Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a000370c68d9ed823135f7ead0ef718d8a19f1afffb9bde44f66e716f053e7de
+size 27280152

checkpoint-800/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-800/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b3b2a9fe97efc66afb054c1eea1715d0f3ee1bee9c40ecd253912387e08b08
+size 27280152

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cdd03ef4c22d2dac545e441023b0b007961fd6f8d681d17370f0b51b291179
+size 54634443

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2dc32b683c347cd54056a94739cfae2012f35d2638126668e73790fd9d69bd6
+size 14645

checkpoint-800/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14aed6cb9282a2b5680ad3b7f930cd55191999273ddde46a4b600bbcaa09ce1f
+size 1383

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010189a72a78f78f9df4bc7b649ca8fca3ca6cb627aad09d04428ae5c9b224b7
+size 1465

checkpoint-800/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-800/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-800/trainer_state.json

@@ -0,0 +1,859 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.8123075366020203,
+  "best_model_checkpoint": "/workspace/outputs/mistral-chatpro-finetuned/checkpoint-800",
+  "epoch": 4.848484848484849,
+  "eval_steps": 25,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 149.54275512695312,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 29.7475,
+      "step": 10
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 269.5798034667969,
+      "learning_rate": 1.95e-06,
+      "loss": 31.5785,
+      "step": 20
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "eval_loss": 1.9893885850906372,
+      "eval_runtime": 27.1115,
+      "eval_samples_per_second": 21.651,
+      "eval_steps_per_second": 2.729,
+      "step": 25
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 121.41719818115234,
+      "learning_rate": 3.4500000000000004e-06,
+      "loss": 28.2201,
+      "step": 30
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 101.0121078491211,
+      "learning_rate": 4.95e-06,
+      "loss": 28.6571,
+      "step": 40
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 283.864501953125,
+      "learning_rate": 6.45e-06,
+      "loss": 26.6667,
+      "step": 50
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "eval_loss": 1.5634442567825317,
+      "eval_runtime": 26.9981,
+      "eval_samples_per_second": 21.742,
+      "eval_steps_per_second": 2.741,
+      "step": 50
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 55.40841293334961,
+      "learning_rate": 7.95e-06,
+      "loss": 22.7511,
+      "step": 60
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 27.064821243286133,
+      "learning_rate": 9.450000000000001e-06,
+      "loss": 20.1933,
+      "step": 70
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "eval_loss": 1.1919723749160767,
+      "eval_runtime": 26.8965,
+      "eval_samples_per_second": 21.824,
+      "eval_steps_per_second": 2.751,
+      "step": 75
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 16.979394912719727,
+      "learning_rate": 1.095e-05,
+      "loss": 18.0581,
+      "step": 80
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 8.984743118286133,
+      "learning_rate": 1.245e-05,
+      "loss": 19.0451,
+      "step": 90
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 8.195664405822754,
+      "learning_rate": 1.395e-05,
+      "loss": 17.7881,
+      "step": 100
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "eval_loss": 1.1023012399673462,
+      "eval_runtime": 26.7164,
+      "eval_samples_per_second": 21.972,
+      "eval_steps_per_second": 2.77,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 8.461085319519043,
+      "learning_rate": 1.545e-05,
+      "loss": 17.4368,
+      "step": 110
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 8.749673843383789,
+      "learning_rate": 1.695e-05,
+      "loss": 17.085,
+      "step": 120
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "eval_loss": 1.0227338075637817,
+      "eval_runtime": 26.8326,
+      "eval_samples_per_second": 21.876,
+      "eval_steps_per_second": 2.758,
+      "step": 125
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 8.67000961303711,
+      "learning_rate": 1.845e-05,
+      "loss": 16.7339,
+      "step": 130
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 8.6713285446167,
+      "learning_rate": 1.995e-05,
+      "loss": 15.519,
+      "step": 140
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 8.540597915649414,
+      "learning_rate": 2.145e-05,
+      "loss": 15.6515,
+      "step": 150
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "eval_loss": 0.9732660055160522,
+      "eval_runtime": 26.7644,
+      "eval_samples_per_second": 21.932,
+      "eval_steps_per_second": 2.765,
+      "step": 150
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 9.956620216369629,
+      "learning_rate": 2.2950000000000002e-05,
+      "loss": 15.3551,
+      "step": 160
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 10.259222984313965,
+      "learning_rate": 2.4449999999999998e-05,
+      "loss": 15.2106,
+      "step": 170
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "eval_loss": 0.9374558925628662,
+      "eval_runtime": 26.6861,
+      "eval_samples_per_second": 21.996,
+      "eval_steps_per_second": 2.773,
+      "step": 175
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 10.587629318237305,
+      "learning_rate": 2.595e-05,
+      "loss": 14.4782,
+      "step": 180
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 11.390460968017578,
+      "learning_rate": 2.7450000000000003e-05,
+      "loss": 14.8752,
+      "step": 190
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 9.895585060119629,
+      "learning_rate": 2.895e-05,
+      "loss": 14.3047,
+      "step": 200
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "eval_loss": 0.9113534688949585,
+      "eval_runtime": 26.6097,
+      "eval_samples_per_second": 22.06,
+      "eval_steps_per_second": 2.781,
+      "step": 200
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 11.74429988861084,
+      "learning_rate": 2.9856e-05,
+      "loss": 15.002,
+      "step": 210
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 11.080912590026855,
+      "learning_rate": 2.9375999999999998e-05,
+      "loss": 14.5833,
+      "step": 220
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "eval_loss": 0.8937327265739441,
+      "eval_runtime": 26.7352,
+      "eval_samples_per_second": 21.956,
+      "eval_steps_per_second": 2.768,
+      "step": 225
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 11.789284706115723,
+      "learning_rate": 2.8896e-05,
+      "loss": 14.1,
+      "step": 230
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 11.529643058776855,
+      "learning_rate": 2.8416e-05,
+      "loss": 13.9745,
+      "step": 240
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 11.497583389282227,
+      "learning_rate": 2.7936e-05,
+      "loss": 14.1046,
+      "step": 250
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "eval_loss": 0.8745776414871216,
+      "eval_runtime": 26.7257,
+      "eval_samples_per_second": 21.964,
+      "eval_steps_per_second": 2.769,
+      "step": 250
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 12.131537437438965,
+      "learning_rate": 2.7456000000000003e-05,
+      "loss": 13.9224,
+      "step": 260
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 11.43172550201416,
+      "learning_rate": 2.6976e-05,
+      "loss": 13.5105,
+      "step": 270
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 0.8645356893539429,
+      "eval_runtime": 26.5864,
+      "eval_samples_per_second": 22.079,
+      "eval_steps_per_second": 2.783,
+      "step": 275
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 12.523551940917969,
+      "learning_rate": 2.6496000000000002e-05,
+      "loss": 14.0794,
+      "step": 280
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 12.029654502868652,
+      "learning_rate": 2.6016e-05,
+      "loss": 13.614,
+      "step": 290
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 11.245109558105469,
+      "learning_rate": 2.5536e-05,
+      "loss": 13.4787,
+      "step": 300
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_loss": 0.8572074770927429,
+      "eval_runtime": 26.609,
+      "eval_samples_per_second": 22.06,
+      "eval_steps_per_second": 2.781,
+      "step": 300
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 11.823022842407227,
+      "learning_rate": 2.5056000000000002e-05,
+      "loss": 13.8165,
+      "step": 310
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 12.330411911010742,
+      "learning_rate": 2.4576000000000003e-05,
+      "loss": 13.8579,
+      "step": 320
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "eval_loss": 0.851715624332428,
+      "eval_runtime": 26.7595,
+      "eval_samples_per_second": 21.936,
+      "eval_steps_per_second": 2.765,
+      "step": 325
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.655832290649414,
+      "learning_rate": 2.4096e-05,
+      "loss": 13.4692,
+      "step": 330
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 12.884317398071289,
+      "learning_rate": 2.3616000000000002e-05,
+      "loss": 13.6527,
+      "step": 340
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 13.385115623474121,
+      "learning_rate": 2.3136e-05,
+      "loss": 13.2391,
+      "step": 350
+    },
+    {
+      "epoch": 2.121212121212121,
+      "eval_loss": 0.8470517992973328,
+      "eval_runtime": 26.7211,
+      "eval_samples_per_second": 21.968,
+      "eval_steps_per_second": 2.769,
+      "step": 350
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 13.529315948486328,
+      "learning_rate": 2.2656e-05,
+      "loss": 13.5396,
+      "step": 360
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 12.98504638671875,
+      "learning_rate": 2.2176e-05,
+      "loss": 13.0834,
+      "step": 370
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "eval_loss": 0.8422382473945618,
+      "eval_runtime": 26.7106,
+      "eval_samples_per_second": 21.976,
+      "eval_steps_per_second": 2.77,
+      "step": 375
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 15.45311164855957,
+      "learning_rate": 2.1696e-05,
+      "loss": 13.2898,
+      "step": 380
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 13.529963493347168,
+      "learning_rate": 2.1216e-05,
+      "loss": 13.4776,
+      "step": 390
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 15.130877494812012,
+      "learning_rate": 2.0736000000000003e-05,
+      "loss": 13.0466,
+      "step": 400
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "eval_loss": 0.8388310074806213,
+      "eval_runtime": 26.656,
+      "eval_samples_per_second": 22.021,
+      "eval_steps_per_second": 2.776,
+      "step": 400
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 14.1300687789917,
+      "learning_rate": 2.0256e-05,
+      "loss": 12.9431,
+      "step": 410
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 13.16057300567627,
+      "learning_rate": 1.9776000000000002e-05,
+      "loss": 13.5177,
+      "step": 420
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "eval_loss": 0.8353358507156372,
+      "eval_runtime": 26.5255,
+      "eval_samples_per_second": 22.13,
+      "eval_steps_per_second": 2.79,
+      "step": 425
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 13.661446571350098,
+      "learning_rate": 1.9296e-05,
+      "loss": 13.3989,
+      "step": 430
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 15.222647666931152,
+      "learning_rate": 1.8816e-05,
+      "loss": 12.9533,
+      "step": 440
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 13.713704109191895,
+      "learning_rate": 1.8336e-05,
+      "loss": 13.0158,
+      "step": 450
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "eval_loss": 0.8321167230606079,
+      "eval_runtime": 26.7516,
+      "eval_samples_per_second": 21.943,
+      "eval_steps_per_second": 2.766,
+      "step": 450
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 15.2013521194458,
+      "learning_rate": 1.7856e-05,
+      "loss": 12.8926,
+      "step": 460
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 17.601028442382812,
+      "learning_rate": 1.7376e-05,
+      "loss": 12.998,
+      "step": 470
+    },
+    {
+      "epoch": 2.878787878787879,
+      "eval_loss": 0.8293758630752563,
+      "eval_runtime": 26.634,
+      "eval_samples_per_second": 22.039,
+      "eval_steps_per_second": 2.778,
+      "step": 475
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 14.226529121398926,
+      "learning_rate": 1.6896000000000002e-05,
+      "loss": 13.3413,
+      "step": 480
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 15.361565589904785,
+      "learning_rate": 1.6416e-05,
+      "loss": 12.9467,
+      "step": 490
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 14.232434272766113,
+      "learning_rate": 1.5936e-05,
+      "loss": 12.7584,
+      "step": 500
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "eval_loss": 0.827523410320282,
+      "eval_runtime": 26.5691,
+      "eval_samples_per_second": 22.093,
+      "eval_steps_per_second": 2.785,
+      "step": 500
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 14.491694450378418,
+      "learning_rate": 1.5456e-05,
+      "loss": 12.8574,
+      "step": 510
+    },
+    {
+      "epoch": 3.1515151515151514,
+      "grad_norm": 14.694238662719727,
+      "learning_rate": 1.4976e-05,
+      "loss": 12.6902,
+      "step": 520
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "eval_loss": 0.8255205154418945,
+      "eval_runtime": 26.6932,
+      "eval_samples_per_second": 21.991,
+      "eval_steps_per_second": 2.772,
+      "step": 525
+    },
+    {
+      "epoch": 3.212121212121212,
+      "grad_norm": 15.725605010986328,
+      "learning_rate": 1.4496000000000001e-05,
+      "loss": 13.2972,
+      "step": 530
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 15.233382225036621,
+      "learning_rate": 1.4016000000000001e-05,
+      "loss": 12.8291,
+      "step": 540
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 16.083650588989258,
+      "learning_rate": 1.3536e-05,
+      "loss": 13.0188,
+      "step": 550
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 0.8239626288414001,
+      "eval_runtime": 26.6742,
+      "eval_samples_per_second": 22.006,
+      "eval_steps_per_second": 2.774,
+      "step": 550
+    },
+    {
+      "epoch": 3.393939393939394,
+      "grad_norm": 15.414470672607422,
+      "learning_rate": 1.3056e-05,
+      "loss": 12.2608,
+      "step": 560
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 15.951211929321289,
+      "learning_rate": 1.2576000000000001e-05,
+      "loss": 13.0705,
+      "step": 570
+    },
+    {
+      "epoch": 3.484848484848485,
+      "eval_loss": 0.8214691281318665,
+      "eval_runtime": 26.618,
+      "eval_samples_per_second": 22.053,
+      "eval_steps_per_second": 2.78,
+      "step": 575
+    },
+    {
+      "epoch": 3.515151515151515,
+      "grad_norm": 15.680049896240234,
+      "learning_rate": 1.2096e-05,
+      "loss": 12.5384,
+      "step": 580
+    },
+    {
+      "epoch": 3.5757575757575757,
+      "grad_norm": 14.927135467529297,
+      "learning_rate": 1.1616e-05,
+      "loss": 12.5877,
+      "step": 590
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 14.922800064086914,
+      "learning_rate": 1.1136e-05,
+      "loss": 12.8308,
+      "step": 600
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "eval_loss": 0.819739580154419,
+      "eval_runtime": 26.5757,
+      "eval_samples_per_second": 22.088,
+      "eval_steps_per_second": 2.784,
+      "step": 600
+    },
+    {
+      "epoch": 3.6969696969696972,
+      "grad_norm": 14.818592071533203,
+      "learning_rate": 1.0656000000000001e-05,
+      "loss": 12.9524,
+      "step": 610
+    },
+    {
+      "epoch": 3.757575757575758,
+      "grad_norm": 17.610429763793945,
+      "learning_rate": 1.0176e-05,
+      "loss": 12.9889,
+      "step": 620
+    },
+    {
+      "epoch": 3.787878787878788,
+      "eval_loss": 0.8184654712677002,
+      "eval_runtime": 26.4854,
+      "eval_samples_per_second": 22.163,
+      "eval_steps_per_second": 2.794,
+      "step": 625
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 15.759525299072266,
+      "learning_rate": 9.696e-06,
+      "loss": 12.8817,
+      "step": 630
+    },
+    {
+      "epoch": 3.878787878787879,
+      "grad_norm": 17.120342254638672,
+      "learning_rate": 9.216e-06,
+      "loss": 12.3056,
+      "step": 640
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "grad_norm": 15.682613372802734,
+      "learning_rate": 8.736e-06,
+      "loss": 12.5948,
+      "step": 650
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "eval_loss": 0.8165481686592102,
+      "eval_runtime": 26.5521,
+      "eval_samples_per_second": 22.107,
+      "eval_steps_per_second": 2.787,
+      "step": 650
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 16.467830657958984,
+      "learning_rate": 8.256e-06,
+      "loss": 13.1715,
+      "step": 660
+    },
+    {
+      "epoch": 4.0606060606060606,
+      "grad_norm": 16.381383895874023,
+      "learning_rate": 7.776e-06,
+      "loss": 11.9258,
+      "step": 670
+    },
+    {
+      "epoch": 4.090909090909091,
+      "eval_loss": 0.8159043192863464,
+      "eval_runtime": 26.5568,
+      "eval_samples_per_second": 22.104,
+      "eval_steps_per_second": 2.786,
+      "step": 675
+    },
+    {
+      "epoch": 4.121212121212121,
+      "grad_norm": 15.943025588989258,
+      "learning_rate": 7.296e-06,
+      "loss": 12.4245,
+      "step": 680
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 16.93096160888672,
+      "learning_rate": 6.8160000000000005e-06,
+      "loss": 12.5944,
+      "step": 690
+    },
+    {
+      "epoch": 4.242424242424242,
+      "grad_norm": 15.807243347167969,
+      "learning_rate": 6.336e-06,
+      "loss": 12.4043,
+      "step": 700
+    },
+    {
+      "epoch": 4.242424242424242,
+      "eval_loss": 0.8148561716079712,
+      "eval_runtime": 26.6856,
+      "eval_samples_per_second": 21.997,
+      "eval_steps_per_second": 2.773,
+      "step": 700
+    },
+    {
+      "epoch": 4.303030303030303,
+      "grad_norm": 16.146684646606445,
+      "learning_rate": 5.856e-06,
+      "loss": 12.3696,
+      "step": 710
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 16.58680534362793,
+      "learning_rate": 5.376e-06,
+      "loss": 12.9824,
+      "step": 720
+    },
+    {
+      "epoch": 4.393939393939394,
+      "eval_loss": 0.813624918460846,
+      "eval_runtime": 26.4692,
+      "eval_samples_per_second": 22.177,
+      "eval_steps_per_second": 2.796,
+      "step": 725
+    },
+    {
+      "epoch": 4.424242424242424,
+      "grad_norm": 15.89395523071289,
+      "learning_rate": 4.896e-06,
+      "loss": 12.6234,
+      "step": 730
+    },
+    {
+      "epoch": 4.484848484848484,
+      "grad_norm": 15.237595558166504,
+      "learning_rate": 4.416e-06,
+      "loss": 12.6045,
+      "step": 740
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 16.327821731567383,
+      "learning_rate": 3.936e-06,
+      "loss": 12.7275,
+      "step": 750
+    },
+    {
+      "epoch": 4.545454545454545,
+      "eval_loss": 0.8129462003707886,
+      "eval_runtime": 26.6701,
+      "eval_samples_per_second": 22.01,
+      "eval_steps_per_second": 2.775,
+      "step": 750
+    },
+    {
+      "epoch": 4.606060606060606,
+      "grad_norm": 16.905481338500977,
+      "learning_rate": 3.456e-06,
+      "loss": 12.56,
+      "step": 760
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 16.580707550048828,
+      "learning_rate": 2.976e-06,
+      "loss": 13.2326,
+      "step": 770
+    },
+    {
+      "epoch": 4.696969696969697,
+      "eval_loss": 0.8126159310340881,
+      "eval_runtime": 26.6639,
+      "eval_samples_per_second": 22.015,
+      "eval_steps_per_second": 2.775,
+      "step": 775
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 14.914974212646484,
+      "learning_rate": 2.496e-06,
+      "loss": 12.7135,
+      "step": 780
+    },
+    {
+      "epoch": 4.787878787878788,
+      "grad_norm": 15.809138298034668,
+      "learning_rate": 2.016e-06,
+      "loss": 12.6518,
+      "step": 790
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 17.07619285583496,
+      "learning_rate": 1.5360000000000002e-06,
+      "loss": 12.9454,
+      "step": 800
+    },
+    {
+      "epoch": 4.848484848484849,
+      "eval_loss": 0.8123075366020203,
+      "eval_runtime": 26.7378,
+      "eval_samples_per_second": 21.954,
+      "eval_steps_per_second": 2.768,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 825,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.596536164371661e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cffd76e545d75eac099a2d6a9df571049db5975b0004b6779682ad7445c6748
+size 5713

checkpoint-825/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-825/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-825/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a000370c68d9ed823135f7ead0ef718d8a19f1afffb9bde44f66e716f053e7de
+size 27280152

checkpoint-825/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1218d98e12f4b7aa4ca37e714cdc6df0894b971783ceb73855060e394991a4
+size 54634443

checkpoint-825/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6941c9b7058307c00bdb84576f0ded4617690c94ab517d2ded8bb44a6e970dd9
+size 14645

checkpoint-825/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab1c991d65e5d6d19c35983cf5e4bcc544a7eb0dd31b26dc8582f569a731fe7
+size 1383

checkpoint-825/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f1d31709b06d0fb34fd27e04ac77dd3b6c89a2a98263fa10741257092eb03ec
+size 1465

checkpoint-825/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-825/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-825/trainer_state.json

@@ -0,0 +1,881 @@
+{
+  "best_global_step": 825,
+  "best_metric": 0.8120399713516235,
+  "best_model_checkpoint": "/workspace/outputs/mistral-chatpro-finetuned/checkpoint-825",
+  "epoch": 5.0,
+  "eval_steps": 25,
+  "global_step": 825,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 149.54275512695312,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 29.7475,
+      "step": 10
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 269.5798034667969,
+      "learning_rate": 1.95e-06,
+      "loss": 31.5785,
+      "step": 20
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "eval_loss": 1.9893885850906372,
+      "eval_runtime": 27.1115,
+      "eval_samples_per_second": 21.651,
+      "eval_steps_per_second": 2.729,
+      "step": 25
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 121.41719818115234,
+      "learning_rate": 3.4500000000000004e-06,
+      "loss": 28.2201,
+      "step": 30
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 101.0121078491211,
+      "learning_rate": 4.95e-06,
+      "loss": 28.6571,
+      "step": 40
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 283.864501953125,
+      "learning_rate": 6.45e-06,
+      "loss": 26.6667,
+      "step": 50
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "eval_loss": 1.5634442567825317,
+      "eval_runtime": 26.9981,
+      "eval_samples_per_second": 21.742,
+      "eval_steps_per_second": 2.741,
+      "step": 50
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 55.40841293334961,
+      "learning_rate": 7.95e-06,
+      "loss": 22.7511,
+      "step": 60
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 27.064821243286133,
+      "learning_rate": 9.450000000000001e-06,
+      "loss": 20.1933,
+      "step": 70
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "eval_loss": 1.1919723749160767,
+      "eval_runtime": 26.8965,
+      "eval_samples_per_second": 21.824,
+      "eval_steps_per_second": 2.751,
+      "step": 75
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 16.979394912719727,
+      "learning_rate": 1.095e-05,
+      "loss": 18.0581,
+      "step": 80
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 8.984743118286133,
+      "learning_rate": 1.245e-05,
+      "loss": 19.0451,
+      "step": 90
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 8.195664405822754,
+      "learning_rate": 1.395e-05,
+      "loss": 17.7881,
+      "step": 100
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "eval_loss": 1.1023012399673462,
+      "eval_runtime": 26.7164,
+      "eval_samples_per_second": 21.972,
+      "eval_steps_per_second": 2.77,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 8.461085319519043,
+      "learning_rate": 1.545e-05,
+      "loss": 17.4368,
+      "step": 110
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 8.749673843383789,
+      "learning_rate": 1.695e-05,
+      "loss": 17.085,
+      "step": 120
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "eval_loss": 1.0227338075637817,
+      "eval_runtime": 26.8326,
+      "eval_samples_per_second": 21.876,
+      "eval_steps_per_second": 2.758,
+      "step": 125
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 8.67000961303711,
+      "learning_rate": 1.845e-05,
+      "loss": 16.7339,
+      "step": 130
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 8.6713285446167,
+      "learning_rate": 1.995e-05,
+      "loss": 15.519,
+      "step": 140
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 8.540597915649414,
+      "learning_rate": 2.145e-05,
+      "loss": 15.6515,
+      "step": 150
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "eval_loss": 0.9732660055160522,
+      "eval_runtime": 26.7644,
+      "eval_samples_per_second": 21.932,
+      "eval_steps_per_second": 2.765,
+      "step": 150
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 9.956620216369629,
+      "learning_rate": 2.2950000000000002e-05,
+      "loss": 15.3551,
+      "step": 160
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 10.259222984313965,
+      "learning_rate": 2.4449999999999998e-05,
+      "loss": 15.2106,
+      "step": 170
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "eval_loss": 0.9374558925628662,
+      "eval_runtime": 26.6861,
+      "eval_samples_per_second": 21.996,
+      "eval_steps_per_second": 2.773,
+      "step": 175
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 10.587629318237305,
+      "learning_rate": 2.595e-05,
+      "loss": 14.4782,
+      "step": 180
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 11.390460968017578,
+      "learning_rate": 2.7450000000000003e-05,
+      "loss": 14.8752,
+      "step": 190
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 9.895585060119629,
+      "learning_rate": 2.895e-05,
+      "loss": 14.3047,
+      "step": 200
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "eval_loss": 0.9113534688949585,
+      "eval_runtime": 26.6097,
+      "eval_samples_per_second": 22.06,
+      "eval_steps_per_second": 2.781,
+      "step": 200
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 11.74429988861084,
+      "learning_rate": 2.9856e-05,
+      "loss": 15.002,
+      "step": 210
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 11.080912590026855,
+      "learning_rate": 2.9375999999999998e-05,
+      "loss": 14.5833,
+      "step": 220
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "eval_loss": 0.8937327265739441,
+      "eval_runtime": 26.7352,
+      "eval_samples_per_second": 21.956,
+      "eval_steps_per_second": 2.768,
+      "step": 225
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 11.789284706115723,
+      "learning_rate": 2.8896e-05,
+      "loss": 14.1,
+      "step": 230
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 11.529643058776855,
+      "learning_rate": 2.8416e-05,
+      "loss": 13.9745,
+      "step": 240
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 11.497583389282227,
+      "learning_rate": 2.7936e-05,
+      "loss": 14.1046,
+      "step": 250
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "eval_loss": 0.8745776414871216,
+      "eval_runtime": 26.7257,
+      "eval_samples_per_second": 21.964,
+      "eval_steps_per_second": 2.769,
+      "step": 250
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 12.131537437438965,
+      "learning_rate": 2.7456000000000003e-05,
+      "loss": 13.9224,
+      "step": 260
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 11.43172550201416,
+      "learning_rate": 2.6976e-05,
+      "loss": 13.5105,
+      "step": 270
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 0.8645356893539429,
+      "eval_runtime": 26.5864,
+      "eval_samples_per_second": 22.079,
+      "eval_steps_per_second": 2.783,
+      "step": 275
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 12.523551940917969,
+      "learning_rate": 2.6496000000000002e-05,
+      "loss": 14.0794,
+      "step": 280
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 12.029654502868652,
+      "learning_rate": 2.6016e-05,
+      "loss": 13.614,
+      "step": 290
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 11.245109558105469,
+      "learning_rate": 2.5536e-05,
+      "loss": 13.4787,
+      "step": 300
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_loss": 0.8572074770927429,
+      "eval_runtime": 26.609,
+      "eval_samples_per_second": 22.06,
+      "eval_steps_per_second": 2.781,
+      "step": 300
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 11.823022842407227,
+      "learning_rate": 2.5056000000000002e-05,
+      "loss": 13.8165,
+      "step": 310
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 12.330411911010742,
+      "learning_rate": 2.4576000000000003e-05,
+      "loss": 13.8579,
+      "step": 320
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "eval_loss": 0.851715624332428,
+      "eval_runtime": 26.7595,
+      "eval_samples_per_second": 21.936,
+      "eval_steps_per_second": 2.765,
+      "step": 325
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.655832290649414,
+      "learning_rate": 2.4096e-05,
+      "loss": 13.4692,
+      "step": 330
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 12.884317398071289,
+      "learning_rate": 2.3616000000000002e-05,
+      "loss": 13.6527,
+      "step": 340
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 13.385115623474121,
+      "learning_rate": 2.3136e-05,
+      "loss": 13.2391,
+      "step": 350
+    },
+    {
+      "epoch": 2.121212121212121,
+      "eval_loss": 0.8470517992973328,
+      "eval_runtime": 26.7211,
+      "eval_samples_per_second": 21.968,
+      "eval_steps_per_second": 2.769,
+      "step": 350
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 13.529315948486328,
+      "learning_rate": 2.2656e-05,
+      "loss": 13.5396,
+      "step": 360
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 12.98504638671875,
+      "learning_rate": 2.2176e-05,
+      "loss": 13.0834,
+      "step": 370
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "eval_loss": 0.8422382473945618,
+      "eval_runtime": 26.7106,
+      "eval_samples_per_second": 21.976,
+      "eval_steps_per_second": 2.77,
+      "step": 375
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 15.45311164855957,
+      "learning_rate": 2.1696e-05,
+      "loss": 13.2898,
+      "step": 380
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 13.529963493347168,
+      "learning_rate": 2.1216e-05,
+      "loss": 13.4776,
+      "step": 390
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 15.130877494812012,
+      "learning_rate": 2.0736000000000003e-05,
+      "loss": 13.0466,
+      "step": 400
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "eval_loss": 0.8388310074806213,
+      "eval_runtime": 26.656,
+      "eval_samples_per_second": 22.021,
+      "eval_steps_per_second": 2.776,
+      "step": 400
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 14.1300687789917,
+      "learning_rate": 2.0256e-05,
+      "loss": 12.9431,
+      "step": 410
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 13.16057300567627,
+      "learning_rate": 1.9776000000000002e-05,
+      "loss": 13.5177,
+      "step": 420
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "eval_loss": 0.8353358507156372,
+      "eval_runtime": 26.5255,
+      "eval_samples_per_second": 22.13,
+      "eval_steps_per_second": 2.79,
+      "step": 425
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 13.661446571350098,
+      "learning_rate": 1.9296e-05,
+      "loss": 13.3989,
+      "step": 430
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 15.222647666931152,
+      "learning_rate": 1.8816e-05,
+      "loss": 12.9533,
+      "step": 440
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 13.713704109191895,
+      "learning_rate": 1.8336e-05,
+      "loss": 13.0158,
+      "step": 450
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "eval_loss": 0.8321167230606079,
+      "eval_runtime": 26.7516,
+      "eval_samples_per_second": 21.943,
+      "eval_steps_per_second": 2.766,
+      "step": 450
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 15.2013521194458,
+      "learning_rate": 1.7856e-05,
+      "loss": 12.8926,
+      "step": 460
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 17.601028442382812,
+      "learning_rate": 1.7376e-05,
+      "loss": 12.998,
+      "step": 470
+    },
+    {
+      "epoch": 2.878787878787879,
+      "eval_loss": 0.8293758630752563,
+      "eval_runtime": 26.634,
+      "eval_samples_per_second": 22.039,
+      "eval_steps_per_second": 2.778,
+      "step": 475
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 14.226529121398926,
+      "learning_rate": 1.6896000000000002e-05,
+      "loss": 13.3413,
+      "step": 480
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 15.361565589904785,
+      "learning_rate": 1.6416e-05,
+      "loss": 12.9467,
+      "step": 490
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 14.232434272766113,
+      "learning_rate": 1.5936e-05,
+      "loss": 12.7584,
+      "step": 500
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "eval_loss": 0.827523410320282,
+      "eval_runtime": 26.5691,
+      "eval_samples_per_second": 22.093,
+      "eval_steps_per_second": 2.785,
+      "step": 500
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 14.491694450378418,
+      "learning_rate": 1.5456e-05,
+      "loss": 12.8574,
+      "step": 510
+    },
+    {
+      "epoch": 3.1515151515151514,
+      "grad_norm": 14.694238662719727,
+      "learning_rate": 1.4976e-05,
+      "loss": 12.6902,
+      "step": 520
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "eval_loss": 0.8255205154418945,
+      "eval_runtime": 26.6932,
+      "eval_samples_per_second": 21.991,
+      "eval_steps_per_second": 2.772,
+      "step": 525
+    },
+    {
+      "epoch": 3.212121212121212,
+      "grad_norm": 15.725605010986328,
+      "learning_rate": 1.4496000000000001e-05,
+      "loss": 13.2972,
+      "step": 530
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 15.233382225036621,
+      "learning_rate": 1.4016000000000001e-05,
+      "loss": 12.8291,
+      "step": 540
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 16.083650588989258,
+      "learning_rate": 1.3536e-05,
+      "loss": 13.0188,
+      "step": 550
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 0.8239626288414001,
+      "eval_runtime": 26.6742,
+      "eval_samples_per_second": 22.006,
+      "eval_steps_per_second": 2.774,
+      "step": 550
+    },
+    {
+      "epoch": 3.393939393939394,
+      "grad_norm": 15.414470672607422,
+      "learning_rate": 1.3056e-05,
+      "loss": 12.2608,
+      "step": 560
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 15.951211929321289,
+      "learning_rate": 1.2576000000000001e-05,
+      "loss": 13.0705,
+      "step": 570
+    },
+    {
+      "epoch": 3.484848484848485,
+      "eval_loss": 0.8214691281318665,
+      "eval_runtime": 26.618,
+      "eval_samples_per_second": 22.053,
+      "eval_steps_per_second": 2.78,
+      "step": 575
+    },
+    {
+      "epoch": 3.515151515151515,
+      "grad_norm": 15.680049896240234,
+      "learning_rate": 1.2096e-05,
+      "loss": 12.5384,
+      "step": 580
+    },
+    {
+      "epoch": 3.5757575757575757,
+      "grad_norm": 14.927135467529297,
+      "learning_rate": 1.1616e-05,
+      "loss": 12.5877,
+      "step": 590
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 14.922800064086914,
+      "learning_rate": 1.1136e-05,
+      "loss": 12.8308,
+      "step": 600
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "eval_loss": 0.819739580154419,
+      "eval_runtime": 26.5757,
+      "eval_samples_per_second": 22.088,
+      "eval_steps_per_second": 2.784,
+      "step": 600
+    },
+    {
+      "epoch": 3.6969696969696972,
+      "grad_norm": 14.818592071533203,
+      "learning_rate": 1.0656000000000001e-05,
+      "loss": 12.9524,
+      "step": 610
+    },
+    {
+      "epoch": 3.757575757575758,
+      "grad_norm": 17.610429763793945,
+      "learning_rate": 1.0176e-05,
+      "loss": 12.9889,
+      "step": 620
+    },
+    {
+      "epoch": 3.787878787878788,
+      "eval_loss": 0.8184654712677002,
+      "eval_runtime": 26.4854,
+      "eval_samples_per_second": 22.163,
+      "eval_steps_per_second": 2.794,
+      "step": 625
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 15.759525299072266,
+      "learning_rate": 9.696e-06,
+      "loss": 12.8817,
+      "step": 630
+    },
+    {
+      "epoch": 3.878787878787879,
+      "grad_norm": 17.120342254638672,
+      "learning_rate": 9.216e-06,
+      "loss": 12.3056,
+      "step": 640
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "grad_norm": 15.682613372802734,
+      "learning_rate": 8.736e-06,
+      "loss": 12.5948,
+      "step": 650
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "eval_loss": 0.8165481686592102,
+      "eval_runtime": 26.5521,
+      "eval_samples_per_second": 22.107,
+      "eval_steps_per_second": 2.787,
+      "step": 650
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 16.467830657958984,
+      "learning_rate": 8.256e-06,
+      "loss": 13.1715,
+      "step": 660
+    },
+    {
+      "epoch": 4.0606060606060606,
+      "grad_norm": 16.381383895874023,
+      "learning_rate": 7.776e-06,
+      "loss": 11.9258,
+      "step": 670
+    },
+    {
+      "epoch": 4.090909090909091,
+      "eval_loss": 0.8159043192863464,
+      "eval_runtime": 26.5568,
+      "eval_samples_per_second": 22.104,
+      "eval_steps_per_second": 2.786,
+      "step": 675
+    },
+    {
+      "epoch": 4.121212121212121,
+      "grad_norm": 15.943025588989258,
+      "learning_rate": 7.296e-06,
+      "loss": 12.4245,
+      "step": 680
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 16.93096160888672,
+      "learning_rate": 6.8160000000000005e-06,
+      "loss": 12.5944,
+      "step": 690
+    },
+    {
+      "epoch": 4.242424242424242,
+      "grad_norm": 15.807243347167969,
+      "learning_rate": 6.336e-06,
+      "loss": 12.4043,
+      "step": 700
+    },
+    {
+      "epoch": 4.242424242424242,
+      "eval_loss": 0.8148561716079712,
+      "eval_runtime": 26.6856,
+      "eval_samples_per_second": 21.997,
+      "eval_steps_per_second": 2.773,
+      "step": 700
+    },
+    {
+      "epoch": 4.303030303030303,
+      "grad_norm": 16.146684646606445,
+      "learning_rate": 5.856e-06,
+      "loss": 12.3696,
+      "step": 710
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 16.58680534362793,
+      "learning_rate": 5.376e-06,
+      "loss": 12.9824,
+      "step": 720
+    },
+    {
+      "epoch": 4.393939393939394,
+      "eval_loss": 0.813624918460846,
+      "eval_runtime": 26.4692,
+      "eval_samples_per_second": 22.177,
+      "eval_steps_per_second": 2.796,
+      "step": 725
+    },
+    {
+      "epoch": 4.424242424242424,
+      "grad_norm": 15.89395523071289,
+      "learning_rate": 4.896e-06,
+      "loss": 12.6234,
+      "step": 730
+    },
+    {
+      "epoch": 4.484848484848484,
+      "grad_norm": 15.237595558166504,
+      "learning_rate": 4.416e-06,
+      "loss": 12.6045,
+      "step": 740
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 16.327821731567383,
+      "learning_rate": 3.936e-06,
+      "loss": 12.7275,
+      "step": 750
+    },
+    {
+      "epoch": 4.545454545454545,
+      "eval_loss": 0.8129462003707886,
+      "eval_runtime": 26.6701,
+      "eval_samples_per_second": 22.01,
+      "eval_steps_per_second": 2.775,
+      "step": 750
+    },
+    {
+      "epoch": 4.606060606060606,
+      "grad_norm": 16.905481338500977,
+      "learning_rate": 3.456e-06,
+      "loss": 12.56,
+      "step": 760
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 16.580707550048828,
+      "learning_rate": 2.976e-06,
+      "loss": 13.2326,
+      "step": 770
+    },
+    {
+      "epoch": 4.696969696969697,
+      "eval_loss": 0.8126159310340881,
+      "eval_runtime": 26.6639,
+      "eval_samples_per_second": 22.015,
+      "eval_steps_per_second": 2.775,
+      "step": 775
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 14.914974212646484,
+      "learning_rate": 2.496e-06,
+      "loss": 12.7135,
+      "step": 780
+    },
+    {
+      "epoch": 4.787878787878788,
+      "grad_norm": 15.809138298034668,
+      "learning_rate": 2.016e-06,
+      "loss": 12.6518,
+      "step": 790
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 17.07619285583496,
+      "learning_rate": 1.5360000000000002e-06,
+      "loss": 12.9454,
+      "step": 800
+    },
+    {
+      "epoch": 4.848484848484849,
+      "eval_loss": 0.8123075366020203,
+      "eval_runtime": 26.7378,
+      "eval_samples_per_second": 21.954,
+      "eval_steps_per_second": 2.768,
+      "step": 800
+    },
+    {
+      "epoch": 4.909090909090909,
+      "grad_norm": 16.335344314575195,
+      "learning_rate": 1.0560000000000001e-06,
+      "loss": 12.5058,
+      "step": 810
+    },
+    {
+      "epoch": 4.96969696969697,
+      "grad_norm": 15.236989974975586,
+      "learning_rate": 5.76e-07,
+      "loss": 12.4509,
+      "step": 820
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.8120399713516235,
+      "eval_runtime": 26.5698,
+      "eval_samples_per_second": 22.093,
+      "eval_steps_per_second": 2.785,
+      "step": 825
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 825,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.771236601757696e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-825/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cffd76e545d75eac099a2d6a9df571049db5975b0004b6779682ad7445c6748
+size 5713

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_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}