Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/codellama-7b-bnb-4bit
+library_name: peft
+---
+
+# 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 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/codellama-7b-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "v_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:d9af439edfd7e1e155a550f3fcb18d7786a35b7ac6701f97e945ae0a09ec0d84
+size 159967880

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,89 @@
+{
+  "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
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "extra_special_tokens": {},
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 16384,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,523 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.1373787671327591,
+      "learning_rate": 9.928057553956835e-05,
+      "loss": 1.0964,
+      "step": 10
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.23093585669994354,
+      "learning_rate": 9.784172661870504e-05,
+      "loss": 0.864,
+      "step": 20
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.1213061660528183,
+      "learning_rate": 9.640287769784174e-05,
+      "loss": 0.5938,
+      "step": 30
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.0565805584192276,
+      "learning_rate": 9.496402877697842e-05,
+      "loss": 0.5041,
+      "step": 40
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.057311397045850754,
+      "learning_rate": 9.35251798561151e-05,
+      "loss": 0.443,
+      "step": 50
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.06346569955348969,
+      "learning_rate": 9.20863309352518e-05,
+      "loss": 0.533,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.04802313446998596,
+      "learning_rate": 9.06474820143885e-05,
+      "loss": 0.4617,
+      "step": 70
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.05171512812376022,
+      "learning_rate": 8.920863309352519e-05,
+      "loss": 0.4229,
+      "step": 80
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.06379946321249008,
+      "learning_rate": 8.776978417266187e-05,
+      "loss": 0.4794,
+      "step": 90
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.06747135519981384,
+      "learning_rate": 8.633093525179857e-05,
+      "loss": 0.4607,
+      "step": 100
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.05382410064339638,
+      "learning_rate": 8.489208633093527e-05,
+      "loss": 0.4922,
+      "step": 110
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.05737805739045143,
+      "learning_rate": 8.345323741007195e-05,
+      "loss": 0.5137,
+      "step": 120
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.05210845544934273,
+      "learning_rate": 8.201438848920863e-05,
+      "loss": 0.4611,
+      "step": 130
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.059042274951934814,
+      "learning_rate": 8.057553956834533e-05,
+      "loss": 0.457,
+      "step": 140
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.05036056786775589,
+      "learning_rate": 7.913669064748202e-05,
+      "loss": 0.4712,
+      "step": 150
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.06213638186454773,
+      "learning_rate": 7.769784172661872e-05,
+      "loss": 0.4253,
+      "step": 160
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.08077629655599594,
+      "learning_rate": 7.62589928057554e-05,
+      "loss": 0.4652,
+      "step": 170
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.067039355635643,
+      "learning_rate": 7.48201438848921e-05,
+      "loss": 0.4623,
+      "step": 180
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.06331554055213928,
+      "learning_rate": 7.338129496402878e-05,
+      "loss": 0.4991,
+      "step": 190
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.07635468244552612,
+      "learning_rate": 7.194244604316547e-05,
+      "loss": 0.4185,
+      "step": 200
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.07588763535022736,
+      "learning_rate": 7.050359712230215e-05,
+      "loss": 0.4232,
+      "step": 210
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.06745592504739761,
+      "learning_rate": 6.906474820143886e-05,
+      "loss": 0.4254,
+      "step": 220
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.07882258296012878,
+      "learning_rate": 6.762589928057555e-05,
+      "loss": 0.4437,
+      "step": 230
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.07268062978982925,
+      "learning_rate": 6.618705035971223e-05,
+      "loss": 0.4725,
+      "step": 240
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.07357478886842728,
+      "learning_rate": 6.474820143884892e-05,
+      "loss": 0.4185,
+      "step": 250
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.07707969099283218,
+      "learning_rate": 6.330935251798561e-05,
+      "loss": 0.4349,
+      "step": 260
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.07666852325201035,
+      "learning_rate": 6.187050359712231e-05,
+      "loss": 0.5036,
+      "step": 270
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.07082293182611465,
+      "learning_rate": 6.0431654676258996e-05,
+      "loss": 0.4336,
+      "step": 280
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.07426683604717255,
+      "learning_rate": 5.899280575539569e-05,
+      "loss": 0.431,
+      "step": 290
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.06738661974668503,
+      "learning_rate": 5.755395683453237e-05,
+      "loss": 0.416,
+      "step": 300
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 0.07940518110990524,
+      "learning_rate": 5.611510791366906e-05,
+      "loss": 0.4314,
+      "step": 310
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.08810248970985413,
+      "learning_rate": 5.467625899280576e-05,
+      "loss": 0.4893,
+      "step": 320
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.08641257137060165,
+      "learning_rate": 5.323741007194245e-05,
+      "loss": 0.3923,
+      "step": 330
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.09313848614692688,
+      "learning_rate": 5.179856115107914e-05,
+      "loss": 0.4295,
+      "step": 340
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.08842173963785172,
+      "learning_rate": 5.035971223021583e-05,
+      "loss": 0.4141,
+      "step": 350
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.08694295585155487,
+      "learning_rate": 4.892086330935252e-05,
+      "loss": 0.4253,
+      "step": 360
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 0.09336841106414795,
+      "learning_rate": 4.748201438848921e-05,
+      "loss": 0.4374,
+      "step": 370
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.08530748635530472,
+      "learning_rate": 4.60431654676259e-05,
+      "loss": 0.4324,
+      "step": 380
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.08860356360673904,
+      "learning_rate": 4.460431654676259e-05,
+      "loss": 0.421,
+      "step": 390
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.10588660836219788,
+      "learning_rate": 4.3165467625899284e-05,
+      "loss": 0.4553,
+      "step": 400
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 0.10128331184387207,
+      "learning_rate": 4.1726618705035975e-05,
+      "loss": 0.4084,
+      "step": 410
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1228618174791336,
+      "learning_rate": 4.0287769784172666e-05,
+      "loss": 0.4199,
+      "step": 420
+    },
+    {
+      "epoch": 3.0714285714285716,
+      "grad_norm": 0.10508912056684494,
+      "learning_rate": 3.884892086330936e-05,
+      "loss": 0.3835,
+      "step": 430
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.09007140249013901,
+      "learning_rate": 3.741007194244605e-05,
+      "loss": 0.4385,
+      "step": 440
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 0.09553549438714981,
+      "learning_rate": 3.597122302158273e-05,
+      "loss": 0.4194,
+      "step": 450
+    },
+    {
+      "epoch": 3.2857142857142856,
+      "grad_norm": 0.11486919969320297,
+      "learning_rate": 3.453237410071943e-05,
+      "loss": 0.4205,
+      "step": 460
+    },
+    {
+      "epoch": 3.357142857142857,
+      "grad_norm": 0.12448228150606155,
+      "learning_rate": 3.3093525179856116e-05,
+      "loss": 0.408,
+      "step": 470
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.10864632576704025,
+      "learning_rate": 3.165467625899281e-05,
+      "loss": 0.4175,
+      "step": 480
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.11113475263118744,
+      "learning_rate": 3.0215827338129498e-05,
+      "loss": 0.3946,
+      "step": 490
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.11032601445913315,
+      "learning_rate": 2.8776978417266186e-05,
+      "loss": 0.4134,
+      "step": 500
+    },
+    {
+      "epoch": 3.642857142857143,
+      "grad_norm": 0.11257655918598175,
+      "learning_rate": 2.733812949640288e-05,
+      "loss": 0.3905,
+      "step": 510
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.12174879759550095,
+      "learning_rate": 2.589928057553957e-05,
+      "loss": 0.4063,
+      "step": 520
+    },
+    {
+      "epoch": 3.7857142857142856,
+      "grad_norm": 0.12508544325828552,
+      "learning_rate": 2.446043165467626e-05,
+      "loss": 0.4375,
+      "step": 530
+    },
+    {
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.1218411847949028,
+      "learning_rate": 2.302158273381295e-05,
+      "loss": 0.3975,
+      "step": 540
+    },
+    {
+      "epoch": 3.928571428571429,
+      "grad_norm": 0.12357600778341293,
+      "learning_rate": 2.1582733812949642e-05,
+      "loss": 0.4305,
+      "step": 550
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.10841184109449387,
+      "learning_rate": 2.0143884892086333e-05,
+      "loss": 0.4134,
+      "step": 560
+    },
+    {
+      "epoch": 4.071428571428571,
+      "grad_norm": 0.12538909912109375,
+      "learning_rate": 1.8705035971223024e-05,
+      "loss": 0.399,
+      "step": 570
+    },
+    {
+      "epoch": 4.142857142857143,
+      "grad_norm": 0.15004506707191467,
+      "learning_rate": 1.7266187050359716e-05,
+      "loss": 0.394,
+      "step": 580
+    },
+    {
+      "epoch": 4.214285714285714,
+      "grad_norm": 0.1259927898645401,
+      "learning_rate": 1.5827338129496403e-05,
+      "loss": 0.4336,
+      "step": 590
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.13113726675510406,
+      "learning_rate": 1.4388489208633093e-05,
+      "loss": 0.4203,
+      "step": 600
+    },
+    {
+      "epoch": 4.357142857142857,
+      "grad_norm": 0.13534702360630035,
+      "learning_rate": 1.2949640287769784e-05,
+      "loss": 0.3731,
+      "step": 610
+    },
+    {
+      "epoch": 4.428571428571429,
+      "grad_norm": 0.14081259071826935,
+      "learning_rate": 1.1510791366906475e-05,
+      "loss": 0.3869,
+      "step": 620
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.13458286225795746,
+      "learning_rate": 1.0071942446043167e-05,
+      "loss": 0.4143,
+      "step": 630
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.12921994924545288,
+      "learning_rate": 8.633093525179858e-06,
+      "loss": 0.3854,
+      "step": 640
+    },
+    {
+      "epoch": 4.642857142857143,
+      "grad_norm": 0.14026252925395966,
+      "learning_rate": 7.1942446043165465e-06,
+      "loss": 0.4295,
+      "step": 650
+    },
+    {
+      "epoch": 4.714285714285714,
+      "grad_norm": 0.14407575130462646,
+      "learning_rate": 5.755395683453238e-06,
+      "loss": 0.4228,
+      "step": 660
+    },
+    {
+      "epoch": 4.785714285714286,
+      "grad_norm": 0.11860533058643341,
+      "learning_rate": 4.316546762589929e-06,
+      "loss": 0.3834,
+      "step": 670
+    },
+    {
+      "epoch": 4.857142857142857,
+      "grad_norm": 0.1333409547805786,
+      "learning_rate": 2.877697841726619e-06,
+      "loss": 0.364,
+      "step": 680
+    },
+    {
+      "epoch": 4.928571428571429,
+      "grad_norm": 0.15710106492042542,
+      "learning_rate": 1.4388489208633094e-06,
+      "loss": 0.387,
+      "step": 690
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.16918131709098816,
+      "learning_rate": 0.0,
+      "loss": 0.355,
+      "step": 700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.7064167003930624e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}