| { | |
| "best_metric": 1.1550209522247314, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.8957345971563981, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.037914691943127965, | |
| "grad_norm": 1.8060966730117798, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9272, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037914691943127965, | |
| "eval_loss": 2.4487714767456055, | |
| "eval_runtime": 2.8678, | |
| "eval_samples_per_second": 17.435, | |
| "eval_steps_per_second": 4.533, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07582938388625593, | |
| "grad_norm": 2.048767328262329, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1904, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11374407582938388, | |
| "grad_norm": 1.9385805130004883, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.3752, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15165876777251186, | |
| "grad_norm": 2.348123788833618, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.4189, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1895734597156398, | |
| "grad_norm": 2.449019432067871, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.3614, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22748815165876776, | |
| "grad_norm": 2.676626443862915, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.371, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26540284360189575, | |
| "grad_norm": 2.7906734943389893, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.914, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3033175355450237, | |
| "grad_norm": 2.417691707611084, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8157, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3412322274881517, | |
| "grad_norm": 2.8479461669921875, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7637, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3791469194312796, | |
| "grad_norm": 2.8216776847839355, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7834, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41706161137440756, | |
| "grad_norm": 3.007326364517212, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.7873, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4549763033175355, | |
| "grad_norm": 3.539130449295044, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.8256, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4928909952606635, | |
| "grad_norm": 4.224482536315918, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.7561, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5308056872037915, | |
| "grad_norm": 3.585408926010132, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.5457, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5687203791469194, | |
| "grad_norm": 3.469649076461792, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.5345, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6066350710900474, | |
| "grad_norm": 3.8057563304901123, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.4979, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6445497630331753, | |
| "grad_norm": 3.8051953315734863, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4968, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6824644549763034, | |
| "grad_norm": 3.9303998947143555, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.5162, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7203791469194313, | |
| "grad_norm": 5.045314788818359, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.4578, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "grad_norm": 4.041980743408203, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.5793, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7962085308056872, | |
| "grad_norm": 3.3375320434570312, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4054, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8341232227488151, | |
| "grad_norm": 3.1427924633026123, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4343, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8720379146919431, | |
| "grad_norm": 3.994842529296875, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.4241, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.909952606635071, | |
| "grad_norm": 4.173420429229736, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.4761, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "grad_norm": 3.5468320846557617, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.4129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "eval_loss": 1.2877497673034668, | |
| "eval_runtime": 2.7925, | |
| "eval_samples_per_second": 17.905, | |
| "eval_steps_per_second": 4.655, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.985781990521327, | |
| "grad_norm": 3.641972780227661, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.3063, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0236966824644549, | |
| "grad_norm": 6.575774192810059, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.2342, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.061611374407583, | |
| "grad_norm": 2.9681127071380615, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.1676, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.099526066350711, | |
| "grad_norm": 3.215055465698242, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3389, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1374407582938388, | |
| "grad_norm": 3.5927894115448, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.3118, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1753554502369667, | |
| "grad_norm": 3.6256959438323975, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.2951, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2132701421800949, | |
| "grad_norm": 4.082485675811768, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3665, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2511848341232228, | |
| "grad_norm": 3.8541548252105713, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.2832, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2890995260663507, | |
| "grad_norm": 3.3070080280303955, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.4977, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3270142180094786, | |
| "grad_norm": 2.957866668701172, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.2518, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3649289099526065, | |
| "grad_norm": 3.1968929767608643, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2103, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4028436018957346, | |
| "grad_norm": 3.788357973098755, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2678, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4407582938388626, | |
| "grad_norm": 3.5773918628692627, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.2282, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4786729857819905, | |
| "grad_norm": 5.209697723388672, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.2627, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5165876777251186, | |
| "grad_norm": 3.6985459327697754, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.3944, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5545023696682465, | |
| "grad_norm": 3.104992151260376, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.1069, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5924170616113744, | |
| "grad_norm": 3.5081048011779785, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.2404, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6303317535545023, | |
| "grad_norm": 4.174959659576416, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2726, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6682464454976302, | |
| "grad_norm": 3.9129672050476074, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.235, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7061611374407581, | |
| "grad_norm": 3.7290847301483154, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.1971, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7440758293838863, | |
| "grad_norm": 4.0499725341796875, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.1738, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7819905213270142, | |
| "grad_norm": 4.013765335083008, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4398, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8199052132701423, | |
| "grad_norm": 3.703307628631592, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.2168, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8578199052132702, | |
| "grad_norm": 3.162926197052002, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.2299, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8957345971563981, | |
| "grad_norm": 3.2073774337768555, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1804, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8957345971563981, | |
| "eval_loss": 1.1550209522247314, | |
| "eval_runtime": 2.8058, | |
| "eval_samples_per_second": 17.82, | |
| "eval_steps_per_second": 4.633, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.12006162399232e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |