| { | |
| "best_metric": 2.992061138153076, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.3401360544217687, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 6.8392791748046875, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3494, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "eval_loss": 8.134939193725586, | |
| "eval_runtime": 3.1555, | |
| "eval_samples_per_second": 15.845, | |
| "eval_steps_per_second": 4.12, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 6.739720821380615, | |
| "learning_rate": 0.0001, | |
| "loss": 7.1922, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 7.031229019165039, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 7.3527, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 8.194382667541504, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 6.042, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 8.183717727661133, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 5.0767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 11.740869522094727, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 4.5583, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 9.3971586227417, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 4.0343, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 9.743473052978516, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 4.1191, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 6.13151741027832, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 3.7088, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 7.639866352081299, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 3.5536, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14965986394557823, | |
| "grad_norm": 6.75575590133667, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 3.7497, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 6.3047943115234375, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 3.8154, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17687074829931973, | |
| "grad_norm": 4.291060924530029, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 3.5203, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 5.791419506072998, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 3.0025, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 3.7248475551605225, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 3.1225, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21768707482993196, | |
| "grad_norm": 4.330467224121094, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 3.2997, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23129251700680273, | |
| "grad_norm": 4.7831621170043945, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 2.9393, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 4.096930027008057, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 3.1609, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2585034013605442, | |
| "grad_norm": 4.522026062011719, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 2.9927, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 4.4654645919799805, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 3.0878, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 4.6324357986450195, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 3.2323, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.29931972789115646, | |
| "grad_norm": 4.298750877380371, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 3.2053, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3129251700680272, | |
| "grad_norm": 4.456368446350098, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 3.2063, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 4.407687664031982, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 3.2895, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 4.699411869049072, | |
| "learning_rate": 1e-05, | |
| "loss": 3.3251, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "eval_loss": 2.992061138153076, | |
| "eval_runtime": 3.2082, | |
| "eval_samples_per_second": 15.585, | |
| "eval_steps_per_second": 4.052, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.984041808658432e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |