| { | |
| "best_metric": 1.1878825426101685, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.016877637130801686, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008438818565400844, | |
| "grad_norm": 2.0711374282836914, | |
| "learning_rate": 2e-05, | |
| "loss": 5.9734, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008438818565400844, | |
| "eval_loss": 1.4170056581497192, | |
| "eval_runtime": 57.0556, | |
| "eval_samples_per_second": 8.746, | |
| "eval_steps_per_second": 4.382, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016877637130801688, | |
| "grad_norm": 2.027665138244629, | |
| "learning_rate": 4e-05, | |
| "loss": 6.0228, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002531645569620253, | |
| "grad_norm": 1.9190106391906738, | |
| "learning_rate": 6e-05, | |
| "loss": 5.6071, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0033755274261603376, | |
| "grad_norm": 1.842444658279419, | |
| "learning_rate": 8e-05, | |
| "loss": 5.8858, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004219409282700422, | |
| "grad_norm": 1.845279574394226, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8225, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004219409282700422, | |
| "eval_loss": 1.3906506299972534, | |
| "eval_runtime": 51.09, | |
| "eval_samples_per_second": 9.767, | |
| "eval_steps_per_second": 4.893, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005063291139240506, | |
| "grad_norm": 1.810034990310669, | |
| "learning_rate": 0.00012, | |
| "loss": 5.7927, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00590717299578059, | |
| "grad_norm": 1.8367875814437866, | |
| "learning_rate": 0.00014, | |
| "loss": 5.5588, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006751054852320675, | |
| "grad_norm": 1.7529375553131104, | |
| "learning_rate": 0.00016, | |
| "loss": 5.1275, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007594936708860759, | |
| "grad_norm": 2.033984422683716, | |
| "learning_rate": 0.00018, | |
| "loss": 5.6724, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008438818565400843, | |
| "grad_norm": 1.9493958950042725, | |
| "learning_rate": 0.0002, | |
| "loss": 5.6368, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008438818565400843, | |
| "eval_loss": 1.3001285791397095, | |
| "eval_runtime": 50.9453, | |
| "eval_samples_per_second": 9.795, | |
| "eval_steps_per_second": 4.907, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009282700421940928, | |
| "grad_norm": 1.998062014579773, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.1065, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010126582278481013, | |
| "grad_norm": 2.0567452907562256, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 5.0806, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010970464135021098, | |
| "grad_norm": 2.400956153869629, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 5.499, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01181434599156118, | |
| "grad_norm": 2.553539991378784, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 5.1545, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012658227848101266, | |
| "grad_norm": 2.5420608520507812, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.5475, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012658227848101266, | |
| "eval_loss": 1.226226568222046, | |
| "eval_runtime": 50.6579, | |
| "eval_samples_per_second": 9.85, | |
| "eval_steps_per_second": 4.935, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01350210970464135, | |
| "grad_norm": 2.7176949977874756, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.1463, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014345991561181435, | |
| "grad_norm": 2.3419106006622314, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 5.0369, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015189873417721518, | |
| "grad_norm": 2.250117063522339, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.8538, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016033755274261603, | |
| "grad_norm": 2.4466376304626465, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 4.7334, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016877637130801686, | |
| "grad_norm": 2.1515731811523438, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.627, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016877637130801686, | |
| "eval_loss": 1.1878825426101685, | |
| "eval_runtime": 50.5519, | |
| "eval_samples_per_second": 9.871, | |
| "eval_steps_per_second": 4.945, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1195062570516480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |