Duplicate from sn56c1/b18b973c-a023-487c-8fe4-fe23cfb905b5

Co-authored-by: Tracy Zhang <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,152 @@
+---
+library_name: peft
+license: other
+base_model: facebook/opt-125m
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: b18b973c-a023-487c-8fe4-fe23cfb905b5
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: facebook/opt-125m
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - fa45899a4384c2c8_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/fa45899a4384c2c8_train_data.json
+  type:
+    field_instruction: instruction
+    field_output: output
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: 1
+eval_max_new_tokens: 128
+eval_steps: 25
+eval_table_size: null
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn56c1/b18b973c-a023-487c-8fe4-fe23cfb905b5
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: cosine
+max_steps: 50
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/fa45899a4384c2c8_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 25
+sequence_len: 2048
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: b18b973c-a023-487c-8fe4-fe23cfb905b5
+wandb_project: god
+wandb_run: mbcv
+wandb_runid: b18b973c-a023-487c-8fe4-fe23cfb905b5
+warmup_ratio: 0.05
+weight_decay: 0.01
+xformers_attention: true
+
+```
+
+</details><br>
+
+# b18b973c-a023-487c-8fe4-fe23cfb905b5
+
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6521
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- training_steps: 41
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 36.282        | 0.0748 | 1    | 3.0608          |
+| 38.2965       | 1.8692 | 25   | 2.6521          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-125m",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "fc1",
+    "fc2",
+    "out_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:966f004f9a3cba0fa5e1a14b7ceaefa5d7fe3076a9f4f3abce0f1acf1211cc47
+size 21286218

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75e68844f2c991ee6f599b68047dc738d6ee1d3089780157ee2ffc84b90d099
+size 21253336

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "facebook/opt-125m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: facebook/opt-125m
+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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-125m",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "fc1",
+    "fc2",
+    "out_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814c8d4998aaec2e2a055d6cfa7026e2f6db1c34857d064ccbf26e43cb336e8e
+size 21253336

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3071895ea7f3d1a7e05325ff1377cc7c6e70278469ebcd903890a53b078f3e
+size 42588474

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00fe1d6a510ecd3ca31281ecc6b907cf1be68ad6c26c3e7e6c32205add64ea2a
+size 14960

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c47d63d5502eb42da4031d0d868b5fb5d45bdcf6deb692cc1b2b64f097265c
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5950d4e0aa8cce66e8e7bc53a74839c4b890608455d1319d1344f1bc7b42af42
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dc65bc65af76a2cda267ab46a1c1fdbc4ce93d8e97a020454d933c2ffa6ca8
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84fc982e8229d2121603832a24f4c07bbdbf63985ed1d38e11762164a04dad3b
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,345 @@
+{
+  "best_metric": 2.6521220207214355,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 3.0654205607476634,
+  "eval_steps": 25,
+  "global_step": 41,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 12.758352279663086,
+      "learning_rate": 5e-05,
+      "loss": 36.282,
+      "step": 1
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "eval_loss": 3.060811758041382,
+      "eval_runtime": 0.217,
+      "eval_samples_per_second": 414.771,
+      "eval_steps_per_second": 55.303,
+      "step": 1
+    },
+    {
+      "epoch": 0.14953271028037382,
+      "grad_norm": 20.263750076293945,
+      "learning_rate": 0.0001,
+      "loss": 42.7203,
+      "step": 2
+    },
+    {
+      "epoch": 0.22429906542056074,
+      "grad_norm": 57.88479995727539,
+      "learning_rate": 9.983786540671051e-05,
+      "loss": 55.9926,
+      "step": 3
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 44.08774948120117,
+      "learning_rate": 9.935251313189564e-05,
+      "loss": 46.6793,
+      "step": 4
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 11.229438781738281,
+      "learning_rate": 9.85470908713026e-05,
+      "loss": 39.1964,
+      "step": 5
+    },
+    {
+      "epoch": 0.4485981308411215,
+      "grad_norm": 39.31789016723633,
+      "learning_rate": 9.742682209735727e-05,
+      "loss": 49.6059,
+      "step": 6
+    },
+    {
+      "epoch": 0.5233644859813084,
+      "grad_norm": 60.52045822143555,
+      "learning_rate": 9.599897218294122e-05,
+      "loss": 53.2442,
+      "step": 7
+    },
+    {
+      "epoch": 0.5981308411214953,
+      "grad_norm": 12.900232315063477,
+      "learning_rate": 9.42728012826605e-05,
+      "loss": 37.8815,
+      "step": 8
+    },
+    {
+      "epoch": 0.6728971962616822,
+      "grad_norm": 21.519189834594727,
+      "learning_rate": 9.225950427718975e-05,
+      "loss": 44.2056,
+      "step": 9
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 56.32939529418945,
+      "learning_rate": 8.997213817017507e-05,
+      "loss": 51.4103,
+      "step": 10
+    },
+    {
+      "epoch": 0.822429906542056,
+      "grad_norm": 14.446544647216797,
+      "learning_rate": 8.742553740855506e-05,
+      "loss": 37.1102,
+      "step": 11
+    },
+    {
+      "epoch": 0.897196261682243,
+      "grad_norm": 17.83036231994629,
+      "learning_rate": 8.463621767547998e-05,
+      "loss": 41.9033,
+      "step": 12
+    },
+    {
+      "epoch": 0.9719626168224299,
+      "grad_norm": 46.029293060302734,
+      "learning_rate": 8.162226877976887e-05,
+      "loss": 54.8429,
+      "step": 13
+    },
+    {
+      "epoch": 1.0467289719626167,
+      "grad_norm": 17.31562614440918,
+      "learning_rate": 7.840323733655778e-05,
+      "loss": 38.5449,
+      "step": 14
+    },
+    {
+      "epoch": 1.1214953271028036,
+      "grad_norm": 15.410332679748535,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 38.6461,
+      "step": 15
+    },
+    {
+      "epoch": 1.1962616822429906,
+      "grad_norm": 18.735742568969727,
+      "learning_rate": 7.143462807015271e-05,
+      "loss": 43.017,
+      "step": 16
+    },
+    {
+      "epoch": 1.2710280373831775,
+      "grad_norm": 37.610233306884766,
+      "learning_rate": 6.773024435212678e-05,
+      "loss": 47.2818,
+      "step": 17
+    },
+    {
+      "epoch": 1.3457943925233644,
+      "grad_norm": 12.432938575744629,
+      "learning_rate": 6.391087319582264e-05,
+      "loss": 37.0608,
+      "step": 18
+    },
+    {
+      "epoch": 1.4205607476635513,
+      "grad_norm": 15.482471466064453,
+      "learning_rate": 6.0001284688802226e-05,
+      "loss": 43.5062,
+      "step": 19
+    },
+    {
+      "epoch": 1.4953271028037383,
+      "grad_norm": 44.31102752685547,
+      "learning_rate": 5.602683401276615e-05,
+      "loss": 48.2458,
+      "step": 20
+    },
+    {
+      "epoch": 1.5700934579439252,
+      "grad_norm": 10.056441307067871,
+      "learning_rate": 5.201329700547076e-05,
+      "loss": 35.6037,
+      "step": 21
+    },
+    {
+      "epoch": 1.644859813084112,
+      "grad_norm": 14.291549682617188,
+      "learning_rate": 4.798670299452926e-05,
+      "loss": 40.7725,
+      "step": 22
+    },
+    {
+      "epoch": 1.719626168224299,
+      "grad_norm": 35.73259353637695,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 47.5375,
+      "step": 23
+    },
+    {
+      "epoch": 1.794392523364486,
+      "grad_norm": 27.332090377807617,
+      "learning_rate": 3.9998715311197785e-05,
+      "loss": 40.5958,
+      "step": 24
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 12.312621116638184,
+      "learning_rate": 3.608912680417737e-05,
+      "loss": 38.2965,
+      "step": 25
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "eval_loss": 2.6521220207214355,
+      "eval_runtime": 0.2136,
+      "eval_samples_per_second": 421.387,
+      "eval_steps_per_second": 56.185,
+      "step": 25
+    },
+    {
+      "epoch": 1.9439252336448598,
+      "grad_norm": 24.132015228271484,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 45.587,
+      "step": 26
+    },
+    {
+      "epoch": 2.0186915887850465,
+      "grad_norm": 37.26287078857422,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 44.63,
+      "step": 27
+    },
+    {
+      "epoch": 2.0934579439252334,
+      "grad_norm": 8.607263565063477,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 35.3202,
+      "step": 28
+    },
+    {
+      "epoch": 2.1682242990654204,
+      "grad_norm": 15.418391227722168,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 40.6338,
+      "step": 29
+    },
+    {
+      "epoch": 2.2429906542056073,
+      "grad_norm": 45.875850677490234,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 48.1675,
+      "step": 30
+    },
+    {
+      "epoch": 2.317757009345794,
+      "grad_norm": 8.112244606018066,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 34.1341,
+      "step": 31
+    },
+    {
+      "epoch": 2.392523364485981,
+      "grad_norm": 11.951674461364746,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 38.6645,
+      "step": 32
+    },
+    {
+      "epoch": 2.467289719626168,
+      "grad_norm": 26.10127067565918,
+      "learning_rate": 1.0027861829824952e-05,
+      "loss": 46.5139,
+      "step": 33
+    },
+    {
+      "epoch": 2.542056074766355,
+      "grad_norm": 22.941789627075195,
+      "learning_rate": 7.740495722810271e-06,
+      "loss": 39.0511,
+      "step": 34
+    },
+    {
+      "epoch": 2.616822429906542,
+      "grad_norm": 10.500677108764648,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 38.4031,
+      "step": 35
+    },
+    {
+      "epoch": 2.691588785046729,
+      "grad_norm": 20.41301918029785,
+      "learning_rate": 4.001027817058789e-06,
+      "loss": 43.299,
+      "step": 36
+    },
+    {
+      "epoch": 2.7663551401869158,
+      "grad_norm": 41.006507873535156,
+      "learning_rate": 2.573177902642726e-06,
+      "loss": 46.7328,
+      "step": 37
+    },
+    {
+      "epoch": 2.8411214953271027,
+      "grad_norm": 9.30128002166748,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 37.2758,
+      "step": 38
+    },
+    {
+      "epoch": 2.9158878504672896,
+      "grad_norm": 15.678587913513184,
+      "learning_rate": 6.474868681043578e-07,
+      "loss": 41.8466,
+      "step": 39
+    },
+    {
+      "epoch": 2.9906542056074765,
+      "grad_norm": 43.43739318847656,
+      "learning_rate": 1.6213459328950352e-07,
+      "loss": 47.5823,
+      "step": 40
+    },
+    {
+      "epoch": 3.0654205607476634,
+      "grad_norm": 11.734439849853516,
+      "learning_rate": 0.0,
+      "loss": 35.6739,
+      "step": 41
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 41,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5827368409104384.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f524371b6c8148c4419329b5f0658c2967e17c8773af52e1db583dee68044c
+size 6776

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f524371b6c8148c4419329b5f0658c2967e17c8773af52e1db583dee68044c
+size 6776