Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/CodeQwen1.5-7B-Chat
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2024-07-30-09-22-49
+  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_2024-07-30-09-22-49
+
+This model is a fine-tuned version of [Qwen/CodeQwen1.5-7B-Chat](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat) on the alpaca_finance dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.16.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e073ccabe42b118a635f726ffc9b1e75555230df4c876eb6bef9a0907ec9c2f
+size 80144136

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9984,
+    "num_input_tokens_seen": 4974128,
+    "total_flos": 2.056832720704635e+17,
+    "train_loss": 2.5180979997683792,
+    "train_runtime": 14081.4059,
+    "train_samples_per_second": 1.42,
+    "train_steps_per_second": 0.022
+}

checkpoint-100/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 0.12.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7999bb661c456683453b534dda3776f186de53f050fe23308eb6710014cdd95c
+size 80144136

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbe00fb431f9677245fb9a05c61287a5536476e68da60b2dd1d5071b940edc3
+size 160546898

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:db19d5f82c8e209abcc21a69b82a57aeda11c164a7ca57df1501e44c35224e2b
+size 1064

checkpoint-100/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
+  }
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.3705686628818512,
+      "learning_rate": 0.00019987329060020616,
+      "loss": 2.7276,
+      "num_input_tokens_seen": 78104,
+      "step": 5
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.28178921341896057,
+      "learning_rate": 0.00019949348350626456,
+      "loss": 2.6452,
+      "num_input_tokens_seen": 157384,
+      "step": 10
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.1864372342824936,
+      "learning_rate": 0.00019886154122075343,
+      "loss": 2.5708,
+      "num_input_tokens_seen": 240256,
+      "step": 15
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.1788010597229004,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 2.5831,
+      "num_input_tokens_seen": 319032,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.23142138123512268,
+      "learning_rate": 0.00019684829181681234,
+      "loss": 2.6138,
+      "num_input_tokens_seen": 397992,
+      "step": 25
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.21496976912021637,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 2.5461,
+      "num_input_tokens_seen": 479904,
+      "step": 30
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.2536880671977997,
+      "learning_rate": 0.0001938539372689649,
+      "loss": 2.5797,
+      "num_input_tokens_seen": 555448,
+      "step": 35
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.39764249324798584,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 2.5482,
+      "num_input_tokens_seen": 630888,
+      "step": 40
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.29237431287765503,
+      "learning_rate": 0.00018990881137654258,
+      "loss": 2.4726,
+      "num_input_tokens_seen": 709456,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.24707558751106262,
+      "learning_rate": 0.0001875918325566888,
+      "loss": 2.5557,
+      "num_input_tokens_seen": 788504,
+      "step": 50
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.24359019100666046,
+      "learning_rate": 0.00018505287956623297,
+      "loss": 2.5357,
+      "num_input_tokens_seen": 864984,
+      "step": 55
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.23572562634944916,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 2.4798,
+      "num_input_tokens_seen": 939136,
+      "step": 60
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.41712337732315063,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 2.5619,
+      "num_input_tokens_seen": 1018024,
+      "step": 65
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.2777227759361267,
+      "learning_rate": 0.00017617123081773591,
+      "loss": 2.5334,
+      "num_input_tokens_seen": 1095072,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.25098717212677,
+      "learning_rate": 0.00017281409538757883,
+      "loss": 2.5199,
+      "num_input_tokens_seen": 1172824,
+      "step": 75
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.24321608245372772,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 2.4897,
+      "num_input_tokens_seen": 1244688,
+      "step": 80
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.25580549240112305,
+      "learning_rate": 0.0001655552259402295,
+      "loss": 2.513,
+      "num_input_tokens_seen": 1321104,
+      "step": 85
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.24990542232990265,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 2.5533,
+      "num_input_tokens_seen": 1402456,
+      "step": 90
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.26301833987236023,
+      "learning_rate": 0.00015763226042909455,
+      "loss": 2.5297,
+      "num_input_tokens_seen": 1483648,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.23519474267959595,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 2.518,
+      "num_input_tokens_seen": 1560608,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 1560608,
+  "num_train_epochs": 1,
+  "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": 6.453210669226394e+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:a11e34958bb0166a27197cc6b1af0b4918fc0bb571b674f64d1bed0d949d03fe
+size 5368

checkpoint-200/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 0.12.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee988893364c38dee1a400f2d758e08986c16761348a3f7f2f709abd2531a8d5
+size 80144136

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d5a55a8d2384f839dcf5c2df1cc51fb9fadc35b2958ec26b99c9602b8ae1f5
+size 160546898

checkpoint-200/rng_state_0.pth

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

checkpoint-200/rng_state_1.pth

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

checkpoint-200/scheduler.pt

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

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "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
+  }
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,353 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.64,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.3705686628818512,
+      "learning_rate": 0.00019987329060020616,
+      "loss": 2.7276,
+      "num_input_tokens_seen": 78104,
+      "step": 5
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.28178921341896057,
+      "learning_rate": 0.00019949348350626456,
+      "loss": 2.6452,
+      "num_input_tokens_seen": 157384,
+      "step": 10
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.1864372342824936,
+      "learning_rate": 0.00019886154122075343,
+      "loss": 2.5708,
+      "num_input_tokens_seen": 240256,
+      "step": 15
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.1788010597229004,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 2.5831,
+      "num_input_tokens_seen": 319032,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.23142138123512268,
+      "learning_rate": 0.00019684829181681234,
+      "loss": 2.6138,
+      "num_input_tokens_seen": 397992,
+      "step": 25
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.21496976912021637,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 2.5461,
+      "num_input_tokens_seen": 479904,
+      "step": 30
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.2536880671977997,
+      "learning_rate": 0.0001938539372689649,
+      "loss": 2.5797,
+      "num_input_tokens_seen": 555448,
+      "step": 35
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.39764249324798584,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 2.5482,
+      "num_input_tokens_seen": 630888,
+      "step": 40
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.29237431287765503,
+      "learning_rate": 0.00018990881137654258,
+      "loss": 2.4726,
+      "num_input_tokens_seen": 709456,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.24707558751106262,
+      "learning_rate": 0.0001875918325566888,
+      "loss": 2.5557,
+      "num_input_tokens_seen": 788504,
+      "step": 50
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.24359019100666046,
+      "learning_rate": 0.00018505287956623297,
+      "loss": 2.5357,
+      "num_input_tokens_seen": 864984,
+      "step": 55
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.23572562634944916,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 2.4798,
+      "num_input_tokens_seen": 939136,
+      "step": 60
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.41712337732315063,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 2.5619,
+      "num_input_tokens_seen": 1018024,
+      "step": 65
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.2777227759361267,
+      "learning_rate": 0.00017617123081773591,
+      "loss": 2.5334,
+      "num_input_tokens_seen": 1095072,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.25098717212677,
+      "learning_rate": 0.00017281409538757883,
+      "loss": 2.5199,
+      "num_input_tokens_seen": 1172824,
+      "step": 75
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.24321608245372772,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 2.4897,
+      "num_input_tokens_seen": 1244688,
+      "step": 80
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.25580549240112305,
+      "learning_rate": 0.0001655552259402295,
+      "loss": 2.513,
+      "num_input_tokens_seen": 1321104,
+      "step": 85
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.24990542232990265,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 2.5533,
+      "num_input_tokens_seen": 1402456,
+      "step": 90
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.26301833987236023,
+      "learning_rate": 0.00015763226042909455,
+      "loss": 2.5297,
+      "num_input_tokens_seen": 1483648,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.23519474267959595,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 2.518,
+      "num_input_tokens_seen": 1560608,
+      "step": 100
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.26162955164909363,
+      "learning_rate": 0.00014912546110838775,
+      "loss": 2.5537,
+      "num_input_tokens_seen": 1640728,
+      "step": 105
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.2565276026725769,
+      "learning_rate": 0.00014467984645016258,
+      "loss": 2.489,
+      "num_input_tokens_seen": 1722440,
+      "step": 110
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.3414108455181122,
+      "learning_rate": 0.00014012100466140578,
+      "loss": 2.5448,
+      "num_input_tokens_seen": 1805984,
+      "step": 115
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.2590246796607971,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 2.4148,
+      "num_input_tokens_seen": 1890592,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2765924036502838,
+      "learning_rate": 0.00013071010920229909,
+      "loss": 2.5512,
+      "num_input_tokens_seen": 1971272,
+      "step": 125
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.2582058906555176,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 2.5264,
+      "num_input_tokens_seen": 2053352,
+      "step": 130
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.2416098713874817,
+      "learning_rate": 0.00012098811020648475,
+      "loss": 2.5525,
+      "num_input_tokens_seen": 2132624,
+      "step": 135
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.3602483868598938,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 2.5029,
+      "num_input_tokens_seen": 2210376,
+      "step": 140
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.2507006824016571,
+      "learning_rate": 0.000111053494730832,
+      "loss": 2.5546,
+      "num_input_tokens_seen": 2292896,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.32158130407333374,
+      "learning_rate": 0.00010603784974222861,
+      "loss": 2.5431,
+      "num_input_tokens_seen": 2376432,
+      "step": 150
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.3036045730113983,
+      "learning_rate": 0.00010100690370728755,
+      "loss": 2.4882,
+      "num_input_tokens_seen": 2451848,
+      "step": 155
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.31646254658699036,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 2.4319,
+      "num_input_tokens_seen": 2532816,
+      "step": 160
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.2881500720977783,
+      "learning_rate": 9.095011241703623e-05,
+      "loss": 2.4688,
+      "num_input_tokens_seen": 2616160,
+      "step": 165
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.27659812569618225,
+      "learning_rate": 8.594975296149076e-05,
+      "loss": 2.5149,
+      "num_input_tokens_seen": 2694864,
+      "step": 170
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.4290514290332794,
+      "learning_rate": 8.098499947332934e-05,
+      "loss": 2.4754,
+      "num_input_tokens_seen": 2770464,
+      "step": 175
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.28775912523269653,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 2.4875,
+      "num_input_tokens_seen": 2852888,
+      "step": 180
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.2709747850894928,
+      "learning_rate": 7.121251475752539e-05,
+      "loss": 2.563,
+      "num_input_tokens_seen": 2933520,
+      "step": 185
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.3473074734210968,
+      "learning_rate": 6.642954884333955e-05,
+      "loss": 2.4903,
+      "num_input_tokens_seen": 3011656,
+      "step": 190
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.28855767846107483,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.5325,
+      "num_input_tokens_seen": 3088960,
+      "step": 195
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.27710187435150146,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 2.4344,
+      "num_input_tokens_seen": 3165160,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 3165160,
+  "num_train_epochs": 1,
+  "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": 1.30881325463765e+17,
+  "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:a11e34958bb0166a27197cc6b1af0b4918fc0bb571b674f64d1bed0d949d03fe
+size 5368

checkpoint-300/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 0.12.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93eb4fb52d911ba38388ae2500a4b98bde499258c2f31c8125fbd3b03c5cd2d
+size 80144136

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3bddffd22dcaf20069a4514e9e8932bf5ccdb0bd0f9b6996febf2ef7e789c0
+size 160546898

checkpoint-300/rng_state_0.pth

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

checkpoint-300/rng_state_1.pth

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

checkpoint-300/scheduler.pt

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

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "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
+  }
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,513 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.96,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.3705686628818512,
+      "learning_rate": 0.00019987329060020616,
+      "loss": 2.7276,
+      "num_input_tokens_seen": 78104,
+      "step": 5
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.28178921341896057,
+      "learning_rate": 0.00019949348350626456,
+      "loss": 2.6452,
+      "num_input_tokens_seen": 157384,
+      "step": 10
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.1864372342824936,
+      "learning_rate": 0.00019886154122075343,
+      "loss": 2.5708,
+      "num_input_tokens_seen": 240256,
+      "step": 15
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.1788010597229004,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 2.5831,
+      "num_input_tokens_seen": 319032,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.23142138123512268,
+      "learning_rate": 0.00019684829181681234,
+      "loss": 2.6138,
+      "num_input_tokens_seen": 397992,
+      "step": 25
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.21496976912021637,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 2.5461,
+      "num_input_tokens_seen": 479904,
+      "step": 30
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.2536880671977997,
+      "learning_rate": 0.0001938539372689649,
+      "loss": 2.5797,
+      "num_input_tokens_seen": 555448,
+      "step": 35
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.39764249324798584,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 2.5482,
+      "num_input_tokens_seen": 630888,
+      "step": 40
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.29237431287765503,
+      "learning_rate": 0.00018990881137654258,
+      "loss": 2.4726,
+      "num_input_tokens_seen": 709456,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.24707558751106262,
+      "learning_rate": 0.0001875918325566888,
+      "loss": 2.5557,
+      "num_input_tokens_seen": 788504,
+      "step": 50
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.24359019100666046,
+      "learning_rate": 0.00018505287956623297,
+      "loss": 2.5357,
+      "num_input_tokens_seen": 864984,
+      "step": 55
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.23572562634944916,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 2.4798,
+      "num_input_tokens_seen": 939136,
+      "step": 60
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.41712337732315063,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 2.5619,
+      "num_input_tokens_seen": 1018024,
+      "step": 65
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.2777227759361267,
+      "learning_rate": 0.00017617123081773591,
+      "loss": 2.5334,
+      "num_input_tokens_seen": 1095072,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.25098717212677,
+      "learning_rate": 0.00017281409538757883,
+      "loss": 2.5199,
+      "num_input_tokens_seen": 1172824,
+      "step": 75
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.24321608245372772,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 2.4897,
+      "num_input_tokens_seen": 1244688,
+      "step": 80
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.25580549240112305,
+      "learning_rate": 0.0001655552259402295,
+      "loss": 2.513,
+      "num_input_tokens_seen": 1321104,
+      "step": 85
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.24990542232990265,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 2.5533,
+      "num_input_tokens_seen": 1402456,
+      "step": 90
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.26301833987236023,
+      "learning_rate": 0.00015763226042909455,
+      "loss": 2.5297,
+      "num_input_tokens_seen": 1483648,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.23519474267959595,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 2.518,
+      "num_input_tokens_seen": 1560608,
+      "step": 100
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.26162955164909363,
+      "learning_rate": 0.00014912546110838775,
+      "loss": 2.5537,
+      "num_input_tokens_seen": 1640728,
+      "step": 105
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.2565276026725769,
+      "learning_rate": 0.00014467984645016258,
+      "loss": 2.489,
+      "num_input_tokens_seen": 1722440,
+      "step": 110
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.3414108455181122,
+      "learning_rate": 0.00014012100466140578,
+      "loss": 2.5448,
+      "num_input_tokens_seen": 1805984,
+      "step": 115
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.2590246796607971,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 2.4148,
+      "num_input_tokens_seen": 1890592,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2765924036502838,
+      "learning_rate": 0.00013071010920229909,
+      "loss": 2.5512,
+      "num_input_tokens_seen": 1971272,
+      "step": 125
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.2582058906555176,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 2.5264,
+      "num_input_tokens_seen": 2053352,
+      "step": 130
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.2416098713874817,
+      "learning_rate": 0.00012098811020648475,
+      "loss": 2.5525,
+      "num_input_tokens_seen": 2132624,
+      "step": 135
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.3602483868598938,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 2.5029,
+      "num_input_tokens_seen": 2210376,
+      "step": 140
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.2507006824016571,
+      "learning_rate": 0.000111053494730832,
+      "loss": 2.5546,
+      "num_input_tokens_seen": 2292896,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.32158130407333374,
+      "learning_rate": 0.00010603784974222861,
+      "loss": 2.5431,
+      "num_input_tokens_seen": 2376432,
+      "step": 150
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.3036045730113983,
+      "learning_rate": 0.00010100690370728755,
+      "loss": 2.4882,
+      "num_input_tokens_seen": 2451848,
+      "step": 155
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.31646254658699036,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 2.4319,
+      "num_input_tokens_seen": 2532816,
+      "step": 160
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.2881500720977783,
+      "learning_rate": 9.095011241703623e-05,
+      "loss": 2.4688,
+      "num_input_tokens_seen": 2616160,
+      "step": 165
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.27659812569618225,
+      "learning_rate": 8.594975296149076e-05,
+      "loss": 2.5149,
+      "num_input_tokens_seen": 2694864,
+      "step": 170
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.4290514290332794,
+      "learning_rate": 8.098499947332934e-05,
+      "loss": 2.4754,
+      "num_input_tokens_seen": 2770464,
+      "step": 175
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.28775912523269653,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 2.4875,
+      "num_input_tokens_seen": 2852888,
+      "step": 180
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.2709747850894928,
+      "learning_rate": 7.121251475752539e-05,
+      "loss": 2.563,
+      "num_input_tokens_seen": 2933520,
+      "step": 185
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.3473074734210968,
+      "learning_rate": 6.642954884333955e-05,
+      "loss": 2.4903,
+      "num_input_tokens_seen": 3011656,
+      "step": 190
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.28855767846107483,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.5325,
+      "num_input_tokens_seen": 3088960,
+      "step": 195
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.27710187435150146,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 2.4344,
+      "num_input_tokens_seen": 3165160,
+      "step": 200
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.3773224651813507,
+      "learning_rate": 5.263846971020108e-05,
+      "loss": 2.4747,
+      "num_input_tokens_seen": 3242128,
+      "step": 205
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.3007236123085022,
+      "learning_rate": 4.826621858223431e-05,
+      "loss": 2.4753,
+      "num_input_tokens_seen": 3323840,
+      "step": 210
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.2919347286224365,
+      "learning_rate": 4.40250705821178e-05,
+      "loss": 2.513,
+      "num_input_tokens_seen": 3404144,
+      "step": 215
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.26084381341934204,
+      "learning_rate": 3.99257735762021e-05,
+      "loss": 2.5244,
+      "num_input_tokens_seen": 3481992,
+      "step": 220
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.3810001611709595,
+      "learning_rate": 3.597871595375121e-05,
+      "loss": 2.4893,
+      "num_input_tokens_seen": 3562480,
+      "step": 225
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.2814476191997528,
+      "learning_rate": 3.219390030081091e-05,
+      "loss": 2.5374,
+      "num_input_tokens_seen": 3648552,
+      "step": 230
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.2949189841747284,
+      "learning_rate": 2.858091805177554e-05,
+      "loss": 2.4568,
+      "num_input_tokens_seen": 3720616,
+      "step": 235
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.32114091515541077,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 2.4686,
+      "num_input_tokens_seen": 3804368,
+      "step": 240
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.30282753705978394,
+      "learning_rate": 2.1906619009284257e-05,
+      "loss": 2.5268,
+      "num_input_tokens_seen": 3880720,
+      "step": 245
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.25529351830482483,
+      "learning_rate": 1.8862216144342692e-05,
+      "loss": 2.4932,
+      "num_input_tokens_seen": 3970064,
+      "step": 250
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.25532060861587524,
+      "learning_rate": 1.6023431677260214e-05,
+      "loss": 2.4882,
+      "num_input_tokens_seen": 4052712,
+      "step": 255
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.32484114170074463,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.5897,
+      "num_input_tokens_seen": 4133104,
+      "step": 260
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.2640307545661926,
+      "learning_rate": 1.0990954684091558e-05,
+      "loss": 2.4555,
+      "num_input_tokens_seen": 4213160,
+      "step": 265
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.6774325370788574,
+      "learning_rate": 8.810015400790994e-06,
+      "loss": 2.5311,
+      "num_input_tokens_seen": 4294240,
+      "step": 270
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.3231619596481323,
+      "learning_rate": 6.860168681805945e-06,
+      "loss": 2.4318,
+      "num_input_tokens_seen": 4373680,
+      "step": 275
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.29059651494026184,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 2.4513,
+      "num_input_tokens_seen": 4452712,
+      "step": 280
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.4263499975204468,
+      "learning_rate": 3.6729198952483724e-06,
+      "loss": 2.4889,
+      "num_input_tokens_seen": 4531416,
+      "step": 285
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.3342815935611725,
+      "learning_rate": 2.4435949152906145e-06,
+      "loss": 2.5461,
+      "num_input_tokens_seen": 4617984,
+      "step": 290
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.2988833785057068,
+      "learning_rate": 1.4614962060194304e-06,
+      "loss": 2.4965,
+      "num_input_tokens_seen": 4698024,
+      "step": 295
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2836878299713135,
+      "learning_rate": 7.291125901946027e-07,
+      "loss": 2.5403,
+      "num_input_tokens_seen": 4779504,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 4779504,
+  "num_train_epochs": 1,
+  "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": 1.9763544932430643e+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:a11e34958bb0166a27197cc6b1af0b4918fc0bb571b674f64d1bed0d949d03fe
+size 5368

checkpoint-312/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 0.12.0

checkpoint-312/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-312/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e073ccabe42b118a635f726ffc9b1e75555230df4c876eb6bef9a0907ec9c2f
+size 80144136

checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc22c2ffbdef912954b1c7a91fba73d75e78dcba6f2abe00f751c8ca2f6331be
+size 160546898

checkpoint-312/rng_state_0.pth

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

checkpoint-312/rng_state_1.pth

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

checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07515c2b046d99c3743a994e794dd47b173671b79b64b92ecc764813da2c450b
+size 1064

checkpoint-312/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
+  }
+}