| { | |
| "best_metric": 0.6473457217216492, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.007600589045651038, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015201178091302076, | |
| "grad_norm": 3.6806018352508545, | |
| "learning_rate": 5e-05, | |
| "loss": 10.9362, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015201178091302076, | |
| "eval_loss": 2.270036220550537, | |
| "eval_runtime": 2215.3772, | |
| "eval_samples_per_second": 20.005, | |
| "eval_steps_per_second": 2.501, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003040235618260415, | |
| "grad_norm": 4.281136512756348, | |
| "learning_rate": 0.0001, | |
| "loss": 12.8607, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00045603534273906226, | |
| "grad_norm": 4.480587959289551, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.5915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000608047123652083, | |
| "grad_norm": 5.4237823486328125, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 14.347, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007600589045651038, | |
| "grad_norm": 7.418390274047852, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 16.8128, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009120706854781245, | |
| "grad_norm": 7.381852149963379, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 16.2258, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010640824663911454, | |
| "grad_norm": 8.722169876098633, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 16.6006, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001216094247304166, | |
| "grad_norm": 18.175546646118164, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 19.5808, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013681060282171868, | |
| "grad_norm": 56.33650207519531, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 27.3127, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015201178091302076, | |
| "grad_norm": 42.97586441040039, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 25.7631, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016721295900432283, | |
| "grad_norm": 37.800636291503906, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 25.2524, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001824141370956249, | |
| "grad_norm": 23.808109283447266, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 19.2508, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00197615315186927, | |
| "grad_norm": 5.850672721862793, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.7128, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0021281649327822907, | |
| "grad_norm": 1.9108561277389526, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.8461, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0022801767136953113, | |
| "grad_norm": 1.9549922943115234, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 9.9272, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002432188494608332, | |
| "grad_norm": 2.2086598873138428, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.741, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0025842002755213527, | |
| "grad_norm": 3.0374670028686523, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.058, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0027362120564343737, | |
| "grad_norm": 4.240527153015137, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 12.878, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0028882238373473946, | |
| "grad_norm": 5.368109703063965, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.87, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003040235618260415, | |
| "grad_norm": 6.570104598999023, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.8896, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003192247399173436, | |
| "grad_norm": 12.811237335205078, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.5877, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0033442591800864566, | |
| "grad_norm": 11.7667236328125, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 9.7508, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0034962709609994776, | |
| "grad_norm": 14.377885818481445, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.7073, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003648282741912498, | |
| "grad_norm": 17.36256980895996, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 12.8663, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003800294522825519, | |
| "grad_norm": 9.72043514251709, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 12.1365, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003800294522825519, | |
| "eval_loss": 0.6713224649429321, | |
| "eval_runtime": 2215.1165, | |
| "eval_samples_per_second": 20.007, | |
| "eval_steps_per_second": 2.501, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00395230630373854, | |
| "grad_norm": 1.512826681137085, | |
| "learning_rate": 5e-05, | |
| "loss": 8.0772, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00410431808465156, | |
| "grad_norm": 1.6408687829971313, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 9.5961, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0042563298655645815, | |
| "grad_norm": 1.6432344913482666, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 9.4028, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004408341646477602, | |
| "grad_norm": 1.914554238319397, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 9.7971, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0045603534273906225, | |
| "grad_norm": 2.6982667446136475, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.672, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004712365208303644, | |
| "grad_norm": 3.2684669494628906, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.3321, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004864376989216664, | |
| "grad_norm": 5.5247673988342285, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.4821, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005016388770129685, | |
| "grad_norm": 7.938380718231201, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.5395, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0051684005510427055, | |
| "grad_norm": 17.899473190307617, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.4639, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005320412331955727, | |
| "grad_norm": 15.6568603515625, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.7289, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005472424112868747, | |
| "grad_norm": 19.337913513183594, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 12.1577, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005624435893781768, | |
| "grad_norm": 9.574126243591309, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.734, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005776447674694789, | |
| "grad_norm": 4.890590667724609, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.5739, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00592845945560781, | |
| "grad_norm": 1.0297945737838745, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 8.4116, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00608047123652083, | |
| "grad_norm": 1.167446494102478, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 9.198, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006232483017433851, | |
| "grad_norm": 1.3607698678970337, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 9.9207, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006384494798346872, | |
| "grad_norm": 2.091355562210083, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 9.8158, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006536506579259893, | |
| "grad_norm": 2.1468160152435303, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.94, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006688518360172913, | |
| "grad_norm": 2.633211374282837, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.1247, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006840530141085934, | |
| "grad_norm": 2.935201644897461, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.9623, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006992541921998955, | |
| "grad_norm": 11.325116157531738, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.6999, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007144553702911976, | |
| "grad_norm": 10.919002532958984, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.5474, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007296565483824996, | |
| "grad_norm": 12.799827575683594, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 12.6207, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007448577264738018, | |
| "grad_norm": 15.819369316101074, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.777, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007600589045651038, | |
| "grad_norm": 11.305403709411621, | |
| "learning_rate": 0.0, | |
| "loss": 12.5455, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007600589045651038, | |
| "eval_loss": 0.6473457217216492, | |
| "eval_runtime": 2211.064, | |
| "eval_samples_per_second": 20.044, | |
| "eval_steps_per_second": 2.506, | |
| "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": 1.1089660061406986e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |