Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: train_2024-05-17-13-21-02
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_2024-05-17-13-21-02
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the sharegpt_common_zh dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.0
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f2607b8b979968d61fec05b36c85d8ce02cab2bfc9ac5bc56aa34dd730a02b
+size 13648432

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9993833504624874,
+    "total_flos": 8.604039501468795e+17,
+    "train_loss": 0.7956282923880377,
+    "train_runtime": 56311.986,
+    "train_samples_per_second": 0.259,
+    "train_steps_per_second": 0.032
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f340bdc6d2c443c6987d4a9f9fc048cd74b07a62d4f15dd91b0e771813d3c2ff
+size 13648432

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9b99998609e2480033fe551ebdcee4d1d7ba31ef792e7a24d9f508bec5dd1a
+size 27370618

checkpoint-100/rng_state.pth

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

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13873c240978112413c3070a4681f1211f79d478becf430fa6ac182f59bc0e50
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1644398766700925,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008221993833504625,
+      "grad_norm": 1.0209685564041138,
+      "learning_rate": 4.999907296225947e-05,
+      "loss": 1.1323,
+      "step": 5
+    },
+    {
+      "epoch": 0.01644398766700925,
+      "grad_norm": 1.084985375404358,
+      "learning_rate": 4.9996291917789814e-05,
+      "loss": 1.043,
+      "step": 10
+    },
+    {
+      "epoch": 0.024665981500513873,
+      "grad_norm": 1.1630356311798096,
+      "learning_rate": 4.999165707284169e-05,
+      "loss": 1.0403,
+      "step": 15
+    },
+    {
+      "epoch": 0.0328879753340185,
+      "grad_norm": 0.9428950548171997,
+      "learning_rate": 4.998516877114917e-05,
+      "loss": 0.7908,
+      "step": 20
+    },
+    {
+      "epoch": 0.041109969167523124,
+      "grad_norm": 0.8565282225608826,
+      "learning_rate": 4.9976827493904315e-05,
+      "loss": 0.8942,
+      "step": 25
+    },
+    {
+      "epoch": 0.04933196300102775,
+      "grad_norm": 0.9475494623184204,
+      "learning_rate": 4.996882074080329e-05,
+      "loss": 1.3336,
+      "step": 30
+    },
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 3.55914044380188,
+      "learning_rate": 4.9957145758791006e-05,
+      "loss": 0.7717,
+      "step": 35
+    },
+    {
+      "epoch": 0.065775950668037,
+      "grad_norm": 0.6254042983055115,
+      "learning_rate": 4.9943619879497585e-05,
+      "loss": 0.7791,
+      "step": 40
+    },
+    {
+      "epoch": 0.07399794450154162,
+      "grad_norm": 1.1033686399459839,
+      "learning_rate": 4.992824410604308e-05,
+      "loss": 0.816,
+      "step": 45
+    },
+    {
+      "epoch": 0.08221993833504625,
+      "grad_norm": 0.6939295530319214,
+      "learning_rate": 4.991101957874126e-05,
+      "loss": 0.8761,
+      "step": 50
+    },
+    {
+      "epoch": 0.09044193216855087,
+      "grad_norm": 0.957773745059967,
+      "learning_rate": 4.98919475750151e-05,
+      "loss": 0.8573,
+      "step": 55
+    },
+    {
+      "epoch": 0.0986639260020555,
+      "grad_norm": 0.6181407570838928,
+      "learning_rate": 4.987102950930195e-05,
+      "loss": 0.8158,
+      "step": 60
+    },
+    {
+      "epoch": 0.10688591983556012,
+      "grad_norm": 0.6531780362129211,
+      "learning_rate": 4.984826693294874e-05,
+      "loss": 0.8796,
+      "step": 65
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 1.6238263845443726,
+      "learning_rate": 4.982366153409685e-05,
+      "loss": 0.7839,
+      "step": 70
+    },
+    {
+      "epoch": 0.12332990750256938,
+      "grad_norm": 18.583261489868164,
+      "learning_rate": 4.979721513755695e-05,
+      "loss": 1.1142,
+      "step": 75
+    },
+    {
+      "epoch": 0.131551901336074,
+      "grad_norm": 0.7723462581634521,
+      "learning_rate": 4.9768929704673654e-05,
+      "loss": 0.8193,
+      "step": 80
+    },
+    {
+      "epoch": 0.1397738951695786,
+      "grad_norm": 0.7994495630264282,
+      "learning_rate": 4.973880733318007e-05,
+      "loss": 0.9853,
+      "step": 85
+    },
+    {
+      "epoch": 0.14799588900308325,
+      "grad_norm": 0.5460528135299683,
+      "learning_rate": 4.970685025704222e-05,
+      "loss": 0.861,
+      "step": 90
+    },
+    {
+      "epoch": 0.15621788283658788,
+      "grad_norm": 1.0410531759262085,
+      "learning_rate": 4.9673060846293326e-05,
+      "loss": 0.8044,
+      "step": 95
+    },
+    {
+      "epoch": 0.1644398766700925,
+      "grad_norm": 0.7643013000488281,
+      "learning_rate": 4.963744160685815e-05,
+      "loss": 0.9048,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1824,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 4.729603122757632e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da40bedcaa97ca5797127d487348c4b521b16e2df25cfedbca83617e93b2e68
+size 5176

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.0

checkpoint-1000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526e7c73d46e4c8056a991463f480152d1051a1be31353f7c1f6910c3a16e70a
+size 13648432

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fb0323cc52adbadd2b32841e72d8cd9e38e4f517a3d05779525ba2cabaef60
+size 27370618

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0bd0e79228d199d5b8cfd33e7164faa5bba3fff97dde6edd5afe317c8fb7081
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1421 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.644398766700925,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008221993833504625,
+      "grad_norm": 1.0209685564041138,
+      "learning_rate": 4.999907296225947e-05,
+      "loss": 1.1323,
+      "step": 5
+    },
+    {
+      "epoch": 0.01644398766700925,
+      "grad_norm": 1.084985375404358,
+      "learning_rate": 4.9996291917789814e-05,
+      "loss": 1.043,
+      "step": 10
+    },
+    {
+      "epoch": 0.024665981500513873,
+      "grad_norm": 1.1630356311798096,
+      "learning_rate": 4.999165707284169e-05,
+      "loss": 1.0403,
+      "step": 15
+    },
+    {
+      "epoch": 0.0328879753340185,
+      "grad_norm": 0.9428950548171997,
+      "learning_rate": 4.998516877114917e-05,
+      "loss": 0.7908,
+      "step": 20
+    },
+    {
+      "epoch": 0.041109969167523124,
+      "grad_norm": 0.8565282225608826,
+      "learning_rate": 4.9976827493904315e-05,
+      "loss": 0.8942,
+      "step": 25
+    },
+    {
+      "epoch": 0.04933196300102775,
+      "grad_norm": 0.9475494623184204,
+      "learning_rate": 4.996882074080329e-05,
+      "loss": 1.3336,
+      "step": 30
+    },
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 3.55914044380188,
+      "learning_rate": 4.9957145758791006e-05,
+      "loss": 0.7717,
+      "step": 35
+    },
+    {
+      "epoch": 0.065775950668037,
+      "grad_norm": 0.6254042983055115,
+      "learning_rate": 4.9943619879497585e-05,
+      "loss": 0.7791,
+      "step": 40
+    },
+    {
+      "epoch": 0.07399794450154162,
+      "grad_norm": 1.1033686399459839,
+      "learning_rate": 4.992824410604308e-05,
+      "loss": 0.816,
+      "step": 45
+    },
+    {
+      "epoch": 0.08221993833504625,
+      "grad_norm": 0.6939295530319214,
+      "learning_rate": 4.991101957874126e-05,
+      "loss": 0.8761,
+      "step": 50
+    },
+    {
+      "epoch": 0.09044193216855087,
+      "grad_norm": 0.957773745059967,
+      "learning_rate": 4.98919475750151e-05,
+      "loss": 0.8573,
+      "step": 55
+    },
+    {
+      "epoch": 0.0986639260020555,
+      "grad_norm": 0.6181407570838928,
+      "learning_rate": 4.987102950930195e-05,
+      "loss": 0.8158,
+      "step": 60
+    },
+    {
+      "epoch": 0.10688591983556012,
+      "grad_norm": 0.6531780362129211,
+      "learning_rate": 4.984826693294874e-05,
+      "loss": 0.8796,
+      "step": 65
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 1.6238263845443726,
+      "learning_rate": 4.982366153409685e-05,
+      "loss": 0.7839,
+      "step": 70
+    },
+    {
+      "epoch": 0.12332990750256938,
+      "grad_norm": 18.583261489868164,
+      "learning_rate": 4.979721513755695e-05,
+      "loss": 1.1142,
+      "step": 75
+    },
+    {
+      "epoch": 0.131551901336074,
+      "grad_norm": 0.7723462581634521,
+      "learning_rate": 4.9768929704673654e-05,
+      "loss": 0.8193,
+      "step": 80
+    },
+    {
+      "epoch": 0.1397738951695786,
+      "grad_norm": 0.7994495630264282,
+      "learning_rate": 4.973880733318007e-05,
+      "loss": 0.9853,
+      "step": 85
+    },
+    {
+      "epoch": 0.14799588900308325,
+      "grad_norm": 0.5460528135299683,
+      "learning_rate": 4.970685025704222e-05,
+      "loss": 0.861,
+      "step": 90
+    },
+    {
+      "epoch": 0.15621788283658788,
+      "grad_norm": 1.0410531759262085,
+      "learning_rate": 4.9673060846293326e-05,
+      "loss": 0.8044,
+      "step": 95
+    },
+    {
+      "epoch": 0.1644398766700925,
+      "grad_norm": 0.7643013000488281,
+      "learning_rate": 4.963744160685815e-05,
+      "loss": 0.9048,
+      "step": 100
+    },
+    {
+      "epoch": 0.17266187050359713,
+      "grad_norm": 0.9957767724990845,
+      "learning_rate": 4.9599995180367e-05,
+      "loss": 0.8768,
+      "step": 105
+    },
+    {
+      "epoch": 0.18088386433710174,
+      "grad_norm": 0.5331000685691833,
+      "learning_rate": 4.956072434395994e-05,
+      "loss": 0.7871,
+      "step": 110
+    },
+    {
+      "epoch": 0.18910585817060638,
+      "grad_norm": 0.6342468857765198,
+      "learning_rate": 4.951963201008076e-05,
+      "loss": 0.9122,
+      "step": 115
+    },
+    {
+      "epoch": 0.197327852004111,
+      "grad_norm": 0.703365683555603,
+      "learning_rate": 4.947672122626101e-05,
+      "loss": 0.7379,
+      "step": 120
+    },
+    {
+      "epoch": 0.20554984583761562,
+      "grad_norm": 0.7069611549377441,
+      "learning_rate": 4.9431995174893984e-05,
+      "loss": 0.8529,
+      "step": 125
+    },
+    {
+      "epoch": 0.21377183967112023,
+      "grad_norm": 0.7649345993995667,
+      "learning_rate": 4.938545717299867e-05,
+      "loss": 0.8618,
+      "step": 130
+    },
+    {
+      "epoch": 0.22199383350462487,
+      "grad_norm": 0.53890061378479,
+      "learning_rate": 4.9337110671973815e-05,
+      "loss": 0.8235,
+      "step": 135
+    },
+    {
+      "epoch": 0.2302158273381295,
+      "grad_norm": 1.6072089672088623,
+      "learning_rate": 4.928695925734191e-05,
+      "loss": 0.8145,
+      "step": 140
+    },
+    {
+      "epoch": 0.23843782117163412,
+      "grad_norm": 1.1523021459579468,
+      "learning_rate": 4.923500664848326e-05,
+      "loss": 1.1315,
+      "step": 145
+    },
+    {
+      "epoch": 0.24665981500513876,
+      "grad_norm": 0.9310020804405212,
+      "learning_rate": 4.9181256698360216e-05,
+      "loss": 0.9059,
+      "step": 150
+    },
+    {
+      "epoch": 0.25488180883864336,
+      "grad_norm": 1.087494134902954,
+      "learning_rate": 4.912571339323135e-05,
+      "loss": 0.8613,
+      "step": 155
+    },
+    {
+      "epoch": 0.263103802672148,
+      "grad_norm": 0.9017001986503601,
+      "learning_rate": 4.906838085235588e-05,
+      "loss": 0.8456,
+      "step": 160
+    },
+    {
+      "epoch": 0.27132579650565264,
+      "grad_norm": 0.6858020424842834,
+      "learning_rate": 4.900926332768814e-05,
+      "loss": 0.697,
+      "step": 165
+    },
+    {
+      "epoch": 0.2795477903391572,
+      "grad_norm": 0.9164858460426331,
+      "learning_rate": 4.894836520356223e-05,
+      "loss": 0.8006,
+      "step": 170
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 0.6167294979095459,
+      "learning_rate": 4.888569099636692e-05,
+      "loss": 0.7694,
+      "step": 175
+    },
+    {
+      "epoch": 0.2959917780061665,
+      "grad_norm": 0.7028630375862122,
+      "learning_rate": 4.882124535421064e-05,
+      "loss": 0.7581,
+      "step": 180
+    },
+    {
+      "epoch": 0.30421377183967113,
+      "grad_norm": 0.774492084980011,
+      "learning_rate": 4.875503305657678e-05,
+      "loss": 0.9007,
+      "step": 185
+    },
+    {
+      "epoch": 0.31243576567317577,
+      "grad_norm": 0.6041566729545593,
+      "learning_rate": 4.868705901396926e-05,
+      "loss": 0.821,
+      "step": 190
+    },
+    {
+      "epoch": 0.32065775950668035,
+      "grad_norm": 0.6822388768196106,
+      "learning_rate": 4.86173282675483e-05,
+      "loss": 0.7113,
+      "step": 195
+    },
+    {
+      "epoch": 0.328879753340185,
+      "grad_norm": 0.5451642870903015,
+      "learning_rate": 4.854584598875659e-05,
+      "loss": 0.7905,
+      "step": 200
+    },
+    {
+      "epoch": 0.3371017471736896,
+      "grad_norm": 0.694070041179657,
+      "learning_rate": 4.8472617478935746e-05,
+      "loss": 0.7346,
+      "step": 205
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 0.715756356716156,
+      "learning_rate": 4.839764816893315e-05,
+      "loss": 0.864,
+      "step": 210
+    },
+    {
+      "epoch": 0.35354573484069884,
+      "grad_norm": 0.777726411819458,
+      "learning_rate": 4.8320943618699175e-05,
+      "loss": 0.7845,
+      "step": 215
+    },
+    {
+      "epoch": 0.3617677286742035,
+      "grad_norm": 0.5659850835800171,
+      "learning_rate": 4.8242509516874875e-05,
+      "loss": 0.7677,
+      "step": 220
+    },
+    {
+      "epoch": 0.3699897225077081,
+      "grad_norm": 0.9791976809501648,
+      "learning_rate": 4.8162351680370044e-05,
+      "loss": 0.8872,
+      "step": 225
+    },
+    {
+      "epoch": 0.37821171634121276,
+      "grad_norm": 0.781254231929779,
+      "learning_rate": 4.808047605393186e-05,
+      "loss": 0.8123,
+      "step": 230
+    },
+    {
+      "epoch": 0.3864337101747174,
+      "grad_norm": 0.6411670446395874,
+      "learning_rate": 4.799688870970396e-05,
+      "loss": 0.758,
+      "step": 235
+    },
+    {
+      "epoch": 0.394655704008222,
+      "grad_norm": 0.6815776824951172,
+      "learning_rate": 4.791159584677618e-05,
+      "loss": 0.8342,
+      "step": 240
+    },
+    {
+      "epoch": 0.4028776978417266,
+      "grad_norm": 0.8110681176185608,
+      "learning_rate": 4.7824603790724756e-05,
+      "loss": 0.8678,
+      "step": 245
+    },
+    {
+      "epoch": 0.41109969167523125,
+      "grad_norm": 0.8205195665359497,
+      "learning_rate": 4.7735918993143204e-05,
+      "loss": 0.841,
+      "step": 250
+    },
+    {
+      "epoch": 0.4193216855087359,
+      "grad_norm": 0.6616660952568054,
+      "learning_rate": 4.7645548031163875e-05,
+      "loss": 0.7849,
+      "step": 255
+    },
+    {
+      "epoch": 0.42754367934224047,
+      "grad_norm": 1.2129219770431519,
+      "learning_rate": 4.755349760697018e-05,
+      "loss": 0.834,
+      "step": 260
+    },
+    {
+      "epoch": 0.4357656731757451,
+      "grad_norm": 3.43440580368042,
+      "learning_rate": 4.7459774547299475e-05,
+      "loss": 0.8394,
+      "step": 265
+    },
+    {
+      "epoch": 0.44398766700924974,
+      "grad_norm": 0.5488320589065552,
+      "learning_rate": 4.736438580293685e-05,
+      "loss": 0.9777,
+      "step": 270
+    },
+    {
+      "epoch": 0.4522096608427544,
+      "grad_norm": 0.7190982699394226,
+      "learning_rate": 4.726733844819958e-05,
+      "loss": 0.7637,
+      "step": 275
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 1.037620186805725,
+      "learning_rate": 4.716863968041252e-05,
+      "loss": 0.8678,
+      "step": 280
+    },
+    {
+      "epoch": 0.4686536485097636,
+      "grad_norm": 0.9103302955627441,
+      "learning_rate": 4.7068296819374266e-05,
+      "loss": 0.7724,
+      "step": 285
+    },
+    {
+      "epoch": 0.47687564234326824,
+      "grad_norm": 0.9514378905296326,
+      "learning_rate": 4.6966317306814366e-05,
+      "loss": 0.8527,
+      "step": 290
+    },
+    {
+      "epoch": 0.4850976361767729,
+      "grad_norm": 1.0511500835418701,
+      "learning_rate": 4.686270870584136e-05,
+      "loss": 0.7902,
+      "step": 295
+    },
+    {
+      "epoch": 0.4933196300102775,
+      "grad_norm": 0.8145704865455627,
+      "learning_rate": 4.675747870038192e-05,
+      "loss": 0.8946,
+      "step": 300
+    },
+    {
+      "epoch": 0.5015416238437821,
+      "grad_norm": 1.0371451377868652,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.8673,
+      "step": 305
+    },
+    {
+      "epoch": 0.5097636176772867,
+      "grad_norm": 0.6650281548500061,
+      "learning_rate": 4.6542185812372896e-05,
+      "loss": 0.7537,
+      "step": 310
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 0.6645053029060364,
+      "learning_rate": 4.6432138896593905e-05,
+      "loss": 0.849,
+      "step": 315
+    },
+    {
+      "epoch": 0.526207605344296,
+      "grad_norm": 0.6810983419418335,
+      "learning_rate": 4.6320502508685525e-05,
+      "loss": 0.8381,
+      "step": 320
+    },
+    {
+      "epoch": 0.5344295991778006,
+      "grad_norm": 0.6818865537643433,
+      "learning_rate": 4.620728492793934e-05,
+      "loss": 0.7549,
+      "step": 325
+    },
+    {
+      "epoch": 0.5426515930113053,
+      "grad_norm": 0.6401437520980835,
+      "learning_rate": 4.609249455091299e-05,
+      "loss": 0.7997,
+      "step": 330
+    },
+    {
+      "epoch": 0.5508735868448099,
+      "grad_norm": 0.9009031057357788,
+      "learning_rate": 4.597613989080739e-05,
+      "loss": 0.7419,
+      "step": 335
+    },
+    {
+      "epoch": 0.5590955806783144,
+      "grad_norm": 0.7448415756225586,
+      "learning_rate": 4.585822957683544e-05,
+      "loss": 0.8626,
+      "step": 340
+    },
+    {
+      "epoch": 0.5673175745118191,
+      "grad_norm": 0.7883594036102295,
+      "learning_rate": 4.573877235358204e-05,
+      "loss": 0.8378,
+      "step": 345
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.7353366613388062,
+      "learning_rate": 4.5617777080355515e-05,
+      "loss": 0.7941,
+      "step": 350
+    },
+    {
+      "epoch": 0.5837615621788284,
+      "grad_norm": 0.6732987761497498,
+      "learning_rate": 4.549525273053067e-05,
+      "loss": 0.7599,
+      "step": 355
+    },
+    {
+      "epoch": 0.591983556012333,
+      "grad_norm": 0.7016430497169495,
+      "learning_rate": 4.5371208390883186e-05,
+      "loss": 0.7602,
+      "step": 360
+    },
+    {
+      "epoch": 0.6002055498458376,
+      "grad_norm": 0.765799880027771,
+      "learning_rate": 4.524565326091583e-05,
+      "loss": 0.8385,
+      "step": 365
+    },
+    {
+      "epoch": 0.6084275436793423,
+      "grad_norm": 0.7388527989387512,
+      "learning_rate": 4.5118596652176116e-05,
+      "loss": 0.8099,
+      "step": 370
+    },
+    {
+      "epoch": 0.6166495375128469,
+      "grad_norm": 0.6414201259613037,
+      "learning_rate": 4.499004798756577e-05,
+      "loss": 0.875,
+      "step": 375
+    },
+    {
+      "epoch": 0.6248715313463515,
+      "grad_norm": 0.6936383843421936,
+      "learning_rate": 4.486001680064187e-05,
+      "loss": 0.7498,
+      "step": 380
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 8.751770973205566,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.8769,
+      "step": 385
+    },
+    {
+      "epoch": 0.6413155190133607,
+      "grad_norm": 0.9969173073768616,
+      "learning_rate": 4.4595545543108235e-05,
+      "loss": 0.9605,
+      "step": 390
+    },
+    {
+      "epoch": 0.6495375128468653,
+      "grad_norm": 0.6103174090385437,
+      "learning_rate": 4.446112508648546e-05,
+      "loss": 0.9421,
+      "step": 395
+    },
+    {
+      "epoch": 0.65775950668037,
+      "grad_norm": 0.5853813290596008,
+      "learning_rate": 4.4325261334068426e-05,
+      "loss": 0.7232,
+      "step": 400
+    },
+    {
+      "epoch": 0.6659815005138746,
+      "grad_norm": 0.6471512913703918,
+      "learning_rate": 4.418796436192322e-05,
+      "loss": 0.8164,
+      "step": 405
+    },
+    {
+      "epoch": 0.6742034943473793,
+      "grad_norm": 0.6468719244003296,
+      "learning_rate": 4.404924435240781e-05,
+      "loss": 0.8688,
+      "step": 410
+    },
+    {
+      "epoch": 0.6824254881808839,
+      "grad_norm": 2.313459873199463,
+      "learning_rate": 4.390911159341697e-05,
+      "loss": 0.771,
+      "step": 415
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 0.9390446543693542,
+      "learning_rate": 4.3767576477619163e-05,
+      "loss": 0.7608,
+      "step": 420
+    },
+    {
+      "epoch": 0.6988694758478932,
+      "grad_norm": 0.7414926886558533,
+      "learning_rate": 4.362464950168593e-05,
+      "loss": 0.8851,
+      "step": 425
+    },
+    {
+      "epoch": 0.7070914696813977,
+      "grad_norm": 4.740745544433594,
+      "learning_rate": 4.348034126551332e-05,
+      "loss": 0.9257,
+      "step": 430
+    },
+    {
+      "epoch": 0.7153134635149023,
+      "grad_norm": 0.7543152570724487,
+      "learning_rate": 4.3334662471435844e-05,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.723535457348407,
+      "grad_norm": 0.811599850654602,
+      "learning_rate": 4.31876239234327e-05,
+      "loss": 0.7989,
+      "step": 440
+    },
+    {
+      "epoch": 0.7317574511819116,
+      "grad_norm": 0.8794097900390625,
+      "learning_rate": 4.303923652632655e-05,
+      "loss": 0.7349,
+      "step": 445
+    },
+    {
+      "epoch": 0.7399794450154162,
+      "grad_norm": 0.7543870806694031,
+      "learning_rate": 4.28895112849748e-05,
+      "loss": 0.7606,
+      "step": 450
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 0.704965353012085,
+      "learning_rate": 4.273845930345339e-05,
+      "loss": 0.7725,
+      "step": 455
+    },
+    {
+      "epoch": 0.7564234326824255,
+      "grad_norm": 1.0041465759277344,
+      "learning_rate": 4.2586091784233326e-05,
+      "loss": 0.7289,
+      "step": 460
+    },
+    {
+      "epoch": 0.7646454265159301,
+      "grad_norm": 0.9165995717048645,
+      "learning_rate": 4.2432420027349886e-05,
+      "loss": 0.8736,
+      "step": 465
+    },
+    {
+      "epoch": 0.7728674203494348,
+      "grad_norm": 0.7650847434997559,
+      "learning_rate": 4.227745542956452e-05,
+      "loss": 0.7891,
+      "step": 470
+    },
+    {
+      "epoch": 0.7810894141829393,
+      "grad_norm": 0.8251364231109619,
+      "learning_rate": 4.212120948351968e-05,
+      "loss": 0.743,
+      "step": 475
+    },
+    {
+      "epoch": 0.789311408016444,
+      "grad_norm": 1.5619304180145264,
+      "learning_rate": 4.196369377688646e-05,
+      "loss": 0.8561,
+      "step": 480
+    },
+    {
+      "epoch": 0.7975334018499486,
+      "grad_norm": 0.6772528886795044,
+      "learning_rate": 4.180491999150527e-05,
+      "loss": 0.7763,
+      "step": 485
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 0.7238550782203674,
+      "learning_rate": 4.164489990251937e-05,
+      "loss": 0.7988,
+      "step": 490
+    },
+    {
+      "epoch": 0.8139773895169579,
+      "grad_norm": 0.9421666264533997,
+      "learning_rate": 4.148364537750172e-05,
+      "loss": 0.9225,
+      "step": 495
+    },
+    {
+      "epoch": 0.8221993833504625,
+      "grad_norm": 0.9528664350509644,
+      "learning_rate": 4.132116837557477e-05,
+      "loss": 0.8358,
+      "step": 500
+    },
+    {
+      "epoch": 0.8304213771839671,
+      "grad_norm": 0.7147894501686096,
+      "learning_rate": 4.115748094652352e-05,
+      "loss": 0.8278,
+      "step": 505
+    },
+    {
+      "epoch": 0.8386433710174718,
+      "grad_norm": 0.7133510112762451,
+      "learning_rate": 4.0992595229901944e-05,
+      "loss": 0.8236,
+      "step": 510
+    },
+    {
+      "epoch": 0.8468653648509764,
+      "grad_norm": 1.1197230815887451,
+      "learning_rate": 4.082652345413259e-05,
+      "loss": 0.7465,
+      "step": 515
+    },
+    {
+      "epoch": 0.8550873586844809,
+      "grad_norm": 0.7799179553985596,
+      "learning_rate": 4.0659277935599785e-05,
+      "loss": 0.8194,
+      "step": 520
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.8654146790504456,
+      "learning_rate": 4.049087107773612e-05,
+      "loss": 0.7754,
+      "step": 525
+    },
+    {
+      "epoch": 0.8715313463514902,
+      "grad_norm": 1.5001493692398071,
+      "learning_rate": 4.032131537010264e-05,
+      "loss": 0.7589,
+      "step": 530
+    },
+    {
+      "epoch": 0.8797533401849948,
+      "grad_norm": 1.256003737449646,
+      "learning_rate": 4.015062338746256e-05,
+      "loss": 0.8673,
+      "step": 535
+    },
+    {
+      "epoch": 0.8879753340184995,
+      "grad_norm": 0.9992612600326538,
+      "learning_rate": 3.997880778884866e-05,
+      "loss": 0.6732,
+      "step": 540
+    },
+    {
+      "epoch": 0.8961973278520041,
+      "grad_norm": 0.6338282227516174,
+      "learning_rate": 3.9805881316624506e-05,
+      "loss": 0.7108,
+      "step": 545
+    },
+    {
+      "epoch": 0.9044193216855088,
+      "grad_norm": 0.6869713664054871,
+      "learning_rate": 3.963185679553936e-05,
+      "loss": 0.8243,
+      "step": 550
+    },
+    {
+      "epoch": 0.9126413155190134,
+      "grad_norm": 1.1732268333435059,
+      "learning_rate": 3.945674713177715e-05,
+      "loss": 0.81,
+      "step": 555
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 0.8158470988273621,
+      "learning_rate": 3.928056531199922e-05,
+      "loss": 0.7879,
+      "step": 560
+    },
+    {
+      "epoch": 0.9290853031860226,
+      "grad_norm": 0.6695348620414734,
+      "learning_rate": 3.910332440238128e-05,
+      "loss": 0.7525,
+      "step": 565
+    },
+    {
+      "epoch": 0.9373072970195272,
+      "grad_norm": 0.7612968683242798,
+      "learning_rate": 3.8925037547644306e-05,
+      "loss": 0.7921,
+      "step": 570
+    },
+    {
+      "epoch": 0.9455292908530318,
+      "grad_norm": 0.6554402709007263,
+      "learning_rate": 3.874571797007974e-05,
+      "loss": 0.7676,
+      "step": 575
+    },
+    {
+      "epoch": 0.9537512846865365,
+      "grad_norm": 0.6809045076370239,
+      "learning_rate": 3.856537896856887e-05,
+      "loss": 0.7712,
+      "step": 580
+    },
+    {
+      "epoch": 0.9619732785200411,
+      "grad_norm": 0.6195858120918274,
+      "learning_rate": 3.838403391759652e-05,
+      "loss": 0.8727,
+      "step": 585
+    },
+    {
+      "epoch": 0.9701952723535457,
+      "grad_norm": 0.5144709944725037,
+      "learning_rate": 3.82016962662592e-05,
+      "loss": 0.7533,
+      "step": 590
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 0.6085109710693359,
+      "learning_rate": 3.801837953726767e-05,
+      "loss": 0.8188,
+      "step": 595
+    },
+    {
+      "epoch": 0.986639260020555,
+      "grad_norm": 0.5800123810768127,
+      "learning_rate": 3.7834097325944013e-05,
+      "loss": 0.6959,
+      "step": 600
+    },
+    {
+      "epoch": 0.9948612538540597,
+      "grad_norm": 0.7396177053451538,
+      "learning_rate": 3.764886329921342e-05,
+      "loss": 0.8678,
+      "step": 605
+    },
+    {
+      "epoch": 1.0030832476875642,
+      "grad_norm": 0.6835121512413025,
+      "learning_rate": 3.746269119459058e-05,
+      "loss": 0.6889,
+      "step": 610
+    },
+    {
+      "epoch": 1.0113052415210688,
+      "grad_norm": 0.5903937220573425,
+      "learning_rate": 3.7275594819160864e-05,
+      "loss": 0.7737,
+      "step": 615
+    },
+    {
+      "epoch": 1.0195272353545735,
+      "grad_norm": 0.7912169098854065,
+      "learning_rate": 3.708758804855637e-05,
+      "loss": 0.8015,
+      "step": 620
+    },
+    {
+      "epoch": 1.027749229188078,
+      "grad_norm": 0.6999536156654358,
+      "learning_rate": 3.689868482592684e-05,
+      "loss": 0.8742,
+      "step": 625
+    },
+    {
+      "epoch": 1.0359712230215827,
+      "grad_norm": 0.7941098809242249,
+      "learning_rate": 3.670889916090562e-05,
+      "loss": 0.8183,
+      "step": 630
+    },
+    {
+      "epoch": 1.0441932168550874,
+      "grad_norm": 2.4059693813323975,
+      "learning_rate": 3.651824512857062e-05,
+      "loss": 0.7953,
+      "step": 635
+    },
+    {
+      "epoch": 1.052415210688592,
+      "grad_norm": 0.6197062730789185,
+      "learning_rate": 3.632673686840051e-05,
+      "loss": 0.8217,
+      "step": 640
+    },
+    {
+      "epoch": 1.0606372045220966,
+      "grad_norm": 0.7037258744239807,
+      "learning_rate": 3.6134388583226086e-05,
+      "loss": 0.8225,
+      "step": 645
+    },
+    {
+      "epoch": 1.0688591983556013,
+      "grad_norm": 0.6145721077919006,
+      "learning_rate": 3.594121453817692e-05,
+      "loss": 0.8372,
+      "step": 650
+    },
+    {
+      "epoch": 1.077081192189106,
+      "grad_norm": 0.864341139793396,
+      "learning_rate": 3.574722905962342e-05,
+      "loss": 0.8261,
+      "step": 655
+    },
+    {
+      "epoch": 1.0853031860226106,
+      "grad_norm": 0.9232112169265747,
+      "learning_rate": 3.555244653411438e-05,
+      "loss": 0.7396,
+      "step": 660
+    },
+    {
+      "epoch": 1.0935251798561152,
+      "grad_norm": 0.7316189408302307,
+      "learning_rate": 3.535688140730997e-05,
+      "loss": 0.7587,
+      "step": 665
+    },
+    {
+      "epoch": 1.1017471736896198,
+      "grad_norm": 1.003225326538086,
+      "learning_rate": 3.516054818291048e-05,
+      "loss": 0.857,
+      "step": 670
+    },
+    {
+      "epoch": 1.1099691675231242,
+      "grad_norm": 0.8353930711746216,
+      "learning_rate": 3.496346142158058e-05,
+      "loss": 0.8011,
+      "step": 675
+    },
+    {
+      "epoch": 1.1181911613566289,
+      "grad_norm": 0.6220695376396179,
+      "learning_rate": 3.4765635739869565e-05,
+      "loss": 0.9088,
+      "step": 680
+    },
+    {
+      "epoch": 1.1264131551901335,
+      "grad_norm": 0.889065682888031,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.7873,
+      "step": 685
+    },
+    {
+      "epoch": 1.1346351490236382,
+      "grad_norm": 0.6756345629692078,
+      "learning_rate": 3.4367826354415984e-05,
+      "loss": 0.8425,
+      "step": 690
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.3749688863754272,
+      "learning_rate": 3.416787215341855e-05,
+      "loss": 0.6699,
+      "step": 695
+    },
+    {
+      "epoch": 1.1510791366906474,
+      "grad_norm": 0.810850977897644,
+      "learning_rate": 3.3967238035342185e-05,
+      "loss": 0.8184,
+      "step": 700
+    },
+    {
+      "epoch": 1.159301130524152,
+      "grad_norm": 0.8415716886520386,
+      "learning_rate": 3.376593887981887e-05,
+      "loss": 0.7828,
+      "step": 705
+    },
+    {
+      "epoch": 1.1675231243576567,
+      "grad_norm": 1.6610947847366333,
+      "learning_rate": 3.356398961580172e-05,
+      "loss": 0.9209,
+      "step": 710
+    },
+    {
+      "epoch": 1.1757451181911613,
+      "grad_norm": 0.7330360412597656,
+      "learning_rate": 3.336140522045791e-05,
+      "loss": 0.7977,
+      "step": 715
+    },
+    {
+      "epoch": 1.183967112024666,
+      "grad_norm": 0.9250292778015137,
+      "learning_rate": 3.315820071805785e-05,
+      "loss": 0.848,
+      "step": 720
+    },
+    {
+      "epoch": 1.1921891058581706,
+      "grad_norm": 0.9417344927787781,
+      "learning_rate": 3.2954391178860954e-05,
+      "loss": 0.7302,
+      "step": 725
+    },
+    {
+      "epoch": 1.2004110996916753,
+      "grad_norm": 1.44640052318573,
+      "learning_rate": 3.2749991717998007e-05,
+      "loss": 0.713,
+      "step": 730
+    },
+    {
+      "epoch": 1.20863309352518,
+      "grad_norm": 0.7730007171630859,
+      "learning_rate": 3.254501749435015e-05,
+      "loss": 0.7393,
+      "step": 735
+    },
+    {
+      "epoch": 1.2168550873586845,
+      "grad_norm": 0.7143975496292114,
+      "learning_rate": 3.233948370942467e-05,
+      "loss": 0.7619,
+      "step": 740
+    },
+    {
+      "epoch": 1.2250770811921892,
+      "grad_norm": 1.0002775192260742,
+      "learning_rate": 3.213340560622763e-05,
+      "loss": 0.7749,
+      "step": 745
+    },
+    {
+      "epoch": 1.2332990750256938,
+      "grad_norm": 0.9485899209976196,
+      "learning_rate": 3.192679846813335e-05,
+      "loss": 0.688,
+      "step": 750
+    },
+    {
+      "epoch": 1.2415210688591984,
+      "grad_norm": 1.6718777418136597,
+      "learning_rate": 3.1719677617751006e-05,
+      "loss": 0.8177,
+      "step": 755
+    },
+    {
+      "epoch": 1.249743062692703,
+      "grad_norm": 0.9025570750236511,
+      "learning_rate": 3.1512058415788183e-05,
+      "loss": 0.8364,
+      "step": 760
+    },
+    {
+      "epoch": 1.2579650565262077,
+      "grad_norm": 0.7739228010177612,
+      "learning_rate": 3.130395625991177e-05,
+      "loss": 0.8356,
+      "step": 765
+    },
+    {
+      "epoch": 1.2661870503597124,
+      "grad_norm": 0.8168063759803772,
+      "learning_rate": 3.1095386583605954e-05,
+      "loss": 0.7878,
+      "step": 770
+    },
+    {
+      "epoch": 1.274409044193217,
+      "grad_norm": 0.7470309138298035,
+      "learning_rate": 3.088636485502764e-05,
+      "loss": 0.8318,
+      "step": 775
+    },
+    {
+      "epoch": 1.2826310380267214,
+      "grad_norm": 0.7045716643333435,
+      "learning_rate": 3.0676906575859334e-05,
+      "loss": 0.7219,
+      "step": 780
+    },
+    {
+      "epoch": 1.290853031860226,
+      "grad_norm": 0.6814378499984741,
+      "learning_rate": 3.04670272801594e-05,
+      "loss": 0.8657,
+      "step": 785
+    },
+    {
+      "epoch": 1.2990750256937307,
+      "grad_norm": 1.2378205060958862,
+      "learning_rate": 3.0256742533210086e-05,
+      "loss": 0.7469,
+      "step": 790
+    },
+    {
+      "epoch": 1.3072970195272353,
+      "grad_norm": 0.9097736477851868,
+      "learning_rate": 3.0046067930363137e-05,
+      "loss": 0.9315,
+      "step": 795
+    },
+    {
+      "epoch": 1.31551901336074,
+      "grad_norm": 1.4382425546646118,
+      "learning_rate": 2.983501909588317e-05,
+      "loss": 0.8883,
+      "step": 800
+    },
+    {
+      "epoch": 1.3237410071942446,
+      "grad_norm": 1.036093831062317,
+      "learning_rate": 2.9623611681788965e-05,
+      "loss": 0.7888,
+      "step": 805
+    },
+    {
+      "epoch": 1.3319630010277492,
+      "grad_norm": 0.8393096327781677,
+      "learning_rate": 2.9411861366692627e-05,
+      "loss": 0.7262,
+      "step": 810
+    },
+    {
+      "epoch": 1.3401849948612539,
+      "grad_norm": 0.9713601469993591,
+      "learning_rate": 2.9199783854636865e-05,
+      "loss": 0.8034,
+      "step": 815
+    },
+    {
+      "epoch": 1.3484069886947585,
+      "grad_norm": 0.752566933631897,
+      "learning_rate": 2.8987394873930275e-05,
+      "loss": 0.6505,
+      "step": 820
+    },
+    {
+      "epoch": 1.3566289825282631,
+      "grad_norm": 1.0012316703796387,
+      "learning_rate": 2.8774710175980922e-05,
+      "loss": 0.799,
+      "step": 825
+    },
+    {
+      "epoch": 1.3648509763617678,
+      "grad_norm": 0.9846720695495605,
+      "learning_rate": 2.856174553412816e-05,
+      "loss": 0.8233,
+      "step": 830
+    },
+    {
+      "epoch": 1.3730729701952724,
+      "grad_norm": 0.6868287920951843,
+      "learning_rate": 2.834851674247282e-05,
+      "loss": 0.7477,
+      "step": 835
+    },
+    {
+      "epoch": 1.381294964028777,
+      "grad_norm": 0.701734721660614,
+      "learning_rate": 2.813503961470587e-05,
+      "loss": 0.7528,
+      "step": 840
+    },
+    {
+      "epoch": 1.3895169578622815,
+      "grad_norm": 0.6953380107879639,
+      "learning_rate": 2.7921329982935646e-05,
+      "loss": 0.8185,
+      "step": 845
+    },
+    {
+      "epoch": 1.397738951695786,
+      "grad_norm": 1.0073038339614868,
+      "learning_rate": 2.7707403696513688e-05,
+      "loss": 0.7114,
+      "step": 850
+    },
+    {
+      "epoch": 1.4059609455292907,
+      "grad_norm": 1.3499199151992798,
+      "learning_rate": 2.7493276620859298e-05,
+      "loss": 0.8409,
+      "step": 855
+    },
+    {
+      "epoch": 1.4141829393627954,
+      "grad_norm": 0.6113609671592712,
+      "learning_rate": 2.727896463628289e-05,
+      "loss": 0.7633,
+      "step": 860
+    },
+    {
+      "epoch": 1.4224049331963,
+      "grad_norm": 0.7573457360267639,
+      "learning_rate": 2.7064483636808313e-05,
+      "loss": 0.731,
+      "step": 865
+    },
+    {
+      "epoch": 1.4306269270298047,
+      "grad_norm": 0.7836306691169739,
+      "learning_rate": 2.6849849528994053e-05,
+      "loss": 0.8232,
+      "step": 870
+    },
+    {
+      "epoch": 1.4388489208633093,
+      "grad_norm": 0.7488899230957031,
+      "learning_rate": 2.663507823075358e-05,
+      "loss": 0.785,
+      "step": 875
+    },
+    {
+      "epoch": 1.447070914696814,
+      "grad_norm": 0.8522717952728271,
+      "learning_rate": 2.642018567017482e-05,
+      "loss": 0.6938,
+      "step": 880
+    },
+    {
+      "epoch": 1.4552929085303186,
+      "grad_norm": 1.3761483430862427,
+      "learning_rate": 2.6205187784338874e-05,
+      "loss": 0.7444,
+      "step": 885
+    },
+    {
+      "epoch": 1.4635149023638232,
+      "grad_norm": 0.669750988483429,
+      "learning_rate": 2.5990100518138088e-05,
+      "loss": 0.7938,
+      "step": 890
+    },
+    {
+      "epoch": 1.4717368961973278,
+      "grad_norm": 0.836729884147644,
+      "learning_rate": 2.577493982309352e-05,
+      "loss": 0.8329,
+      "step": 895
+    },
+    {
+      "epoch": 1.4799588900308325,
+      "grad_norm": 1.0972259044647217,
+      "learning_rate": 2.555972165617194e-05,
+      "loss": 0.8275,
+      "step": 900
+    },
+    {
+      "epoch": 1.4881808838643371,
+      "grad_norm": 1.3486735820770264,
+      "learning_rate": 2.5344461978602413e-05,
+      "loss": 0.8497,
+      "step": 905
+    },
+    {
+      "epoch": 1.4964028776978417,
+      "grad_norm": 0.8719611763954163,
+      "learning_rate": 2.512917675469253e-05,
+      "loss": 0.7744,
+      "step": 910
+    },
+    {
+      "epoch": 1.5046248715313464,
+      "grad_norm": 0.7670440077781677,
+      "learning_rate": 2.49138819506445e-05,
+      "loss": 0.8424,
+      "step": 915
+    },
+    {
+      "epoch": 1.512846865364851,
+      "grad_norm": 0.8988850116729736,
+      "learning_rate": 2.4698593533371038e-05,
+      "loss": 0.8447,
+      "step": 920
+    },
+    {
+      "epoch": 1.5210688591983557,
+      "grad_norm": 1.1595510244369507,
+      "learning_rate": 2.4483327469311148e-05,
+      "loss": 0.7433,
+      "step": 925
+    },
+    {
+      "epoch": 1.5292908530318603,
+      "grad_norm": 0.9172937870025635,
+      "learning_rate": 2.4268099723246088e-05,
+      "loss": 0.7145,
+      "step": 930
+    },
+    {
+      "epoch": 1.537512846865365,
+      "grad_norm": 0.6933180093765259,
+      "learning_rate": 2.405292625711535e-05,
+      "loss": 0.8367,
+      "step": 935
+    },
+    {
+      "epoch": 1.5457348406988696,
+      "grad_norm": 0.67847740650177,
+      "learning_rate": 2.3837823028832822e-05,
+      "loss": 0.7216,
+      "step": 940
+    },
+    {
+      "epoch": 1.5539568345323742,
+      "grad_norm": 1.0530544519424438,
+      "learning_rate": 2.3622805991103362e-05,
+      "loss": 0.8308,
+      "step": 945
+    },
+    {
+      "epoch": 1.5621788283658788,
+      "grad_norm": 1.2174192667007446,
+      "learning_rate": 2.340789109023969e-05,
+      "loss": 0.7712,
+      "step": 950
+    },
+    {
+      "epoch": 1.5704008221993835,
+      "grad_norm": 0.8486307859420776,
+      "learning_rate": 2.3193094264979736e-05,
+      "loss": 0.6857,
+      "step": 955
+    },
+    {
+      "epoch": 1.5786228160328881,
+      "grad_norm": 0.8623594045639038,
+      "learning_rate": 2.2978431445304575e-05,
+      "loss": 0.7837,
+      "step": 960
+    },
+    {
+      "epoch": 1.5868448098663928,
+      "grad_norm": 0.6950398683547974,
+      "learning_rate": 2.2763918551257018e-05,
+      "loss": 0.71,
+      "step": 965
+    },
+    {
+      "epoch": 1.5950668036998972,
+      "grad_norm": 1.0914013385772705,
+      "learning_rate": 2.2549571491760986e-05,
+      "loss": 0.7722,
+      "step": 970
+    },
+    {
+      "epoch": 1.6032887975334018,
+      "grad_norm": 0.9067034721374512,
+      "learning_rate": 2.2335406163441563e-05,
+      "loss": 0.8407,
+      "step": 975
+    },
+    {
+      "epoch": 1.6115107913669064,
+      "grad_norm": 0.6557819843292236,
+      "learning_rate": 2.21214384494461e-05,
+      "loss": 0.6819,
+      "step": 980
+    },
+    {
+      "epoch": 1.619732785200411,
+      "grad_norm": 1.041945457458496,
+      "learning_rate": 2.190768421826631e-05,
+      "loss": 0.7743,
+      "step": 985
+    },
+    {
+      "epoch": 1.6279547790339157,
+      "grad_norm": 1.0989412069320679,
+      "learning_rate": 2.169415932256135e-05,
+      "loss": 0.724,
+      "step": 990
+    },
+    {
+      "epoch": 1.6361767728674204,
+      "grad_norm": 1.0662113428115845,
+      "learning_rate": 2.1480879597982153e-05,
+      "loss": 0.9112,
+      "step": 995
+    },
+    {
+      "epoch": 1.644398766700925,
+      "grad_norm": 0.7899945974349976,
+      "learning_rate": 2.1267860861997035e-05,
+      "loss": 0.7436,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1824,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 4.714445035856855e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da40bedcaa97ca5797127d487348c4b521b16e2df25cfedbca83617e93b2e68
+size 5176

checkpoint-1100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.0

checkpoint-1100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e76298071f0726b1f85f845065d2a795fab1082471258ea235115debd4084de
+size 13648432

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64122776015ba993589d8002eb459ceb7bab1e11a796847623209d1ded9d9368
+size 27370618

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8ab60446b0f45ee957ac353a2566feabee948f07e9104e0af91cc69b851fdf
+size 1064

checkpoint-1100/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-1100/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1100/trainer_state.json

@@ -0,0 +1,1561 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8088386433710175,
+  "eval_steps": 500,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008221993833504625,
+      "grad_norm": 1.0209685564041138,
+      "learning_rate": 4.999907296225947e-05,
+      "loss": 1.1323,
+      "step": 5
+    },
+    {
+      "epoch": 0.01644398766700925,
+      "grad_norm": 1.084985375404358,
+      "learning_rate": 4.9996291917789814e-05,
+      "loss": 1.043,
+      "step": 10
+    },
+    {
+      "epoch": 0.024665981500513873,
+      "grad_norm": 1.1630356311798096,
+      "learning_rate": 4.999165707284169e-05,
+      "loss": 1.0403,
+      "step": 15
+    },
+    {
+      "epoch": 0.0328879753340185,
+      "grad_norm": 0.9428950548171997,
+      "learning_rate": 4.998516877114917e-05,
+      "loss": 0.7908,
+      "step": 20
+    },
+    {
+      "epoch": 0.041109969167523124,
+      "grad_norm": 0.8565282225608826,
+      "learning_rate": 4.9976827493904315e-05,
+      "loss": 0.8942,
+      "step": 25
+    },
+    {
+      "epoch": 0.04933196300102775,
+      "grad_norm": 0.9475494623184204,
+      "learning_rate": 4.996882074080329e-05,
+      "loss": 1.3336,
+      "step": 30
+    },
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 3.55914044380188,
+      "learning_rate": 4.9957145758791006e-05,
+      "loss": 0.7717,
+      "step": 35
+    },
+    {
+      "epoch": 0.065775950668037,
+      "grad_norm": 0.6254042983055115,
+      "learning_rate": 4.9943619879497585e-05,
+      "loss": 0.7791,
+      "step": 40
+    },
+    {
+      "epoch": 0.07399794450154162,
+      "grad_norm": 1.1033686399459839,
+      "learning_rate": 4.992824410604308e-05,
+      "loss": 0.816,
+      "step": 45
+    },
+    {
+      "epoch": 0.08221993833504625,
+      "grad_norm": 0.6939295530319214,
+      "learning_rate": 4.991101957874126e-05,
+      "loss": 0.8761,
+      "step": 50
+    },
+    {
+      "epoch": 0.09044193216855087,
+      "grad_norm": 0.957773745059967,
+      "learning_rate": 4.98919475750151e-05,
+      "loss": 0.8573,
+      "step": 55
+    },
+    {
+      "epoch": 0.0986639260020555,
+      "grad_norm": 0.6181407570838928,
+      "learning_rate": 4.987102950930195e-05,
+      "loss": 0.8158,
+      "step": 60
+    },
+    {
+      "epoch": 0.10688591983556012,
+      "grad_norm": 0.6531780362129211,
+      "learning_rate": 4.984826693294874e-05,
+      "loss": 0.8796,
+      "step": 65
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 1.6238263845443726,
+      "learning_rate": 4.982366153409685e-05,
+      "loss": 0.7839,
+      "step": 70
+    },
+    {
+      "epoch": 0.12332990750256938,
+      "grad_norm": 18.583261489868164,
+      "learning_rate": 4.979721513755695e-05,
+      "loss": 1.1142,
+      "step": 75
+    },
+    {
+      "epoch": 0.131551901336074,
+      "grad_norm": 0.7723462581634521,
+      "learning_rate": 4.9768929704673654e-05,
+      "loss": 0.8193,
+      "step": 80
+    },
+    {
+      "epoch": 0.1397738951695786,
+      "grad_norm": 0.7994495630264282,
+      "learning_rate": 4.973880733318007e-05,
+      "loss": 0.9853,
+      "step": 85
+    },
+    {
+      "epoch": 0.14799588900308325,
+      "grad_norm": 0.5460528135299683,
+      "learning_rate": 4.970685025704222e-05,
+      "loss": 0.861,
+      "step": 90
+    },
+    {
+      "epoch": 0.15621788283658788,
+      "grad_norm": 1.0410531759262085,
+      "learning_rate": 4.9673060846293326e-05,
+      "loss": 0.8044,
+      "step": 95
+    },
+    {
+      "epoch": 0.1644398766700925,
+      "grad_norm": 0.7643013000488281,
+      "learning_rate": 4.963744160685815e-05,
+      "loss": 0.9048,
+      "step": 100
+    },
+    {
+      "epoch": 0.17266187050359713,
+      "grad_norm": 0.9957767724990845,
+      "learning_rate": 4.9599995180367e-05,
+      "loss": 0.8768,
+      "step": 105
+    },
+    {
+      "epoch": 0.18088386433710174,
+      "grad_norm": 0.5331000685691833,
+      "learning_rate": 4.956072434395994e-05,
+      "loss": 0.7871,
+      "step": 110
+    },
+    {
+      "epoch": 0.18910585817060638,
+      "grad_norm": 0.6342468857765198,
+      "learning_rate": 4.951963201008076e-05,
+      "loss": 0.9122,
+      "step": 115
+    },
+    {
+      "epoch": 0.197327852004111,
+      "grad_norm": 0.703365683555603,
+      "learning_rate": 4.947672122626101e-05,
+      "loss": 0.7379,
+      "step": 120
+    },
+    {
+      "epoch": 0.20554984583761562,
+      "grad_norm": 0.7069611549377441,
+      "learning_rate": 4.9431995174893984e-05,
+      "loss": 0.8529,
+      "step": 125
+    },
+    {
+      "epoch": 0.21377183967112023,
+      "grad_norm": 0.7649345993995667,
+      "learning_rate": 4.938545717299867e-05,
+      "loss": 0.8618,
+      "step": 130
+    },
+    {
+      "epoch": 0.22199383350462487,
+      "grad_norm": 0.53890061378479,
+      "learning_rate": 4.9337110671973815e-05,
+      "loss": 0.8235,
+      "step": 135
+    },
+    {
+      "epoch": 0.2302158273381295,
+      "grad_norm": 1.6072089672088623,
+      "learning_rate": 4.928695925734191e-05,
+      "loss": 0.8145,
+      "step": 140
+    },
+    {
+      "epoch": 0.23843782117163412,
+      "grad_norm": 1.1523021459579468,
+      "learning_rate": 4.923500664848326e-05,
+      "loss": 1.1315,
+      "step": 145
+    },
+    {
+      "epoch": 0.24665981500513876,
+      "grad_norm": 0.9310020804405212,
+      "learning_rate": 4.9181256698360216e-05,
+      "loss": 0.9059,
+      "step": 150
+    },
+    {
+      "epoch": 0.25488180883864336,
+      "grad_norm": 1.087494134902954,
+      "learning_rate": 4.912571339323135e-05,
+      "loss": 0.8613,
+      "step": 155
+    },
+    {
+      "epoch": 0.263103802672148,
+      "grad_norm": 0.9017001986503601,
+      "learning_rate": 4.906838085235588e-05,
+      "loss": 0.8456,
+      "step": 160
+    },
+    {
+      "epoch": 0.27132579650565264,
+      "grad_norm": 0.6858020424842834,
+      "learning_rate": 4.900926332768814e-05,
+      "loss": 0.697,
+      "step": 165
+    },
+    {
+      "epoch": 0.2795477903391572,
+      "grad_norm": 0.9164858460426331,
+      "learning_rate": 4.894836520356223e-05,
+      "loss": 0.8006,
+      "step": 170
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 0.6167294979095459,
+      "learning_rate": 4.888569099636692e-05,
+      "loss": 0.7694,
+      "step": 175
+    },
+    {
+      "epoch": 0.2959917780061665,
+      "grad_norm": 0.7028630375862122,
+      "learning_rate": 4.882124535421064e-05,
+      "loss": 0.7581,
+      "step": 180
+    },
+    {
+      "epoch": 0.30421377183967113,
+      "grad_norm": 0.774492084980011,
+      "learning_rate": 4.875503305657678e-05,
+      "loss": 0.9007,
+      "step": 185
+    },
+    {
+      "epoch": 0.31243576567317577,
+      "grad_norm": 0.6041566729545593,
+      "learning_rate": 4.868705901396926e-05,
+      "loss": 0.821,
+      "step": 190
+    },
+    {
+      "epoch": 0.32065775950668035,
+      "grad_norm": 0.6822388768196106,
+      "learning_rate": 4.86173282675483e-05,
+      "loss": 0.7113,
+      "step": 195
+    },
+    {
+      "epoch": 0.328879753340185,
+      "grad_norm": 0.5451642870903015,
+      "learning_rate": 4.854584598875659e-05,
+      "loss": 0.7905,
+      "step": 200
+    },
+    {
+      "epoch": 0.3371017471736896,
+      "grad_norm": 0.694070041179657,
+      "learning_rate": 4.8472617478935746e-05,
+      "loss": 0.7346,
+      "step": 205
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 0.715756356716156,
+      "learning_rate": 4.839764816893315e-05,
+      "loss": 0.864,
+      "step": 210
+    },
+    {
+      "epoch": 0.35354573484069884,
+      "grad_norm": 0.777726411819458,
+      "learning_rate": 4.8320943618699175e-05,
+      "loss": 0.7845,
+      "step": 215
+    },
+    {
+      "epoch": 0.3617677286742035,
+      "grad_norm": 0.5659850835800171,
+      "learning_rate": 4.8242509516874875e-05,
+      "loss": 0.7677,
+      "step": 220
+    },
+    {
+      "epoch": 0.3699897225077081,
+      "grad_norm": 0.9791976809501648,
+      "learning_rate": 4.8162351680370044e-05,
+      "loss": 0.8872,
+      "step": 225
+    },
+    {
+      "epoch": 0.37821171634121276,
+      "grad_norm": 0.781254231929779,
+      "learning_rate": 4.808047605393186e-05,
+      "loss": 0.8123,
+      "step": 230
+    },
+    {
+      "epoch": 0.3864337101747174,
+      "grad_norm": 0.6411670446395874,
+      "learning_rate": 4.799688870970396e-05,
+      "loss": 0.758,
+      "step": 235
+    },
+    {
+      "epoch": 0.394655704008222,
+      "grad_norm": 0.6815776824951172,
+      "learning_rate": 4.791159584677618e-05,
+      "loss": 0.8342,
+      "step": 240
+    },
+    {
+      "epoch": 0.4028776978417266,
+      "grad_norm": 0.8110681176185608,
+      "learning_rate": 4.7824603790724756e-05,
+      "loss": 0.8678,
+      "step": 245
+    },
+    {
+      "epoch": 0.41109969167523125,
+      "grad_norm": 0.8205195665359497,
+      "learning_rate": 4.7735918993143204e-05,
+      "loss": 0.841,
+      "step": 250
+    },
+    {
+      "epoch": 0.4193216855087359,
+      "grad_norm": 0.6616660952568054,
+      "learning_rate": 4.7645548031163875e-05,
+      "loss": 0.7849,
+      "step": 255
+    },
+    {
+      "epoch": 0.42754367934224047,
+      "grad_norm": 1.2129219770431519,
+      "learning_rate": 4.755349760697018e-05,
+      "loss": 0.834,
+      "step": 260
+    },
+    {
+      "epoch": 0.4357656731757451,
+      "grad_norm": 3.43440580368042,
+      "learning_rate": 4.7459774547299475e-05,
+      "loss": 0.8394,
+      "step": 265
+    },
+    {
+      "epoch": 0.44398766700924974,
+      "grad_norm": 0.5488320589065552,
+      "learning_rate": 4.736438580293685e-05,
+      "loss": 0.9777,
+      "step": 270
+    },
+    {
+      "epoch": 0.4522096608427544,
+      "grad_norm": 0.7190982699394226,
+      "learning_rate": 4.726733844819958e-05,
+      "loss": 0.7637,
+      "step": 275
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 1.037620186805725,
+      "learning_rate": 4.716863968041252e-05,
+      "loss": 0.8678,
+      "step": 280
+    },
+    {
+      "epoch": 0.4686536485097636,
+      "grad_norm": 0.9103302955627441,
+      "learning_rate": 4.7068296819374266e-05,
+      "loss": 0.7724,
+      "step": 285
+    },
+    {
+      "epoch": 0.47687564234326824,
+      "grad_norm": 0.9514378905296326,
+      "learning_rate": 4.6966317306814366e-05,
+      "loss": 0.8527,
+      "step": 290
+    },
+    {
+      "epoch": 0.4850976361767729,
+      "grad_norm": 1.0511500835418701,
+      "learning_rate": 4.686270870584136e-05,
+      "loss": 0.7902,
+      "step": 295
+    },
+    {
+      "epoch": 0.4933196300102775,
+      "grad_norm": 0.8145704865455627,
+      "learning_rate": 4.675747870038192e-05,
+      "loss": 0.8946,
+      "step": 300
+    },
+    {
+      "epoch": 0.5015416238437821,
+      "grad_norm": 1.0371451377868652,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.8673,
+      "step": 305
+    },
+    {
+      "epoch": 0.5097636176772867,
+      "grad_norm": 0.6650281548500061,
+      "learning_rate": 4.6542185812372896e-05,
+      "loss": 0.7537,
+      "step": 310
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 0.6645053029060364,
+      "learning_rate": 4.6432138896593905e-05,
+      "loss": 0.849,
+      "step": 315
+    },
+    {
+      "epoch": 0.526207605344296,
+      "grad_norm": 0.6810983419418335,
+      "learning_rate": 4.6320502508685525e-05,
+      "loss": 0.8381,
+      "step": 320
+    },
+    {
+      "epoch": 0.5344295991778006,
+      "grad_norm": 0.6818865537643433,
+      "learning_rate": 4.620728492793934e-05,
+      "loss": 0.7549,
+      "step": 325
+    },
+    {
+      "epoch": 0.5426515930113053,
+      "grad_norm": 0.6401437520980835,
+      "learning_rate": 4.609249455091299e-05,
+      "loss": 0.7997,
+      "step": 330
+    },
+    {
+      "epoch": 0.5508735868448099,
+      "grad_norm": 0.9009031057357788,
+      "learning_rate": 4.597613989080739e-05,
+      "loss": 0.7419,
+      "step": 335
+    },
+    {
+      "epoch": 0.5590955806783144,
+      "grad_norm": 0.7448415756225586,
+      "learning_rate": 4.585822957683544e-05,
+      "loss": 0.8626,
+      "step": 340
+    },
+    {
+      "epoch": 0.5673175745118191,
+      "grad_norm": 0.7883594036102295,
+      "learning_rate": 4.573877235358204e-05,
+      "loss": 0.8378,
+      "step": 345
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.7353366613388062,
+      "learning_rate": 4.5617777080355515e-05,
+      "loss": 0.7941,
+      "step": 350
+    },
+    {
+      "epoch": 0.5837615621788284,
+      "grad_norm": 0.6732987761497498,
+      "learning_rate": 4.549525273053067e-05,
+      "loss": 0.7599,
+      "step": 355
+    },
+    {
+      "epoch": 0.591983556012333,
+      "grad_norm": 0.7016430497169495,
+      "learning_rate": 4.5371208390883186e-05,
+      "loss": 0.7602,
+      "step": 360
+    },
+    {
+      "epoch": 0.6002055498458376,
+      "grad_norm": 0.765799880027771,
+      "learning_rate": 4.524565326091583e-05,
+      "loss": 0.8385,
+      "step": 365
+    },
+    {
+      "epoch": 0.6084275436793423,
+      "grad_norm": 0.7388527989387512,
+      "learning_rate": 4.5118596652176116e-05,
+      "loss": 0.8099,
+      "step": 370
+    },
+    {
+      "epoch": 0.6166495375128469,
+      "grad_norm": 0.6414201259613037,
+      "learning_rate": 4.499004798756577e-05,
+      "loss": 0.875,
+      "step": 375
+    },
+    {
+      "epoch": 0.6248715313463515,
+      "grad_norm": 0.6936383843421936,
+      "learning_rate": 4.486001680064187e-05,
+      "loss": 0.7498,
+      "step": 380
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 8.751770973205566,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.8769,
+      "step": 385
+    },
+    {
+      "epoch": 0.6413155190133607,
+      "grad_norm": 0.9969173073768616,
+      "learning_rate": 4.4595545543108235e-05,
+      "loss": 0.9605,
+      "step": 390
+    },
+    {
+      "epoch": 0.6495375128468653,
+      "grad_norm": 0.6103174090385437,
+      "learning_rate": 4.446112508648546e-05,
+      "loss": 0.9421,
+      "step": 395
+    },
+    {
+      "epoch": 0.65775950668037,
+      "grad_norm": 0.5853813290596008,
+      "learning_rate": 4.4325261334068426e-05,
+      "loss": 0.7232,
+      "step": 400
+    },
+    {
+      "epoch": 0.6659815005138746,
+      "grad_norm": 0.6471512913703918,
+      "learning_rate": 4.418796436192322e-05,
+      "loss": 0.8164,
+      "step": 405
+    },
+    {
+      "epoch": 0.6742034943473793,
+      "grad_norm": 0.6468719244003296,
+      "learning_rate": 4.404924435240781e-05,
+      "loss": 0.8688,
+      "step": 410
+    },
+    {
+      "epoch": 0.6824254881808839,
+      "grad_norm": 2.313459873199463,
+      "learning_rate": 4.390911159341697e-05,
+      "loss": 0.771,
+      "step": 415
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 0.9390446543693542,
+      "learning_rate": 4.3767576477619163e-05,
+      "loss": 0.7608,
+      "step": 420
+    },
+    {
+      "epoch": 0.6988694758478932,
+      "grad_norm": 0.7414926886558533,
+      "learning_rate": 4.362464950168593e-05,
+      "loss": 0.8851,
+      "step": 425
+    },
+    {
+      "epoch": 0.7070914696813977,
+      "grad_norm": 4.740745544433594,
+      "learning_rate": 4.348034126551332e-05,
+      "loss": 0.9257,
+      "step": 430
+    },
+    {
+      "epoch": 0.7153134635149023,
+      "grad_norm": 0.7543152570724487,
+      "learning_rate": 4.3334662471435844e-05,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.723535457348407,
+      "grad_norm": 0.811599850654602,
+      "learning_rate": 4.31876239234327e-05,
+      "loss": 0.7989,
+      "step": 440
+    },
+    {
+      "epoch": 0.7317574511819116,
+      "grad_norm": 0.8794097900390625,
+      "learning_rate": 4.303923652632655e-05,
+      "loss": 0.7349,
+      "step": 445
+    },
+    {
+      "epoch": 0.7399794450154162,
+      "grad_norm": 0.7543870806694031,
+      "learning_rate": 4.28895112849748e-05,
+      "loss": 0.7606,
+      "step": 450
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 0.704965353012085,
+      "learning_rate": 4.273845930345339e-05,
+      "loss": 0.7725,
+      "step": 455
+    },
+    {
+      "epoch": 0.7564234326824255,
+      "grad_norm": 1.0041465759277344,
+      "learning_rate": 4.2586091784233326e-05,
+      "loss": 0.7289,
+      "step": 460
+    },
+    {
+      "epoch": 0.7646454265159301,
+      "grad_norm": 0.9165995717048645,
+      "learning_rate": 4.2432420027349886e-05,
+      "loss": 0.8736,
+      "step": 465
+    },
+    {
+      "epoch": 0.7728674203494348,
+      "grad_norm": 0.7650847434997559,
+      "learning_rate": 4.227745542956452e-05,
+      "loss": 0.7891,
+      "step": 470
+    },
+    {
+      "epoch": 0.7810894141829393,
+      "grad_norm": 0.8251364231109619,
+      "learning_rate": 4.212120948351968e-05,
+      "loss": 0.743,
+      "step": 475
+    },
+    {
+      "epoch": 0.789311408016444,
+      "grad_norm": 1.5619304180145264,
+      "learning_rate": 4.196369377688646e-05,
+      "loss": 0.8561,
+      "step": 480
+    },
+    {
+      "epoch": 0.7975334018499486,
+      "grad_norm": 0.6772528886795044,
+      "learning_rate": 4.180491999150527e-05,
+      "loss": 0.7763,
+      "step": 485
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 0.7238550782203674,
+      "learning_rate": 4.164489990251937e-05,
+      "loss": 0.7988,
+      "step": 490
+    },
+    {
+      "epoch": 0.8139773895169579,
+      "grad_norm": 0.9421666264533997,
+      "learning_rate": 4.148364537750172e-05,
+      "loss": 0.9225,
+      "step": 495
+    },
+    {
+      "epoch": 0.8221993833504625,
+      "grad_norm": 0.9528664350509644,
+      "learning_rate": 4.132116837557477e-05,
+      "loss": 0.8358,
+      "step": 500
+    },
+    {
+      "epoch": 0.8304213771839671,
+      "grad_norm": 0.7147894501686096,
+      "learning_rate": 4.115748094652352e-05,
+      "loss": 0.8278,
+      "step": 505
+    },
+    {
+      "epoch": 0.8386433710174718,
+      "grad_norm": 0.7133510112762451,
+      "learning_rate": 4.0992595229901944e-05,
+      "loss": 0.8236,
+      "step": 510
+    },
+    {
+      "epoch": 0.8468653648509764,
+      "grad_norm": 1.1197230815887451,
+      "learning_rate": 4.082652345413259e-05,
+      "loss": 0.7465,
+      "step": 515
+    },
+    {
+      "epoch": 0.8550873586844809,
+      "grad_norm": 0.7799179553985596,
+      "learning_rate": 4.0659277935599785e-05,
+      "loss": 0.8194,
+      "step": 520
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.8654146790504456,
+      "learning_rate": 4.049087107773612e-05,
+      "loss": 0.7754,
+      "step": 525
+    },
+    {
+      "epoch": 0.8715313463514902,
+      "grad_norm": 1.5001493692398071,
+      "learning_rate": 4.032131537010264e-05,
+      "loss": 0.7589,
+      "step": 530
+    },
+    {
+      "epoch": 0.8797533401849948,
+      "grad_norm": 1.256003737449646,
+      "learning_rate": 4.015062338746256e-05,
+      "loss": 0.8673,
+      "step": 535
+    },
+    {
+      "epoch": 0.8879753340184995,
+      "grad_norm": 0.9992612600326538,
+      "learning_rate": 3.997880778884866e-05,
+      "loss": 0.6732,
+      "step": 540
+    },
+    {
+      "epoch": 0.8961973278520041,
+      "grad_norm": 0.6338282227516174,
+      "learning_rate": 3.9805881316624506e-05,
+      "loss": 0.7108,
+      "step": 545
+    },
+    {
+      "epoch": 0.9044193216855088,
+      "grad_norm": 0.6869713664054871,
+      "learning_rate": 3.963185679553936e-05,
+      "loss": 0.8243,
+      "step": 550
+    },
+    {
+      "epoch": 0.9126413155190134,
+      "grad_norm": 1.1732268333435059,
+      "learning_rate": 3.945674713177715e-05,
+      "loss": 0.81,
+      "step": 555
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 0.8158470988273621,
+      "learning_rate": 3.928056531199922e-05,
+      "loss": 0.7879,
+      "step": 560
+    },
+    {
+      "epoch": 0.9290853031860226,
+      "grad_norm": 0.6695348620414734,
+      "learning_rate": 3.910332440238128e-05,
+      "loss": 0.7525,
+      "step": 565
+    },
+    {
+      "epoch": 0.9373072970195272,
+      "grad_norm": 0.7612968683242798,
+      "learning_rate": 3.8925037547644306e-05,
+      "loss": 0.7921,
+      "step": 570
+    },
+    {
+      "epoch": 0.9455292908530318,
+      "grad_norm": 0.6554402709007263,
+      "learning_rate": 3.874571797007974e-05,
+      "loss": 0.7676,
+      "step": 575
+    },
+    {
+      "epoch": 0.9537512846865365,
+      "grad_norm": 0.6809045076370239,
+      "learning_rate": 3.856537896856887e-05,
+      "loss": 0.7712,
+      "step": 580
+    },
+    {
+      "epoch": 0.9619732785200411,
+      "grad_norm": 0.6195858120918274,
+      "learning_rate": 3.838403391759652e-05,
+      "loss": 0.8727,
+      "step": 585
+    },
+    {
+      "epoch": 0.9701952723535457,
+      "grad_norm": 0.5144709944725037,
+      "learning_rate": 3.82016962662592e-05,
+      "loss": 0.7533,
+      "step": 590
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 0.6085109710693359,
+      "learning_rate": 3.801837953726767e-05,
+      "loss": 0.8188,
+      "step": 595
+    },
+    {
+      "epoch": 0.986639260020555,
+      "grad_norm": 0.5800123810768127,
+      "learning_rate": 3.7834097325944013e-05,
+      "loss": 0.6959,
+      "step": 600
+    },
+    {
+      "epoch": 0.9948612538540597,
+      "grad_norm": 0.7396177053451538,
+      "learning_rate": 3.764886329921342e-05,
+      "loss": 0.8678,
+      "step": 605
+    },
+    {
+      "epoch": 1.0030832476875642,
+      "grad_norm": 0.6835121512413025,
+      "learning_rate": 3.746269119459058e-05,
+      "loss": 0.6889,
+      "step": 610
+    },
+    {
+      "epoch": 1.0113052415210688,
+      "grad_norm": 0.5903937220573425,
+      "learning_rate": 3.7275594819160864e-05,
+      "loss": 0.7737,
+      "step": 615
+    },
+    {
+      "epoch": 1.0195272353545735,
+      "grad_norm": 0.7912169098854065,
+      "learning_rate": 3.708758804855637e-05,
+      "loss": 0.8015,
+      "step": 620
+    },
+    {
+      "epoch": 1.027749229188078,
+      "grad_norm": 0.6999536156654358,
+      "learning_rate": 3.689868482592684e-05,
+      "loss": 0.8742,
+      "step": 625
+    },
+    {
+      "epoch": 1.0359712230215827,
+      "grad_norm": 0.7941098809242249,
+      "learning_rate": 3.670889916090562e-05,
+      "loss": 0.8183,
+      "step": 630
+    },
+    {
+      "epoch": 1.0441932168550874,
+      "grad_norm": 2.4059693813323975,
+      "learning_rate": 3.651824512857062e-05,
+      "loss": 0.7953,
+      "step": 635
+    },
+    {
+      "epoch": 1.052415210688592,
+      "grad_norm": 0.6197062730789185,
+      "learning_rate": 3.632673686840051e-05,
+      "loss": 0.8217,
+      "step": 640
+    },
+    {
+      "epoch": 1.0606372045220966,
+      "grad_norm": 0.7037258744239807,
+      "learning_rate": 3.6134388583226086e-05,
+      "loss": 0.8225,
+      "step": 645
+    },
+    {
+      "epoch": 1.0688591983556013,
+      "grad_norm": 0.6145721077919006,
+      "learning_rate": 3.594121453817692e-05,
+      "loss": 0.8372,
+      "step": 650
+    },
+    {
+      "epoch": 1.077081192189106,
+      "grad_norm": 0.864341139793396,
+      "learning_rate": 3.574722905962342e-05,
+      "loss": 0.8261,
+      "step": 655
+    },
+    {
+      "epoch": 1.0853031860226106,
+      "grad_norm": 0.9232112169265747,
+      "learning_rate": 3.555244653411438e-05,
+      "loss": 0.7396,
+      "step": 660
+    },
+    {
+      "epoch": 1.0935251798561152,
+      "grad_norm": 0.7316189408302307,
+      "learning_rate": 3.535688140730997e-05,
+      "loss": 0.7587,
+      "step": 665
+    },
+    {
+      "epoch": 1.1017471736896198,
+      "grad_norm": 1.003225326538086,
+      "learning_rate": 3.516054818291048e-05,
+      "loss": 0.857,
+      "step": 670
+    },
+    {
+      "epoch": 1.1099691675231242,
+      "grad_norm": 0.8353930711746216,
+      "learning_rate": 3.496346142158058e-05,
+      "loss": 0.8011,
+      "step": 675
+    },
+    {
+      "epoch": 1.1181911613566289,
+      "grad_norm": 0.6220695376396179,
+      "learning_rate": 3.4765635739869565e-05,
+      "loss": 0.9088,
+      "step": 680
+    },
+    {
+      "epoch": 1.1264131551901335,
+      "grad_norm": 0.889065682888031,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.7873,
+      "step": 685
+    },
+    {
+      "epoch": 1.1346351490236382,
+      "grad_norm": 0.6756345629692078,
+      "learning_rate": 3.4367826354415984e-05,
+      "loss": 0.8425,
+      "step": 690
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.3749688863754272,
+      "learning_rate": 3.416787215341855e-05,
+      "loss": 0.6699,
+      "step": 695
+    },
+    {
+      "epoch": 1.1510791366906474,
+      "grad_norm": 0.810850977897644,
+      "learning_rate": 3.3967238035342185e-05,
+      "loss": 0.8184,
+      "step": 700
+    },
+    {
+      "epoch": 1.159301130524152,
+      "grad_norm": 0.8415716886520386,
+      "learning_rate": 3.376593887981887e-05,
+      "loss": 0.7828,
+      "step": 705
+    },
+    {
+      "epoch": 1.1675231243576567,
+      "grad_norm": 1.6610947847366333,
+      "learning_rate": 3.356398961580172e-05,
+      "loss": 0.9209,
+      "step": 710
+    },
+    {
+      "epoch": 1.1757451181911613,
+      "grad_norm": 0.7330360412597656,
+      "learning_rate": 3.336140522045791e-05,
+      "loss": 0.7977,
+      "step": 715
+    },
+    {
+      "epoch": 1.183967112024666,
+      "grad_norm": 0.9250292778015137,
+      "learning_rate": 3.315820071805785e-05,
+      "loss": 0.848,
+      "step": 720
+    },
+    {
+      "epoch": 1.1921891058581706,
+      "grad_norm": 0.9417344927787781,
+      "learning_rate": 3.2954391178860954e-05,
+      "loss": 0.7302,
+      "step": 725
+    },
+    {
+      "epoch": 1.2004110996916753,
+      "grad_norm": 1.44640052318573,
+      "learning_rate": 3.2749991717998007e-05,
+      "loss": 0.713,
+      "step": 730
+    },
+    {
+      "epoch": 1.20863309352518,
+      "grad_norm": 0.7730007171630859,
+      "learning_rate": 3.254501749435015e-05,
+      "loss": 0.7393,
+      "step": 735
+    },
+    {
+      "epoch": 1.2168550873586845,
+      "grad_norm": 0.7143975496292114,
+      "learning_rate": 3.233948370942467e-05,
+      "loss": 0.7619,
+      "step": 740
+    },
+    {
+      "epoch": 1.2250770811921892,
+      "grad_norm": 1.0002775192260742,
+      "learning_rate": 3.213340560622763e-05,
+      "loss": 0.7749,
+      "step": 745
+    },
+    {
+      "epoch": 1.2332990750256938,
+      "grad_norm": 0.9485899209976196,
+      "learning_rate": 3.192679846813335e-05,
+      "loss": 0.688,
+      "step": 750
+    },
+    {
+      "epoch": 1.2415210688591984,
+      "grad_norm": 1.6718777418136597,
+      "learning_rate": 3.1719677617751006e-05,
+      "loss": 0.8177,
+      "step": 755
+    },
+    {
+      "epoch": 1.249743062692703,
+      "grad_norm": 0.9025570750236511,
+      "learning_rate": 3.1512058415788183e-05,
+      "loss": 0.8364,
+      "step": 760
+    },
+    {
+      "epoch": 1.2579650565262077,
+      "grad_norm": 0.7739228010177612,
+      "learning_rate": 3.130395625991177e-05,
+      "loss": 0.8356,
+      "step": 765
+    },
+    {
+      "epoch": 1.2661870503597124,
+      "grad_norm": 0.8168063759803772,
+      "learning_rate": 3.1095386583605954e-05,
+      "loss": 0.7878,
+      "step": 770
+    },
+    {
+      "epoch": 1.274409044193217,
+      "grad_norm": 0.7470309138298035,
+      "learning_rate": 3.088636485502764e-05,
+      "loss": 0.8318,
+      "step": 775
+    },
+    {
+      "epoch": 1.2826310380267214,
+      "grad_norm": 0.7045716643333435,
+      "learning_rate": 3.0676906575859334e-05,
+      "loss": 0.7219,
+      "step": 780
+    },
+    {
+      "epoch": 1.290853031860226,
+      "grad_norm": 0.6814378499984741,
+      "learning_rate": 3.04670272801594e-05,
+      "loss": 0.8657,
+      "step": 785
+    },
+    {
+      "epoch": 1.2990750256937307,
+      "grad_norm": 1.2378205060958862,
+      "learning_rate": 3.0256742533210086e-05,
+      "loss": 0.7469,
+      "step": 790
+    },
+    {
+      "epoch": 1.3072970195272353,
+      "grad_norm": 0.9097736477851868,
+      "learning_rate": 3.0046067930363137e-05,
+      "loss": 0.9315,
+      "step": 795
+    },
+    {
+      "epoch": 1.31551901336074,
+      "grad_norm": 1.4382425546646118,
+      "learning_rate": 2.983501909588317e-05,
+      "loss": 0.8883,
+      "step": 800
+    },
+    {
+      "epoch": 1.3237410071942446,
+      "grad_norm": 1.036093831062317,
+      "learning_rate": 2.9623611681788965e-05,
+      "loss": 0.7888,
+      "step": 805
+    },
+    {
+      "epoch": 1.3319630010277492,
+      "grad_norm": 0.8393096327781677,
+      "learning_rate": 2.9411861366692627e-05,
+      "loss": 0.7262,
+      "step": 810
+    },
+    {
+      "epoch": 1.3401849948612539,
+      "grad_norm": 0.9713601469993591,
+      "learning_rate": 2.9199783854636865e-05,
+      "loss": 0.8034,
+      "step": 815
+    },
+    {
+      "epoch": 1.3484069886947585,
+      "grad_norm": 0.752566933631897,
+      "learning_rate": 2.8987394873930275e-05,
+      "loss": 0.6505,
+      "step": 820
+    },
+    {
+      "epoch": 1.3566289825282631,
+      "grad_norm": 1.0012316703796387,
+      "learning_rate": 2.8774710175980922e-05,
+      "loss": 0.799,
+      "step": 825
+    },
+    {
+      "epoch": 1.3648509763617678,
+      "grad_norm": 0.9846720695495605,
+      "learning_rate": 2.856174553412816e-05,
+      "loss": 0.8233,
+      "step": 830
+    },
+    {
+      "epoch": 1.3730729701952724,
+      "grad_norm": 0.6868287920951843,
+      "learning_rate": 2.834851674247282e-05,
+      "loss": 0.7477,
+      "step": 835
+    },
+    {
+      "epoch": 1.381294964028777,
+      "grad_norm": 0.701734721660614,
+      "learning_rate": 2.813503961470587e-05,
+      "loss": 0.7528,
+      "step": 840
+    },
+    {
+      "epoch": 1.3895169578622815,
+      "grad_norm": 0.6953380107879639,
+      "learning_rate": 2.7921329982935646e-05,
+      "loss": 0.8185,
+      "step": 845
+    },
+    {
+      "epoch": 1.397738951695786,
+      "grad_norm": 1.0073038339614868,
+      "learning_rate": 2.7707403696513688e-05,
+      "loss": 0.7114,
+      "step": 850
+    },
+    {
+      "epoch": 1.4059609455292907,
+      "grad_norm": 1.3499199151992798,
+      "learning_rate": 2.7493276620859298e-05,
+      "loss": 0.8409,
+      "step": 855
+    },
+    {
+      "epoch": 1.4141829393627954,
+      "grad_norm": 0.6113609671592712,
+      "learning_rate": 2.727896463628289e-05,
+      "loss": 0.7633,
+      "step": 860
+    },
+    {
+      "epoch": 1.4224049331963,
+      "grad_norm": 0.7573457360267639,
+      "learning_rate": 2.7064483636808313e-05,
+      "loss": 0.731,
+      "step": 865
+    },
+    {
+      "epoch": 1.4306269270298047,
+      "grad_norm": 0.7836306691169739,
+      "learning_rate": 2.6849849528994053e-05,
+      "loss": 0.8232,
+      "step": 870
+    },
+    {
+      "epoch": 1.4388489208633093,
+      "grad_norm": 0.7488899230957031,
+      "learning_rate": 2.663507823075358e-05,
+      "loss": 0.785,
+      "step": 875
+    },
+    {
+      "epoch": 1.447070914696814,
+      "grad_norm": 0.8522717952728271,
+      "learning_rate": 2.642018567017482e-05,
+      "loss": 0.6938,
+      "step": 880
+    },
+    {
+      "epoch": 1.4552929085303186,
+      "grad_norm": 1.3761483430862427,
+      "learning_rate": 2.6205187784338874e-05,
+      "loss": 0.7444,
+      "step": 885
+    },
+    {
+      "epoch": 1.4635149023638232,
+      "grad_norm": 0.669750988483429,
+      "learning_rate": 2.5990100518138088e-05,
+      "loss": 0.7938,
+      "step": 890
+    },
+    {
+      "epoch": 1.4717368961973278,
+      "grad_norm": 0.836729884147644,
+      "learning_rate": 2.577493982309352e-05,
+      "loss": 0.8329,
+      "step": 895
+    },
+    {
+      "epoch": 1.4799588900308325,
+      "grad_norm": 1.0972259044647217,
+      "learning_rate": 2.555972165617194e-05,
+      "loss": 0.8275,
+      "step": 900
+    },
+    {
+      "epoch": 1.4881808838643371,
+      "grad_norm": 1.3486735820770264,
+      "learning_rate": 2.5344461978602413e-05,
+      "loss": 0.8497,
+      "step": 905
+    },
+    {
+      "epoch": 1.4964028776978417,
+      "grad_norm": 0.8719611763954163,
+      "learning_rate": 2.512917675469253e-05,
+      "loss": 0.7744,
+      "step": 910
+    },
+    {
+      "epoch": 1.5046248715313464,
+      "grad_norm": 0.7670440077781677,
+      "learning_rate": 2.49138819506445e-05,
+      "loss": 0.8424,
+      "step": 915
+    },
+    {
+      "epoch": 1.512846865364851,
+      "grad_norm": 0.8988850116729736,
+      "learning_rate": 2.4698593533371038e-05,
+      "loss": 0.8447,
+      "step": 920
+    },
+    {
+      "epoch": 1.5210688591983557,
+      "grad_norm": 1.1595510244369507,
+      "learning_rate": 2.4483327469311148e-05,
+      "loss": 0.7433,
+      "step": 925
+    },
+    {
+      "epoch": 1.5292908530318603,
+      "grad_norm": 0.9172937870025635,
+      "learning_rate": 2.4268099723246088e-05,
+      "loss": 0.7145,
+      "step": 930
+    },
+    {
+      "epoch": 1.537512846865365,
+      "grad_norm": 0.6933180093765259,
+      "learning_rate": 2.405292625711535e-05,
+      "loss": 0.8367,
+      "step": 935
+    },
+    {
+      "epoch": 1.5457348406988696,
+      "grad_norm": 0.67847740650177,
+      "learning_rate": 2.3837823028832822e-05,
+      "loss": 0.7216,
+      "step": 940
+    },
+    {
+      "epoch": 1.5539568345323742,
+      "grad_norm": 1.0530544519424438,
+      "learning_rate": 2.3622805991103362e-05,
+      "loss": 0.8308,
+      "step": 945
+    },
+    {
+      "epoch": 1.5621788283658788,
+      "grad_norm": 1.2174192667007446,
+      "learning_rate": 2.340789109023969e-05,
+      "loss": 0.7712,
+      "step": 950
+    },
+    {
+      "epoch": 1.5704008221993835,
+      "grad_norm": 0.8486307859420776,
+      "learning_rate": 2.3193094264979736e-05,
+      "loss": 0.6857,
+      "step": 955
+    },
+    {
+      "epoch": 1.5786228160328881,
+      "grad_norm": 0.8623594045639038,
+      "learning_rate": 2.2978431445304575e-05,
+      "loss": 0.7837,
+      "step": 960
+    },
+    {
+      "epoch": 1.5868448098663928,
+      "grad_norm": 0.6950398683547974,
+      "learning_rate": 2.2763918551257018e-05,
+      "loss": 0.71,
+      "step": 965
+    },
+    {
+      "epoch": 1.5950668036998972,
+      "grad_norm": 1.0914013385772705,
+      "learning_rate": 2.2549571491760986e-05,
+      "loss": 0.7722,
+      "step": 970
+    },
+    {
+      "epoch": 1.6032887975334018,
+      "grad_norm": 0.9067034721374512,
+      "learning_rate": 2.2335406163441563e-05,
+      "loss": 0.8407,
+      "step": 975
+    },
+    {
+      "epoch": 1.6115107913669064,
+      "grad_norm": 0.6557819843292236,
+      "learning_rate": 2.21214384494461e-05,
+      "loss": 0.6819,
+      "step": 980
+    },
+    {
+      "epoch": 1.619732785200411,
+      "grad_norm": 1.041945457458496,
+      "learning_rate": 2.190768421826631e-05,
+      "loss": 0.7743,
+      "step": 985
+    },
+    {
+      "epoch": 1.6279547790339157,
+      "grad_norm": 1.0989412069320679,
+      "learning_rate": 2.169415932256135e-05,
+      "loss": 0.724,
+      "step": 990
+    },
+    {
+      "epoch": 1.6361767728674204,
+      "grad_norm": 1.0662113428115845,
+      "learning_rate": 2.1480879597982153e-05,
+      "loss": 0.9112,
+      "step": 995
+    },
+    {
+      "epoch": 1.644398766700925,
+      "grad_norm": 0.7899945974349976,
+      "learning_rate": 2.1267860861997035e-05,
+      "loss": 0.7436,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6526207605344296,
+      "grad_norm": 0.6741964221000671,
+      "learning_rate": 2.1055118912718635e-05,
+      "loss": 0.764,
+      "step": 1005
+    },
+    {
+      "epoch": 1.6608427543679343,
+      "grad_norm": 0.8556591868400574,
+      "learning_rate": 2.0842669527732224e-05,
+      "loss": 0.7574,
+      "step": 1010
+    },
+    {
+      "epoch": 1.6690647482014387,
+      "grad_norm": 0.7665844559669495,
+      "learning_rate": 2.0630528462925605e-05,
+      "loss": 0.8355,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6772867420349433,
+      "grad_norm": 5.5894317626953125,
+      "learning_rate": 2.0418711451320677e-05,
+      "loss": 0.7511,
+      "step": 1020
+    },
+    {
+      "epoch": 1.685508735868448,
+      "grad_norm": 1.258982539176941,
+      "learning_rate": 2.0207234201906547e-05,
+      "loss": 0.7888,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6937307297019526,
+      "grad_norm": 2.3158013820648193,
+      "learning_rate": 1.9996112398474506e-05,
+      "loss": 0.867,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7019527235354572,
+      "grad_norm": 1.3393203020095825,
+      "learning_rate": 1.978536169845495e-05,
+      "loss": 0.7291,
+      "step": 1035
+    },
+    {
+      "epoch": 1.7101747173689619,
+      "grad_norm": 1.3093374967575073,
+      "learning_rate": 1.9574997731756096e-05,
+      "loss": 0.8257,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7183967112024665,
+      "grad_norm": 0.8741866946220398,
+      "learning_rate": 1.936503609960485e-05,
+      "loss": 0.7578,
+      "step": 1045
+    },
+    {
+      "epoch": 1.7266187050359711,
+      "grad_norm": 0.9648747444152832,
+      "learning_rate": 1.9155492373389766e-05,
+      "loss": 0.713,
+      "step": 1050
+    },
+    {
+      "epoch": 1.7348406988694758,
+      "grad_norm": 1.377737045288086,
+      "learning_rate": 1.894638209350626e-05,
+      "loss": 0.7607,
+      "step": 1055
+    },
+    {
+      "epoch": 1.7430626927029804,
+      "grad_norm": 0.8467380404472351,
+      "learning_rate": 1.8737720768204046e-05,
+      "loss": 0.7561,
+      "step": 1060
+    },
+    {
+      "epoch": 1.751284686536485,
+      "grad_norm": 0.7661263346672058,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.7497,
+      "step": 1065
+    },
+    {
+      "epoch": 1.7595066803699897,
+      "grad_norm": 0.932976484298706,
+      "learning_rate": 1.8321806846715477e-05,
+      "loss": 0.7758,
+      "step": 1070
+    },
+    {
+      "epoch": 1.7677286742034943,
+      "grad_norm": 0.860954761505127,
+      "learning_rate": 1.8114585095961304e-05,
+      "loss": 0.79,
+      "step": 1075
+    },
+    {
+      "epoch": 1.775950668036999,
+      "grad_norm": 1.4737056493759155,
+      "learning_rate": 1.7907873988365146e-05,
+      "loss": 0.7781,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7841726618705036,
+      "grad_norm": 0.927992582321167,
+      "learning_rate": 1.7701688854246857e-05,
+      "loss": 0.8249,
+      "step": 1085
+    },
+    {
+      "epoch": 1.7923946557040082,
+      "grad_norm": 6.58436393737793,
+      "learning_rate": 1.7496044984918507e-05,
+      "loss": 0.7702,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8006166495375129,
+      "grad_norm": 0.8995419144630432,
+      "learning_rate": 1.7290957631550337e-05,
+      "loss": 1.0053,
+      "step": 1095
+    },
+    {
+      "epoch": 1.8088386433710175,
+      "grad_norm": 0.5598780512809753,
+      "learning_rate": 1.7086442004039654e-05,
+      "loss": 0.6576,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1824,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 5.18790731676844e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da40bedcaa97ca5797127d487348c4b521b16e2df25cfedbca83617e93b2e68
+size 5176

checkpoint-1200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.0

checkpoint-1200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060843d0b80459cd4aafc762f20fa8b6908f8371db951e0e6b582a51cf64e471
+size 13648432

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44efd134cb72472a287e1300f197bc3be76c4e0650d4b560a1180320b2b4349f
+size 27370618

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3cc4c6c870c355fc549426dd488da6cc246495b11fbc7511d13011908f26b28
+size 1064

checkpoint-1200/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-1200/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}