| { | |
| "best_metric": 1.108001947402954, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.056657223796033995, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011331444759206798, | |
| "grad_norm": 3.730471611022949, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9342, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011331444759206798, | |
| "eval_loss": 1.9385651350021362, | |
| "eval_runtime": 180.3974, | |
| "eval_samples_per_second": 32.955, | |
| "eval_steps_per_second": 4.124, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022662889518413596, | |
| "grad_norm": 3.502908229827881, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9786, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033994334277620396, | |
| "grad_norm": 3.0848944187164307, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7841, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004532577903682719, | |
| "grad_norm": 2.3751518726348877, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.3923, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0056657223796034, | |
| "grad_norm": 0.9001646041870117, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.294, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006798866855524079, | |
| "grad_norm": 0.5481812953948975, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2386, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00793201133144476, | |
| "grad_norm": 0.5999112129211426, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.2196, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009065155807365438, | |
| "grad_norm": 0.29560431838035583, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2161, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010198300283286119, | |
| "grad_norm": 0.44561514258384705, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1931, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0113314447592068, | |
| "grad_norm": 0.4556409418582916, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012464589235127478, | |
| "grad_norm": 0.3806966245174408, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1541, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013597733711048159, | |
| "grad_norm": 0.5077003240585327, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1115, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014730878186968839, | |
| "grad_norm": 0.35587725043296814, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0538, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01586402266288952, | |
| "grad_norm": 0.2802821099758148, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1781, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0169971671388102, | |
| "grad_norm": 0.2896048426628113, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.1739, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018130311614730877, | |
| "grad_norm": 0.2867259979248047, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1876, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019263456090651557, | |
| "grad_norm": 0.2677183747291565, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1692, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020396600566572238, | |
| "grad_norm": 0.23088912665843964, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.131, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02152974504249292, | |
| "grad_norm": 0.28265196084976196, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1539, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0226628895184136, | |
| "grad_norm": 0.25443291664123535, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1563, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02379603399433428, | |
| "grad_norm": 0.2580697238445282, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1228, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024929178470254956, | |
| "grad_norm": 0.25163376331329346, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1178, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026062322946175637, | |
| "grad_norm": 0.26076334714889526, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1137, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.027195467422096317, | |
| "grad_norm": 0.26753100752830505, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1262, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028328611898016998, | |
| "grad_norm": 0.4042368233203888, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0133, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028328611898016998, | |
| "eval_loss": 1.121332049369812, | |
| "eval_runtime": 180.3027, | |
| "eval_samples_per_second": 32.972, | |
| "eval_steps_per_second": 4.126, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029461756373937678, | |
| "grad_norm": 0.37851259112358093, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1602, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03059490084985836, | |
| "grad_norm": 0.3290565311908722, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.1472, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03172804532577904, | |
| "grad_norm": 0.2516811490058899, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1543, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03286118980169972, | |
| "grad_norm": 0.3208964467048645, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.135, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0339943342776204, | |
| "grad_norm": 0.26425492763519287, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.151, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03512747875354107, | |
| "grad_norm": 0.34969091415405273, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1472, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.036260623229461754, | |
| "grad_norm": 0.2773855924606323, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1479, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.037393767705382434, | |
| "grad_norm": 0.30572637915611267, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.119, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.038526912181303115, | |
| "grad_norm": 0.39220941066741943, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1109, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.039660056657223795, | |
| "grad_norm": 0.300199419260025, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0948, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.040793201133144476, | |
| "grad_norm": 0.25450271368026733, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0864, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.041926345609065156, | |
| "grad_norm": 0.5626171827316284, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0807, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04305949008498584, | |
| "grad_norm": 0.2916627526283264, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0341, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04419263456090652, | |
| "grad_norm": 0.47983884811401367, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.1236, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0453257790368272, | |
| "grad_norm": 0.7446145415306091, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1391, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04645892351274788, | |
| "grad_norm": 0.5644591450691223, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.1314, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04759206798866856, | |
| "grad_norm": 0.4467518627643585, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1334, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04872521246458923, | |
| "grad_norm": 0.28938040137290955, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0917, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04985835694050991, | |
| "grad_norm": 0.2925053536891937, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.136, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05099150141643059, | |
| "grad_norm": 0.2758999168872833, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1402, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05212464589235127, | |
| "grad_norm": 0.2369970977306366, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1282, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.053257790368271954, | |
| "grad_norm": 0.2726738154888153, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0924, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.054390934844192634, | |
| "grad_norm": 0.27999621629714966, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1117, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.055524079320113315, | |
| "grad_norm": 0.34448206424713135, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0974, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.056657223796033995, | |
| "grad_norm": 0.31993088126182556, | |
| "learning_rate": 0.0, | |
| "loss": 0.9778, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.056657223796033995, | |
| "eval_loss": 1.108001947402954, | |
| "eval_runtime": 180.4135, | |
| "eval_samples_per_second": 32.952, | |
| "eval_steps_per_second": 4.124, | |
| "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 | |
| } | |