Upload fine-tuned LLaMA-2-7B emotion analysis model

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+hallucination_analysis.png filter=lfs diff=lfs merge=lfs -text
+performance_metrics.png filter=lfs diff=lfs merge=lfs -text
+training_curves.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,124 @@
+---
+license: apache-2.0
+base_model: NousResearch/Llama-2-7b-chat-hf
+tags:
+- llama2
+- emotion-analysis
+- activity-context
+- fine-tuned
+- goemotions
+datasets:
+- AA65327/GoEmotions_Alpaca_Final
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# LLaMA-2-7B Emotion Analysis with Activity Context
+
+## Model Description
+
+This model is a fine-tuned version of NousResearch/Llama-2-7b-chat-hf on the GoEmotions dataset with activity context integration. 
+It analyzes emotions in text while considering the user's recent activity patterns to provide more contextual insights.
+
+## Training Details
+
+### Training Data
+- **Dataset**: AA65327/GoEmotions_Alpaca_Final
+- **Training samples**: N/A
+- **Validation samples**: N/A
+
+### Training Configuration
+- **Base model**: NousResearch/Llama-2-7b-chat-hf
+- **Training epochs**: 1
+- **Batch size**: 1
+- **Learning rate**: 0.0002
+- **LoRA rank**: 8
+- **LoRA alpha**: 32
+
+## Performance Metrics
+
+### Evaluation Results
+- **Perplexity**: 26.08
+- **ROUGE-1**: 0.190
+- **ROUGE-2**: 0.170
+- **ROUGE-L**: 0.190
+- **BLEU Score**: 8.039
+- **Inference Speed**: 1.3 tokens/sec
+- **Hallucination Rate**: 2.400
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+# Load model and tokenizer
+base_model = AutoModelForCausalLM.from_pretrained(
+    "NousResearch/Llama-2-7b-chat-hf",
+    load_in_4bit=True,
+    device_map="auto"
+)
+model = PeftModel.from_pretrained(base_model, "AA65327/llama2-emotion-activity-20251005")
+tokenizer = AutoTokenizer.from_pretrained("AA65327/llama2-emotion-activity-20251005")
+
+# Format your prompt
+def format_prompt(instruction, input_text, activity_log):
+    return f"""Below is an instruction that describes a task, paired with an input that provides further context.
+Write a response that appropriately completes the request.
+
+### Instruction:
+{instruction}
+
+### Input:
+Current message: {input_text}
+Activity log (past 3 days, hours per activity): {activity_log}
+
+### Response:
+"""
+
+# Example usage
+instruction = "Evaluate the emotion in this text and suggest why the person might feel this way."
+input_text = "I'm feeling really excited about this new project!"
+activity_log = "working_out: [2, 1, 3]; reading: [1, 2, 0]; socializing: [3, 4, 2]"
+
+prompt = format_prompt(instruction, input_text, activity_log)
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.7)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
+
+## Training Procedure
+
+The model was trained using LoRA (Low-Rank Adaptation) technique with the following approach:
+1. Load base LLaMA-2-7B-Chat model with 4-bit quantization
+2. Apply LoRA adapters to query and value projection layers
+3. Fine-tune on emotion analysis tasks with activity context
+4. Implement gradient checkpointing and mixed precision training
+5. Use early stopping based on validation loss
+
+## Limitations and Bias
+
+- The model may reflect biases present in the training data
+- Performance may vary on domains not represented in the training set
+- Activity context interpretation is based on patterns learned from training data
+- Generated content should be reviewed for factual accuracy
+
+## Citation
+
+```bibtex
+@misc{llama2-emotion-activity-2025,
+  author = {AA65327},
+  title = {LLaMA-2-7B Emotion Analysis with Activity Context},
+  year = {2025},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/AA65327/llama2-emotion-activity-20251005}
+}
+```
+
+## Acknowledgments
+
+- Meta AI for the base LLaMA-2 model
+- Google Research for the GoEmotions dataset
+- Hugging Face for the transformers library and model hosting

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "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",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2898596731c6d103dac68e0c797a69bd04469c5066cf458134301caa68597dde
+size 33588528

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

checkpoint-50/README.md

@@ -0,0 +1,207 @@
+---
+base_model: NousResearch/Llama-2-7b-chat-hf
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:NousResearch/Llama-2-7b-chat-hf
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-50/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "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",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-50/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2898596731c6d103dac68e0c797a69bd04469c5066cf458134301caa68597dde
+size 33588528

checkpoint-50/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

checkpoint-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5d92048df8e9c44ffe67116a14424df38bb672c781b15b009c9c28d65b2d63
+size 67327691

checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d073bd6c91f8e22d16ac1a0c8d491664eb3be2f8b609f9f44458561f061786ca
+size 14645

checkpoint-50/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4293d1449e7b8ded03fb6577e4185f63efc99517fd5f93bfced72522213551b2
+size 1383

checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31edc2a2bbce91c1e6afed681e5dc14966c375f87f735113b40ed0fe4d96a219
+size 1465

checkpoint-50/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-50/tokenizer.model

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

checkpoint-50/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-50/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": 50,
+  "best_metric": 0.9238768815994263,
+  "best_model_checkpoint": "./llama2-goemotions-lora-optimized/checkpoint-50",
+  "epoch": 0.001151808339092375,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000230361667818475,
+      "grad_norm": 2.6401069164276123,
+      "learning_rate": 0.00018,
+      "loss": 3.5448,
+      "step": 10
+    },
+    {
+      "epoch": 0.00046072333563695,
+      "grad_norm": 3.533531904220581,
+      "learning_rate": 0.000155,
+      "loss": 2.0609,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005759041695461875,
+      "eval_loss": 1.1123775243759155,
+      "eval_runtime": 6017.5045,
+      "eval_samples_per_second": 1.804,
+      "eval_steps_per_second": 1.804,
+      "step": 25
+    },
+    {
+      "epoch": 0.000691085003455425,
+      "grad_norm": 1.6841713190078735,
+      "learning_rate": 0.000105,
+      "loss": 1.1921,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009214466712739,
+      "grad_norm": 1.636803388595581,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.0012,
+      "step": 40
+    },
+    {
+      "epoch": 0.001151808339092375,
+      "grad_norm": 1.3772783279418945,
+      "learning_rate": 5e-06,
+      "loss": 0.9673,
+      "step": 50
+    },
+    {
+      "epoch": 0.001151808339092375,
+      "eval_loss": 0.9238768815994263,
+      "eval_runtime": 6019.9295,
+      "eval_samples_per_second": 1.803,
+      "eval_steps_per_second": 1.803,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1016176469606400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d041afb86be4a082acdec15891d0f748eda550dea5a4ae87ad52f771ca6ac082
+size 5777

evaluation_metrics.json

@@ -0,0 +1,12 @@
+{
+  "perplexity": 26.080894470214844,
+  "tokens_per_second": 1.3229382650688788,
+  "samples_per_second": 0.11811948795257846,
+  "avg_time_per_sample": 8.466003513336181,
+  "rouge1": 0.190389919784236,
+  "rouge2": 0.16995296818860808,
+  "rougeL": 0.190389919784236,
+  "bleu": 8.038511090894387,
+  "avg_hallucination": 2.40048841144491,
+  "hallucination_std": 0.3121710792145274
+}

metrics.csv

@@ -0,0 +1,2 @@
+perplexity,tokens_per_second,samples_per_second,avg_time_per_sample,rouge1,rouge2,rougeL,bleu,avg_hallucination,hallucination_std
+26.080894470214844,1.3229382650688788,0.11811948795257846,8.466003513336181,0.190389919784236,0.16995296818860808,0.190389919784236,8.038511090894387,2.40048841144491,0.3121710792145274

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_global_step": 50,
+  "best_metric": 0.9238768815994263,
+  "best_model_checkpoint": "./llama2-goemotions-lora-optimized/checkpoint-50",
+  "epoch": 0.001151808339092375,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000230361667818475,
+      "grad_norm": 2.6401069164276123,
+      "learning_rate": 0.00018,
+      "loss": 3.5448,
+      "step": 10
+    },
+    {
+      "epoch": 0.00046072333563695,
+      "grad_norm": 3.533531904220581,
+      "learning_rate": 0.000155,
+      "loss": 2.0609,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005759041695461875,
+      "eval_loss": 1.1123775243759155,
+      "eval_runtime": 6017.5045,
+      "eval_samples_per_second": 1.804,
+      "eval_steps_per_second": 1.804,
+      "step": 25
+    },
+    {
+      "epoch": 0.000691085003455425,
+      "grad_norm": 1.6841713190078735,
+      "learning_rate": 0.000105,
+      "loss": 1.1921,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009214466712739,
+      "grad_norm": 1.636803388595581,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.0012,
+      "step": 40
+    },
+    {
+      "epoch": 0.001151808339092375,
+      "grad_norm": 1.3772783279418945,
+      "learning_rate": 5e-06,
+      "loss": 0.9673,
+      "step": 50
+    },
+    {
+      "epoch": 0.001151808339092375,
+      "eval_loss": 0.9238768815994263,
+      "eval_runtime": 6019.9295,
+      "eval_samples_per_second": 1.803,
+      "eval_steps_per_second": 1.803,
+      "step": 50
+    },
+    {
+      "epoch": 0.001151808339092375,
+      "step": 50,
+      "total_flos": 1016176469606400.0,
+      "train_loss": 1.7532618713378907,
+      "train_runtime": 12121.5826,
+      "train_samples_per_second": 0.004,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1016176469606400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d041afb86be4a082acdec15891d0f748eda550dea5a4ae87ad52f771ca6ac082
+size 5777