step": 643
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002774819143547206,
+      "loss": 0.4298,
+      "step": 644
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00027708416989598387,
+      "loss": 0.5178,
+      "step": 645
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002766860670556722,
+      "loss": 0.3434,
+      "step": 646
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002762876076846551,
+      "loss": 0.3862,
+      "step": 647
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027588879363545934,
+      "loss": 0.4459,
+      "step": 648
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002754896267622608,
+      "loss": 0.3934,
+      "step": 649
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027509010892087565,
+      "loss": 0.4349,
+      "step": 650
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000274690241968752,
+      "loss": 0.4178,
+      "step": 651
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002742900277649607,
+      "loss": 0.4151,
+      "step": 652
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002738894681701874,
+      "loss": 0.3888,
+      "step": 653
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027348856504672323,
+      "loss": 0.4214,
+      "step": 654
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002730873202584567,
+      "loss": 0.519,
+      "step": 655
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00027268573567086477,
+      "loss": 0.5463,
+      "step": 656
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027228381315100417,
+      "loss": 0.3367,
+      "step": 657
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027188155456750256,
+      "loss": 0.4629,
+      "step": 658
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00027147896179055043,
+      "loss": 0.4456,
+      "step": 659
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002710760366918917,
+      "loss": 0.4348,
+      "step": 660
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002706727811448153,
+      "loss": 0.4505,
+      "step": 661
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002702691970241468,
+      "loss": 0.5028,
+      "step": 662
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026986528620623904,
+      "loss": 0.5257,
+      "step": 663
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026946105056896403,
+      "loss": 0.4977,
+      "step": 664
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026905649199170377,
+      "loss": 0.421,
+      "step": 665
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002686516123553417,
+      "loss": 0.4931,
+      "step": 666
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00026824641354225397,
+      "loss": 0.5818,
+      "step": 667
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002678408974363005,
+      "loss": 0.4211,
+      "step": 668
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026743506592281674,
+      "loss": 0.5182,
+      "step": 669
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00026702892088860413,
+      "loss": 0.5591,
+      "step": 670
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002666224642219221,
+      "loss": 0.5363,
+      "step": 671
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002662156978124786,
+      "loss": 0.5866,
+      "step": 672
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002658086235514218,
+      "loss": 0.422,
+      "step": 673
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002654012433313312,
+      "loss": 0.5375,
+      "step": 674
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002649935590462087,
+      "loss": 0.4752,
+      "step": 675
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00026458557259146986,
+      "loss": 0.4271,
+      "step": 676
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002641772858639351,
+      "loss": 0.4843,
+      "step": 677
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026376870076182086,
+      "loss": 0.4827,
+      "step": 678
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026335981918473086,
+      "loss": 0.47,
+      "step": 679
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002629506430336472,
+      "loss": 0.368,
+      "step": 680
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00026254117421092133,
+      "loss": 0.481,
+      "step": 681
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002621314146202656,
+      "loss": 0.4153,
+      "step": 682
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002617213661667443,
+      "loss": 0.4397,
+      "step": 683
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002613110307567643,
+      "loss": 0.4052,
+      "step": 684
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026090041029806695,
+      "loss": 0.4652,
+      "step": 685
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026048950669971884,
+      "loss": 0.3826,
+      "step": 686
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00026007832187210277,
+      "loss": 0.5639,
+      "step": 687
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025966685772690906,
+      "loss": 0.3917,
+      "step": 688
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025925511617712685,
+      "loss": 0.5248,
+      "step": 689
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002588430991370347,
+      "loss": 0.3796,
+      "step": 690
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002584308085221922,
+      "loss": 0.4391,
+      "step": 691
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00025801824624943084,
+      "loss": 0.4514,
+      "step": 692
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025760541423684496,
+      "loss": 0.5046,
+      "step": 693
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002571923144037831,
+      "loss": 0.4578,
+      "step": 694
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002567789486708389,
+      "loss": 0.4681,
+      "step": 695
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025636531895984236,
+      "loss": 0.4501,
+      "step": 696
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002559514271938506,
+      "loss": 0.4411,
+      "step": 697
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025553727529713916,
+      "loss": 0.401,
+      "step": 698
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025512286519519293,
+      "loss": 0.4911,
+      "step": 699
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002547081988146974,
+      "loss": 0.3754,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00025429327808352946,
+      "loss": 0.3807,
+      "step": 701
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002538781049307486,
+      "loss": 0.4193,
+      "step": 702
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002534626812865876,
+      "loss": 0.5259,
+      "step": 703
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00025304700908244433,
+      "loss": 0.3684,
+      "step": 704
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002526310902508718,
+      "loss": 0.5423,
+      "step": 705
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002522149267255699,
+      "loss": 0.4288,
+      "step": 706
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.000251798520441376,
+      "loss": 0.5046,
+      "step": 707
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002513818733342564,
+      "loss": 0.3777,
+      "step": 708
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025096498734129667,
+      "loss": 0.5171,
+      "step": 709
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0002505478644006932,
+      "loss": 0.3785,
+      "step": 710
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00025013050645174414,
+      "loss": 0.5413,
+      "step": 711
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024971291543483994,
+      "loss": 0.5018,
+      "step": 712
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00024929509329145477,
+      "loss": 0.5212,
+      "step": 713
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024887704196413746,
+      "loss": 0.483,
+      "step": 714
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002484587633965023,
+      "loss": 0.3684,
+      "step": 715
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024804025953322005,
+      "loss": 0.3782,
+      "step": 716
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00024762153232000877,
+      "loss": 0.4995,
+      "step": 717
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002472025837036253,
+      "loss": 0.4324,
+      "step": 718
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002467834156318555,
+      "loss": 0.5203,
+      "step": 719
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002463640300535057,
+      "loss": 0.423,
+      "step": 720
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002459444289183933,
+      "loss": 0.4537,
+      "step": 721
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00024552461417733817,
+      "loss": 0.4124,
+      "step": 722
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002451045877821528,
+      "loss": 0.4865,
+      "step": 723
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002446843516856343,
+      "loss": 0.4845,
+      "step": 724
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024426390784155425,
+      "loss": 0.4174,
+      "step": 725
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024384325820465033,
+      "loss": 0.4456,
+      "step": 726
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002434224047306169,
+      "loss": 0.4429,
+      "step": 727
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002430013493760961,
+      "loss": 0.363,
+      "step": 728
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00024258009409866853,
+      "loss": 0.4769,
+      "step": 729
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024215864085684442,
+      "loss": 0.4597,
+      "step": 730
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024173699161005429,
+      "loss": 0.366,
+      "step": 731
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024131514831863995,
+      "loss": 0.4746,
+      "step": 732
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0002408931129438453,
+      "loss": 0.5608,
+      "step": 733
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00024047088744780744,
+      "loss": 0.4292,
+      "step": 734
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00024004847379354726,
+      "loss": 0.4743,
+      "step": 735
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023962587394496038,
+      "loss": 0.3855,
+      "step": 736
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023920308986680834,
+      "loss": 0.4573,
+      "step": 737
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00023878012352470892,
+      "loss": 0.3937,
+      "step": 738
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0002383569768851274,
+      "loss": 0.4371,
+      "step": 739
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023793365191536735,
+      "loss": 0.5432,
+      "step": 740
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023751015058356135,
+      "loss": 0.4803,
+      "step": 741
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.000237086474858662,
+      "loss": 0.4281,
+      "step": 742
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023666262671043263,
+      "loss": 0.4031,
+      "step": 743
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00023623860810943826,
+      "loss": 0.4725,
+      "step": 744
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0002358144210270364,
+      "loss": 0.4644,
+      "step": 745
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023539006743536774,
+      "loss": 0.4848,
+      "step": 746
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023496554930734718,
+      "loss": 0.4084,
+      "step": 747
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023454086861665472,
+      "loss": 0.4322,
+      "step": 748
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023411602733772595,
+      "loss": 0.4847,
+      "step": 749
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00023369102744574312,
+      "loss": 0.4298,
+      "step": 750
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023326587091662603,
+      "loss": 0.4268,
+      "step": 751
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023284055972702254,
+      "loss": 0.4089,
+      "step": 752
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0002324150958542997,
+      "loss": 0.4214,
+      "step": 753
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023198948127653446,
+      "loss": 0.5576,
+      "step": 754
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00023156371797250418,
+      "loss": 0.4377,
+      "step": 755
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00023113780792167785,
+      "loss": 0.4934,
+      "step": 756
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002307117531042068,
+      "loss": 0.3698,
+      "step": 757
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00023028555550091536,
+      "loss": 0.4722,
+      "step": 758
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00022985921709329157,
+      "loss": 0.3837,
+      "step": 759
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00022943273986347822,
+      "loss": 0.5132,
+      "step": 760
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002290061257942635,
+      "loss": 0.487,
+      "step": 761
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022857937686907183,
+      "loss": 0.3857,
+      "step": 762
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022815249507195445,
+      "loss": 0.4135,
+      "step": 763
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022772548238758064,
+      "loss": 0.4639,
+      "step": 764
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00022729834080122791,
+      "loss": 0.5297,
+      "step": 765
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022687107229877324,
+      "loss": 0.4485,
+      "step": 766
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022644367886668357,
+      "loss": 0.467,
+      "step": 767
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022601616249200675,
+      "loss": 0.4304,
+      "step": 768
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022558852516236217,
+      "loss": 0.5531,
+      "step": 769
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00022516076886593158,
+      "loss": 0.5021,
+      "step": 770
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022473289559144988,
+      "loss": 0.433,
+      "step": 771
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022430490732819566,
+      "loss": 0.505,
+      "step": 772
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022387680606598235,
+      "loss": 0.4677,
+      "step": 773
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022344859379514858,
+      "loss": 0.4421,
+      "step": 774
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00022302027250654905,
+      "loss": 0.4282,
+      "step": 775
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0002225918441915456,
+      "loss": 0.366,
+      "step": 776
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022216331084199724,
+      "loss": 0.4147,
+      "step": 777
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022173467445025158,
+      "loss": 0.586,
+      "step": 778
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022130593700913522,
+      "loss": 0.5285,
+      "step": 779
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00022087710051194463,
+      "loss": 0.4484,
+      "step": 780
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0002204481669524367,
+      "loss": 0.4063,
+      "step": 781
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002200191383248197,
+      "loss": 0.4751,
+      "step": 782
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021959001662374373,
+      "loss": 0.3936,
+      "step": 783
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021916080384429184,
+      "loss": 0.4433,
+      "step": 784
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002187315019819703,
+      "loss": 0.4883,
+      "step": 785
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00021830211303269965,
+      "loss": 0.4925,
+      "step": 786
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021787263899280537,
+      "loss": 0.4597,
+      "step": 787
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021744308185900848,
+      "loss": 0.4954,
+      "step": 788
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021701344362841626,
+      "loss": 0.4025,
+      "step": 789
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021658372629851318,
+      "loss": 0.5734,
+      "step": 790
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00021615393186715128,
+      "loss": 0.3779,
+      "step": 791
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021572406233254116,
+      "loss": 0.4994,
+      "step": 792
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021529411969324275,
+      "loss": 0.5359,
+      "step": 793
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021486410594815554,
+      "loss": 0.4738,
+      "step": 794
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021443402309650979,
+      "loss": 0.4915,
+      "step": 795
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00021400387313785704,
+      "loss": 0.4991,
+      "step": 796
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021357365807206087,
+      "loss": 0.4503,
+      "step": 797
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0002131433798992874,
+      "loss": 0.4887,
+      "step": 798
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021271304061999633,
+      "loss": 0.4279,
+      "step": 799
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021228264223493139,
+      "loss": 0.5367,
+      "step": 800
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021185218674511097,
+      "loss": 0.3212,
+      "step": 801
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00021142167615181915,
+      "loss": 0.493,
+      "step": 802
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002109911124565962,
+      "loss": 0.3635,
+      "step": 803
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00021056049766122916,
+      "loss": 0.3494,
+      "step": 804
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00021012983376774254,
+      "loss": 0.3536,
+      "step": 805
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002096991227783895,
+      "loss": 0.4335,
+      "step": 806
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00020926836669564168,
+      "loss": 0.4673,
+      "step": 807
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020883756752218075,
+      "loss": 0.5269,
+      "step": 808
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0002084067272608886,
+      "loss": 0.4365,
+      "step": 809
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020797584791483806,
+      "loss": 0.2998,
+      "step": 810
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020754493148728375,
+      "loss": 0.4318,
+      "step": 811
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00020711397998165264,
+      "loss": 0.3205,
+      "step": 812
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020668299540153493,
+      "loss": 0.5026,
+      "step": 813
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020625197975067438,
+      "loss": 0.3923,
+      "step": 814
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0002058209350329594,
+      "loss": 0.3026,
+      "step": 815
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020538986325241342,
+      "loss": 0.4729,
+      "step": 816
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00020495876641318567,
+      "loss": 0.3236,
+      "step": 817
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0002045276465195419,
+      "loss": 0.4934,
+      "step": 818
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020409650557585523,
+      "loss": 0.3791,
+      "step": 819
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020366534558659635,
+      "loss": 0.3879,
+      "step": 820
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020323416855632477,
+      "loss": 0.3807,
+      "step": 821
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00020280297648967897,
+      "loss": 0.415,
+      "step": 822
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020237177139136758,
+      "loss": 0.3824,
+      "step": 823
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0002019405552661596,
+      "loss": 0.3854,
+      "step": 824
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020150933011887543,
+      "loss": 0.3781,
+      "step": 825
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020107809795437745,
+      "loss": 0.3904,
+      "step": 826
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00020064686077756057,
+      "loss": 0.3213,
+      "step": 827
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00020021562059334302,
+      "loss": 0.4888,
+      "step": 828
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019978437940665702,
+      "loss": 0.3375,
+      "step": 829
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001993531392224394,
+      "loss": 0.4325,
+      "step": 830
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019892190204562257,
+      "loss": 0.2865,
+      "step": 831
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001984906698811246,
+      "loss": 0.3984,
+      "step": 832
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019805944473384038,
+      "loss": 0.3011,
+      "step": 833
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019762822860863247,
+      "loss": 0.4063,
+      "step": 834
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019719702351032105,
+      "loss": 0.4489,
+      "step": 835
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019676583144367525,
+      "loss": 0.3991,
+      "step": 836
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019633465441340367,
+      "loss": 0.2736,
+      "step": 837
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00019590349442414484,
+      "loss": 0.3842,
+      "step": 838
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0001954723534804581,
+      "loss": 0.346,
+      "step": 839
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0001950412335868144,
+      "loss": 0.3435,
+      "step": 840
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019461013674758668,
+      "loss": 0.4139,
+      "step": 841
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019417906496704064,
+      "loss": 0.4031,
+      "step": 842
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00019374802024932567,
+      "loss": 0.352,
+      "step": 843
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019331700459846517,
+      "loss": 0.332,
+      "step": 844
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019288602001834735,
+      "loss": 0.3822,
+      "step": 845
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019245506851271632,
+      "loss": 0.3912,
+      "step": 846
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.000192024152085162,
+      "loss": 0.4028,
+      "step": 847
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00019159327273911145,
+      "loss": 0.3625,
+      "step": 848
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00019116243247781927,
+      "loss": 0.392,
+      "step": 849
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00019073163330435842,
+      "loss": 0.3687,
+      "step": 850
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00019030087722161055,
+      "loss": 0.3794,
+      "step": 851
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00018987016623225747,
+      "loss": 0.4095,
+      "step": 852
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00018943950233877094,
+      "loss": 0.3665,
+      "step": 853
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00018900888754340382,
+      "loss": 0.3826,
+      "step": 854
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001885783238481809,
+      "loss": 0.4903,
+      "step": 855
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00018814781325488905,
+      "loss": 0.3174,
+      "step": 856
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00018771735776506866,
+      "loss": 0.3987,
+      "step": 857
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001872869593800037,
+      "loss": 0.4488,
+      "step": 858
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00018685662010071261,
+      "loss": 0.3298,
+      "step": 859
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001864263419279392,
+      "loss": 0.3385,
+      "step": 860
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00018599612686214304,
+      "loss": 0.4442,
+      "step": 861
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00018556597690349023,
+      "loss": 0.3132,
+      "step": 862
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001851358940518445,
+      "loss": 0.5051,
+      "step": 863
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001847058803067573,
+      "loss": 0.3919,
+      "step": 864
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00018427593766745884,
+      "loss": 0.4193,
+      "step": 865
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001838460681328488,
+      "loss": 0.3196,
+      "step": 866
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00018341627370148692,
+      "loss": 0.6047,
+      "step": 867
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00018298655637158376,
+      "loss": 0.3741,
+      "step": 868
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00018255691814099157,
+      "loss": 0.4033,
+      "step": 869
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018212736100719465,
+      "loss": 0.422,
+      "step": 870
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018169788696730034,
+      "loss": 0.3358,
+      "step": 871
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018126849801802976,
+      "loss": 0.3295,
+      "step": 872
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018083919615570823,
+      "loss": 0.4859,
+      "step": 873
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00018040998337625627,
+      "loss": 0.2917,
+      "step": 874
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00017998086167518034,
+      "loss": 0.3505,
+      "step": 875
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00017955183304756332,
+      "loss": 0.5962,
+      "step": 876
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0001791228994880554,
+      "loss": 0.3097,
+      "step": 877
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00017869406299086482,
+      "loss": 0.4547,
+      "step": 878
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0001782653255497485,
+      "loss": 0.4567,
+      "step": 879
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0001778366891580028,
+      "loss": 0.3815,
+      "step": 880
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00017740815580845446,
+      "loss": 0.5061,
+      "step": 881
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00017697972749345094,
+      "loss": 0.3729,
+      "step": 882
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0001765514062048515,
+      "loss": 0.3626,
+      "step": 883
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00017612319393401772,
+      "loss": 0.4256,
+      "step": 884
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00017569509267180433,
+      "loss": 0.4114,
+      "step": 885
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017526710440855017,
+      "loss": 0.3554,
+      "step": 886
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017483923113406844,
+      "loss": 0.4741,
+      "step": 887
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017441147483763785,
+      "loss": 0.4472,
+      "step": 888
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017398383750799327,
+      "loss": 0.4325,
+      "step": 889
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00017355632113331648,
+      "loss": 0.4184,
+      "step": 890
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00017312892770122678,
+      "loss": 0.468,
+      "step": 891
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0001727016591987721,
+      "loss": 0.3996,
+      "step": 892
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00017227451761241938,
+      "loss": 0.4718,
+      "step": 893
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00017184750492804554,
+      "loss": 0.4076,
+      "step": 894
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00017142062313092824,
+      "loss": 0.337,
+      "step": 895
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00017099387420573656,
+      "loss": 0.3534,
+      "step": 896
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0001705672601365218,
+      "loss": 0.4757,
+      "step": 897
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00017014078290670848,
+      "loss": 0.4629,
+      "step": 898
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00016971444449908474,
+      "loss": 0.4999,
+      "step": 899
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0001692882468957932,
+      "loss": 0.4404,
+      "step": 900
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001688621920783222,
+      "loss": 0.4102,
+      "step": 901
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00016843628202749592,
+      "loss": 0.4285,
+      "step": 902
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001680105187234656,
+      "loss": 0.4326,
+      "step": 903
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001675849041457003,
+      "loss": 0.507,
+      "step": 904
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00016715944027297753,
+      "loss": 0.3976,
+      "step": 905
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00016673412908337401,
+      "loss": 0.4173,
+      "step": 906
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0001663089725542569,
+      "loss": 0.4053,
+      "step": 907
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0001658839726622741,
+      "loss": 0.4606,
+      "step": 908
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00016545913138334535,
+      "loss": 0.3376,
+      "step": 909
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00016503445069265287,
+      "loss": 0.4466,
+      "step": 910
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00016460993256463228,
+      "loss": 0.3034,
+      "step": 911
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00016418557897296366,
+      "loss": 0.4127,
+      "step": 912
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00016376139189056176,
+      "loss": 0.4437,
+      "step": 913
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0001633373732895674,
+      "loss": 0.4479,
+      "step": 914
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00016291352514133807,
+      "loss": 0.4006,
+      "step": 915
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00016248984941643873,
+      "loss": 0.4428,
+      "step": 916
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00016206634808463267,
+      "loss": 0.3704,
+      "step": 917
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00016164302311487262,
+      "loss": 0.3807,
+      "step": 918
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00016121987647529115,
+      "loss": 0.4194,
+      "step": 919
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00016079691013319168,
+      "loss": 0.4486,
+      "step": 920
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00016037412605503966,
+      "loss": 0.3642,
+      "step": 921
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00015995152620645287,
+      "loss": 0.4344,
+      "step": 922
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00015952911255219258,
+      "loss": 0.3868,
+      "step": 923
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00015910688705615472,
+      "loss": 0.4161,
+      "step": 924
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00015868485168136015,
+      "loss": 0.4094,
+      "step": 925
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00015826300838994573,
+      "loss": 0.4528,
+      "step": 926
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00015784135914315563,
+      "loss": 0.3656,
+      "step": 927
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00015741990590133152,
+      "loss": 0.4982,
+      "step": 928
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00015699865062390392,
+      "loss": 0.4157,
+      "step": 929
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00015657759526938313,
+      "loss": 0.3153,
+      "step": 930
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00015615674179534977,
+      "loss": 0.4343,
+      "step": 931
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00015573609215844582,
+      "loss": 0.4922,
+      "step": 932
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.0001553156483143658,
+      "loss": 0.5049,
+      "step": 933
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00015489541221784726,
+      "loss": 0.4128,
+      "step": 934
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00015447538582266193,
+      "loss": 0.3353,
+      "step": 935
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00015405557108160673,
+      "loss": 0.4553,
+      "step": 936
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00015363596994649433,
+      "loss": 0.406,
+      "step": 937
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00015321658436814455,
+      "loss": 0.4339,
+      "step": 938
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00015279741629637477,
+      "loss": 0.4105,
+      "step": 939
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00015237846767999122,
+      "loss": 0.4491,
+      "step": 940
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00015195974046678003,
+      "loss": 0.3728,
+      "step": 941
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00015154123660349774,
+      "loss": 0.3357,
+      "step": 942
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00015112295803586256,
+      "loss": 0.3035,
+      "step": 943
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00015070490670854528,
+      "loss": 0.347,
+      "step": 944
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00015028708456516017,
+      "loss": 0.4472,
+      "step": 945
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00014986949354825588,
+      "loss": 0.3888,
+      "step": 946
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00014945213559930677,
+      "loss": 0.4407,
+      "step": 947
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00014903501265870338,
+      "loss": 0.5161,
+      "step": 948
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00014861812666574364,
+      "loss": 0.4002,
+      "step": 949
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.000148201479558624,
+      "loss": 0.3079,
+      "step": 950
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1557,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 1.2732085224403108e+18,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-950/training_args.bin b/checkpoint-950/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4843df7aa1383a371fb28dea27d303b1a1145e1
--- /dev/null
+++ b/checkpoint-950/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637e0437b5818f76ea2fea2aa5b87010fc39a85bdfc12277d436c72e69d11811
+size 4155
diff --git a/runs/Oct04_17-40-29_1d91a4065171/events.out.tfevents.1696441230.1d91a4065171.307.0 b/runs/Oct04_17-40-29_1d91a4065171/events.out.tfevents.1696441230.1d91a4065171.307.0
new file mode 100644
index 0000000000000000000000000000000000000000..009fb5a6e6f3e4a487fb5803df7cc12e57e4b1bd
--- /dev/null
+++ b/runs/Oct04_17-40-29_1d91a4065171/events.out.tfevents.1696441230.1d91a4065171.307.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae46c2aa78109fe31ca441a309d500e731611b459d605805509aaa11f3af18e7
+size 48378
diff --git a/runs/Oct04_19-14-59_1d91a4065171/events.out.tfevents.1696446900.1d91a4065171.25416.0 b/runs/Oct04_19-14-59_1d91a4065171/events.out.tfevents.1696446900.1d91a4065171.25416.0
new file mode 100644
index 0000000000000000000000000000000000000000..ada1e49420f883cf37fa3b592880d492da392f5c
--- /dev/null
+++ b/runs/Oct04_19-14-59_1d91a4065171/events.out.tfevents.1696446900.1d91a4065171.25416.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84457bdb71c62cf805181e935aaf204d848ac64419f49ddc9efacfbe4ced43ca
+size 28439
diff --git a/training_args.bin b/training_args.bin
index c62257ab265a8cae4034c6b32ccac107cefb7904..c4843df7aa1383a371fb28dea27d303b1a1145e1 100644
--- a/training_args.bin
+++ b/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eabffe952601acc55592b8f8ba3066e48ba407a023d340dfa5fe5150891586f
+oid sha256:637e0437b5818f76ea2fea2aa5b87010fc39a85bdfc12277d436c72e69d11811
 size 4155