Upload task output fa30d435-3229-4c56-871d-51ad38cfbe7a

README.md

@@ -0,0 +1,202 @@
+---
+base_model: None
+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 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "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": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6637822566c77111fc42fe30acbd605342b8492cf43c1dd9537249cd5bfd4508
+size 578859568

loss.txt

@@ -0,0 +1 @@
+swa,3_checkpoints_averaged

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd13b1f10a586a5482f9616069647bd73d5b14eb85af5e6515dad980e4df2e6d
+size 289452768

special_tokens_map.json

@@ -0,0 +1,49 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<empty_output>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,170 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<empty_output>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

trainer_state.json

@@ -0,0 +1,646 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 0.44878774881362915,
+      "learning_rate": 0.000289521783910996,
+      "loss": 3.3605,
+      "step": 5
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.325467973947525,
+      "learning_rate": 0.0003618400166398465,
+      "loss": 2.8945,
+      "step": 10
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 0.2423306256532669,
+      "learning_rate": 0.0003615873730705915,
+      "loss": 2.6612,
+      "step": 15
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.2094593495130539,
+      "learning_rate": 0.000361140772483858,
+      "loss": 2.5949,
+      "step": 20
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 0.2044210284948349,
+      "learning_rate": 0.00036050085463068467,
+      "loss": 2.5521,
+      "step": 25
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.23538050055503845,
+      "learning_rate": 0.0003596685361872319,
+      "loss": 2.492,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.1984870284795761,
+      "learning_rate": 0.0003586450094416527,
+      "loss": 2.5206,
+      "step": 35
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.14157792925834656,
+      "learning_rate": 0.0003574317405861506,
+      "loss": 2.4296,
+      "step": 40
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.12453815340995789,
+      "learning_rate": 0.00035603046761667424,
+      "loss": 2.44,
+      "step": 45
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.11900381743907928,
+      "learning_rate": 0.0003544431978432544,
+      "loss": 2.4788,
+      "step": 50
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 0.19382521510124207,
+      "learning_rate": 0.00035267220501455183,
+      "loss": 2.4395,
+      "step": 55
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.184844508767128,
+      "learning_rate": 0.00035072002606073425,
+      "loss": 2.3968,
+      "step": 60
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 0.15302661061286926,
+      "learning_rate": 0.0003485894574593484,
+      "loss": 2.386,
+      "step": 65
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.14385174214839935,
+      "learning_rate": 0.00034628355122939266,
+      "loss": 2.3891,
+      "step": 70
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.1122179701924324,
+      "learning_rate": 0.0003438056105593294,
+      "loss": 2.4124,
+      "step": 75
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.12257640808820724,
+      "learning_rate": 0.0003411591850752994,
+      "loss": 2.379,
+      "step": 80
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 0.11705131083726883,
+      "learning_rate": 0.0003383480657563163,
+      "loss": 2.3352,
+      "step": 85
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.11879861354827881,
+      "learning_rate": 0.0003353762795037261,
+      "loss": 2.3836,
+      "step": 90
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 0.12045249342918396,
+      "learning_rate": 0.0003322480833727093,
+      "loss": 2.3884,
+      "step": 95
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.12423133105039597,
+      "learning_rate": 0.00032896795847409084,
+      "loss": 2.346,
+      "step": 100
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.14303036034107208,
+      "learning_rate": 0.00032554060355519153,
+      "loss": 2.3621,
+      "step": 105
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.1502680629491806,
+      "learning_rate": 0.00032197092826891826,
+      "loss": 2.2704,
+      "step": 110
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 0.13060663640499115,
+      "learning_rate": 0.00031826404614073307,
+      "loss": 2.3163,
+      "step": 115
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.13510695099830627,
+      "learning_rate": 0.00031442526724357743,
+      "loss": 2.321,
+      "step": 120
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.12903311848640442,
+      "learning_rate": 0.0003104600905912439,
+      "loss": 2.2986,
+      "step": 125
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.12716606259346008,
+      "learning_rate": 0.0003063741962610917,
+      "loss": 2.2794,
+      "step": 130
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 0.14283885061740875,
+      "learning_rate": 0.0003021734372573907,
+      "loss": 2.2997,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1486726701259613,
+      "learning_rate": 0.00029786383112694937,
+      "loss": 2.3651,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.305704355239868,
+      "eval_runtime": 4.346,
+      "eval_samples_per_second": 12.885,
+      "eval_steps_per_second": 12.885,
+      "step": 140
+    },
+    {
+      "epoch": 1.0357142857142858,
+      "grad_norm": 0.1466517597436905,
+      "learning_rate": 0.0002934515513390363,
+      "loss": 2.2312,
+      "step": 145
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.13890157639980316,
+      "learning_rate": 0.0002889429184419459,
+      "loss": 2.1697,
+      "step": 150
+    },
+    {
+      "epoch": 1.1071428571428572,
+      "grad_norm": 0.12447746843099594,
+      "learning_rate": 0.0002843443910088731,
+      "loss": 2.1876,
+      "step": 155
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.14858925342559814,
+      "learning_rate": 0.0002796625563860696,
+      "loss": 2.2529,
+      "step": 160
+    },
+    {
+      "epoch": 1.1785714285714286,
+      "grad_norm": 0.14622247219085693,
+      "learning_rate": 0.00027490412125653413,
+      "loss": 2.1692,
+      "step": 165
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.16352051496505737,
+      "learning_rate": 0.0002700759020327533,
+      "loss": 2.1683,
+      "step": 170
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.15044339001178741,
+      "learning_rate": 0.0002651848150922565,
+      "loss": 2.208,
+      "step": 175
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.18973936140537262,
+      "learning_rate": 0.00026023786686997193,
+      "loss": 2.1757,
+      "step": 180
+    },
+    {
+      "epoch": 1.3214285714285714,
+      "grad_norm": 0.1430087834596634,
+      "learning_rate": 0.00025524214382157567,
+      "loss": 2.1456,
+      "step": 185
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.15100987255573273,
+      "learning_rate": 0.00025020480227221244,
+      "loss": 2.1492,
+      "step": 190
+    },
+    {
+      "epoch": 1.3928571428571428,
+      "grad_norm": 0.1682235598564148,
+      "learning_rate": 0.00024513305816512866,
+      "loss": 2.1298,
+      "step": 195
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.13889002799987793,
+      "learning_rate": 0.0002400341767249034,
+      "loss": 2.1426,
+      "step": 200
+    },
+    {
+      "epoch": 1.4642857142857144,
+      "grad_norm": 0.15031439065933228,
+      "learning_rate": 0.00023491546205008394,
+      "loss": 2.1629,
+      "step": 205
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.15855388343334198,
+      "learning_rate": 0.000229784246650135,
+      "loss": 2.1245,
+      "step": 210
+    },
+    {
+      "epoch": 1.5357142857142856,
+      "grad_norm": 0.1361117959022522,
+      "learning_rate": 0.0002246478809416899,
+      "loss": 2.1539,
+      "step": 215
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.1389189511537552,
+      "learning_rate": 0.000219513722719149,
+      "loss": 2.1689,
+      "step": 220
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 0.14022548496723175,
+      "learning_rate": 0.00021438912661471057,
+      "loss": 2.1066,
+      "step": 225
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.15505997836589813,
+      "learning_rate": 0.00020928143356293064,
+      "loss": 2.1704,
+      "step": 230
+    },
+    {
+      "epoch": 1.6785714285714286,
+      "grad_norm": 0.15153466165065765,
+      "learning_rate": 0.00020419796028490518,
+      "loss": 2.1221,
+      "step": 235
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.15661795437335968,
+      "learning_rate": 0.00019914598880713764,
+      "loss": 2.1085,
+      "step": 240
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.18082356452941895,
+      "learning_rate": 0.00019413275603010594,
+      "loss": 2.1192,
+      "step": 245
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.1475025713443756,
+      "learning_rate": 0.00018916544336147238,
+      "loss": 2.1576,
+      "step": 250
+    },
+    {
+      "epoch": 1.8214285714285714,
+      "grad_norm": 0.1800713986158371,
+      "learning_rate": 0.00018425116642878646,
+      "loss": 2.2125,
+      "step": 255
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.1504836529493332,
+      "learning_rate": 0.0001793969648864165,
+      "loss": 2.1063,
+      "step": 260
+    },
+    {
+      "epoch": 1.8928571428571428,
+      "grad_norm": 0.15903660655021667,
+      "learning_rate": 0.0001746097923313131,
+      "loss": 2.1268,
+      "step": 265
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.17211540043354034,
+      "learning_rate": 0.00016989650634204837,
+      "loss": 2.1333,
+      "step": 270
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 0.15337097644805908,
+      "learning_rate": 0.0001652638586554003,
+      "loss": 2.1328,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.15568628907203674,
+      "learning_rate": 0.00016071848549455535,
+      "loss": 2.151,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.22261381149292,
+      "eval_runtime": 4.2486,
+      "eval_samples_per_second": 13.181,
+      "eval_steps_per_second": 13.181,
+      "step": 280
+    },
+    {
+      "epoch": 2.0357142857142856,
+      "grad_norm": 0.16075798869132996,
+      "learning_rate": 0.00015626689806278225,
+      "loss": 2.0259,
+      "step": 285
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.17610718309879303,
+      "learning_rate": 0.00015191547321619653,
+      "loss": 2.0075,
+      "step": 290
+    },
+    {
+      "epoch": 2.107142857142857,
+      "grad_norm": 0.16602124273777008,
+      "learning_rate": 0.00014767044432897506,
+      "loss": 2.038,
+      "step": 295
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.16692619025707245,
+      "learning_rate": 0.0001435378923641078,
+      "loss": 1.9613,
+      "step": 300
+    },
+    {
+      "epoch": 2.1785714285714284,
+      "grad_norm": 0.18126952648162842,
+      "learning_rate": 0.000139523737162477,
+      "loss": 1.9858,
+      "step": 305
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 0.17799189686775208,
+      "learning_rate": 0.00013563372896274205,
+      "loss": 1.9845,
+      "step": 310
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.16581512987613678,
+      "learning_rate": 0.00013187344016417777,
+      "loss": 1.9754,
+      "step": 315
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.18213392794132233,
+      "learning_rate": 0.00012824825734426663,
+      "loss": 2.0338,
+      "step": 320
+    },
+    {
+      "epoch": 2.3214285714285716,
+      "grad_norm": 0.20415815711021423,
+      "learning_rate": 0.00012476337354247802,
+      "loss": 1.9789,
+      "step": 325
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.18837185204029083,
+      "learning_rate": 0.00012142378082128922,
+      "loss": 1.9793,
+      "step": 330
+    },
+    {
+      "epoch": 2.392857142857143,
+      "grad_norm": 0.18530172109603882,
+      "learning_rate": 0.00011823426311510409,
+      "loss": 1.9982,
+      "step": 335
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.18085235357284546,
+      "learning_rate": 0.00011519938937731338,
+      "loss": 1.9721,
+      "step": 340
+    },
+    {
+      "epoch": 2.4642857142857144,
+      "grad_norm": 0.17293037474155426,
+      "learning_rate": 0.00011232350703531239,
+      "loss": 1.962,
+      "step": 345
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.17826664447784424,
+      "learning_rate": 0.00010961073576285371,
+      "loss": 1.9523,
+      "step": 350
+    },
+    {
+      "epoch": 2.5357142857142856,
+      "grad_norm": 0.17852868139743805,
+      "learning_rate": 0.00010706496157865393,
+      "loss": 1.9601,
+      "step": 355
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.1897851526737213,
+      "learning_rate": 0.00010468983127970931,
+      "loss": 1.9985,
+      "step": 360
+    },
+    {
+      "epoch": 2.607142857142857,
+      "grad_norm": 0.17821991443634033,
+      "learning_rate": 0.00010248874721729424,
+      "loss": 1.9627,
+      "step": 365
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 0.16785487532615662,
+      "learning_rate": 0.00010046486242312592,
+      "loss": 1.9742,
+      "step": 370
+    },
+    {
+      "epoch": 2.678571428571429,
+      "grad_norm": 0.19044014811515808,
+      "learning_rate": 9.862107609267647e-05,
+      "loss": 1.9747,
+      "step": 375
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.18507127463817596,
+      "learning_rate": 9.696002943210377e-05,
+      "loss": 1.9357,
+      "step": 380
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.17904826998710632,
+      "learning_rate": 9.548410187474875e-05,
+      "loss": 1.994,
+      "step": 385
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.19766312837600708,
+      "learning_rate": 9.419540767262022e-05,
+      "loss": 1.9463,
+      "step": 390
+    },
+    {
+      "epoch": 2.821428571428571,
+      "grad_norm": 0.1815754771232605,
+      "learning_rate": 9.309579286774919e-05,
+      "loss": 1.9613,
+      "step": 395
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.19703654944896698,
+      "learning_rate": 9.21868326477514e-05,
+      "loss": 2.0123,
+      "step": 400
+    },
+    {
+      "epoch": 2.892857142857143,
+      "grad_norm": 0.18807531893253326,
+      "learning_rate": 9.146982908938626e-05,
+      "loss": 1.9648,
+      "step": 405
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 0.2164294570684433,
+      "learning_rate": 9.094580929334454e-05,
+      "loss": 1.997,
+      "step": 410
+    },
+    {
+      "epoch": 2.9642857142857144,
+      "grad_norm": 0.1642838567495346,
+      "learning_rate": 9.061552391293631e-05,
+      "loss": 1.9741,
+      "step": 415
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19275926053524017,
+      "learning_rate": 9.047944607878754e-05,
+      "loss": 1.9786,
+      "step": 420
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.21170711517334,
+      "eval_runtime": 4.2499,
+      "eval_samples_per_second": 13.177,
+      "eval_steps_per_second": 13.177,
+      "step": 420
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 140,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.26490868301824e+17,
+  "train_batch_size": 25,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2edb30c60d48614f93c80c6cc7086cb52ee4874bd8dd170c29a97ebabd1d1c3
+size 5624