Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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 0.7.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/data_large/ccy/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1859cc173c38e0f05981b2c56c93ac699c344c6c820b3ffbed3fd66ec5824eab
+size 536906096

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.99,
+    "train_loss": 0.919522538692889,
+    "train_runtime": 22845.2596,
+    "train_samples": 13533,
+    "train_samples_per_second": 2.37,
+    "train_steps_per_second": 0.074
+}

checkpoint-1268/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /mnt/data_large/ccy/Llama-2-7b-hf
+---
+
+# 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 0.7.1

checkpoint-1268/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/data_large/ccy/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1268/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918ba67576dfb282162108698fae489071f4de24dca6d4c751e20c11fd7b7b1d
+size 536906096

checkpoint-1268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a38f753e10caea5d384c06fa52bda80c8fbb41366033e1e6eaa252fcbb80b0
+size 14244

checkpoint-1268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065504389cd16f2d91e511461d61631d15f88f180be762e46ac01340795e4711
+size 1064

checkpoint-1268/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1268/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fd05faa475f5ea09145da8181858be9d5440fb2c8d86f380c3fb0a9ba1c01b
+size 5048

checkpoint-1688/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /mnt/data_large/ccy/Llama-2-7b-hf
+---
+
+# 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 0.7.1

checkpoint-1688/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/data_large/ccy/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1688/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1859cc173c38e0f05981b2c56c93ac699c344c6c820b3ffbed3fd66ec5824eab
+size 536906096

checkpoint-1688/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed510da765d7528239c019f96e5b113502b9076e6877f36b1ef71dec9407ac7
+size 14244

checkpoint-1688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7b46e58b36711ce4d0c11a744b6a236cdbd186ba673b47a6a0bf50ff772c1e
+size 1064

checkpoint-1688/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1688/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1688/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fd05faa475f5ea09145da8181858be9d5440fb2c8d86f380c3fb0a9ba1c01b
+size 5048

checkpoint-422/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /mnt/data_large/ccy/Llama-2-7b-hf
+---
+
+# 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 0.7.1

checkpoint-422/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/data_large/ccy/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-422/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403dbafa3daffbd5348258f01a709f0e284bb3b658137302dbe544ab22683ed5
+size 536906096

checkpoint-422/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b9070fedd63094044d883c4d878793b52d473110b2a7fdd9a17fa930d5bb15
+size 14244

checkpoint-422/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fcea01ed6559d0ccfde485502a8166b43f9af46ad085b19f2b12bb8f79cb91e
+size 1064

checkpoint-422/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-422/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-422/trainer_state.json

@@ -0,0 +1,2553 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9978570900761102,
+  "eval_steps": 500,
+  "global_step": 422,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 2.8563,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.843137254901962e-07,
+      "loss": 3.0208,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 4.0651,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5686274509803923e-06,
+      "loss": 3.3154,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 3.9875,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 9.4198,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.7450980392156867e-06,
+      "loss": 3.4956,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.1372549019607846e-06,
+      "loss": 3.646,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 2.9569,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 3.2712,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.313725490196079e-06,
+      "loss": 4.4552,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 3.2141,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.098039215686274e-06,
+      "loss": 2.8645,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.4901960784313735e-06,
+      "loss": 2.9299,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 3.2333,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.274509803921569e-06,
+      "loss": 3.3361,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.8326,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 5.9936,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.450980392156863e-06,
+      "loss": 2.7551,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 2.3296,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 2.1901,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.627450980392157e-06,
+      "loss": 1.7673,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.019607843137256e-06,
+      "loss": 1.6721,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 1.7151,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 1.7576,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.0196078431372549e-05,
+      "loss": 1.4461,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.0588235294117648e-05,
+      "loss": 3.8357,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.0980392156862747e-05,
+      "loss": 1.5292,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1372549019607844e-05,
+      "loss": 1.484,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 1.2995,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.215686274509804e-05,
+      "loss": 1.1459,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2549019607843138e-05,
+      "loss": 1.1017,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2941176470588238e-05,
+      "loss": 1.2681,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.7749,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3725490196078432e-05,
+      "loss": 1.4039,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4117647058823532e-05,
+      "loss": 1.304,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4509803921568629e-05,
+      "loss": 1.1641,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4901960784313726e-05,
+      "loss": 1.0715,
+      "step": 38
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5294117647058822e-05,
+      "loss": 1.0567,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.568627450980392e-05,
+      "loss": 1.3111,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.607843137254902e-05,
+      "loss": 1.4909,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.647058823529412e-05,
+      "loss": 0.961,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.686274509803922e-05,
+      "loss": 1.1519,
+      "step": 43
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.7254901960784314e-05,
+      "loss": 0.9403,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 1.1603,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.8039215686274513e-05,
+      "loss": 0.9909,
+      "step": 46
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.843137254901961e-05,
+      "loss": 1.0872,
+      "step": 47
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.8823529411764708e-05,
+      "loss": 1.0935,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9215686274509807e-05,
+      "loss": 1.2776,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9607843137254903e-05,
+      "loss": 1.0812,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 1.0436,
+      "step": 51
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9987782529016497e-05,
+      "loss": 1.275,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.997556505803299e-05,
+      "loss": 1.1309,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9963347587049484e-05,
+      "loss": 1.0838,
+      "step": 54
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9951130116065975e-05,
+      "loss": 1.0861,
+      "step": 55
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.993891264508247e-05,
+      "loss": 0.9737,
+      "step": 56
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9926695174098962e-05,
+      "loss": 0.9726,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9914477703115457e-05,
+      "loss": 1.1044,
+      "step": 58
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9902260232131952e-05,
+      "loss": 1.2198,
+      "step": 59
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9890042761148444e-05,
+      "loss": 1.2454,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.987782529016494e-05,
+      "loss": 1.0945,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.986560781918143e-05,
+      "loss": 1.2243,
+      "step": 62
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9853390348197926e-05,
+      "loss": 1.0895,
+      "step": 63
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9841172877214418e-05,
+      "loss": 1.3153,
+      "step": 64
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9828955406230913e-05,
+      "loss": 1.3891,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9816737935247404e-05,
+      "loss": 1.1219,
+      "step": 66
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.98045204642639e-05,
+      "loss": 1.0493,
+      "step": 67
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.979230299328039e-05,
+      "loss": 1.0645,
+      "step": 68
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9780085522296886e-05,
+      "loss": 1.3425,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9767868051313378e-05,
+      "loss": 1.8974,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9755650580329873e-05,
+      "loss": 1.0191,
+      "step": 71
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9743433109346365e-05,
+      "loss": 1.1784,
+      "step": 72
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.973121563836286e-05,
+      "loss": 1.0353,
+      "step": 73
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9718998167379355e-05,
+      "loss": 1.2755,
+      "step": 74
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.970678069639585e-05,
+      "loss": 0.9851,
+      "step": 75
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9694563225412342e-05,
+      "loss": 1.2396,
+      "step": 76
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9682345754428837e-05,
+      "loss": 1.2519,
+      "step": 77
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.967012828344533e-05,
+      "loss": 0.9313,
+      "step": 78
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9657910812461824e-05,
+      "loss": 1.1745,
+      "step": 79
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9645693341478315e-05,
+      "loss": 1.0521,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.963347587049481e-05,
+      "loss": 0.9781,
+      "step": 81
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9621258399511302e-05,
+      "loss": 1.0292,
+      "step": 82
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9609040928527797e-05,
+      "loss": 0.851,
+      "step": 83
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.959682345754429e-05,
+      "loss": 1.1486,
+      "step": 84
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9584605986560784e-05,
+      "loss": 1.0732,
+      "step": 85
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9572388515577276e-05,
+      "loss": 1.0466,
+      "step": 86
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.956017104459377e-05,
+      "loss": 0.9275,
+      "step": 87
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9547953573610263e-05,
+      "loss": 1.7509,
+      "step": 88
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9535736102626758e-05,
+      "loss": 1.3038,
+      "step": 89
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9523518631643253e-05,
+      "loss": 0.8664,
+      "step": 90
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9511301160659744e-05,
+      "loss": 1.1555,
+      "step": 91
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.949908368967624e-05,
+      "loss": 1.1517,
+      "step": 92
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.948686621869273e-05,
+      "loss": 1.0223,
+      "step": 93
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9474648747709226e-05,
+      "loss": 1.0649,
+      "step": 94
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9462431276725718e-05,
+      "loss": 1.0147,
+      "step": 95
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9450213805742213e-05,
+      "loss": 1.3624,
+      "step": 96
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9437996334758705e-05,
+      "loss": 1.1294,
+      "step": 97
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.94257788637752e-05,
+      "loss": 1.1903,
+      "step": 98
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.941356139279169e-05,
+      "loss": 0.8732,
+      "step": 99
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9401343921808187e-05,
+      "loss": 1.1793,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.938912645082468e-05,
+      "loss": 0.9008,
+      "step": 101
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9376908979841174e-05,
+      "loss": 1.2374,
+      "step": 102
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.936469150885767e-05,
+      "loss": 0.9163,
+      "step": 103
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9352474037874164e-05,
+      "loss": 0.9702,
+      "step": 104
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9340256566890655e-05,
+      "loss": 1.0813,
+      "step": 105
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.932803909590715e-05,
+      "loss": 1.1164,
+      "step": 106
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9315821624923642e-05,
+      "loss": 0.9403,
+      "step": 107
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9303604153940137e-05,
+      "loss": 1.074,
+      "step": 108
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.929138668295663e-05,
+      "loss": 1.1077,
+      "step": 109
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9279169211973124e-05,
+      "loss": 1.0153,
+      "step": 110
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9266951740989616e-05,
+      "loss": 1.0281,
+      "step": 111
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.925473427000611e-05,
+      "loss": 0.9075,
+      "step": 112
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9242516799022603e-05,
+      "loss": 1.2191,
+      "step": 113
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9230299328039098e-05,
+      "loss": 1.0649,
+      "step": 114
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.921808185705559e-05,
+      "loss": 0.9901,
+      "step": 115
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9205864386072085e-05,
+      "loss": 1.0329,
+      "step": 116
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9193646915088576e-05,
+      "loss": 1.4406,
+      "step": 117
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.918142944410507e-05,
+      "loss": 1.138,
+      "step": 118
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9169211973121567e-05,
+      "loss": 1.1755,
+      "step": 119
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9156994502138058e-05,
+      "loss": 0.9568,
+      "step": 120
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9144777031154553e-05,
+      "loss": 1.0204,
+      "step": 121
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.913255956017105e-05,
+      "loss": 0.9391,
+      "step": 122
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.912034208918754e-05,
+      "loss": 1.109,
+      "step": 123
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9108124618204035e-05,
+      "loss": 1.2183,
+      "step": 124
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9095907147220527e-05,
+      "loss": 0.9377,
+      "step": 125
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9083689676237022e-05,
+      "loss": 1.0865,
+      "step": 126
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9071472205253514e-05,
+      "loss": 1.2078,
+      "step": 127
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.905925473427001e-05,
+      "loss": 1.0149,
+      "step": 128
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.90470372632865e-05,
+      "loss": 1.1191,
+      "step": 129
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9034819792302996e-05,
+      "loss": 1.0933,
+      "step": 130
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9022602321319487e-05,
+      "loss": 0.9312,
+      "step": 131
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9010384850335982e-05,
+      "loss": 0.794,
+      "step": 132
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8998167379352474e-05,
+      "loss": 0.8745,
+      "step": 133
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.898594990836897e-05,
+      "loss": 0.9092,
+      "step": 134
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.8973732437385464e-05,
+      "loss": 0.7504,
+      "step": 135
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.8961514966401956e-05,
+      "loss": 1.2165,
+      "step": 136
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.894929749541845e-05,
+      "loss": 0.9727,
+      "step": 137
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8937080024434943e-05,
+      "loss": 1.0236,
+      "step": 138
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8924862553451438e-05,
+      "loss": 0.9628,
+      "step": 139
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.891264508246793e-05,
+      "loss": 0.8762,
+      "step": 140
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8900427611484425e-05,
+      "loss": 1.0712,
+      "step": 141
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8888210140500916e-05,
+      "loss": 0.7999,
+      "step": 142
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.887599266951741e-05,
+      "loss": 0.9812,
+      "step": 143
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8863775198533903e-05,
+      "loss": 1.8394,
+      "step": 144
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.88515577275504e-05,
+      "loss": 0.9033,
+      "step": 145
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.883934025656689e-05,
+      "loss": 0.9813,
+      "step": 146
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8827122785583385e-05,
+      "loss": 0.7722,
+      "step": 147
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8814905314599877e-05,
+      "loss": 0.9991,
+      "step": 148
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8802687843616375e-05,
+      "loss": 0.9531,
+      "step": 149
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8790470372632867e-05,
+      "loss": 0.9034,
+      "step": 150
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8778252901649362e-05,
+      "loss": 0.8741,
+      "step": 151
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8766035430665854e-05,
+      "loss": 1.1228,
+      "step": 152
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.875381795968235e-05,
+      "loss": 0.7849,
+      "step": 153
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.874160048869884e-05,
+      "loss": 0.9642,
+      "step": 154
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8729383017715336e-05,
+      "loss": 1.0823,
+      "step": 155
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8717165546731827e-05,
+      "loss": 1.2156,
+      "step": 156
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8704948075748323e-05,
+      "loss": 1.4682,
+      "step": 157
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8692730604764814e-05,
+      "loss": 1.2043,
+      "step": 158
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.868051313378131e-05,
+      "loss": 0.9802,
+      "step": 159
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.86682956627978e-05,
+      "loss": 1.1539,
+      "step": 160
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8656078191814296e-05,
+      "loss": 1.1245,
+      "step": 161
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8643860720830788e-05,
+      "loss": 1.099,
+      "step": 162
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8631643249847283e-05,
+      "loss": 1.0272,
+      "step": 163
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8619425778863778e-05,
+      "loss": 1.0072,
+      "step": 164
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.860720830788027e-05,
+      "loss": 1.0215,
+      "step": 165
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8594990836896765e-05,
+      "loss": 1.0221,
+      "step": 166
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8582773365913257e-05,
+      "loss": 1.0754,
+      "step": 167
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.857055589492975e-05,
+      "loss": 0.9724,
+      "step": 168
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8558338423946243e-05,
+      "loss": 1.031,
+      "step": 169
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.854612095296274e-05,
+      "loss": 1.157,
+      "step": 170
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.853390348197923e-05,
+      "loss": 0.9819,
+      "step": 171
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8521686010995725e-05,
+      "loss": 1.1156,
+      "step": 172
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.850946854001222e-05,
+      "loss": 1.0699,
+      "step": 173
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8497251069028712e-05,
+      "loss": 1.1092,
+      "step": 174
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8485033598045207e-05,
+      "loss": 1.0092,
+      "step": 175
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.84728161270617e-05,
+      "loss": 1.0403,
+      "step": 176
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8460598656078194e-05,
+      "loss": 0.8809,
+      "step": 177
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8448381185094686e-05,
+      "loss": 1.0139,
+      "step": 178
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.843616371411118e-05,
+      "loss": 1.0701,
+      "step": 179
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8423946243127676e-05,
+      "loss": 0.9199,
+      "step": 180
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8411728772144168e-05,
+      "loss": 0.8542,
+      "step": 181
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8399511301160663e-05,
+      "loss": 1.0369,
+      "step": 182
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8387293830177154e-05,
+      "loss": 0.9847,
+      "step": 183
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.837507635919365e-05,
+      "loss": 0.8046,
+      "step": 184
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.836285888821014e-05,
+      "loss": 1.2821,
+      "step": 185
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8350641417226636e-05,
+      "loss": 1.0127,
+      "step": 186
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8338423946243128e-05,
+      "loss": 0.8535,
+      "step": 187
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8326206475259623e-05,
+      "loss": 0.984,
+      "step": 188
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8313989004276115e-05,
+      "loss": 0.771,
+      "step": 189
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.830177153329261e-05,
+      "loss": 2.1482,
+      "step": 190
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.82895540623091e-05,
+      "loss": 0.7799,
+      "step": 191
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8277336591325597e-05,
+      "loss": 1.1474,
+      "step": 192
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.826511912034209e-05,
+      "loss": 1.0967,
+      "step": 193
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8252901649358587e-05,
+      "loss": 0.8824,
+      "step": 194
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.824068417837508e-05,
+      "loss": 0.9202,
+      "step": 195
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8228466707391574e-05,
+      "loss": 0.8055,
+      "step": 196
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8216249236408065e-05,
+      "loss": 0.7309,
+      "step": 197
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.820403176542456e-05,
+      "loss": 1.1121,
+      "step": 198
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8191814294441052e-05,
+      "loss": 1.5694,
+      "step": 199
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8179596823457547e-05,
+      "loss": 1.2677,
+      "step": 200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.816737935247404e-05,
+      "loss": 1.1242,
+      "step": 201
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8155161881490534e-05,
+      "loss": 0.8419,
+      "step": 202
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8142944410507026e-05,
+      "loss": 1.1399,
+      "step": 203
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.813072693952352e-05,
+      "loss": 0.7964,
+      "step": 204
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8118509468540013e-05,
+      "loss": 0.9321,
+      "step": 205
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.8106291997556508e-05,
+      "loss": 0.8461,
+      "step": 206
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.8094074526573e-05,
+      "loss": 1.0457,
+      "step": 207
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.8081857055589494e-05,
+      "loss": 1.085,
+      "step": 208
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.806963958460599e-05,
+      "loss": 0.9105,
+      "step": 209
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.805742211362248e-05,
+      "loss": 0.9143,
+      "step": 210
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.8045204642638976e-05,
+      "loss": 1.0978,
+      "step": 211
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.8032987171655468e-05,
+      "loss": 0.9884,
+      "step": 212
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.8020769700671963e-05,
+      "loss": 1.0179,
+      "step": 213
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8008552229688455e-05,
+      "loss": 1.2135,
+      "step": 214
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.799633475870495e-05,
+      "loss": 0.9051,
+      "step": 215
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7984117287721442e-05,
+      "loss": 0.8954,
+      "step": 216
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7971899816737937e-05,
+      "loss": 1.1429,
+      "step": 217
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.795968234575443e-05,
+      "loss": 1.0803,
+      "step": 218
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7947464874770924e-05,
+      "loss": 1.0558,
+      "step": 219
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7935247403787415e-05,
+      "loss": 1.0904,
+      "step": 220
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.792302993280391e-05,
+      "loss": 1.0909,
+      "step": 221
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7910812461820402e-05,
+      "loss": 1.1515,
+      "step": 222
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7898594990836897e-05,
+      "loss": 1.0393,
+      "step": 223
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7886377519853392e-05,
+      "loss": 1.0072,
+      "step": 224
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7874160048869887e-05,
+      "loss": 0.8387,
+      "step": 225
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.786194257788638e-05,
+      "loss": 0.8908,
+      "step": 226
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7849725106902874e-05,
+      "loss": 0.875,
+      "step": 227
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7837507635919366e-05,
+      "loss": 1.0477,
+      "step": 228
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.782529016493586e-05,
+      "loss": 1.0117,
+      "step": 229
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7813072693952353e-05,
+      "loss": 1.1684,
+      "step": 230
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7800855222968848e-05,
+      "loss": 1.1475,
+      "step": 231
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.778863775198534e-05,
+      "loss": 1.2069,
+      "step": 232
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7776420281001835e-05,
+      "loss": 1.1107,
+      "step": 233
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7764202810018326e-05,
+      "loss": 0.9738,
+      "step": 234
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.775198533903482e-05,
+      "loss": 0.8838,
+      "step": 235
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7739767868051313e-05,
+      "loss": 1.0103,
+      "step": 236
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7727550397067808e-05,
+      "loss": 0.9279,
+      "step": 237
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.77153329260843e-05,
+      "loss": 0.9682,
+      "step": 238
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7703115455100795e-05,
+      "loss": 1.2049,
+      "step": 239
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.769089798411729e-05,
+      "loss": 1.0387,
+      "step": 240
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7678680513133785e-05,
+      "loss": 0.9754,
+      "step": 241
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7666463042150277e-05,
+      "loss": 1.0202,
+      "step": 242
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7654245571166772e-05,
+      "loss": 1.0224,
+      "step": 243
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.7642028100183264e-05,
+      "loss": 0.8577,
+      "step": 244
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.762981062919976e-05,
+      "loss": 0.9112,
+      "step": 245
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.761759315821625e-05,
+      "loss": 0.9395,
+      "step": 246
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.7605375687232746e-05,
+      "loss": 1.1198,
+      "step": 247
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7593158216249237e-05,
+      "loss": 1.4934,
+      "step": 248
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7580940745265732e-05,
+      "loss": 1.0408,
+      "step": 249
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7568723274282224e-05,
+      "loss": 0.9475,
+      "step": 250
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.755650580329872e-05,
+      "loss": 1.1368,
+      "step": 251
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.754428833231521e-05,
+      "loss": 0.9984,
+      "step": 252
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7532070861331706e-05,
+      "loss": 1.1552,
+      "step": 253
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.75198533903482e-05,
+      "loss": 1.0785,
+      "step": 254
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7507635919364693e-05,
+      "loss": 0.8089,
+      "step": 255
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7495418448381188e-05,
+      "loss": 1.0439,
+      "step": 256
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.748320097739768e-05,
+      "loss": 0.7603,
+      "step": 257
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7470983506414175e-05,
+      "loss": 0.8235,
+      "step": 258
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7458766035430666e-05,
+      "loss": 1.7352,
+      "step": 259
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.744654856444716e-05,
+      "loss": 0.9731,
+      "step": 260
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7434331093463653e-05,
+      "loss": 0.8848,
+      "step": 261
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.742211362248015e-05,
+      "loss": 0.8874,
+      "step": 262
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.740989615149664e-05,
+      "loss": 1.0125,
+      "step": 263
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7397678680513135e-05,
+      "loss": 1.0552,
+      "step": 264
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7385461209529627e-05,
+      "loss": 0.9488,
+      "step": 265
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7373243738546122e-05,
+      "loss": 0.794,
+      "step": 266
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7361026267562614e-05,
+      "loss": 1.0277,
+      "step": 267
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.734880879657911e-05,
+      "loss": 0.835,
+      "step": 268
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7336591325595604e-05,
+      "loss": 1.2321,
+      "step": 269
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.73243738546121e-05,
+      "loss": 0.9804,
+      "step": 270
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.731215638362859e-05,
+      "loss": 1.1228,
+      "step": 271
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7299938912645086e-05,
+      "loss": 1.1392,
+      "step": 272
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7287721441661577e-05,
+      "loss": 0.8711,
+      "step": 273
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7275503970678073e-05,
+      "loss": 0.9201,
+      "step": 274
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7263286499694564e-05,
+      "loss": 1.008,
+      "step": 275
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.725106902871106e-05,
+      "loss": 1.0344,
+      "step": 276
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.723885155772755e-05,
+      "loss": 0.9427,
+      "step": 277
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7226634086744046e-05,
+      "loss": 0.8963,
+      "step": 278
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7214416615760538e-05,
+      "loss": 1.3487,
+      "step": 279
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7202199144777033e-05,
+      "loss": 1.0002,
+      "step": 280
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7189981673793525e-05,
+      "loss": 0.961,
+      "step": 281
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.717776420281002e-05,
+      "loss": 0.9015,
+      "step": 282
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.716554673182651e-05,
+      "loss": 0.9172,
+      "step": 283
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.7153329260843007e-05,
+      "loss": 0.9849,
+      "step": 284
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.71411117898595e-05,
+      "loss": 0.9166,
+      "step": 285
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.7128894318875993e-05,
+      "loss": 1.0685,
+      "step": 286
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.711667684789249e-05,
+      "loss": 1.0196,
+      "step": 287
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.710445937690898e-05,
+      "loss": 0.8409,
+      "step": 288
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.7092241905925475e-05,
+      "loss": 0.9327,
+      "step": 289
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7080024434941967e-05,
+      "loss": 0.8675,
+      "step": 290
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7067806963958462e-05,
+      "loss": 1.1109,
+      "step": 291
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7055589492974954e-05,
+      "loss": 0.8427,
+      "step": 292
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.704337202199145e-05,
+      "loss": 1.1322,
+      "step": 293
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7031154551007944e-05,
+      "loss": 0.9094,
+      "step": 294
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7018937080024436e-05,
+      "loss": 1.1168,
+      "step": 295
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.700671960904093e-05,
+      "loss": 0.9982,
+      "step": 296
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.6994502138057422e-05,
+      "loss": 0.7812,
+      "step": 297
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.6982284667073918e-05,
+      "loss": 0.8858,
+      "step": 298
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.6970067196090413e-05,
+      "loss": 0.9693,
+      "step": 299
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.6957849725106904e-05,
+      "loss": 0.9097,
+      "step": 300
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.69456322541234e-05,
+      "loss": 0.9178,
+      "step": 301
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.693341478313989e-05,
+      "loss": 1.0581,
+      "step": 302
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6921197312156386e-05,
+      "loss": 1.1521,
+      "step": 303
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6908979841172878e-05,
+      "loss": 1.065,
+      "step": 304
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6896762370189373e-05,
+      "loss": 0.8954,
+      "step": 305
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6884544899205865e-05,
+      "loss": 0.7037,
+      "step": 306
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.687232742822236e-05,
+      "loss": 0.9347,
+      "step": 307
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.686010995723885e-05,
+      "loss": 0.9681,
+      "step": 308
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.6847892486255347e-05,
+      "loss": 0.8554,
+      "step": 309
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.683567501527184e-05,
+      "loss": 0.8793,
+      "step": 310
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6823457544288334e-05,
+      "loss": 0.8881,
+      "step": 311
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6811240073304825e-05,
+      "loss": 0.9284,
+      "step": 312
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.679902260232132e-05,
+      "loss": 0.9632,
+      "step": 313
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6786805131337815e-05,
+      "loss": 1.0815,
+      "step": 314
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.677458766035431e-05,
+      "loss": 0.9314,
+      "step": 315
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.6762370189370802e-05,
+      "loss": 0.7965,
+      "step": 316
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.6750152718387297e-05,
+      "loss": 0.8365,
+      "step": 317
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.673793524740379e-05,
+      "loss": 1.2019,
+      "step": 318
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.6725717776420284e-05,
+      "loss": 0.9525,
+      "step": 319
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6713500305436776e-05,
+      "loss": 0.7911,
+      "step": 320
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.670128283445327e-05,
+      "loss": 0.9614,
+      "step": 321
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6689065363469763e-05,
+      "loss": 1.0212,
+      "step": 322
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6676847892486258e-05,
+      "loss": 1.128,
+      "step": 323
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.666463042150275e-05,
+      "loss": 0.9668,
+      "step": 324
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.6652412950519245e-05,
+      "loss": 0.9095,
+      "step": 325
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.6640195479535736e-05,
+      "loss": 0.8985,
+      "step": 326
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.662797800855223e-05,
+      "loss": 0.8876,
+      "step": 327
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6615760537568723e-05,
+      "loss": 0.9104,
+      "step": 328
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6603543066585218e-05,
+      "loss": 0.9719,
+      "step": 329
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6591325595601713e-05,
+      "loss": 1.2485,
+      "step": 330
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6579108124618205e-05,
+      "loss": 0.8247,
+      "step": 331
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.65668906536347e-05,
+      "loss": 1.1209,
+      "step": 332
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.6554673182651192e-05,
+      "loss": 1.0325,
+      "step": 333
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.6542455711667687e-05,
+      "loss": 1.0139,
+      "step": 334
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.653023824068418e-05,
+      "loss": 1.0233,
+      "step": 335
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.6518020769700674e-05,
+      "loss": 0.8545,
+      "step": 336
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6505803298717165e-05,
+      "loss": 1.2186,
+      "step": 337
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.649358582773366e-05,
+      "loss": 0.9952,
+      "step": 338
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6481368356750152e-05,
+      "loss": 1.2843,
+      "step": 339
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6469150885766647e-05,
+      "loss": 1.2914,
+      "step": 340
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.645693341478314e-05,
+      "loss": 0.7621,
+      "step": 341
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6444715943799634e-05,
+      "loss": 1.0924,
+      "step": 342
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6432498472816126e-05,
+      "loss": 1.1418,
+      "step": 343
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6420281001832624e-05,
+      "loss": 0.9116,
+      "step": 344
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6408063530849116e-05,
+      "loss": 1.7392,
+      "step": 345
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.639584605986561e-05,
+      "loss": 0.7273,
+      "step": 346
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6383628588882103e-05,
+      "loss": 0.9469,
+      "step": 347
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6371411117898598e-05,
+      "loss": 0.7986,
+      "step": 348
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.635919364691509e-05,
+      "loss": 0.8359,
+      "step": 349
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6346976175931585e-05,
+      "loss": 0.7852,
+      "step": 350
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6334758704948076e-05,
+      "loss": 1.1206,
+      "step": 351
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.632254123396457e-05,
+      "loss": 0.9291,
+      "step": 352
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6310323762981063e-05,
+      "loss": 1.0176,
+      "step": 353
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6298106291997558e-05,
+      "loss": 1.018,
+      "step": 354
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.628588882101405e-05,
+      "loss": 0.7873,
+      "step": 355
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6273671350030545e-05,
+      "loss": 0.9801,
+      "step": 356
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6261453879047037e-05,
+      "loss": 0.752,
+      "step": 357
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6249236408063532e-05,
+      "loss": 0.8991,
+      "step": 358
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6237018937080027e-05,
+      "loss": 0.8771,
+      "step": 359
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.622480146609652e-05,
+      "loss": 0.8734,
+      "step": 360
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6212583995113014e-05,
+      "loss": 0.9302,
+      "step": 361
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.620036652412951e-05,
+      "loss": 0.9362,
+      "step": 362
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6188149053146e-05,
+      "loss": 0.9994,
+      "step": 363
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6175931582162496e-05,
+      "loss": 0.7499,
+      "step": 364
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6163714111178987e-05,
+      "loss": 1.7184,
+      "step": 365
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6151496640195482e-05,
+      "loss": 1.0205,
+      "step": 366
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6139279169211974e-05,
+      "loss": 0.8763,
+      "step": 367
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.612706169822847e-05,
+      "loss": 1.0264,
+      "step": 368
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.611484422724496e-05,
+      "loss": 0.9088,
+      "step": 369
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6102626756261456e-05,
+      "loss": 0.7762,
+      "step": 370
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6090409285277948e-05,
+      "loss": 0.876,
+      "step": 371
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6078191814294443e-05,
+      "loss": 1.0591,
+      "step": 372
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6065974343310935e-05,
+      "loss": 0.8602,
+      "step": 373
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.605375687232743e-05,
+      "loss": 0.8489,
+      "step": 374
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6041539401343925e-05,
+      "loss": 0.9205,
+      "step": 375
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6029321930360416e-05,
+      "loss": 0.926,
+      "step": 376
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.601710445937691e-05,
+      "loss": 0.8983,
+      "step": 377
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6004886988393403e-05,
+      "loss": 1.0779,
+      "step": 378
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.59926695174099e-05,
+      "loss": 0.9446,
+      "step": 379
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.598045204642639e-05,
+      "loss": 1.1564,
+      "step": 380
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.5968234575442885e-05,
+      "loss": 1.0101,
+      "step": 381
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.5956017104459377e-05,
+      "loss": 1.0597,
+      "step": 382
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.5943799633475872e-05,
+      "loss": 0.9408,
+      "step": 383
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.5931582162492364e-05,
+      "loss": 1.1833,
+      "step": 384
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.591936469150886e-05,
+      "loss": 1.0106,
+      "step": 385
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.590714722052535e-05,
+      "loss": 1.6698,
+      "step": 386
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5894929749541846e-05,
+      "loss": 1.0123,
+      "step": 387
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5882712278558337e-05,
+      "loss": 0.9237,
+      "step": 388
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5870494807574836e-05,
+      "loss": 0.9182,
+      "step": 389
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5858277336591327e-05,
+      "loss": 0.9832,
+      "step": 390
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5846059865607823e-05,
+      "loss": 0.7884,
+      "step": 391
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5833842394624314e-05,
+      "loss": 1.0028,
+      "step": 392
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.582162492364081e-05,
+      "loss": 1.0835,
+      "step": 393
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.58094074526573e-05,
+      "loss": 0.9394,
+      "step": 394
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5797189981673796e-05,
+      "loss": 1.25,
+      "step": 395
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5784972510690288e-05,
+      "loss": 1.0046,
+      "step": 396
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5772755039706783e-05,
+      "loss": 0.6862,
+      "step": 397
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5760537568723275e-05,
+      "loss": 0.9672,
+      "step": 398
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.574832009773977e-05,
+      "loss": 0.847,
+      "step": 399
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.573610262675626e-05,
+      "loss": 1.1316,
+      "step": 400
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5723885155772757e-05,
+      "loss": 1.1577,
+      "step": 401
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5711667684789248e-05,
+      "loss": 0.7909,
+      "step": 402
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5699450213805743e-05,
+      "loss": 0.9476,
+      "step": 403
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.568723274282224e-05,
+      "loss": 0.8651,
+      "step": 404
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.567501527183873e-05,
+      "loss": 0.8349,
+      "step": 405
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5662797800855225e-05,
+      "loss": 1.0023,
+      "step": 406
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5650580329871717e-05,
+      "loss": 0.9267,
+      "step": 407
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5638362858888212e-05,
+      "loss": 0.7568,
+      "step": 408
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5626145387904704e-05,
+      "loss": 0.9849,
+      "step": 409
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.56139279169212e-05,
+      "loss": 0.8452,
+      "step": 410
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.560171044593769e-05,
+      "loss": 0.9507,
+      "step": 411
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5589492974954186e-05,
+      "loss": 0.9459,
+      "step": 412
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.557727550397068e-05,
+      "loss": 0.9053,
+      "step": 413
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5565058032987173e-05,
+      "loss": 1.0029,
+      "step": 414
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5552840562003668e-05,
+      "loss": 0.7987,
+      "step": 415
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.554062309102016e-05,
+      "loss": 0.7423,
+      "step": 416
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5528405620036654e-05,
+      "loss": 1.0905,
+      "step": 417
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5516188149053146e-05,
+      "loss": 0.829,
+      "step": 418
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.550397067806964e-05,
+      "loss": 0.698,
+      "step": 419
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5491753207086136e-05,
+      "loss": 0.8893,
+      "step": 420
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5479535736102628e-05,
+      "loss": 0.992,
+      "step": 421
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5467318265119123e-05,
+      "loss": 1.0658,
+      "step": 422
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 2.030735869261906e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-422/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fd05faa475f5ea09145da8181858be9d5440fb2c8d86f380c3fb0a9ba1c01b
+size 5048

checkpoint-845/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /mnt/data_large/ccy/Llama-2-7b-hf
+---
+
+# 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 0.7.1

checkpoint-845/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/data_large/ccy/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-845/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9dfe3cc9b14d825825614d6d80c0b266eec43fbc411d8ecaf55cad238ac6e43
+size 536906096

checkpoint-845/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4726e21ac73a6860f8d58bfd98475f534161d5e368957c386fbde1470914ad0
+size 14244

checkpoint-845/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50a668b3cfee1f185ee2d62fd9f67d9359c4f4b9684a6479a2a98a92c318c22
+size 1064

checkpoint-845/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-845/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-845/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fd05faa475f5ea09145da8181858be9d5440fb2c8d86f380c3fb0a9ba1c01b
+size 5048

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train.log

@@ -0,0 +1,205 @@
+09/02/2024 09:22:37 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
+09/02/2024 09:22:37 - INFO - __main__ - Training parameters TrainingArguments(
+_n_gpu=1,
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+analysis_dataset=bbh,
+analysis_mode=False,
+auto_find_batch_size=False,
+bf16=True,
+bf16_full_eval=False,
+data_seed=9,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+dispatch_batches=None,
+do_eval=False,
+do_predict=False,
+do_train=True,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_steps=None,
+evaluation_strategy=no,
+fp16=False,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[<FSDPOption.FULL_SHARD: 'full_shard'>, <FSDPOption.AUTO_WRAP: 'auto_wrap'>],
+fsdp_config={'fsdp_transformer_layer_cls_to_wrap': ['LlamaDecoderLayer'], 'fsdp_backward_prefetch': 'backward_pre', 'limit_all_gathers': 'true', 'use_orig_params': 'true', 'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+gradient_accumulation_steps=32,
+gradient_checkpointing=False,
+gradient_checkpointing_kwargs=None,
+greater_is_better=None,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=False,
+hub_strategy=every_save,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=2e-05,
+length_column_name=length,
+load_best_model_at_end=False,
+local_rank=0,
+log_level=passive,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=../out/llama2-7b-p0.05-lora-seed9/runs/Sep02_09-22-37_dlc19oe6tjflhwaw-master-0,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=1.0,
+logging_strategy=steps,
+lr_scheduler_kwargs={},
+lr_scheduler_type=linear,
+max_grad_norm=1.0,
+max_steps=-1,
+metric_for_best_model=None,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_train_epochs=4.0,
+optim=adamw_torch,
+optim_args=None,
+output_dir=../out/llama2-7b-p0.05-lora-seed9,
+overwrite_output_dir=True,
+past_index=-1,
+per_device_eval_batch_size=8,
+per_device_train_batch_size=1,
+prediction_loss_only=False,
+push_to_hub=False,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=True,
+report_to=['wandb'],
+resume_from_checkpoint=None,
+run_name=../out/llama2-7b-p0.05-lora-seed9,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=500,
+save_strategy=epoch,
+save_total_limit=None,
+seed=0,
+skip_memory_metrics=True,
+split_batches=False,
+tf32=False,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torchdynamo=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+train_dataset_names=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_mps_device=False,
+warmup_ratio=0.03,
+warmup_steps=0,
+weight_decay=0.0,
+)
+09/02/2024 09:22:37 - INFO - __main__ - Model parameters ModelArguments(model_name_or_path='/mnt/data_large/ccy/Llama-2-7b-hf', config_name=None, tokenizer_name=None, cache_dir=None, use_fast_tokenizer=True, model_revision='main', use_auth_token=False, torch_dtype=None, lora=True, lora_r=128, lora_alpha=512.0, lora_dropout=0.1, lora_target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj'])
+09/02/2024 09:22:37 - INFO - __main__ - Dataset parameters DataArguments(train_files=['./data/train/processed/flan_v2/flan_v2_data.jsonl', './data/train/processed/cot/cot_data.jsonl', './data/train/processed/dolly/dolly_data.jsonl', './data/train/processed/oasst1/oasst1_data.jsonl'], overwrite_cache=False, preprocessing_num_workers=None, max_seq_length=2048, sample_data_seed=42, percentage=0.05)
+[INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file tokenizer.model
+[INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file tokenizer.json
+[INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file added_tokens.json
+[INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file special_tokens_map.json
+[INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file tokenizer_config.json
+Using custom data configuration default-f9134d95c1961a9a
+09/02/2024 09:22:38 - INFO - datasets.builder - Using custom data configuration default-f9134d95c1961a9a
+Loading Dataset Infos from /home/pai/envs/less/lib/python3.10/site-packages/datasets/packaged_modules/json
+09/02/2024 09:22:38 - INFO - datasets.info - Loading Dataset Infos from /home/pai/envs/less/lib/python3.10/site-packages/datasets/packaged_modules/json
+Overwrite dataset info from restored data version if exists.
+09/02/2024 09:22:38 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists.
+Loading Dataset info from /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7
+09/02/2024 09:22:38 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7
+Found cached dataset json (/root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7)
+09/02/2024 09:22:38 - INFO - datasets.builder - Found cached dataset json (/root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7)
+Loading Dataset info from /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7
+09/02/2024 09:22:38 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7
+/mnt/data_large/ccy/Llama-2-7b-hf
+['./data/train/processed/flan_v2/flan_v2_data.jsonl', './data/train/processed/cot/cot_data.jsonl', './data/train/processed/dolly/dolly_data.jsonl', './data/train/processed/oasst1/oasst1_data.jsonl']
+['dataset', 'id', 'messages']
+Process #0 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00000_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #0 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00000_of_00010.arrow
+Process #1 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00001_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #1 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00001_of_00010.arrow
+Process #2 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00002_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #2 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00002_of_00010.arrow
+Process #3 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00003_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #3 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00003_of_00010.arrow
+Process #4 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00004_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #4 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00004_of_00010.arrow
+Process #5 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00005_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #5 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00005_of_00010.arrow
+Process #6 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00006_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #6 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00006_of_00010.arrow
+Process #7 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00007_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #7 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00007_of_00010.arrow
+Process #8 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00008_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #8 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00008_of_00010.arrow
+Process #9 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00009_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #9 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00009_of_00010.arrow
+Loading cached processed dataset at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_*_of_00010.arrow
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_*_of_00010.arrow
+Concatenating 10 shards
+09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Concatenating 10 shards
+[INFO|configuration_utils.py:737] 2024-09-02 09:22:38,728 >> loading configuration file /mnt/data_large/ccy/Llama-2-7b-hf/config.json
+[INFO|configuration_utils.py:802] 2024-09-02 09:22:38,729 >> Model config LlamaConfig {
+  "_name_or_path": "/mnt/data_large/ccy/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+[INFO|modeling_utils.py:3341] 2024-09-02 09:22:38,764 >> loading weights file /mnt/data_large/ccy/Llama-2-7b-hf/model.safetensors.index.json
+[INFO|configuration_utils.py:826] 2024-09-02 09:22:38,765 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2
+}
+
+

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.99,
+    "train_loss": 0.919522538692889,
+    "train_runtime": 22845.2596,
+    "train_samples": 13533,
+    "train_samples_per_second": 2.37,
+    "train_steps_per_second": 0.074
+}