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": [
+    "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 sha256:1b873794793689516c5f9b6fe9f19e2f6f1055585496e125bd7e1b64f80120ca
+size 16794200

checkpoint-2500/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-2500/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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b873794793689516c5f9b6fe9f19e2f6f1055585496e125bd7e1b64f80120ca
+size 16794200

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6241f46eca3946d363c6812f88a1ea5ab39248137406c04f0fb85e9eb9f5d1d
+size 33662074

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e1e55b2a0c8bc18bd768d33a89237dea74f4ee907d13006c7a12b6ccb1453c
+size 14244

checkpoint-2500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601ce08c79a2eaeca202eba2cb6e92b2fca131ce81001cf02dfa76571baaa630
+size 988

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5650b7a6656194ab46bbbbc7dc3ed0ee154453c5b8b70986b20c0ede2a874311
+size 1064

checkpoint-2500/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-2500/tokenizer.model

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

checkpoint-2500/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-2500/trainer_state.json

@@ -0,0 +1,584 @@
+{
+  "best_global_step": 2500,
+  "best_metric": 0.7841161489486694,
+  "best_model_checkpoint": "./llama2-m2/checkpoint-2500",
+  "epoch": 2.9767718880285887,
+  "eval_steps": 100,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05955926146515783,
+      "grad_norm": 11.590325355529785,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 3.0703,
+      "step": 50
+    },
+    {
+      "epoch": 0.11911852293031566,
+      "grad_norm": 6.117842197418213,
+      "learning_rate": 9.9e-06,
+      "loss": 2.3868,
+      "step": 100
+    },
+    {
+      "epoch": 0.11911852293031566,
+      "eval_loss": 1.5943528413772583,
+      "eval_runtime": 86.9995,
+      "eval_samples_per_second": 8.081,
+      "eval_steps_per_second": 2.023,
+      "step": 100
+    },
+    {
+      "epoch": 0.1786777843954735,
+      "grad_norm": 0.4276258051395416,
+      "learning_rate": 9.797269342159703e-06,
+      "loss": 1.1152,
+      "step": 150
+    },
+    {
+      "epoch": 0.23823704586063132,
+      "grad_norm": 0.34813204407691956,
+      "learning_rate": 9.590401323955318e-06,
+      "loss": 0.9458,
+      "step": 200
+    },
+    {
+      "epoch": 0.23823704586063132,
+      "eval_loss": 0.9201429486274719,
+      "eval_runtime": 86.8761,
+      "eval_samples_per_second": 8.092,
+      "eval_steps_per_second": 2.026,
+      "step": 200
+    },
+    {
+      "epoch": 0.29779630732578916,
+      "grad_norm": 0.31664666533470154,
+      "learning_rate": 9.383533305750931e-06,
+      "loss": 0.8754,
+      "step": 250
+    },
+    {
+      "epoch": 0.357355568790947,
+      "grad_norm": 0.3039833903312683,
+      "learning_rate": 9.176665287546546e-06,
+      "loss": 0.8236,
+      "step": 300
+    },
+    {
+      "epoch": 0.357355568790947,
+      "eval_loss": 0.8294563293457031,
+      "eval_runtime": 86.6916,
+      "eval_samples_per_second": 8.109,
+      "eval_steps_per_second": 2.03,
+      "step": 300
+    },
+    {
+      "epoch": 0.4169148302561048,
+      "grad_norm": 0.3569670021533966,
+      "learning_rate": 8.969797269342161e-06,
+      "loss": 0.7643,
+      "step": 350
+    },
+    {
+      "epoch": 0.47647409172126265,
+      "grad_norm": 0.4587797224521637,
+      "learning_rate": 8.762929251137776e-06,
+      "loss": 0.7638,
+      "step": 400
+    },
+    {
+      "epoch": 0.47647409172126265,
+      "eval_loss": 0.8007138967514038,
+      "eval_runtime": 86.7325,
+      "eval_samples_per_second": 8.105,
+      "eval_steps_per_second": 2.029,
+      "step": 400
+    },
+    {
+      "epoch": 0.5360333531864205,
+      "grad_norm": 0.2903870940208435,
+      "learning_rate": 8.556061232933389e-06,
+      "loss": 0.7505,
+      "step": 450
+    },
+    {
+      "epoch": 0.5955926146515783,
+      "grad_norm": 0.39271315932273865,
+      "learning_rate": 8.349193214729004e-06,
+      "loss": 0.7773,
+      "step": 500
+    },
+    {
+      "epoch": 0.5955926146515783,
+      "eval_loss": 0.7964405417442322,
+      "eval_runtime": 86.7496,
+      "eval_samples_per_second": 8.104,
+      "eval_steps_per_second": 2.029,
+      "step": 500
+    },
+    {
+      "epoch": 0.6551518761167362,
+      "grad_norm": 0.2611350119113922,
+      "learning_rate": 8.142325196524617e-06,
+      "loss": 0.7339,
+      "step": 550
+    },
+    {
+      "epoch": 0.714711137581894,
+      "grad_norm": 0.3096601665019989,
+      "learning_rate": 7.935457178320233e-06,
+      "loss": 0.7867,
+      "step": 600
+    },
+    {
+      "epoch": 0.714711137581894,
+      "eval_loss": 0.7935438752174377,
+      "eval_runtime": 86.8192,
+      "eval_samples_per_second": 8.097,
+      "eval_steps_per_second": 2.027,
+      "step": 600
+    },
+    {
+      "epoch": 0.7742703990470519,
+      "grad_norm": 0.28062084317207336,
+      "learning_rate": 7.728589160115847e-06,
+      "loss": 0.7642,
+      "step": 650
+    },
+    {
+      "epoch": 0.8338296605122096,
+      "grad_norm": 0.2916211783885956,
+      "learning_rate": 7.521721141911461e-06,
+      "loss": 0.7436,
+      "step": 700
+    },
+    {
+      "epoch": 0.8338296605122096,
+      "eval_loss": 0.7918882369995117,
+      "eval_runtime": 86.8706,
+      "eval_samples_per_second": 8.092,
+      "eval_steps_per_second": 2.026,
+      "step": 700
+    },
+    {
+      "epoch": 0.8933889219773675,
+      "grad_norm": 0.4260661005973816,
+      "learning_rate": 7.3148531237070755e-06,
+      "loss": 0.7944,
+      "step": 750
+    },
+    {
+      "epoch": 0.9529481834425253,
+      "grad_norm": 0.3311309218406677,
+      "learning_rate": 7.1079851055026895e-06,
+      "loss": 0.7618,
+      "step": 800
+    },
+    {
+      "epoch": 0.9529481834425253,
+      "eval_loss": 0.7905948758125305,
+      "eval_runtime": 86.7293,
+      "eval_samples_per_second": 8.106,
+      "eval_steps_per_second": 2.029,
+      "step": 800
+    },
+    {
+      "epoch": 1.0119118522930315,
+      "grad_norm": 0.33902204036712646,
+      "learning_rate": 6.901117087298304e-06,
+      "loss": 0.7565,
+      "step": 850
+    },
+    {
+      "epoch": 1.0714711137581894,
+      "grad_norm": 0.3156481981277466,
+      "learning_rate": 6.694249069093918e-06,
+      "loss": 0.7834,
+      "step": 900
+    },
+    {
+      "epoch": 1.0714711137581894,
+      "eval_loss": 0.789471447467804,
+      "eval_runtime": 86.7639,
+      "eval_samples_per_second": 8.102,
+      "eval_steps_per_second": 2.028,
+      "step": 900
+    },
+    {
+      "epoch": 1.1310303752233473,
+      "grad_norm": 0.29626569151878357,
+      "learning_rate": 6.487381050889533e-06,
+      "loss": 0.7636,
+      "step": 950
+    },
+    {
+      "epoch": 1.1905896366885051,
+      "grad_norm": 0.32058003544807434,
+      "learning_rate": 6.280513032685147e-06,
+      "loss": 0.7588,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1905896366885051,
+      "eval_loss": 0.7887451648712158,
+      "eval_runtime": 86.8029,
+      "eval_samples_per_second": 8.099,
+      "eval_steps_per_second": 2.028,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2501488981536628,
+      "grad_norm": 0.3029298484325409,
+      "learning_rate": 6.073645014480761e-06,
+      "loss": 0.7651,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3097081596188207,
+      "grad_norm": 0.30075645446777344,
+      "learning_rate": 5.866776996276376e-06,
+      "loss": 0.747,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3097081596188207,
+      "eval_loss": 0.7880399227142334,
+      "eval_runtime": 86.7707,
+      "eval_samples_per_second": 8.102,
+      "eval_steps_per_second": 2.028,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3692674210839786,
+      "grad_norm": 0.30230703949928284,
+      "learning_rate": 5.659908978071991e-06,
+      "loss": 0.7694,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4288266825491365,
+      "grad_norm": 0.2981889545917511,
+      "learning_rate": 5.453040959867605e-06,
+      "loss": 0.7546,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4288266825491365,
+      "eval_loss": 0.7873143553733826,
+      "eval_runtime": 86.9249,
+      "eval_samples_per_second": 8.087,
+      "eval_steps_per_second": 2.025,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4883859440142944,
+      "grad_norm": 0.33295580744743347,
+      "learning_rate": 5.246172941663219e-06,
+      "loss": 0.7356,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547945205479452,
+      "grad_norm": 0.2881334125995636,
+      "learning_rate": 5.039304923458833e-06,
+      "loss": 0.7616,
+      "step": 1300
+    },
+    {
+      "epoch": 1.547945205479452,
+      "eval_loss": 0.7868330478668213,
+      "eval_runtime": 86.9371,
+      "eval_samples_per_second": 8.086,
+      "eval_steps_per_second": 2.024,
+      "step": 1300
+    },
+    {
+      "epoch": 1.60750446694461,
+      "grad_norm": 0.42549142241477966,
+      "learning_rate": 4.832436905254448e-06,
+      "loss": 0.7613,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6670637284097678,
+      "grad_norm": 0.32537880539894104,
+      "learning_rate": 4.625568887050063e-06,
+      "loss": 0.777,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6670637284097678,
+      "eval_loss": 0.7863583564758301,
+      "eval_runtime": 86.9105,
+      "eval_samples_per_second": 8.089,
+      "eval_steps_per_second": 2.025,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7266229898749255,
+      "grad_norm": 0.31612130999565125,
+      "learning_rate": 4.418700868845677e-06,
+      "loss": 0.7123,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7861822513400833,
+      "grad_norm": 0.39497706294059753,
+      "learning_rate": 4.211832850641292e-06,
+      "loss": 0.7999,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7861822513400833,
+      "eval_loss": 0.7859570980072021,
+      "eval_runtime": 86.7739,
+      "eval_samples_per_second": 8.102,
+      "eval_steps_per_second": 2.028,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8457415128052412,
+      "grad_norm": 0.3905975818634033,
+      "learning_rate": 4.004964832436906e-06,
+      "loss": 0.7105,
+      "step": 1550
+    },
+    {
+      "epoch": 1.905300774270399,
+      "grad_norm": 0.3420596718788147,
+      "learning_rate": 3.7980968142325196e-06,
+      "loss": 0.7735,
+      "step": 1600
+    },
+    {
+      "epoch": 1.905300774270399,
+      "eval_loss": 0.7855594754219055,
+      "eval_runtime": 86.9977,
+      "eval_samples_per_second": 8.081,
+      "eval_steps_per_second": 2.023,
+      "step": 1600
+    },
+    {
+      "epoch": 1.964860035735557,
+      "grad_norm": 0.2925880551338196,
+      "learning_rate": 3.5912287960281345e-06,
+      "loss": 0.7675,
+      "step": 1650
+    },
+    {
+      "epoch": 2.023823704586063,
+      "grad_norm": 0.42387983202934265,
+      "learning_rate": 3.3843607778237485e-06,
+      "loss": 0.7679,
+      "step": 1700
+    },
+    {
+      "epoch": 2.023823704586063,
+      "eval_loss": 0.7852116227149963,
+      "eval_runtime": 86.7932,
+      "eval_samples_per_second": 8.1,
+      "eval_steps_per_second": 2.028,
+      "step": 1700
+    },
+    {
+      "epoch": 2.083382966051221,
+      "grad_norm": 0.3012678325176239,
+      "learning_rate": 3.1774927596193634e-06,
+      "loss": 0.7529,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1429422275163788,
+      "grad_norm": 0.3647378385066986,
+      "learning_rate": 2.9706247414149774e-06,
+      "loss": 0.7772,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1429422275163788,
+      "eval_loss": 0.7850247025489807,
+      "eval_runtime": 86.7181,
+      "eval_samples_per_second": 8.107,
+      "eval_steps_per_second": 2.03,
+      "step": 1800
+    },
+    {
+      "epoch": 2.202501488981537,
+      "grad_norm": 0.30863115191459656,
+      "learning_rate": 2.763756723210592e-06,
+      "loss": 0.7485,
+      "step": 1850
+    },
+    {
+      "epoch": 2.2620607504466945,
+      "grad_norm": 0.3829723298549652,
+      "learning_rate": 2.5568887050062062e-06,
+      "loss": 0.7449,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2620607504466945,
+      "eval_loss": 0.7847884893417358,
+      "eval_runtime": 86.725,
+      "eval_samples_per_second": 8.106,
+      "eval_steps_per_second": 2.029,
+      "step": 1900
+    },
+    {
+      "epoch": 2.321620011911852,
+      "grad_norm": 0.3733135759830475,
+      "learning_rate": 2.3500206868018207e-06,
+      "loss": 0.7508,
+      "step": 1950
+    },
+    {
+      "epoch": 2.3811792733770103,
+      "grad_norm": 0.37344199419021606,
+      "learning_rate": 2.143152668597435e-06,
+      "loss": 0.7509,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3811792733770103,
+      "eval_loss": 0.7846249938011169,
+      "eval_runtime": 86.7361,
+      "eval_samples_per_second": 8.105,
+      "eval_steps_per_second": 2.029,
+      "step": 2000
+    },
+    {
+      "epoch": 2.440738534842168,
+      "grad_norm": 0.46035104990005493,
+      "learning_rate": 1.9362846503930496e-06,
+      "loss": 0.7901,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5002977963073256,
+      "grad_norm": 0.31786802411079407,
+      "learning_rate": 1.7294166321886638e-06,
+      "loss": 0.7654,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5002977963073256,
+      "eval_loss": 0.7844468951225281,
+      "eval_runtime": 86.7628,
+      "eval_samples_per_second": 8.103,
+      "eval_steps_per_second": 2.029,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5598570577724837,
+      "grad_norm": 0.337811678647995,
+      "learning_rate": 1.5225486139842782e-06,
+      "loss": 0.7524,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6194163192376414,
+      "grad_norm": 0.29232126474380493,
+      "learning_rate": 1.3156805957798926e-06,
+      "loss": 0.7279,
+      "step": 2200
+    },
+    {
+      "epoch": 2.6194163192376414,
+      "eval_loss": 0.7843312621116638,
+      "eval_runtime": 86.7533,
+      "eval_samples_per_second": 8.103,
+      "eval_steps_per_second": 2.029,
+      "step": 2200
+    },
+    {
+      "epoch": 2.678975580702799,
+      "grad_norm": 0.4377705454826355,
+      "learning_rate": 1.1088125775755069e-06,
+      "loss": 0.7593,
+      "step": 2250
+    },
+    {
+      "epoch": 2.738534842167957,
+      "grad_norm": 0.36447674036026,
+      "learning_rate": 9.019445593711212e-07,
+      "loss": 0.7523,
+      "step": 2300
+    },
+    {
+      "epoch": 2.738534842167957,
+      "eval_loss": 0.7842342257499695,
+      "eval_runtime": 86.8097,
+      "eval_samples_per_second": 8.098,
+      "eval_steps_per_second": 2.027,
+      "step": 2300
+    },
+    {
+      "epoch": 2.798094103633115,
+      "grad_norm": 0.38712531328201294,
+      "learning_rate": 6.950765411667356e-07,
+      "loss": 0.7347,
+      "step": 2350
+    },
+    {
+      "epoch": 2.857653365098273,
+      "grad_norm": 0.34733325242996216,
+      "learning_rate": 4.882085229623501e-07,
+      "loss": 0.7605,
+      "step": 2400
+    },
+    {
+      "epoch": 2.857653365098273,
+      "eval_loss": 0.7841441035270691,
+      "eval_runtime": 86.8339,
+      "eval_samples_per_second": 8.096,
+      "eval_steps_per_second": 2.027,
+      "step": 2400
+    },
+    {
+      "epoch": 2.9172126265634306,
+      "grad_norm": 0.3819723129272461,
+      "learning_rate": 2.8134050475796445e-07,
+      "loss": 0.7412,
+      "step": 2450
+    },
+    {
+      "epoch": 2.9767718880285887,
+      "grad_norm": 0.3409363329410553,
+      "learning_rate": 7.447248655357883e-08,
+      "loss": 0.7425,
+      "step": 2500
+    },
+    {
+      "epoch": 2.9767718880285887,
+      "eval_loss": 0.7841161489486694,
+      "eval_runtime": 87.2598,
+      "eval_samples_per_second": 8.056,
+      "eval_steps_per_second": 2.017,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.120601880087757e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93397caa9376b8eea4ec6b2e017638fbcd88c220589b7cb21e7657564bf41c5
+size 5304

checkpoint-2517/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-2517/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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2517/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369a6bf7ee643e3ba50fd638abe939141e191f2014624e286b7e466098b4ae14
+size 16794200

checkpoint-2517/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704dc3b8caddfde87937ed6b9d8684dc70a49ffa0de01ba1a197121afeb809ae
+size 33662074

checkpoint-2517/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828c7d933353ef81fc8594deed2134690a2af46b85bf3d554aa09aee813e6c1b
+size 14244

checkpoint-2517/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb761d3cc1874f86b8b2f5c74b835c73b0addb9152f406fdd449327345f7b1e2
+size 988

checkpoint-2517/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ddfb35a3498eade0cc73c7b00f4616bcaf4ec172aaa78b0fcbe453f538bf41
+size 1064

checkpoint-2517/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-2517/tokenizer.model

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

checkpoint-2517/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-2517/trainer_state.json

@@ -0,0 +1,584 @@
+{
+  "best_global_step": 2500,
+  "best_metric": 0.7841161489486694,
+  "best_model_checkpoint": "./llama2-m2/checkpoint-2500",
+  "epoch": 2.997022036926742,
+  "eval_steps": 100,
+  "global_step": 2517,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05955926146515783,
+      "grad_norm": 11.590325355529785,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 3.0703,
+      "step": 50
+    },
+    {
+      "epoch": 0.11911852293031566,
+      "grad_norm": 6.117842197418213,
+      "learning_rate": 9.9e-06,
+      "loss": 2.3868,
+      "step": 100
+    },
+    {
+      "epoch": 0.11911852293031566,
+      "eval_loss": 1.5943528413772583,
+      "eval_runtime": 86.9995,
+      "eval_samples_per_second": 8.081,
+      "eval_steps_per_second": 2.023,
+      "step": 100
+    },
+    {
+      "epoch": 0.1786777843954735,
+      "grad_norm": 0.4276258051395416,
+      "learning_rate": 9.797269342159703e-06,
+      "loss": 1.1152,
+      "step": 150
+    },
+    {
+      "epoch": 0.23823704586063132,
+      "grad_norm": 0.34813204407691956,
+      "learning_rate": 9.590401323955318e-06,
+      "loss": 0.9458,
+      "step": 200
+    },
+    {
+      "epoch": 0.23823704586063132,
+      "eval_loss": 0.9201429486274719,
+      "eval_runtime": 86.8761,
+      "eval_samples_per_second": 8.092,
+      "eval_steps_per_second": 2.026,
+      "step": 200
+    },
+    {
+      "epoch": 0.29779630732578916,
+      "grad_norm": 0.31664666533470154,
+      "learning_rate": 9.383533305750931e-06,
+      "loss": 0.8754,
+      "step": 250
+    },
+    {
+      "epoch": 0.357355568790947,
+      "grad_norm": 0.3039833903312683,
+      "learning_rate": 9.176665287546546e-06,
+      "loss": 0.8236,
+      "step": 300
+    },
+    {
+      "epoch": 0.357355568790947,
+      "eval_loss": 0.8294563293457031,
+      "eval_runtime": 86.6916,
+      "eval_samples_per_second": 8.109,
+      "eval_steps_per_second": 2.03,
+      "step": 300
+    },
+    {
+      "epoch": 0.4169148302561048,
+      "grad_norm": 0.3569670021533966,
+      "learning_rate": 8.969797269342161e-06,
+      "loss": 0.7643,
+      "step": 350
+    },
+    {
+      "epoch": 0.47647409172126265,
+      "grad_norm": 0.4587797224521637,
+      "learning_rate": 8.762929251137776e-06,
+      "loss": 0.7638,
+      "step": 400
+    },
+    {
+      "epoch": 0.47647409172126265,
+      "eval_loss": 0.8007138967514038,
+      "eval_runtime": 86.7325,
+      "eval_samples_per_second": 8.105,
+      "eval_steps_per_second": 2.029,
+      "step": 400
+    },
+    {
+      "epoch": 0.5360333531864205,
+      "grad_norm": 0.2903870940208435,
+      "learning_rate": 8.556061232933389e-06,
+      "loss": 0.7505,
+      "step": 450
+    },
+    {
+      "epoch": 0.5955926146515783,
+      "grad_norm": 0.39271315932273865,
+      "learning_rate": 8.349193214729004e-06,
+      "loss": 0.7773,
+      "step": 500
+    },
+    {
+      "epoch": 0.5955926146515783,
+      "eval_loss": 0.7964405417442322,
+      "eval_runtime": 86.7496,
+      "eval_samples_per_second": 8.104,
+      "eval_steps_per_second": 2.029,
+      "step": 500
+    },
+    {
+      "epoch": 0.6551518761167362,
+      "grad_norm": 0.2611350119113922,
+      "learning_rate": 8.142325196524617e-06,
+      "loss": 0.7339,
+      "step": 550
+    },
+    {
+      "epoch": 0.714711137581894,
+      "grad_norm": 0.3096601665019989,
+      "learning_rate": 7.935457178320233e-06,
+      "loss": 0.7867,
+      "step": 600
+    },
+    {
+      "epoch": 0.714711137581894,
+      "eval_loss": 0.7935438752174377,
+      "eval_runtime": 86.8192,
+      "eval_samples_per_second": 8.097,
+      "eval_steps_per_second": 2.027,
+      "step": 600
+    },
+    {
+      "epoch": 0.7742703990470519,
+      "grad_norm": 0.28062084317207336,
+      "learning_rate": 7.728589160115847e-06,
+      "loss": 0.7642,
+      "step": 650
+    },
+    {
+      "epoch": 0.8338296605122096,
+      "grad_norm": 0.2916211783885956,
+      "learning_rate": 7.521721141911461e-06,
+      "loss": 0.7436,
+      "step": 700
+    },
+    {
+      "epoch": 0.8338296605122096,
+      "eval_loss": 0.7918882369995117,
+      "eval_runtime": 86.8706,
+      "eval_samples_per_second": 8.092,
+      "eval_steps_per_second": 2.026,
+      "step": 700
+    },
+    {
+      "epoch": 0.8933889219773675,
+      "grad_norm": 0.4260661005973816,
+      "learning_rate": 7.3148531237070755e-06,
+      "loss": 0.7944,
+      "step": 750
+    },
+    {
+      "epoch": 0.9529481834425253,
+      "grad_norm": 0.3311309218406677,
+      "learning_rate": 7.1079851055026895e-06,
+      "loss": 0.7618,
+      "step": 800
+    },
+    {
+      "epoch": 0.9529481834425253,
+      "eval_loss": 0.7905948758125305,
+      "eval_runtime": 86.7293,
+      "eval_samples_per_second": 8.106,
+      "eval_steps_per_second": 2.029,
+      "step": 800
+    },
+    {
+      "epoch": 1.0119118522930315,
+      "grad_norm": 0.33902204036712646,
+      "learning_rate": 6.901117087298304e-06,
+      "loss": 0.7565,
+      "step": 850
+    },
+    {
+      "epoch": 1.0714711137581894,
+      "grad_norm": 0.3156481981277466,
+      "learning_rate": 6.694249069093918e-06,
+      "loss": 0.7834,
+      "step": 900
+    },
+    {
+      "epoch": 1.0714711137581894,
+      "eval_loss": 0.789471447467804,
+      "eval_runtime": 86.7639,
+      "eval_samples_per_second": 8.102,
+      "eval_steps_per_second": 2.028,
+      "step": 900
+    },
+    {
+      "epoch": 1.1310303752233473,
+      "grad_norm": 0.29626569151878357,
+      "learning_rate": 6.487381050889533e-06,
+      "loss": 0.7636,
+      "step": 950
+    },
+    {
+      "epoch": 1.1905896366885051,
+      "grad_norm": 0.32058003544807434,
+      "learning_rate": 6.280513032685147e-06,
+      "loss": 0.7588,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1905896366885051,
+      "eval_loss": 0.7887451648712158,
+      "eval_runtime": 86.8029,
+      "eval_samples_per_second": 8.099,
+      "eval_steps_per_second": 2.028,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2501488981536628,
+      "grad_norm": 0.3029298484325409,
+      "learning_rate": 6.073645014480761e-06,
+      "loss": 0.7651,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3097081596188207,
+      "grad_norm": 0.30075645446777344,
+      "learning_rate": 5.866776996276376e-06,
+      "loss": 0.747,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3097081596188207,
+      "eval_loss": 0.7880399227142334,
+      "eval_runtime": 86.7707,
+      "eval_samples_per_second": 8.102,
+      "eval_steps_per_second": 2.028,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3692674210839786,
+      "grad_norm": 0.30230703949928284,
+      "learning_rate": 5.659908978071991e-06,
+      "loss": 0.7694,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4288266825491365,
+      "grad_norm": 0.2981889545917511,
+      "learning_rate": 5.453040959867605e-06,
+      "loss": 0.7546,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4288266825491365,
+      "eval_loss": 0.7873143553733826,
+      "eval_runtime": 86.9249,
+      "eval_samples_per_second": 8.087,
+      "eval_steps_per_second": 2.025,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4883859440142944,
+      "grad_norm": 0.33295580744743347,
+      "learning_rate": 5.246172941663219e-06,
+      "loss": 0.7356,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547945205479452,
+      "grad_norm": 0.2881334125995636,
+      "learning_rate": 5.039304923458833e-06,
+      "loss": 0.7616,
+      "step": 1300
+    },
+    {
+      "epoch": 1.547945205479452,
+      "eval_loss": 0.7868330478668213,
+      "eval_runtime": 86.9371,
+      "eval_samples_per_second": 8.086,
+      "eval_steps_per_second": 2.024,
+      "step": 1300
+    },
+    {
+      "epoch": 1.60750446694461,
+      "grad_norm": 0.42549142241477966,
+      "learning_rate": 4.832436905254448e-06,
+      "loss": 0.7613,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6670637284097678,
+      "grad_norm": 0.32537880539894104,
+      "learning_rate": 4.625568887050063e-06,
+      "loss": 0.777,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6670637284097678,
+      "eval_loss": 0.7863583564758301,
+      "eval_runtime": 86.9105,
+      "eval_samples_per_second": 8.089,
+      "eval_steps_per_second": 2.025,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7266229898749255,
+      "grad_norm": 0.31612130999565125,
+      "learning_rate": 4.418700868845677e-06,
+      "loss": 0.7123,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7861822513400833,
+      "grad_norm": 0.39497706294059753,
+      "learning_rate": 4.211832850641292e-06,
+      "loss": 0.7999,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7861822513400833,
+      "eval_loss": 0.7859570980072021,
+      "eval_runtime": 86.7739,
+      "eval_samples_per_second": 8.102,
+      "eval_steps_per_second": 2.028,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8457415128052412,
+      "grad_norm": 0.3905975818634033,
+      "learning_rate": 4.004964832436906e-06,
+      "loss": 0.7105,
+      "step": 1550
+    },
+    {
+      "epoch": 1.905300774270399,
+      "grad_norm": 0.3420596718788147,
+      "learning_rate": 3.7980968142325196e-06,
+      "loss": 0.7735,
+      "step": 1600
+    },
+    {
+      "epoch": 1.905300774270399,
+      "eval_loss": 0.7855594754219055,
+      "eval_runtime": 86.9977,
+      "eval_samples_per_second": 8.081,
+      "eval_steps_per_second": 2.023,
+      "step": 1600
+    },
+    {
+      "epoch": 1.964860035735557,
+      "grad_norm": 0.2925880551338196,
+      "learning_rate": 3.5912287960281345e-06,
+      "loss": 0.7675,
+      "step": 1650
+    },
+    {
+      "epoch": 2.023823704586063,
+      "grad_norm": 0.42387983202934265,
+      "learning_rate": 3.3843607778237485e-06,
+      "loss": 0.7679,
+      "step": 1700
+    },
+    {
+      "epoch": 2.023823704586063,
+      "eval_loss": 0.7852116227149963,
+      "eval_runtime": 86.7932,
+      "eval_samples_per_second": 8.1,
+      "eval_steps_per_second": 2.028,
+      "step": 1700
+    },
+    {
+      "epoch": 2.083382966051221,
+      "grad_norm": 0.3012678325176239,
+      "learning_rate": 3.1774927596193634e-06,
+      "loss": 0.7529,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1429422275163788,
+      "grad_norm": 0.3647378385066986,
+      "learning_rate": 2.9706247414149774e-06,
+      "loss": 0.7772,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1429422275163788,
+      "eval_loss": 0.7850247025489807,
+      "eval_runtime": 86.7181,
+      "eval_samples_per_second": 8.107,
+      "eval_steps_per_second": 2.03,
+      "step": 1800
+    },
+    {
+      "epoch": 2.202501488981537,
+      "grad_norm": 0.30863115191459656,
+      "learning_rate": 2.763756723210592e-06,
+      "loss": 0.7485,
+      "step": 1850
+    },
+    {
+      "epoch": 2.2620607504466945,
+      "grad_norm": 0.3829723298549652,
+      "learning_rate": 2.5568887050062062e-06,
+      "loss": 0.7449,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2620607504466945,
+      "eval_loss": 0.7847884893417358,
+      "eval_runtime": 86.725,
+      "eval_samples_per_second": 8.106,
+      "eval_steps_per_second": 2.029,
+      "step": 1900
+    },
+    {
+      "epoch": 2.321620011911852,
+      "grad_norm": 0.3733135759830475,
+      "learning_rate": 2.3500206868018207e-06,
+      "loss": 0.7508,
+      "step": 1950
+    },
+    {
+      "epoch": 2.3811792733770103,
+      "grad_norm": 0.37344199419021606,
+      "learning_rate": 2.143152668597435e-06,
+      "loss": 0.7509,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3811792733770103,
+      "eval_loss": 0.7846249938011169,
+      "eval_runtime": 86.7361,
+      "eval_samples_per_second": 8.105,
+      "eval_steps_per_second": 2.029,
+      "step": 2000
+    },
+    {
+      "epoch": 2.440738534842168,
+      "grad_norm": 0.46035104990005493,
+      "learning_rate": 1.9362846503930496e-06,
+      "loss": 0.7901,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5002977963073256,
+      "grad_norm": 0.31786802411079407,
+      "learning_rate": 1.7294166321886638e-06,
+      "loss": 0.7654,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5002977963073256,
+      "eval_loss": 0.7844468951225281,
+      "eval_runtime": 86.7628,
+      "eval_samples_per_second": 8.103,
+      "eval_steps_per_second": 2.029,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5598570577724837,
+      "grad_norm": 0.337811678647995,
+      "learning_rate": 1.5225486139842782e-06,
+      "loss": 0.7524,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6194163192376414,
+      "grad_norm": 0.29232126474380493,
+      "learning_rate": 1.3156805957798926e-06,
+      "loss": 0.7279,
+      "step": 2200
+    },
+    {
+      "epoch": 2.6194163192376414,
+      "eval_loss": 0.7843312621116638,
+      "eval_runtime": 86.7533,
+      "eval_samples_per_second": 8.103,
+      "eval_steps_per_second": 2.029,
+      "step": 2200
+    },
+    {
+      "epoch": 2.678975580702799,
+      "grad_norm": 0.4377705454826355,
+      "learning_rate": 1.1088125775755069e-06,
+      "loss": 0.7593,
+      "step": 2250
+    },
+    {
+      "epoch": 2.738534842167957,
+      "grad_norm": 0.36447674036026,
+      "learning_rate": 9.019445593711212e-07,
+      "loss": 0.7523,
+      "step": 2300
+    },
+    {
+      "epoch": 2.738534842167957,
+      "eval_loss": 0.7842342257499695,
+      "eval_runtime": 86.8097,
+      "eval_samples_per_second": 8.098,
+      "eval_steps_per_second": 2.027,
+      "step": 2300
+    },
+    {
+      "epoch": 2.798094103633115,
+      "grad_norm": 0.38712531328201294,
+      "learning_rate": 6.950765411667356e-07,
+      "loss": 0.7347,
+      "step": 2350
+    },
+    {
+      "epoch": 2.857653365098273,
+      "grad_norm": 0.34733325242996216,
+      "learning_rate": 4.882085229623501e-07,
+      "loss": 0.7605,
+      "step": 2400
+    },
+    {
+      "epoch": 2.857653365098273,
+      "eval_loss": 0.7841441035270691,
+      "eval_runtime": 86.8339,
+      "eval_samples_per_second": 8.096,
+      "eval_steps_per_second": 2.027,
+      "step": 2400
+    },
+    {
+      "epoch": 2.9172126265634306,
+      "grad_norm": 0.3819723129272461,
+      "learning_rate": 2.8134050475796445e-07,
+      "loss": 0.7412,
+      "step": 2450
+    },
+    {
+      "epoch": 2.9767718880285887,
+      "grad_norm": 0.3409363329410553,
+      "learning_rate": 7.447248655357883e-08,
+      "loss": 0.7425,
+      "step": 2500
+    },
+    {
+      "epoch": 2.9767718880285887,
+      "eval_loss": 0.7841161489486694,
+      "eval_runtime": 87.2598,
+      "eval_samples_per_second": 8.056,
+      "eval_steps_per_second": 2.017,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.17584683310121e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2517/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93397caa9376b8eea4ec6b2e017638fbcd88c220589b7cb21e7657564bf41c5
+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
+}