| { | |
| "best_metric": 3.5896806716918945, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.007033430775655537, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014066861551311076, | |
| "grad_norm": 0.9536049962043762, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2531, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014066861551311076, | |
| "eval_loss": 5.379810810089111, | |
| "eval_runtime": 3.0033, | |
| "eval_samples_per_second": 16.649, | |
| "eval_steps_per_second": 4.329, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028133723102622153, | |
| "grad_norm": 1.4742906093597412, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0519, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00042200584653933227, | |
| "grad_norm": 1.8351389169692993, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005626744620524431, | |
| "grad_norm": 2.465190887451172, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.3919, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007033430775655537, | |
| "grad_norm": 3.3312063217163086, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.6585, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008440116930786645, | |
| "grad_norm": 3.3281242847442627, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.4326, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009846803085917753, | |
| "grad_norm": 2.3460187911987305, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.2619, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011253489241048861, | |
| "grad_norm": 2.295300006866455, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.3407, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012660175396179967, | |
| "grad_norm": 2.3964247703552246, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.2455, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014066861551311075, | |
| "grad_norm": 2.7469544410705566, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.165, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015473547706442183, | |
| "grad_norm": 3.301067590713501, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.3956, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001688023386157329, | |
| "grad_norm": 4.632366180419922, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.6585, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018286920016704399, | |
| "grad_norm": 3.030580997467041, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.4551, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019693606171835507, | |
| "grad_norm": 3.136796236038208, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.8662, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0021100292326966612, | |
| "grad_norm": 2.37330961227417, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.968, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022506978482097722, | |
| "grad_norm": 2.297255277633667, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.3438, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002391366463722883, | |
| "grad_norm": 3.2573561668395996, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.8021, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0025320350792359934, | |
| "grad_norm": 2.693838596343994, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.7436, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0026727036947491044, | |
| "grad_norm": 2.1688923835754395, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.9824, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002813372310262215, | |
| "grad_norm": 1.9488747119903564, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.9613, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002954040925775326, | |
| "grad_norm": 2.2130255699157715, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.8042, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0030947095412884366, | |
| "grad_norm": 2.4047369956970215, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.0572, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0032353781568015476, | |
| "grad_norm": 2.5875649452209473, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.953, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003376046772314658, | |
| "grad_norm": 2.5539562702178955, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.2999, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0035167153878277687, | |
| "grad_norm": 3.557594060897827, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.8709, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0035167153878277687, | |
| "eval_loss": 3.7035763263702393, | |
| "eval_runtime": 2.9891, | |
| "eval_samples_per_second": 16.727, | |
| "eval_steps_per_second": 4.349, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0036573840033408797, | |
| "grad_norm": 0.719357430934906, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.8378, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0037980526188539903, | |
| "grad_norm": 0.8073096871376038, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.5049, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003938721234367101, | |
| "grad_norm": 0.8840256929397583, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.9195, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0040793898498802115, | |
| "grad_norm": 1.1521762609481812, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.4451, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0042200584653933225, | |
| "grad_norm": 1.198631763458252, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.6565, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0043607270809064335, | |
| "grad_norm": 1.3765795230865479, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.7224, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0045013956964195445, | |
| "grad_norm": 1.346805214881897, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.6726, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004642064311932655, | |
| "grad_norm": 1.2883901596069336, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.7782, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004782732927445766, | |
| "grad_norm": 1.4923596382141113, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.7878, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004923401542958877, | |
| "grad_norm": 1.637706995010376, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.9159, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005064070158471987, | |
| "grad_norm": 1.7289783954620361, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.0645, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005204738773985098, | |
| "grad_norm": 2.8105924129486084, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.4649, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005345407389498209, | |
| "grad_norm": 0.6356281638145447, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.8927, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00548607600501132, | |
| "grad_norm": 0.5997741222381592, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.3777, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00562674462052443, | |
| "grad_norm": 0.7866092324256897, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.7802, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005767413236037541, | |
| "grad_norm": 0.8625376224517822, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.0477, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005908081851550652, | |
| "grad_norm": 0.9740644693374634, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.5105, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006048750467063762, | |
| "grad_norm": 1.083276629447937, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.5828, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006189419082576873, | |
| "grad_norm": 1.3166731595993042, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.7169, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006330087698089984, | |
| "grad_norm": 1.4437602758407593, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.7671, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006470756313603095, | |
| "grad_norm": 1.6273506879806519, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.6367, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006611424929116205, | |
| "grad_norm": 1.676190972328186, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.6023, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006752093544629316, | |
| "grad_norm": 2.3617000579833984, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.9218, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.006892762160142427, | |
| "grad_norm": 2.1535112857818604, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.0372, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007033430775655537, | |
| "grad_norm": 3.9727821350097656, | |
| "learning_rate": 1e-05, | |
| "loss": 4.6256, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007033430775655537, | |
| "eval_loss": 3.5896806716918945, | |
| "eval_runtime": 3.0738, | |
| "eval_samples_per_second": 16.266, | |
| "eval_steps_per_second": 4.229, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |