| { | |
| "best_metric": 0.1645851880311966, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6751054852320675, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01350210970464135, | |
| "grad_norm": 5.568134784698486, | |
| "learning_rate": 5e-05, | |
| "loss": 5.0373, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01350210970464135, | |
| "eval_loss": 7.028787136077881, | |
| "eval_runtime": 15.16, | |
| "eval_samples_per_second": 32.915, | |
| "eval_steps_per_second": 4.156, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0270042194092827, | |
| "grad_norm": 5.84205436706543, | |
| "learning_rate": 0.0001, | |
| "loss": 5.4682, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 4.690907955169678, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.1249, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0540084388185654, | |
| "grad_norm": 4.773595333099365, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.6998, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06751054852320675, | |
| "grad_norm": 5.237292766571045, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.8722, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 5.305476188659668, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.1481, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09451476793248945, | |
| "grad_norm": 4.838389873504639, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2607, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1080168776371308, | |
| "grad_norm": 4.015415668487549, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6512, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 4.844939231872559, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4396, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1350210970464135, | |
| "grad_norm": 5.061824798583984, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3046, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14852320675105485, | |
| "grad_norm": 5.038525104522705, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7938, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 4.529359817504883, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5913, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17552742616033756, | |
| "grad_norm": 6.800049781799316, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9533, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1890295358649789, | |
| "grad_norm": 4.591196537017822, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.632, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 2.5431854724884033, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3908, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2160337552742616, | |
| "grad_norm": 2.365417957305908, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3317, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22953586497890296, | |
| "grad_norm": 2.108243703842163, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3239, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2430379746835443, | |
| "grad_norm": 1.2970813512802124, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2324, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25654008438818565, | |
| "grad_norm": 1.0303891897201538, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2151, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.270042194092827, | |
| "grad_norm": 1.3435170650482178, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28354430379746837, | |
| "grad_norm": 1.1844052076339722, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2042, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2970464135021097, | |
| "grad_norm": 1.5148234367370605, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1827, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3105485232067511, | |
| "grad_norm": 1.2344573736190796, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1451, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3240506329113924, | |
| "grad_norm": 1.2660400867462158, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1178, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.33755274261603374, | |
| "grad_norm": 1.4386123418807983, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.084, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33755274261603374, | |
| "eval_loss": 0.3598560690879822, | |
| "eval_runtime": 15.178, | |
| "eval_samples_per_second": 32.876, | |
| "eval_steps_per_second": 4.151, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3510548523206751, | |
| "grad_norm": 4.339173316955566, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6258, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.36455696202531646, | |
| "grad_norm": 3.878525733947754, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5842, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3780590717299578, | |
| "grad_norm": 3.5104947090148926, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.512, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.39156118143459917, | |
| "grad_norm": 2.3546969890594482, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.367, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 1.871620774269104, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3047, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.41856540084388183, | |
| "grad_norm": 1.3824152946472168, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2219, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4320675105485232, | |
| "grad_norm": 1.3422837257385254, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1512, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.44556962025316454, | |
| "grad_norm": 1.333117961883545, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1522, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.45907172995780593, | |
| "grad_norm": 2.088132381439209, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2185, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47257383966244726, | |
| "grad_norm": 2.526772975921631, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2609, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4860759493670886, | |
| "grad_norm": 2.376660108566284, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2183, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.49957805907173, | |
| "grad_norm": 2.1182215213775635, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1805, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5130801687763713, | |
| "grad_norm": 0.9188656806945801, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.236, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5265822784810127, | |
| "grad_norm": 1.0770657062530518, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2585, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.540084388185654, | |
| "grad_norm": 0.9798564314842224, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2234, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5535864978902953, | |
| "grad_norm": 0.7824795842170715, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2099, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5670886075949367, | |
| "grad_norm": 0.8526087403297424, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1849, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.580590717299578, | |
| "grad_norm": 0.685903012752533, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1996, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5940928270042194, | |
| "grad_norm": 0.954988956451416, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1537, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 0.699277400970459, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1394, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6210970464135022, | |
| "grad_norm": 0.5863059163093567, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1467, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6345991561181434, | |
| "grad_norm": 1.0702379941940308, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1562, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6481012658227848, | |
| "grad_norm": 1.1115703582763672, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.145, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6616033755274262, | |
| "grad_norm": 1.0013189315795898, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1066, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6751054852320675, | |
| "grad_norm": 1.1740268468856812, | |
| "learning_rate": 0.0, | |
| "loss": 0.1087, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6751054852320675, | |
| "eval_loss": 0.1645851880311966, | |
| "eval_runtime": 15.1774, | |
| "eval_samples_per_second": 32.878, | |
| "eval_steps_per_second": 4.151, | |
| "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": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |