| { | |
| "best_metric": 0.41177281737327576, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09030364600970764, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018060729201941528, | |
| "grad_norm": 1.1679450273513794, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6004, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018060729201941528, | |
| "eval_loss": 0.8847251534461975, | |
| "eval_runtime": 90.5294, | |
| "eval_samples_per_second": 41.202, | |
| "eval_steps_per_second": 5.159, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036121458403883056, | |
| "grad_norm": 1.3293408155441284, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7309, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005418218760582459, | |
| "grad_norm": 1.1348483562469482, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7001, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007224291680776611, | |
| "grad_norm": 0.891630232334137, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.654, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009030364600970764, | |
| "grad_norm": 0.6690797805786133, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.5954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010836437521164918, | |
| "grad_norm": 0.7938116788864136, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.4948, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01264251044135907, | |
| "grad_norm": 0.51275235414505, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.549, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014448583361553222, | |
| "grad_norm": 0.5153568983078003, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5082, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016254656281747375, | |
| "grad_norm": 0.4821842610836029, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5415, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018060729201941527, | |
| "grad_norm": 0.47277501225471497, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5302, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019866802122135683, | |
| "grad_norm": 0.46804219484329224, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.559, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.021672875042329835, | |
| "grad_norm": 0.5385531187057495, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5089, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023478947962523988, | |
| "grad_norm": 0.31599441170692444, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3866, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02528502088271814, | |
| "grad_norm": 0.31341472268104553, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4071, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.027091093802912292, | |
| "grad_norm": 0.3027861714363098, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4013, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028897166723106445, | |
| "grad_norm": 0.32209834456443787, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4672, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.030703239643300597, | |
| "grad_norm": 0.35165438055992126, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4605, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03250931256349475, | |
| "grad_norm": 0.3231716454029083, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.431, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.034315385483688905, | |
| "grad_norm": 0.28098562359809875, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4488, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.036121458403883054, | |
| "grad_norm": 0.29532745480537415, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4626, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03792753132407721, | |
| "grad_norm": 0.3408537805080414, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.487, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.039733604244271366, | |
| "grad_norm": 0.33273807168006897, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.444, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.041539677164465515, | |
| "grad_norm": 0.34283336997032166, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4601, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04334575008465967, | |
| "grad_norm": 0.3913612365722656, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5043, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04515182300485382, | |
| "grad_norm": 0.4402361810207367, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4355, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04515182300485382, | |
| "eval_loss": 0.4249492883682251, | |
| "eval_runtime": 90.4536, | |
| "eval_samples_per_second": 41.237, | |
| "eval_steps_per_second": 5.163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.046957895925047975, | |
| "grad_norm": 0.20495416224002838, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3645, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.048763968845242124, | |
| "grad_norm": 0.24285714328289032, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3556, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05057004176543628, | |
| "grad_norm": 0.25440144538879395, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4104, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.052376114685630436, | |
| "grad_norm": 0.2471897006034851, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4108, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.054182187605824585, | |
| "grad_norm": 0.26587310433387756, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.422, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05598826052601874, | |
| "grad_norm": 0.2613593339920044, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4146, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05779433344621289, | |
| "grad_norm": 0.2861674427986145, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4656, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.059600406366407045, | |
| "grad_norm": 0.2913093864917755, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4247, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.061406479286601194, | |
| "grad_norm": 0.3075777292251587, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.438, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06321255220679535, | |
| "grad_norm": 0.32408568263053894, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4746, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0650186251269895, | |
| "grad_norm": 0.34247300028800964, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4418, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06682469804718366, | |
| "grad_norm": 0.3859308362007141, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4453, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06863077096737781, | |
| "grad_norm": 0.2347421646118164, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.353, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07043684388757196, | |
| "grad_norm": 0.21311472356319427, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3831, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07224291680776611, | |
| "grad_norm": 0.22881631553173065, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4234, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07404898972796027, | |
| "grad_norm": 0.2297966629266739, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3825, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07585506264815442, | |
| "grad_norm": 0.2609304189682007, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4715, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07766113556834857, | |
| "grad_norm": 0.25210073590278625, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.41, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07946720848854273, | |
| "grad_norm": 0.2684996724128723, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4345, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08127328140873688, | |
| "grad_norm": 0.27470850944519043, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4293, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08307935432893103, | |
| "grad_norm": 0.27928435802459717, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4149, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08488542724912518, | |
| "grad_norm": 0.28541573882102966, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4271, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08669150016931934, | |
| "grad_norm": 0.30577269196510315, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.453, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08849757308951349, | |
| "grad_norm": 0.3629637658596039, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4461, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09030364600970764, | |
| "grad_norm": 0.3974674344062805, | |
| "learning_rate": 0.0, | |
| "loss": 0.4008, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09030364600970764, | |
| "eval_loss": 0.41177281737327576, | |
| "eval_runtime": 90.5093, | |
| "eval_samples_per_second": 41.211, | |
| "eval_steps_per_second": 5.16, | |
| "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": 1.5899604877626573e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |