| { | |
| "best_metric": 1.098726749420166, | |
| "best_model_checkpoint": "./beans_outputs/checkpoint-1300", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 3.964278221130371, | |
| "learning_rate": 0.005, | |
| "loss": 0.9625, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3383458646616541, | |
| "eval_loss": 1.1997095346450806, | |
| "eval_runtime": 0.9373, | |
| "eval_samples_per_second": 141.894, | |
| "eval_steps_per_second": 18.137, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.5754929184913635, | |
| "learning_rate": 0.005, | |
| "loss": 1.2026, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3308270676691729, | |
| "eval_loss": 1.1204776763916016, | |
| "eval_runtime": 0.9634, | |
| "eval_samples_per_second": 138.047, | |
| "eval_steps_per_second": 17.645, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 0.5505106449127197, | |
| "learning_rate": 0.005, | |
| "loss": 1.1354, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3308270676691729, | |
| "eval_loss": 1.099075198173523, | |
| "eval_runtime": 0.9285, | |
| "eval_samples_per_second": 143.241, | |
| "eval_steps_per_second": 18.309, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.4573482573032379, | |
| "learning_rate": 0.005, | |
| "loss": 1.1074, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 0.1797952502965927, | |
| "learning_rate": 0.005, | |
| "loss": 1.1071, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3308270676691729, | |
| "eval_loss": 1.101277232170105, | |
| "eval_runtime": 0.9468, | |
| "eval_samples_per_second": 140.474, | |
| "eval_steps_per_second": 17.955, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 0.0814356580376625, | |
| "learning_rate": 0.005, | |
| "loss": 1.102, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3308270676691729, | |
| "eval_loss": 1.0996899604797363, | |
| "eval_runtime": 0.994, | |
| "eval_samples_per_second": 133.802, | |
| "eval_steps_per_second": 17.103, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.384615384615385, | |
| "grad_norm": 0.49848759174346924, | |
| "learning_rate": 0.005, | |
| "loss": 1.1064, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3383458646616541, | |
| "eval_loss": 1.0997720956802368, | |
| "eval_runtime": 0.9552, | |
| "eval_samples_per_second": 139.237, | |
| "eval_steps_per_second": 17.797, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 0.38272586464881897, | |
| "learning_rate": 0.005, | |
| "loss": 1.1083, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.923076923076923, | |
| "grad_norm": 0.37760409712791443, | |
| "learning_rate": 0.005, | |
| "loss": 1.1008, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.3308270676691729, | |
| "eval_loss": 1.099931001663208, | |
| "eval_runtime": 0.9388, | |
| "eval_samples_per_second": 141.67, | |
| "eval_steps_per_second": 18.108, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 0.26804277300834656, | |
| "learning_rate": 0.005, | |
| "loss": 1.1015, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.3308270676691729, | |
| "eval_loss": 1.0987836122512817, | |
| "eval_runtime": 0.9412, | |
| "eval_samples_per_second": 141.315, | |
| "eval_steps_per_second": 18.063, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 8.461538461538462, | |
| "grad_norm": 0.3317204713821411, | |
| "learning_rate": 0.005, | |
| "loss": 1.0998, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.3308270676691729, | |
| "eval_loss": 1.1042646169662476, | |
| "eval_runtime": 0.9609, | |
| "eval_samples_per_second": 138.415, | |
| "eval_steps_per_second": 17.692, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 0.2213129699230194, | |
| "learning_rate": 0.005, | |
| "loss": 1.1156, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.4260609745979309, | |
| "learning_rate": 0.005, | |
| "loss": 1.1085, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.3383458646616541, | |
| "eval_loss": 1.098726749420166, | |
| "eval_runtime": 0.9647, | |
| "eval_samples_per_second": 137.865, | |
| "eval_steps_per_second": 17.622, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1300, | |
| "total_flos": 8.772706474360013e+17, | |
| "train_loss": 1.1044638824462891, | |
| "train_runtime": 173.1626, | |
| "train_samples_per_second": 59.713, | |
| "train_steps_per_second": 7.507 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.772706474360013e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |