Upload 12 files

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+library_name: peft
+base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
+---
+
+# 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

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a58c34870ae5ef773b51d8fb7f47bdd762b0a37616f5a6ae8708960bf30933b
+size 167832240

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00eee73183c9265f497dba099945739d1bbf49be42d9ca7bb3c107231324cf61
+size 84570708

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec995be8da3d39228d72b8931b8e5157f0339a5f6c8af5793ddbc486f90572ed
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa41211d323a3363275f879a622aa34ba4d6b9ecee7b316b032578d61e144814
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "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
+}

trainer_state.json

@@ -0,0 +1,1421 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09142857142857143,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.563270330429077,
+      "learning_rate": 4e-05,
+      "loss": 2.4127,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.333299160003662,
+      "learning_rate": 8e-05,
+      "loss": 2.3102,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.8613317012786865,
+      "learning_rate": 0.00012,
+      "loss": 2.1983,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.620126485824585,
+      "learning_rate": 0.00016,
+      "loss": 2.0917,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.0352119207382202,
+      "learning_rate": 0.0002,
+      "loss": 1.9613,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.8601917624473572,
+      "learning_rate": 0.00019979899497487438,
+      "loss": 1.6927,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.273868203163147,
+      "learning_rate": 0.00019959798994974876,
+      "loss": 1.6828,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.0873847007751465,
+      "learning_rate": 0.00019939698492462313,
+      "loss": 1.5088,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.5800795555114746,
+      "learning_rate": 0.0001991959798994975,
+      "loss": 1.3702,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.693160355091095,
+      "learning_rate": 0.00019899497487437187,
+      "loss": 1.3718,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.49409618973731995,
+      "learning_rate": 0.00019879396984924622,
+      "loss": 1.3583,
+      "step": 11
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.47029319405555725,
+      "learning_rate": 0.00019859296482412062,
+      "loss": 1.2791,
+      "step": 12
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.43618088960647583,
+      "learning_rate": 0.000198391959798995,
+      "loss": 1.3161,
+      "step": 13
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3907912075519562,
+      "learning_rate": 0.00019819095477386937,
+      "loss": 1.2954,
+      "step": 14
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.6292415857315063,
+      "learning_rate": 0.0001979899497487437,
+      "loss": 1.3397,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.37423521280288696,
+      "learning_rate": 0.0001977889447236181,
+      "loss": 1.3983,
+      "step": 16
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3845643699169159,
+      "learning_rate": 0.00019758793969849249,
+      "loss": 1.3349,
+      "step": 17
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3657298982143402,
+      "learning_rate": 0.00019738693467336683,
+      "loss": 1.2767,
+      "step": 18
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3727971315383911,
+      "learning_rate": 0.0001971859296482412,
+      "loss": 1.3672,
+      "step": 19
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.35123032331466675,
+      "learning_rate": 0.0001969849246231156,
+      "loss": 1.3692,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.4003850221633911,
+      "learning_rate": 0.00019678391959798995,
+      "loss": 1.3412,
+      "step": 21
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3638221323490143,
+      "learning_rate": 0.00019658291457286432,
+      "loss": 1.2813,
+      "step": 22
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.391216903924942,
+      "learning_rate": 0.0001963819095477387,
+      "loss": 1.2853,
+      "step": 23
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.4370620846748352,
+      "learning_rate": 0.0001961809045226131,
+      "loss": 1.2524,
+      "step": 24
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3566085696220398,
+      "learning_rate": 0.00019597989949748744,
+      "loss": 1.3192,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.35438084602355957,
+      "learning_rate": 0.00019577889447236181,
+      "loss": 1.2858,
+      "step": 26
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3968108296394348,
+      "learning_rate": 0.0001955778894472362,
+      "loss": 1.3112,
+      "step": 27
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.36512017250061035,
+      "learning_rate": 0.00019537688442211056,
+      "loss": 1.278,
+      "step": 28
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3982504606246948,
+      "learning_rate": 0.00019517587939698493,
+      "loss": 1.2392,
+      "step": 29
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.38377949595451355,
+      "learning_rate": 0.0001949748743718593,
+      "loss": 1.2843,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3582867980003357,
+      "learning_rate": 0.00019477386934673368,
+      "loss": 1.3008,
+      "step": 31
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3572194576263428,
+      "learning_rate": 0.00019457286432160805,
+      "loss": 1.294,
+      "step": 32
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.35502907633781433,
+      "learning_rate": 0.00019437185929648243,
+      "loss": 1.3877,
+      "step": 33
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3649040460586548,
+      "learning_rate": 0.0001941708542713568,
+      "loss": 1.2966,
+      "step": 34
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3649256229400635,
+      "learning_rate": 0.00019396984924623117,
+      "loss": 1.2354,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.36085084080696106,
+      "learning_rate": 0.00019376884422110552,
+      "loss": 1.2409,
+      "step": 36
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.35929059982299805,
+      "learning_rate": 0.00019356783919597992,
+      "loss": 1.243,
+      "step": 37
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3897881805896759,
+      "learning_rate": 0.0001933668341708543,
+      "loss": 1.3945,
+      "step": 38
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.35484543442726135,
+      "learning_rate": 0.00019316582914572864,
+      "loss": 1.3433,
+      "step": 39
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.35691192746162415,
+      "learning_rate": 0.000192964824120603,
+      "loss": 1.3243,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3804129958152771,
+      "learning_rate": 0.0001927638190954774,
+      "loss": 1.2509,
+      "step": 41
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3623339831829071,
+      "learning_rate": 0.00019256281407035178,
+      "loss": 1.1799,
+      "step": 42
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3411855697631836,
+      "learning_rate": 0.00019236180904522613,
+      "loss": 1.2372,
+      "step": 43
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.36590930819511414,
+      "learning_rate": 0.0001921608040201005,
+      "loss": 1.2585,
+      "step": 44
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.30974116921424866,
+      "learning_rate": 0.0001919597989949749,
+      "loss": 1.2974,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.32794803380966187,
+      "learning_rate": 0.00019175879396984925,
+      "loss": 1.2696,
+      "step": 46
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.33263906836509705,
+      "learning_rate": 0.00019155778894472362,
+      "loss": 1.3209,
+      "step": 47
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.31748828291893005,
+      "learning_rate": 0.000191356783919598,
+      "loss": 1.278,
+      "step": 48
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.34738561511039734,
+      "learning_rate": 0.0001911557788944724,
+      "loss": 1.2105,
+      "step": 49
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3313944339752197,
+      "learning_rate": 0.00019095477386934674,
+      "loss": 1.2527,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.33137476444244385,
+      "learning_rate": 0.0001907537688442211,
+      "loss": 1.2984,
+      "step": 51
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.31752490997314453,
+      "learning_rate": 0.00019055276381909548,
+      "loss": 1.307,
+      "step": 52
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3111082911491394,
+      "learning_rate": 0.00019035175879396986,
+      "loss": 1.2769,
+      "step": 53
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.31065696477890015,
+      "learning_rate": 0.00019015075376884423,
+      "loss": 1.3082,
+      "step": 54
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3382773697376251,
+      "learning_rate": 0.0001899497487437186,
+      "loss": 1.2744,
+      "step": 55
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.34320947527885437,
+      "learning_rate": 0.00018974874371859298,
+      "loss": 1.3013,
+      "step": 56
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.33131280541419983,
+      "learning_rate": 0.00018954773869346732,
+      "loss": 1.4066,
+      "step": 57
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3357389569282532,
+      "learning_rate": 0.00018934673366834172,
+      "loss": 1.2841,
+      "step": 58
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3200838267803192,
+      "learning_rate": 0.0001891457286432161,
+      "loss": 1.2654,
+      "step": 59
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3336584270000458,
+      "learning_rate": 0.00018894472361809047,
+      "loss": 1.1716,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3128441274166107,
+      "learning_rate": 0.00018874371859296481,
+      "loss": 1.3009,
+      "step": 61
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.30249112844467163,
+      "learning_rate": 0.00018854271356783921,
+      "loss": 1.2311,
+      "step": 62
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3263241946697235,
+      "learning_rate": 0.0001883417085427136,
+      "loss": 1.2344,
+      "step": 63
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.32348358631134033,
+      "learning_rate": 0.00018814070351758793,
+      "loss": 1.3023,
+      "step": 64
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.6508419513702393,
+      "learning_rate": 0.0001879396984924623,
+      "loss": 1.2028,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.34560996294021606,
+      "learning_rate": 0.0001877386934673367,
+      "loss": 1.389,
+      "step": 66
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.36555996537208557,
+      "learning_rate": 0.00018753768844221108,
+      "loss": 1.3653,
+      "step": 67
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3195466697216034,
+      "learning_rate": 0.00018733668341708543,
+      "loss": 1.2412,
+      "step": 68
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.30555933713912964,
+      "learning_rate": 0.0001871356783919598,
+      "loss": 1.2357,
+      "step": 69
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.30776411294937134,
+      "learning_rate": 0.0001869346733668342,
+      "loss": 1.3112,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.31933915615081787,
+      "learning_rate": 0.00018673366834170854,
+      "loss": 1.1951,
+      "step": 71
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3241545259952545,
+      "learning_rate": 0.00018653266331658292,
+      "loss": 1.2717,
+      "step": 72
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3117482364177704,
+      "learning_rate": 0.0001863316582914573,
+      "loss": 1.3031,
+      "step": 73
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.33056551218032837,
+      "learning_rate": 0.0001861306532663317,
+      "loss": 1.2098,
+      "step": 74
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.32441195845603943,
+      "learning_rate": 0.00018592964824120604,
+      "loss": 1.2135,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.34216779470443726,
+      "learning_rate": 0.0001857286432160804,
+      "loss": 1.2531,
+      "step": 76
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.32885247468948364,
+      "learning_rate": 0.00018552763819095478,
+      "loss": 1.3054,
+      "step": 77
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.34541794657707214,
+      "learning_rate": 0.00018532663316582915,
+      "loss": 1.3207,
+      "step": 78
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.30329057574272156,
+      "learning_rate": 0.00018512562814070353,
+      "loss": 1.2652,
+      "step": 79
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.31469491124153137,
+      "learning_rate": 0.0001849246231155779,
+      "loss": 1.1961,
+      "step": 80
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3181230127811432,
+      "learning_rate": 0.00018472361809045227,
+      "loss": 1.3111,
+      "step": 81
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3181725740432739,
+      "learning_rate": 0.00018452261306532662,
+      "loss": 1.3353,
+      "step": 82
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3154084384441376,
+      "learning_rate": 0.00018432160804020102,
+      "loss": 1.2418,
+      "step": 83
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.35061103105545044,
+      "learning_rate": 0.0001841206030150754,
+      "loss": 1.2332,
+      "step": 84
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3259966969490051,
+      "learning_rate": 0.00018391959798994977,
+      "loss": 1.3633,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.31192857027053833,
+      "learning_rate": 0.0001837185929648241,
+      "loss": 1.1886,
+      "step": 86
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.32024237513542175,
+      "learning_rate": 0.0001835175879396985,
+      "loss": 1.2141,
+      "step": 87
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.302498459815979,
+      "learning_rate": 0.00018331658291457288,
+      "loss": 1.237,
+      "step": 88
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3569789230823517,
+      "learning_rate": 0.00018311557788944723,
+      "loss": 1.3015,
+      "step": 89
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3121156692504883,
+      "learning_rate": 0.0001829145728643216,
+      "loss": 1.281,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.31279826164245605,
+      "learning_rate": 0.000182713567839196,
+      "loss": 1.2924,
+      "step": 91
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3210877478122711,
+      "learning_rate": 0.00018251256281407038,
+      "loss": 1.3082,
+      "step": 92
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.331406831741333,
+      "learning_rate": 0.00018231155778894472,
+      "loss": 1.2434,
+      "step": 93
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3135213255882263,
+      "learning_rate": 0.0001821105527638191,
+      "loss": 1.2188,
+      "step": 94
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.31146401166915894,
+      "learning_rate": 0.0001819095477386935,
+      "loss": 1.2484,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.32071712613105774,
+      "learning_rate": 0.00018170854271356784,
+      "loss": 1.1927,
+      "step": 96
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3343571722507477,
+      "learning_rate": 0.00018150753768844221,
+      "loss": 1.3443,
+      "step": 97
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3510550558567047,
+      "learning_rate": 0.0001813065326633166,
+      "loss": 1.2832,
+      "step": 98
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.33436939120292664,
+      "learning_rate": 0.00018110552763819096,
+      "loss": 1.252,
+      "step": 99
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3175451159477234,
+      "learning_rate": 0.00018090452261306533,
+      "loss": 1.251,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.32603979110717773,
+      "learning_rate": 0.0001807035175879397,
+      "loss": 1.228,
+      "step": 101
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3073003590106964,
+      "learning_rate": 0.00018050251256281408,
+      "loss": 1.2659,
+      "step": 102
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3285619616508484,
+      "learning_rate": 0.00018030150753768845,
+      "loss": 1.2826,
+      "step": 103
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3038572072982788,
+      "learning_rate": 0.00018010050251256282,
+      "loss": 1.217,
+      "step": 104
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.35778746008872986,
+      "learning_rate": 0.0001798994974874372,
+      "loss": 1.2901,
+      "step": 105
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.2900612950325012,
+      "learning_rate": 0.00017969849246231157,
+      "loss": 1.2651,
+      "step": 106
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.32928743958473206,
+      "learning_rate": 0.00017949748743718592,
+      "loss": 1.3143,
+      "step": 107
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.32471874356269836,
+      "learning_rate": 0.00017929648241206032,
+      "loss": 1.1834,
+      "step": 108
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.30989256501197815,
+      "learning_rate": 0.0001790954773869347,
+      "loss": 1.2216,
+      "step": 109
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3371771275997162,
+      "learning_rate": 0.00017889447236180906,
+      "loss": 1.197,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.31041428446769714,
+      "learning_rate": 0.0001786934673366834,
+      "loss": 1.27,
+      "step": 111
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3152185082435608,
+      "learning_rate": 0.0001784924623115578,
+      "loss": 1.2436,
+      "step": 112
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3227459490299225,
+      "learning_rate": 0.00017829145728643218,
+      "loss": 1.2401,
+      "step": 113
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3246959149837494,
+      "learning_rate": 0.00017809045226130653,
+      "loss": 1.2703,
+      "step": 114
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.38032859563827515,
+      "learning_rate": 0.0001778894472361809,
+      "loss": 1.3266,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.33325478434562683,
+      "learning_rate": 0.0001776884422110553,
+      "loss": 1.2954,
+      "step": 116
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3178690969944,
+      "learning_rate": 0.00017748743718592967,
+      "loss": 1.1793,
+      "step": 117
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.31393784284591675,
+      "learning_rate": 0.00017728643216080402,
+      "loss": 1.277,
+      "step": 118
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3150279223918915,
+      "learning_rate": 0.0001770854271356784,
+      "loss": 1.293,
+      "step": 119
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.32476913928985596,
+      "learning_rate": 0.0001768844221105528,
+      "loss": 1.2569,
+      "step": 120
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.36075925827026367,
+      "learning_rate": 0.00017668341708542714,
+      "loss": 1.205,
+      "step": 121
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.33134496212005615,
+      "learning_rate": 0.0001764824120603015,
+      "loss": 1.2299,
+      "step": 122
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.30507662892341614,
+      "learning_rate": 0.00017628140703517588,
+      "loss": 1.2883,
+      "step": 123
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.34049952030181885,
+      "learning_rate": 0.00017608040201005026,
+      "loss": 1.214,
+      "step": 124
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3405919373035431,
+      "learning_rate": 0.00017587939698492463,
+      "loss": 1.2738,
+      "step": 125
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3306083679199219,
+      "learning_rate": 0.000175678391959799,
+      "loss": 1.2415,
+      "step": 126
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.33770737051963806,
+      "learning_rate": 0.00017547738693467338,
+      "loss": 1.3233,
+      "step": 127
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3261878788471222,
+      "learning_rate": 0.00017527638190954775,
+      "loss": 1.2695,
+      "step": 128
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3433193266391754,
+      "learning_rate": 0.00017507537688442212,
+      "loss": 1.2052,
+      "step": 129
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3111405670642853,
+      "learning_rate": 0.0001748743718592965,
+      "loss": 1.2798,
+      "step": 130
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3630310297012329,
+      "learning_rate": 0.00017467336683417087,
+      "loss": 1.2567,
+      "step": 131
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.31963038444519043,
+      "learning_rate": 0.00017447236180904521,
+      "loss": 1.2455,
+      "step": 132
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.299695760011673,
+      "learning_rate": 0.00017427135678391961,
+      "loss": 1.207,
+      "step": 133
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3167514503002167,
+      "learning_rate": 0.000174070351758794,
+      "loss": 1.2378,
+      "step": 134
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.31375688314437866,
+      "learning_rate": 0.00017386934673366836,
+      "loss": 1.2658,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.34311383962631226,
+      "learning_rate": 0.0001736683417085427,
+      "loss": 1.2004,
+      "step": 136
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.31706517934799194,
+      "learning_rate": 0.0001734673366834171,
+      "loss": 1.1879,
+      "step": 137
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.31296172738075256,
+      "learning_rate": 0.00017326633165829148,
+      "loss": 1.1866,
+      "step": 138
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3254072368144989,
+      "learning_rate": 0.00017306532663316582,
+      "loss": 1.1952,
+      "step": 139
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3165453374385834,
+      "learning_rate": 0.0001728643216080402,
+      "loss": 1.3459,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.35455992817878723,
+      "learning_rate": 0.0001726633165829146,
+      "loss": 1.2494,
+      "step": 141
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.3116908073425293,
+      "learning_rate": 0.00017246231155778897,
+      "loss": 1.2225,
+      "step": 142
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3141638934612274,
+      "learning_rate": 0.00017226130653266332,
+      "loss": 1.3385,
+      "step": 143
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3096507787704468,
+      "learning_rate": 0.0001720603015075377,
+      "loss": 1.3257,
+      "step": 144
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3160630464553833,
+      "learning_rate": 0.00017185929648241206,
+      "loss": 1.2683,
+      "step": 145
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3342824876308441,
+      "learning_rate": 0.00017165829145728644,
+      "loss": 1.2551,
+      "step": 146
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3086145222187042,
+      "learning_rate": 0.0001714572864321608,
+      "loss": 1.2456,
+      "step": 147
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3001709282398224,
+      "learning_rate": 0.00017125628140703518,
+      "loss": 1.2287,
+      "step": 148
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3277103304862976,
+      "learning_rate": 0.00017105527638190955,
+      "loss": 1.3302,
+      "step": 149
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.33616161346435547,
+      "learning_rate": 0.00017085427135678393,
+      "loss": 1.2604,
+      "step": 150
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3231915533542633,
+      "learning_rate": 0.0001706532663316583,
+      "loss": 1.2367,
+      "step": 151
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3305569291114807,
+      "learning_rate": 0.00017045226130653267,
+      "loss": 1.2387,
+      "step": 152
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.35031118988990784,
+      "learning_rate": 0.00017025125628140705,
+      "loss": 1.2464,
+      "step": 153
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3142334222793579,
+      "learning_rate": 0.00017005025125628142,
+      "loss": 1.3614,
+      "step": 154
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.31159430742263794,
+      "learning_rate": 0.0001698492462311558,
+      "loss": 1.2556,
+      "step": 155
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3273050785064697,
+      "learning_rate": 0.00016964824120603016,
+      "loss": 1.3519,
+      "step": 156
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3299296796321869,
+      "learning_rate": 0.0001694472361809045,
+      "loss": 1.1763,
+      "step": 157
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.33138513565063477,
+      "learning_rate": 0.0001692462311557789,
+      "loss": 1.17,
+      "step": 158
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.30424776673316956,
+      "learning_rate": 0.00016904522613065328,
+      "loss": 1.123,
+      "step": 159
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3452983498573303,
+      "learning_rate": 0.00016884422110552766,
+      "loss": 1.2999,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.33614206314086914,
+      "learning_rate": 0.000168643216080402,
+      "loss": 1.262,
+      "step": 161
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.32416558265686035,
+      "learning_rate": 0.0001684422110552764,
+      "loss": 1.2514,
+      "step": 162
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.29827457666397095,
+      "learning_rate": 0.00016824120603015078,
+      "loss": 1.2461,
+      "step": 163
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.32572871446609497,
+      "learning_rate": 0.00016804020100502512,
+      "loss": 1.2393,
+      "step": 164
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.32171282172203064,
+      "learning_rate": 0.0001678391959798995,
+      "loss": 1.3045,
+      "step": 165
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.34592801332473755,
+      "learning_rate": 0.0001676381909547739,
+      "loss": 1.2669,
+      "step": 166
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.33795440196990967,
+      "learning_rate": 0.00016743718592964827,
+      "loss": 1.1404,
+      "step": 167
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.32598641514778137,
+      "learning_rate": 0.0001672361809045226,
+      "loss": 1.2495,
+      "step": 168
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.31816181540489197,
+      "learning_rate": 0.00016703517587939699,
+      "loss": 1.3003,
+      "step": 169
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3340943157672882,
+      "learning_rate": 0.00016683417085427136,
+      "loss": 1.2615,
+      "step": 170
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3242477476596832,
+      "learning_rate": 0.00016663316582914573,
+      "loss": 1.2527,
+      "step": 171
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.308652400970459,
+      "learning_rate": 0.0001664321608040201,
+      "loss": 1.3241,
+      "step": 172
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.31818273663520813,
+      "learning_rate": 0.00016623115577889448,
+      "loss": 1.3712,
+      "step": 173
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.32885751128196716,
+      "learning_rate": 0.00016603015075376885,
+      "loss": 1.2583,
+      "step": 174
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.32561740279197693,
+      "learning_rate": 0.00016582914572864322,
+      "loss": 1.2458,
+      "step": 175
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3278496563434601,
+      "learning_rate": 0.0001656281407035176,
+      "loss": 1.2205,
+      "step": 176
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.32530438899993896,
+      "learning_rate": 0.00016542713567839197,
+      "loss": 1.2235,
+      "step": 177
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.31232836842536926,
+      "learning_rate": 0.00016522613065326634,
+      "loss": 1.199,
+      "step": 178
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3209743797779083,
+      "learning_rate": 0.00016502512562814072,
+      "loss": 1.2717,
+      "step": 179
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.329940527677536,
+      "learning_rate": 0.0001648241206030151,
+      "loss": 1.2425,
+      "step": 180
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3144824802875519,
+      "learning_rate": 0.00016462311557788946,
+      "loss": 1.2444,
+      "step": 181
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3218553066253662,
+      "learning_rate": 0.0001644221105527638,
+      "loss": 1.2815,
+      "step": 182
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.33460506796836853,
+      "learning_rate": 0.0001642211055276382,
+      "loss": 1.3774,
+      "step": 183
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3300727605819702,
+      "learning_rate": 0.00016402010050251258,
+      "loss": 1.3436,
+      "step": 184
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3530360460281372,
+      "learning_rate": 0.00016381909547738695,
+      "loss": 1.2605,
+      "step": 185
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3326485753059387,
+      "learning_rate": 0.0001636180904522613,
+      "loss": 1.2202,
+      "step": 186
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.31355732679367065,
+      "learning_rate": 0.0001634170854271357,
+      "loss": 1.2798,
+      "step": 187
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3162304759025574,
+      "learning_rate": 0.00016321608040201007,
+      "loss": 1.2118,
+      "step": 188
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.32264095544815063,
+      "learning_rate": 0.00016301507537688442,
+      "loss": 1.2775,
+      "step": 189
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.30425918102264404,
+      "learning_rate": 0.0001628140703517588,
+      "loss": 1.1438,
+      "step": 190
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.33907556533813477,
+      "learning_rate": 0.00016261306532663316,
+      "loss": 1.4077,
+      "step": 191
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.32334232330322266,
+      "learning_rate": 0.00016241206030150756,
+      "loss": 1.2673,
+      "step": 192
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.32999834418296814,
+      "learning_rate": 0.0001622110552763819,
+      "loss": 1.257,
+      "step": 193
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3223746120929718,
+      "learning_rate": 0.00016201005025125628,
+      "loss": 1.2125,
+      "step": 194
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3236989378929138,
+      "learning_rate": 0.00016180904522613066,
+      "loss": 1.3645,
+      "step": 195
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3303336203098297,
+      "learning_rate": 0.00016160804020100503,
+      "loss": 1.2786,
+      "step": 196
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3135005831718445,
+      "learning_rate": 0.0001614070351758794,
+      "loss": 1.2775,
+      "step": 197
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3185466527938843,
+      "learning_rate": 0.00016120603015075378,
+      "loss": 1.2128,
+      "step": 198
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3355714976787567,
+      "learning_rate": 0.00016100502512562815,
+      "loss": 1.307,
+      "step": 199
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.339216023683548,
+      "learning_rate": 0.00016080402010050252,
+      "loss": 1.2845,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "total_flos": 9.299042116288512e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa4eeaf829b7025ebff9e7e2b092d9eeb78c49b155d2e019614d1e7fc608faf
+size 4856