| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 100.0, | |
| "global_step": 6300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 3.3650793650793656e-05, | |
| "loss": 0.067, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "eval_accuracy": 0.9120488561846123, | |
| "eval_f1": 0.5542691751085383, | |
| "eval_loss": 0.5247976183891296, | |
| "eval_precision": 0.5292491939198526, | |
| "eval_recall": 0.5817721518987342, | |
| "eval_runtime": 6.9983, | |
| "eval_samples_per_second": 71.445, | |
| "eval_steps_per_second": 9.002, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 31.75, | |
| "learning_rate": 2.7301587301587305e-05, | |
| "loss": 0.0049, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 31.75, | |
| "eval_accuracy": 0.9141012163988587, | |
| "eval_f1": 0.5845740785940932, | |
| "eval_loss": 0.6428591012954712, | |
| "eval_precision": 0.5643261074458058, | |
| "eval_recall": 0.6063291139240506, | |
| "eval_runtime": 7.0179, | |
| "eval_samples_per_second": 71.246, | |
| "eval_steps_per_second": 8.977, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 47.62, | |
| "learning_rate": 2.0952380952380954e-05, | |
| "loss": 0.0022, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 47.62, | |
| "eval_accuracy": 0.9139510437002553, | |
| "eval_f1": 0.5792592592592594, | |
| "eval_loss": 0.6684653162956238, | |
| "eval_precision": 0.5653012048192771, | |
| "eval_recall": 0.5939240506329114, | |
| "eval_runtime": 6.9798, | |
| "eval_samples_per_second": 71.636, | |
| "eval_steps_per_second": 9.026, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 63.49, | |
| "learning_rate": 1.4603174603174603e-05, | |
| "loss": 0.0013, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 63.49, | |
| "eval_accuracy": 0.9137007558692496, | |
| "eval_f1": 0.5624591236102028, | |
| "eval_loss": 0.6453785300254822, | |
| "eval_precision": 0.5818673883626523, | |
| "eval_recall": 0.5443037974683544, | |
| "eval_runtime": 6.9826, | |
| "eval_samples_per_second": 71.607, | |
| "eval_steps_per_second": 9.022, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 79.37, | |
| "learning_rate": 8.253968253968254e-06, | |
| "loss": 0.0004, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 79.37, | |
| "eval_accuracy": 0.9153025979876859, | |
| "eval_f1": 0.5703675246510438, | |
| "eval_loss": 0.7095718383789062, | |
| "eval_precision": 0.5770925110132159, | |
| "eval_recall": 0.5637974683544303, | |
| "eval_runtime": 7.0736, | |
| "eval_samples_per_second": 70.685, | |
| "eval_steps_per_second": 8.906, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 95.24, | |
| "learning_rate": 1.904761904761905e-06, | |
| "loss": 0.0003, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 95.24, | |
| "eval_accuracy": 0.9154777994693898, | |
| "eval_f1": 0.581075973289656, | |
| "eval_loss": 0.7306210994720459, | |
| "eval_precision": 0.5783797341359418, | |
| "eval_recall": 0.5837974683544304, | |
| "eval_runtime": 7.1135, | |
| "eval_samples_per_second": 70.289, | |
| "eval_steps_per_second": 8.856, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 6300, | |
| "total_flos": 9.28710140928e+16, | |
| "train_loss": 0.012086462969226497, | |
| "train_runtime": 3307.3744, | |
| "train_samples_per_second": 30.235, | |
| "train_steps_per_second": 1.905 | |
| } | |
| ], | |
| "max_steps": 6300, | |
| "num_train_epochs": 100, | |
| "total_flos": 9.28710140928e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |