--- license: apache-2.0 datasets: - CoIR-Retrieval/CodeSearchNet-python-queries-corpus language: - en - ar - zh - ru - fr metrics: - loss - accuracy base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 pipeline_tag: text-generation library_name: transformers tags: - chat - conversational - programming - algorithms - ethical-hacking - open-source - tinyllama new_version: v1.0 training_data: 156GB of diverse text data (including programming and algorithmic content) model-index: - name: TINYLAMA results: - task: type: text-generation dataset: type: custom name: Local Dataset (156GB) metrics: - type: loss value: TBD (To Be Determined after retraining) - type: accuracy value: TBD (To Be Determined after retraining) eval_results: - task: Text Generation dataset: Local Dataset (156GB) metrics: - name: Loss value: TBD (To Be Determined after retraining) - name: Accuracy value: TBD (To Be Determined after retraining)
cdf548f
verified
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 3, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 489931407360.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |