| { | |
| "best_metric": 0.6414645910263062, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.32193158953722334, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006438631790744467, | |
| "grad_norm": 5.758460521697998, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006438631790744467, | |
| "eval_loss": 6.066755294799805, | |
| "eval_runtime": 27.4965, | |
| "eval_samples_per_second": 38.078, | |
| "eval_steps_per_second": 4.764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012877263581488933, | |
| "grad_norm": 6.174899578094482, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0514, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0193158953722334, | |
| "grad_norm": 5.623106479644775, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.5826, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025754527162977867, | |
| "grad_norm": 5.640625953674316, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.8584, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03219315895372234, | |
| "grad_norm": 5.98725700378418, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4196, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0386317907444668, | |
| "grad_norm": 4.09985876083374, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7034, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04507042253521127, | |
| "grad_norm": 3.7372446060180664, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.51, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05150905432595573, | |
| "grad_norm": 2.7311766147613525, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1435, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0579476861167002, | |
| "grad_norm": 2.5494556427001953, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0787, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06438631790744467, | |
| "grad_norm": 3.4875409603118896, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1593, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07082494969818913, | |
| "grad_norm": 3.1091856956481934, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0259, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0772635814889336, | |
| "grad_norm": 3.4979512691497803, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1409, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08370221327967807, | |
| "grad_norm": 2.4156033992767334, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0615, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09014084507042254, | |
| "grad_norm": 1.8686261177062988, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9069, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.096579476861167, | |
| "grad_norm": 1.4878034591674805, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8149, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10301810865191147, | |
| "grad_norm": 1.5322922468185425, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7772, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10945674044265594, | |
| "grad_norm": 1.8353601694107056, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8866, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1158953722334004, | |
| "grad_norm": 1.784643530845642, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8496, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12233400402414486, | |
| "grad_norm": 2.0500004291534424, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8587, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12877263581488935, | |
| "grad_norm": 1.686715006828308, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1352112676056338, | |
| "grad_norm": 1.7424335479736328, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9163, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14164989939637826, | |
| "grad_norm": 1.8051137924194336, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8257, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14808853118712273, | |
| "grad_norm": 1.809727430343628, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7397, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1545271629778672, | |
| "grad_norm": 2.0471720695495605, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8385, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16096579476861167, | |
| "grad_norm": 2.538386821746826, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7014, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16096579476861167, | |
| "eval_loss": 0.7676683664321899, | |
| "eval_runtime": 27.6237, | |
| "eval_samples_per_second": 37.902, | |
| "eval_steps_per_second": 4.742, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16740442655935614, | |
| "grad_norm": 1.329602837562561, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6918, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1738430583501006, | |
| "grad_norm": 1.2770546674728394, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.735, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.18028169014084508, | |
| "grad_norm": 1.4017536640167236, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5865, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18672032193158955, | |
| "grad_norm": 1.3825314044952393, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6696, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.193158953722334, | |
| "grad_norm": 1.6134448051452637, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7824, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19959758551307846, | |
| "grad_norm": 1.6515852212905884, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7637, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.20603621730382293, | |
| "grad_norm": 1.673492431640625, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7608, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2124748490945674, | |
| "grad_norm": 1.5567281246185303, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7211, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21891348088531187, | |
| "grad_norm": 1.4139515161514282, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7465, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 1.6844676733016968, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6431, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2317907444668008, | |
| "grad_norm": 1.7753030061721802, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6708, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23822937625754528, | |
| "grad_norm": 1.9843260049819946, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6408, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24466800804828973, | |
| "grad_norm": 1.216661810874939, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5066, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2511066398390342, | |
| "grad_norm": 1.046256422996521, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6026, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2575452716297787, | |
| "grad_norm": 1.155771255493164, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5317, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26398390342052314, | |
| "grad_norm": 1.118788719177246, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.514, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2704225352112676, | |
| "grad_norm": 1.3662763833999634, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6024, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2768611670020121, | |
| "grad_norm": 1.4658805131912231, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6011, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2832997987927565, | |
| "grad_norm": 1.420807957649231, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5863, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.289738430583501, | |
| "grad_norm": 1.4393686056137085, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5785, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.29617706237424546, | |
| "grad_norm": 1.3944177627563477, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5679, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.30261569416498996, | |
| "grad_norm": 1.7562270164489746, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7089, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3090543259557344, | |
| "grad_norm": 1.736271619796753, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5688, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3154929577464789, | |
| "grad_norm": 1.8209768533706665, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5624, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32193158953722334, | |
| "grad_norm": 1.960559368133545, | |
| "learning_rate": 0.0, | |
| "loss": 0.477, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32193158953722334, | |
| "eval_loss": 0.6414645910263062, | |
| "eval_runtime": 27.5843, | |
| "eval_samples_per_second": 37.956, | |
| "eval_steps_per_second": 4.749, | |
| "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 | |
| } | |