End of training

README.md

@@ -0,0 +1,166 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: heegyu/WizardVicuna-open-llama-3b-v2
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: b6b4f58d-74b4-47d2-b130-62df0ddc5472
+  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: heegyu/WizardVicuna-open-llama-3b-v2
+bf16: true
+chat_template: llama3
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 146d47cdb6b05b08_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/146d47cdb6b05b08_train_data.json
+  type:
+    field_input: chosen
+    field_instruction: question
+    field_output: rejected
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 5
+eval_batch_size: 4
+eval_max_new_tokens: 128
+eval_steps: 50
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn56b1/b6b4f58d-74b4-47d2-b130-62df0ddc5472
+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: 32
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+max_steps: 100
+micro_batch_size: 4
+mlflow_experiment_name: /tmp/146d47cdb6b05b08_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+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: 50
+saves_per_epoch: null
+sequence_len: 1024
+special_tokens:
+  pad_token: </s>
+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: b6b4f58d-74b4-47d2-b130-62df0ddc5472
+wandb_project: god
+wandb_run: kikf
+wandb_runid: b6b4f58d-74b4-47d2-b130-62df0ddc5472
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# b6b4f58d-74b4-47d2-b130-62df0ddc5472
+
+This model is a fine-tuned version of [heegyu/WizardVicuna-open-llama-3b-v2](https://huggingface.co/heegyu/WizardVicuna-open-llama-3b-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2729
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.3458        | 0.0052 | 1    | 1.5109          |
+| 1.2864        | 0.2597 | 50   | 1.3044          |
+| 1.2382        | 0.5195 | 100  | 1.2729          |
+
+
+### 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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "heegyu/WizardVicuna-open-llama-3b-v2",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_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:e2c3ed34353a5e508c157ec5e82e7d90400a9eaeaaa6919a2dd4890b731604cb
+size 101834682

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c79515e3ce668408a3bf1b111489815ae9224ef68a571a3cccbd2d370e1970
+size 101752088

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "heegyu/WizardVicuna-open-llama-3b-v2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 100,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: heegyu/WizardVicuna-open-llama-3b-v2
+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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "heegyu/WizardVicuna-open-llama-3b-v2",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_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:c7c79515e3ce668408a3bf1b111489815ae9224ef68a571a3cccbd2d370e1970
+size 101752088

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf564f42eef836687cde3d55983b02eac0b038838386351a2d9d1495e9a6a50a
+size 203713238

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47db969b740437cf68ce089f2454060fc800a919552a10ed97bf15cad8a983d
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
+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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "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>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,766 @@
+{
+  "best_metric": 1.2729405164718628,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.5194805194805194,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005194805194805195,
+      "grad_norm": 0.4177940785884857,
+      "learning_rate": 1e-05,
+      "loss": 1.3458,
+      "step": 1
+    },
+    {
+      "epoch": 0.005194805194805195,
+      "eval_loss": 1.5109460353851318,
+      "eval_runtime": 31.5573,
+      "eval_samples_per_second": 5.165,
+      "eval_steps_per_second": 1.299,
+      "step": 1
+    },
+    {
+      "epoch": 0.01038961038961039,
+      "grad_norm": 0.40045127272605896,
+      "learning_rate": 2e-05,
+      "loss": 1.4257,
+      "step": 2
+    },
+    {
+      "epoch": 0.015584415584415584,
+      "grad_norm": 0.3874695301055908,
+      "learning_rate": 3e-05,
+      "loss": 1.4884,
+      "step": 3
+    },
+    {
+      "epoch": 0.02077922077922078,
+      "grad_norm": 0.34974992275238037,
+      "learning_rate": 4e-05,
+      "loss": 1.361,
+      "step": 4
+    },
+    {
+      "epoch": 0.025974025974025976,
+      "grad_norm": 0.35995498299598694,
+      "learning_rate": 5e-05,
+      "loss": 1.2804,
+      "step": 5
+    },
+    {
+      "epoch": 0.03116883116883117,
+      "grad_norm": 0.3070196807384491,
+      "learning_rate": 6e-05,
+      "loss": 1.305,
+      "step": 6
+    },
+    {
+      "epoch": 0.03636363636363636,
+      "grad_norm": 0.3768017292022705,
+      "learning_rate": 7e-05,
+      "loss": 1.3585,
+      "step": 7
+    },
+    {
+      "epoch": 0.04155844155844156,
+      "grad_norm": 0.30300381779670715,
+      "learning_rate": 8e-05,
+      "loss": 1.2692,
+      "step": 8
+    },
+    {
+      "epoch": 0.046753246753246755,
+      "grad_norm": 0.33119237422943115,
+      "learning_rate": 9e-05,
+      "loss": 1.3356,
+      "step": 9
+    },
+    {
+      "epoch": 0.05194805194805195,
+      "grad_norm": 0.28153595328330994,
+      "learning_rate": 0.0001,
+      "loss": 1.1681,
+      "step": 10
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 0.4325452148914337,
+      "learning_rate": 9.99695413509548e-05,
+      "loss": 1.3646,
+      "step": 11
+    },
+    {
+      "epoch": 0.06233766233766234,
+      "grad_norm": 0.43212607502937317,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.3236,
+      "step": 12
+    },
+    {
+      "epoch": 0.06753246753246753,
+      "grad_norm": 0.39351075887680054,
+      "learning_rate": 9.972609476841367e-05,
+      "loss": 1.2301,
+      "step": 13
+    },
+    {
+      "epoch": 0.07272727272727272,
+      "grad_norm": 0.3731982409954071,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 1.2337,
+      "step": 14
+    },
+    {
+      "epoch": 0.07792207792207792,
+      "grad_norm": 0.34622952342033386,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.2392,
+      "step": 15
+    },
+    {
+      "epoch": 0.08311688311688312,
+      "grad_norm": 0.373747855424881,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.3094,
+      "step": 16
+    },
+    {
+      "epoch": 0.08831168831168831,
+      "grad_norm": 0.3230806291103363,
+      "learning_rate": 9.851478631379982e-05,
+      "loss": 1.1379,
+      "step": 17
+    },
+    {
+      "epoch": 0.09350649350649351,
+      "grad_norm": 0.36096540093421936,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 1.3651,
+      "step": 18
+    },
+    {
+      "epoch": 0.0987012987012987,
+      "grad_norm": 0.35373595356941223,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.4041,
+      "step": 19
+    },
+    {
+      "epoch": 0.1038961038961039,
+      "grad_norm": 0.3317319452762604,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 1.3334,
+      "step": 20
+    },
+    {
+      "epoch": 0.10909090909090909,
+      "grad_norm": 0.35586485266685486,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 1.3277,
+      "step": 21
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 0.3231983780860901,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.2227,
+      "step": 22
+    },
+    {
+      "epoch": 0.11948051948051948,
+      "grad_norm": 0.3345981538295746,
+      "learning_rate": 9.493970231495835e-05,
+      "loss": 1.2484,
+      "step": 23
+    },
+    {
+      "epoch": 0.12467532467532468,
+      "grad_norm": 0.3658851385116577,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 1.2305,
+      "step": 24
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 0.37067246437072754,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.131,
+      "step": 25
+    },
+    {
+      "epoch": 0.13506493506493505,
+      "grad_norm": 0.40390706062316895,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.289,
+      "step": 26
+    },
+    {
+      "epoch": 0.14025974025974025,
+      "grad_norm": 0.3715671896934509,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.1788,
+      "step": 27
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 0.3955548405647278,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.4516,
+      "step": 28
+    },
+    {
+      "epoch": 0.15064935064935064,
+      "grad_norm": 0.4545679986476898,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.5039,
+      "step": 29
+    },
+    {
+      "epoch": 0.15584415584415584,
+      "grad_norm": 0.39818987250328064,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.2946,
+      "step": 30
+    },
+    {
+      "epoch": 0.16103896103896104,
+      "grad_norm": 0.4657442271709442,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.4087,
+      "step": 31
+    },
+    {
+      "epoch": 0.16623376623376623,
+      "grad_norm": 0.47173669934272766,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.2468,
+      "step": 32
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.40042179822921753,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.1191,
+      "step": 33
+    },
+    {
+      "epoch": 0.17662337662337663,
+      "grad_norm": 0.4369649887084961,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.3715,
+      "step": 34
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.47712573409080505,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.2312,
+      "step": 35
+    },
+    {
+      "epoch": 0.18701298701298702,
+      "grad_norm": 0.5139972567558289,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.5135,
+      "step": 36
+    },
+    {
+      "epoch": 0.19220779220779222,
+      "grad_norm": 0.4982706904411316,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.2006,
+      "step": 37
+    },
+    {
+      "epoch": 0.1974025974025974,
+      "grad_norm": 0.485422283411026,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.3658,
+      "step": 38
+    },
+    {
+      "epoch": 0.2025974025974026,
+      "grad_norm": 0.49507665634155273,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.2338,
+      "step": 39
+    },
+    {
+      "epoch": 0.2077922077922078,
+      "grad_norm": 0.5692687034606934,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.4821,
+      "step": 40
+    },
+    {
+      "epoch": 0.21298701298701297,
+      "grad_norm": 0.4980921149253845,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.215,
+      "step": 41
+    },
+    {
+      "epoch": 0.21818181818181817,
+      "grad_norm": 0.6296183466911316,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.4862,
+      "step": 42
+    },
+    {
+      "epoch": 0.22337662337662337,
+      "grad_norm": 0.6405119895935059,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.2837,
+      "step": 43
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.7146792411804199,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.4082,
+      "step": 44
+    },
+    {
+      "epoch": 0.23376623376623376,
+      "grad_norm": 0.8238335251808167,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.6744,
+      "step": 45
+    },
+    {
+      "epoch": 0.23896103896103896,
+      "grad_norm": 0.8879733681678772,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.4372,
+      "step": 46
+    },
+    {
+      "epoch": 0.24415584415584415,
+      "grad_norm": 0.992831826210022,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.7714,
+      "step": 47
+    },
+    {
+      "epoch": 0.24935064935064935,
+      "grad_norm": 1.3995647430419922,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.5566,
+      "step": 48
+    },
+    {
+      "epoch": 0.2545454545454545,
+      "grad_norm": 0.34774672985076904,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.2085,
+      "step": 49
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 0.3489333391189575,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.2864,
+      "step": 50
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "eval_loss": 1.3044037818908691,
+      "eval_runtime": 31.1095,
+      "eval_samples_per_second": 5.24,
+      "eval_steps_per_second": 1.318,
+      "step": 50
+    },
+    {
+      "epoch": 0.2649350649350649,
+      "grad_norm": 0.33038291335105896,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.2938,
+      "step": 51
+    },
+    {
+      "epoch": 0.2701298701298701,
+      "grad_norm": 0.32780855894088745,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.1114,
+      "step": 52
+    },
+    {
+      "epoch": 0.2753246753246753,
+      "grad_norm": 0.32513588666915894,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.2657,
+      "step": 53
+    },
+    {
+      "epoch": 0.2805194805194805,
+      "grad_norm": 0.31361356377601624,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.2757,
+      "step": 54
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.3155638575553894,
+      "learning_rate": 5e-05,
+      "loss": 1.2063,
+      "step": 55
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.31585606932640076,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.0867,
+      "step": 56
+    },
+    {
+      "epoch": 0.2961038961038961,
+      "grad_norm": 0.3095378577709198,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.1155,
+      "step": 57
+    },
+    {
+      "epoch": 0.3012987012987013,
+      "grad_norm": 0.31880173087120056,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.3034,
+      "step": 58
+    },
+    {
+      "epoch": 0.3064935064935065,
+      "grad_norm": 0.3153369724750519,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.1679,
+      "step": 59
+    },
+    {
+      "epoch": 0.3116883116883117,
+      "grad_norm": 0.3115677535533905,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.1694,
+      "step": 60
+    },
+    {
+      "epoch": 0.3168831168831169,
+      "grad_norm": 0.3476245403289795,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.2466,
+      "step": 61
+    },
+    {
+      "epoch": 0.3220779220779221,
+      "grad_norm": 0.3204329311847687,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.2314,
+      "step": 62
+    },
+    {
+      "epoch": 0.32727272727272727,
+      "grad_norm": 0.31050464510917664,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.1565,
+      "step": 63
+    },
+    {
+      "epoch": 0.33246753246753247,
+      "grad_norm": 0.3489195704460144,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.231,
+      "step": 64
+    },
+    {
+      "epoch": 0.33766233766233766,
+      "grad_norm": 0.31092599034309387,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.9795,
+      "step": 65
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.3266049325466156,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.1326,
+      "step": 66
+    },
+    {
+      "epoch": 0.34805194805194806,
+      "grad_norm": 0.34862658381462097,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.0544,
+      "step": 67
+    },
+    {
+      "epoch": 0.35324675324675325,
+      "grad_norm": 0.3720819056034088,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.2346,
+      "step": 68
+    },
+    {
+      "epoch": 0.35844155844155845,
+      "grad_norm": 0.3748229444026947,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.2632,
+      "step": 69
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.3992089629173279,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2955,
+      "step": 70
+    },
+    {
+      "epoch": 0.36883116883116884,
+      "grad_norm": 0.3803309500217438,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.137,
+      "step": 71
+    },
+    {
+      "epoch": 0.37402597402597404,
+      "grad_norm": 0.41548168659210205,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.3413,
+      "step": 72
+    },
+    {
+      "epoch": 0.37922077922077924,
+      "grad_norm": 0.4588744044303894,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4306,
+      "step": 73
+    },
+    {
+      "epoch": 0.38441558441558443,
+      "grad_norm": 0.4805556833744049,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.277,
+      "step": 74
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 0.4144364595413208,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.1136,
+      "step": 75
+    },
+    {
+      "epoch": 0.3948051948051948,
+      "grad_norm": 0.46915677189826965,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.2499,
+      "step": 76
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5677196979522705,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.3259,
+      "step": 77
+    },
+    {
+      "epoch": 0.4051948051948052,
+      "grad_norm": 0.5241764783859253,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.2467,
+      "step": 78
+    },
+    {
+      "epoch": 0.4103896103896104,
+      "grad_norm": 0.5175052285194397,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.2434,
+      "step": 79
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "grad_norm": 0.47252026200294495,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.261,
+      "step": 80
+    },
+    {
+      "epoch": 0.42077922077922075,
+      "grad_norm": 0.49494829773902893,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.2451,
+      "step": 81
+    },
+    {
+      "epoch": 0.42597402597402595,
+      "grad_norm": 0.5081787109375,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2701,
+      "step": 82
+    },
+    {
+      "epoch": 0.43116883116883115,
+      "grad_norm": 0.501038134098053,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.2223,
+      "step": 83
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.5236621499061584,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.3133,
+      "step": 84
+    },
+    {
+      "epoch": 0.44155844155844154,
+      "grad_norm": 0.5346829295158386,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2814,
+      "step": 85
+    },
+    {
+      "epoch": 0.44675324675324674,
+      "grad_norm": 0.602837085723877,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.3313,
+      "step": 86
+    },
+    {
+      "epoch": 0.45194805194805193,
+      "grad_norm": 0.628185510635376,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.3623,
+      "step": 87
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.6955432891845703,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.3763,
+      "step": 88
+    },
+    {
+      "epoch": 0.4623376623376623,
+      "grad_norm": 0.6017211675643921,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.2264,
+      "step": 89
+    },
+    {
+      "epoch": 0.4675324675324675,
+      "grad_norm": 0.7660609483718872,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.3396,
+      "step": 90
+    },
+    {
+      "epoch": 0.4727272727272727,
+      "grad_norm": 0.6864474415779114,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.3113,
+      "step": 91
+    },
+    {
+      "epoch": 0.4779220779220779,
+      "grad_norm": 0.8158310055732727,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4984,
+      "step": 92
+    },
+    {
+      "epoch": 0.4831168831168831,
+      "grad_norm": 0.8039913177490234,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.3747,
+      "step": 93
+    },
+    {
+      "epoch": 0.4883116883116883,
+      "grad_norm": 0.9546723961830139,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5949,
+      "step": 94
+    },
+    {
+      "epoch": 0.4935064935064935,
+      "grad_norm": 1.4390336275100708,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.7096,
+      "step": 95
+    },
+    {
+      "epoch": 0.4987012987012987,
+      "grad_norm": 1.3720232248306274,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.923,
+      "step": 96
+    },
+    {
+      "epoch": 0.5038961038961038,
+      "grad_norm": 0.26757583022117615,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.0475,
+      "step": 97
+    },
+    {
+      "epoch": 0.509090909090909,
+      "grad_norm": 0.30529433488845825,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.201,
+      "step": 98
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.2671392261981964,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0222,
+      "step": 99
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 0.2957288920879364,
+      "learning_rate": 0.0,
+      "loss": 1.2382,
+      "step": 100
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "eval_loss": 1.2729405164718628,
+      "eval_runtime": 31.7043,
+      "eval_samples_per_second": 5.141,
+      "eval_steps_per_second": 1.293,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "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": 5.589344683819008e+16,
+  "train_batch_size": 4,
+  "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:cd8dcd221ba002cbd995a7a95a6556a839af177471ad1c83bc00b81aaab99a7a
+size 6840

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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "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>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8dcd221ba002cbd995a7a95a6556a839af177471ad1c83bc00b81aaab99a7a
+size 6840