Upload folder using huggingface_hub

README.md

@@ -1,3 +1,202 @@
----
-license: wtfpl
----
+---
+library_name: peft
+base_model: bigcode/starcoder2-3b
+---
+
+# 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 0.7.1

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-3b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_proj",
+    "v_proj",
+    "q_proj",
+    "c_fc",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeddb6af4069f456e57c41801a36344876ee5eea7c6cff80049a41f5517b7a8e
+size 95402480

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff442dcea0242a069c0521a227a97a2d001dc00bc6b82d19f504fe24e9ac0e99
+size 48178804

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7b3032c0686a455c301d1e0de094e1944fb6cab7b894efa7af4d6a1738bd6b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a293a0aa058e8c0b1c3d105d19ab4609814ed51038f918b70bf2cace9be209
+size 1064

special_tokens_map.json

@@ -0,0 +1,64 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,357 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

trainer_state.json

@@ -0,0 +1,303 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.014790468364832,
+  "eval_steps": 200,
+  "global_step": 3660,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3286770747740345,
+      "grad_norm": 0.4525283873081207,
+      "learning_rate": 1.9879568983287468e-05,
+      "loss": 2.0164,
+      "step": 200
+    },
+    {
+      "epoch": 0.3286770747740345,
+      "eval_loss": 0.808789849281311,
+      "eval_runtime": 648.6859,
+      "eval_samples_per_second": 1.893,
+      "eval_steps_per_second": 0.237,
+      "step": 200
+    },
+    {
+      "epoch": 0.657354149548069,
+      "grad_norm": 0.48705440759658813,
+      "learning_rate": 1.9466986959828063e-05,
+      "loss": 1.1703,
+      "step": 400
+    },
+    {
+      "epoch": 0.657354149548069,
+      "eval_loss": 0.7549917697906494,
+      "eval_runtime": 645.5309,
+      "eval_samples_per_second": 1.902,
+      "eval_steps_per_second": 0.239,
+      "step": 400
+    },
+    {
+      "epoch": 0.9860312243221035,
+      "grad_norm": 0.6883838176727295,
+      "learning_rate": 1.877302694199442e-05,
+      "loss": 1.0269,
+      "step": 600
+    },
+    {
+      "epoch": 0.9860312243221035,
+      "eval_loss": 0.7438387870788574,
+      "eval_runtime": 649.872,
+      "eval_samples_per_second": 1.89,
+      "eval_steps_per_second": 0.237,
+      "step": 600
+    },
+    {
+      "epoch": 1.314708299096138,
+      "grad_norm": 0.5763583183288574,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.9723,
+      "step": 800
+    },
+    {
+      "epoch": 1.314708299096138,
+      "eval_loss": 0.7379218935966492,
+      "eval_runtime": 649.5248,
+      "eval_samples_per_second": 1.891,
+      "eval_steps_per_second": 0.237,
+      "step": 800
+    },
+    {
+      "epoch": 1.6433853738701725,
+      "grad_norm": 0.5101306438446045,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 0.9505,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6433853738701725,
+      "eval_loss": 0.7350366711616516,
+      "eval_runtime": 650.1904,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 0.237,
+      "step": 1000
+    },
+    {
+      "epoch": 1.972062448644207,
+      "grad_norm": 0.5611714124679565,
+      "learning_rate": 1.524704487799008e-05,
+      "loss": 0.9255,
+      "step": 1200
+    },
+    {
+      "epoch": 1.972062448644207,
+      "eval_loss": 0.7326610684394836,
+      "eval_runtime": 652.5211,
+      "eval_samples_per_second": 1.882,
+      "eval_steps_per_second": 0.236,
+      "step": 1200
+    },
+    {
+      "epoch": 2.3007395234182417,
+      "grad_norm": 0.5886391401290894,
+      "learning_rate": 1.3706910390450679e-05,
+      "loss": 0.9188,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3007395234182417,
+      "eval_loss": 0.7313700914382935,
+      "eval_runtime": 647.8807,
+      "eval_samples_per_second": 1.895,
+      "eval_steps_per_second": 0.238,
+      "step": 1400
+    },
+    {
+      "epoch": 2.629416598192276,
+      "grad_norm": 0.5193888545036316,
+      "learning_rate": 1.2056599030859367e-05,
+      "loss": 0.9001,
+      "step": 1600
+    },
+    {
+      "epoch": 2.629416598192276,
+      "eval_loss": 0.7305780053138733,
+      "eval_runtime": 648.1334,
+      "eval_samples_per_second": 1.895,
+      "eval_steps_per_second": 0.238,
+      "step": 1600
+    },
+    {
+      "epoch": 2.9580936729663105,
+      "grad_norm": 0.580741286277771,
+      "learning_rate": 1.0345161389697083e-05,
+      "loss": 0.8896,
+      "step": 1800
+    },
+    {
+      "epoch": 2.9580936729663105,
+      "eval_loss": 0.7289234399795532,
+      "eval_runtime": 648.6387,
+      "eval_samples_per_second": 1.893,
+      "eval_steps_per_second": 0.237,
+      "step": 1800
+    },
+    {
+      "epoch": 3.286770747740345,
+      "grad_norm": 0.5864242911338806,
+      "learning_rate": 8.62346485412832e-06,
+      "loss": 0.8851,
+      "step": 2000
+    },
+    {
+      "epoch": 3.286770747740345,
+      "eval_loss": 0.7283803224563599,
+      "eval_runtime": 648.5025,
+      "eval_samples_per_second": 1.894,
+      "eval_steps_per_second": 0.237,
+      "step": 2000
+    },
+    {
+      "epoch": 3.61544782251438,
+      "grad_norm": 0.8759085536003113,
+      "learning_rate": 6.942681726402474e-06,
+      "loss": 0.893,
+      "step": 2200
+    },
+    {
+      "epoch": 3.61544782251438,
+      "eval_loss": 0.7277897596359253,
+      "eval_runtime": 649.5645,
+      "eval_samples_per_second": 1.89,
+      "eval_steps_per_second": 0.237,
+      "step": 2200
+    },
+    {
+      "epoch": 3.944124897288414,
+      "grad_norm": 0.6328697204589844,
+      "learning_rate": 5.352768279562315e-06,
+      "loss": 0.8713,
+      "step": 2400
+    },
+    {
+      "epoch": 3.944124897288414,
+      "eval_loss": 0.7274895906448364,
+      "eval_runtime": 648.0857,
+      "eval_samples_per_second": 1.895,
+      "eval_steps_per_second": 0.238,
+      "step": 2400
+    },
+    {
+      "epoch": 4.272801972062449,
+      "grad_norm": 0.5513933300971985,
+      "learning_rate": 3.900979955999271e-06,
+      "loss": 0.8729,
+      "step": 2600
+    },
+    {
+      "epoch": 4.272801972062449,
+      "eval_loss": 0.7273133993148804,
+      "eval_runtime": 648.0021,
+      "eval_samples_per_second": 1.895,
+      "eval_steps_per_second": 0.238,
+      "step": 2600
+    },
+    {
+      "epoch": 4.6014790468364835,
+      "grad_norm": 0.4977937638759613,
+      "learning_rate": 2.6304668401566334e-06,
+      "loss": 0.8796,
+      "step": 2800
+    },
+    {
+      "epoch": 4.6014790468364835,
+      "eval_loss": 0.727094829082489,
+      "eval_runtime": 650.7111,
+      "eval_samples_per_second": 1.887,
+      "eval_steps_per_second": 0.237,
+      "step": 2800
+    },
+    {
+      "epoch": 4.930156121610517,
+      "grad_norm": 0.5514353513717651,
+      "learning_rate": 1.5789911507718824e-06,
+      "loss": 0.8674,
+      "step": 3000
+    },
+    {
+      "epoch": 4.930156121610517,
+      "eval_loss": 0.7267969250679016,
+      "eval_runtime": 647.9762,
+      "eval_samples_per_second": 1.895,
+      "eval_steps_per_second": 0.238,
+      "step": 3000
+    },
+    {
+      "epoch": 5.258833196384552,
+      "grad_norm": 0.573556661605835,
+      "learning_rate": 7.778048713818975e-07,
+      "loss": 0.8716,
+      "step": 3200
+    },
+    {
+      "epoch": 5.258833196384552,
+      "eval_loss": 0.7268173694610596,
+      "eval_runtime": 646.5688,
+      "eval_samples_per_second": 1.899,
+      "eval_steps_per_second": 0.238,
+      "step": 3200
+    },
+    {
+      "epoch": 5.587510271158587,
+      "grad_norm": 0.6027952432632446,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.8666,
+      "step": 3400
+    },
+    {
+      "epoch": 5.587510271158587,
+      "eval_loss": 0.726804256439209,
+      "eval_runtime": 646.8487,
+      "eval_samples_per_second": 1.898,
+      "eval_steps_per_second": 0.238,
+      "step": 3400
+    },
+    {
+      "epoch": 5.916187345932621,
+      "grad_norm": 0.7252454161643982,
+      "learning_rate": 1.340517319543877e-08,
+      "loss": 0.8669,
+      "step": 3600
+    },
+    {
+      "epoch": 5.916187345932621,
+      "eval_loss": 0.7267909049987793,
+      "eval_runtime": 645.845,
+      "eval_samples_per_second": 1.901,
+      "eval_steps_per_second": 0.238,
+      "step": 3600
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 3660,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 5.222777133780173e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb1c886fd1e38dd6b4e6b4836915557668e0eae1b72e6476a0663387a9f0c77
+size 5496