Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2024-06-17-19-49-05
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_2024-06-17-19-49-05
+
+This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) on the glaive_toolcall_zh and the glaive_toolcall_en datasets.
+
+## 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1787638372f2802325b733b1571d9ca936b9289c35e57615b1c7d3388036168e
+size 80792096

added_tokens.json

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

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "num_input_tokens_seen": 2965968,
+    "total_flos": 1.2618658999382835e+17,
+    "train_loss": 0.45766232585906985,
+    "train_runtime": 3803.7297,
+    "train_samples_per_second": 1.577,
+    "train_steps_per_second": 0.099
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4696f39a57c4837231038a5681ef750668c779b95285f8a4933a82a3ba745d3a
+size 80792096

checkpoint-100/added_tokens.json

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

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3a402d35184df6a5f4db089a9be2a2fd189b327684b544c97110b5ee635b0e
+size 161810282

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
+size 14512

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
+size 14512

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d58469739bed67d87db1abce3894a977a31f777e839f826ba70688552f1283
+size 1064

checkpoint-100/special_tokens_map.json

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.4841386675834656,
+      "learning_rate": 4.997807075247146e-05,
+      "loss": 0.688,
+      "num_input_tokens_seen": 46776,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3365215063095093,
+      "learning_rate": 4.991232148123761e-05,
+      "loss": 0.763,
+      "num_input_tokens_seen": 85136,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5198595523834229,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 0.6882,
+      "num_input_tokens_seen": 126584,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.40807807445526123,
+      "learning_rate": 4.964990092676263e-05,
+      "loss": 0.6951,
+      "num_input_tokens_seen": 167968,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.439756840467453,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.5008,
+      "num_input_tokens_seen": 206832,
+      "step": 25
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.45932796597480774,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.542,
+      "num_input_tokens_seen": 243656,
+      "step": 30
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.3281826376914978,
+      "learning_rate": 4.893298743830168e-05,
+      "loss": 0.5369,
+      "num_input_tokens_seen": 284016,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2551577389240265,
+      "learning_rate": 4.860940925593703e-05,
+      "loss": 0.4948,
+      "num_input_tokens_seen": 327408,
+      "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5936368107795715,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 0.5244,
+      "num_input_tokens_seen": 363376,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2480110377073288,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.421,
+      "num_input_tokens_seen": 398840,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4601157307624817,
+      "learning_rate": 4.7392794005985326e-05,
+      "loss": 0.4517,
+      "num_input_tokens_seen": 436136,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6387960314750671,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.4661,
+      "num_input_tokens_seen": 475856,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.4365377128124237,
+      "learning_rate": 4.638410650401267e-05,
+      "loss": 0.4928,
+      "num_input_tokens_seen": 514496,
+      "step": 65
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2992519438266754,
+      "learning_rate": 4.5823031017752485e-05,
+      "loss": 0.5424,
+      "num_input_tokens_seen": 554424,
+      "step": 70
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.828787088394165,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.5419,
+      "num_input_tokens_seen": 593264,
+      "step": 75
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2943418622016907,
+      "learning_rate": 4.4592336433146e-05,
+      "loss": 0.4558,
+      "num_input_tokens_seen": 630264,
+      "step": 80
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3707512617111206,
+      "learning_rate": 4.3924876391293915e-05,
+      "loss": 0.5656,
+      "num_input_tokens_seen": 668864,
+      "step": 85
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4809654653072357,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 0.4832,
+      "num_input_tokens_seen": 712504,
+      "step": 90
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.516292929649353,
+      "learning_rate": 4.249158351283414e-05,
+      "loss": 0.4626,
+      "num_input_tokens_seen": 748872,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5604212284088135,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.4837,
+      "num_input_tokens_seen": 788408,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 375,
+  "num_input_tokens_seen": 788408,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.3542680298389504e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661318f0adf1e9b7779e5ab9012273df3a3e9d25b7c3db616fe15b58a8fb6da7
+size 5304

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d207b8079ce4a5c1ce04f851bff68bdc5fcaefb91cf36ca207025b660ca08b
+size 80792096

checkpoint-200/added_tokens.json

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

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10039ecdef5e22d19b1e466d4028857882e1c6cffe1e3e8e36294c79180ef9a3
+size 161810282

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb795a5cea0baa625c50007a6c9da09c6bbb5c16b560424070384a479e7d8a6
+size 14512

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f19604377bd828eb366c68946ad997a4ff4d69beaeea93ee58915135768ec63
+size 14512

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e8335a86c55e338e659eac99517ff54d99c08ecf9d644c4bf32cc498410e11
+size 1064

checkpoint-200/special_tokens_map.json

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

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,353 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.4841386675834656,
+      "learning_rate": 4.997807075247146e-05,
+      "loss": 0.688,
+      "num_input_tokens_seen": 46776,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3365215063095093,
+      "learning_rate": 4.991232148123761e-05,
+      "loss": 0.763,
+      "num_input_tokens_seen": 85136,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5198595523834229,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 0.6882,
+      "num_input_tokens_seen": 126584,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.40807807445526123,
+      "learning_rate": 4.964990092676263e-05,
+      "loss": 0.6951,
+      "num_input_tokens_seen": 167968,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.439756840467453,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.5008,
+      "num_input_tokens_seen": 206832,
+      "step": 25
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.45932796597480774,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.542,
+      "num_input_tokens_seen": 243656,
+      "step": 30
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.3281826376914978,
+      "learning_rate": 4.893298743830168e-05,
+      "loss": 0.5369,
+      "num_input_tokens_seen": 284016,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2551577389240265,
+      "learning_rate": 4.860940925593703e-05,
+      "loss": 0.4948,
+      "num_input_tokens_seen": 327408,
+      "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5936368107795715,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 0.5244,
+      "num_input_tokens_seen": 363376,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2480110377073288,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.421,
+      "num_input_tokens_seen": 398840,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4601157307624817,
+      "learning_rate": 4.7392794005985326e-05,
+      "loss": 0.4517,
+      "num_input_tokens_seen": 436136,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6387960314750671,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.4661,
+      "num_input_tokens_seen": 475856,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.4365377128124237,
+      "learning_rate": 4.638410650401267e-05,
+      "loss": 0.4928,
+      "num_input_tokens_seen": 514496,
+      "step": 65
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2992519438266754,
+      "learning_rate": 4.5823031017752485e-05,
+      "loss": 0.5424,
+      "num_input_tokens_seen": 554424,
+      "step": 70
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.828787088394165,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.5419,
+      "num_input_tokens_seen": 593264,
+      "step": 75
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2943418622016907,
+      "learning_rate": 4.4592336433146e-05,
+      "loss": 0.4558,
+      "num_input_tokens_seen": 630264,
+      "step": 80
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3707512617111206,
+      "learning_rate": 4.3924876391293915e-05,
+      "loss": 0.5656,
+      "num_input_tokens_seen": 668864,
+      "step": 85
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4809654653072357,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 0.4832,
+      "num_input_tokens_seen": 712504,
+      "step": 90
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.516292929649353,
+      "learning_rate": 4.249158351283414e-05,
+      "loss": 0.4626,
+      "num_input_tokens_seen": 748872,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5604212284088135,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.4837,
+      "num_input_tokens_seen": 788408,
+      "step": 100
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7355071902275085,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 0.5144,
+      "num_input_tokens_seen": 828448,
+      "step": 105
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.46999862790107727,
+      "learning_rate": 4.011497787155938e-05,
+      "loss": 0.493,
+      "num_input_tokens_seen": 864680,
+      "step": 110
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5488362312316895,
+      "learning_rate": 3.92678391921108e-05,
+      "loss": 0.4083,
+      "num_input_tokens_seen": 902568,
+      "step": 115
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5053719282150269,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 0.5172,
+      "num_input_tokens_seen": 944752,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.44234323501586914,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.5843,
+      "num_input_tokens_seen": 988656,
+      "step": 125
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4518623352050781,
+      "learning_rate": 3.6582400877996546e-05,
+      "loss": 0.4567,
+      "num_input_tokens_seen": 1028584,
+      "step": 130
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.39792686700820923,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 0.418,
+      "num_input_tokens_seen": 1065104,
+      "step": 135
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5141780376434326,
+      "learning_rate": 3.4687889661302576e-05,
+      "loss": 0.3785,
+      "num_input_tokens_seen": 1106744,
+      "step": 140
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.5755515098571777,
+      "learning_rate": 3.3714301183045385e-05,
+      "loss": 0.4097,
+      "num_input_tokens_seen": 1140672,
+      "step": 145
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.4626426696777344,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.4507,
+      "num_input_tokens_seen": 1177280,
+      "step": 150
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.49699896574020386,
+      "learning_rate": 3.172299551538164e-05,
+      "loss": 0.368,
+      "num_input_tokens_seen": 1215744,
+      "step": 155
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5842998027801514,
+      "learning_rate": 3.0708771752766394e-05,
+      "loss": 0.4301,
+      "num_input_tokens_seen": 1257040,
+      "step": 160
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.46173322200775146,
+      "learning_rate": 2.9684532864643122e-05,
+      "loss": 0.4488,
+      "num_input_tokens_seen": 1295992,
+      "step": 165
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.4926168918609619,
+      "learning_rate": 2.8652075714060295e-05,
+      "loss": 0.4075,
+      "num_input_tokens_seen": 1334672,
+      "step": 170
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.5110897421836853,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.4991,
+      "num_input_tokens_seen": 1379280,
+      "step": 175
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.33892518281936646,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 0.4894,
+      "num_input_tokens_seen": 1419704,
+      "step": 180
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.46542254090309143,
+      "learning_rate": 2.5523560497083926e-05,
+      "loss": 0.4967,
+      "num_input_tokens_seen": 1459256,
+      "step": 185
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.9100029468536377,
+      "learning_rate": 2.447643950291608e-05,
+      "loss": 0.5297,
+      "num_input_tokens_seen": 1503576,
+      "step": 190
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.7347203493118286,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 0.3939,
+      "num_input_tokens_seen": 1539904,
+      "step": 195
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6078445315361023,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.461,
+      "num_input_tokens_seen": 1580560,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 375,
+  "num_input_tokens_seen": 1580560,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.724464885419213e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661318f0adf1e9b7779e5ab9012273df3a3e9d25b7c3db616fe15b58a8fb6da7
+size 5304

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e63a8bee75ee008ed5a2f979b687b3b7654460a7b4ca59efb18396480cce26
+size 80792096

checkpoint-300/added_tokens.json

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

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69da12865994f4be0a5bb3b1962d3e80e55ba78ef7bb8cfac4a2ccc77e118b03
+size 161810282

checkpoint-300/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
+size 14512

checkpoint-300/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
+size 14512

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549a67e527aab8085b244754e7da9f150ce85bcdffa67b9f8105d2450473be33
+size 1064

checkpoint-300/special_tokens_map.json

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

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,513 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.4841386675834656,
+      "learning_rate": 4.997807075247146e-05,
+      "loss": 0.688,
+      "num_input_tokens_seen": 46776,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3365215063095093,
+      "learning_rate": 4.991232148123761e-05,
+      "loss": 0.763,
+      "num_input_tokens_seen": 85136,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5198595523834229,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 0.6882,
+      "num_input_tokens_seen": 126584,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.40807807445526123,
+      "learning_rate": 4.964990092676263e-05,
+      "loss": 0.6951,
+      "num_input_tokens_seen": 167968,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.439756840467453,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.5008,
+      "num_input_tokens_seen": 206832,
+      "step": 25
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.45932796597480774,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.542,
+      "num_input_tokens_seen": 243656,
+      "step": 30
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.3281826376914978,
+      "learning_rate": 4.893298743830168e-05,
+      "loss": 0.5369,
+      "num_input_tokens_seen": 284016,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2551577389240265,
+      "learning_rate": 4.860940925593703e-05,
+      "loss": 0.4948,
+      "num_input_tokens_seen": 327408,
+      "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5936368107795715,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 0.5244,
+      "num_input_tokens_seen": 363376,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2480110377073288,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.421,
+      "num_input_tokens_seen": 398840,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4601157307624817,
+      "learning_rate": 4.7392794005985326e-05,
+      "loss": 0.4517,
+      "num_input_tokens_seen": 436136,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6387960314750671,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.4661,
+      "num_input_tokens_seen": 475856,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.4365377128124237,
+      "learning_rate": 4.638410650401267e-05,
+      "loss": 0.4928,
+      "num_input_tokens_seen": 514496,
+      "step": 65
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2992519438266754,
+      "learning_rate": 4.5823031017752485e-05,
+      "loss": 0.5424,
+      "num_input_tokens_seen": 554424,
+      "step": 70
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.828787088394165,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.5419,
+      "num_input_tokens_seen": 593264,
+      "step": 75
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2943418622016907,
+      "learning_rate": 4.4592336433146e-05,
+      "loss": 0.4558,
+      "num_input_tokens_seen": 630264,
+      "step": 80
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3707512617111206,
+      "learning_rate": 4.3924876391293915e-05,
+      "loss": 0.5656,
+      "num_input_tokens_seen": 668864,
+      "step": 85
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4809654653072357,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 0.4832,
+      "num_input_tokens_seen": 712504,
+      "step": 90
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.516292929649353,
+      "learning_rate": 4.249158351283414e-05,
+      "loss": 0.4626,
+      "num_input_tokens_seen": 748872,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5604212284088135,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.4837,
+      "num_input_tokens_seen": 788408,
+      "step": 100
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7355071902275085,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 0.5144,
+      "num_input_tokens_seen": 828448,
+      "step": 105
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.46999862790107727,
+      "learning_rate": 4.011497787155938e-05,
+      "loss": 0.493,
+      "num_input_tokens_seen": 864680,
+      "step": 110
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5488362312316895,
+      "learning_rate": 3.92678391921108e-05,
+      "loss": 0.4083,
+      "num_input_tokens_seen": 902568,
+      "step": 115
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5053719282150269,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 0.5172,
+      "num_input_tokens_seen": 944752,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.44234323501586914,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.5843,
+      "num_input_tokens_seen": 988656,
+      "step": 125
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4518623352050781,
+      "learning_rate": 3.6582400877996546e-05,
+      "loss": 0.4567,
+      "num_input_tokens_seen": 1028584,
+      "step": 130
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.39792686700820923,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 0.418,
+      "num_input_tokens_seen": 1065104,
+      "step": 135
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5141780376434326,
+      "learning_rate": 3.4687889661302576e-05,
+      "loss": 0.3785,
+      "num_input_tokens_seen": 1106744,
+      "step": 140
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.5755515098571777,
+      "learning_rate": 3.3714301183045385e-05,
+      "loss": 0.4097,
+      "num_input_tokens_seen": 1140672,
+      "step": 145
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.4626426696777344,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.4507,
+      "num_input_tokens_seen": 1177280,
+      "step": 150
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.49699896574020386,
+      "learning_rate": 3.172299551538164e-05,
+      "loss": 0.368,
+      "num_input_tokens_seen": 1215744,
+      "step": 155
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5842998027801514,
+      "learning_rate": 3.0708771752766394e-05,
+      "loss": 0.4301,
+      "num_input_tokens_seen": 1257040,
+      "step": 160
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.46173322200775146,
+      "learning_rate": 2.9684532864643122e-05,
+      "loss": 0.4488,
+      "num_input_tokens_seen": 1295992,
+      "step": 165
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.4926168918609619,
+      "learning_rate": 2.8652075714060295e-05,
+      "loss": 0.4075,
+      "num_input_tokens_seen": 1334672,
+      "step": 170
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.5110897421836853,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.4991,
+      "num_input_tokens_seen": 1379280,
+      "step": 175
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.33892518281936646,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 0.4894,
+      "num_input_tokens_seen": 1419704,
+      "step": 180
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.46542254090309143,
+      "learning_rate": 2.5523560497083926e-05,
+      "loss": 0.4967,
+      "num_input_tokens_seen": 1459256,
+      "step": 185
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.9100029468536377,
+      "learning_rate": 2.447643950291608e-05,
+      "loss": 0.5297,
+      "num_input_tokens_seen": 1503576,
+      "step": 190
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.7347203493118286,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 0.3939,
+      "num_input_tokens_seen": 1539904,
+      "step": 195
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6078445315361023,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.461,
+      "num_input_tokens_seen": 1580560,
+      "step": 200
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.5878064632415771,
+      "learning_rate": 2.1347924285939714e-05,
+      "loss": 0.4622,
+      "num_input_tokens_seen": 1623608,
+      "step": 205
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.6516324877738953,
+      "learning_rate": 2.031546713535688e-05,
+      "loss": 0.4043,
+      "num_input_tokens_seen": 1660744,
+      "step": 210
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.9136825203895569,
+      "learning_rate": 1.9291228247233605e-05,
+      "loss": 0.428,
+      "num_input_tokens_seen": 1698784,
+      "step": 215
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.751567006111145,
+      "learning_rate": 1.827700448461836e-05,
+      "loss": 0.3779,
+      "num_input_tokens_seen": 1734792,
+      "step": 220
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.8802843689918518,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.4526,
+      "num_input_tokens_seen": 1776144,
+      "step": 225
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.6807656288146973,
+      "learning_rate": 1.6285698816954624e-05,
+      "loss": 0.4627,
+      "num_input_tokens_seen": 1815864,
+      "step": 230
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.6222789883613586,
+      "learning_rate": 1.5312110338697426e-05,
+      "loss": 0.4873,
+      "num_input_tokens_seen": 1856168,
+      "step": 235
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.5224676728248596,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 0.3234,
+      "num_input_tokens_seen": 1899120,
+      "step": 240
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.4191940724849701,
+      "learning_rate": 1.3417599122003464e-05,
+      "loss": 0.4438,
+      "num_input_tokens_seen": 1936808,
+      "step": 245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6064372062683105,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.4407,
+      "num_input_tokens_seen": 1977312,
+      "step": 250
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.5188178420066833,
+      "learning_rate": 1.1604330125525079e-05,
+      "loss": 0.4401,
+      "num_input_tokens_seen": 2018336,
+      "step": 255
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.5036932826042175,
+      "learning_rate": 1.0732160807889211e-05,
+      "loss": 0.3771,
+      "num_input_tokens_seen": 2057776,
+      "step": 260
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.5732894539833069,
+      "learning_rate": 9.88502212844063e-06,
+      "loss": 0.4043,
+      "num_input_tokens_seen": 2102312,
+      "step": 265
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.6521058082580566,
+      "learning_rate": 9.064400256282757e-06,
+      "loss": 0.4018,
+      "num_input_tokens_seen": 2137304,
+      "step": 270
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.698835015296936,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.4258,
+      "num_input_tokens_seen": 2176144,
+      "step": 275
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.7500255107879639,
+      "learning_rate": 7.508416487165862e-06,
+      "loss": 0.3912,
+      "num_input_tokens_seen": 2211640,
+      "step": 280
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7223864793777466,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 0.3458,
+      "num_input_tokens_seen": 2247272,
+      "step": 285
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.6346307992935181,
+      "learning_rate": 6.075123608706093e-06,
+      "loss": 0.4255,
+      "num_input_tokens_seen": 2285776,
+      "step": 290
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.6048356890678406,
+      "learning_rate": 5.4076635668540075e-06,
+      "loss": 0.4222,
+      "num_input_tokens_seen": 2326112,
+      "step": 295
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.0743402242660522,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.399,
+      "num_input_tokens_seen": 2362816,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 375,
+  "num_input_tokens_seen": 2362816,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.005255938455634e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661318f0adf1e9b7779e5ab9012273df3a3e9d25b7c3db616fe15b58a8fb6da7
+size 5304