Model save

README.md

@@ -1,36 +1,19 @@
 ---
 library_name: peft
 tags:
-- liuhaotian/llava-v1.5-13b_10.0_602276
-- liuhaotian/llava-v1.5-13b_9.0_602276
-- liuhaotian/llava-v1.5-13b_8.0_602276
-- liuhaotian/llava-v1.5-13b_7.0_602276
-- liuhaotian/llava-v1.5-13b_6.0_602276
-- liuhaotian/llava-v1.5-13b_5.0_602276
-- liuhaotian/llava-v1.5-13b_4.0_602276
-- liuhaotian/llava-v1.5-13b_3.0_602276
-- liuhaotian/llava-v1.5-13b_2.0_602276
-- liuhaotian/llava-v1.5-13b_1.0_602276
 - generated_from_trainer
 base_model: liuhaotian/llava-v1.5-13b
 model-index:
-- name: liuhaotian/llava-v1.5-13b_10.0_602276
+- name: llava_13b_exact_location_name_synthetic
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# liuhaotian/llava-v1.5-13b_10.0_602276
+# llava_13b_exact_location_name_synthetic
 
-This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_10.0_602276](https://huggingface.co/liuhaotian/llava-v1.5-13b_10.0_602276) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.0022
-- eval_runtime: 55.1607
-- eval_samples_per_second: 15.718
-- eval_steps_per_second: 0.508
-- epoch: 9.0
-- step: 252
+This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
 
 ## Model description
 

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
-    "v_proj",
     "up_proj",
-    "gate_proj",
     "o_proj",
-    "q_proj"
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ddaa241787f6409e37a5f48e2f063a18dd9b022874902be759093643f4d6ee
+oid sha256:e1b2582b692b13611e3505defb6e50477ccb75c89fbdcca86cf157e1a7ff687f
 size 1001466944

liuhaotian/llava-v1.5-13b_1.0/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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]
+- **Funded by [optional]:** [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 Dataset 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 Dataset 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]
+### Framework versions
+
+- PEFT 0.10.0

liuhaotian/llava-v1.5-13b_1.0/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

liuhaotian/llava-v1.5-13b_1.0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b2582b692b13611e3505defb6e50477ccb75c89fbdcca86cf157e1a7ff687f
+size 1001466944

liuhaotian/llava-v1.5-13b_1.0/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

liuhaotian/llava-v1.5-13b_1.0/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

liuhaotian/llava-v1.5-13b_1.0/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

liuhaotian/llava-v1.5-13b_1.0/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840

trainer_state.json

@@ -17,145 +17,145 @@
     {
       "epoch": 0.07,
       "learning_rate": 6.309297535714573e-05,
-      "loss": 1.202,
+      "loss": 1.2013,
       "step": 2
     },
     {
       "epoch": 0.11,
       "learning_rate": 0.0001,
-      "loss": 1.1727,
+      "loss": 1.1723,
       "step": 3
     },
     {
       "epoch": 0.14,
       "learning_rate": 0.00012618595071429146,
-      "loss": 1.1316,
+      "loss": 1.1317,
       "step": 4
     },
     {
       "epoch": 0.18,
       "learning_rate": 0.0001464973520717927,
-      "loss": 1.0778,
+      "loss": 1.0776,
       "step": 5
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.00016309297535714573,
-      "loss": 1.0263,
+      "loss": 1.0266,
       "step": 6
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.00017712437491614223,
-      "loss": 0.9944,
+      "loss": 0.9953,
       "step": 7
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0001892789260714372,
-      "loss": 0.9553,
+      "loss": 0.9563,
       "step": 8
     },
     {
       "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 0.9323,
+      "loss": 0.9337,
       "step": 9
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 0.95,
+      "loss": 0.9513,
       "step": 10
     },
     {
       "epoch": 0.39,
       "learning_rate": 0.0002,
-      "loss": 0.881,
+      "loss": 0.8823,
       "step": 11
     },
     {
       "epoch": 0.43,
       "learning_rate": 0.0002,
-      "loss": 0.844,
+      "loss": 0.8438,
       "step": 12
     },
     {
       "epoch": 0.46,
       "learning_rate": 0.0002,
-      "loss": 0.8188,
+      "loss": 0.8205,
       "step": 13
     },
     {
       "epoch": 0.5,
       "learning_rate": 0.0002,
-      "loss": 0.7805,
+      "loss": 0.7802,
       "step": 14
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 0.7746,
+      "loss": 0.7714,
       "step": 15
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 0.7301,
+      "loss": 0.732,
       "step": 16
     },
     {
       "epoch": 0.61,
       "learning_rate": 0.0002,
-      "loss": 0.6493,
+      "loss": 0.6475,
       "step": 17
     },
     {
       "epoch": 0.64,
       "learning_rate": 0.0002,
-      "loss": 0.7035,
+      "loss": 0.7026,
       "step": 18
     },
     {
       "epoch": 0.68,
       "learning_rate": 0.0002,
-      "loss": 0.6117,
+      "loss": 0.611,
       "step": 19
     },
     {
       "epoch": 0.71,
       "learning_rate": 0.0002,
-      "loss": 0.6592,
+      "loss": 0.6581,
       "step": 20
     },
     {
       "epoch": 0.75,
       "learning_rate": 0.0002,
-      "loss": 0.5196,
+      "loss": 0.5189,
       "step": 21
     },
     {
       "epoch": 0.79,
       "learning_rate": 0.0002,
-      "loss": 0.4843,
+      "loss": 0.4852,
       "step": 22
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 0.4495,
+      "loss": 0.4482,
       "step": 23
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 0.3754,
+      "loss": 0.3752,
       "step": 24
     },
     {
       "epoch": 0.89,
       "learning_rate": 0.0002,
-      "loss": 0.4255,
+      "loss": 0.4258,
       "step": 25
     },
     {
@@ -167,153 +167,153 @@
     {
       "epoch": 0.96,
       "learning_rate": 0.0002,
-      "loss": 0.3981,
+      "loss": 0.3977,
       "step": 27
     },
     {
       "epoch": 1.0,
       "learning_rate": 0.0002,
-      "loss": 0.3214,
+      "loss": 0.3239,
       "step": 28
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.24818769097328186,
-      "eval_runtime": 55.2393,
-      "eval_samples_per_second": 15.695,
-      "eval_steps_per_second": 0.507,
+      "eval_loss": 0.24691244959831238,
+      "eval_runtime": 54.9798,
+      "eval_samples_per_second": 15.769,
+      "eval_steps_per_second": 0.509,
       "step": 28
     },
     {
       "epoch": 1.04,
       "learning_rate": 0.0002,
-      "loss": 0.2308,
+      "loss": 0.2309,
       "step": 29
     },
     {
       "epoch": 1.07,
       "learning_rate": 0.0002,
-      "loss": 0.2436,
+      "loss": 0.2426,
       "step": 30
     },
     {
       "epoch": 1.11,
       "learning_rate": 0.0002,
-      "loss": 0.2235,
+      "loss": 0.2226,
       "step": 31
     },
     {
       "epoch": 1.14,
       "learning_rate": 0.0002,
-      "loss": 0.1936,
+      "loss": 0.1932,
       "step": 32
     },
     {
       "epoch": 1.18,
       "learning_rate": 0.0002,
-      "loss": 0.2112,
+      "loss": 0.212,
       "step": 33
     },
     {
       "epoch": 1.21,
       "learning_rate": 0.0002,
-      "loss": 0.1917,
+      "loss": 0.1909,
       "step": 34
     },
     {
       "epoch": 1.25,
       "learning_rate": 0.0002,
-      "loss": 0.2321,
+      "loss": 0.2315,
       "step": 35
     },
     {
       "epoch": 1.29,
       "learning_rate": 0.0002,
-      "loss": 0.1529,
+      "loss": 0.1531,
       "step": 36
     },
     {
       "epoch": 1.32,
       "learning_rate": 0.0002,
-      "loss": 0.153,
+      "loss": 0.1523,
       "step": 37
     },
     {
       "epoch": 1.36,
       "learning_rate": 0.0002,
-      "loss": 0.0953,
+      "loss": 0.0959,
       "step": 38
     },
     {
       "epoch": 1.39,
       "learning_rate": 0.0002,
-      "loss": 0.1034,
+      "loss": 0.1044,
       "step": 39
     },
     {
       "epoch": 1.43,
       "learning_rate": 0.0002,
-      "loss": 0.1744,
+      "loss": 0.1752,
       "step": 40
     },
     {
       "epoch": 1.46,
       "learning_rate": 0.0002,
-      "loss": 0.114,
+      "loss": 0.1159,
       "step": 41
     },
     {
       "epoch": 1.5,
       "learning_rate": 0.0002,
-      "loss": 0.1056,
+      "loss": 0.1041,
       "step": 42
     },
     {
       "epoch": 1.54,
       "learning_rate": 0.0002,
-      "loss": 0.1304,
+      "loss": 0.1311,
       "step": 43
     },
     {
       "epoch": 1.57,
       "learning_rate": 0.0002,
-      "loss": 0.1312,
+      "loss": 0.1307,
       "step": 44
     },
     {
       "epoch": 1.61,
       "learning_rate": 0.0002,
-      "loss": 0.0674,
+      "loss": 0.0678,
       "step": 45
     },
     {
       "epoch": 1.64,
       "learning_rate": 0.0002,
-      "loss": 0.0739,
+      "loss": 0.0746,
       "step": 46
     },
     {
       "epoch": 1.68,
       "learning_rate": 0.0002,
-      "loss": 0.0908,
+      "loss": 0.0903,
       "step": 47
     },
     {
       "epoch": 1.71,
       "learning_rate": 0.0002,
-      "loss": 0.1123,
+      "loss": 0.1146,
       "step": 48
     },
     {
       "epoch": 1.75,
       "learning_rate": 0.0002,
-      "loss": 0.0984,
+      "loss": 0.1019,
       "step": 49
     },
     {
       "epoch": 1.79,
       "learning_rate": 0.0002,
-      "loss": 0.0546,
+      "loss": 0.056,
       "step": 50
     },
     {
@@ -325,457 +325,457 @@
     {
       "epoch": 1.86,
       "learning_rate": 0.0002,
-      "loss": 0.0477,
+      "loss": 0.0487,
       "step": 52
     },
     {
       "epoch": 1.89,
       "learning_rate": 0.0002,
-      "loss": 0.1093,
+      "loss": 0.1094,
       "step": 53
     },
     {
       "epoch": 1.93,
       "learning_rate": 0.0002,
-      "loss": 0.1574,
+      "loss": 0.1581,
       "step": 54
     },
     {
       "epoch": 1.96,
       "learning_rate": 0.0002,
-      "loss": 0.1059,
+      "loss": 0.1083,
       "step": 55
     },
     {
       "epoch": 2.0,
       "learning_rate": 0.0002,
-      "loss": 0.0395,
+      "loss": 0.0396,
       "step": 56
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.04451237618923187,
-      "eval_runtime": 55.2461,
-      "eval_samples_per_second": 15.693,
-      "eval_steps_per_second": 0.507,
+      "eval_loss": 0.04381483793258667,
+      "eval_runtime": 55.1711,
+      "eval_samples_per_second": 15.715,
+      "eval_steps_per_second": 0.508,
       "step": 56
     },
     {
       "epoch": 2.04,
       "learning_rate": 0.0002,
-      "loss": 0.0381,
+      "loss": 0.0368,
       "step": 57
     },
     {
       "epoch": 2.07,
       "learning_rate": 0.0002,
-      "loss": 0.0298,
+      "loss": 0.0299,
       "step": 58
     },
     {
       "epoch": 2.11,
       "learning_rate": 0.0002,
-      "loss": 0.0321,
+      "loss": 0.0304,
       "step": 59
     },
     {
       "epoch": 2.14,
       "learning_rate": 0.0002,
-      "loss": 0.0437,
+      "loss": 0.0429,
       "step": 60
     },
     {
       "epoch": 2.18,
       "learning_rate": 0.0002,
-      "loss": 0.0272,
+      "loss": 0.0256,
       "step": 61
     },
     {
       "epoch": 2.21,
       "learning_rate": 0.0002,
-      "loss": 0.0381,
+      "loss": 0.0375,
       "step": 62
     },
     {
       "epoch": 2.25,
       "learning_rate": 0.0002,
-      "loss": 0.0266,
+      "loss": 0.0248,
       "step": 63
     },
     {
       "epoch": 2.29,
       "learning_rate": 0.0002,
-      "loss": 0.0228,
+      "loss": 0.022,
       "step": 64
     },
     {
       "epoch": 2.32,
       "learning_rate": 0.0002,
-      "loss": 0.029,
+      "loss": 0.0292,
       "step": 65
     },
     {
       "epoch": 2.36,
       "learning_rate": 0.0002,
-      "loss": 0.0288,
+      "loss": 0.0273,
       "step": 66
     },
     {
       "epoch": 2.39,
       "learning_rate": 0.0002,
-      "loss": 0.0155,
+      "loss": 0.0152,
       "step": 67
     },
     {
       "epoch": 2.43,
       "learning_rate": 0.0002,
-      "loss": 0.0294,
+      "loss": 0.0301,
       "step": 68
     },
     {
       "epoch": 2.46,
       "learning_rate": 0.0002,
-      "loss": 0.0368,
+      "loss": 0.0358,
       "step": 69
     },
     {
       "epoch": 2.5,
       "learning_rate": 0.0002,
-      "loss": 0.0278,
+      "loss": 0.0269,
       "step": 70
     },
     {
       "epoch": 2.54,
       "learning_rate": 0.0002,
-      "loss": 0.0194,
+      "loss": 0.0179,
       "step": 71
     },
     {
       "epoch": 2.57,
       "learning_rate": 0.0002,
-      "loss": 0.0216,
+      "loss": 0.0183,
       "step": 72
     },
     {
       "epoch": 2.61,
       "learning_rate": 0.0002,
-      "loss": 0.0142,
+      "loss": 0.0132,
       "step": 73
     },
     {
       "epoch": 2.64,
       "learning_rate": 0.0002,
-      "loss": 0.0362,
+      "loss": 0.0329,
       "step": 74
     },
     {
       "epoch": 2.68,
       "learning_rate": 0.0002,
-      "loss": 0.0279,
+      "loss": 0.0267,
       "step": 75
     },
     {
       "epoch": 2.71,
       "learning_rate": 0.0002,
-      "loss": 0.0171,
+      "loss": 0.0193,
       "step": 76
     },
     {
       "epoch": 2.75,
       "learning_rate": 0.0002,
-      "loss": 0.0126,
+      "loss": 0.0101,
       "step": 77
     },
     {
       "epoch": 2.79,
       "learning_rate": 0.0002,
-      "loss": 0.026,
+      "loss": 0.023,
       "step": 78
     },
     {
       "epoch": 2.82,
       "learning_rate": 0.0002,
-      "loss": 0.03,
+      "loss": 0.0317,
       "step": 79
     },
     {
       "epoch": 2.86,
       "learning_rate": 0.0002,
-      "loss": 0.0253,
+      "loss": 0.0225,
       "step": 80
     },
     {
       "epoch": 2.89,
       "learning_rate": 0.0002,
-      "loss": 0.0229,
+      "loss": 0.0198,
       "step": 81
     },
     {
       "epoch": 2.93,
       "learning_rate": 0.0002,
-      "loss": 0.0245,
+      "loss": 0.0232,
       "step": 82
     },
     {
       "epoch": 2.96,
       "learning_rate": 0.0002,
-      "loss": 0.0309,
+      "loss": 0.0287,
       "step": 83
     },
     {
       "epoch": 3.0,
       "learning_rate": 0.0002,
-      "loss": 0.0125,
+      "loss": 0.0086,
       "step": 84
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.012688164599239826,
-      "eval_runtime": 55.285,
-      "eval_samples_per_second": 15.682,
-      "eval_steps_per_second": 0.506,
+      "eval_loss": 0.01250830665230751,
+      "eval_runtime": 54.9958,
+      "eval_samples_per_second": 15.765,
+      "eval_steps_per_second": 0.509,
       "step": 84
     },
     {
       "epoch": 3.04,
       "learning_rate": 0.0002,
-      "loss": 0.0061,
+      "loss": 0.0059,
       "step": 85
     },
     {
       "epoch": 3.07,
       "learning_rate": 0.0002,
-      "loss": 0.012,
+      "loss": 0.0121,
       "step": 86
     },
     {
       "epoch": 3.11,
       "learning_rate": 0.0002,
-      "loss": 0.0101,
+      "loss": 0.0091,
       "step": 87
     },
     {
       "epoch": 3.14,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0078,
       "step": 88
     },
     {
       "epoch": 3.18,
       "learning_rate": 0.0002,
-      "loss": 0.0099,
+      "loss": 0.0124,
       "step": 89
     },
     {
       "epoch": 3.21,
       "learning_rate": 0.0002,
-      "loss": 0.0128,
+      "loss": 0.0107,
       "step": 90
     },
     {
       "epoch": 3.25,
       "learning_rate": 0.0002,
-      "loss": 0.0107,
+      "loss": 0.0106,
       "step": 91
     },
     {
       "epoch": 3.29,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0107,
       "step": 92
     },
     {
       "epoch": 3.32,
       "learning_rate": 0.0002,
-      "loss": 0.0053,
+      "loss": 0.0119,
       "step": 93
     },
     {
       "epoch": 3.36,
       "learning_rate": 0.0002,
-      "loss": 0.0072,
+      "loss": 0.0054,
       "step": 94
     },
     {
       "epoch": 3.39,
       "learning_rate": 0.0002,
-      "loss": 0.0105,
+      "loss": 0.0078,
       "step": 95
     },
     {
       "epoch": 3.43,
       "learning_rate": 0.0002,
-      "loss": 0.0118,
+      "loss": 0.0132,
       "step": 96
     },
     {
       "epoch": 3.46,
       "learning_rate": 0.0002,
-      "loss": 0.0087,
+      "loss": 0.0123,
       "step": 97
     },
     {
       "epoch": 3.5,
       "learning_rate": 0.0002,
-      "loss": 0.0117,
+      "loss": 0.0144,
       "step": 98
     },
     {
       "epoch": 3.54,
       "learning_rate": 0.0002,
-      "loss": 0.0174,
+      "loss": 0.0099,
       "step": 99
     },
     {
       "epoch": 3.57,
       "learning_rate": 0.0002,
-      "loss": 0.0053,
+      "loss": 0.0075,
       "step": 100
     },
     {
       "epoch": 3.61,
       "learning_rate": 0.0002,
-      "loss": 0.0189,
+      "loss": 0.0131,
       "step": 101
     },
     {
       "epoch": 3.64,
       "learning_rate": 0.0002,
-      "loss": 0.0093,
+      "loss": 0.0076,
       "step": 102
     },
     {
       "epoch": 3.68,
       "learning_rate": 0.0002,
-      "loss": 0.0142,
+      "loss": 0.0129,
       "step": 103
     },
     {
       "epoch": 3.71,
       "learning_rate": 0.0002,
-      "loss": 0.0151,
+      "loss": 0.0122,
       "step": 104
     },
     {
       "epoch": 3.75,
       "learning_rate": 0.0002,
-      "loss": 0.0162,
+      "loss": 0.0113,
       "step": 105
     },
     {
       "epoch": 3.79,
       "learning_rate": 0.0002,
-      "loss": 0.0134,
+      "loss": 0.0101,
       "step": 106
     },
     {
       "epoch": 3.82,
       "learning_rate": 0.0002,
-      "loss": 0.0071,
+      "loss": 0.006,
       "step": 107
     },
     {
       "epoch": 3.86,
       "learning_rate": 0.0002,
-      "loss": 0.0113,
+      "loss": 0.0078,
       "step": 108
     },
     {
       "epoch": 3.89,
       "learning_rate": 0.0002,
-      "loss": 0.0084,
+      "loss": 0.0052,
       "step": 109
     },
     {
       "epoch": 3.93,
       "learning_rate": 0.0002,
-      "loss": 0.0171,
+      "loss": 0.0155,
       "step": 110
     },
     {
       "epoch": 3.96,
       "learning_rate": 0.0002,
-      "loss": 0.0032,
+      "loss": 0.0043,
       "step": 111
     },
     {
       "epoch": 4.0,
       "learning_rate": 0.0002,
-      "loss": 0.0046,
+      "loss": 0.005,
       "step": 112
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.005700697656720877,
-      "eval_runtime": 55.3607,
-      "eval_samples_per_second": 15.661,
-      "eval_steps_per_second": 0.506,
+      "eval_loss": 0.005612094886600971,
+      "eval_runtime": 55.1695,
+      "eval_samples_per_second": 15.715,
+      "eval_steps_per_second": 0.508,
       "step": 112
     },
     {
       "epoch": 4.04,
       "learning_rate": 0.0002,
-      "loss": 0.0057,
+      "loss": 0.0061,
       "step": 113
     },
     {
       "epoch": 4.07,
       "learning_rate": 0.0002,
-      "loss": 0.0052,
+      "loss": 0.0056,
       "step": 114
     },
     {
       "epoch": 4.11,
       "learning_rate": 0.0002,
-      "loss": 0.0047,
+      "loss": 0.0034,
       "step": 115
     },
     {
       "epoch": 4.14,
       "learning_rate": 0.0002,
-      "loss": 0.0073,
+      "loss": 0.0048,
       "step": 116
     },
     {
       "epoch": 4.18,
       "learning_rate": 0.0002,
-      "loss": 0.0047,
+      "loss": 0.005,
       "step": 117
     },
     {
       "epoch": 4.21,
       "learning_rate": 0.0002,
-      "loss": 0.0061,
+      "loss": 0.0062,
       "step": 118
     },
     {
       "epoch": 4.25,
       "learning_rate": 0.0002,
-      "loss": 0.0106,
+      "loss": 0.0131,
       "step": 119
     },
     {
       "epoch": 4.29,
       "learning_rate": 0.0002,
-      "loss": 0.0082,
+      "loss": 0.0064,
       "step": 120
     },
     {
       "epoch": 4.32,
       "learning_rate": 0.0002,
-      "loss": 0.006,
+      "loss": 0.005,
       "step": 121
     },
     {
       "epoch": 4.36,
       "learning_rate": 0.0002,
-      "loss": 0.0059,
+      "loss": 0.0044,
       "step": 122
     },
     {
       "epoch": 4.39,
       "learning_rate": 0.0002,
-      "loss": 0.0064,
+      "loss": 0.0069,
       "step": 123
     },
     {
@@ -787,995 +787,995 @@
     {
       "epoch": 4.46,
       "learning_rate": 0.0002,
-      "loss": 0.0075,
+      "loss": 0.0043,
       "step": 125
     },
     {
       "epoch": 4.5,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0032,
       "step": 126
     },
     {
       "epoch": 4.54,
       "learning_rate": 0.0002,
-      "loss": 0.0024,
+      "loss": 0.0028,
       "step": 127
     },
     {
       "epoch": 4.57,
       "learning_rate": 0.0002,
-      "loss": 0.0034,
+      "loss": 0.0053,
       "step": 128
     },
     {
       "epoch": 4.61,
       "learning_rate": 0.0002,
-      "loss": 0.0039,
+      "loss": 0.0052,
       "step": 129
     },
     {
       "epoch": 4.64,
       "learning_rate": 0.0002,
-      "loss": 0.0039,
+      "loss": 0.0106,
       "step": 130
     },
     {
       "epoch": 4.68,
       "learning_rate": 0.0002,
-      "loss": 0.0035,
+      "loss": 0.0071,
       "step": 131
     },
     {
       "epoch": 4.71,
       "learning_rate": 0.0002,
-      "loss": 0.0033,
+      "loss": 0.0044,
       "step": 132
     },
     {
       "epoch": 4.75,
       "learning_rate": 0.0002,
-      "loss": 0.0088,
+      "loss": 0.0075,
       "step": 133
     },
     {
       "epoch": 4.79,
       "learning_rate": 0.0002,
-      "loss": 0.0022,
+      "loss": 0.0026,
       "step": 134
     },
     {
       "epoch": 4.82,
       "learning_rate": 0.0002,
-      "loss": 0.0049,
+      "loss": 0.0071,
       "step": 135
     },
     {
       "epoch": 4.86,
       "learning_rate": 0.0002,
-      "loss": 0.0036,
+      "loss": 0.005,
       "step": 136
     },
     {
       "epoch": 4.89,
       "learning_rate": 0.0002,
-      "loss": 0.0035,
+      "loss": 0.0042,
       "step": 137
     },
     {
       "epoch": 4.93,
       "learning_rate": 0.0002,
-      "loss": 0.0077,
+      "loss": 0.0059,
       "step": 138
     },
     {
       "epoch": 4.96,
       "learning_rate": 0.0002,
-      "loss": 0.0046,
+      "loss": 0.004,
       "step": 139
     },
     {
       "epoch": 5.0,
       "learning_rate": 0.0002,
-      "loss": 0.0044,
+      "loss": 0.0051,
       "step": 140
     },
     {
       "epoch": 5.0,
-      "eval_loss": 0.0035695512779057026,
-      "eval_runtime": 55.238,
-      "eval_samples_per_second": 15.696,
-      "eval_steps_per_second": 0.507,
+      "eval_loss": 0.004839635919779539,
+      "eval_runtime": 55.1037,
+      "eval_samples_per_second": 15.734,
+      "eval_steps_per_second": 0.508,
       "step": 140
     },
     {
       "epoch": 5.04,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0045,
       "step": 141
     },
     {
       "epoch": 5.07,
       "learning_rate": 0.0002,
-      "loss": 0.0029,
+      "loss": 0.0066,
       "step": 142
     },
     {
       "epoch": 5.11,
       "learning_rate": 0.0002,
-      "loss": 0.0056,
+      "loss": 0.0023,
       "step": 143
     },
     {
       "epoch": 5.14,
       "learning_rate": 0.0002,
-      "loss": 0.0072,
+      "loss": 0.0047,
       "step": 144
     },
     {
       "epoch": 5.18,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0081,
       "step": 145
     },
     {
       "epoch": 5.21,
       "learning_rate": 0.0002,
-      "loss": 0.0046,
+      "loss": 0.0074,
       "step": 146
     },
     {
       "epoch": 5.25,
       "learning_rate": 0.0002,
-      "loss": 0.0062,
+      "loss": 0.002,
       "step": 147
     },
     {
       "epoch": 5.29,
       "learning_rate": 0.0002,
-      "loss": 0.0029,
+      "loss": 0.0049,
       "step": 148
     },
     {
       "epoch": 5.32,
       "learning_rate": 0.0002,
-      "loss": 0.0088,
+      "loss": 0.0093,
       "step": 149
     },
     {
       "epoch": 5.36,
       "learning_rate": 0.0002,
-      "loss": 0.0035,
+      "loss": 0.0028,
       "step": 150
     },
     {
       "epoch": 5.39,
       "learning_rate": 0.0002,
-      "loss": 0.0019,
+      "loss": 0.005,
       "step": 151
     },
     {
       "epoch": 5.43,
       "learning_rate": 0.0002,
-      "loss": 0.0021,
+      "loss": 0.0027,
       "step": 152
     },
     {
       "epoch": 5.46,
       "learning_rate": 0.0002,
-      "loss": 0.0049,
+      "loss": 0.0024,
       "step": 153
     },
     {
       "epoch": 5.5,
       "learning_rate": 0.0002,
-      "loss": 0.0034,
+      "loss": 0.0051,
       "step": 154
     },
     {
       "epoch": 5.54,
       "learning_rate": 0.0002,
-      "loss": 0.0037,
+      "loss": 0.0057,
       "step": 155
     },
     {
       "epoch": 5.57,
       "learning_rate": 0.0002,
-      "loss": 0.0059,
+      "loss": 0.0042,
       "step": 156
     },
     {
       "epoch": 5.61,
       "learning_rate": 0.0002,
-      "loss": 0.0055,
+      "loss": 0.0076,
       "step": 157
     },
     {
       "epoch": 5.64,
       "learning_rate": 0.0002,
-      "loss": 0.004,
+      "loss": 0.0026,
       "step": 158
     },
     {
       "epoch": 5.68,
       "learning_rate": 0.0002,
-      "loss": 0.0043,
+      "loss": 0.0062,
       "step": 159
     },
     {
       "epoch": 5.71,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0039,
       "step": 160
     },
     {
       "epoch": 5.75,
       "learning_rate": 0.0002,
-      "loss": 0.0054,
+      "loss": 0.0028,
       "step": 161
     },
     {
       "epoch": 5.79,
       "learning_rate": 0.0002,
-      "loss": 0.0046,
+      "loss": 0.0068,
       "step": 162
     },
     {
       "epoch": 5.82,
       "learning_rate": 0.0002,
-      "loss": 0.0062,
+      "loss": 0.001,
       "step": 163
     },
     {
       "epoch": 5.86,
       "learning_rate": 0.0002,
-      "loss": 0.0081,
+      "loss": 0.0036,
       "step": 164
     },
     {
       "epoch": 5.89,
       "learning_rate": 0.0002,
-      "loss": 0.0053,
+      "loss": 0.004,
       "step": 165
     },
     {
       "epoch": 5.93,
       "learning_rate": 0.0002,
-      "loss": 0.0057,
+      "loss": 0.0028,
       "step": 166
     },
     {
       "epoch": 5.96,
       "learning_rate": 0.0002,
-      "loss": 0.01,
+      "loss": 0.0046,
       "step": 167
     },
     {
       "epoch": 6.0,
       "learning_rate": 0.0002,
-      "loss": 0.0044,
+      "loss": 0.0036,
       "step": 168
     },
     {
       "epoch": 6.0,
-      "eval_loss": 0.004916314501315355,
-      "eval_runtime": 55.2584,
-      "eval_samples_per_second": 15.69,
-      "eval_steps_per_second": 0.507,
+      "eval_loss": 0.0032981247641146183,
+      "eval_runtime": 55.1126,
+      "eval_samples_per_second": 15.731,
+      "eval_steps_per_second": 0.508,
       "step": 168
     },
     {
       "epoch": 6.04,
       "learning_rate": 0.0002,
-      "loss": 0.0035,
+      "loss": 0.0021,
       "step": 169
     },
     {
       "epoch": 6.07,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0053,
       "step": 170
     },
     {
       "epoch": 6.11,
       "learning_rate": 0.0002,
-      "loss": 0.0036,
+      "loss": 0.0034,
       "step": 171
     },
     {
       "epoch": 6.14,
       "learning_rate": 0.0002,
-      "loss": 0.0032,
+      "loss": 0.0051,
       "step": 172
     },
     {
       "epoch": 6.18,
       "learning_rate": 0.0002,
-      "loss": 0.0078,
+      "loss": 0.004,
       "step": 173
     },
     {
       "epoch": 6.21,
       "learning_rate": 0.0002,
-      "loss": 0.0061,
+      "loss": 0.0032,
       "step": 174
     },
     {
       "epoch": 6.25,
       "learning_rate": 0.0002,
-      "loss": 0.0081,
+      "loss": 0.0039,
       "step": 175
     },
     {
       "epoch": 6.29,
       "learning_rate": 0.0002,
-      "loss": 0.0034,
+      "loss": 0.0045,
       "step": 176
     },
     {
       "epoch": 6.32,
       "learning_rate": 0.0002,
-      "loss": 0.0035,
+      "loss": 0.0105,
       "step": 177
     },
     {
       "epoch": 6.36,
       "learning_rate": 0.0002,
-      "loss": 0.0041,
+      "loss": 0.0017,
       "step": 178
     },
     {
       "epoch": 6.39,
       "learning_rate": 0.0002,
-      "loss": 0.003,
+      "loss": 0.0073,
       "step": 179
     },
     {
       "epoch": 6.43,
       "learning_rate": 0.0002,
-      "loss": 0.0025,
+      "loss": 0.0088,
       "step": 180
     },
     {
       "epoch": 6.46,
       "learning_rate": 0.0002,
-      "loss": 0.0032,
+      "loss": 0.0029,
       "step": 181
     },
     {
       "epoch": 6.5,
       "learning_rate": 0.0002,
-      "loss": 0.004,
+      "loss": 0.0087,
       "step": 182
     },
     {
       "epoch": 6.54,
       "learning_rate": 0.0002,
-      "loss": 0.0042,
+      "loss": 0.0045,
       "step": 183
     },
     {
       "epoch": 6.57,
       "learning_rate": 0.0002,
-      "loss": 0.0058,
+      "loss": 0.0096,
       "step": 184
     },
     {
       "epoch": 6.61,
       "learning_rate": 0.0002,
-      "loss": 0.0027,
+      "loss": 0.0036,
       "step": 185
     },
     {
       "epoch": 6.64,
       "learning_rate": 0.0002,
-      "loss": 0.0043,
+      "loss": 0.0061,
       "step": 186
     },
     {
       "epoch": 6.68,
       "learning_rate": 0.0002,
-      "loss": 0.0025,
+      "loss": 0.0052,
       "step": 187
     },
     {
       "epoch": 6.71,
       "learning_rate": 0.0002,
-      "loss": 0.0039,
+      "loss": 0.0033,
       "step": 188
     },
     {
       "epoch": 6.75,
       "learning_rate": 0.0002,
-      "loss": 0.0024,
+      "loss": 0.0072,
       "step": 189
     },
     {
       "epoch": 6.79,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0016,
       "step": 190
     },
     {
       "epoch": 6.82,
       "learning_rate": 0.0002,
-      "loss": 0.0027,
+      "loss": 0.0024,
       "step": 191
     },
     {
       "epoch": 6.86,
       "learning_rate": 0.0002,
-      "loss": 0.0075,
+      "loss": 0.0044,
       "step": 192
     },
     {
       "epoch": 6.89,
       "learning_rate": 0.0002,
-      "loss": 0.0028,
+      "loss": 0.0011,
       "step": 193
     },
     {
       "epoch": 6.93,
       "learning_rate": 0.0002,
-      "loss": 0.0029,
+      "loss": 0.0054,
       "step": 194
     },
     {
       "epoch": 6.96,
       "learning_rate": 0.0002,
-      "loss": 0.0017,
+      "loss": 0.0023,
       "step": 195
     },
     {
       "epoch": 7.0,
       "learning_rate": 0.0002,
-      "loss": 0.0014,
+      "loss": 0.006,
       "step": 196
     },
     {
       "epoch": 7.0,
-      "eval_loss": 0.0020930657628923655,
-      "eval_runtime": 55.303,
-      "eval_samples_per_second": 15.677,
-      "eval_steps_per_second": 0.506,
+      "eval_loss": 0.0035514547489583492,
+      "eval_runtime": 55.2585,
+      "eval_samples_per_second": 15.69,
+      "eval_steps_per_second": 0.507,
       "step": 196
     },
     {
       "epoch": 7.04,
       "learning_rate": 0.0002,
-      "loss": 0.0009,
+      "loss": 0.0016,
       "step": 197
     },
     {
       "epoch": 7.07,
       "learning_rate": 0.0002,
-      "loss": 0.0074,
+      "loss": 0.0049,
       "step": 198
     },
     {
       "epoch": 7.11,
       "learning_rate": 0.0002,
-      "loss": 0.0018,
+      "loss": 0.002,
       "step": 199
     },
     {
       "epoch": 7.14,
       "learning_rate": 0.0002,
-      "loss": 0.0017,
+      "loss": 0.0067,
       "step": 200
     },
     {
       "epoch": 7.18,
       "learning_rate": 0.0002,
-      "loss": 0.0008,
+      "loss": 0.002,
       "step": 201
     },
     {
       "epoch": 7.21,
       "learning_rate": 0.0002,
-      "loss": 0.0017,
+      "loss": 0.0024,
       "step": 202
     },
     {
       "epoch": 7.25,
       "learning_rate": 0.0002,
-      "loss": 0.0028,
+      "loss": 0.0032,
       "step": 203
     },
     {
       "epoch": 7.29,
       "learning_rate": 0.0002,
-      "loss": 0.0024,
+      "loss": 0.0088,
       "step": 204
     },
     {
       "epoch": 7.32,
       "learning_rate": 0.0002,
-      "loss": 0.0014,
+      "loss": 0.0013,
       "step": 205
     },
     {
       "epoch": 7.36,
       "learning_rate": 0.0002,
-      "loss": 0.0059,
+      "loss": 0.0034,
       "step": 206
     },
     {
       "epoch": 7.39,
       "learning_rate": 0.0002,
-      "loss": 0.0012,
+      "loss": 0.0022,
       "step": 207
     },
     {
       "epoch": 7.43,
       "learning_rate": 0.0002,
-      "loss": 0.0019,
+      "loss": 0.0016,
       "step": 208
     },
     {
       "epoch": 7.46,
       "learning_rate": 0.0002,
-      "loss": 0.0028,
+      "loss": 0.0024,
       "step": 209
     },
     {
       "epoch": 7.5,
       "learning_rate": 0.0002,
-      "loss": 0.0025,
+      "loss": 0.0023,
       "step": 210
     },
     {
       "epoch": 7.54,
       "learning_rate": 0.0002,
-      "loss": 0.0003,
+      "loss": 0.0022,
       "step": 211
     },
     {
       "epoch": 7.57,
       "learning_rate": 0.0002,
-      "loss": 0.0006,
+      "loss": 0.0022,
       "step": 212
     },
     {
       "epoch": 7.61,
       "learning_rate": 0.0002,
-      "loss": 0.001,
+      "loss": 0.0084,
       "step": 213
     },
     {
       "epoch": 7.64,
       "learning_rate": 0.0002,
-      "loss": 0.0016,
+      "loss": 0.0039,
       "step": 214
     },
     {
       "epoch": 7.68,
       "learning_rate": 0.0002,
-      "loss": 0.0058,
+      "loss": 0.0035,
       "step": 215
     },
     {
       "epoch": 7.71,
       "learning_rate": 0.0002,
-      "loss": 0.0011,
+      "loss": 0.0021,
       "step": 216
     },
     {
       "epoch": 7.75,
       "learning_rate": 0.0002,
-      "loss": 0.0035,
+      "loss": 0.004,
       "step": 217
     },
     {
       "epoch": 7.79,
       "learning_rate": 0.0002,
-      "loss": 0.0015,
+      "loss": 0.0027,
       "step": 218
     },
     {
       "epoch": 7.82,
       "learning_rate": 0.0002,
-      "loss": 0.0061,
+      "loss": 0.0019,
       "step": 219
     },
     {
       "epoch": 7.86,
       "learning_rate": 0.0002,
-      "loss": 0.0015,
+      "loss": 0.0013,
       "step": 220
     },
     {
       "epoch": 7.89,
       "learning_rate": 0.0002,
-      "loss": 0.0025,
+      "loss": 0.0043,
       "step": 221
     },
     {
       "epoch": 7.93,
       "learning_rate": 0.0002,
-      "loss": 0.0008,
+      "loss": 0.0012,
       "step": 222
     },
     {
       "epoch": 7.96,
       "learning_rate": 0.0002,
-      "loss": 0.0016,
+      "loss": 0.0008,
       "step": 223
     },
     {
       "epoch": 8.0,
       "learning_rate": 0.0002,
-      "loss": 0.003,
+      "loss": 0.0017,
       "step": 224
     },
     {
       "epoch": 8.0,
-      "eval_loss": 0.0014942155685275793,
-      "eval_runtime": 55.2573,
-      "eval_samples_per_second": 15.69,
-      "eval_steps_per_second": 0.507,
+      "eval_loss": 0.0020963489077985287,
+      "eval_runtime": 55.1683,
+      "eval_samples_per_second": 15.716,
+      "eval_steps_per_second": 0.508,
       "step": 224
     },
     {
       "epoch": 8.04,
       "learning_rate": 0.0002,
-      "loss": 0.0011,
+      "loss": 0.002,
       "step": 225
     },
     {
       "epoch": 8.07,
       "learning_rate": 0.0002,
-      "loss": 0.0044,
+      "loss": 0.0008,
       "step": 226
     },
     {
       "epoch": 8.11,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0017,
       "step": 227
     },
     {
       "epoch": 8.14,
       "learning_rate": 0.0002,
-      "loss": 0.0007,
+      "loss": 0.0013,
       "step": 228
     },
     {
       "epoch": 8.18,
       "learning_rate": 0.0002,
-      "loss": 0.0005,
+      "loss": 0.0007,
       "step": 229
     },
     {
       "epoch": 8.21,
       "learning_rate": 0.0002,
-      "loss": 0.0012,
+      "loss": 0.0005,
       "step": 230
     },
     {
       "epoch": 8.25,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0021,
       "step": 231
     },
     {
       "epoch": 8.29,
       "learning_rate": 0.0002,
-      "loss": 0.0026,
+      "loss": 0.0037,
       "step": 232
     },
     {
       "epoch": 8.32,
       "learning_rate": 0.0002,
-      "loss": 0.0015,
+      "loss": 0.0034,
       "step": 233
     },
     {
       "epoch": 8.36,
       "learning_rate": 0.0002,
-      "loss": 0.0025,
+      "loss": 0.0038,
       "step": 234
     },
     {
       "epoch": 8.39,
       "learning_rate": 0.0002,
-      "loss": 0.0008,
+      "loss": 0.0018,
       "step": 235
     },
     {
       "epoch": 8.43,
       "learning_rate": 0.0002,
-      "loss": 0.0026,
+      "loss": 0.0006,
       "step": 236
     },
     {
       "epoch": 8.46,
       "learning_rate": 0.0002,
-      "loss": 0.0003,
+      "loss": 0.0118,
       "step": 237
     },
     {
       "epoch": 8.5,
       "learning_rate": 0.0002,
-      "loss": 0.0005,
+      "loss": 0.0046,
       "step": 238
     },
     {
       "epoch": 8.54,
       "learning_rate": 0.0002,
-      "loss": 0.0023,
+      "loss": 0.0043,
       "step": 239
     },
     {
       "epoch": 8.57,
       "learning_rate": 0.0002,
-      "loss": 0.002,
+      "loss": 0.0023,
       "step": 240
     },
     {
       "epoch": 8.61,
       "learning_rate": 0.0002,
-      "loss": 0.0017,
+      "loss": 0.0038,
       "step": 241
     },
     {
       "epoch": 8.64,
       "learning_rate": 0.0002,
-      "loss": 0.0025,
+      "loss": 0.0056,
       "step": 242
     },
     {
       "epoch": 8.68,
       "learning_rate": 0.0002,
-      "loss": 0.0006,
+      "loss": 0.0083,
       "step": 243
     },
     {
       "epoch": 8.71,
       "learning_rate": 0.0002,
-      "loss": 0.0014,
+      "loss": 0.0039,
       "step": 244
     },
     {
       "epoch": 8.75,
       "learning_rate": 0.0002,
-      "loss": 0.0018,
+      "loss": 0.003,
       "step": 245
     },
     {
       "epoch": 8.79,
       "learning_rate": 0.0002,
-      "loss": 0.0006,
+      "loss": 0.0021,
       "step": 246
     },
     {
       "epoch": 8.82,
       "learning_rate": 0.0002,
-      "loss": 0.0012,
+      "loss": 0.002,
       "step": 247
     },
     {
       "epoch": 8.86,
       "learning_rate": 0.0002,
-      "loss": 0.0005,
+      "loss": 0.0037,
       "step": 248
     },
     {
       "epoch": 8.89,
       "learning_rate": 0.0002,
-      "loss": 0.0007,
+      "loss": 0.0014,
       "step": 249
     },
     {
       "epoch": 8.93,
       "learning_rate": 0.0002,
-      "loss": 0.0027,
+      "loss": 0.0037,
       "step": 250
     },
     {
       "epoch": 8.96,
       "learning_rate": 0.0002,
-      "loss": 0.0018,
+      "loss": 0.0031,
       "step": 251
     },
     {
       "epoch": 9.0,
       "learning_rate": 0.0002,
-      "loss": 0.0029,
+      "loss": 0.0041,
       "step": 252
     },
     {
       "epoch": 9.0,
-      "eval_loss": 0.0013407374499365687,
-      "eval_runtime": 54.9274,
-      "eval_samples_per_second": 15.784,
-      "eval_steps_per_second": 0.51,
+      "eval_loss": 0.0022224283311516047,
+      "eval_runtime": 55.1607,
+      "eval_samples_per_second": 15.718,
+      "eval_steps_per_second": 0.508,
       "step": 252
     },
     {
       "epoch": 9.04,
       "learning_rate": 0.0002,
-      "loss": 0.0041,
+      "loss": 0.0009,
       "step": 253
     },
     {
       "epoch": 9.07,
       "learning_rate": 0.0002,
-      "loss": 0.003,
+      "loss": 0.0011,
       "step": 254
     },
     {
       "epoch": 9.11,
       "learning_rate": 0.0002,
-      "loss": 0.0004,
+      "loss": 0.0038,
       "step": 255
     },
     {
       "epoch": 9.14,
       "learning_rate": 0.0002,
-      "loss": 0.0027,
+      "loss": 0.0026,
       "step": 256
     },
     {
       "epoch": 9.18,
       "learning_rate": 0.0002,
-      "loss": 0.003,
+      "loss": 0.004,
       "step": 257
     },
     {
       "epoch": 9.21,
       "learning_rate": 0.0002,
-      "loss": 0.0005,
+      "loss": 0.0047,
       "step": 258
     },
     {
       "epoch": 9.25,
       "learning_rate": 0.0002,
-      "loss": 0.0019,
+      "loss": 0.0023,
       "step": 259
     },
     {
       "epoch": 9.29,
       "learning_rate": 0.0002,
-      "loss": 0.0028,
+      "loss": 0.003,
       "step": 260
     },
     {
       "epoch": 9.32,
       "learning_rate": 0.0002,
-      "loss": 0.0014,
+      "loss": 0.0007,
       "step": 261
     },
     {
       "epoch": 9.36,
       "learning_rate": 0.0002,
-      "loss": 0.0018,
+      "loss": 0.0073,
       "step": 262
     },
     {
       "epoch": 9.39,
       "learning_rate": 0.0002,
-      "loss": 0.0038,
+      "loss": 0.0023,
       "step": 263
     },
     {
       "epoch": 9.43,
       "learning_rate": 0.0002,
-      "loss": 0.0019,
+      "loss": 0.0081,
       "step": 264
     },
     {
       "epoch": 9.46,
       "learning_rate": 0.0002,
-      "loss": 0.0008,
+      "loss": 0.0043,
       "step": 265
     },
     {
       "epoch": 9.5,
       "learning_rate": 0.0002,
-      "loss": 0.0021,
+      "loss": 0.0039,
       "step": 266
     },
     {
       "epoch": 9.54,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0052,
       "step": 267
     },
     {
       "epoch": 9.57,
       "learning_rate": 0.0002,
-      "loss": 0.0024,
+      "loss": 0.0049,
       "step": 268
     },
     {
       "epoch": 9.61,
       "learning_rate": 0.0002,
-      "loss": 0.0031,
+      "loss": 0.0076,
       "step": 269
     },
     {
       "epoch": 9.64,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0062,
       "step": 270
     },
     {
       "epoch": 9.68,
       "learning_rate": 0.0002,
-      "loss": 0.0014,
+      "loss": 0.005,
       "step": 271
     },
     {
       "epoch": 9.71,
       "learning_rate": 0.0002,
-      "loss": 0.0023,
+      "loss": 0.0063,
       "step": 272
     },
     {
       "epoch": 9.75,
       "learning_rate": 0.0002,
-      "loss": 0.0006,
+      "loss": 0.0052,
       "step": 273
     },
     {
       "epoch": 9.79,
       "learning_rate": 0.0002,
-      "loss": 0.0015,
+      "loss": 0.0042,
       "step": 274
     },
     {
       "epoch": 9.82,
       "learning_rate": 0.0002,
-      "loss": 0.0011,
+      "loss": 0.0087,
       "step": 275
     },
     {
       "epoch": 9.86,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0064,
       "step": 276
     },
     {
       "epoch": 9.89,
       "learning_rate": 0.0002,
-      "loss": 0.0014,
+      "loss": 0.0047,
       "step": 277
     },
     {
       "epoch": 9.93,
       "learning_rate": 0.0002,
-      "loss": 0.0016,
+      "loss": 0.0034,
       "step": 278
     },
     {
       "epoch": 9.96,
       "learning_rate": 0.0002,
-      "loss": 0.0007,
+      "loss": 0.0054,
       "step": 279
     },
     {
       "epoch": 10.0,
       "learning_rate": 0.0002,
-      "loss": 0.0011,
+      "loss": 0.0031,
       "step": 280
     },
     {
       "epoch": 10.0,
-      "eval_loss": 0.0036755690816789865,
-      "eval_runtime": 55.2858,
-      "eval_samples_per_second": 15.682,
-      "eval_steps_per_second": 0.506,
+      "eval_loss": 0.004367400426417589,
+      "eval_runtime": 55.2334,
+      "eval_samples_per_second": 15.697,
+      "eval_steps_per_second": 0.507,
       "step": 280
     },
     {
       "epoch": 10.0,
       "step": 280,
       "total_flos": 8.298694499798876e+17,
-      "train_loss": 0.09669673074760275,
-      "train_runtime": 3076.0317,
-      "train_samples_per_second": 2.819,
-      "train_steps_per_second": 0.091
+      "train_loss": 0.09713323155904488,
+      "train_runtime": 3137.8873,
+      "train_samples_per_second": 2.763,
+      "train_steps_per_second": 0.089
     }
   ],
   "logging_steps": 1.0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94bf3956f8afb1a220e42c04100c7f1281e8d2abcaf4f1bdc986598710eb313d
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
 size 6840