Upload folder using huggingface_hub

README.md

@@ -1,199 +1,9 @@
 ---
-library_name: transformers
-tags: []
+library_name: peft
 ---
+## Training procedure
 
-# Model Card for Model ID
+### Framework versions
 
-<!-- Provide a quick summary of what the model is/does. -->
 
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **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]
+- PEFT 0.5.0

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd6b99f5fd9b7919dc4cbaee8e6533961673f09ec72ca77d8362b1c63b444cc
+size 639787082

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "llava-hf/llava-1.5-7b-hf",
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_aspect_ratio": "pad",
+  "image_token_index": 32000,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 32001,
+  "pretraining_tp": 1,
+  "projector_hidden_act": "gelu",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "float16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6f71e844de54ca47720d30675ea9c43c9858ca4c0f6836e8c8bc05bddbecf9
+size 41961648

trainer_state.json

@@ -0,0 +1,1890 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 11.2153,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 11.2101,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6e-05,
+      "loss": 11.1907,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 11.0346,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001,
+      "loss": 10.6171,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 10.0148,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014,
+      "loss": 9.4405,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00016,
+      "loss": 9.7438,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00018,
+      "loss": 8.707,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 8.8771,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019999451693655123,
+      "loss": 8.7858,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019997806834748456,
+      "loss": 8.511,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019995065603657316,
+      "loss": 8.2111,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 8.0204,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001998629534754574,
+      "loss": 7.9454,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019980267284282717,
+      "loss": 7.8055,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019973144772244582,
+      "loss": 7.6032,
+      "step": 17
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 7.7403,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019955619646030802,
+      "loss": 7.7085,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019945218953682734,
+      "loss": 7.5279,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019933727656003963,
+      "loss": 7.2119,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 6.9685,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019907478404714436,
+      "loss": 6.8322,
+      "step": 23
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019892723329629887,
+      "loss": 6.7232,
+      "step": 24
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 6.7616,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 6.5955,
+      "step": 26
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001984195607969242,
+      "loss": 6.4523,
+      "step": 27
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001982287250728689,
+      "loss": 6.3178,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019802711746217218,
+      "loss": 6.371,
+      "step": 29
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 6.4004,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019759167619387476,
+      "loss": 6.2502,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019735789028731604,
+      "loss": 6.1807,
+      "step": 32
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019711342799096361,
+      "loss": 6.1244,
+      "step": 33
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 6.0723,
+      "step": 34
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 5.8887,
+      "step": 35
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019631625667976583,
+      "loss": 5.8987,
+      "step": 36
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001960293685676943,
+      "loss": 5.5855,
+      "step": 37
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 5.7129,
+      "step": 38
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001954240328516277,
+      "loss": 5.8263,
+      "step": 39
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 5.7092,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001947768410009586,
+      "loss": 5.6344,
+      "step": 41
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 5.5662,
+      "step": 42
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019408807689542257,
+      "loss": 5.5991,
+      "step": 43
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019372819894918915,
+      "loss": 5.3797,
+      "step": 44
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019335804264972018,
+      "loss": 5.4445,
+      "step": 45
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 5.4585,
+      "step": 46
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001925870584809995,
+      "loss": 5.2898,
+      "step": 47
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019218631515885006,
+      "loss": 5.196,
+      "step": 48
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019177546256839812,
+      "loss": 5.2029,
+      "step": 49
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.3546,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019092361090470688,
+      "loss": 5.2278,
+      "step": 51
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019048270524660196,
+      "loss": 5.2661,
+      "step": 52
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019003187714021938,
+      "loss": 5.0926,
+      "step": 53
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 5.2142,
+      "step": 54
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 5.1078,
+      "step": 55
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00018862035792312147,
+      "loss": 5.1481,
+      "step": 56
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001881303452064992,
+      "loss": 5.1971,
+      "step": 57
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 5.1135,
+      "step": 58
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00018712138111201895,
+      "loss": 5.1675,
+      "step": 59
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 4.9891,
+      "step": 60
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001860742027003944,
+      "loss": 4.9451,
+      "step": 61
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 4.8872,
+      "step": 62
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00018498926929868642,
+      "loss": 5.0473,
+      "step": 63
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018443279255020152,
+      "loss": 4.9591,
+      "step": 64
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018386705679454242,
+      "loss": 4.8218,
+      "step": 65
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 4.8672,
+      "step": 66
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00018270805742745617,
+      "loss": 4.9517,
+      "step": 67
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00018211492091337042,
+      "loss": 4.7033,
+      "step": 68
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00018151277957285543,
+      "loss": 4.6816,
+      "step": 69
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.6706,
+      "step": 70
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018028174751911146,
+      "loss": 4.8965,
+      "step": 71
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00017965299180241963,
+      "loss": 4.5277,
+      "step": 72
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00017901550123756906,
+      "loss": 4.709,
+      "step": 73
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000178369345732584,
+      "loss": 4.5827,
+      "step": 74
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0001777145961456971,
+      "loss": 4.526,
+      "step": 75
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00017705132427757895,
+      "loss": 4.4775,
+      "step": 76
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00017637960286346425,
+      "loss": 4.389,
+      "step": 77
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 4.5912,
+      "step": 78
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00017501110696304596,
+      "loss": 4.3966,
+      "step": 79
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017431448254773944,
+      "loss": 4.3832,
+      "step": 80
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017360970871197346,
+      "loss": 4.3049,
+      "step": 81
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 4.5175,
+      "step": 82
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017217602280983623,
+      "loss": 4.4391,
+      "step": 83
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017144726796328034,
+      "loss": 4.359,
+      "step": 84
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 4.4578,
+      "step": 85
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 4.2509,
+      "step": 86
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001692143173870407,
+      "loss": 4.213,
+      "step": 87
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00016845471059286887,
+      "loss": 4.3808,
+      "step": 88
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016768759696826608,
+      "loss": 4.2431,
+      "step": 89
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.1752,
+      "step": 90
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016613118653236518,
+      "loss": 4.1288,
+      "step": 91
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00016534206039901057,
+      "loss": 4.2743,
+      "step": 92
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00016454576877239507,
+      "loss": 4.1326,
+      "step": 93
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000163742398974869,
+      "loss": 4.2462,
+      "step": 94
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016293203910498376,
+      "loss": 4.1801,
+      "step": 95
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016211477802783103,
+      "loss": 4.2519,
+      "step": 96
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016129070536529766,
+      "loss": 4.1227,
+      "step": 97
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 4.096,
+      "step": 98
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001596224874965616,
+      "loss": 4.1539,
+      "step": 99
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 4.1399,
+      "step": 100
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001579281172342679,
+      "loss": 4.0179,
+      "step": 101
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 4.2023,
+      "step": 102
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00015620833778521307,
+      "loss": 4.017,
+      "step": 103
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015533915492433443,
+      "loss": 4.0196,
+      "step": 104
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015446390350150273,
+      "loss": 4.0342,
+      "step": 105
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 4.2113,
+      "step": 106
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015269557954966778,
+      "loss": 3.9744,
+      "step": 107
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015180270093731303,
+      "loss": 3.9296,
+      "step": 108
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015090414157503714,
+      "loss": 4.1932,
+      "step": 109
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.9307,
+      "step": 110
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014909037536151409,
+      "loss": 4.1181,
+      "step": 111
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014817536741017152,
+      "loss": 4.0439,
+      "step": 112
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014725507648690543,
+      "loss": 4.0253,
+      "step": 113
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 4.0668,
+      "step": 114
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 3.9828,
+      "step": 115
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00014446351791849276,
+      "loss": 4.0319,
+      "step": 116
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00014352310993723277,
+      "loss": 3.9696,
+      "step": 117
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 3.9411,
+      "step": 118
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00014162807922604012,
+      "loss": 4.0313,
+      "step": 119
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 3.9115,
+      "step": 120
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00013971478906347806,
+      "loss": 3.941,
+      "step": 121
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 3.975,
+      "step": 122
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00013778407868184672,
+      "loss": 3.7062,
+      "step": 123
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00013681245526846783,
+      "loss": 3.8805,
+      "step": 124
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00013583679495453,
+      "loss": 3.7612,
+      "step": 125
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 3.7326,
+      "step": 126
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013387379202452917,
+      "loss": 3.8042,
+      "step": 127
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013288666467385833,
+      "loss": 3.9848,
+      "step": 128
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00013189593092980702,
+      "loss": 4.011,
+      "step": 129
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.8322,
+      "step": 130
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00012990407922560868,
+      "loss": 3.7704,
+      "step": 131
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012890317969444716,
+      "loss": 3.8909,
+      "step": 132
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012789911060392294,
+      "loss": 3.8207,
+      "step": 133
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 3.8095,
+      "step": 134
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 3.8504,
+      "step": 135
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001248689887164855,
+      "loss": 3.6548,
+      "step": 136
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001238533457578581,
+      "loss": 3.7723,
+      "step": 137
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 3.6582,
+      "step": 138
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00012181432413965428,
+      "loss": 3.6674,
+      "step": 139
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00012079116908177593,
+      "loss": 3.9033,
+      "step": 140
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011976573403791262,
+      "loss": 3.7011,
+      "step": 141
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 3.8179,
+      "step": 142
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011770847403195834,
+      "loss": 3.6867,
+      "step": 143
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011667687467161024,
+      "loss": 3.6831,
+      "step": 144
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 3.8595,
+      "step": 145
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 3.721,
+      "step": 146
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011357155724343045,
+      "loss": 3.712,
+      "step": 147
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011253332335643043,
+      "loss": 3.6603,
+      "step": 148
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011149371504928668,
+      "loss": 3.6563,
+      "step": 149
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.5381,
+      "step": 150
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010941083133185146,
+      "loss": 3.7151,
+      "step": 151
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010836778433323158,
+      "loss": 3.7003,
+      "step": 152
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010732381971276318,
+      "loss": 3.8455,
+      "step": 153
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 3.5937,
+      "step": 154
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001052335956242944,
+      "loss": 3.5345,
+      "step": 155
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010418756537291996,
+      "loss": 3.527,
+      "step": 156
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010314107590781284,
+      "loss": 3.5617,
+      "step": 157
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 3.5834,
+      "step": 158
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010104717841162458,
+      "loss": 3.6394,
+      "step": 159
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001,
+      "loss": 3.4265,
+      "step": 160
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.895282158837545e-05,
+      "loss": 3.4816,
+      "step": 161
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 3.5481,
+      "step": 162
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.685892409218717e-05,
+      "loss": 3.6996,
+      "step": 163
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.581243462708006e-05,
+      "loss": 3.6275,
+      "step": 164
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.476640437570562e-05,
+      "loss": 3.5595,
+      "step": 165
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 3.4173,
+      "step": 166
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.267618028723686e-05,
+      "loss": 3.6742,
+      "step": 167
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.163221566676847e-05,
+      "loss": 3.5923,
+      "step": 168
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.058916866814858e-05,
+      "loss": 3.5414,
+      "step": 169
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.7635,
+      "step": 170
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.850628495071336e-05,
+      "loss": 3.3945,
+      "step": 171
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.746667664356956e-05,
+      "loss": 3.5575,
+      "step": 172
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.642844275656957e-05,
+      "loss": 3.4334,
+      "step": 173
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 3.5686,
+      "step": 174
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.7207,
+      "step": 175
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.332312532838978e-05,
+      "loss": 3.4545,
+      "step": 176
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.229152596804168e-05,
+      "loss": 3.4879,
+      "step": 177
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 3.6279,
+      "step": 178
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.023426596208739e-05,
+      "loss": 3.4412,
+      "step": 179
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.920883091822408e-05,
+      "loss": 3.5066,
+      "step": 180
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.818567586034577e-05,
+      "loss": 3.3587,
+      "step": 181
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 3.5664,
+      "step": 182
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.614665424214193e-05,
+      "loss": 3.4065,
+      "step": 183
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.513101128351454e-05,
+      "loss": 3.6623,
+      "step": 184
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 3.3463,
+      "step": 185
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 3.5487,
+      "step": 186
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.210088939607708e-05,
+      "loss": 3.3901,
+      "step": 187
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.109682030555283e-05,
+      "loss": 3.2565,
+      "step": 188
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.009592077439134e-05,
+      "loss": 3.4692,
+      "step": 189
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.4258,
+      "step": 190
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.8104069070193e-05,
+      "loss": 3.4803,
+      "step": 191
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.711333532614168e-05,
+      "loss": 3.5306,
+      "step": 192
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.612620797547087e-05,
+      "loss": 3.4718,
+      "step": 193
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 3.4513,
+      "step": 194
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.416320504546997e-05,
+      "loss": 3.6049,
+      "step": 195
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.318754473153221e-05,
+      "loss": 3.4402,
+      "step": 196
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.22159213181533e-05,
+      "loss": 3.4833,
+      "step": 197
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 3.493,
+      "step": 198
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.0285210936521955e-05,
+      "loss": 3.3789,
+      "step": 199
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.9326335692419995e-05,
+      "loss": 3.386,
+      "step": 200
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.83719207739599e-05,
+      "loss": 3.5344,
+      "step": 201
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.4203,
+      "step": 202
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.647689006276726e-05,
+      "loss": 3.5331,
+      "step": 203
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.553648208150728e-05,
+      "loss": 3.5052,
+      "step": 204
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 3.631,
+      "step": 205
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 3.4552,
+      "step": 206
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.274492351309461e-05,
+      "loss": 3.4078,
+      "step": 207
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.182463258982846e-05,
+      "loss": 3.4163,
+      "step": 208
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.090962463848592e-05,
+      "loss": 3.4208,
+      "step": 209
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.5513,
+      "step": 210
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.909585842496287e-05,
+      "loss": 3.4736,
+      "step": 211
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.8197299062686995e-05,
+      "loss": 3.4162,
+      "step": 212
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.7304420450332244e-05,
+      "loss": 3.4161,
+      "step": 213
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 3.5424,
+      "step": 214
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.5536096498497295e-05,
+      "loss": 3.4375,
+      "step": 215
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.46608450756656e-05,
+      "loss": 3.4181,
+      "step": 216
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.379166221478697e-05,
+      "loss": 3.4234,
+      "step": 217
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 3.2769,
+      "step": 218
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.207188276573214e-05,
+      "loss": 3.5804,
+      "step": 219
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.4969,
+      "step": 220
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.037751250343841e-05,
+      "loss": 3.4878,
+      "step": 221
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.954008851376252e-05,
+      "loss": 3.4461,
+      "step": 222
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8709294634702376e-05,
+      "loss": 3.4997,
+      "step": 223
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.788522197216897e-05,
+      "loss": 3.2672,
+      "step": 224
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.7067960895016275e-05,
+      "loss": 3.4284,
+      "step": 225
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 3.3721,
+      "step": 226
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.545423122760493e-05,
+      "loss": 3.3755,
+      "step": 227
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.465793960098945e-05,
+      "loss": 3.412,
+      "step": 228
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.386881346763483e-05,
+      "loss": 3.3902,
+      "step": 229
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.3975,
+      "step": 230
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.231240303173394e-05,
+      "loss": 3.3772,
+      "step": 231
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.154528940713113e-05,
+      "loss": 3.1924,
+      "step": 232
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.078568261295933e-05,
+      "loss": 3.439,
+      "step": 233
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0033665948663448e-05,
+      "loss": 3.2018,
+      "step": 234
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.4706,
+      "step": 235
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8552732036719687e-05,
+      "loss": 3.4761,
+      "step": 236
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7823977190163786e-05,
+      "loss": 3.4259,
+      "step": 237
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.4053,
+      "step": 238
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.639029128802657e-05,
+      "loss": 3.2636,
+      "step": 239
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 3.3724,
+      "step": 240
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4988893036954043e-05,
+      "loss": 3.3544,
+      "step": 241
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4300494434824373e-05,
+      "loss": 3.2656,
+      "step": 242
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.362039713653581e-05,
+      "loss": 3.4023,
+      "step": 243
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2948675722421086e-05,
+      "loss": 3.2969,
+      "step": 244
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2285403854302912e-05,
+      "loss": 3.4511,
+      "step": 245
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.163065426741603e-05,
+      "loss": 3.4428,
+      "step": 246
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.098449876243096e-05,
+      "loss": 3.3647,
+      "step": 247
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0347008197580374e-05,
+      "loss": 3.2604,
+      "step": 248
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9718252480888566e-05,
+      "loss": 3.3492,
+      "step": 249
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.3132,
+      "step": 250
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.848722042714457e-05,
+      "loss": 3.1101,
+      "step": 251
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.78850790866296e-05,
+      "loss": 3.4295,
+      "step": 252
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7291942572543807e-05,
+      "loss": 3.27,
+      "step": 253
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6707875928990058e-05,
+      "loss": 3.307,
+      "step": 254
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6132943205457606e-05,
+      "loss": 3.2597,
+      "step": 255
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5567207449798515e-05,
+      "loss": 3.2053,
+      "step": 256
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5010730701313625e-05,
+      "loss": 3.2863,
+      "step": 257
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4463573983949341e-05,
+      "loss": 3.1945,
+      "step": 258
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3925797299605647e-05,
+      "loss": 3.3066,
+      "step": 259
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 3.3855,
+      "step": 260
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2878618887981064e-05,
+      "loss": 3.1933,
+      "step": 261
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2369331995613665e-05,
+      "loss": 3.4084,
+      "step": 262
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1869654793500784e-05,
+      "loss": 3.315,
+      "step": 263
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1379642076878527e-05,
+      "loss": 3.3994,
+      "step": 264
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.2624,
+      "step": 265
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.042882397605871e-05,
+      "loss": 3.2287,
+      "step": 266
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.968122859780648e-06,
+      "loss": 3.245,
+      "step": 267
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.517294753398064e-06,
+      "loss": 3.2106,
+      "step": 268
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.076389095293148e-06,
+      "loss": 3.2575,
+      "step": 269
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.3462,
+      "step": 270
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.224537431601886e-06,
+      "loss": 3.5159,
+      "step": 271
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.81368484114996e-06,
+      "loss": 3.3177,
+      "step": 272
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.412941519000527e-06,
+      "loss": 3.1598,
+      "step": 273
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.4421,
+      "step": 274
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.6419573502798374e-06,
+      "loss": 3.2242,
+      "step": 275
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.2718010508108545e-06,
+      "loss": 3.3379,
+      "step": 276
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.911923104577455e-06,
+      "loss": 3.3409,
+      "step": 277
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.562362976251901e-06,
+      "loss": 3.2563,
+      "step": 278
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.223158999041444e-06,
+      "loss": 3.322,
+      "step": 279
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 3.365,
+      "step": 280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.575967148372317e-06,
+      "loss": 3.3066,
+      "step": 281
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.268050246793276e-06,
+      "loss": 3.2917,
+      "step": 282
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.970631432305694e-06,
+      "loss": 3.2967,
+      "step": 283
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.68374332023419e-06,
+      "loss": 3.2636,
+      "step": 284
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 3.2059,
+      "step": 285
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1416838871368924e-06,
+      "loss": 3.2664,
+      "step": 286
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8865720090364034e-06,
+      "loss": 3.4219,
+      "step": 287
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6421097126839712e-06,
+      "loss": 3.3064,
+      "step": 288
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.4083238061252567e-06,
+      "loss": 3.1889,
+      "step": 289
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.4085,
+      "step": 290
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9728825378278246e-06,
+      "loss": 3.3206,
+      "step": 291
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.771274927131139e-06,
+      "loss": 3.4628,
+      "step": 292
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.580439203075812e-06,
+      "loss": 3.1341,
+      "step": 293
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.400396292949513e-06,
+      "loss": 3.3387,
+      "step": 294
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 3.2056,
+      "step": 295
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0727667037011668e-06,
+      "loss": 3.1854,
+      "step": 296
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.252159528556403e-07,
+      "loss": 3.2785,
+      "step": 297
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.885298685522235e-07,
+      "loss": 3.4136,
+      "step": 298
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.627234399603555e-07,
+      "loss": 3.2466,
+      "step": 299
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 3.5445,
+      "step": 300
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.438035396920004e-07,
+      "loss": 3.4556,
+      "step": 301
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.50714075049563e-07,
+      "loss": 3.0958,
+      "step": 302
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.685522775541904e-07,
+      "loss": 3.3386,
+      "step": 303
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.973271571728441e-07,
+      "loss": 3.3139,
+      "step": 304
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3704652454261668e-07,
+      "loss": 3.2791,
+      "step": 305
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.771699011416168e-08,
+      "loss": 3.2188,
+      "step": 306
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.934396342684e-08,
+      "loss": 3.3562,
+      "step": 307
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.193165251545004e-08,
+      "loss": 3.3555,
+      "step": 308
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.483063448785686e-09,
+      "loss": 3.609,
+      "step": 309
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 3.4165,
+      "step": 310
+    },
+    {
+      "epoch": 1.0,
+      "step": 310,
+      "total_flos": 53958111068160.0,
+      "train_loss": 4.296783600314971,
+      "train_runtime": 4111.9826,
+      "train_samples_per_second": 7.229,
+      "train_steps_per_second": 0.075
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 53958111068160.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}