Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: train_2024-03-13-19-46-19
+  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_2024-03-13-19-46-19
+
+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 dockerNLCommands dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0162
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0372        | 2.78  | 100  | 0.0332          |
+| 0.0125        | 5.56  | 200  | 0.0162          |
+| 0.005         | 8.33  | 300  | 0.0203          |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "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 sha256:1d2f8effb443d5f2e2db3b2b0fad018fd5db2e68197201fa3e8b472ad8914910
+size 13648432

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.01622922532260418,
+    "eval_runtime": 2.41,
+    "eval_samples_per_second": 50.208,
+    "eval_steps_per_second": 3.32,
+    "train_loss": 0.0840026685127264,
+    "train_runtime": 1533.7769,
+    "train_samples_per_second": 14.957,
+    "train_steps_per_second": 0.235
+}

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 0.9.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "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:ddc6960040e357e61dc83465564a7be78b60e2f0e329227e967be2bf36142f1d
+size 13648432

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f9103a988014ced7b9ebe5df1852053c18f7cb2b5b2a9ff935fd63bc416fa6
+size 27370618

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142e1faa0c6800ef4a8a4424724c21c9614b94d1feed868058a6b29c7d4063d8
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a527d8eb69e7ca542e76d10e50395e7cdd0d2c2f68f372c0e6a6295e64d6b83
+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 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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 %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% 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 +1,169 @@
+{
+  "best_metric": 0.03319624438881874,
+  "best_model_checkpoint": "saves/Custom/lora/train_2024-03-13-19-46-19/checkpoint-100",
+  "epoch": 2.7777777777777777,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "grad_norm": 7.693007469177246,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 1.7543,
+      "step": 5
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.394199371337891,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 1.0206,
+      "step": 10
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.683964729309082,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.5826,
+      "step": 15
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8806061744689941,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.4099,
+      "step": 20
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.9219516515731812,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.3052,
+      "step": 25
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.6164277791976929,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.244,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.8378784656524658,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.1924,
+      "step": 35
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 2.151557445526123,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.1655,
+      "step": 40
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.2347593307495117,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.1203,
+      "step": 45
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.1008129119873047,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.1188,
+      "step": 50
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.351984977722168,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.0852,
+      "step": 55
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.8272274732589722,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.0854,
+      "step": 60
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.3354312181472778,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.0672,
+      "step": 65
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.7812442779541016,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.0455,
+      "step": 70
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.6480517387390137,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.0366,
+      "step": 75
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 1.5116844177246094,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.0503,
+      "step": 80
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.792582631111145,
+      "learning_rate": 4.34319334202531e-05,
+      "loss": 0.0429,
+      "step": 85
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.4267895221710205,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.0482,
+      "step": 90
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.7215550541877747,
+      "learning_rate": 4.188975519039151e-05,
+      "loss": 0.0317,
+      "step": 95
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.289726972579956,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.0372,
+      "step": 100
+    },
+    {
+      "epoch": 2.78,
+      "eval_loss": 0.03319624438881874,
+      "eval_runtime": 2.4078,
+      "eval_samples_per_second": 50.252,
+      "eval_steps_per_second": 3.322,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 2.0503540659388416e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d1ac05d9947a75b55a44ca930d0e3429fea1f6e34c0448f7ab0d37cfa5ca20
+size 5048

checkpoint-200/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 0.9.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "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-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d2f8effb443d5f2e2db3b2b0fad018fd5db2e68197201fa3e8b472ad8914910
+size 13648432

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7034fe8c5d32730822929b7288dd3213011a96b1ea1926dc6cd1ab0af0bf7e
+size 27370618

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fba168fae9a4d13accc62c0cd114757c083aee03a0e3059db9d2c046b93ba43
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d925e9d382deac6e8a269a123cdf85e167e1ed7f81e825d2010fd401cc48cfdf
+size 1064

checkpoint-200/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-200/tokenizer.model

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

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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 %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% 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-200/trainer_state.json

@@ -0,0 +1,317 @@
+{
+  "best_metric": 0.01622922532260418,
+  "best_model_checkpoint": "saves/Custom/lora/train_2024-03-13-19-46-19/checkpoint-200",
+  "epoch": 5.555555555555555,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "grad_norm": 7.693007469177246,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 1.7543,
+      "step": 5
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.394199371337891,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 1.0206,
+      "step": 10
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.683964729309082,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.5826,
+      "step": 15
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8806061744689941,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.4099,
+      "step": 20
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.9219516515731812,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.3052,
+      "step": 25
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.6164277791976929,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.244,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.8378784656524658,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.1924,
+      "step": 35
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 2.151557445526123,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.1655,
+      "step": 40
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.2347593307495117,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.1203,
+      "step": 45
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.1008129119873047,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.1188,
+      "step": 50
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.351984977722168,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.0852,
+      "step": 55
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.8272274732589722,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.0854,
+      "step": 60
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.3354312181472778,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.0672,
+      "step": 65
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.7812442779541016,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.0455,
+      "step": 70
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.6480517387390137,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.0366,
+      "step": 75
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 1.5116844177246094,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.0503,
+      "step": 80
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.792582631111145,
+      "learning_rate": 4.34319334202531e-05,
+      "loss": 0.0429,
+      "step": 85
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.4267895221710205,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.0482,
+      "step": 90
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.7215550541877747,
+      "learning_rate": 4.188975519039151e-05,
+      "loss": 0.0317,
+      "step": 95
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.289726972579956,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.0372,
+      "step": 100
+    },
+    {
+      "epoch": 2.78,
+      "eval_loss": 0.03319624438881874,
+      "eval_runtime": 2.4078,
+      "eval_samples_per_second": 50.252,
+      "eval_steps_per_second": 3.322,
+      "step": 100
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 1.3112704753875732,
+      "learning_rate": 4.021903572521802e-05,
+      "loss": 0.0245,
+      "step": 105
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 1.9846090078353882,
+      "learning_rate": 3.933941090877615e-05,
+      "loss": 0.0333,
+      "step": 110
+    },
+    {
+      "epoch": 3.19,
+      "grad_norm": 2.320976734161377,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.0351,
+      "step": 115
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 2.042772054672241,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0261,
+      "step": 120
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 2.495635747909546,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.0204,
+      "step": 125
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 0.8619056344032288,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.0122,
+      "step": 130
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 1.8066715002059937,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.0288,
+      "step": 135
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 3.5700998306274414,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.0222,
+      "step": 140
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 1.5312789678573608,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.0249,
+      "step": 145
+    },
+    {
+      "epoch": 4.17,
+      "grad_norm": 0.45907583832740784,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.0227,
+      "step": 150
+    },
+    {
+      "epoch": 4.31,
+      "grad_norm": 1.6312272548675537,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.0171,
+      "step": 155
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 2.005723476409912,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.0169,
+      "step": 160
+    },
+    {
+      "epoch": 4.58,
+      "grad_norm": 1.4385231733322144,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.0192,
+      "step": 165
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 1.0173711776733398,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.0136,
+      "step": 170
+    },
+    {
+      "epoch": 4.86,
+      "grad_norm": 1.2668229341506958,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.0122,
+      "step": 175
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.913548469543457,
+      "learning_rate": 2.5e-05,
+      "loss": 0.012,
+      "step": 180
+    },
+    {
+      "epoch": 5.14,
+      "grad_norm": 2.155971050262451,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.0128,
+      "step": 185
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 1.0692299604415894,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.0127,
+      "step": 190
+    },
+    {
+      "epoch": 5.42,
+      "grad_norm": 0.9680432081222534,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.0158,
+      "step": 195
+    },
+    {
+      "epoch": 5.56,
+      "grad_norm": 1.0661903619766235,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0125,
+      "step": 200
+    },
+    {
+      "epoch": 5.56,
+      "eval_loss": 0.01622922532260418,
+      "eval_runtime": 2.4123,
+      "eval_samples_per_second": 50.161,
+      "eval_steps_per_second": 3.316,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 4.092376135473562e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d1ac05d9947a75b55a44ca930d0e3429fea1f6e34c0448f7ab0d37cfa5ca20
+size 5048

checkpoint-300/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 0.9.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "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-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab419004c127afc61e072e8a50c987ebbe9f3b1c3437a6203d133fcb113783f0
+size 13648432

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be045f8c92b3439acbb016250a9a33b49058e269403ac6ea3ad1d5e1a34c75f7
+size 27370618

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec9ca6c7ff14571a14ffd162d7750a852b862fbf8b352cf45c88448b04fec46
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac32e2030af53c85f84a8f2e11abbf6b5ac30b14bae56931a5d1c3ca5022e51
+size 1064

checkpoint-300/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-300/tokenizer.model

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

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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 %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% 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-300/trainer_state.json

@@ -0,0 +1,465 @@
+{
+  "best_metric": 0.01622922532260418,
+  "best_model_checkpoint": "saves/Custom/lora/train_2024-03-13-19-46-19/checkpoint-200",
+  "epoch": 8.333333333333334,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "grad_norm": 7.693007469177246,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 1.7543,
+      "step": 5
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.394199371337891,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 1.0206,
+      "step": 10
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.683964729309082,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.5826,
+      "step": 15
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8806061744689941,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.4099,
+      "step": 20
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.9219516515731812,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.3052,
+      "step": 25
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.6164277791976929,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.244,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.8378784656524658,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.1924,
+      "step": 35
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 2.151557445526123,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.1655,
+      "step": 40
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.2347593307495117,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.1203,
+      "step": 45
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.1008129119873047,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.1188,
+      "step": 50
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.351984977722168,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.0852,
+      "step": 55
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.8272274732589722,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.0854,
+      "step": 60
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.3354312181472778,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.0672,
+      "step": 65
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.7812442779541016,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.0455,
+      "step": 70
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.6480517387390137,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.0366,
+      "step": 75
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 1.5116844177246094,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.0503,
+      "step": 80
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.792582631111145,
+      "learning_rate": 4.34319334202531e-05,
+      "loss": 0.0429,
+      "step": 85
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.4267895221710205,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.0482,
+      "step": 90
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.7215550541877747,
+      "learning_rate": 4.188975519039151e-05,
+      "loss": 0.0317,
+      "step": 95
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.289726972579956,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.0372,
+      "step": 100
+    },
+    {
+      "epoch": 2.78,
+      "eval_loss": 0.03319624438881874,
+      "eval_runtime": 2.4078,
+      "eval_samples_per_second": 50.252,
+      "eval_steps_per_second": 3.322,
+      "step": 100
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 1.3112704753875732,
+      "learning_rate": 4.021903572521802e-05,
+      "loss": 0.0245,
+      "step": 105
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 1.9846090078353882,
+      "learning_rate": 3.933941090877615e-05,
+      "loss": 0.0333,
+      "step": 110
+    },
+    {
+      "epoch": 3.19,
+      "grad_norm": 2.320976734161377,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.0351,
+      "step": 115
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 2.042772054672241,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0261,
+      "step": 120
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 2.495635747909546,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.0204,
+      "step": 125
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 0.8619056344032288,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.0122,
+      "step": 130
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 1.8066715002059937,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.0288,
+      "step": 135
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 3.5700998306274414,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.0222,
+      "step": 140
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 1.5312789678573608,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.0249,
+      "step": 145
+    },
+    {
+      "epoch": 4.17,
+      "grad_norm": 0.45907583832740784,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.0227,
+      "step": 150
+    },
+    {
+      "epoch": 4.31,
+      "grad_norm": 1.6312272548675537,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.0171,
+      "step": 155
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 2.005723476409912,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.0169,
+      "step": 160
+    },
+    {
+      "epoch": 4.58,
+      "grad_norm": 1.4385231733322144,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.0192,
+      "step": 165
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 1.0173711776733398,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.0136,
+      "step": 170
+    },
+    {
+      "epoch": 4.86,
+      "grad_norm": 1.2668229341506958,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.0122,
+      "step": 175
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.913548469543457,
+      "learning_rate": 2.5e-05,
+      "loss": 0.012,
+      "step": 180
+    },
+    {
+      "epoch": 5.14,
+      "grad_norm": 2.155971050262451,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.0128,
+      "step": 185
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 1.0692299604415894,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.0127,
+      "step": 190
+    },
+    {
+      "epoch": 5.42,
+      "grad_norm": 0.9680432081222534,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.0158,
+      "step": 195
+    },
+    {
+      "epoch": 5.56,
+      "grad_norm": 1.0661903619766235,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0125,
+      "step": 200
+    },
+    {
+      "epoch": 5.56,
+      "eval_loss": 0.01622922532260418,
+      "eval_runtime": 2.4123,
+      "eval_samples_per_second": 50.161,
+      "eval_steps_per_second": 3.316,
+      "step": 200
+    },
+    {
+      "epoch": 5.69,
+      "grad_norm": 0.8271896243095398,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 0.0081,
+      "step": 205
+    },
+    {
+      "epoch": 5.83,
+      "grad_norm": 1.7405743598937988,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.0125,
+      "step": 210
+    },
+    {
+      "epoch": 5.97,
+      "grad_norm": 1.2488248348236084,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 0.0104,
+      "step": 215
+    },
+    {
+      "epoch": 6.11,
+      "grad_norm": 0.5560044050216675,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.007,
+      "step": 220
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 1.4551178216934204,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.012,
+      "step": 225
+    },
+    {
+      "epoch": 6.39,
+      "grad_norm": 1.6263498067855835,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 0.0132,
+      "step": 230
+    },
+    {
+      "epoch": 6.53,
+      "grad_norm": 0.22708508372306824,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 0.0042,
+      "step": 235
+    },
+    {
+      "epoch": 6.67,
+      "grad_norm": 0.6515786051750183,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0088,
+      "step": 240
+    },
+    {
+      "epoch": 6.81,
+      "grad_norm": 0.4397377669811249,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 0.0041,
+      "step": 245
+    },
+    {
+      "epoch": 6.94,
+      "grad_norm": 1.5320991277694702,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.0102,
+      "step": 250
+    },
+    {
+      "epoch": 7.08,
+      "grad_norm": 1.1604887247085571,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.0067,
+      "step": 255
+    },
+    {
+      "epoch": 7.22,
+      "grad_norm": 1.5971548557281494,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.0037,
+      "step": 260
+    },
+    {
+      "epoch": 7.36,
+      "grad_norm": 0.9654971361160278,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.0067,
+      "step": 265
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 2.1204416751861572,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0058,
+      "step": 270
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.866258442401886,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.0059,
+      "step": 275
+    },
+    {
+      "epoch": 7.78,
+      "grad_norm": 0.6335222125053406,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.0094,
+      "step": 280
+    },
+    {
+      "epoch": 7.92,
+      "grad_norm": 0.981534481048584,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.009,
+      "step": 285
+    },
+    {
+      "epoch": 8.06,
+      "grad_norm": 0.859342098236084,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.0063,
+      "step": 290
+    },
+    {
+      "epoch": 8.19,
+      "grad_norm": 0.47514280676841736,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.0034,
+      "step": 295
+    },
+    {
+      "epoch": 8.33,
+      "grad_norm": 1.3065800666809082,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.005,
+      "step": 300
+    },
+    {
+      "epoch": 8.33,
+      "eval_loss": 0.02027682214975357,
+      "eval_runtime": 2.411,
+      "eval_samples_per_second": 50.188,
+      "eval_steps_per_second": 3.318,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 6.13289571385344e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d1ac05d9947a75b55a44ca930d0e3429fea1f6e34c0448f7ab0d37cfa5ca20
+size 5048

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.01622922532260418,
+    "eval_runtime": 2.41,
+    "eval_samples_per_second": 50.208,
+    "eval_steps_per_second": 3.32
+}

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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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 %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% 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
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.0840026685127264,
+    "train_runtime": 1533.7769,
+    "train_samples_per_second": 14.957,
+    "train_steps_per_second": 0.235
+}

trainer_log.jsonl

@@ -0,0 +1,77 @@
+{"current_steps": 5, "total_steps": 360, "loss": 1.7543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.997620553954645e-05, "epoch": 0.14, "percentage": 1.39, "elapsed_time": "0:00:22", "remaining_time": "0:26:31"}
+{"current_steps": 10, "total_steps": 360, "loss": 1.0206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.990486745229364e-05, "epoch": 0.28, "percentage": 2.78, "elapsed_time": "0:00:42", "remaining_time": "0:24:57"}
+{"current_steps": 15, "total_steps": 360, "loss": 0.5826, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9786121534345265e-05, "epoch": 0.42, "percentage": 4.17, "elapsed_time": "0:01:03", "remaining_time": "0:24:20"}
+{"current_steps": 20, "total_steps": 360, "loss": 0.4099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.962019382530521e-05, "epoch": 0.56, "percentage": 5.56, "elapsed_time": "0:01:23", "remaining_time": "0:23:36"}
+{"current_steps": 25, "total_steps": 360, "loss": 0.3052, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.940740017799833e-05, "epoch": 0.69, "percentage": 6.94, "elapsed_time": "0:01:43", "remaining_time": "0:23:09"}
+{"current_steps": 30, "total_steps": 360, "loss": 0.244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.914814565722671e-05, "epoch": 0.83, "percentage": 8.33, "elapsed_time": "0:02:05", "remaining_time": "0:22:58"}
+{"current_steps": 35, "total_steps": 360, "loss": 0.1924, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.884292376870567e-05, "epoch": 0.97, "percentage": 9.72, "elapsed_time": "0:02:26", "remaining_time": "0:22:39"}
+{"current_steps": 40, "total_steps": 360, "loss": 0.1655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.849231551964771e-05, "epoch": 1.11, "percentage": 11.11, "elapsed_time": "0:02:47", "remaining_time": "0:22:20"}
+{"current_steps": 45, "total_steps": 360, "loss": 0.1203, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8096988312782174e-05, "epoch": 1.25, "percentage": 12.5, "elapsed_time": "0:03:08", "remaining_time": "0:21:59"}
+{"current_steps": 50, "total_steps": 360, "loss": 0.1188, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.765769467591625e-05, "epoch": 1.39, "percentage": 13.89, "elapsed_time": "0:03:28", "remaining_time": "0:21:33"}
+{"current_steps": 55, "total_steps": 360, "loss": 0.0852, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.717527082945554e-05, "epoch": 1.53, "percentage": 15.28, "elapsed_time": "0:03:50", "remaining_time": "0:21:16"}
+{"current_steps": 60, "total_steps": 360, "loss": 0.0854, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.665063509461097e-05, "epoch": 1.67, "percentage": 16.67, "elapsed_time": "0:04:11", "remaining_time": "0:20:57"}
+{"current_steps": 65, "total_steps": 360, "loss": 0.0672, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.608478614532215e-05, "epoch": 1.81, "percentage": 18.06, "elapsed_time": "0:04:33", "remaining_time": "0:20:40"}
+{"current_steps": 70, "total_steps": 360, "loss": 0.0455, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.54788011072248e-05, "epoch": 1.94, "percentage": 19.44, "elapsed_time": "0:04:55", "remaining_time": "0:20:22"}
+{"current_steps": 75, "total_steps": 360, "loss": 0.0366, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4833833507280884e-05, "epoch": 2.08, "percentage": 20.83, "elapsed_time": "0:05:14", "remaining_time": "0:19:56"}
+{"current_steps": 80, "total_steps": 360, "loss": 0.0503, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.415111107797445e-05, "epoch": 2.22, "percentage": 22.22, "elapsed_time": "0:05:36", "remaining_time": "0:19:38"}
+{"current_steps": 85, "total_steps": 360, "loss": 0.0429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.34319334202531e-05, "epoch": 2.36, "percentage": 23.61, "elapsed_time": "0:05:57", "remaining_time": "0:19:17"}
+{"current_steps": 90, "total_steps": 360, "loss": 0.0482, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.267766952966369e-05, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:06:19", "remaining_time": "0:18:58"}
+{"current_steps": 95, "total_steps": 360, "loss": 0.0317, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.188975519039151e-05, "epoch": 2.64, "percentage": 26.39, "elapsed_time": "0:06:41", "remaining_time": "0:18:39"}
+{"current_steps": 100, "total_steps": 360, "loss": 0.0372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1069690242163484e-05, "epoch": 2.78, "percentage": 27.78, "elapsed_time": "0:07:02", "remaining_time": "0:18:19"}
+{"current_steps": 100, "total_steps": 360, "loss": null, "eval_loss": 0.03319624438881874, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.78, "percentage": 27.78, "elapsed_time": "0:07:02", "remaining_time": "0:18:19"}
+{"current_steps": 105, "total_steps": 360, "loss": 0.0245, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.021903572521802e-05, "epoch": 2.92, "percentage": 29.17, "elapsed_time": "0:07:26", "remaining_time": "0:18:04"}
+{"current_steps": 110, "total_steps": 360, "loss": 0.0333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.933941090877615e-05, "epoch": 3.06, "percentage": 30.56, "elapsed_time": "0:07:47", "remaining_time": "0:17:42"}
+{"current_steps": 115, "total_steps": 360, "loss": 0.0351, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.84324902086706e-05, "epoch": 3.19, "percentage": 31.94, "elapsed_time": "0:08:07", "remaining_time": "0:17:19"}
+{"current_steps": 120, "total_steps": 360, "loss": 0.0261, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7500000000000003e-05, "epoch": 3.33, "percentage": 33.33, "elapsed_time": "0:08:28", "remaining_time": "0:16:57"}
+{"current_steps": 125, "total_steps": 360, "loss": 0.0204, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.654371533087586e-05, "epoch": 3.47, "percentage": 34.72, "elapsed_time": "0:08:49", "remaining_time": "0:16:35"}
+{"current_steps": 130, "total_steps": 360, "loss": 0.0122, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.556545654351749e-05, "epoch": 3.61, "percentage": 36.11, "elapsed_time": "0:09:11", "remaining_time": "0:16:15"}
+{"current_steps": 135, "total_steps": 360, "loss": 0.0288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.456708580912725e-05, "epoch": 3.75, "percentage": 37.5, "elapsed_time": "0:09:32", "remaining_time": "0:15:53"}
+{"current_steps": 140, "total_steps": 360, "loss": 0.0222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.355050358314172e-05, "epoch": 3.89, "percentage": 38.89, "elapsed_time": "0:09:53", "remaining_time": "0:15:33"}
+{"current_steps": 145, "total_steps": 360, "loss": 0.0249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.251764498760683e-05, "epoch": 4.03, "percentage": 40.28, "elapsed_time": "0:10:14", "remaining_time": "0:15:11"}
+{"current_steps": 150, "total_steps": 360, "loss": 0.0227, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.147047612756302e-05, "epoch": 4.17, "percentage": 41.67, "elapsed_time": "0:10:35", "remaining_time": "0:14:50"}
+{"current_steps": 155, "total_steps": 360, "loss": 0.0171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0410990348452573e-05, "epoch": 4.31, "percentage": 43.06, "elapsed_time": "0:10:57", "remaining_time": "0:14:29"}
+{"current_steps": 160, "total_steps": 360, "loss": 0.0169, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9341204441673266e-05, "epoch": 4.44, "percentage": 44.44, "elapsed_time": "0:11:18", "remaining_time": "0:14:08"}
+{"current_steps": 165, "total_steps": 360, "loss": 0.0192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8263154805501297e-05, "epoch": 4.58, "percentage": 45.83, "elapsed_time": "0:11:39", "remaining_time": "0:13:46"}
+{"current_steps": 170, "total_steps": 360, "loss": 0.0136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.717889356869146e-05, "epoch": 4.72, "percentage": 47.22, "elapsed_time": "0:12:01", "remaining_time": "0:13:25"}
+{"current_steps": 175, "total_steps": 360, "loss": 0.0122, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6090484684133404e-05, "epoch": 4.86, "percentage": 48.61, "elapsed_time": "0:12:23", "remaining_time": "0:13:05"}
+{"current_steps": 180, "total_steps": 360, "loss": 0.012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:12:43", "remaining_time": "0:12:43"}
+{"current_steps": 185, "total_steps": 360, "loss": 0.0128, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3909515315866605e-05, "epoch": 5.14, "percentage": 51.39, "elapsed_time": "0:13:05", "remaining_time": "0:12:23"}
+{"current_steps": 190, "total_steps": 360, "loss": 0.0127, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2821106431308544e-05, "epoch": 5.28, "percentage": 52.78, "elapsed_time": "0:13:27", "remaining_time": "0:12:02"}
+{"current_steps": 195, "total_steps": 360, "loss": 0.0158, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.173684519449872e-05, "epoch": 5.42, "percentage": 54.17, "elapsed_time": "0:13:48", "remaining_time": "0:11:41"}
+{"current_steps": 200, "total_steps": 360, "loss": 0.0125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0658795558326743e-05, "epoch": 5.56, "percentage": 55.56, "elapsed_time": "0:14:10", "remaining_time": "0:11:20"}
+{"current_steps": 200, "total_steps": 360, "loss": null, "eval_loss": 0.01622922532260418, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.56, "percentage": 55.56, "elapsed_time": "0:14:10", "remaining_time": "0:11:20"}
+{"current_steps": 205, "total_steps": 360, "loss": 0.0081, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.958900965154743e-05, "epoch": 5.69, "percentage": 56.94, "elapsed_time": "0:14:34", "remaining_time": "0:11:01"}
+{"current_steps": 210, "total_steps": 360, "loss": 0.0125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.852952387243698e-05, "epoch": 5.83, "percentage": 58.33, "elapsed_time": "0:14:55", "remaining_time": "0:10:39"}
+{"current_steps": 215, "total_steps": 360, "loss": 0.0104, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7482355012393177e-05, "epoch": 5.97, "percentage": 59.72, "elapsed_time": "0:15:16", "remaining_time": "0:10:18"}
+{"current_steps": 220, "total_steps": 360, "loss": 0.007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6449496416858284e-05, "epoch": 6.11, "percentage": 61.11, "elapsed_time": "0:15:37", "remaining_time": "0:09:56"}
+{"current_steps": 225, "total_steps": 360, "loss": 0.012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5432914190872757e-05, "epoch": 6.25, "percentage": 62.5, "elapsed_time": "0:15:58", "remaining_time": "0:09:35"}
+{"current_steps": 230, "total_steps": 360, "loss": 0.0132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.443454345648252e-05, "epoch": 6.39, "percentage": 63.89, "elapsed_time": "0:16:19", "remaining_time": "0:09:13"}
+{"current_steps": 235, "total_steps": 360, "loss": 0.0042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3456284669124158e-05, "epoch": 6.53, "percentage": 65.28, "elapsed_time": "0:16:40", "remaining_time": "0:08:52"}
+{"current_steps": 240, "total_steps": 360, "loss": 0.0088, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2500000000000006e-05, "epoch": 6.67, "percentage": 66.67, "elapsed_time": "0:17:01", "remaining_time": "0:08:30"}
+{"current_steps": 245, "total_steps": 360, "loss": 0.0041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1567509791329401e-05, "epoch": 6.81, "percentage": 68.06, "elapsed_time": "0:17:23", "remaining_time": "0:08:09"}
+{"current_steps": 250, "total_steps": 360, "loss": 0.0102, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0660589091223855e-05, "epoch": 6.94, "percentage": 69.44, "elapsed_time": "0:17:45", "remaining_time": "0:07:48"}
+{"current_steps": 255, "total_steps": 360, "loss": 0.0067, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.780964274781984e-06, "epoch": 7.08, "percentage": 70.83, "elapsed_time": "0:18:05", "remaining_time": "0:07:27"}
+{"current_steps": 260, "total_steps": 360, "loss": 0.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.930309757836517e-06, "epoch": 7.22, "percentage": 72.22, "elapsed_time": "0:18:26", "remaining_time": "0:07:05"}
+{"current_steps": 265, "total_steps": 360, "loss": 0.0067, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.110244809608495e-06, "epoch": 7.36, "percentage": 73.61, "elapsed_time": "0:18:48", "remaining_time": "0:06:44"}
+{"current_steps": 270, "total_steps": 360, "loss": 0.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.3223304703363135e-06, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:19:10", "remaining_time": "0:06:23"}
+{"current_steps": 275, "total_steps": 360, "loss": 0.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.568066579746901e-06, "epoch": 7.64, "percentage": 76.39, "elapsed_time": "0:19:31", "remaining_time": "0:06:02"}
+{"current_steps": 280, "total_steps": 360, "loss": 0.0094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.848888922025553e-06, "epoch": 7.78, "percentage": 77.78, "elapsed_time": "0:19:52", "remaining_time": "0:05:40"}
+{"current_steps": 285, "total_steps": 360, "loss": 0.009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.166166492719124e-06, "epoch": 7.92, "percentage": 79.17, "elapsed_time": "0:20:13", "remaining_time": "0:05:19"}
+{"current_steps": 290, "total_steps": 360, "loss": 0.0063, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.521198892775203e-06, "epoch": 8.06, "percentage": 80.56, "elapsed_time": "0:20:34", "remaining_time": "0:04:57"}
+{"current_steps": 295, "total_steps": 360, "loss": 0.0034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9152138546778625e-06, "epoch": 8.19, "percentage": 81.94, "elapsed_time": "0:20:56", "remaining_time": "0:04:36"}
+{"current_steps": 300, "total_steps": 360, "loss": 0.005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3493649053890326e-06, "epoch": 8.33, "percentage": 83.33, "elapsed_time": "0:21:17", "remaining_time": "0:04:15"}
+{"current_steps": 300, "total_steps": 360, "loss": null, "eval_loss": 0.02027682214975357, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 8.33, "percentage": 83.33, "elapsed_time": "0:21:17", "remaining_time": "0:04:15"}
+{"current_steps": 305, "total_steps": 360, "loss": 0.0031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8247291705444575e-06, "epoch": 8.47, "percentage": 84.72, "elapsed_time": "0:21:42", "remaining_time": "0:03:54"}
+{"current_steps": 310, "total_steps": 360, "loss": 0.0042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3423053240837515e-06, "epoch": 8.61, "percentage": 86.11, "elapsed_time": "0:22:03", "remaining_time": "0:03:33"}
+{"current_steps": 315, "total_steps": 360, "loss": 0.0031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9030116872178316e-06, "epoch": 8.75, "percentage": 87.5, "elapsed_time": "0:22:24", "remaining_time": "0:03:12"}
+{"current_steps": 320, "total_steps": 360, "loss": 0.0071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5076844803522922e-06, "epoch": 8.89, "percentage": 88.89, "elapsed_time": "0:22:44", "remaining_time": "0:02:50"}
+{"current_steps": 325, "total_steps": 360, "loss": 0.0078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1570762312943295e-06, "epoch": 9.03, "percentage": 90.28, "elapsed_time": "0:23:05", "remaining_time": "0:02:29"}
+{"current_steps": 330, "total_steps": 360, "loss": 0.0014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.51854342773295e-07, "epoch": 9.17, "percentage": 91.67, "elapsed_time": "0:23:26", "remaining_time": "0:02:07"}
+{"current_steps": 335, "total_steps": 360, "loss": 0.0025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.925998220016659e-07, "epoch": 9.31, "percentage": 93.06, "elapsed_time": "0:23:49", "remaining_time": "0:01:46"}
+{"current_steps": 340, "total_steps": 360, "loss": 0.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7980617469479953e-07, "epoch": 9.44, "percentage": 94.44, "elapsed_time": "0:24:10", "remaining_time": "0:01:25"}
+{"current_steps": 345, "total_steps": 360, "loss": 0.0063, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1387846565474045e-07, "epoch": 9.58, "percentage": 95.83, "elapsed_time": "0:24:31", "remaining_time": "0:01:03"}
+{"current_steps": 350, "total_steps": 360, "loss": 0.0036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.513254770636137e-08, "epoch": 9.72, "percentage": 97.22, "elapsed_time": "0:24:52", "remaining_time": "0:00:42"}
+{"current_steps": 355, "total_steps": 360, "loss": 0.0038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3794460453555047e-08, "epoch": 9.86, "percentage": 98.61, "elapsed_time": "0:25:13", "remaining_time": "0:00:21"}
+{"current_steps": 360, "total_steps": 360, "loss": 0.0084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:25:33", "remaining_time": "0:00:00"}
+{"current_steps": 360, "total_steps": 360, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:25:33", "remaining_time": "0:00:00"}
+{"current_steps": 8, "total_steps": 8, "loss": null, "eval_loss": 0.01622922532260418, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:25:36", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,558 @@
+{
+  "best_metric": 0.01622922532260418,
+  "best_model_checkpoint": "saves/Custom/lora/train_2024-03-13-19-46-19/checkpoint-200",
+  "epoch": 10.0,
+  "eval_steps": 100,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "grad_norm": 7.693007469177246,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 1.7543,
+      "step": 5
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.394199371337891,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 1.0206,
+      "step": 10
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.683964729309082,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.5826,
+      "step": 15
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8806061744689941,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.4099,
+      "step": 20
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.9219516515731812,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.3052,
+      "step": 25
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.6164277791976929,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.244,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.8378784656524658,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.1924,
+      "step": 35
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 2.151557445526123,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.1655,
+      "step": 40
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.2347593307495117,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.1203,
+      "step": 45
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.1008129119873047,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.1188,
+      "step": 50
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.351984977722168,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.0852,
+      "step": 55
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.8272274732589722,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.0854,
+      "step": 60
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.3354312181472778,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.0672,
+      "step": 65
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.7812442779541016,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.0455,
+      "step": 70
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.6480517387390137,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.0366,
+      "step": 75
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 1.5116844177246094,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.0503,
+      "step": 80
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.792582631111145,
+      "learning_rate": 4.34319334202531e-05,
+      "loss": 0.0429,
+      "step": 85
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.4267895221710205,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.0482,
+      "step": 90
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.7215550541877747,
+      "learning_rate": 4.188975519039151e-05,
+      "loss": 0.0317,
+      "step": 95
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.289726972579956,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.0372,
+      "step": 100
+    },
+    {
+      "epoch": 2.78,
+      "eval_loss": 0.03319624438881874,
+      "eval_runtime": 2.4078,
+      "eval_samples_per_second": 50.252,
+      "eval_steps_per_second": 3.322,
+      "step": 100
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 1.3112704753875732,
+      "learning_rate": 4.021903572521802e-05,
+      "loss": 0.0245,
+      "step": 105
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 1.9846090078353882,
+      "learning_rate": 3.933941090877615e-05,
+      "loss": 0.0333,
+      "step": 110
+    },
+    {
+      "epoch": 3.19,
+      "grad_norm": 2.320976734161377,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.0351,
+      "step": 115
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 2.042772054672241,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0261,
+      "step": 120
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 2.495635747909546,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.0204,
+      "step": 125
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 0.8619056344032288,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.0122,
+      "step": 130
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 1.8066715002059937,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.0288,
+      "step": 135
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 3.5700998306274414,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.0222,
+      "step": 140
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 1.5312789678573608,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.0249,
+      "step": 145
+    },
+    {
+      "epoch": 4.17,
+      "grad_norm": 0.45907583832740784,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.0227,
+      "step": 150
+    },
+    {
+      "epoch": 4.31,
+      "grad_norm": 1.6312272548675537,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.0171,
+      "step": 155
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 2.005723476409912,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.0169,
+      "step": 160
+    },
+    {
+      "epoch": 4.58,
+      "grad_norm": 1.4385231733322144,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.0192,
+      "step": 165
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 1.0173711776733398,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.0136,
+      "step": 170
+    },
+    {
+      "epoch": 4.86,
+      "grad_norm": 1.2668229341506958,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.0122,
+      "step": 175
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.913548469543457,
+      "learning_rate": 2.5e-05,
+      "loss": 0.012,
+      "step": 180
+    },
+    {
+      "epoch": 5.14,
+      "grad_norm": 2.155971050262451,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.0128,
+      "step": 185
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 1.0692299604415894,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.0127,
+      "step": 190
+    },
+    {
+      "epoch": 5.42,
+      "grad_norm": 0.9680432081222534,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.0158,
+      "step": 195
+    },
+    {
+      "epoch": 5.56,
+      "grad_norm": 1.0661903619766235,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0125,
+      "step": 200
+    },
+    {
+      "epoch": 5.56,
+      "eval_loss": 0.01622922532260418,
+      "eval_runtime": 2.4123,
+      "eval_samples_per_second": 50.161,
+      "eval_steps_per_second": 3.316,
+      "step": 200
+    },
+    {
+      "epoch": 5.69,
+      "grad_norm": 0.8271896243095398,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 0.0081,
+      "step": 205
+    },
+    {
+      "epoch": 5.83,
+      "grad_norm": 1.7405743598937988,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.0125,
+      "step": 210
+    },
+    {
+      "epoch": 5.97,
+      "grad_norm": 1.2488248348236084,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 0.0104,
+      "step": 215
+    },
+    {
+      "epoch": 6.11,
+      "grad_norm": 0.5560044050216675,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.007,
+      "step": 220
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 1.4551178216934204,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.012,
+      "step": 225
+    },
+    {
+      "epoch": 6.39,
+      "grad_norm": 1.6263498067855835,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 0.0132,
+      "step": 230
+    },
+    {
+      "epoch": 6.53,
+      "grad_norm": 0.22708508372306824,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 0.0042,
+      "step": 235
+    },
+    {
+      "epoch": 6.67,
+      "grad_norm": 0.6515786051750183,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0088,
+      "step": 240
+    },
+    {
+      "epoch": 6.81,
+      "grad_norm": 0.4397377669811249,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 0.0041,
+      "step": 245
+    },
+    {
+      "epoch": 6.94,
+      "grad_norm": 1.5320991277694702,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.0102,
+      "step": 250
+    },
+    {
+      "epoch": 7.08,
+      "grad_norm": 1.1604887247085571,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.0067,
+      "step": 255
+    },
+    {
+      "epoch": 7.22,
+      "grad_norm": 1.5971548557281494,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.0037,
+      "step": 260
+    },
+    {
+      "epoch": 7.36,
+      "grad_norm": 0.9654971361160278,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.0067,
+      "step": 265
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 2.1204416751861572,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0058,
+      "step": 270
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.866258442401886,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.0059,
+      "step": 275
+    },
+    {
+      "epoch": 7.78,
+      "grad_norm": 0.6335222125053406,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.0094,
+      "step": 280
+    },
+    {
+      "epoch": 7.92,
+      "grad_norm": 0.981534481048584,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.009,
+      "step": 285
+    },
+    {
+      "epoch": 8.06,
+      "grad_norm": 0.859342098236084,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.0063,
+      "step": 290
+    },
+    {
+      "epoch": 8.19,
+      "grad_norm": 0.47514280676841736,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.0034,
+      "step": 295
+    },
+    {
+      "epoch": 8.33,
+      "grad_norm": 1.3065800666809082,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.005,
+      "step": 300
+    },
+    {
+      "epoch": 8.33,
+      "eval_loss": 0.02027682214975357,
+      "eval_runtime": 2.411,
+      "eval_samples_per_second": 50.188,
+      "eval_steps_per_second": 3.318,
+      "step": 300
+    },
+    {
+      "epoch": 8.47,
+      "grad_norm": 0.5928324460983276,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 0.0031,
+      "step": 305
+    },
+    {
+      "epoch": 8.61,
+      "grad_norm": 0.5617555975914001,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 0.0042,
+      "step": 310
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 0.668617844581604,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0031,
+      "step": 315
+    },
+    {
+      "epoch": 8.89,
+      "grad_norm": 0.8139355182647705,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.0071,
+      "step": 320
+    },
+    {
+      "epoch": 9.03,
+      "grad_norm": 1.4223390817642212,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 0.0078,
+      "step": 325
+    },
+    {
+      "epoch": 9.17,
+      "grad_norm": 0.5418530702590942,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.0014,
+      "step": 330
+    },
+    {
+      "epoch": 9.31,
+      "grad_norm": 0.22671547532081604,
+      "learning_rate": 5.925998220016659e-07,
+      "loss": 0.0025,
+      "step": 335
+    },
+    {
+      "epoch": 9.44,
+      "grad_norm": 0.6007376909255981,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.0058,
+      "step": 340
+    },
+    {
+      "epoch": 9.58,
+      "grad_norm": 0.395778089761734,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.0063,
+      "step": 345
+    },
+    {
+      "epoch": 9.72,
+      "grad_norm": 0.9250916242599487,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 0.0036,
+      "step": 350
+    },
+    {
+      "epoch": 9.86,
+      "grad_norm": 0.47003576159477234,
+      "learning_rate": 2.3794460453555047e-08,
+      "loss": 0.0038,
+      "step": 355
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.8105049133300781,
+      "learning_rate": 0.0,
+      "loss": 0.0084,
+      "step": 360
+    },
+    {
+      "epoch": 10.0,
+      "step": 360,
+      "total_flos": 7.351825810744934e+16,
+      "train_loss": 0.0840026685127264,
+      "train_runtime": 1533.7769,
+      "train_samples_per_second": 14.957,
+      "train_steps_per_second": 0.235
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 7.351825810744934e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d1ac05d9947a75b55a44ca930d0e3429fea1f6e34c0448f7ab0d37cfa5ca20
+size 5048