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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "v_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 sha256:86e1d965fd5c449f55ca9cb42d97b7a451bd77c9887e013329ce58e962d35338
+size 639691872

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 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.571428571428571,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 0.2544403374195099,
+      "learning_rate": 9.970149253731344e-05,
+      "loss": 1.4916,
+      "step": 10
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.17301955819129944,
+      "learning_rate": 9.91044776119403e-05,
+      "loss": 0.908,
+      "step": 20
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 0.11398938298225403,
+      "learning_rate": 9.850746268656717e-05,
+      "loss": 0.4285,
+      "step": 30
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.08889368921518326,
+      "learning_rate": 9.791044776119404e-05,
+      "loss": 0.3305,
+      "step": 40
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 0.07145170122385025,
+      "learning_rate": 9.731343283582089e-05,
+      "loss": 0.3709,
+      "step": 50
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.08652878552675247,
+      "learning_rate": 9.671641791044777e-05,
+      "loss": 0.3822,
+      "step": 60
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.0885363519191742,
+      "learning_rate": 9.611940298507464e-05,
+      "loss": 0.3799,
+      "step": 70
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.07026822865009308,
+      "learning_rate": 9.552238805970149e-05,
+      "loss": 0.4085,
+      "step": 80
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.07123386859893799,
+      "learning_rate": 9.492537313432837e-05,
+      "loss": 0.2925,
+      "step": 90
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.07839447259902954,
+      "learning_rate": 9.432835820895522e-05,
+      "loss": 0.3455,
+      "step": 100
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 0.0755082443356514,
+      "learning_rate": 9.373134328358209e-05,
+      "loss": 0.3406,
+      "step": 110
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.0823201835155487,
+      "learning_rate": 9.313432835820896e-05,
+      "loss": 0.3259,
+      "step": 120
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 0.08403510600328445,
+      "learning_rate": 9.253731343283582e-05,
+      "loss": 0.3017,
+      "step": 130
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.10145727545022964,
+      "learning_rate": 9.194029850746269e-05,
+      "loss": 0.3473,
+      "step": 140
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.07516448199748993,
+      "learning_rate": 9.134328358208956e-05,
+      "loss": 0.2865,
+      "step": 150
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.07223515212535858,
+      "learning_rate": 9.074626865671642e-05,
+      "loss": 0.3045,
+      "step": 160
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 0.07799769937992096,
+      "learning_rate": 9.014925373134329e-05,
+      "loss": 0.3306,
+      "step": 170
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.08388201892375946,
+      "learning_rate": 8.955223880597016e-05,
+      "loss": 0.309,
+      "step": 180
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 0.0838930755853653,
+      "learning_rate": 8.895522388059702e-05,
+      "loss": 0.3356,
+      "step": 190
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.07891852408647537,
+      "learning_rate": 8.835820895522389e-05,
+      "loss": 0.3048,
+      "step": 200
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.07239601761102676,
+      "learning_rate": 8.776119402985074e-05,
+      "loss": 0.3601,
+      "step": 210
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.07549150288105011,
+      "learning_rate": 8.716417910447762e-05,
+      "loss": 0.3415,
+      "step": 220
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 0.08595260232686996,
+      "learning_rate": 8.656716417910447e-05,
+      "loss": 0.3521,
+      "step": 230
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.08356776833534241,
+      "learning_rate": 8.597014925373134e-05,
+      "loss": 0.2898,
+      "step": 240
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.07699938863515854,
+      "learning_rate": 8.537313432835822e-05,
+      "loss": 0.3038,
+      "step": 250
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.07691926509141922,
+      "learning_rate": 8.477611940298507e-05,
+      "loss": 0.3403,
+      "step": 260
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 0.07808340340852737,
+      "learning_rate": 8.417910447761194e-05,
+      "loss": 0.3164,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07639653235673904,
+      "learning_rate": 8.358208955223881e-05,
+      "loss": 0.2872,
+      "step": 280
+    },
+    {
+      "epoch": 1.0357142857142858,
+      "grad_norm": 0.07973363250494003,
+      "learning_rate": 8.298507462686567e-05,
+      "loss": 0.3111,
+      "step": 290
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.08878948539495468,
+      "learning_rate": 8.238805970149254e-05,
+      "loss": 0.317,
+      "step": 300
+    },
+    {
+      "epoch": 1.1071428571428572,
+      "grad_norm": 0.07322458922863007,
+      "learning_rate": 8.179104477611941e-05,
+      "loss": 0.2999,
+      "step": 310
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.08571141958236694,
+      "learning_rate": 8.119402985074627e-05,
+      "loss": 0.2642,
+      "step": 320
+    },
+    {
+      "epoch": 1.1785714285714286,
+      "grad_norm": 0.10807636380195618,
+      "learning_rate": 8.059701492537314e-05,
+      "loss": 0.3024,
+      "step": 330
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.1146746426820755,
+      "learning_rate": 8e-05,
+      "loss": 0.2788,
+      "step": 340
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.10096397995948792,
+      "learning_rate": 7.940298507462687e-05,
+      "loss": 0.278,
+      "step": 350
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.08820641040802002,
+      "learning_rate": 7.880597014925374e-05,
+      "loss": 0.3123,
+      "step": 360
+    },
+    {
+      "epoch": 1.3214285714285714,
+      "grad_norm": 0.09731289744377136,
+      "learning_rate": 7.820895522388059e-05,
+      "loss": 0.2962,
+      "step": 370
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.09726134687662125,
+      "learning_rate": 7.761194029850747e-05,
+      "loss": 0.2723,
+      "step": 380
+    },
+    {
+      "epoch": 1.3928571428571428,
+      "grad_norm": 0.1366291046142578,
+      "learning_rate": 7.701492537313433e-05,
+      "loss": 0.2549,
+      "step": 390
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.09392824023962021,
+      "learning_rate": 7.641791044776119e-05,
+      "loss": 0.2785,
+      "step": 400
+    },
+    {
+      "epoch": 1.4642857142857144,
+      "grad_norm": 0.10537943243980408,
+      "learning_rate": 7.582089552238806e-05,
+      "loss": 0.2692,
+      "step": 410
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.11430277675390244,
+      "learning_rate": 7.522388059701493e-05,
+      "loss": 0.2787,
+      "step": 420
+    },
+    {
+      "epoch": 1.5357142857142856,
+      "grad_norm": 0.1093386635184288,
+      "learning_rate": 7.46268656716418e-05,
+      "loss": 0.2953,
+      "step": 430
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.10960441827774048,
+      "learning_rate": 7.402985074626866e-05,
+      "loss": 0.2906,
+      "step": 440
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 0.11768423765897751,
+      "learning_rate": 7.343283582089552e-05,
+      "loss": 0.3433,
+      "step": 450
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.10420206189155579,
+      "learning_rate": 7.283582089552239e-05,
+      "loss": 0.2769,
+      "step": 460
+    },
+    {
+      "epoch": 1.6785714285714286,
+      "grad_norm": 0.090525321662426,
+      "learning_rate": 7.223880597014926e-05,
+      "loss": 0.2859,
+      "step": 470
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.11874176561832428,
+      "learning_rate": 7.164179104477612e-05,
+      "loss": 0.3243,
+      "step": 480
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.08634401112794876,
+      "learning_rate": 7.104477611940299e-05,
+      "loss": 0.2398,
+      "step": 490
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.10205753147602081,
+      "learning_rate": 7.044776119402984e-05,
+      "loss": 0.3725,
+      "step": 500
+    },
+    {
+      "epoch": 1.8214285714285714,
+      "grad_norm": 0.09119073301553726,
+      "learning_rate": 6.985074626865672e-05,
+      "loss": 0.2374,
+      "step": 510
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.11212314665317535,
+      "learning_rate": 6.925373134328359e-05,
+      "loss": 0.2958,
+      "step": 520
+    },
+    {
+      "epoch": 1.8928571428571428,
+      "grad_norm": 0.11491134017705917,
+      "learning_rate": 6.865671641791044e-05,
+      "loss": 0.291,
+      "step": 530
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.11586255580186844,
+      "learning_rate": 6.805970149253732e-05,
+      "loss": 0.3222,
+      "step": 540
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 0.10049410909414291,
+      "learning_rate": 6.746268656716418e-05,
+      "loss": 0.2914,
+      "step": 550
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.08521942794322968,
+      "learning_rate": 6.686567164179106e-05,
+      "loss": 0.2999,
+      "step": 560
+    },
+    {
+      "epoch": 2.0357142857142856,
+      "grad_norm": 0.11586008220911026,
+      "learning_rate": 6.626865671641791e-05,
+      "loss": 0.2531,
+      "step": 570
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.1241249069571495,
+      "learning_rate": 6.567164179104478e-05,
+      "loss": 0.2422,
+      "step": 580
+    },
+    {
+      "epoch": 2.107142857142857,
+      "grad_norm": 0.15100309252738953,
+      "learning_rate": 6.507462686567164e-05,
+      "loss": 0.2177,
+      "step": 590
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.1219455674290657,
+      "learning_rate": 6.447761194029851e-05,
+      "loss": 0.2349,
+      "step": 600
+    },
+    {
+      "epoch": 2.1785714285714284,
+      "grad_norm": 0.1460845172405243,
+      "learning_rate": 6.388059701492538e-05,
+      "loss": 0.2407,
+      "step": 610
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 0.1512862741947174,
+      "learning_rate": 6.328358208955224e-05,
+      "loss": 0.284,
+      "step": 620
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.14087745547294617,
+      "learning_rate": 6.268656716417911e-05,
+      "loss": 0.2561,
+      "step": 630
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.11492959409952164,
+      "learning_rate": 6.208955223880598e-05,
+      "loss": 0.2708,
+      "step": 640
+    },
+    {
+      "epoch": 2.3214285714285716,
+      "grad_norm": 0.15090124309062958,
+      "learning_rate": 6.149253731343284e-05,
+      "loss": 0.2092,
+      "step": 650
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.1459421068429947,
+      "learning_rate": 6.08955223880597e-05,
+      "loss": 0.2442,
+      "step": 660
+    },
+    {
+      "epoch": 2.392857142857143,
+      "grad_norm": 0.1471620351076126,
+      "learning_rate": 6.029850746268657e-05,
+      "loss": 0.267,
+      "step": 670
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.1476091742515564,
+      "learning_rate": 5.970149253731343e-05,
+      "loss": 0.2867,
+      "step": 680
+    },
+    {
+      "epoch": 2.4642857142857144,
+      "grad_norm": 0.15003158152103424,
+      "learning_rate": 5.91044776119403e-05,
+      "loss": 0.2711,
+      "step": 690
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.16726762056350708,
+      "learning_rate": 5.8507462686567175e-05,
+      "loss": 0.2398,
+      "step": 700
+    },
+    {
+      "epoch": 2.5357142857142856,
+      "grad_norm": 0.1285712569952011,
+      "learning_rate": 5.7910447761194034e-05,
+      "loss": 0.2768,
+      "step": 710
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.13130241632461548,
+      "learning_rate": 5.73134328358209e-05,
+      "loss": 0.2486,
+      "step": 720
+    },
+    {
+      "epoch": 2.607142857142857,
+      "grad_norm": 0.15794238448143005,
+      "learning_rate": 5.671641791044776e-05,
+      "loss": 0.2367,
+      "step": 730
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 0.16475516557693481,
+      "learning_rate": 5.6119402985074634e-05,
+      "loss": 0.2593,
+      "step": 740
+    },
+    {
+      "epoch": 2.678571428571429,
+      "grad_norm": 0.14723050594329834,
+      "learning_rate": 5.5522388059701494e-05,
+      "loss": 0.2398,
+      "step": 750
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.14579030871391296,
+      "learning_rate": 5.492537313432836e-05,
+      "loss": 0.2603,
+      "step": 760
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.14156433939933777,
+      "learning_rate": 5.432835820895522e-05,
+      "loss": 0.2241,
+      "step": 770
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.1483439803123474,
+      "learning_rate": 5.373134328358209e-05,
+      "loss": 0.2514,
+      "step": 780
+    },
+    {
+      "epoch": 2.821428571428571,
+      "grad_norm": 0.1641162484884262,
+      "learning_rate": 5.313432835820896e-05,
+      "loss": 0.2479,
+      "step": 790
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.1514202207326889,
+      "learning_rate": 5.253731343283582e-05,
+      "loss": 0.2317,
+      "step": 800
+    },
+    {
+      "epoch": 2.892857142857143,
+      "grad_norm": 0.13422024250030518,
+      "learning_rate": 5.194029850746269e-05,
+      "loss": 0.2639,
+      "step": 810
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 0.12607942521572113,
+      "learning_rate": 5.134328358208955e-05,
+      "loss": 0.2111,
+      "step": 820
+    },
+    {
+      "epoch": 2.9642857142857144,
+      "grad_norm": 0.13523127138614655,
+      "learning_rate": 5.074626865671642e-05,
+      "loss": 0.2522,
+      "step": 830
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.17928624153137207,
+      "learning_rate": 5.014925373134328e-05,
+      "loss": 0.2688,
+      "step": 840
+    },
+    {
+      "epoch": 3.0357142857142856,
+      "grad_norm": 0.15228058397769928,
+      "learning_rate": 4.955223880597015e-05,
+      "loss": 0.1855,
+      "step": 850
+    },
+    {
+      "epoch": 3.0714285714285716,
+      "grad_norm": 0.15598702430725098,
+      "learning_rate": 4.895522388059702e-05,
+      "loss": 0.2103,
+      "step": 860
+    },
+    {
+      "epoch": 3.107142857142857,
+      "grad_norm": 0.16875101625919342,
+      "learning_rate": 4.8358208955223885e-05,
+      "loss": 0.2006,
+      "step": 870
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.16867318749427795,
+      "learning_rate": 4.7761194029850745e-05,
+      "loss": 0.1751,
+      "step": 880
+    },
+    {
+      "epoch": 3.1785714285714284,
+      "grad_norm": 0.17668938636779785,
+      "learning_rate": 4.716417910447761e-05,
+      "loss": 0.1818,
+      "step": 890
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 0.19076865911483765,
+      "learning_rate": 4.656716417910448e-05,
+      "loss": 0.2115,
+      "step": 900
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.21991585195064545,
+      "learning_rate": 4.5970149253731345e-05,
+      "loss": 0.2076,
+      "step": 910
+    },
+    {
+      "epoch": 3.2857142857142856,
+      "grad_norm": 0.1979696899652481,
+      "learning_rate": 4.537313432835821e-05,
+      "loss": 0.2359,
+      "step": 920
+    },
+    {
+      "epoch": 3.3214285714285716,
+      "grad_norm": 0.20029081404209137,
+      "learning_rate": 4.477611940298508e-05,
+      "loss": 0.1868,
+      "step": 930
+    },
+    {
+      "epoch": 3.357142857142857,
+      "grad_norm": 0.20280781388282776,
+      "learning_rate": 4.4179104477611944e-05,
+      "loss": 0.2117,
+      "step": 940
+    },
+    {
+      "epoch": 3.392857142857143,
+      "grad_norm": 0.22452795505523682,
+      "learning_rate": 4.358208955223881e-05,
+      "loss": 0.2021,
+      "step": 950
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.1844116449356079,
+      "learning_rate": 4.298507462686567e-05,
+      "loss": 0.2223,
+      "step": 960
+    },
+    {
+      "epoch": 3.4642857142857144,
+      "grad_norm": 0.19978521764278412,
+      "learning_rate": 4.238805970149254e-05,
+      "loss": 0.1995,
+      "step": 970
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.19762808084487915,
+      "learning_rate": 4.1791044776119404e-05,
+      "loss": 0.1821,
+      "step": 980
+    },
+    {
+      "epoch": 3.5357142857142856,
+      "grad_norm": 0.19516855478286743,
+      "learning_rate": 4.119402985074627e-05,
+      "loss": 0.1961,
+      "step": 990
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.1498711109161377,
+      "learning_rate": 4.059701492537314e-05,
+      "loss": 0.1688,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1290615384629248e+17,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}