| { | |
| "best_metric": 1.2797590494155884, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1991017964071857, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023952095808383235, | |
| "grad_norm": 4.3831467628479, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023952095808383235, | |
| "eval_loss": 3.31597900390625, | |
| "eval_runtime": 2.4507, | |
| "eval_samples_per_second": 20.403, | |
| "eval_steps_per_second": 5.305, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04790419161676647, | |
| "grad_norm": 6.220251083374023, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5286, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0718562874251497, | |
| "grad_norm": 5.368954181671143, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.5211, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09580838323353294, | |
| "grad_norm": 5.073603630065918, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.8314, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "grad_norm": 1.7181708812713623, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.4547, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1437125748502994, | |
| "grad_norm": 1.9311556816101074, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2218, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16766467065868262, | |
| "grad_norm": 2.3383331298828125, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.7581, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "grad_norm": 1.030449628829956, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.5957, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2155688622754491, | |
| "grad_norm": 0.7178290486335754, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.4386, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "grad_norm": 1.3254685401916504, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1794, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2634730538922156, | |
| "grad_norm": 2.477407932281494, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.5794, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2874251497005988, | |
| "grad_norm": 2.236238956451416, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.5889, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.31137724550898205, | |
| "grad_norm": 1.6854743957519531, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6731, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.33532934131736525, | |
| "grad_norm": 1.1402990818023682, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.3601, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3592814371257485, | |
| "grad_norm": 0.6827440857887268, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2027, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.38323353293413176, | |
| "grad_norm": 2.249011516571045, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.7293, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.40718562874251496, | |
| "grad_norm": 2.279639482498169, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.7747, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4311377245508982, | |
| "grad_norm": 1.2636538743972778, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.5692, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4550898203592814, | |
| "grad_norm": 1.0719739198684692, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.4809, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "grad_norm": 1.850277066230774, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.209, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5029940119760479, | |
| "grad_norm": 0.649785041809082, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2188, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5269461077844312, | |
| "grad_norm": 0.7884364128112793, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2773, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5508982035928144, | |
| "grad_norm": 0.6881579756736755, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.4354, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5748502994011976, | |
| "grad_norm": 0.8806324601173401, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2282, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5988023952095808, | |
| "grad_norm": 2.3608176708221436, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1773, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5988023952095808, | |
| "eval_loss": 1.6385608911514282, | |
| "eval_runtime": 1.8398, | |
| "eval_samples_per_second": 27.176, | |
| "eval_steps_per_second": 7.066, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6227544910179641, | |
| "grad_norm": 3.454927444458008, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.4419, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6467065868263473, | |
| "grad_norm": 15.82660961151123, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.979, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6706586826347305, | |
| "grad_norm": 2.704850673675537, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.5964, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6946107784431138, | |
| "grad_norm": 0.9731075763702393, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3988, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.718562874251497, | |
| "grad_norm": 0.9410566091537476, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1846, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7425149700598802, | |
| "grad_norm": 0.6559235453605652, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.2623, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7664670658682635, | |
| "grad_norm": 0.8387520909309387, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.289, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7904191616766467, | |
| "grad_norm": 0.8098101615905762, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3178, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8143712574850299, | |
| "grad_norm": 0.6314873099327087, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.302, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8383233532934131, | |
| "grad_norm": 0.613024115562439, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.1753, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8622754491017964, | |
| "grad_norm": 0.9052037596702576, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.7577, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8862275449101796, | |
| "grad_norm": 0.9839400053024292, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.6996, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9101796407185628, | |
| "grad_norm": 0.8733965158462524, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.5614, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9341317365269461, | |
| "grad_norm": 0.7196979522705078, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3533, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9580838323353293, | |
| "grad_norm": 0.7690499424934387, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.241, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9820359281437125, | |
| "grad_norm": 1.088390827178955, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.0753, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0074850299401197, | |
| "grad_norm": 0.6395664811134338, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.8832, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.031437125748503, | |
| "grad_norm": 0.5951088070869446, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1295, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0553892215568863, | |
| "grad_norm": 0.5507844686508179, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.3376, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0793413173652695, | |
| "grad_norm": 0.5301908850669861, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.2178, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1032934131736527, | |
| "grad_norm": 0.6889688372612, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.2051, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.127245508982036, | |
| "grad_norm": 0.6885656714439392, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.5593, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.151197604790419, | |
| "grad_norm": 0.7920830845832825, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.6038, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1751497005988023, | |
| "grad_norm": 0.7186149954795837, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.4422, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1991017964071857, | |
| "grad_norm": 0.717149555683136, | |
| "learning_rate": 1e-05, | |
| "loss": 1.2962, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1991017964071857, | |
| "eval_loss": 1.2797590494155884, | |
| "eval_runtime": 1.8277, | |
| "eval_samples_per_second": 27.356, | |
| "eval_steps_per_second": 7.113, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |