Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-4B-Chat
+model-index:
+- name: train_2024-03-10-09-12-31
+  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. -->
+
+# train_2024-03-10-09-12-31
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-4B-Chat](https://huggingface.co/Qwen/Qwen1.5-4B-Chat) on the gozaru_ja dataset.
+
+## 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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-4B-Chat",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270a07b6c18e0564fa240633abc032ffc3e005c2cac4528674e69a8aedccdd7e
+size 62660744

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.8196016863370552,
+    "train_runtime": 2685.2386,
+    "train_samples_per_second": 3.724,
+    "train_steps_per_second": 0.116
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-4B-Chat
+---
+
+# 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 0.9.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-4B-Chat",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8fda1647665477112caad129624c0b5af356a5bd110ca7e95a38d62b5ebf68
+size 62660744

checkpoint-100/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4e4404d8ddd2ef1eb23479fc75d861482b91972ac9743123184fc3e6f5867f
+size 125644962

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fad36a1f296454260218ccba8fbf20d1ecfc1595b507bd9ab4a97741148b567
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db19d5f82c8e209abcc21a69b82a57aeda11c164a7ca57df1501e44c35224e2b
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8396336436271667,
+      "learning_rate": 0.00019987329060020616,
+      "loss": 2.8923,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.7428969740867615,
+      "learning_rate": 0.00019949348350626456,
+      "loss": 2.0944,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5937550067901611,
+      "learning_rate": 0.00019886154122075343,
+      "loss": 2.0323,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4460415542125702,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 1.9436,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4390580952167511,
+      "learning_rate": 0.00019684829181681234,
+      "loss": 2.0292,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.43469828367233276,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 1.9654,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.48699721693992615,
+      "learning_rate": 0.0001938539372689649,
+      "loss": 1.9041,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5205313563346863,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 1.8992,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5224802494049072,
+      "learning_rate": 0.00018990881137654258,
+      "loss": 1.8393,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5004997849464417,
+      "learning_rate": 0.0001875918325566888,
+      "loss": 1.615,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5422343611717224,
+      "learning_rate": 0.00018505287956623297,
+      "loss": 1.9873,
+      "step": 55
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.47483357787132263,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 1.9264,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4191422164440155,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 1.828,
+      "step": 65
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.41457584500312805,
+      "learning_rate": 0.00017617123081773591,
+      "loss": 1.8083,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.524440348148346,
+      "learning_rate": 0.00017281409538757883,
+      "loss": 1.8268,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5396173000335693,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 1.7587,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.5633752942085266,
+      "learning_rate": 0.0001655552259402295,
+      "loss": 1.7939,
+      "step": 85
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5931205153465271,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 1.848,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.677586019039154,
+      "learning_rate": 0.00015763226042909455,
+      "loss": 1.7407,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5012004971504211,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 1.8559,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 4.552629939339264e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33f3d22ffe059813829af0f30a0a876287dc508c7f1cd67423455339441d050
+size 5112

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-4B-Chat
+---
+
+# 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 0.9.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-4B-Chat",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c3012996b1ea870bd7abf7dcf25aaeffbb7bf0d7828283709e7a1888e8b55a
+size 62660744

checkpoint-200/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5afe272e18d91cb02da9ea0ed21f2a7caff5b9616ddc742fe11bcc42787caf
+size 125644962

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391d503f9a0e3d1e237424a616a8f21b36afea21361b2bbb40170a49878dc3dc
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1672929cbd1b23a6c0955975e4aa190f3ae3bcbc48783ce2a380161c2e528bc5
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,301 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.64,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8396336436271667,
+      "learning_rate": 0.00019987329060020616,
+      "loss": 2.8923,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.7428969740867615,
+      "learning_rate": 0.00019949348350626456,
+      "loss": 2.0944,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5937550067901611,
+      "learning_rate": 0.00019886154122075343,
+      "loss": 2.0323,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4460415542125702,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 1.9436,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4390580952167511,
+      "learning_rate": 0.00019684829181681234,
+      "loss": 2.0292,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.43469828367233276,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 1.9654,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.48699721693992615,
+      "learning_rate": 0.0001938539372689649,
+      "loss": 1.9041,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5205313563346863,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 1.8992,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5224802494049072,
+      "learning_rate": 0.00018990881137654258,
+      "loss": 1.8393,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5004997849464417,
+      "learning_rate": 0.0001875918325566888,
+      "loss": 1.615,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5422343611717224,
+      "learning_rate": 0.00018505287956623297,
+      "loss": 1.9873,
+      "step": 55
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.47483357787132263,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 1.9264,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4191422164440155,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 1.828,
+      "step": 65
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.41457584500312805,
+      "learning_rate": 0.00017617123081773591,
+      "loss": 1.8083,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.524440348148346,
+      "learning_rate": 0.00017281409538757883,
+      "loss": 1.8268,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5396173000335693,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 1.7587,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.5633752942085266,
+      "learning_rate": 0.0001655552259402295,
+      "loss": 1.7939,
+      "step": 85
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5931205153465271,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 1.848,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.677586019039154,
+      "learning_rate": 0.00015763226042909455,
+      "loss": 1.7407,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5012004971504211,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 1.8559,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.5996416807174683,
+      "learning_rate": 0.00014912546110838775,
+      "loss": 1.8363,
+      "step": 105
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5592181086540222,
+      "learning_rate": 0.00014467984645016258,
+      "loss": 1.6798,
+      "step": 110
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.6498942971229553,
+      "learning_rate": 0.00014012100466140578,
+      "loss": 1.6868,
+      "step": 115
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5339984893798828,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 1.8213,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5681377649307251,
+      "learning_rate": 0.00013071010920229909,
+      "loss": 1.7561,
+      "step": 125
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5253719687461853,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 1.7834,
+      "step": 130
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.5420334935188293,
+      "learning_rate": 0.00012098811020648475,
+      "loss": 1.9342,
+      "step": 135
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.6371601819992065,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 1.8081,
+      "step": 140
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5578604340553284,
+      "learning_rate": 0.000111053494730832,
+      "loss": 1.7449,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.768509030342102,
+      "learning_rate": 0.00010603784974222861,
+      "loss": 1.8202,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.627295970916748,
+      "learning_rate": 0.00010100690370728755,
+      "loss": 1.7587,
+      "step": 155
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.6519939303398132,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 1.8827,
+      "step": 160
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.6148818135261536,
+      "learning_rate": 9.095011241703623e-05,
+      "loss": 1.8022,
+      "step": 165
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.5009266138076782,
+      "learning_rate": 8.594975296149076e-05,
+      "loss": 1.7515,
+      "step": 170
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5753130316734314,
+      "learning_rate": 8.098499947332934e-05,
+      "loss": 1.7027,
+      "step": 175
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.5501881241798401,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 1.7445,
+      "step": 180
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.6279743909835815,
+      "learning_rate": 7.121251475752539e-05,
+      "loss": 1.7094,
+      "step": 185
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5455606579780579,
+      "learning_rate": 6.642954884333955e-05,
+      "loss": 1.7047,
+      "step": 190
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5445593595504761,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.6086,
+      "step": 195
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6656392812728882,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 1.7098,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 9.200724451688448e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33f3d22ffe059813829af0f30a0a876287dc508c7f1cd67423455339441d050
+size 5112

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-4B-Chat
+---
+
+# 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 0.9.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-4B-Chat",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5ab8d68941e9b29a8320eacac2d10a77ca9b45f8fe16cbc896da3315c95a6d
+size 62660744

checkpoint-300/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9e59524a8445793ced8e0850af71053a643673b66e407c4c17e0132e22859f
+size 125644962

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:035984ab7df79a07d92510cec4e76931bd9a53ba3c561ac87bf6cf07b577f197
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d0a8fa4f4f33edaee237d6f99d4cc867fb2e10c314d06eddcbd7defb0675e9
+size 1064

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.96,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8396336436271667,
+      "learning_rate": 0.00019987329060020616,
+      "loss": 2.8923,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.7428969740867615,
+      "learning_rate": 0.00019949348350626456,
+      "loss": 2.0944,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5937550067901611,
+      "learning_rate": 0.00019886154122075343,
+      "loss": 2.0323,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4460415542125702,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 1.9436,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4390580952167511,
+      "learning_rate": 0.00019684829181681234,
+      "loss": 2.0292,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.43469828367233276,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 1.9654,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.48699721693992615,
+      "learning_rate": 0.0001938539372689649,
+      "loss": 1.9041,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5205313563346863,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 1.8992,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5224802494049072,
+      "learning_rate": 0.00018990881137654258,
+      "loss": 1.8393,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5004997849464417,
+      "learning_rate": 0.0001875918325566888,
+      "loss": 1.615,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5422343611717224,
+      "learning_rate": 0.00018505287956623297,
+      "loss": 1.9873,
+      "step": 55
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.47483357787132263,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 1.9264,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4191422164440155,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 1.828,
+      "step": 65
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.41457584500312805,
+      "learning_rate": 0.00017617123081773591,
+      "loss": 1.8083,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.524440348148346,
+      "learning_rate": 0.00017281409538757883,
+      "loss": 1.8268,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5396173000335693,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 1.7587,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.5633752942085266,
+      "learning_rate": 0.0001655552259402295,
+      "loss": 1.7939,
+      "step": 85
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5931205153465271,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 1.848,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.677586019039154,
+      "learning_rate": 0.00015763226042909455,
+      "loss": 1.7407,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5012004971504211,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 1.8559,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.5996416807174683,
+      "learning_rate": 0.00014912546110838775,
+      "loss": 1.8363,
+      "step": 105
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5592181086540222,
+      "learning_rate": 0.00014467984645016258,
+      "loss": 1.6798,
+      "step": 110
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.6498942971229553,
+      "learning_rate": 0.00014012100466140578,
+      "loss": 1.6868,
+      "step": 115
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5339984893798828,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 1.8213,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5681377649307251,
+      "learning_rate": 0.00013071010920229909,
+      "loss": 1.7561,
+      "step": 125
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5253719687461853,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 1.7834,
+      "step": 130
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.5420334935188293,
+      "learning_rate": 0.00012098811020648475,
+      "loss": 1.9342,
+      "step": 135
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.6371601819992065,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 1.8081,
+      "step": 140
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5578604340553284,
+      "learning_rate": 0.000111053494730832,
+      "loss": 1.7449,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.768509030342102,
+      "learning_rate": 0.00010603784974222861,
+      "loss": 1.8202,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.627295970916748,
+      "learning_rate": 0.00010100690370728755,
+      "loss": 1.7587,
+      "step": 155
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.6519939303398132,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 1.8827,
+      "step": 160
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.6148818135261536,
+      "learning_rate": 9.095011241703623e-05,
+      "loss": 1.8022,
+      "step": 165
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.5009266138076782,
+      "learning_rate": 8.594975296149076e-05,
+      "loss": 1.7515,
+      "step": 170
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5753130316734314,
+      "learning_rate": 8.098499947332934e-05,
+      "loss": 1.7027,
+      "step": 175
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.5501881241798401,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 1.7445,
+      "step": 180
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.6279743909835815,
+      "learning_rate": 7.121251475752539e-05,
+      "loss": 1.7094,
+      "step": 185
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5455606579780579,
+      "learning_rate": 6.642954884333955e-05,
+      "loss": 1.7047,
+      "step": 190
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5445593595504761,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.6086,
+      "step": 195
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6656392812728882,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 1.7098,
+      "step": 200
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.5549783706665039,
+      "learning_rate": 5.263846971020108e-05,
+      "loss": 1.7766,
+      "step": 205
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.594687819480896,
+      "learning_rate": 4.826621858223431e-05,
+      "loss": 1.9863,
+      "step": 210
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.5940021276473999,
+      "learning_rate": 4.40250705821178e-05,
+      "loss": 1.7957,
+      "step": 215
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.6612168550491333,
+      "learning_rate": 3.99257735762021e-05,
+      "loss": 1.7848,
+      "step": 220
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5535335540771484,
+      "learning_rate": 3.597871595375121e-05,
+      "loss": 1.8688,
+      "step": 225
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.607822597026825,
+      "learning_rate": 3.219390030081091e-05,
+      "loss": 1.6451,
+      "step": 230
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6583452820777893,
+      "learning_rate": 2.858091805177554e-05,
+      "loss": 1.8795,
+      "step": 235
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.5893087983131409,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 1.7631,
+      "step": 240
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.5828584432601929,
+      "learning_rate": 2.1906619009284257e-05,
+      "loss": 1.7843,
+      "step": 245
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5105574727058411,
+      "learning_rate": 1.8862216144342692e-05,
+      "loss": 1.7854,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.6286787390708923,
+      "learning_rate": 1.6023431677260214e-05,
+      "loss": 1.5676,
+      "step": 255
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.5752671957015991,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.6083,
+      "step": 260
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.5867213606834412,
+      "learning_rate": 1.0990954684091558e-05,
+      "loss": 1.8291,
+      "step": 265
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.6025935411453247,
+      "learning_rate": 8.810015400790994e-06,
+      "loss": 1.7606,
+      "step": 270
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.5295992493629456,
+      "learning_rate": 6.860168681805945e-06,
+      "loss": 1.7076,
+      "step": 275
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.6831830143928528,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.706,
+      "step": 280
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.6414029002189636,
+      "learning_rate": 3.6729198952483724e-06,
+      "loss": 1.7685,
+      "step": 285
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.5466156601905823,
+      "learning_rate": 2.4435949152906145e-06,
+      "loss": 1.7422,
+      "step": 290
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7220910787582397,
+      "learning_rate": 1.4614962060194304e-06,
+      "loss": 1.8109,
+      "step": 295
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6633021235466003,
+      "learning_rate": 7.291125901946027e-07,
+      "loss": 1.7055,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1.3827390944772096e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33f3d22ffe059813829af0f30a0a876287dc508c7f1cd67423455339441d050
+size 5112

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.8196016863370552,
+    "train_runtime": 2685.2386,
+    "train_samples_per_second": 3.724,
+    "train_steps_per_second": 0.116
+}

trainer_log.jsonl

@@ -0,0 +1,63 @@
+{"current_steps": 5, "total_steps": 312, "loss": 2.8923, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019987329060020616, "epoch": 0.02, "percentage": 1.6, "elapsed_time": "0:00:44", "remaining_time": "0:45:07"}
+{"current_steps": 10, "total_steps": 312, "loss": 2.0944, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019949348350626456, "epoch": 0.03, "percentage": 3.21, "elapsed_time": "0:01:26", "remaining_time": "0:43:22"}
+{"current_steps": 15, "total_steps": 312, "loss": 2.0323, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019886154122075343, "epoch": 0.05, "percentage": 4.81, "elapsed_time": "0:02:12", "remaining_time": "0:43:39"}
+{"current_steps": 20, "total_steps": 312, "loss": 1.9436, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019797906520422677, "epoch": 0.06, "percentage": 6.41, "elapsed_time": "0:02:57", "remaining_time": "0:43:14"}
+{"current_steps": 25, "total_steps": 312, "loss": 2.0292, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019684829181681234, "epoch": 0.08, "percentage": 8.01, "elapsed_time": "0:03:41", "remaining_time": "0:42:24"}
+{"current_steps": 30, "total_steps": 312, "loss": 1.9654, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019547208665085457, "epoch": 0.1, "percentage": 9.62, "elapsed_time": "0:04:18", "remaining_time": "0:40:33"}
+{"current_steps": 35, "total_steps": 312, "loss": 1.9041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001938539372689649, "epoch": 0.11, "percentage": 11.22, "elapsed_time": "0:04:58", "remaining_time": "0:39:18"}
+{"current_steps": 40, "total_steps": 312, "loss": 1.8992, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019199794436588243, "epoch": 0.13, "percentage": 12.82, "elapsed_time": "0:05:39", "remaining_time": "0:38:30"}
+{"current_steps": 45, "total_steps": 312, "loss": 1.8393, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018990881137654258, "epoch": 0.14, "percentage": 14.42, "elapsed_time": "0:06:24", "remaining_time": "0:38:02"}
+{"current_steps": 50, "total_steps": 312, "loss": 1.615, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001875918325566888, "epoch": 0.16, "percentage": 16.03, "elapsed_time": "0:07:08", "remaining_time": "0:37:27"}
+{"current_steps": 55, "total_steps": 312, "loss": 1.9873, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018505287956623297, "epoch": 0.18, "percentage": 17.63, "elapsed_time": "0:07:48", "remaining_time": "0:36:29"}
+{"current_steps": 60, "total_steps": 312, "loss": 1.9264, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018229838658936564, "epoch": 0.19, "percentage": 19.23, "elapsed_time": "0:08:33", "remaining_time": "0:35:58"}
+{"current_steps": 65, "total_steps": 312, "loss": 1.828, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017933533402912354, "epoch": 0.21, "percentage": 20.83, "elapsed_time": "0:09:19", "remaining_time": "0:35:24"}
+{"current_steps": 70, "total_steps": 312, "loss": 1.8083, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017617123081773591, "epoch": 0.22, "percentage": 22.44, "elapsed_time": "0:09:58", "remaining_time": "0:34:30"}
+{"current_steps": 75, "total_steps": 312, "loss": 1.8268, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017281409538757883, "epoch": 0.24, "percentage": 24.04, "elapsed_time": "0:10:38", "remaining_time": "0:33:36"}
+{"current_steps": 80, "total_steps": 312, "loss": 1.7587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016927243535095997, "epoch": 0.26, "percentage": 25.64, "elapsed_time": "0:11:19", "remaining_time": "0:32:50"}
+{"current_steps": 85, "total_steps": 312, "loss": 1.7939, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001655552259402295, "epoch": 0.27, "percentage": 27.24, "elapsed_time": "0:12:06", "remaining_time": "0:32:19"}
+{"current_steps": 90, "total_steps": 312, "loss": 1.848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016167188726285434, "epoch": 0.29, "percentage": 28.85, "elapsed_time": "0:12:46", "remaining_time": "0:31:31"}
+{"current_steps": 95, "total_steps": 312, "loss": 1.7407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015763226042909455, "epoch": 0.3, "percentage": 30.45, "elapsed_time": "0:13:24", "remaining_time": "0:30:37"}
+{"current_steps": 100, "total_steps": 312, "loss": 1.8559, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001534465826127801, "epoch": 0.32, "percentage": 32.05, "elapsed_time": "0:14:12", "remaining_time": "0:30:06"}
+{"current_steps": 105, "total_steps": 312, "loss": 1.8363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014912546110838775, "epoch": 0.34, "percentage": 33.65, "elapsed_time": "0:14:56", "remaining_time": "0:29:27"}
+{"current_steps": 110, "total_steps": 312, "loss": 1.6798, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014467984645016258, "epoch": 0.35, "percentage": 35.26, "elapsed_time": "0:15:40", "remaining_time": "0:28:47"}
+{"current_steps": 115, "total_steps": 312, "loss": 1.6868, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014012100466140578, "epoch": 0.37, "percentage": 36.86, "elapsed_time": "0:16:25", "remaining_time": "0:28:09"}
+{"current_steps": 120, "total_steps": 312, "loss": 1.8213, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013546048870425356, "epoch": 0.38, "percentage": 38.46, "elapsed_time": "0:17:09", "remaining_time": "0:27:27"}
+{"current_steps": 125, "total_steps": 312, "loss": 1.7561, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013071010920229909, "epoch": 0.4, "percentage": 40.06, "elapsed_time": "0:17:54", "remaining_time": "0:26:46"}
+{"current_steps": 130, "total_steps": 312, "loss": 1.7834, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012588190451025207, "epoch": 0.42, "percentage": 41.67, "elapsed_time": "0:18:38", "remaining_time": "0:26:06"}
+{"current_steps": 135, "total_steps": 312, "loss": 1.9342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012098811020648475, "epoch": 0.43, "percentage": 43.27, "elapsed_time": "0:19:27", "remaining_time": "0:25:30"}
+{"current_steps": 140, "total_steps": 312, "loss": 1.8081, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011604112808577603, "epoch": 0.45, "percentage": 44.87, "elapsed_time": "0:20:14", "remaining_time": "0:24:52"}
+{"current_steps": 145, "total_steps": 312, "loss": 1.7449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000111053494730832, "epoch": 0.46, "percentage": 46.47, "elapsed_time": "0:21:00", "remaining_time": "0:24:11"}
+{"current_steps": 150, "total_steps": 312, "loss": 1.8202, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010603784974222861, "epoch": 0.48, "percentage": 48.08, "elapsed_time": "0:21:41", "remaining_time": "0:23:25"}
+{"current_steps": 155, "total_steps": 312, "loss": 1.7587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010100690370728755, "epoch": 0.5, "percentage": 49.68, "elapsed_time": "0:22:24", "remaining_time": "0:22:41"}
+{"current_steps": 160, "total_steps": 312, "loss": 1.8827, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.597340598905852e-05, "epoch": 0.51, "percentage": 51.28, "elapsed_time": "0:23:07", "remaining_time": "0:21:58"}
+{"current_steps": 165, "total_steps": 312, "loss": 1.8022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.095011241703623e-05, "epoch": 0.53, "percentage": 52.88, "elapsed_time": "0:23:45", "remaining_time": "0:21:09"}
+{"current_steps": 170, "total_steps": 312, "loss": 1.7515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.594975296149076e-05, "epoch": 0.54, "percentage": 54.49, "elapsed_time": "0:24:31", "remaining_time": "0:20:28"}
+{"current_steps": 175, "total_steps": 312, "loss": 1.7027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.098499947332934e-05, "epoch": 0.56, "percentage": 56.09, "elapsed_time": "0:25:12", "remaining_time": "0:19:44"}
+{"current_steps": 180, "total_steps": 312, "loss": 1.7445, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.606843357124426e-05, "epoch": 0.58, "percentage": 57.69, "elapsed_time": "0:25:55", "remaining_time": "0:19:00"}
+{"current_steps": 185, "total_steps": 312, "loss": 1.7094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.121251475752539e-05, "epoch": 0.59, "percentage": 59.29, "elapsed_time": "0:26:35", "remaining_time": "0:18:15"}
+{"current_steps": 190, "total_steps": 312, "loss": 1.7047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.642954884333955e-05, "epoch": 0.61, "percentage": 60.9, "elapsed_time": "0:27:15", "remaining_time": "0:17:30"}
+{"current_steps": 195, "total_steps": 312, "loss": 1.6086, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.173165676349103e-05, "epoch": 0.62, "percentage": 62.5, "elapsed_time": "0:27:56", "remaining_time": "0:16:46"}
+{"current_steps": 200, "total_steps": 312, "loss": 1.7098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.713074385969457e-05, "epoch": 0.64, "percentage": 64.1, "elapsed_time": "0:28:41", "remaining_time": "0:16:03"}
+{"current_steps": 205, "total_steps": 312, "loss": 1.7766, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.263846971020108e-05, "epoch": 0.66, "percentage": 65.71, "elapsed_time": "0:29:23", "remaining_time": "0:15:20"}
+{"current_steps": 210, "total_steps": 312, "loss": 1.9863, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.826621858223431e-05, "epoch": 0.67, "percentage": 67.31, "elapsed_time": "0:30:02", "remaining_time": "0:14:35"}
+{"current_steps": 215, "total_steps": 312, "loss": 1.7957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.40250705821178e-05, "epoch": 0.69, "percentage": 68.91, "elapsed_time": "0:30:42", "remaining_time": "0:13:51"}
+{"current_steps": 220, "total_steps": 312, "loss": 1.7848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.99257735762021e-05, "epoch": 0.7, "percentage": 70.51, "elapsed_time": "0:31:25", "remaining_time": "0:13:08"}
+{"current_steps": 225, "total_steps": 312, "loss": 1.8688, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.597871595375121e-05, "epoch": 0.72, "percentage": 72.12, "elapsed_time": "0:32:07", "remaining_time": "0:12:25"}
+{"current_steps": 230, "total_steps": 312, "loss": 1.6451, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.219390030081091e-05, "epoch": 0.74, "percentage": 73.72, "elapsed_time": "0:32:50", "remaining_time": "0:11:42"}
+{"current_steps": 235, "total_steps": 312, "loss": 1.8795, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.858091805177554e-05, "epoch": 0.75, "percentage": 75.32, "elapsed_time": "0:33:32", "remaining_time": "0:10:59"}
+{"current_steps": 240, "total_steps": 312, "loss": 1.7631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.514892518288988e-05, "epoch": 0.77, "percentage": 76.92, "elapsed_time": "0:34:15", "remaining_time": "0:10:16"}
+{"current_steps": 245, "total_steps": 312, "loss": 1.7843, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1906619009284257e-05, "epoch": 0.78, "percentage": 78.53, "elapsed_time": "0:34:56", "remaining_time": "0:09:33"}
+{"current_steps": 250, "total_steps": 312, "loss": 1.7854, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8862216144342692e-05, "epoch": 0.8, "percentage": 80.13, "elapsed_time": "0:35:41", "remaining_time": "0:08:51"}
+{"current_steps": 255, "total_steps": 312, "loss": 1.5676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6023431677260214e-05, "epoch": 0.82, "percentage": 81.73, "elapsed_time": "0:36:23", "remaining_time": "0:08:08"}
+{"current_steps": 260, "total_steps": 312, "loss": 1.6083, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.339745962155613e-05, "epoch": 0.83, "percentage": 83.33, "elapsed_time": "0:37:14", "remaining_time": "0:07:26"}
+{"current_steps": 265, "total_steps": 312, "loss": 1.8291, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0990954684091558e-05, "epoch": 0.85, "percentage": 84.94, "elapsed_time": "0:37:55", "remaining_time": "0:06:43"}
+{"current_steps": 270, "total_steps": 312, "loss": 1.7606, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.810015400790994e-06, "epoch": 0.86, "percentage": 86.54, "elapsed_time": "0:38:40", "remaining_time": "0:06:01"}
+{"current_steps": 275, "total_steps": 312, "loss": 1.7076, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.860168681805945e-06, "epoch": 0.88, "percentage": 88.14, "elapsed_time": "0:39:25", "remaining_time": "0:05:18"}
+{"current_steps": 280, "total_steps": 312, "loss": 1.706, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.146355805285452e-06, "epoch": 0.9, "percentage": 89.74, "elapsed_time": "0:40:09", "remaining_time": "0:04:35"}
+{"current_steps": 285, "total_steps": 312, "loss": 1.7685, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6729198952483724e-06, "epoch": 0.91, "percentage": 91.35, "elapsed_time": "0:40:56", "remaining_time": "0:03:52"}
+{"current_steps": 290, "total_steps": 312, "loss": 1.7422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4435949152906145e-06, "epoch": 0.93, "percentage": 92.95, "elapsed_time": "0:41:35", "remaining_time": "0:03:09"}
+{"current_steps": 295, "total_steps": 312, "loss": 1.8109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4614962060194304e-06, "epoch": 0.94, "percentage": 94.55, "elapsed_time": "0:42:19", "remaining_time": "0:02:26"}
+{"current_steps": 300, "total_steps": 312, "loss": 1.7055, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.291125901946027e-07, "epoch": 0.96, "percentage": 96.15, "elapsed_time": "0:43:04", "remaining_time": "0:01:43"}
+{"current_steps": 305, "total_steps": 312, "loss": 1.73, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4830006558373973e-07, "epoch": 0.98, "percentage": 97.76, "elapsed_time": "0:43:47", "remaining_time": "0:01:00"}
+{"current_steps": 310, "total_steps": 312, "loss": 1.9092, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0277101514987184e-08, "epoch": 0.99, "percentage": 99.36, "elapsed_time": "0:44:31", "remaining_time": "0:00:17"}
+{"current_steps": 312, "total_steps": 312, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:44:45", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,464 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8396336436271667,
+      "learning_rate": 0.00019987329060020616,
+      "loss": 2.8923,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.7428969740867615,
+      "learning_rate": 0.00019949348350626456,
+      "loss": 2.0944,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5937550067901611,
+      "learning_rate": 0.00019886154122075343,
+      "loss": 2.0323,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4460415542125702,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 1.9436,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4390580952167511,
+      "learning_rate": 0.00019684829181681234,
+      "loss": 2.0292,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.43469828367233276,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 1.9654,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.48699721693992615,
+      "learning_rate": 0.0001938539372689649,
+      "loss": 1.9041,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5205313563346863,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 1.8992,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5224802494049072,
+      "learning_rate": 0.00018990881137654258,
+      "loss": 1.8393,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5004997849464417,
+      "learning_rate": 0.0001875918325566888,
+      "loss": 1.615,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5422343611717224,
+      "learning_rate": 0.00018505287956623297,
+      "loss": 1.9873,
+      "step": 55
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.47483357787132263,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 1.9264,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4191422164440155,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 1.828,
+      "step": 65
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.41457584500312805,
+      "learning_rate": 0.00017617123081773591,
+      "loss": 1.8083,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.524440348148346,
+      "learning_rate": 0.00017281409538757883,
+      "loss": 1.8268,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5396173000335693,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 1.7587,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.5633752942085266,
+      "learning_rate": 0.0001655552259402295,
+      "loss": 1.7939,
+      "step": 85
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5931205153465271,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 1.848,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.677586019039154,
+      "learning_rate": 0.00015763226042909455,
+      "loss": 1.7407,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5012004971504211,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 1.8559,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.5996416807174683,
+      "learning_rate": 0.00014912546110838775,
+      "loss": 1.8363,
+      "step": 105
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5592181086540222,
+      "learning_rate": 0.00014467984645016258,
+      "loss": 1.6798,
+      "step": 110
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.6498942971229553,
+      "learning_rate": 0.00014012100466140578,
+      "loss": 1.6868,
+      "step": 115
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5339984893798828,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 1.8213,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5681377649307251,
+      "learning_rate": 0.00013071010920229909,
+      "loss": 1.7561,
+      "step": 125
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5253719687461853,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 1.7834,
+      "step": 130
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.5420334935188293,
+      "learning_rate": 0.00012098811020648475,
+      "loss": 1.9342,
+      "step": 135
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.6371601819992065,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 1.8081,
+      "step": 140
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5578604340553284,
+      "learning_rate": 0.000111053494730832,
+      "loss": 1.7449,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.768509030342102,
+      "learning_rate": 0.00010603784974222861,
+      "loss": 1.8202,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.627295970916748,
+      "learning_rate": 0.00010100690370728755,
+      "loss": 1.7587,
+      "step": 155
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.6519939303398132,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 1.8827,
+      "step": 160
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.6148818135261536,
+      "learning_rate": 9.095011241703623e-05,
+      "loss": 1.8022,
+      "step": 165
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.5009266138076782,
+      "learning_rate": 8.594975296149076e-05,
+      "loss": 1.7515,
+      "step": 170
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5753130316734314,
+      "learning_rate": 8.098499947332934e-05,
+      "loss": 1.7027,
+      "step": 175
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.5501881241798401,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 1.7445,
+      "step": 180
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.6279743909835815,
+      "learning_rate": 7.121251475752539e-05,
+      "loss": 1.7094,
+      "step": 185
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5455606579780579,
+      "learning_rate": 6.642954884333955e-05,
+      "loss": 1.7047,
+      "step": 190
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5445593595504761,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.6086,
+      "step": 195
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6656392812728882,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 1.7098,
+      "step": 200
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.5549783706665039,
+      "learning_rate": 5.263846971020108e-05,
+      "loss": 1.7766,
+      "step": 205
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.594687819480896,
+      "learning_rate": 4.826621858223431e-05,
+      "loss": 1.9863,
+      "step": 210
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.5940021276473999,
+      "learning_rate": 4.40250705821178e-05,
+      "loss": 1.7957,
+      "step": 215
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.6612168550491333,
+      "learning_rate": 3.99257735762021e-05,
+      "loss": 1.7848,
+      "step": 220
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5535335540771484,
+      "learning_rate": 3.597871595375121e-05,
+      "loss": 1.8688,
+      "step": 225
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.607822597026825,
+      "learning_rate": 3.219390030081091e-05,
+      "loss": 1.6451,
+      "step": 230
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6583452820777893,
+      "learning_rate": 2.858091805177554e-05,
+      "loss": 1.8795,
+      "step": 235
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.5893087983131409,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 1.7631,
+      "step": 240
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.5828584432601929,
+      "learning_rate": 2.1906619009284257e-05,
+      "loss": 1.7843,
+      "step": 245
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5105574727058411,
+      "learning_rate": 1.8862216144342692e-05,
+      "loss": 1.7854,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.6286787390708923,
+      "learning_rate": 1.6023431677260214e-05,
+      "loss": 1.5676,
+      "step": 255
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.5752671957015991,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.6083,
+      "step": 260
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.5867213606834412,
+      "learning_rate": 1.0990954684091558e-05,
+      "loss": 1.8291,
+      "step": 265
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.6025935411453247,
+      "learning_rate": 8.810015400790994e-06,
+      "loss": 1.7606,
+      "step": 270
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.5295992493629456,
+      "learning_rate": 6.860168681805945e-06,
+      "loss": 1.7076,
+      "step": 275
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.6831830143928528,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.706,
+      "step": 280
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.6414029002189636,
+      "learning_rate": 3.6729198952483724e-06,
+      "loss": 1.7685,
+      "step": 285
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.5466156601905823,
+      "learning_rate": 2.4435949152906145e-06,
+      "loss": 1.7422,
+      "step": 290
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7220910787582397,
+      "learning_rate": 1.4614962060194304e-06,
+      "loss": 1.8109,
+      "step": 295
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6633021235466003,
+      "learning_rate": 7.291125901946027e-07,
+      "loss": 1.7055,
+      "step": 300
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.5576484799385071,
+      "learning_rate": 2.4830006558373973e-07,
+      "loss": 1.73,
+      "step": 305
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.6037314534187317,
+      "learning_rate": 2.0277101514987184e-08,
+      "loss": 1.9092,
+      "step": 310
+    },
+    {
+      "epoch": 1.0,
+      "step": 312,
+      "total_flos": 1.4358009139789824e+17,
+      "train_loss": 1.8196016863370552,
+      "train_runtime": 2685.2386,
+      "train_samples_per_second": 3.724,
+      "train_steps_per_second": 0.116
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1.4358009139789824e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}