Upload folder using huggingface_hub

README.md

@@ -0,0 +1,207 @@
+---
+base_model: allenai/OLMo-2-1124-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:allenai/OLMo-2-1124-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.0

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "allenai/OLMo-2-1124-7B-Instruct",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add54f49f5d10162c9dca88db70ef6b78fb4eb3bd62ce24034c90b0c6e2c877e
+size 639691872

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe80b64f62681c8d8ca95b46768ea22e3987c18de8470bbfabe3487707562f99
+size 1279647314

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79efac7a9fc1e8d2e6ed66f1b87f0fc96aefe8f10a72516c7891434fb4ff8b5e
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3adde8a0661d775ce3e7d9d5c774afb77c8d46ab620d0c67a7d84247ea62d79
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:184906cdeef9b0c24b1fab2e2749076c79a0740b39b603d7f3848fa923553db1
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60aa43a389b1e1f19be91633fa203cc45faf36f1c9a232aaae24a1e9edafc0d
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76a9a1992442d4d4ca3b361c551c3f0a502c8aa39462f360845d0da811e495a
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5b3c4e7be71739e889058126695aabb3725da815f211f50ca45ab0ebf36d99
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9972ac715a05dfa1c5df4816ec876e6c97e9f8f49661dad2d7b19ff825a21239
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2cd689af80a5ec27b220827ef49b24c53e19238dae9b22607edaae6f78c02c9
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e7524950df06585d3a7ba733cefee4292c182136a43c2bce4baa5abf39d690
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": "<|pad|>",
+    "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 +1,190 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n'  + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,452 @@
+{
+  "best_metric": 1.268411636352539,
+  "best_model_checkpoint": "/gscratch/stf/seunguk/dipika/olmo-code-sft/train/result_outputs/7b_py23_mix_10k_normal/allenai_OLMo-2-1124-7B-Instruct/r64_lr1.5e-05/checkpoint-429",
+  "epoch": 3.0,
+  "eval_steps": 39,
+  "global_step": 459,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006535947712418301,
+      "grad_norm": 3.6004388332366943,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 7.4653,
+      "step": 1
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 3.2401626110076904,
+      "learning_rate": 3e-06,
+      "loss": 7.7982,
+      "step": 10
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 2.898332118988037,
+      "learning_rate": 6e-06,
+      "loss": 7.8085,
+      "step": 20
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 2.342164993286133,
+      "learning_rate": 9e-06,
+      "loss": 7.0685,
+      "step": 30
+    },
+    {
+      "epoch": 0.2549019607843137,
+      "eval_loss": 1.5568805932998657,
+      "eval_runtime": 6.1754,
+      "eval_samples_per_second": 16.193,
+      "eval_steps_per_second": 2.105,
+      "step": 39
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 1.3029459714889526,
+      "learning_rate": 1.2e-05,
+      "loss": 6.2268,
+      "step": 40
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.8066064715385437,
+      "learning_rate": 1.5e-05,
+      "loss": 5.6646,
+      "step": 50
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.640289843082428,
+      "learning_rate": 1.4977885819099278e-05,
+      "loss": 5.4284,
+      "step": 60
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.5137796401977539,
+      "learning_rate": 1.4911673686262952e-05,
+      "loss": 5.4141,
+      "step": 70
+    },
+    {
+      "epoch": 0.5098039215686274,
+      "eval_loss": 1.329179286956787,
+      "eval_runtime": 6.0801,
+      "eval_samples_per_second": 16.447,
+      "eval_steps_per_second": 2.138,
+      "step": 78
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.4564005732536316,
+      "learning_rate": 1.4801754062046587e-05,
+      "loss": 5.243,
+      "step": 80
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.4929277300834656,
+      "learning_rate": 1.4648775155104705e-05,
+      "loss": 5.2285,
+      "step": 90
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.5199493169784546,
+      "learning_rate": 1.4453639099629869e-05,
+      "loss": 5.2129,
+      "step": 100
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.41562795639038086,
+      "learning_rate": 1.4217496635363684e-05,
+      "loss": 5.2174,
+      "step": 110
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "eval_loss": 1.2994059324264526,
+      "eval_runtime": 6.1041,
+      "eval_samples_per_second": 16.382,
+      "eval_steps_per_second": 2.13,
+      "step": 117
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.4347153902053833,
+      "learning_rate": 1.3941740321552318e-05,
+      "loss": 5.1946,
+      "step": 120
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.4713277816772461,
+      "learning_rate": 1.3627996324864611e-05,
+      "loss": 5.1453,
+      "step": 130
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.4941399395465851,
+      "learning_rate": 1.3278114829700362e-05,
+      "loss": 5.1508,
+      "step": 140
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.5141309499740601,
+      "learning_rate": 1.2894159127440344e-05,
+      "loss": 5.0553,
+      "step": 150
+    },
+    {
+      "epoch": 1.0196078431372548,
+      "eval_loss": 1.2868971824645996,
+      "eval_runtime": 6.1033,
+      "eval_samples_per_second": 16.385,
+      "eval_steps_per_second": 2.13,
+      "step": 156
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 0.4459021985530853,
+      "learning_rate": 1.2478393448979922e-05,
+      "loss": 5.0354,
+      "step": 160
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.518979549407959,
+      "learning_rate": 1.2033269612299312e-05,
+      "loss": 5.0699,
+      "step": 170
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.5595972537994385,
+      "learning_rate": 1.1561412563811198e-05,
+      "loss": 5.0097,
+      "step": 180
+    },
+    {
+      "epoch": 1.2418300653594772,
+      "grad_norm": 0.49540629982948303,
+      "learning_rate": 1.1065604898750127e-05,
+      "loss": 5.075,
+      "step": 190
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "eval_loss": 1.2794718742370605,
+      "eval_runtime": 6.0945,
+      "eval_samples_per_second": 16.408,
+      "eval_steps_per_second": 2.133,
+      "step": 195
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 0.5955595970153809,
+      "learning_rate": 1.0548770451888665e-05,
+      "loss": 4.9689,
+      "step": 200
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.5468981862068176,
+      "learning_rate": 1.0013957055347779e-05,
+      "loss": 5.1004,
+      "step": 210
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 0.5972552299499512,
+      "learning_rate": 9.464318565180596e-06,
+      "loss": 5.0697,
+      "step": 220
+    },
+    {
+      "epoch": 1.5032679738562091,
+      "grad_norm": 0.5224605202674866,
+      "learning_rate": 8.903096262720867e-06,
+      "loss": 5.1168,
+      "step": 230
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "eval_loss": 1.274889349937439,
+      "eval_runtime": 6.1193,
+      "eval_samples_per_second": 16.342,
+      "eval_steps_per_second": 2.124,
+      "step": 234
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.563854455947876,
+      "learning_rate": 8.333599740374487e-06,
+      "loss": 5.0523,
+      "step": 240
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.5406912565231323,
+      "learning_rate": 7.75918738457279e-06,
+      "loss": 4.9938,
+      "step": 250
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 0.5734691023826599,
+      "learning_rate": 7.183246570981859e-06,
+      "loss": 5.0574,
+      "step": 260
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.5452589392662048,
+      "learning_rate": 6.609173688758989e-06,
+      "loss": 5.0522,
+      "step": 270
+    },
+    {
+      "epoch": 1.784313725490196,
+      "eval_loss": 1.2728018760681152,
+      "eval_runtime": 6.1187,
+      "eval_samples_per_second": 16.343,
+      "eval_steps_per_second": 2.125,
+      "step": 273
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 0.5308836102485657,
+      "learning_rate": 6.0403541116555636e-06,
+      "loss": 5.0906,
+      "step": 280
+    },
+    {
+      "epoch": 1.8954248366013071,
+      "grad_norm": 0.5624706745147705,
+      "learning_rate": 5.480142234079027e-06,
+      "loss": 5.0739,
+      "step": 290
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.6330104470252991,
+      "learning_rate": 4.9318416898436404e-06,
+      "loss": 5.0924,
+      "step": 300
+    },
+    {
+      "epoch": 2.026143790849673,
+      "grad_norm": 0.550271213054657,
+      "learning_rate": 4.398685870262254e-06,
+      "loss": 4.9703,
+      "step": 310
+    },
+    {
+      "epoch": 2.0392156862745097,
+      "eval_loss": 1.2705397605895996,
+      "eval_runtime": 6.092,
+      "eval_samples_per_second": 16.415,
+      "eval_steps_per_second": 2.134,
+      "step": 312
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 0.5277569890022278,
+      "learning_rate": 3.883818856466194e-06,
+      "loss": 5.0368,
+      "step": 320
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.49453046917915344,
+      "learning_rate": 3.390276878397574e-06,
+      "loss": 4.9466,
+      "step": 330
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.4974152445793152,
+      "learning_rate": 2.9209704098124204e-06,
+      "loss": 5.1187,
+      "step": 340
+    },
+    {
+      "epoch": 2.287581699346405,
+      "grad_norm": 0.6691598892211914,
+      "learning_rate": 2.47866700488251e-06,
+      "loss": 4.9278,
+      "step": 350
+    },
+    {
+      "epoch": 2.2941176470588234,
+      "eval_loss": 1.269243836402893,
+      "eval_runtime": 6.1135,
+      "eval_samples_per_second": 16.357,
+      "eval_steps_per_second": 2.126,
+      "step": 351
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.6030656099319458,
+      "learning_rate": 2.0659749776104147e-06,
+      "loss": 4.8925,
+      "step": 360
+    },
+    {
+      "epoch": 2.418300653594771,
+      "grad_norm": 0.6159414052963257,
+      "learning_rate": 1.6853280203020998e-06,
+      "loss": 5.0115,
+      "step": 370
+    },
+    {
+      "epoch": 2.4836601307189543,
+      "grad_norm": 0.5232154726982117,
+      "learning_rate": 1.3389708518037574e-06,
+      "loss": 5.015,
+      "step": 380
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.5964416265487671,
+      "learning_rate": 1.0289459801368406e-06,
+      "loss": 5.0732,
+      "step": 390
+    },
+    {
+      "epoch": 2.549019607843137,
+      "eval_loss": 1.2685757875442505,
+      "eval_runtime": 6.0856,
+      "eval_samples_per_second": 16.432,
+      "eval_steps_per_second": 2.136,
+      "step": 390
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 0.5542371869087219,
+      "learning_rate": 7.570816575935527e-07,
+      "loss": 5.0339,
+      "step": 400
+    },
+    {
+      "epoch": 2.6797385620915035,
+      "grad_norm": 0.6067601442337036,
+      "learning_rate": 5.249810993230036e-07,
+      "loss": 5.0544,
+      "step": 410
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.5335155129432678,
+      "learning_rate": 3.3401302898726395e-07,
+      "loss": 4.9646,
+      "step": 420
+    },
+    {
+      "epoch": 2.803921568627451,
+      "eval_loss": 1.268411636352539,
+      "eval_runtime": 6.0899,
+      "eval_samples_per_second": 16.421,
+      "eval_steps_per_second": 2.135,
+      "step": 429
+    },
+    {
+      "epoch": 2.810457516339869,
+      "grad_norm": 0.5043578743934631,
+      "learning_rate": 1.853036072406436e-07,
+      "loss": 4.9906,
+      "step": 430
+    },
+    {
+      "epoch": 2.8758169934640523,
+      "grad_norm": 0.6804988384246826,
+      "learning_rate": 7.972979063091468e-08,
+      "loss": 5.096,
+      "step": 440
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.6172552704811096,
+      "learning_rate": 1.7914160085782116e-08,
+      "loss": 5.0006,
+      "step": 450
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 459,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 39,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 10,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.087892566070788e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c33d52a15e06892e3c746f1be422f96f3a3926e9f7a23687482125db6fcbc04
+size 5560