| { | |
| "best_metric": 0.9899665551839465, | |
| "best_model_checkpoint": "./DiMa_new_artifacts\\checkpoint-1131", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1131, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13262599469496023, | |
| "grad_norm": 6.313917636871338, | |
| "learning_rate": 6.622516556291392e-06, | |
| "loss": 0.6543, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.26525198938992045, | |
| "grad_norm": 8.760651588439941, | |
| "learning_rate": 1.3245033112582784e-05, | |
| "loss": 0.3545, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3978779840848806, | |
| "grad_norm": 12.38838005065918, | |
| "learning_rate": 1.9867549668874173e-05, | |
| "loss": 0.1951, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5305039787798409, | |
| "grad_norm": 13.237753868103027, | |
| "learning_rate": 1.9277818717759768e-05, | |
| "loss": 0.1559, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6631299734748011, | |
| "grad_norm": 11.964133262634277, | |
| "learning_rate": 1.8540899042004423e-05, | |
| "loss": 0.1602, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7957559681697612, | |
| "grad_norm": 27.106698989868164, | |
| "learning_rate": 1.780397936624908e-05, | |
| "loss": 0.1055, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9283819628647215, | |
| "grad_norm": 0.026046760380268097, | |
| "learning_rate": 1.7067059690493736e-05, | |
| "loss": 0.1148, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9774647887323944, | |
| "eval_f1": 0.9838492597577388, | |
| "eval_loss": 0.08887767791748047, | |
| "eval_precision": 0.9905149051490515, | |
| "eval_recall": 0.9772727272727273, | |
| "eval_runtime": 62.9416, | |
| "eval_samples_per_second": 16.92, | |
| "eval_steps_per_second": 1.064, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.0610079575596818, | |
| "grad_norm": 0.028772667050361633, | |
| "learning_rate": 1.6330140014738394e-05, | |
| "loss": 0.0809, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.193633952254642, | |
| "grad_norm": 0.056088343262672424, | |
| "learning_rate": 1.5593220338983053e-05, | |
| "loss": 0.0649, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.3262599469496021, | |
| "grad_norm": 6.098559379577637, | |
| "learning_rate": 1.485630066322771e-05, | |
| "loss": 0.0768, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4588859416445623, | |
| "grad_norm": 99.54315948486328, | |
| "learning_rate": 1.4119380987472366e-05, | |
| "loss": 0.0453, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.5915119363395225, | |
| "grad_norm": 6.803869247436523, | |
| "learning_rate": 1.3382461311717023e-05, | |
| "loss": 0.1294, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 0.2954126298427582, | |
| "learning_rate": 1.2645541635961683e-05, | |
| "loss": 0.0839, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.8567639257294428, | |
| "grad_norm": 0.047186098992824554, | |
| "learning_rate": 1.190862196020634e-05, | |
| "loss": 0.0557, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.9893899204244032, | |
| "grad_norm": 0.12770341336727142, | |
| "learning_rate": 1.1171702284450996e-05, | |
| "loss": 0.0466, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9802816901408451, | |
| "eval_f1": 0.986083499005964, | |
| "eval_loss": 0.1403597742319107, | |
| "eval_precision": 0.9776609724047306, | |
| "eval_recall": 0.9946524064171123, | |
| "eval_runtime": 64.2771, | |
| "eval_samples_per_second": 16.569, | |
| "eval_steps_per_second": 1.042, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 2.1220159151193636, | |
| "grad_norm": 0.012713871896266937, | |
| "learning_rate": 1.0434782608695653e-05, | |
| "loss": 0.0479, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.2546419098143238, | |
| "grad_norm": 0.013412756845355034, | |
| "learning_rate": 9.697862932940311e-06, | |
| "loss": 0.0227, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.387267904509284, | |
| "grad_norm": 0.0069837020710110664, | |
| "learning_rate": 8.960943257184968e-06, | |
| "loss": 0.024, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.519893899204244, | |
| "grad_norm": 0.006205807905644178, | |
| "learning_rate": 8.224023581429625e-06, | |
| "loss": 0.0216, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.6525198938992043, | |
| "grad_norm": 0.013195905834436417, | |
| "learning_rate": 7.487103905674282e-06, | |
| "loss": 0.0302, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.7851458885941645, | |
| "grad_norm": 0.010757376439869404, | |
| "learning_rate": 6.750184229918939e-06, | |
| "loss": 0.0021, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.9177718832891246, | |
| "grad_norm": 25.593114852905273, | |
| "learning_rate": 6.013264554163597e-06, | |
| "loss": 0.0222, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9859154929577465, | |
| "eval_f1": 0.9899665551839465, | |
| "eval_loss": 0.0968979001045227, | |
| "eval_precision": 0.9906291834002677, | |
| "eval_recall": 0.9893048128342246, | |
| "eval_runtime": 62.8419, | |
| "eval_samples_per_second": 16.947, | |
| "eval_steps_per_second": 1.066, | |
| "step": 1131 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1508, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 628769644546560.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |