| { | |
| "best_metric": 0.3007971942424774, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4804804804804805, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00960960960960961, | |
| "grad_norm": 15.39601993560791, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8756, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00960960960960961, | |
| "eval_loss": 7.646325588226318, | |
| "eval_runtime": 14.4833, | |
| "eval_samples_per_second": 48.401, | |
| "eval_steps_per_second": 6.076, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01921921921921922, | |
| "grad_norm": 16.163427352905273, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2556, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02882882882882883, | |
| "grad_norm": 33.284996032714844, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.0358, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03843843843843844, | |
| "grad_norm": 9.641700744628906, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.627, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04804804804804805, | |
| "grad_norm": 9.19076156616211, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.6859, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05765765765765766, | |
| "grad_norm": 8.365531921386719, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.7575, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06726726726726727, | |
| "grad_norm": 7.4769392013549805, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.0754, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07687687687687687, | |
| "grad_norm": 7.682229518890381, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4743, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "grad_norm": 7.058053970336914, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.8494, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0960960960960961, | |
| "grad_norm": 7.4664740562438965, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2984, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1057057057057057, | |
| "grad_norm": 7.336606502532959, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.688, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11531531531531532, | |
| "grad_norm": 6.41059684753418, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2399, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12492492492492492, | |
| "grad_norm": 4.18792200088501, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8169, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13453453453453454, | |
| "grad_norm": 5.746119499206543, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0413, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 9.597984313964844, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.6015, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15375375375375375, | |
| "grad_norm": 14.256322860717773, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4307, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16336336336336335, | |
| "grad_norm": 6.535587787628174, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7575, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17297297297297298, | |
| "grad_norm": 5.319492340087891, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7171, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1825825825825826, | |
| "grad_norm": 4.824494361877441, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5784, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1921921921921922, | |
| "grad_norm": 9.844202995300293, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7493, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2018018018018018, | |
| "grad_norm": 7.926790237426758, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6446, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2114114114114114, | |
| "grad_norm": 6.569388389587402, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4904, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22102102102102103, | |
| "grad_norm": 2.623183488845825, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4138, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.23063063063063063, | |
| "grad_norm": 4.689478397369385, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4675, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24024024024024024, | |
| "grad_norm": 8.908453941345215, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6329, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24024024024024024, | |
| "eval_loss": 0.45955586433410645, | |
| "eval_runtime": 14.5027, | |
| "eval_samples_per_second": 48.336, | |
| "eval_steps_per_second": 6.068, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24984984984984984, | |
| "grad_norm": 5.062581539154053, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4846, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2594594594594595, | |
| "grad_norm": 5.369364261627197, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4504, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2690690690690691, | |
| "grad_norm": 9.659736633300781, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2836, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2786786786786787, | |
| "grad_norm": 6.549679756164551, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4753, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 6.411563873291016, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4494, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2978978978978979, | |
| "grad_norm": 5.894447326660156, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.38, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3075075075075075, | |
| "grad_norm": 3.534438133239746, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4184, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3171171171171171, | |
| "grad_norm": 2.5293240547180176, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4075, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3267267267267267, | |
| "grad_norm": 1.8533108234405518, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3149, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.33633633633633636, | |
| "grad_norm": 2.5232226848602295, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4054, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.34594594594594597, | |
| "grad_norm": 1.6775366067886353, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.393, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 2.5080814361572266, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3019, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3651651651651652, | |
| "grad_norm": 2.5424108505249023, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3511, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3747747747747748, | |
| "grad_norm": 2.8998568058013916, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3987, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3843843843843844, | |
| "grad_norm": 5.538645267486572, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2767, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.393993993993994, | |
| "grad_norm": 4.446637153625488, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2942, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4036036036036036, | |
| "grad_norm": 2.0864498615264893, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3179, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4132132132132132, | |
| "grad_norm": 2.080223321914673, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2306, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4228228228228228, | |
| "grad_norm": 2.7075343132019043, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2878, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 2.4655637741088867, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3793, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.44204204204204206, | |
| "grad_norm": 1.119294285774231, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2866, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.45165165165165166, | |
| "grad_norm": 1.4257920980453491, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3256, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.46126126126126127, | |
| "grad_norm": 1.6645019054412842, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2609, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4708708708708709, | |
| "grad_norm": 1.221898078918457, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3151, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4804804804804805, | |
| "grad_norm": 1.8430705070495605, | |
| "learning_rate": 0.0, | |
| "loss": 0.3629, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4804804804804805, | |
| "eval_loss": 0.3007971942424774, | |
| "eval_runtime": 14.4599, | |
| "eval_samples_per_second": 48.479, | |
| "eval_steps_per_second": 6.086, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |