| { | |
| "best_metric": 5.741369932366069e-06, | |
| "best_model_checkpoint": "insuff_supported_arguments/checkpoint-4628", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4628, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.03457513824105263, | |
| "learning_rate": 1.9279746470757707e-05, | |
| "loss": 0.1457, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.0055348570458590984, | |
| "learning_rate": 1.8559492941515416e-05, | |
| "loss": 0.0066, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.002291068434715271, | |
| "learning_rate": 1.783923941227312e-05, | |
| "loss": 0.0014, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.003473889548331499, | |
| "learning_rate": 1.7118985883030827e-05, | |
| "loss": 0.0114, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.0016763019375503063, | |
| "learning_rate": 1.6398732353788535e-05, | |
| "loss": 0.0031, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.0010241195559501648, | |
| "learning_rate": 1.567847882454624e-05, | |
| "loss": 0.0012, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.00029286000062711537, | |
| "learning_rate": 1.4958225295303948e-05, | |
| "loss": 0.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.0003028396749868989, | |
| "learning_rate": 1.4237971766061655e-05, | |
| "loss": 0.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.0002893279306590557, | |
| "learning_rate": 1.3517718236819362e-05, | |
| "loss": 0.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_NEGATIVE": { | |
| "f1-score": 1.0, | |
| "precision": 1.0, | |
| "recall": 1.0, | |
| "support": 13620.0 | |
| }, | |
| "eval_POSITIVE": { | |
| "f1-score": 1.0, | |
| "precision": 1.0, | |
| "recall": 1.0, | |
| "support": 6960.0 | |
| }, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 5.741369932366069e-06, | |
| "eval_macro avg": { | |
| "f1-score": 1.0, | |
| "precision": 1.0, | |
| "recall": 1.0, | |
| "support": 20580.0 | |
| }, | |
| "eval_runtime": 11.5238, | |
| "eval_samples_per_second": 1785.875, | |
| "eval_steps_per_second": 111.682, | |
| "eval_weighted avg": { | |
| "f1-score": 1.0, | |
| "precision": 1.0, | |
| "recall": 1.0, | |
| "support": 20580.0 | |
| }, | |
| "step": 4628 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 13884, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2984335256486880.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |