Upload folder using huggingface_hub

sft/README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/CodeQwen1.5-7B-Chat
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/CodeQwen1.5-7B-Chat](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat) on the coding_train dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.1
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

sft/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6d8ccc8fa15e4a68eae9cfc07be7a9fd665e2950f1ab1ce87454918a01311d
+size 640740392

sft/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9933774834437086,
+    "total_flos": 1.0660613606866944e+16,
+    "train_loss": 0.39357583204905194,
+    "train_runtime": 105.2274,
+    "train_samples_per_second": 2.87,
+    "train_steps_per_second": 0.713
+}

sft/checkpoint-19/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/CodeQwen1.5-7B-Chat
+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 0.15.1

sft/checkpoint-19/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

sft/checkpoint-19/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e949436b5189fd3a27c6ad4c7034e756ba3bdb0b1ba3e0da951d38043a45c2a
+size 640740392

sft/checkpoint-19/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5583a43c2cb14a2365e36dffeeb3cc16c2dceddece4c4f90b1d64780f4c23c13
+size 1281737938

sft/checkpoint-19/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

sft/checkpoint-19/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e3bd115fb7914e3157d1cddd28d2440908da5dddf3ed8b9232586a56c11e23
+size 1064

sft/checkpoint-19/special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<fim_pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

sft/checkpoint-19/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 19,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.9129361510276794,
+      "learning_rate": 6.368314950360415e-05,
+      "loss": 0.6959,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 19,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3314290917441536e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

sft/checkpoint-19/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ab81d876582ba955e0e24f982c7c8827663908c50b1d038622e1fa3427e581
+size 5688

sft/checkpoint-75/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/CodeQwen1.5-7B-Chat
+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 0.15.1

sft/checkpoint-75/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

sft/checkpoint-75/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6d8ccc8fa15e4a68eae9cfc07be7a9fd665e2950f1ab1ce87454918a01311d
+size 640740392

sft/checkpoint-75/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1f7b4565f0c8bfbdc4212770fc9b0c5611d740a28987efc99c235dc824fea9
+size 1281737938

sft/checkpoint-75/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

sft/checkpoint-75/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
+size 1064

sft/checkpoint-75/special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<fim_pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

sft/checkpoint-75/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9933774834437086,
+  "eval_steps": 50,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06622516556291391,
+      "grad_norm": 2.831176519393921,
+      "learning_rate": 5e-05,
+      "loss": 1.256,
+      "step": 5
+    },
+    {
+      "epoch": 0.13245033112582782,
+      "grad_norm": 3.2754790782928467,
+      "learning_rate": 9.994504457428558e-05,
+      "loss": 0.5174,
+      "step": 10
+    },
+    {
+      "epoch": 0.1986754966887417,
+      "grad_norm": 4.314864158630371,
+      "learning_rate": 9.8034259378842e-05,
+      "loss": 0.5304,
+      "step": 15
+    },
+    {
+      "epoch": 0.26490066225165565,
+      "grad_norm": 0.8949492573738098,
+      "learning_rate": 9.349531862043952e-05,
+      "loss": 0.4987,
+      "step": 20
+    },
+    {
+      "epoch": 0.33112582781456956,
+      "grad_norm": 1.7747893333435059,
+      "learning_rate": 8.657656676318346e-05,
+      "loss": 0.3812,
+      "step": 25
+    },
+    {
+      "epoch": 0.3973509933774834,
+      "grad_norm": 0.8053502440452576,
+      "learning_rate": 7.765655770625997e-05,
+      "loss": 0.3345,
+      "step": 30
+    },
+    {
+      "epoch": 0.46357615894039733,
+      "grad_norm": 1.1480026245117188,
+      "learning_rate": 6.722334251421665e-05,
+      "loss": 0.3257,
+      "step": 35
+    },
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 1.200183391571045,
+      "learning_rate": 5.584776609860414e-05,
+      "loss": 0.28,
+      "step": 40
+    },
+    {
+      "epoch": 0.5960264900662252,
+      "grad_norm": 1.2405061721801758,
+      "learning_rate": 4.415223390139588e-05,
+      "loss": 0.2278,
+      "step": 45
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "grad_norm": 1.8566575050354004,
+      "learning_rate": 3.277665748578336e-05,
+      "loss": 0.2934,
+      "step": 50
+    },
+    {
+      "epoch": 0.7284768211920529,
+      "grad_norm": 1.3541169166564941,
+      "learning_rate": 2.234344229374003e-05,
+      "loss": 0.2716,
+      "step": 55
+    },
+    {
+      "epoch": 0.7947019867549668,
+      "grad_norm": 2.3510825634002686,
+      "learning_rate": 1.3423433236816563e-05,
+      "loss": 0.2924,
+      "step": 60
+    },
+    {
+      "epoch": 0.8609271523178808,
+      "grad_norm": 1.2402220964431763,
+      "learning_rate": 6.50468137956049e-06,
+      "loss": 0.2178,
+      "step": 65
+    },
+    {
+      "epoch": 0.9271523178807947,
+      "grad_norm": 0.5436655282974243,
+      "learning_rate": 1.9657406211579966e-06,
+      "loss": 0.2539,
+      "step": 70
+    },
+    {
+      "epoch": 0.9933774834437086,
+      "grad_norm": 1.2217155694961548,
+      "learning_rate": 5.4955425714431353e-08,
+      "loss": 0.2228,
+      "step": 75
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0660613606866944e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

sft/checkpoint-75/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07545fdccab9d22d92a4f45ed6c4fbd7b3a1c60cec794ebaffadcd66d6bfd3bf
+size 5688

sft/special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<fim_pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

sft/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9933774834437086,
+    "total_flos": 1.0660613606866944e+16,
+    "train_loss": 0.39357583204905194,
+    "train_runtime": 105.2274,
+    "train_samples_per_second": 2.87,
+    "train_steps_per_second": 0.713
+}

sft/trainer_log.jsonl

@@ -0,0 +1,16 @@
+{"current_steps": 5, "total_steps": 75, "loss": 1.256, "lr": 5e-05, "epoch": 0.06622516556291391, "percentage": 6.67, "elapsed_time": "0:00:06", "remaining_time": "0:01:37"}
+{"current_steps": 10, "total_steps": 75, "loss": 0.5174, "lr": 9.994504457428558e-05, "epoch": 0.13245033112582782, "percentage": 13.33, "elapsed_time": "0:00:12", "remaining_time": "0:01:19"}
+{"current_steps": 15, "total_steps": 75, "loss": 0.5304, "lr": 9.8034259378842e-05, "epoch": 0.1986754966887417, "percentage": 20.0, "elapsed_time": "0:00:20", "remaining_time": "0:01:20"}
+{"current_steps": 20, "total_steps": 75, "loss": 0.4987, "lr": 9.349531862043952e-05, "epoch": 0.26490066225165565, "percentage": 26.67, "elapsed_time": "0:00:26", "remaining_time": "0:01:11"}
+{"current_steps": 25, "total_steps": 75, "loss": 0.3812, "lr": 8.657656676318346e-05, "epoch": 0.33112582781456956, "percentage": 33.33, "elapsed_time": "0:00:32", "remaining_time": "0:01:04"}
+{"current_steps": 30, "total_steps": 75, "loss": 0.3345, "lr": 7.765655770625997e-05, "epoch": 0.3973509933774834, "percentage": 40.0, "elapsed_time": "0:00:37", "remaining_time": "0:00:56"}
+{"current_steps": 35, "total_steps": 75, "loss": 0.3257, "lr": 6.722334251421665e-05, "epoch": 0.46357615894039733, "percentage": 46.67, "elapsed_time": "0:00:43", "remaining_time": "0:00:50"}
+{"current_steps": 40, "total_steps": 75, "loss": 0.28, "lr": 5.584776609860414e-05, "epoch": 0.5298013245033113, "percentage": 53.33, "elapsed_time": "0:00:50", "remaining_time": "0:00:44"}
+{"current_steps": 45, "total_steps": 75, "loss": 0.2278, "lr": 4.415223390139588e-05, "epoch": 0.5960264900662252, "percentage": 60.0, "elapsed_time": "0:00:56", "remaining_time": "0:00:37"}
+{"current_steps": 50, "total_steps": 75, "loss": 0.2934, "lr": 3.277665748578336e-05, "epoch": 0.6622516556291391, "percentage": 66.67, "elapsed_time": "0:01:02", "remaining_time": "0:00:31"}
+{"current_steps": 55, "total_steps": 75, "loss": 0.2716, "lr": 2.234344229374003e-05, "epoch": 0.7284768211920529, "percentage": 73.33, "elapsed_time": "0:01:09", "remaining_time": "0:00:25"}
+{"current_steps": 60, "total_steps": 75, "loss": 0.2924, "lr": 1.3423433236816563e-05, "epoch": 0.7947019867549668, "percentage": 80.0, "elapsed_time": "0:01:18", "remaining_time": "0:00:19"}
+{"current_steps": 65, "total_steps": 75, "loss": 0.2178, "lr": 6.50468137956049e-06, "epoch": 0.8609271523178808, "percentage": 86.67, "elapsed_time": "0:01:24", "remaining_time": "0:00:13"}
+{"current_steps": 70, "total_steps": 75, "loss": 0.2539, "lr": 1.9657406211579966e-06, "epoch": 0.9271523178807947, "percentage": 93.33, "elapsed_time": "0:01:33", "remaining_time": "0:00:06"}
+{"current_steps": 75, "total_steps": 75, "loss": 0.2228, "lr": 5.4955425714431353e-08, "epoch": 0.9933774834437086, "percentage": 100.0, "elapsed_time": "0:01:40", "remaining_time": "0:00:00"}
+{"current_steps": 75, "total_steps": 75, "epoch": 0.9933774834437086, "percentage": 100.0, "elapsed_time": "0:01:43", "remaining_time": "0:00:00"}

sft/trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9933774834437086,
+  "eval_steps": 50,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06622516556291391,
+      "grad_norm": 2.831176519393921,
+      "learning_rate": 5e-05,
+      "loss": 1.256,
+      "step": 5
+    },
+    {
+      "epoch": 0.13245033112582782,
+      "grad_norm": 3.2754790782928467,
+      "learning_rate": 9.994504457428558e-05,
+      "loss": 0.5174,
+      "step": 10
+    },
+    {
+      "epoch": 0.1986754966887417,
+      "grad_norm": 4.314864158630371,
+      "learning_rate": 9.8034259378842e-05,
+      "loss": 0.5304,
+      "step": 15
+    },
+    {
+      "epoch": 0.26490066225165565,
+      "grad_norm": 0.8949492573738098,
+      "learning_rate": 9.349531862043952e-05,
+      "loss": 0.4987,
+      "step": 20
+    },
+    {
+      "epoch": 0.33112582781456956,
+      "grad_norm": 1.7747893333435059,
+      "learning_rate": 8.657656676318346e-05,
+      "loss": 0.3812,
+      "step": 25
+    },
+    {
+      "epoch": 0.3973509933774834,
+      "grad_norm": 0.8053502440452576,
+      "learning_rate": 7.765655770625997e-05,
+      "loss": 0.3345,
+      "step": 30
+    },
+    {
+      "epoch": 0.46357615894039733,
+      "grad_norm": 1.1480026245117188,
+      "learning_rate": 6.722334251421665e-05,
+      "loss": 0.3257,
+      "step": 35
+    },
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 1.200183391571045,
+      "learning_rate": 5.584776609860414e-05,
+      "loss": 0.28,
+      "step": 40
+    },
+    {
+      "epoch": 0.5960264900662252,
+      "grad_norm": 1.2405061721801758,
+      "learning_rate": 4.415223390139588e-05,
+      "loss": 0.2278,
+      "step": 45
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "grad_norm": 1.8566575050354004,
+      "learning_rate": 3.277665748578336e-05,
+      "loss": 0.2934,
+      "step": 50
+    },
+    {
+      "epoch": 0.7284768211920529,
+      "grad_norm": 1.3541169166564941,
+      "learning_rate": 2.234344229374003e-05,
+      "loss": 0.2716,
+      "step": 55
+    },
+    {
+      "epoch": 0.7947019867549668,
+      "grad_norm": 2.3510825634002686,
+      "learning_rate": 1.3423433236816563e-05,
+      "loss": 0.2924,
+      "step": 60
+    },
+    {
+      "epoch": 0.8609271523178808,
+      "grad_norm": 1.2402220964431763,
+      "learning_rate": 6.50468137956049e-06,
+      "loss": 0.2178,
+      "step": 65
+    },
+    {
+      "epoch": 0.9271523178807947,
+      "grad_norm": 0.5436655282974243,
+      "learning_rate": 1.9657406211579966e-06,
+      "loss": 0.2539,
+      "step": 70
+    },
+    {
+      "epoch": 0.9933774834437086,
+      "grad_norm": 1.2217155694961548,
+      "learning_rate": 5.4955425714431353e-08,
+      "loss": 0.2228,
+      "step": 75
+    },
+    {
+      "epoch": 0.9933774834437086,
+      "step": 75,
+      "total_flos": 1.0660613606866944e+16,
+      "train_loss": 0.39357583204905194,
+      "train_runtime": 105.2274,
+      "train_samples_per_second": 2.87,
+      "train_steps_per_second": 0.713
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0660613606866944e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

sft/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07545fdccab9d22d92a4f45ed6c4fbd7b3a1c60cec794ebaffadcd66d6bfd3bf
+size 5688