Upload folder using huggingface_hub

README.md

@@ -0,0 +1,141 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Qwen/Qwen2-7B
+model-index:
+- name: outputs/out
+  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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: Qwen/Qwen2-7B
+trust_remote_code: true
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./outputs/out
+sequence_len: 2048
+sample_packing: true
+eval_sample_packing: true
+pad_to_sequence_len: true
+adapter: qlora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 0.0002
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: true
+gradient_checkpointing: false
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: false
+warmup_steps: 10
+evals_per_epoch: 4
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+special_tokens:
+
+```
+
+</details><br>
+
+# outputs/out
+
+This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3265
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 10.7953       | 0.0031 | 1    | 10.8104         |
+| 5.4963        | 0.2513 | 80   | 5.4101          |
+| 5.0323        | 0.5026 | 160  | 5.0758          |
+| 4.9877        | 0.7538 | 240  | 4.8417          |
+| 4.7408        | 1.0051 | 320  | 4.6180          |
+| 4.5097        | 1.2442 | 400  | 4.5066          |
+| 4.3959        | 1.4955 | 480  | 4.4513          |
+| 4.2488        | 1.7468 | 560  | 4.4107          |
+| 4.3507        | 1.9980 | 640  | 4.3784          |
+| 4.2352        | 2.2352 | 720  | 4.3684          |
+| 4.2141        | 2.4865 | 800  | 4.3505          |
+| 4.2739        | 2.7377 | 880  | 4.3375          |
+| 4.4037        | 2.9890 | 960  | 4.3310          |
+| 4.195         | 3.2269 | 1040 | 4.3287          |
+| 4.1996        | 3.4782 | 1120 | 4.3268          |
+| 4.1353        | 3.7295 | 1200 | 4.3265          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_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 sha256:8182fe0f09118e42ee24f7be2305434cd9ed061a857d5649f849c4e2e9cda598
+size 161622314

added_tokens.json

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

checkpoint-1272/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen2-7B
+---
+
+# 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 0.11.1

checkpoint-1272/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1272/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a20e60e858d2682abc14528a71fccccf14339ac8667eeacbeb2091b6f76bd5
+size 161533584

checkpoint-1272/added_tokens.json

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

checkpoint-1272/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6719c69de9c12cb87233d422b5d745ae6a388fd8edc923389d893c2aeb4b4813
+size 323292010

checkpoint-1272/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a6fd22b5a4ce5f800a83b8932a9fe2576ea0ffe9b9beff333869bfd7b6cf2c
+size 14244

checkpoint-1272/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5a8f3dd119b7d57929465357243f6d4aae3de0ec76a858fb5197d358a60f4c
+size 1064

checkpoint-1272/special_tokens_map.json

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

checkpoint-1272/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1272/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c048912f6ba3fdf50f66b1635aa253feb31cfba85c9f47fc5603099baef225
+size 5944

checkpoint-318/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen2-7B
+---
+
+# 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 0.11.1

checkpoint-318/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-318/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f56d15074efcbd4884547275ec291a7576da3bf3c9e0b0c1fbd56f6835d3dd17
+size 161533584

checkpoint-318/added_tokens.json

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

checkpoint-318/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73bbb72cb3285a1d5b4aadfbc9bfa173b41e3770dca4d49265bf67c923a69c59
+size 323292010

checkpoint-318/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767e13f11ef09bcfb4e0e134c72ea653c7855060e44fb6dcb5ccff5902c50afb
+size 14244

checkpoint-318/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff5efa8ad7dad6adb047949e33858535b3068c546845d66e19365128712ead9
+size 1064

checkpoint-318/special_tokens_map.json

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

checkpoint-318/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-318/trainer_state.json

@@ -0,0 +1,2291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9988221436984688,
+  "eval_steps": 80,
+  "global_step": 318,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0031409501374165686,
+      "grad_norm": 5.125,
+      "learning_rate": 2e-05,
+      "loss": 10.7953,
+      "step": 1
+    },
+    {
+      "epoch": 0.0031409501374165686,
+      "eval_loss": 10.810359001159668,
+      "eval_runtime": 65.1601,
+      "eval_samples_per_second": 39.917,
+      "eval_steps_per_second": 39.917,
+      "step": 1
+    },
+    {
+      "epoch": 0.006281900274833137,
+      "grad_norm": 4.59375,
+      "learning_rate": 4e-05,
+      "loss": 10.599,
+      "step": 2
+    },
+    {
+      "epoch": 0.009422850412249705,
+      "grad_norm": 5.65625,
+      "learning_rate": 6e-05,
+      "loss": 10.8341,
+      "step": 3
+    },
+    {
+      "epoch": 0.012563800549666274,
+      "grad_norm": 4.59375,
+      "learning_rate": 8e-05,
+      "loss": 10.2321,
+      "step": 4
+    },
+    {
+      "epoch": 0.015704750687082842,
+      "grad_norm": 5.09375,
+      "learning_rate": 0.0001,
+      "loss": 9.926,
+      "step": 5
+    },
+    {
+      "epoch": 0.01884570082449941,
+      "grad_norm": 5.09375,
+      "learning_rate": 0.00012,
+      "loss": 9.2807,
+      "step": 6
+    },
+    {
+      "epoch": 0.02198665096191598,
+      "grad_norm": 5.21875,
+      "learning_rate": 0.00014,
+      "loss": 8.7401,
+      "step": 7
+    },
+    {
+      "epoch": 0.02512760109933255,
+      "grad_norm": 5.3125,
+      "learning_rate": 0.00016,
+      "loss": 7.7479,
+      "step": 8
+    },
+    {
+      "epoch": 0.028268551236749116,
+      "grad_norm": 3.78125,
+      "learning_rate": 0.00018,
+      "loss": 7.3356,
+      "step": 9
+    },
+    {
+      "epoch": 0.031409501374165684,
+      "grad_norm": 4.15625,
+      "learning_rate": 0.0002,
+      "loss": 6.8649,
+      "step": 10
+    },
+    {
+      "epoch": 0.03455045151158225,
+      "grad_norm": 1.9296875,
+      "learning_rate": 0.00019999969015048862,
+      "loss": 6.7994,
+      "step": 11
+    },
+    {
+      "epoch": 0.03769140164899882,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.0001999987606038746,
+      "loss": 6.2436,
+      "step": 12
+    },
+    {
+      "epoch": 0.040832351786415394,
+      "grad_norm": 2.125,
+      "learning_rate": 0.0001999972113659183,
+      "loss": 6.6684,
+      "step": 13
+    },
+    {
+      "epoch": 0.04397330192383196,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.00019999504244622043,
+      "loss": 6.4968,
+      "step": 14
+    },
+    {
+      "epoch": 0.04711425206124853,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.00019999225385822165,
+      "loss": 6.3331,
+      "step": 15
+    },
+    {
+      "epoch": 0.0502552021986651,
+      "grad_norm": 0.88671875,
+      "learning_rate": 0.00019998884561920284,
+      "loss": 6.3441,
+      "step": 16
+    },
+    {
+      "epoch": 0.053396152336081665,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.00019998481775028491,
+      "loss": 5.8419,
+      "step": 17
+    },
+    {
+      "epoch": 0.05653710247349823,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001999801702764284,
+      "loss": 6.1942,
+      "step": 18
+    },
+    {
+      "epoch": 0.0596780526109148,
+      "grad_norm": 1.75,
+      "learning_rate": 0.00019997490322643376,
+      "loss": 6.017,
+      "step": 19
+    },
+    {
+      "epoch": 0.06281900274833137,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00019996901663294078,
+      "loss": 6.2501,
+      "step": 20
+    },
+    {
+      "epoch": 0.06595995288574794,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.00019996251053242865,
+      "loss": 5.9597,
+      "step": 21
+    },
+    {
+      "epoch": 0.0691009030231645,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.0001999553849652156,
+      "loss": 6.0591,
+      "step": 22
+    },
+    {
+      "epoch": 0.07224185316058107,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.00019994763997545874,
+      "loss": 6.2802,
+      "step": 23
+    },
+    {
+      "epoch": 0.07538280329799764,
+      "grad_norm": 1.7265625,
+      "learning_rate": 0.00019993927561115366,
+      "loss": 6.082,
+      "step": 24
+    },
+    {
+      "epoch": 0.0785237534354142,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00019993029192413424,
+      "loss": 6.1596,
+      "step": 25
+    },
+    {
+      "epoch": 0.08166470357283079,
+      "grad_norm": 1.609375,
+      "learning_rate": 0.00019992068897007232,
+      "loss": 5.9254,
+      "step": 26
+    },
+    {
+      "epoch": 0.08480565371024736,
+      "grad_norm": 1.5234375,
+      "learning_rate": 0.0001999104668084773,
+      "loss": 5.893,
+      "step": 27
+    },
+    {
+      "epoch": 0.08794660384766392,
+      "grad_norm": 0.90234375,
+      "learning_rate": 0.00019989962550269583,
+      "loss": 6.1184,
+      "step": 28
+    },
+    {
+      "epoch": 0.09108755398508049,
+      "grad_norm": 0.88671875,
+      "learning_rate": 0.00019988816511991135,
+      "loss": 5.9582,
+      "step": 29
+    },
+    {
+      "epoch": 0.09422850412249706,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00019987608573114376,
+      "loss": 5.8845,
+      "step": 30
+    },
+    {
+      "epoch": 0.09736945425991363,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0001998633874112489,
+      "loss": 6.1202,
+      "step": 31
+    },
+    {
+      "epoch": 0.1005104043973302,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.00019985007023891815,
+      "loss": 5.7627,
+      "step": 32
+    },
+    {
+      "epoch": 0.10365135453474676,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019983613429667792,
+      "loss": 6.0619,
+      "step": 33
+    },
+    {
+      "epoch": 0.10679230467216333,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00019982157967088904,
+      "loss": 5.683,
+      "step": 34
+    },
+    {
+      "epoch": 0.1099332548095799,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.0001998064064517464,
+      "loss": 5.8008,
+      "step": 35
+    },
+    {
+      "epoch": 0.11307420494699646,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00019979061473327837,
+      "loss": 5.8867,
+      "step": 36
+    },
+    {
+      "epoch": 0.11621515508441303,
+      "grad_norm": 1.671875,
+      "learning_rate": 0.000199774204613346,
+      "loss": 5.9331,
+      "step": 37
+    },
+    {
+      "epoch": 0.1193561052218296,
+      "grad_norm": 1.4375,
+      "learning_rate": 0.00019975717619364263,
+      "loss": 5.4695,
+      "step": 38
+    },
+    {
+      "epoch": 0.12249705535924617,
+      "grad_norm": 1.4765625,
+      "learning_rate": 0.0001997395295796933,
+      "loss": 5.9711,
+      "step": 39
+    },
+    {
+      "epoch": 0.12563800549666274,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.00019972126488085378,
+      "loss": 5.7401,
+      "step": 40
+    },
+    {
+      "epoch": 0.12877895563407932,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00019970238221031034,
+      "loss": 5.7064,
+      "step": 41
+    },
+    {
+      "epoch": 0.13191990577149587,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019968288168507864,
+      "loss": 5.6272,
+      "step": 42
+    },
+    {
+      "epoch": 0.13506085590891245,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.00019966276342600327,
+      "loss": 5.4439,
+      "step": 43
+    },
+    {
+      "epoch": 0.138201806046329,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0001996420275577569,
+      "loss": 5.9631,
+      "step": 44
+    },
+    {
+      "epoch": 0.1413427561837456,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00019962067420883944,
+      "loss": 5.8393,
+      "step": 45
+    },
+    {
+      "epoch": 0.14448370632116214,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00019959870351157747,
+      "loss": 5.7997,
+      "step": 46
+    },
+    {
+      "epoch": 0.14762465645857872,
+      "grad_norm": 1.3984375,
+      "learning_rate": 0.0001995761156021231,
+      "loss": 5.656,
+      "step": 47
+    },
+    {
+      "epoch": 0.15076560659599528,
+      "grad_norm": 1.4921875,
+      "learning_rate": 0.00019955291062045345,
+      "loss": 5.7152,
+      "step": 48
+    },
+    {
+      "epoch": 0.15390655673341186,
+      "grad_norm": 1.828125,
+      "learning_rate": 0.00019952908871036956,
+      "loss": 5.7215,
+      "step": 49
+    },
+    {
+      "epoch": 0.1570475068708284,
+      "grad_norm": 1.0,
+      "learning_rate": 0.0001995046500194955,
+      "loss": 5.6857,
+      "step": 50
+    },
+    {
+      "epoch": 0.160188457008245,
+      "grad_norm": 1.3984375,
+      "learning_rate": 0.00019947959469927772,
+      "loss": 5.6698,
+      "step": 51
+    },
+    {
+      "epoch": 0.16332940714566158,
+      "grad_norm": 1.3515625,
+      "learning_rate": 0.0001994539229049837,
+      "loss": 5.2906,
+      "step": 52
+    },
+    {
+      "epoch": 0.16647035728307813,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00019942763479570132,
+      "loss": 5.4673,
+      "step": 53
+    },
+    {
+      "epoch": 0.1696113074204947,
+      "grad_norm": 0.890625,
+      "learning_rate": 0.00019940073053433777,
+      "loss": 5.5959,
+      "step": 54
+    },
+    {
+      "epoch": 0.17275225755791127,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.00019937321028761846,
+      "loss": 5.9431,
+      "step": 55
+    },
+    {
+      "epoch": 0.17589320769532785,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.00019934507422608608,
+      "loss": 5.754,
+      "step": 56
+    },
+    {
+      "epoch": 0.1790341578327444,
+      "grad_norm": 0.984375,
+      "learning_rate": 0.00019931632252409955,
+      "loss": 5.405,
+      "step": 57
+    },
+    {
+      "epoch": 0.18217510797016098,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.00019928695535983287,
+      "loss": 5.5907,
+      "step": 58
+    },
+    {
+      "epoch": 0.18531605810757754,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.00019925697291527415,
+      "loss": 5.7941,
+      "step": 59
+    },
+    {
+      "epoch": 0.18845700824499412,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00019922637537622418,
+      "loss": 5.6169,
+      "step": 60
+    },
+    {
+      "epoch": 0.19159795838241067,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019919516293229569,
+      "loss": 5.5379,
+      "step": 61
+    },
+    {
+      "epoch": 0.19473890851982725,
+      "grad_norm": 0.8203125,
+      "learning_rate": 0.00019916333577691184,
+      "loss": 5.6157,
+      "step": 62
+    },
+    {
+      "epoch": 0.1978798586572438,
+      "grad_norm": 1.484375,
+      "learning_rate": 0.00019913089410730526,
+      "loss": 5.5043,
+      "step": 63
+    },
+    {
+      "epoch": 0.2010208087946604,
+      "grad_norm": 0.98046875,
+      "learning_rate": 0.00019909783812451664,
+      "loss": 5.7083,
+      "step": 64
+    },
+    {
+      "epoch": 0.20416175893207694,
+      "grad_norm": 1.125,
+      "learning_rate": 0.00019906416803339353,
+      "loss": 5.5739,
+      "step": 65
+    },
+    {
+      "epoch": 0.20730270906949352,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00019902988404258922,
+      "loss": 5.5447,
+      "step": 66
+    },
+    {
+      "epoch": 0.21044365920691008,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00019899498636456126,
+      "loss": 5.3392,
+      "step": 67
+    },
+    {
+      "epoch": 0.21358460934432666,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.0001989594752155702,
+      "loss": 5.3176,
+      "step": 68
+    },
+    {
+      "epoch": 0.21672555948174324,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00019892335081567826,
+      "loss": 5.1688,
+      "step": 69
+    },
+    {
+      "epoch": 0.2198665096191598,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.00019888661338874803,
+      "loss": 5.5142,
+      "step": 70
+    },
+    {
+      "epoch": 0.22300745975657638,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.000198849263162441,
+      "loss": 5.3004,
+      "step": 71
+    },
+    {
+      "epoch": 0.22614840989399293,
+      "grad_norm": 0.7890625,
+      "learning_rate": 0.0001988113003682161,
+      "loss": 5.5914,
+      "step": 72
+    },
+    {
+      "epoch": 0.2292893600314095,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00019877272524132847,
+      "loss": 5.4175,
+      "step": 73
+    },
+    {
+      "epoch": 0.23243031016882607,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.00019873353802082771,
+      "loss": 5.0854,
+      "step": 74
+    },
+    {
+      "epoch": 0.23557126030624265,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019869373894955669,
+      "loss": 5.5772,
+      "step": 75
+    },
+    {
+      "epoch": 0.2387122104436592,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00019865332827414988,
+      "loss": 5.4289,
+      "step": 76
+    },
+    {
+      "epoch": 0.24185316058107578,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001986123062450318,
+      "loss": 5.5427,
+      "step": 77
+    },
+    {
+      "epoch": 0.24499411071849234,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.0001985706731164156,
+      "loss": 5.3294,
+      "step": 78
+    },
+    {
+      "epoch": 0.24813506085590892,
+      "grad_norm": 1.4921875,
+      "learning_rate": 0.00019852842914630137,
+      "loss": 5.3756,
+      "step": 79
+    },
+    {
+      "epoch": 0.25127601099332547,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00019848557459647455,
+      "loss": 5.4963,
+      "step": 80
+    },
+    {
+      "epoch": 0.25127601099332547,
+      "eval_loss": 5.410098075866699,
+      "eval_runtime": 66.9514,
+      "eval_samples_per_second": 38.849,
+      "eval_steps_per_second": 38.849,
+      "step": 80
+    },
+    {
+      "epoch": 0.254416961130742,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019844210973250437,
+      "loss": 5.4053,
+      "step": 81
+    },
+    {
+      "epoch": 0.25755791126815863,
+      "grad_norm": 1.3359375,
+      "learning_rate": 0.0001983980348237422,
+      "loss": 5.3084,
+      "step": 82
+    },
+    {
+      "epoch": 0.2606988614055752,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00019835335014331976,
+      "loss": 5.4774,
+      "step": 83
+    },
+    {
+      "epoch": 0.26383981154299174,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019830805596814766,
+      "loss": 5.3591,
+      "step": 84
+    },
+    {
+      "epoch": 0.2669807616804083,
+      "grad_norm": 1.46875,
+      "learning_rate": 0.00019826215257891342,
+      "loss": 5.2504,
+      "step": 85
+    },
+    {
+      "epoch": 0.2701217118178249,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019821564026007988,
+      "loss": 5.2333,
+      "step": 86
+    },
+    {
+      "epoch": 0.27326266195524146,
+      "grad_norm": 1.4765625,
+      "learning_rate": 0.0001981685192998834,
+      "loss": 5.4557,
+      "step": 87
+    },
+    {
+      "epoch": 0.276403612092658,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019812078999033222,
+      "loss": 5.5066,
+      "step": 88
+    },
+    {
+      "epoch": 0.2795445622300746,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.00019807245262720426,
+      "loss": 5.3617,
+      "step": 89
+    },
+    {
+      "epoch": 0.2826855123674912,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.0001980235075100458,
+      "loss": 5.4076,
+      "step": 90
+    },
+    {
+      "epoch": 0.28582646250490773,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.00019797395494216923,
+      "loss": 5.2482,
+      "step": 91
+    },
+    {
+      "epoch": 0.2889674126423243,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00019792379523065126,
+      "loss": 5.1448,
+      "step": 92
+    },
+    {
+      "epoch": 0.2921083627797409,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0001978730286863312,
+      "loss": 5.2483,
+      "step": 93
+    },
+    {
+      "epoch": 0.29524931291715745,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.0001978216556238088,
+      "loss": 5.1698,
+      "step": 94
+    },
+    {
+      "epoch": 0.298390263054574,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00019776967636144245,
+      "loss": 5.3225,
+      "step": 95
+    },
+    {
+      "epoch": 0.30153121319199055,
+      "grad_norm": 0.80859375,
+      "learning_rate": 0.00019771709122134713,
+      "loss": 5.3077,
+      "step": 96
+    },
+    {
+      "epoch": 0.30467216332940716,
+      "grad_norm": 0.76953125,
+      "learning_rate": 0.00019766390052939242,
+      "loss": 5.2636,
+      "step": 97
+    },
+    {
+      "epoch": 0.3078131134668237,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.00019761010461520054,
+      "loss": 5.4547,
+      "step": 98
+    },
+    {
+      "epoch": 0.31095406360424027,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001975557038121442,
+      "loss": 5.2564,
+      "step": 99
+    },
+    {
+      "epoch": 0.3140950137416568,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.00019750069845734473,
+      "loss": 4.9768,
+      "step": 100
+    },
+    {
+      "epoch": 0.31723596387907343,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019744508889166966,
+      "loss": 5.2283,
+      "step": 101
+    },
+    {
+      "epoch": 0.32037691401649,
+      "grad_norm": 1.34375,
+      "learning_rate": 0.00019738887545973102,
+      "loss": 5.4258,
+      "step": 102
+    },
+    {
+      "epoch": 0.32351786415390654,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00019733205850988285,
+      "loss": 5.2331,
+      "step": 103
+    },
+    {
+      "epoch": 0.32665881429132315,
+      "grad_norm": 0.828125,
+      "learning_rate": 0.00019727463839421926,
+      "loss": 5.1852,
+      "step": 104
+    },
+    {
+      "epoch": 0.3297997644287397,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.00019721661546857213,
+      "loss": 5.4063,
+      "step": 105
+    },
+    {
+      "epoch": 0.33294071456615626,
+      "grad_norm": 0.8359375,
+      "learning_rate": 0.000197157990092509,
+      "loss": 5.2671,
+      "step": 106
+    },
+    {
+      "epoch": 0.3360816647035728,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.00019709876262933066,
+      "loss": 5.3544,
+      "step": 107
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 0.9609375,
+      "learning_rate": 0.0001970389334460692,
+      "loss": 5.1728,
+      "step": 108
+    },
+    {
+      "epoch": 0.342363564978406,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.00019697850291348548,
+      "loss": 5.3887,
+      "step": 109
+    },
+    {
+      "epoch": 0.34550451511582253,
+      "grad_norm": 0.8984375,
+      "learning_rate": 0.00019691747140606692,
+      "loss": 5.1095,
+      "step": 110
+    },
+    {
+      "epoch": 0.3486454652532391,
+      "grad_norm": 0.96875,
+      "learning_rate": 0.00019685583930202514,
+      "loss": 5.1703,
+      "step": 111
+    },
+    {
+      "epoch": 0.3517864153906557,
+      "grad_norm": 0.81640625,
+      "learning_rate": 0.0001967936069832937,
+      "loss": 5.17,
+      "step": 112
+    },
+    {
+      "epoch": 0.35492736552807225,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.00019673077483552568,
+      "loss": 5.0519,
+      "step": 113
+    },
+    {
+      "epoch": 0.3580683156654888,
+      "grad_norm": 0.87109375,
+      "learning_rate": 0.00019666734324809125,
+      "loss": 5.186,
+      "step": 114
+    },
+    {
+      "epoch": 0.36120926580290535,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.00019660331261407544,
+      "loss": 5.0202,
+      "step": 115
+    },
+    {
+      "epoch": 0.36435021594032196,
+      "grad_norm": 0.70703125,
+      "learning_rate": 0.00019653868333027535,
+      "loss": 5.1102,
+      "step": 116
+    },
+    {
+      "epoch": 0.3674911660777385,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.00019647345579719807,
+      "loss": 5.1,
+      "step": 117
+    },
+    {
+      "epoch": 0.37063211621515507,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.000196407630419058,
+      "loss": 5.0466,
+      "step": 118
+    },
+    {
+      "epoch": 0.3737730663525716,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00019634120760377428,
+      "loss": 5.3088,
+      "step": 119
+    },
+    {
+      "epoch": 0.37691401648998824,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.00019627418776296858,
+      "loss": 5.2293,
+      "step": 120
+    },
+    {
+      "epoch": 0.3800549666274048,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019620657131196208,
+      "loss": 5.2738,
+      "step": 121
+    },
+    {
+      "epoch": 0.38319591676482134,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019613835866977335,
+      "loss": 4.9497,
+      "step": 122
+    },
+    {
+      "epoch": 0.38633686690223795,
+      "grad_norm": 0.9375,
+      "learning_rate": 0.00019606955025911542,
+      "loss": 5.2231,
+      "step": 123
+    },
+    {
+      "epoch": 0.3894778170396545,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00019600014650639333,
+      "loss": 5.3426,
+      "step": 124
+    },
+    {
+      "epoch": 0.39261876717707106,
+      "grad_norm": 0.76953125,
+      "learning_rate": 0.00019593014784170153,
+      "loss": 5.0717,
+      "step": 125
+    },
+    {
+      "epoch": 0.3957597173144876,
+      "grad_norm": 0.9140625,
+      "learning_rate": 0.00019585955469882097,
+      "loss": 5.1569,
+      "step": 126
+    },
+    {
+      "epoch": 0.3989006674519042,
+      "grad_norm": 0.75390625,
+      "learning_rate": 0.0001957883675152167,
+      "loss": 4.9017,
+      "step": 127
+    },
+    {
+      "epoch": 0.4020416175893208,
+      "grad_norm": 0.96484375,
+      "learning_rate": 0.00019571658673203502,
+      "loss": 5.1124,
+      "step": 128
+    },
+    {
+      "epoch": 0.40518256772673733,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.00019564421279410075,
+      "loss": 4.7849,
+      "step": 129
+    },
+    {
+      "epoch": 0.4083235178641539,
+      "grad_norm": 0.90234375,
+      "learning_rate": 0.00019557124614991443,
+      "loss": 5.1534,
+      "step": 130
+    },
+    {
+      "epoch": 0.4114644680015705,
+      "grad_norm": 1.015625,
+      "learning_rate": 0.00019549768725164967,
+      "loss": 5.2731,
+      "step": 131
+    },
+    {
+      "epoch": 0.41460541813898705,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00019542353655515023,
+      "loss": 5.0467,
+      "step": 132
+    },
+    {
+      "epoch": 0.4177463682764036,
+      "grad_norm": 0.8671875,
+      "learning_rate": 0.00019534879451992728,
+      "loss": 4.8911,
+      "step": 133
+    },
+    {
+      "epoch": 0.42088731841382016,
+      "grad_norm": 0.875,
+      "learning_rate": 0.00019527346160915646,
+      "loss": 5.2338,
+      "step": 134
+    },
+    {
+      "epoch": 0.42402826855123676,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019519753828967508,
+      "loss": 5.1705,
+      "step": 135
+    },
+    {
+      "epoch": 0.4271692186886533,
+      "grad_norm": 0.96484375,
+      "learning_rate": 0.00019512102503197923,
+      "loss": 5.3178,
+      "step": 136
+    },
+    {
+      "epoch": 0.43031016882606987,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00019504392231022076,
+      "loss": 5.1462,
+      "step": 137
+    },
+    {
+      "epoch": 0.4334511189634865,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.00019496623060220457,
+      "loss": 5.0293,
+      "step": 138
+    },
+    {
+      "epoch": 0.43659206910090304,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019488795038938536,
+      "loss": 5.0523,
+      "step": 139
+    },
+    {
+      "epoch": 0.4397330192383196,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019480908215686486,
+      "loss": 5.0893,
+      "step": 140
+    },
+    {
+      "epoch": 0.44287396937573614,
+      "grad_norm": 0.79296875,
+      "learning_rate": 0.00019472962639338875,
+      "loss": 5.0682,
+      "step": 141
+    },
+    {
+      "epoch": 0.44601491951315275,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.00019464958359134354,
+      "loss": 5.1261,
+      "step": 142
+    },
+    {
+      "epoch": 0.4491558696505693,
+      "grad_norm": 1.09375,
+      "learning_rate": 0.00019456895424675382,
+      "loss": 5.2513,
+      "step": 143
+    },
+    {
+      "epoch": 0.45229681978798586,
+      "grad_norm": 0.87890625,
+      "learning_rate": 0.00019448773885927877,
+      "loss": 5.0248,
+      "step": 144
+    },
+    {
+      "epoch": 0.4554377699254024,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.00019440593793220936,
+      "loss": 4.9527,
+      "step": 145
+    },
+    {
+      "epoch": 0.458578720062819,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00019432355197246515,
+      "loss": 5.1182,
+      "step": 146
+    },
+    {
+      "epoch": 0.4617196702002356,
+      "grad_norm": 1.125,
+      "learning_rate": 0.00019424058149059112,
+      "loss": 5.043,
+      "step": 147
+    },
+    {
+      "epoch": 0.46486062033765213,
+      "grad_norm": 0.98828125,
+      "learning_rate": 0.00019415702700075453,
+      "loss": 5.1351,
+      "step": 148
+    },
+    {
+      "epoch": 0.4680015704750687,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.00019407288902074176,
+      "loss": 5.0489,
+      "step": 149
+    },
+    {
+      "epoch": 0.4711425206124853,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.00019398816807195498,
+      "loss": 4.8494,
+      "step": 150
+    },
+    {
+      "epoch": 0.47428347074990185,
+      "grad_norm": 0.9140625,
+      "learning_rate": 0.00019390286467940918,
+      "loss": 5.196,
+      "step": 151
+    },
+    {
+      "epoch": 0.4774244208873184,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0001938169793717286,
+      "loss": 4.9598,
+      "step": 152
+    },
+    {
+      "epoch": 0.48056537102473496,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0001937305126811437,
+      "loss": 5.1067,
+      "step": 153
+    },
+    {
+      "epoch": 0.48370632116215156,
+      "grad_norm": 0.7890625,
+      "learning_rate": 0.0001936434651434876,
+      "loss": 5.1599,
+      "step": 154
+    },
+    {
+      "epoch": 0.4868472712995681,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.00019355583729819317,
+      "loss": 4.9971,
+      "step": 155
+    },
+    {
+      "epoch": 0.48998822143698467,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0001934676296882892,
+      "loss": 5.0528,
+      "step": 156
+    },
+    {
+      "epoch": 0.4931291715744013,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.00019337884286039746,
+      "loss": 5.2021,
+      "step": 157
+    },
+    {
+      "epoch": 0.49627012171181784,
+      "grad_norm": 1.015625,
+      "learning_rate": 0.00019328947736472904,
+      "loss": 4.7814,
+      "step": 158
+    },
+    {
+      "epoch": 0.4994110718492344,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00019319953375508106,
+      "loss": 5.0906,
+      "step": 159
+    },
+    {
+      "epoch": 0.5025520219866509,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00019310901258883317,
+      "loss": 5.0323,
+      "step": 160
+    },
+    {
+      "epoch": 0.5025520219866509,
+      "eval_loss": 5.075822353363037,
+      "eval_runtime": 66.934,
+      "eval_samples_per_second": 38.859,
+      "eval_steps_per_second": 38.859,
+      "step": 160
+    },
+    {
+      "epoch": 0.5056929721240675,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.00019301791442694413,
+      "loss": 5.1209,
+      "step": 161
+    },
+    {
+      "epoch": 0.508833922261484,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.00019292623983394838,
+      "loss": 5.0187,
+      "step": 162
+    },
+    {
+      "epoch": 0.5119748723989007,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0001928339893779525,
+      "loss": 4.9584,
+      "step": 163
+    },
+    {
+      "epoch": 0.5151158225363173,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.00019274116363063163,
+      "loss": 4.9459,
+      "step": 164
+    },
+    {
+      "epoch": 0.5182567726737338,
+      "grad_norm": 0.859375,
+      "learning_rate": 0.00019264776316722603,
+      "loss": 4.7699,
+      "step": 165
+    },
+    {
+      "epoch": 0.5213977228111504,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.00019255378856653746,
+      "loss": 5.0324,
+      "step": 166
+    },
+    {
+      "epoch": 0.5245386729485669,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.00019245924041092562,
+      "loss": 5.2702,
+      "step": 167
+    },
+    {
+      "epoch": 0.5276796230859835,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019236411928630446,
+      "loss": 5.0989,
+      "step": 168
+    },
+    {
+      "epoch": 0.5308205732234,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00019226842578213874,
+      "loss": 4.7667,
+      "step": 169
+    },
+    {
+      "epoch": 0.5339615233608166,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.00019217216049144007,
+      "loss": 4.8303,
+      "step": 170
+    },
+    {
+      "epoch": 0.5371024734982333,
+      "grad_norm": 0.8984375,
+      "learning_rate": 0.00019207532401076358,
+      "loss": 5.0607,
+      "step": 171
+    },
+    {
+      "epoch": 0.5402434236356498,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.00019197791694020396,
+      "loss": 4.96,
+      "step": 172
+    },
+    {
+      "epoch": 0.5433843737730664,
+      "grad_norm": 0.91796875,
+      "learning_rate": 0.00019187993988339192,
+      "loss": 5.0107,
+      "step": 173
+    },
+    {
+      "epoch": 0.5465253239104829,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.0001917813934474903,
+      "loss": 5.1961,
+      "step": 174
+    },
+    {
+      "epoch": 0.5496662740478995,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001916822782431904,
+      "loss": 5.0727,
+      "step": 175
+    },
+    {
+      "epoch": 0.552807224185316,
+      "grad_norm": 1.203125,
+      "learning_rate": 0.00019158259488470815,
+      "loss": 4.8185,
+      "step": 176
+    },
+    {
+      "epoch": 0.5559481743227326,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.00019148234398978038,
+      "loss": 5.2447,
+      "step": 177
+    },
+    {
+      "epoch": 0.5590891244601492,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0001913815261796609,
+      "loss": 5.0844,
+      "step": 178
+    },
+    {
+      "epoch": 0.5622300745975658,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.0001912801420791167,
+      "loss": 5.0112,
+      "step": 179
+    },
+    {
+      "epoch": 0.5653710247349824,
+      "grad_norm": 1.3671875,
+      "learning_rate": 0.000191178192316424,
+      "loss": 5.1335,
+      "step": 180
+    },
+    {
+      "epoch": 0.5685119748723989,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00019107567752336458,
+      "loss": 5.1664,
+      "step": 181
+    },
+    {
+      "epoch": 0.5716529250098155,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.0001909725983352215,
+      "loss": 4.9254,
+      "step": 182
+    },
+    {
+      "epoch": 0.574793875147232,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00019086895539077562,
+      "loss": 4.8303,
+      "step": 183
+    },
+    {
+      "epoch": 0.5779348252846486,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00019076474933230116,
+      "loss": 4.9595,
+      "step": 184
+    },
+    {
+      "epoch": 0.5810757754220651,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019065998080556204,
+      "loss": 5.0253,
+      "step": 185
+    },
+    {
+      "epoch": 0.5842167255594818,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.00019055465045980782,
+      "loss": 5.1003,
+      "step": 186
+    },
+    {
+      "epoch": 0.5873576756968983,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019044875894776966,
+      "loss": 4.9631,
+      "step": 187
+    },
+    {
+      "epoch": 0.5904986258343149,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019034230692565614,
+      "loss": 4.9462,
+      "step": 188
+    },
+    {
+      "epoch": 0.5936395759717314,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.0001902352950531495,
+      "loss": 4.8688,
+      "step": 189
+    },
+    {
+      "epoch": 0.596780526109148,
+      "grad_norm": 1.3359375,
+      "learning_rate": 0.0001901277239934012,
+      "loss": 5.1219,
+      "step": 190
+    },
+    {
+      "epoch": 0.5999214762465646,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00019001959441302806,
+      "loss": 5.0382,
+      "step": 191
+    },
+    {
+      "epoch": 0.6030624263839811,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00018991090698210802,
+      "loss": 4.9474,
+      "step": 192
+    },
+    {
+      "epoch": 0.6062033765213978,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018980166237417606,
+      "loss": 5.034,
+      "step": 193
+    },
+    {
+      "epoch": 0.6093443266588143,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00018969186126621996,
+      "loss": 5.0142,
+      "step": 194
+    },
+    {
+      "epoch": 0.6124852767962309,
+      "grad_norm": 1.203125,
+      "learning_rate": 0.00018958150433867605,
+      "loss": 4.7944,
+      "step": 195
+    },
+    {
+      "epoch": 0.6156262269336474,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.0001894705922754252,
+      "loss": 4.7905,
+      "step": 196
+    },
+    {
+      "epoch": 0.618767177071064,
+      "grad_norm": 0.92578125,
+      "learning_rate": 0.0001893591257637883,
+      "loss": 4.8537,
+      "step": 197
+    },
+    {
+      "epoch": 0.6219081272084805,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.00018924710549452232,
+      "loss": 4.8625,
+      "step": 198
+    },
+    {
+      "epoch": 0.6250490773458971,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001891345321618157,
+      "loss": 5.1188,
+      "step": 199
+    },
+    {
+      "epoch": 0.6281900274833137,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.00018902140646328435,
+      "loss": 4.7798,
+      "step": 200
+    },
+    {
+      "epoch": 0.6313309776207303,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0001889077290999671,
+      "loss": 4.9184,
+      "step": 201
+    },
+    {
+      "epoch": 0.6344719277581469,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00018879350077632143,
+      "loss": 5.0932,
+      "step": 202
+    },
+    {
+      "epoch": 0.6376128778955634,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.00018867872220021913,
+      "loss": 4.9846,
+      "step": 203
+    },
+    {
+      "epoch": 0.64075382803298,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.00018856339408294202,
+      "loss": 4.8107,
+      "step": 204
+    },
+    {
+      "epoch": 0.6438947781703965,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.0001884475171391772,
+      "loss": 4.9413,
+      "step": 205
+    },
+    {
+      "epoch": 0.6470357283078131,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00018833109208701298,
+      "loss": 4.9209,
+      "step": 206
+    },
+    {
+      "epoch": 0.6501766784452296,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00018821411964793433,
+      "loss": 4.8073,
+      "step": 207
+    },
+    {
+      "epoch": 0.6533176285826463,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.00018809660054681823,
+      "loss": 4.7729,
+      "step": 208
+    },
+    {
+      "epoch": 0.6564585787200629,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.0001879785355119295,
+      "loss": 5.0412,
+      "step": 209
+    },
+    {
+      "epoch": 0.6595995288574794,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.0001878599252749159,
+      "loss": 4.8707,
+      "step": 210
+    },
+    {
+      "epoch": 0.662740478994896,
+      "grad_norm": 1.6015625,
+      "learning_rate": 0.00018774077057080398,
+      "loss": 4.6271,
+      "step": 211
+    },
+    {
+      "epoch": 0.6658814291323125,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.00018762107213799427,
+      "loss": 4.8702,
+      "step": 212
+    },
+    {
+      "epoch": 0.6690223792697291,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.00018750083071825677,
+      "loss": 4.8727,
+      "step": 213
+    },
+    {
+      "epoch": 0.6721633294071456,
+      "grad_norm": 1.71875,
+      "learning_rate": 0.0001873800470567264,
+      "loss": 4.8376,
+      "step": 214
+    },
+    {
+      "epoch": 0.6753042795445622,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00018725872190189827,
+      "loss": 4.8666,
+      "step": 215
+    },
+    {
+      "epoch": 0.6784452296819788,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00018713685600562328,
+      "loss": 5.038,
+      "step": 216
+    },
+    {
+      "epoch": 0.6815861798193954,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.00018701445012310315,
+      "loss": 4.9007,
+      "step": 217
+    },
+    {
+      "epoch": 0.684727129956812,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00018689150501288593,
+      "loss": 4.8299,
+      "step": 218
+    },
+    {
+      "epoch": 0.6878680800942285,
+      "grad_norm": 1.3125,
+      "learning_rate": 0.00018676802143686126,
+      "loss": 4.801,
+      "step": 219
+    },
+    {
+      "epoch": 0.6910090302316451,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00018664400016025568,
+      "loss": 4.7097,
+      "step": 220
+    },
+    {
+      "epoch": 0.6941499803690616,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00018651944195162778,
+      "loss": 4.8088,
+      "step": 221
+    },
+    {
+      "epoch": 0.6972909305064782,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0001863943475828636,
+      "loss": 4.9253,
+      "step": 222
+    },
+    {
+      "epoch": 0.7004318806438948,
+      "grad_norm": 1.40625,
+      "learning_rate": 0.00018626871782917174,
+      "loss": 4.8615,
+      "step": 223
+    },
+    {
+      "epoch": 0.7035728307813114,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00018614255346907855,
+      "loss": 4.7592,
+      "step": 224
+    },
+    {
+      "epoch": 0.7067137809187279,
+      "grad_norm": 1.5,
+      "learning_rate": 0.0001860158552844233,
+      "loss": 4.6569,
+      "step": 225
+    },
+    {
+      "epoch": 0.7098547310561445,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.0001858886240603534,
+      "loss": 4.8259,
+      "step": 226
+    },
+    {
+      "epoch": 0.712995681193561,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00018576086058531957,
+      "loss": 4.8066,
+      "step": 227
+    },
+    {
+      "epoch": 0.7161366313309776,
+      "grad_norm": 1.3828125,
+      "learning_rate": 0.00018563256565107072,
+      "loss": 4.8039,
+      "step": 228
+    },
+    {
+      "epoch": 0.7192775814683942,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00018550374005264937,
+      "loss": 4.8336,
+      "step": 229
+    },
+    {
+      "epoch": 0.7224185316058107,
+      "grad_norm": 1.4765625,
+      "learning_rate": 0.0001853743845883865,
+      "loss": 4.7032,
+      "step": 230
+    },
+    {
+      "epoch": 0.7255594817432274,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.0001852445000598966,
+      "loss": 4.827,
+      "step": 231
+    },
+    {
+      "epoch": 0.7287004318806439,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.0001851140872720729,
+      "loss": 4.996,
+      "step": 232
+    },
+    {
+      "epoch": 0.7318413820180605,
+      "grad_norm": 1.7109375,
+      "learning_rate": 0.0001849831470330821,
+      "loss": 4.7288,
+      "step": 233
+    },
+    {
+      "epoch": 0.734982332155477,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00018485168015435966,
+      "loss": 4.8204,
+      "step": 234
+    },
+    {
+      "epoch": 0.7381232822928936,
+      "grad_norm": 1.5546875,
+      "learning_rate": 0.00018471968745060444,
+      "loss": 4.8829,
+      "step": 235
+    },
+    {
+      "epoch": 0.7412642324303101,
+      "grad_norm": 1.5234375,
+      "learning_rate": 0.00018458716973977405,
+      "loss": 4.7297,
+      "step": 236
+    },
+    {
+      "epoch": 0.7444051825677267,
+      "grad_norm": 1.6640625,
+      "learning_rate": 0.00018445412784307932,
+      "loss": 4.7916,
+      "step": 237
+    },
+    {
+      "epoch": 0.7475461327051433,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0001843205625849797,
+      "loss": 4.5585,
+      "step": 238
+    },
+    {
+      "epoch": 0.7506870828425599,
+      "grad_norm": 1.5234375,
+      "learning_rate": 0.00018418647479317776,
+      "loss": 4.9319,
+      "step": 239
+    },
+    {
+      "epoch": 0.7538280329799765,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00018405186529861416,
+      "loss": 4.9877,
+      "step": 240
+    },
+    {
+      "epoch": 0.7538280329799765,
+      "eval_loss": 4.841662406921387,
+      "eval_runtime": 66.8839,
+      "eval_samples_per_second": 38.888,
+      "eval_steps_per_second": 38.888,
+      "step": 240
+    },
+    {
+      "epoch": 0.756968983117393,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00018391673493546273,
+      "loss": 4.7421,
+      "step": 241
+    },
+    {
+      "epoch": 0.7601099332548096,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.00018378108454112494,
+      "loss": 4.6469,
+      "step": 242
+    },
+    {
+      "epoch": 0.7632508833922261,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00018364491495622497,
+      "loss": 4.7609,
+      "step": 243
+    },
+    {
+      "epoch": 0.7663918335296427,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.00018350822702460444,
+      "loss": 4.737,
+      "step": 244
+    },
+    {
+      "epoch": 0.7695327836670592,
+      "grad_norm": 1.7734375,
+      "learning_rate": 0.0001833710215933171,
+      "loss": 4.7964,
+      "step": 245
+    },
+    {
+      "epoch": 0.7726737338044759,
+      "grad_norm": 1.6640625,
+      "learning_rate": 0.00018323329951262367,
+      "loss": 4.8785,
+      "step": 246
+    },
+    {
+      "epoch": 0.7758146839418925,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.0001830950616359865,
+      "loss": 4.83,
+      "step": 247
+    },
+    {
+      "epoch": 0.778955634079309,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00018295630882006445,
+      "loss": 4.9096,
+      "step": 248
+    },
+    {
+      "epoch": 0.7820965842167256,
+      "grad_norm": 1.6484375,
+      "learning_rate": 0.00018281704192470727,
+      "loss": 4.7864,
+      "step": 249
+    },
+    {
+      "epoch": 0.7852375343541421,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.00018267726181295065,
+      "loss": 4.8557,
+      "step": 250
+    },
+    {
+      "epoch": 0.7883784844915587,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.00018253696935101047,
+      "loss": 4.8157,
+      "step": 251
+    },
+    {
+      "epoch": 0.7915194346289752,
+      "grad_norm": 2.21875,
+      "learning_rate": 0.00018239616540827782,
+      "loss": 4.8016,
+      "step": 252
+    },
+    {
+      "epoch": 0.7946603847663918,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.0001822548508573133,
+      "loss": 4.657,
+      "step": 253
+    },
+    {
+      "epoch": 0.7978013349038084,
+      "grad_norm": 2.21875,
+      "learning_rate": 0.00018211302657384186,
+      "loss": 4.7423,
+      "step": 254
+    },
+    {
+      "epoch": 0.800942285041225,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00018197069343674715,
+      "loss": 4.8695,
+      "step": 255
+    },
+    {
+      "epoch": 0.8040832351786416,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00018182785232806627,
+      "loss": 4.9817,
+      "step": 256
+    },
+    {
+      "epoch": 0.8072241853160581,
+      "grad_norm": 2.125,
+      "learning_rate": 0.00018168450413298416,
+      "loss": 4.794,
+      "step": 257
+    },
+    {
+      "epoch": 0.8103651354534747,
+      "grad_norm": 1.9921875,
+      "learning_rate": 0.00018154064973982816,
+      "loss": 4.9111,
+      "step": 258
+    },
+    {
+      "epoch": 0.8135060855908912,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.0001813962900400626,
+      "loss": 4.9169,
+      "step": 259
+    },
+    {
+      "epoch": 0.8166470357283078,
+      "grad_norm": 1.765625,
+      "learning_rate": 0.00018125142592828307,
+      "loss": 4.7243,
+      "step": 260
+    },
+    {
+      "epoch": 0.8197879858657244,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00018110605830221104,
+      "loss": 4.8339,
+      "step": 261
+    },
+    {
+      "epoch": 0.822928936003141,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.00018096018806268834,
+      "loss": 4.6423,
+      "step": 262
+    },
+    {
+      "epoch": 0.8260698861405575,
+      "grad_norm": 1.9453125,
+      "learning_rate": 0.00018081381611367134,
+      "loss": 4.6603,
+      "step": 263
+    },
+    {
+      "epoch": 0.8292108362779741,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00018066694336222564,
+      "loss": 4.8327,
+      "step": 264
+    },
+    {
+      "epoch": 0.8323517864153906,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.0001805195707185202,
+      "loss": 4.7741,
+      "step": 265
+    },
+    {
+      "epoch": 0.8354927365528072,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.00018037169909582192,
+      "loss": 4.8735,
+      "step": 266
+    },
+    {
+      "epoch": 0.8386336866902238,
+      "grad_norm": 1.9375,
+      "learning_rate": 0.00018022332941048972,
+      "loss": 4.5862,
+      "step": 267
+    },
+    {
+      "epoch": 0.8417746368276403,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.00018007446258196916,
+      "loss": 4.6305,
+      "step": 268
+    },
+    {
+      "epoch": 0.844915586965057,
+      "grad_norm": 1.8046875,
+      "learning_rate": 0.00017992509953278644,
+      "loss": 4.7259,
+      "step": 269
+    },
+    {
+      "epoch": 0.8480565371024735,
+      "grad_norm": 1.9765625,
+      "learning_rate": 0.000179775241188543,
+      "loss": 4.7171,
+      "step": 270
+    },
+    {
+      "epoch": 0.8511974872398901,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.0001796248884779095,
+      "loss": 4.5035,
+      "step": 271
+    },
+    {
+      "epoch": 0.8543384373773066,
+      "grad_norm": 1.7265625,
+      "learning_rate": 0.0001794740423326202,
+      "loss": 4.5654,
+      "step": 272
+    },
+    {
+      "epoch": 0.8574793875147232,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00017932270368746723,
+      "loss": 4.7109,
+      "step": 273
+    },
+    {
+      "epoch": 0.8606203376521397,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.00017917087348029464,
+      "loss": 4.6446,
+      "step": 274
+    },
+    {
+      "epoch": 0.8637612877895563,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0001790185526519928,
+      "loss": 4.6444,
+      "step": 275
+    },
+    {
+      "epoch": 0.866902237926973,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00017886574214649235,
+      "loss": 4.6852,
+      "step": 276
+    },
+    {
+      "epoch": 0.8700431880643895,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.0001787124429107585,
+      "loss": 4.6116,
+      "step": 277
+    },
+    {
+      "epoch": 0.8731841382018061,
+      "grad_norm": 1.875,
+      "learning_rate": 0.00017855865589478515,
+      "loss": 4.7119,
+      "step": 278
+    },
+    {
+      "epoch": 0.8763250883392226,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00017840438205158891,
+      "loss": 4.7154,
+      "step": 279
+    },
+    {
+      "epoch": 0.8794660384766392,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00017824962233720332,
+      "loss": 4.7945,
+      "step": 280
+    },
+    {
+      "epoch": 0.8826069886140557,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.00017809437771067272,
+      "loss": 4.7312,
+      "step": 281
+    },
+    {
+      "epoch": 0.8857479387514723,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00017793864913404663,
+      "loss": 4.5674,
+      "step": 282
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00017778243757237352,
+      "loss": 4.6855,
+      "step": 283
+    },
+    {
+      "epoch": 0.8920298390263055,
+      "grad_norm": 2.40625,
+      "learning_rate": 0.00017762574399369485,
+      "loss": 4.7105,
+      "step": 284
+    },
+    {
+      "epoch": 0.8951707891637221,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00017746856936903926,
+      "loss": 4.7111,
+      "step": 285
+    },
+    {
+      "epoch": 0.8983117393011386,
+      "grad_norm": 1.984375,
+      "learning_rate": 0.0001773109146724163,
+      "loss": 4.7511,
+      "step": 286
+    },
+    {
+      "epoch": 0.9014526894385552,
+      "grad_norm": 2.34375,
+      "learning_rate": 0.00017715278088081062,
+      "loss": 4.7156,
+      "step": 287
+    },
+    {
+      "epoch": 0.9045936395759717,
+      "grad_norm": 2.796875,
+      "learning_rate": 0.0001769941689741758,
+      "loss": 4.7225,
+      "step": 288
+    },
+    {
+      "epoch": 0.9077345897133883,
+      "grad_norm": 2.703125,
+      "learning_rate": 0.00017683507993542825,
+      "loss": 4.7426,
+      "step": 289
+    },
+    {
+      "epoch": 0.9108755398508048,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.0001766755147504412,
+      "loss": 4.8524,
+      "step": 290
+    },
+    {
+      "epoch": 0.9140164899882215,
+      "grad_norm": 2.65625,
+      "learning_rate": 0.00017651547440803851,
+      "loss": 4.6249,
+      "step": 291
+    },
+    {
+      "epoch": 0.917157440125638,
+      "grad_norm": 3.125,
+      "learning_rate": 0.00017635495989998864,
+      "loss": 4.8815,
+      "step": 292
+    },
+    {
+      "epoch": 0.9202983902630546,
+      "grad_norm": 2.71875,
+      "learning_rate": 0.00017619397222099848,
+      "loss": 4.7107,
+      "step": 293
+    },
+    {
+      "epoch": 0.9234393404004712,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.00017603251236870702,
+      "loss": 4.5988,
+      "step": 294
+    },
+    {
+      "epoch": 0.9265802905378877,
+      "grad_norm": 2.703125,
+      "learning_rate": 0.0001758705813436794,
+      "loss": 4.43,
+      "step": 295
+    },
+    {
+      "epoch": 0.9297212406753043,
+      "grad_norm": 2.84375,
+      "learning_rate": 0.00017570818014940064,
+      "loss": 4.8238,
+      "step": 296
+    },
+    {
+      "epoch": 0.9328621908127208,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.00017554530979226933,
+      "loss": 4.7022,
+      "step": 297
+    },
+    {
+      "epoch": 0.9360031409501374,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00017538197128159148,
+      "loss": 4.8184,
+      "step": 298
+    },
+    {
+      "epoch": 0.939144091087554,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00017521816562957428,
+      "loss": 4.4714,
+      "step": 299
+    },
+    {
+      "epoch": 0.9422850412249706,
+      "grad_norm": 2.40625,
+      "learning_rate": 0.00017505389385131972,
+      "loss": 4.4407,
+      "step": 300
+    },
+    {
+      "epoch": 0.9454259913623871,
+      "grad_norm": 3.25,
+      "learning_rate": 0.00017488915696481838,
+      "loss": 4.6623,
+      "step": 301
+    },
+    {
+      "epoch": 0.9485669414998037,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00017472395599094317,
+      "loss": 4.6181,
+      "step": 302
+    },
+    {
+      "epoch": 0.9517078916372202,
+      "grad_norm": 2.890625,
+      "learning_rate": 0.00017455829195344293,
+      "loss": 4.6449,
+      "step": 303
+    },
+    {
+      "epoch": 0.9548488417746368,
+      "grad_norm": 6.84375,
+      "learning_rate": 0.00017439216587893604,
+      "loss": 4.538,
+      "step": 304
+    },
+    {
+      "epoch": 0.9579897919120534,
+      "grad_norm": 3.5625,
+      "learning_rate": 0.0001742255787969042,
+      "loss": 4.7436,
+      "step": 305
+    },
+    {
+      "epoch": 0.9611307420494699,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00017405853173968589,
+      "loss": 4.7237,
+      "step": 306
+    },
+    {
+      "epoch": 0.9642716921868866,
+      "grad_norm": 2.3125,
+      "learning_rate": 0.0001738910257424701,
+      "loss": 4.5708,
+      "step": 307
+    },
+    {
+      "epoch": 0.9674126423243031,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00017372306184328985,
+      "loss": 4.4765,
+      "step": 308
+    },
+    {
+      "epoch": 0.9705535924617197,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00017355464108301585,
+      "loss": 4.6697,
+      "step": 309
+    },
+    {
+      "epoch": 0.9736945425991362,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00017338576450534984,
+      "loss": 4.5376,
+      "step": 310
+    },
+    {
+      "epoch": 0.9768354927365528,
+      "grad_norm": 2.671875,
+      "learning_rate": 0.00017321643315681832,
+      "loss": 4.7185,
+      "step": 311
+    },
+    {
+      "epoch": 0.9799764428739693,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.000173046648086766,
+      "loss": 4.6617,
+      "step": 312
+    },
+    {
+      "epoch": 0.9831173930113859,
+      "grad_norm": 3.1875,
+      "learning_rate": 0.00017287641034734934,
+      "loss": 4.7403,
+      "step": 313
+    },
+    {
+      "epoch": 0.9862583431488026,
+      "grad_norm": 2.21875,
+      "learning_rate": 0.00017270572099352993,
+      "loss": 4.5652,
+      "step": 314
+    },
+    {
+      "epoch": 0.9893992932862191,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.000172534581083068,
+      "loss": 4.5723,
+      "step": 315
+    },
+    {
+      "epoch": 0.9925402434236357,
+      "grad_norm": 2.9375,
+      "learning_rate": 0.00017236299167651593,
+      "loss": 4.6485,
+      "step": 316
+    },
+    {
+      "epoch": 0.9956811935610522,
+      "grad_norm": 3.109375,
+      "learning_rate": 0.0001721909538372116,
+      "loss": 4.5751,
+      "step": 317
+    },
+    {
+      "epoch": 0.9988221436984688,
+      "grad_norm": 3.046875,
+      "learning_rate": 0.0001720184686312718,
+      "loss": 4.5623,
+      "step": 318
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1272,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 318,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2355630330845594e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-318/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c048912f6ba3fdf50f66b1635aa253feb31cfba85c9f47fc5603099baef225
+size 5944

checkpoint-636/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen2-7B
+---
+
+# 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 0.11.1

checkpoint-636/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-636/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07d6ee74007904be8bdfc0276e3e9d743b7720aab9a4391f04959f75190460d
+size 161533584

checkpoint-636/added_tokens.json

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

checkpoint-636/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6c59012ea80fa2d5312ce6ffd4d03653dce0d304eb47121ba16c55165d7444
+size 323292010

checkpoint-636/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f540726a21b66ac948a449f0493d515b3e0f5fd4c8fa79d8c5609763375c4b
+size 14244

checkpoint-636/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:569f4c805f3e58d4307eff4de10074f081dc248f83cfce3c3df473761292b689
+size 1064

checkpoint-636/special_tokens_map.json

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

checkpoint-636/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-636/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c048912f6ba3fdf50f66b1635aa253feb31cfba85c9f47fc5603099baef225
+size 5944

checkpoint-954/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen2-7B
+---
+
+# 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 0.11.1

checkpoint-954/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-954/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054c164ed96935e000b99ce00a988bd298fe4270ce2508e6614fb9f549795e7b
+size 161533584

checkpoint-954/added_tokens.json

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