Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+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 0.15.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hpc2hdd/home/xyang346/llama2/llama/llama-2-7b-hf/7B",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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 sha256:19f6a86c93335376911b5940d4746bd56a20b93092125d5ab73b94e2d0cfa95d
+size 16794200

checkpoint-290/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hpc2hdd/home/xyang346/llama2/llama/llama-2-7b-hf/7B
+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 0.15.1

checkpoint-290/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hpc2hdd/home/xyang346/llama2/llama/llama-2-7b-hf/7B",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-290/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c774f4dec5d56798e2687162d20cb7c4d43c6573568678f0d91d059414445c16
+size 16794200

checkpoint-290/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1693a438f0c591625e19c65b8c21def6383a1fb36c570aa7b8f157200d07874
+size 33662074

checkpoint-290/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8425def0aee636dc8a99242115c35325aea22c6a358ad3c9b29656d10824f541
+size 14244

checkpoint-290/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c5e85eeec566bdec80b4059f055bc9dd626082a9fd4657577efc5e1e0ebb4c
+size 988

checkpoint-290/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48caffb94aba9182c95e4f5346cd47673b2fc9133dbb86f24b70dad316572533
+size 1064

checkpoint-290/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-290/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-290/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "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-290/trainer_state.json

@@ -0,0 +1,672 @@
+{
+  "best_global_step": 290,
+  "best_metric": 6.4777703285217285,
+  "best_model_checkpoint": "./llama2-step4/checkpoint-290",
+  "epoch": 48.333333333333336,
+  "eval_steps": 10,
+  "global_step": 290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 8.655,
+      "step": 5
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 5.807435035705566,
+      "learning_rate": 9e-06,
+      "loss": 8.6675,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 8.762306213378906,
+      "eval_runtime": 1.1641,
+      "eval_samples_per_second": 8.591,
+      "eval_steps_per_second": 2.577,
+      "step": 10
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 4.866168022155762,
+      "learning_rate": 9.862068965517241e-06,
+      "loss": 8.5013,
+      "step": 15
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.68835973739624,
+      "learning_rate": 9.689655172413794e-06,
+      "loss": 8.3972,
+      "step": 20
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 8.49362850189209,
+      "eval_runtime": 1.1628,
+      "eval_samples_per_second": 8.6,
+      "eval_steps_per_second": 2.58,
+      "step": 20
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 7.694056510925293,
+      "learning_rate": 9.517241379310346e-06,
+      "loss": 8.2902,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 6.873053550720215,
+      "learning_rate": 9.344827586206898e-06,
+      "loss": 8.1007,
+      "step": 30
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 8.257888793945312,
+      "eval_runtime": 1.1642,
+      "eval_samples_per_second": 8.59,
+      "eval_steps_per_second": 2.577,
+      "step": 30
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 6.409057140350342,
+      "learning_rate": 9.172413793103448e-06,
+      "loss": 8.0427,
+      "step": 35
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 5.669801235198975,
+      "learning_rate": 9e-06,
+      "loss": 7.9235,
+      "step": 40
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 8.044379234313965,
+      "eval_runtime": 1.1677,
+      "eval_samples_per_second": 8.564,
+      "eval_steps_per_second": 2.569,
+      "step": 40
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 4.534883499145508,
+      "learning_rate": 8.827586206896552e-06,
+      "loss": 7.708,
+      "step": 45
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 4.812073707580566,
+      "learning_rate": 8.655172413793104e-06,
+      "loss": 7.6847,
+      "step": 50
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_loss": 7.831937313079834,
+      "eval_runtime": 1.1678,
+      "eval_samples_per_second": 8.563,
+      "eval_steps_per_second": 2.569,
+      "step": 50
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 4.398963928222656,
+      "learning_rate": 8.482758620689656e-06,
+      "loss": 7.5551,
+      "step": 55
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 6.508076190948486,
+      "learning_rate": 8.310344827586207e-06,
+      "loss": 7.4255,
+      "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 7.6158857345581055,
+      "eval_runtime": 1.1694,
+      "eval_samples_per_second": 8.552,
+      "eval_steps_per_second": 2.566,
+      "step": 60
+    },
+    {
+      "epoch": 10.833333333333334,
+      "grad_norm": 7.493861198425293,
+      "learning_rate": 8.137931034482759e-06,
+      "loss": 7.3105,
+      "step": 65
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 5.808365821838379,
+      "learning_rate": 7.965517241379311e-06,
+      "loss": 7.3573,
+      "step": 70
+    },
+    {
+      "epoch": 11.666666666666666,
+      "eval_loss": 7.405577659606934,
+      "eval_runtime": 1.17,
+      "eval_samples_per_second": 8.547,
+      "eval_steps_per_second": 2.564,
+      "step": 70
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 5.766481399536133,
+      "learning_rate": 7.793103448275863e-06,
+      "loss": 7.0032,
+      "step": 75
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 5.715093612670898,
+      "learning_rate": 7.655172413793104e-06,
+      "loss": 6.9862,
+      "step": 80
+    },
+    {
+      "epoch": 13.333333333333334,
+      "eval_loss": 7.243984222412109,
+      "eval_runtime": 1.1687,
+      "eval_samples_per_second": 8.556,
+      "eval_steps_per_second": 2.567,
+      "step": 80
+    },
+    {
+      "epoch": 14.166666666666666,
+      "grad_norm": 6.890617370605469,
+      "learning_rate": 7.482758620689656e-06,
+      "loss": 6.908,
+      "step": 85
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 6.349765300750732,
+      "learning_rate": 7.310344827586208e-06,
+      "loss": 6.8809,
+      "step": 90
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 7.085419654846191,
+      "eval_runtime": 1.1695,
+      "eval_samples_per_second": 8.55,
+      "eval_steps_per_second": 2.565,
+      "step": 90
+    },
+    {
+      "epoch": 15.833333333333334,
+      "grad_norm": 5.365812301635742,
+      "learning_rate": 7.137931034482759e-06,
+      "loss": 6.7798,
+      "step": 95
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 7.526610374450684,
+      "learning_rate": 6.9655172413793105e-06,
+      "loss": 6.606,
+      "step": 100
+    },
+    {
+      "epoch": 16.666666666666668,
+      "eval_loss": 6.946846961975098,
+      "eval_runtime": 1.1712,
+      "eval_samples_per_second": 8.538,
+      "eval_steps_per_second": 2.561,
+      "step": 100
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 5.357245922088623,
+      "learning_rate": 6.7931034482758626e-06,
+      "loss": 6.7679,
+      "step": 105
+    },
+    {
+      "epoch": 18.333333333333332,
+      "grad_norm": 7.445984363555908,
+      "learning_rate": 6.620689655172415e-06,
+      "loss": 6.4131,
+      "step": 110
+    },
+    {
+      "epoch": 18.333333333333332,
+      "eval_loss": 6.84014892578125,
+      "eval_runtime": 1.1688,
+      "eval_samples_per_second": 8.556,
+      "eval_steps_per_second": 2.567,
+      "step": 110
+    },
+    {
+      "epoch": 19.166666666666668,
+      "grad_norm": 5.064093589782715,
+      "learning_rate": 6.448275862068966e-06,
+      "loss": 6.4387,
+      "step": 115
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 6.121270179748535,
+      "learning_rate": 6.275862068965518e-06,
+      "loss": 6.5389,
+      "step": 120
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 6.772418975830078,
+      "eval_runtime": 1.1693,
+      "eval_samples_per_second": 8.552,
+      "eval_steps_per_second": 2.566,
+      "step": 120
+    },
+    {
+      "epoch": 20.833333333333332,
+      "grad_norm": 4.504457473754883,
+      "learning_rate": 6.103448275862069e-06,
+      "loss": 6.3358,
+      "step": 125
+    },
+    {
+      "epoch": 21.666666666666668,
+      "grad_norm": 2.5440237522125244,
+      "learning_rate": 5.9310344827586205e-06,
+      "loss": 6.4499,
+      "step": 130
+    },
+    {
+      "epoch": 21.666666666666668,
+      "eval_loss": 6.720807075500488,
+      "eval_runtime": 1.169,
+      "eval_samples_per_second": 8.554,
+      "eval_steps_per_second": 2.566,
+      "step": 130
+    },
+    {
+      "epoch": 22.5,
+      "grad_norm": 3.769169807434082,
+      "learning_rate": 5.758620689655173e-06,
+      "loss": 6.3462,
+      "step": 135
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 3.5738062858581543,
+      "learning_rate": 5.586206896551725e-06,
+      "loss": 6.3467,
+      "step": 140
+    },
+    {
+      "epoch": 23.333333333333332,
+      "eval_loss": 6.676053047180176,
+      "eval_runtime": 1.1692,
+      "eval_samples_per_second": 8.553,
+      "eval_steps_per_second": 2.566,
+      "step": 140
+    },
+    {
+      "epoch": 24.166666666666668,
+      "grad_norm": 2.525397539138794,
+      "learning_rate": 5.413793103448276e-06,
+      "loss": 6.4262,
+      "step": 145
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 7.168394565582275,
+      "learning_rate": 5.241379310344829e-06,
+      "loss": 6.2056,
+      "step": 150
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 6.641719818115234,
+      "eval_runtime": 1.1685,
+      "eval_samples_per_second": 8.558,
+      "eval_steps_per_second": 2.567,
+      "step": 150
+    },
+    {
+      "epoch": 25.833333333333332,
+      "grad_norm": 3.0939154624938965,
+      "learning_rate": 5.06896551724138e-06,
+      "loss": 6.1915,
+      "step": 155
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 3.166870355606079,
+      "learning_rate": 4.896551724137931e-06,
+      "loss": 6.3653,
+      "step": 160
+    },
+    {
+      "epoch": 26.666666666666668,
+      "eval_loss": 6.614515781402588,
+      "eval_runtime": 1.1686,
+      "eval_samples_per_second": 8.557,
+      "eval_steps_per_second": 2.567,
+      "step": 160
+    },
+    {
+      "epoch": 27.5,
+      "grad_norm": 4.855230331420898,
+      "learning_rate": 4.724137931034483e-06,
+      "loss": 6.0945,
+      "step": 165
+    },
+    {
+      "epoch": 28.333333333333332,
+      "grad_norm": 4.497844219207764,
+      "learning_rate": 4.551724137931035e-06,
+      "loss": 6.4573,
+      "step": 170
+    },
+    {
+      "epoch": 28.333333333333332,
+      "eval_loss": 6.58881139755249,
+      "eval_runtime": 1.1689,
+      "eval_samples_per_second": 8.555,
+      "eval_steps_per_second": 2.566,
+      "step": 170
+    },
+    {
+      "epoch": 29.166666666666668,
+      "grad_norm": 5.766814231872559,
+      "learning_rate": 4.379310344827587e-06,
+      "loss": 6.25,
+      "step": 175
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 2.9528305530548096,
+      "learning_rate": 4.206896551724138e-06,
+      "loss": 6.1068,
+      "step": 180
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 6.571514129638672,
+      "eval_runtime": 1.1695,
+      "eval_samples_per_second": 8.551,
+      "eval_steps_per_second": 2.565,
+      "step": 180
+    },
+    {
+      "epoch": 30.833333333333332,
+      "grad_norm": 4.210498809814453,
+      "learning_rate": 4.03448275862069e-06,
+      "loss": 6.4773,
+      "step": 185
+    },
+    {
+      "epoch": 31.666666666666668,
+      "grad_norm": 3.7556307315826416,
+      "learning_rate": 3.862068965517241e-06,
+      "loss": 6.1074,
+      "step": 190
+    },
+    {
+      "epoch": 31.666666666666668,
+      "eval_loss": 6.5557684898376465,
+      "eval_runtime": 1.1685,
+      "eval_samples_per_second": 8.558,
+      "eval_steps_per_second": 2.567,
+      "step": 190
+    },
+    {
+      "epoch": 32.5,
+      "grad_norm": 2.2701170444488525,
+      "learning_rate": 3.6896551724137934e-06,
+      "loss": 6.0287,
+      "step": 195
+    },
+    {
+      "epoch": 33.333333333333336,
+      "grad_norm": 3.6891818046569824,
+      "learning_rate": 3.517241379310345e-06,
+      "loss": 6.0739,
+      "step": 200
+    },
+    {
+      "epoch": 33.333333333333336,
+      "eval_loss": 6.541436195373535,
+      "eval_runtime": 1.1714,
+      "eval_samples_per_second": 8.537,
+      "eval_steps_per_second": 2.561,
+      "step": 200
+    },
+    {
+      "epoch": 34.166666666666664,
+      "grad_norm": 3.8515024185180664,
+      "learning_rate": 3.3448275862068967e-06,
+      "loss": 6.2661,
+      "step": 205
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 2.5693061351776123,
+      "learning_rate": 3.172413793103449e-06,
+      "loss": 6.1364,
+      "step": 210
+    },
+    {
+      "epoch": 35.0,
+      "eval_loss": 6.5295000076293945,
+      "eval_runtime": 1.1683,
+      "eval_samples_per_second": 8.559,
+      "eval_steps_per_second": 2.568,
+      "step": 210
+    },
+    {
+      "epoch": 35.833333333333336,
+      "grad_norm": 3.240337610244751,
+      "learning_rate": 3e-06,
+      "loss": 6.4022,
+      "step": 215
+    },
+    {
+      "epoch": 36.666666666666664,
+      "grad_norm": 3.298610210418701,
+      "learning_rate": 2.827586206896552e-06,
+      "loss": 6.0031,
+      "step": 220
+    },
+    {
+      "epoch": 36.666666666666664,
+      "eval_loss": 6.518210411071777,
+      "eval_runtime": 1.1686,
+      "eval_samples_per_second": 8.557,
+      "eval_steps_per_second": 2.567,
+      "step": 220
+    },
+    {
+      "epoch": 37.5,
+      "grad_norm": 2.766157865524292,
+      "learning_rate": 2.6551724137931034e-06,
+      "loss": 5.9806,
+      "step": 225
+    },
+    {
+      "epoch": 38.333333333333336,
+      "grad_norm": 13.019350051879883,
+      "learning_rate": 2.4827586206896555e-06,
+      "loss": 6.1952,
+      "step": 230
+    },
+    {
+      "epoch": 38.333333333333336,
+      "eval_loss": 6.507277011871338,
+      "eval_runtime": 1.168,
+      "eval_samples_per_second": 8.562,
+      "eval_steps_per_second": 2.568,
+      "step": 230
+    },
+    {
+      "epoch": 39.166666666666664,
+      "grad_norm": 7.104252815246582,
+      "learning_rate": 2.310344827586207e-06,
+      "loss": 5.9675,
+      "step": 235
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 2.4420504570007324,
+      "learning_rate": 2.137931034482759e-06,
+      "loss": 6.2932,
+      "step": 240
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 6.499304294586182,
+      "eval_runtime": 1.1692,
+      "eval_samples_per_second": 8.553,
+      "eval_steps_per_second": 2.566,
+      "step": 240
+    },
+    {
+      "epoch": 40.833333333333336,
+      "grad_norm": 4.704829692840576,
+      "learning_rate": 1.9655172413793105e-06,
+      "loss": 6.086,
+      "step": 245
+    },
+    {
+      "epoch": 41.666666666666664,
+      "grad_norm": 8.435072898864746,
+      "learning_rate": 1.7931034482758622e-06,
+      "loss": 5.9113,
+      "step": 250
+    },
+    {
+      "epoch": 41.666666666666664,
+      "eval_loss": 6.4918694496154785,
+      "eval_runtime": 1.1699,
+      "eval_samples_per_second": 8.548,
+      "eval_steps_per_second": 2.564,
+      "step": 250
+    },
+    {
+      "epoch": 42.5,
+      "grad_norm": 8.287426948547363,
+      "learning_rate": 1.6206896551724138e-06,
+      "loss": 6.4342,
+      "step": 255
+    },
+    {
+      "epoch": 43.333333333333336,
+      "grad_norm": 2.980454921722412,
+      "learning_rate": 1.4482758620689657e-06,
+      "loss": 5.8916,
+      "step": 260
+    },
+    {
+      "epoch": 43.333333333333336,
+      "eval_loss": 6.487914085388184,
+      "eval_runtime": 1.1689,
+      "eval_samples_per_second": 8.555,
+      "eval_steps_per_second": 2.567,
+      "step": 260
+    },
+    {
+      "epoch": 44.166666666666664,
+      "grad_norm": 3.5956976413726807,
+      "learning_rate": 1.2758620689655174e-06,
+      "loss": 6.2072,
+      "step": 265
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 3.0276715755462646,
+      "learning_rate": 1.103448275862069e-06,
+      "loss": 6.1625,
+      "step": 270
+    },
+    {
+      "epoch": 45.0,
+      "eval_loss": 6.483713626861572,
+      "eval_runtime": 1.169,
+      "eval_samples_per_second": 8.554,
+      "eval_steps_per_second": 2.566,
+      "step": 270
+    },
+    {
+      "epoch": 45.833333333333336,
+      "grad_norm": 8.784070014953613,
+      "learning_rate": 9.310344827586208e-07,
+      "loss": 5.9684,
+      "step": 275
+    },
+    {
+      "epoch": 46.666666666666664,
+      "grad_norm": 2.9220991134643555,
+      "learning_rate": 7.586206896551725e-07,
+      "loss": 6.2368,
+      "step": 280
+    },
+    {
+      "epoch": 46.666666666666664,
+      "eval_loss": 6.479860782623291,
+      "eval_runtime": 1.1685,
+      "eval_samples_per_second": 8.558,
+      "eval_steps_per_second": 2.567,
+      "step": 280
+    },
+    {
+      "epoch": 47.5,
+      "grad_norm": 1.8880271911621094,
+      "learning_rate": 5.862068965517241e-07,
+      "loss": 6.2116,
+      "step": 285
+    },
+    {
+      "epoch": 48.333333333333336,
+      "grad_norm": 1.3617124557495117,
+      "learning_rate": 4.137931034482759e-07,
+      "loss": 6.0661,
+      "step": 290
+    },
+    {
+      "epoch": 48.333333333333336,
+      "eval_loss": 6.4777703285217285,
+      "eval_runtime": 1.1695,
+      "eval_samples_per_second": 8.551,
+      "eval_steps_per_second": 2.565,
+      "step": 290
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.42413904347136e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-290/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b6a9b3aa55ca9670f8d5427327bb984ce97d529e320a26d7279dacdabf3779
+size 5304

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hpc2hdd/home/xyang346/llama2/llama/llama-2-7b-hf/7B
+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 0.15.1

checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hpc2hdd/home/xyang346/llama2/llama/llama-2-7b-hf/7B",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f6a86c93335376911b5940d4746bd56a20b93092125d5ab73b94e2d0cfa95d
+size 16794200

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4809e7c3326c1e89b6faf134f4edebbebe09829652030511afc10d246d6060
+size 33662074

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96af6430e0949a4cb35632ab8eb41a3283df5b6adfe36a9fbd05173ee192bfc4
+size 14244

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdd241b36133eb74c3c35f3c85da41a8e78b1748c36854794a1b067a117f226
+size 988

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbeda3e49e8eb1752e3b4ebf4359690263b9ea3099b08b4e2156fb98318696ae
+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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "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-300/trainer_state.json

@@ -0,0 +1,694 @@
+{
+  "best_global_step": 300,
+  "best_metric": 6.477707862854004,
+  "best_model_checkpoint": "./llama2-step4/checkpoint-300",
+  "epoch": 50.0,
+  "eval_steps": 10,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 8.655,
+      "step": 5
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 5.807435035705566,
+      "learning_rate": 9e-06,
+      "loss": 8.6675,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 8.762306213378906,
+      "eval_runtime": 1.1641,
+      "eval_samples_per_second": 8.591,
+      "eval_steps_per_second": 2.577,
+      "step": 10
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 4.866168022155762,
+      "learning_rate": 9.862068965517241e-06,
+      "loss": 8.5013,
+      "step": 15
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.68835973739624,
+      "learning_rate": 9.689655172413794e-06,
+      "loss": 8.3972,
+      "step": 20
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 8.49362850189209,
+      "eval_runtime": 1.1628,
+      "eval_samples_per_second": 8.6,
+      "eval_steps_per_second": 2.58,
+      "step": 20
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 7.694056510925293,
+      "learning_rate": 9.517241379310346e-06,
+      "loss": 8.2902,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 6.873053550720215,
+      "learning_rate": 9.344827586206898e-06,
+      "loss": 8.1007,
+      "step": 30
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 8.257888793945312,
+      "eval_runtime": 1.1642,
+      "eval_samples_per_second": 8.59,
+      "eval_steps_per_second": 2.577,
+      "step": 30
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 6.409057140350342,
+      "learning_rate": 9.172413793103448e-06,
+      "loss": 8.0427,
+      "step": 35
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 5.669801235198975,
+      "learning_rate": 9e-06,
+      "loss": 7.9235,
+      "step": 40
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 8.044379234313965,
+      "eval_runtime": 1.1677,
+      "eval_samples_per_second": 8.564,
+      "eval_steps_per_second": 2.569,
+      "step": 40
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 4.534883499145508,
+      "learning_rate": 8.827586206896552e-06,
+      "loss": 7.708,
+      "step": 45
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 4.812073707580566,
+      "learning_rate": 8.655172413793104e-06,
+      "loss": 7.6847,
+      "step": 50
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_loss": 7.831937313079834,
+      "eval_runtime": 1.1678,
+      "eval_samples_per_second": 8.563,
+      "eval_steps_per_second": 2.569,
+      "step": 50
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 4.398963928222656,
+      "learning_rate": 8.482758620689656e-06,
+      "loss": 7.5551,
+      "step": 55
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 6.508076190948486,
+      "learning_rate": 8.310344827586207e-06,
+      "loss": 7.4255,
+      "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 7.6158857345581055,
+      "eval_runtime": 1.1694,
+      "eval_samples_per_second": 8.552,
+      "eval_steps_per_second": 2.566,
+      "step": 60
+    },
+    {
+      "epoch": 10.833333333333334,
+      "grad_norm": 7.493861198425293,
+      "learning_rate": 8.137931034482759e-06,
+      "loss": 7.3105,
+      "step": 65
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 5.808365821838379,
+      "learning_rate": 7.965517241379311e-06,
+      "loss": 7.3573,
+      "step": 70
+    },
+    {
+      "epoch": 11.666666666666666,
+      "eval_loss": 7.405577659606934,
+      "eval_runtime": 1.17,
+      "eval_samples_per_second": 8.547,
+      "eval_steps_per_second": 2.564,
+      "step": 70
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 5.766481399536133,
+      "learning_rate": 7.793103448275863e-06,
+      "loss": 7.0032,
+      "step": 75
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 5.715093612670898,
+      "learning_rate": 7.655172413793104e-06,
+      "loss": 6.9862,
+      "step": 80
+    },
+    {
+      "epoch": 13.333333333333334,
+      "eval_loss": 7.243984222412109,
+      "eval_runtime": 1.1687,
+      "eval_samples_per_second": 8.556,
+      "eval_steps_per_second": 2.567,
+      "step": 80
+    },
+    {
+      "epoch": 14.166666666666666,
+      "grad_norm": 6.890617370605469,
+      "learning_rate": 7.482758620689656e-06,
+      "loss": 6.908,
+      "step": 85
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 6.349765300750732,
+      "learning_rate": 7.310344827586208e-06,
+      "loss": 6.8809,
+      "step": 90
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 7.085419654846191,
+      "eval_runtime": 1.1695,
+      "eval_samples_per_second": 8.55,
+      "eval_steps_per_second": 2.565,
+      "step": 90
+    },
+    {
+      "epoch": 15.833333333333334,
+      "grad_norm": 5.365812301635742,
+      "learning_rate": 7.137931034482759e-06,
+      "loss": 6.7798,
+      "step": 95
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 7.526610374450684,
+      "learning_rate": 6.9655172413793105e-06,
+      "loss": 6.606,
+      "step": 100
+    },
+    {
+      "epoch": 16.666666666666668,
+      "eval_loss": 6.946846961975098,
+      "eval_runtime": 1.1712,
+      "eval_samples_per_second": 8.538,
+      "eval_steps_per_second": 2.561,
+      "step": 100
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 5.357245922088623,
+      "learning_rate": 6.7931034482758626e-06,
+      "loss": 6.7679,
+      "step": 105
+    },
+    {
+      "epoch": 18.333333333333332,
+      "grad_norm": 7.445984363555908,
+      "learning_rate": 6.620689655172415e-06,
+      "loss": 6.4131,
+      "step": 110
+    },
+    {
+      "epoch": 18.333333333333332,
+      "eval_loss": 6.84014892578125,
+      "eval_runtime": 1.1688,
+      "eval_samples_per_second": 8.556,
+      "eval_steps_per_second": 2.567,
+      "step": 110
+    },
+    {
+      "epoch": 19.166666666666668,
+      "grad_norm": 5.064093589782715,
+      "learning_rate": 6.448275862068966e-06,
+      "loss": 6.4387,
+      "step": 115
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 6.121270179748535,
+      "learning_rate": 6.275862068965518e-06,
+      "loss": 6.5389,
+      "step": 120
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 6.772418975830078,
+      "eval_runtime": 1.1693,
+      "eval_samples_per_second": 8.552,
+      "eval_steps_per_second": 2.566,
+      "step": 120
+    },
+    {
+      "epoch": 20.833333333333332,
+      "grad_norm": 4.504457473754883,
+      "learning_rate": 6.103448275862069e-06,
+      "loss": 6.3358,
+      "step": 125
+    },
+    {
+      "epoch": 21.666666666666668,
+      "grad_norm": 2.5440237522125244,
+      "learning_rate": 5.9310344827586205e-06,
+      "loss": 6.4499,
+      "step": 130
+    },
+    {
+      "epoch": 21.666666666666668,
+      "eval_loss": 6.720807075500488,
+      "eval_runtime": 1.169,
+      "eval_samples_per_second": 8.554,
+      "eval_steps_per_second": 2.566,
+      "step": 130
+    },
+    {
+      "epoch": 22.5,
+      "grad_norm": 3.769169807434082,
+      "learning_rate": 5.758620689655173e-06,
+      "loss": 6.3462,
+      "step": 135
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 3.5738062858581543,
+      "learning_rate": 5.586206896551725e-06,
+      "loss": 6.3467,
+      "step": 140
+    },
+    {
+      "epoch": 23.333333333333332,
+      "eval_loss": 6.676053047180176,
+      "eval_runtime": 1.1692,
+      "eval_samples_per_second": 8.553,
+      "eval_steps_per_second": 2.566,
+      "step": 140
+    },
+    {
+      "epoch": 24.166666666666668,
+      "grad_norm": 2.525397539138794,
+      "learning_rate": 5.413793103448276e-06,
+      "loss": 6.4262,
+      "step": 145
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 7.168394565582275,
+      "learning_rate": 5.241379310344829e-06,
+      "loss": 6.2056,
+      "step": 150
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 6.641719818115234,
+      "eval_runtime": 1.1685,
+      "eval_samples_per_second": 8.558,
+      "eval_steps_per_second": 2.567,
+      "step": 150
+    },
+    {
+      "epoch": 25.833333333333332,
+      "grad_norm": 3.0939154624938965,
+      "learning_rate": 5.06896551724138e-06,
+      "loss": 6.1915,
+      "step": 155
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 3.166870355606079,
+      "learning_rate": 4.896551724137931e-06,
+      "loss": 6.3653,
+      "step": 160
+    },
+    {
+      "epoch": 26.666666666666668,
+      "eval_loss": 6.614515781402588,
+      "eval_runtime": 1.1686,
+      "eval_samples_per_second": 8.557,
+      "eval_steps_per_second": 2.567,
+      "step": 160
+    },
+    {
+      "epoch": 27.5,
+      "grad_norm": 4.855230331420898,
+      "learning_rate": 4.724137931034483e-06,
+      "loss": 6.0945,
+      "step": 165
+    },
+    {
+      "epoch": 28.333333333333332,
+      "grad_norm": 4.497844219207764,
+      "learning_rate": 4.551724137931035e-06,
+      "loss": 6.4573,
+      "step": 170
+    },
+    {
+      "epoch": 28.333333333333332,
+      "eval_loss": 6.58881139755249,
+      "eval_runtime": 1.1689,
+      "eval_samples_per_second": 8.555,
+      "eval_steps_per_second": 2.566,
+      "step": 170
+    },
+    {
+      "epoch": 29.166666666666668,
+      "grad_norm": 5.766814231872559,
+      "learning_rate": 4.379310344827587e-06,
+      "loss": 6.25,
+      "step": 175
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 2.9528305530548096,
+      "learning_rate": 4.206896551724138e-06,
+      "loss": 6.1068,
+      "step": 180
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 6.571514129638672,
+      "eval_runtime": 1.1695,
+      "eval_samples_per_second": 8.551,
+      "eval_steps_per_second": 2.565,
+      "step": 180
+    },
+    {
+      "epoch": 30.833333333333332,
+      "grad_norm": 4.210498809814453,
+      "learning_rate": 4.03448275862069e-06,
+      "loss": 6.4773,
+      "step": 185
+    },
+    {
+      "epoch": 31.666666666666668,
+      "grad_norm": 3.7556307315826416,
+      "learning_rate": 3.862068965517241e-06,
+      "loss": 6.1074,
+      "step": 190
+    },
+    {
+      "epoch": 31.666666666666668,
+      "eval_loss": 6.5557684898376465,
+      "eval_runtime": 1.1685,
+      "eval_samples_per_second": 8.558,
+      "eval_steps_per_second": 2.567,
+      "step": 190
+    },
+    {
+      "epoch": 32.5,
+      "grad_norm": 2.2701170444488525,
+      "learning_rate": 3.6896551724137934e-06,
+      "loss": 6.0287,
+      "step": 195
+    },
+    {
+      "epoch": 33.333333333333336,
+      "grad_norm": 3.6891818046569824,
+      "learning_rate": 3.517241379310345e-06,
+      "loss": 6.0739,
+      "step": 200
+    },
+    {
+      "epoch": 33.333333333333336,
+      "eval_loss": 6.541436195373535,
+      "eval_runtime": 1.1714,
+      "eval_samples_per_second": 8.537,
+      "eval_steps_per_second": 2.561,
+      "step": 200
+    },
+    {
+      "epoch": 34.166666666666664,
+      "grad_norm": 3.8515024185180664,
+      "learning_rate": 3.3448275862068967e-06,
+      "loss": 6.2661,
+      "step": 205
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 2.5693061351776123,
+      "learning_rate": 3.172413793103449e-06,
+      "loss": 6.1364,
+      "step": 210
+    },
+    {
+      "epoch": 35.0,
+      "eval_loss": 6.5295000076293945,
+      "eval_runtime": 1.1683,
+      "eval_samples_per_second": 8.559,
+      "eval_steps_per_second": 2.568,
+      "step": 210
+    },
+    {
+      "epoch": 35.833333333333336,
+      "grad_norm": 3.240337610244751,
+      "learning_rate": 3e-06,
+      "loss": 6.4022,
+      "step": 215
+    },
+    {
+      "epoch": 36.666666666666664,
+      "grad_norm": 3.298610210418701,
+      "learning_rate": 2.827586206896552e-06,
+      "loss": 6.0031,
+      "step": 220
+    },
+    {
+      "epoch": 36.666666666666664,
+      "eval_loss": 6.518210411071777,
+      "eval_runtime": 1.1686,
+      "eval_samples_per_second": 8.557,
+      "eval_steps_per_second": 2.567,
+      "step": 220
+    },
+    {
+      "epoch": 37.5,
+      "grad_norm": 2.766157865524292,
+      "learning_rate": 2.6551724137931034e-06,
+      "loss": 5.9806,
+      "step": 225
+    },
+    {
+      "epoch": 38.333333333333336,
+      "grad_norm": 13.019350051879883,
+      "learning_rate": 2.4827586206896555e-06,
+      "loss": 6.1952,
+      "step": 230
+    },
+    {
+      "epoch": 38.333333333333336,
+      "eval_loss": 6.507277011871338,
+      "eval_runtime": 1.168,
+      "eval_samples_per_second": 8.562,
+      "eval_steps_per_second": 2.568,
+      "step": 230
+    },
+    {
+      "epoch": 39.166666666666664,
+      "grad_norm": 7.104252815246582,
+      "learning_rate": 2.310344827586207e-06,
+      "loss": 5.9675,
+      "step": 235
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 2.4420504570007324,
+      "learning_rate": 2.137931034482759e-06,
+      "loss": 6.2932,
+      "step": 240
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 6.499304294586182,
+      "eval_runtime": 1.1692,
+      "eval_samples_per_second": 8.553,
+      "eval_steps_per_second": 2.566,
+      "step": 240
+    },
+    {
+      "epoch": 40.833333333333336,
+      "grad_norm": 4.704829692840576,
+      "learning_rate": 1.9655172413793105e-06,
+      "loss": 6.086,
+      "step": 245
+    },
+    {
+      "epoch": 41.666666666666664,
+      "grad_norm": 8.435072898864746,
+      "learning_rate": 1.7931034482758622e-06,
+      "loss": 5.9113,
+      "step": 250
+    },
+    {
+      "epoch": 41.666666666666664,
+      "eval_loss": 6.4918694496154785,
+      "eval_runtime": 1.1699,
+      "eval_samples_per_second": 8.548,
+      "eval_steps_per_second": 2.564,
+      "step": 250
+    },
+    {
+      "epoch": 42.5,
+      "grad_norm": 8.287426948547363,
+      "learning_rate": 1.6206896551724138e-06,
+      "loss": 6.4342,
+      "step": 255
+    },
+    {
+      "epoch": 43.333333333333336,
+      "grad_norm": 2.980454921722412,
+      "learning_rate": 1.4482758620689657e-06,
+      "loss": 5.8916,
+      "step": 260
+    },
+    {
+      "epoch": 43.333333333333336,
+      "eval_loss": 6.487914085388184,
+      "eval_runtime": 1.1689,
+      "eval_samples_per_second": 8.555,
+      "eval_steps_per_second": 2.567,
+      "step": 260
+    },
+    {
+      "epoch": 44.166666666666664,
+      "grad_norm": 3.5956976413726807,
+      "learning_rate": 1.2758620689655174e-06,
+      "loss": 6.2072,
+      "step": 265
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 3.0276715755462646,
+      "learning_rate": 1.103448275862069e-06,
+      "loss": 6.1625,
+      "step": 270
+    },
+    {
+      "epoch": 45.0,
+      "eval_loss": 6.483713626861572,
+      "eval_runtime": 1.169,
+      "eval_samples_per_second": 8.554,
+      "eval_steps_per_second": 2.566,
+      "step": 270
+    },
+    {
+      "epoch": 45.833333333333336,
+      "grad_norm": 8.784070014953613,
+      "learning_rate": 9.310344827586208e-07,
+      "loss": 5.9684,
+      "step": 275
+    },
+    {
+      "epoch": 46.666666666666664,
+      "grad_norm": 2.9220991134643555,
+      "learning_rate": 7.586206896551725e-07,
+      "loss": 6.2368,
+      "step": 280
+    },
+    {
+      "epoch": 46.666666666666664,
+      "eval_loss": 6.479860782623291,
+      "eval_runtime": 1.1685,
+      "eval_samples_per_second": 8.558,
+      "eval_steps_per_second": 2.567,
+      "step": 280
+    },
+    {
+      "epoch": 47.5,
+      "grad_norm": 1.8880271911621094,
+      "learning_rate": 5.862068965517241e-07,
+      "loss": 6.2116,
+      "step": 285
+    },
+    {
+      "epoch": 48.333333333333336,
+      "grad_norm": 1.3617124557495117,
+      "learning_rate": 4.137931034482759e-07,
+      "loss": 6.0661,
+      "step": 290
+    },
+    {
+      "epoch": 48.333333333333336,
+      "eval_loss": 6.4777703285217285,
+      "eval_runtime": 1.1695,
+      "eval_samples_per_second": 8.551,
+      "eval_steps_per_second": 2.565,
+      "step": 290
+    },
+    {
+      "epoch": 49.166666666666664,
+      "grad_norm": 3.9891092777252197,
+      "learning_rate": 2.413793103448276e-07,
+      "loss": 6.1543,
+      "step": 295
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 3.708580493927002,
+      "learning_rate": 6.896551724137931e-08,
+      "loss": 5.9788,
+      "step": 300
+    },
+    {
+      "epoch": 50.0,
+      "eval_loss": 6.477707862854004,
+      "eval_runtime": 1.1698,
+      "eval_samples_per_second": 8.548,
+      "eval_steps_per_second": 2.565,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.7491093553152e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b6a9b3aa55ca9670f8d5427327bb984ce97d529e320a26d7279dacdabf3779
+size 5304

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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "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
+}