Upload 12 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": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_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:a75ba24f7b58c53b4b4691a647fb4865d00b68c9e364e12f8e4a015662cc9996
+size 159967880

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70894608b1f2fd6ce57b63ceee2507324c1bd7b5a5a3eac87f02361d34fcb64c
+size 320200274

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d4fbb4eb2a12b17b73babfa38b90bdafc73a682a0af60498a1e002b1fd5b3a
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a6b6b8cf99b0c2174cd2e01d3f497f96d31938cf35230876ea28c69c51c665
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c288e8f0186316bc491d8fbed73a999620ce45d9721a64b200870d22a1a84a90
+size 1064

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 +1,524 @@
+{
+  "best_global_step": null,
+  "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": 0.15036863088607788,
+      "learning_rate": 9.928057553956835e-05,
+      "loss": 1.1077,
+      "step": 10
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.193057581782341,
+      "learning_rate": 9.784172661870504e-05,
+      "loss": 1.0083,
+      "step": 20
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.08045618236064911,
+      "learning_rate": 9.640287769784174e-05,
+      "loss": 0.7485,
+      "step": 30
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.11583670973777771,
+      "learning_rate": 9.496402877697842e-05,
+      "loss": 0.712,
+      "step": 40
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.11208095401525497,
+      "learning_rate": 9.35251798561151e-05,
+      "loss": 0.7233,
+      "step": 50
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.11208643764257431,
+      "learning_rate": 9.20863309352518e-05,
+      "loss": 0.7492,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.12728804349899292,
+      "learning_rate": 9.06474820143885e-05,
+      "loss": 0.667,
+      "step": 70
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.11325202882289886,
+      "learning_rate": 8.920863309352519e-05,
+      "loss": 0.7477,
+      "step": 80
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.10744063556194305,
+      "learning_rate": 8.776978417266187e-05,
+      "loss": 0.7106,
+      "step": 90
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.11867828667163849,
+      "learning_rate": 8.633093525179857e-05,
+      "loss": 0.6824,
+      "step": 100
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.10340498387813568,
+      "learning_rate": 8.489208633093527e-05,
+      "loss": 0.7038,
+      "step": 110
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.15735560655593872,
+      "learning_rate": 8.345323741007195e-05,
+      "loss": 0.6034,
+      "step": 120
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.16039283573627472,
+      "learning_rate": 8.201438848920863e-05,
+      "loss": 0.6561,
+      "step": 130
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.14552897214889526,
+      "learning_rate": 8.057553956834533e-05,
+      "loss": 0.6506,
+      "step": 140
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.1838674396276474,
+      "learning_rate": 7.913669064748202e-05,
+      "loss": 0.6045,
+      "step": 150
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.195386603474617,
+      "learning_rate": 7.769784172661872e-05,
+      "loss": 0.6637,
+      "step": 160
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.19899536669254303,
+      "learning_rate": 7.62589928057554e-05,
+      "loss": 0.6108,
+      "step": 170
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.18925336003303528,
+      "learning_rate": 7.48201438848921e-05,
+      "loss": 0.6481,
+      "step": 180
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.18190115690231323,
+      "learning_rate": 7.338129496402878e-05,
+      "loss": 0.6594,
+      "step": 190
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.17894072830677032,
+      "learning_rate": 7.194244604316547e-05,
+      "loss": 0.5453,
+      "step": 200
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.20920348167419434,
+      "learning_rate": 7.050359712230215e-05,
+      "loss": 0.5897,
+      "step": 210
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.20813661813735962,
+      "learning_rate": 6.906474820143886e-05,
+      "loss": 0.5848,
+      "step": 220
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.24429826438426971,
+      "learning_rate": 6.762589928057555e-05,
+      "loss": 0.6198,
+      "step": 230
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.22697171568870544,
+      "learning_rate": 6.618705035971223e-05,
+      "loss": 0.5842,
+      "step": 240
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.2556312084197998,
+      "learning_rate": 6.474820143884892e-05,
+      "loss": 0.5371,
+      "step": 250
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.2177497297525406,
+      "learning_rate": 6.330935251798561e-05,
+      "loss": 0.5704,
+      "step": 260
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.2518755793571472,
+      "learning_rate": 6.187050359712231e-05,
+      "loss": 0.5212,
+      "step": 270
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.25046634674072266,
+      "learning_rate": 6.0431654676258996e-05,
+      "loss": 0.5667,
+      "step": 280
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.24478240311145782,
+      "learning_rate": 5.899280575539569e-05,
+      "loss": 0.5879,
+      "step": 290
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.2547719478607178,
+      "learning_rate": 5.755395683453237e-05,
+      "loss": 0.5369,
+      "step": 300
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 0.2863396108150482,
+      "learning_rate": 5.611510791366906e-05,
+      "loss": 0.5181,
+      "step": 310
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.28480178117752075,
+      "learning_rate": 5.467625899280576e-05,
+      "loss": 0.4763,
+      "step": 320
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.19697213172912598,
+      "learning_rate": 5.323741007194245e-05,
+      "loss": 0.6052,
+      "step": 330
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.2452905774116516,
+      "learning_rate": 5.179856115107914e-05,
+      "loss": 0.5286,
+      "step": 340
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.2562999427318573,
+      "learning_rate": 5.035971223021583e-05,
+      "loss": 0.5392,
+      "step": 350
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.3020641803741455,
+      "learning_rate": 4.892086330935252e-05,
+      "loss": 0.4734,
+      "step": 360
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 0.2998867928981781,
+      "learning_rate": 4.748201438848921e-05,
+      "loss": 0.4996,
+      "step": 370
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.32622605562210083,
+      "learning_rate": 4.60431654676259e-05,
+      "loss": 0.539,
+      "step": 380
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.2696865499019623,
+      "learning_rate": 4.460431654676259e-05,
+      "loss": 0.5506,
+      "step": 390
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.28632229566574097,
+      "learning_rate": 4.3165467625899284e-05,
+      "loss": 0.4951,
+      "step": 400
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 0.2761767506599426,
+      "learning_rate": 4.1726618705035975e-05,
+      "loss": 0.4887,
+      "step": 410
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3062366843223572,
+      "learning_rate": 4.0287769784172666e-05,
+      "loss": 0.4837,
+      "step": 420
+    },
+    {
+      "epoch": 3.0714285714285716,
+      "grad_norm": 0.33878713846206665,
+      "learning_rate": 3.884892086330936e-05,
+      "loss": 0.4278,
+      "step": 430
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.273576557636261,
+      "learning_rate": 3.741007194244605e-05,
+      "loss": 0.4776,
+      "step": 440
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 0.314053475856781,
+      "learning_rate": 3.597122302158273e-05,
+      "loss": 0.549,
+      "step": 450
+    },
+    {
+      "epoch": 3.2857142857142856,
+      "grad_norm": 0.3175768554210663,
+      "learning_rate": 3.453237410071943e-05,
+      "loss": 0.4587,
+      "step": 460
+    },
+    {
+      "epoch": 3.357142857142857,
+      "grad_norm": 0.287589430809021,
+      "learning_rate": 3.3093525179856116e-05,
+      "loss": 0.4272,
+      "step": 470
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.32573071122169495,
+      "learning_rate": 3.165467625899281e-05,
+      "loss": 0.4506,
+      "step": 480
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.41540372371673584,
+      "learning_rate": 3.0215827338129498e-05,
+      "loss": 0.5129,
+      "step": 490
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.33923348784446716,
+      "learning_rate": 2.8776978417266186e-05,
+      "loss": 0.494,
+      "step": 500
+    },
+    {
+      "epoch": 3.642857142857143,
+      "grad_norm": 0.3455836772918701,
+      "learning_rate": 2.733812949640288e-05,
+      "loss": 0.4687,
+      "step": 510
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.34565624594688416,
+      "learning_rate": 2.589928057553957e-05,
+      "loss": 0.4534,
+      "step": 520
+    },
+    {
+      "epoch": 3.7857142857142856,
+      "grad_norm": 0.343277245759964,
+      "learning_rate": 2.446043165467626e-05,
+      "loss": 0.5045,
+      "step": 530
+    },
+    {
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.31855452060699463,
+      "learning_rate": 2.302158273381295e-05,
+      "loss": 0.4918,
+      "step": 540
+    },
+    {
+      "epoch": 3.928571428571429,
+      "grad_norm": 0.3254612684249878,
+      "learning_rate": 2.1582733812949642e-05,
+      "loss": 0.4812,
+      "step": 550
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.3659997284412384,
+      "learning_rate": 2.0143884892086333e-05,
+      "loss": 0.4657,
+      "step": 560
+    },
+    {
+      "epoch": 4.071428571428571,
+      "grad_norm": 0.4133649170398712,
+      "learning_rate": 1.8705035971223024e-05,
+      "loss": 0.4157,
+      "step": 570
+    },
+    {
+      "epoch": 4.142857142857143,
+      "grad_norm": 0.4074523150920868,
+      "learning_rate": 1.7266187050359716e-05,
+      "loss": 0.4519,
+      "step": 580
+    },
+    {
+      "epoch": 4.214285714285714,
+      "grad_norm": 0.3066883683204651,
+      "learning_rate": 1.5827338129496403e-05,
+      "loss": 0.483,
+      "step": 590
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.3481828272342682,
+      "learning_rate": 1.4388489208633093e-05,
+      "loss": 0.4698,
+      "step": 600
+    },
+    {
+      "epoch": 4.357142857142857,
+      "grad_norm": 0.3295931816101074,
+      "learning_rate": 1.2949640287769784e-05,
+      "loss": 0.4964,
+      "step": 610
+    },
+    {
+      "epoch": 4.428571428571429,
+      "grad_norm": 0.4130198061466217,
+      "learning_rate": 1.1510791366906475e-05,
+      "loss": 0.4405,
+      "step": 620
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.34325918555259705,
+      "learning_rate": 1.0071942446043167e-05,
+      "loss": 0.4128,
+      "step": 630
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.4057556092739105,
+      "learning_rate": 8.633093525179858e-06,
+      "loss": 0.4438,
+      "step": 640
+    },
+    {
+      "epoch": 4.642857142857143,
+      "grad_norm": 0.4750465154647827,
+      "learning_rate": 7.1942446043165465e-06,
+      "loss": 0.4443,
+      "step": 650
+    },
+    {
+      "epoch": 4.714285714285714,
+      "grad_norm": 0.36197009682655334,
+      "learning_rate": 5.755395683453238e-06,
+      "loss": 0.3771,
+      "step": 660
+    },
+    {
+      "epoch": 4.785714285714286,
+      "grad_norm": 0.40253880620002747,
+      "learning_rate": 4.316546762589929e-06,
+      "loss": 0.4005,
+      "step": 670
+    },
+    {
+      "epoch": 4.857142857142857,
+      "grad_norm": 0.39900633692741394,
+      "learning_rate": 2.877697841726619e-06,
+      "loss": 0.4658,
+      "step": 680
+    },
+    {
+      "epoch": 4.928571428571429,
+      "grad_norm": 0.3553173840045929,
+      "learning_rate": 1.4388489208633094e-06,
+      "loss": 0.4362,
+      "step": 690
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.38214293122291565,
+      "learning_rate": 0.0,
+      "loss": 0.4493,
+      "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": 3.056291313827021e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}