| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-40", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.21518987341772153, | |
| "eval_f1_macro": 0.11805555555555557, | |
| "eval_f1_micro": 0.21518987341772153, | |
| "eval_f1_weighted": 0.07621308016877638, | |
| "eval_loss": NaN, | |
| "eval_precision_macro": 0.07172995780590717, | |
| "eval_precision_micro": 0.21518987341772153, | |
| "eval_precision_weighted": 0.04630668162153501, | |
| "eval_recall_macro": 0.3333333333333333, | |
| "eval_recall_micro": 0.21518987341772153, | |
| "eval_recall_weighted": 0.21518987341772153, | |
| "eval_runtime": 2.1556, | |
| "eval_samples_per_second": 36.649, | |
| "eval_steps_per_second": 2.32, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.4332702823346176e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |