| { | |
| "best_metric": 1.764018177986145, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08406893652795293, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016813787305590584, | |
| "grad_norm": 9.957021713256836, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016813787305590584, | |
| "eval_loss": 3.21144437789917, | |
| "eval_runtime": 53.0784, | |
| "eval_samples_per_second": 18.878, | |
| "eval_steps_per_second": 2.374, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003362757461118117, | |
| "grad_norm": 13.708298683166504, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1329, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005044136191677175, | |
| "grad_norm": 12.74589729309082, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1098, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006725514922236234, | |
| "grad_norm": 9.0891752243042, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8129, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008406893652795292, | |
| "grad_norm": 7.467917442321777, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5554, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01008827238335435, | |
| "grad_norm": 7.4391961097717285, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.2017, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011769651113913409, | |
| "grad_norm": 7.036105632781982, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.3765, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013451029844472467, | |
| "grad_norm": 11.589292526245117, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.1577, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015132408575031526, | |
| "grad_norm": 7.228753566741943, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.9935, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016813787305590584, | |
| "grad_norm": 8.207776069641113, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.8316, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018495166036149643, | |
| "grad_norm": 7.985312461853027, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.8113, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0201765447667087, | |
| "grad_norm": 7.26406192779541, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.8366, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02185792349726776, | |
| "grad_norm": 6.2105631828308105, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.7943, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023539302227826818, | |
| "grad_norm": 8.026552200317383, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.8496, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025220680958385876, | |
| "grad_norm": 6.089547634124756, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.4218, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026902059688944935, | |
| "grad_norm": 6.291636943817139, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.4374, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028583438419503993, | |
| "grad_norm": 13.020359992980957, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.9619, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03026481715006305, | |
| "grad_norm": 7.324967861175537, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.7719, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.031946195880622114, | |
| "grad_norm": 6.144652843475342, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.8435, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03362757461118117, | |
| "grad_norm": 4.967810153961182, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4193, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03530895334174023, | |
| "grad_norm": 4.567094802856445, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.5105, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.036990332072299285, | |
| "grad_norm": 4.7514328956604, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.6116, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03867171080285835, | |
| "grad_norm": 4.926995277404785, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6433, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0403530895334174, | |
| "grad_norm": 5.670762538909912, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.8285, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042034468263976464, | |
| "grad_norm": 4.81981897354126, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5872, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042034468263976464, | |
| "eval_loss": 1.8223572969436646, | |
| "eval_runtime": 53.8519, | |
| "eval_samples_per_second": 18.607, | |
| "eval_steps_per_second": 2.34, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04371584699453552, | |
| "grad_norm": 5.934324741363525, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.0369, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04539722572509458, | |
| "grad_norm": 4.599030017852783, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.6305, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.047078604455653636, | |
| "grad_norm": 4.753709316253662, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.9704, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0487599831862127, | |
| "grad_norm": 3.938774585723877, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.4958, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05044136191677175, | |
| "grad_norm": 4.442599773406982, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.7748, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.052122740647330815, | |
| "grad_norm": 4.685940742492676, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.8004, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05380411937788987, | |
| "grad_norm": 4.308958530426025, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.5518, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05548549810844893, | |
| "grad_norm": 4.3257737159729, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.7638, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.057166876839007986, | |
| "grad_norm": 4.2862324714660645, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.6903, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05884825556956705, | |
| "grad_norm": 4.446920394897461, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.5118, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0605296343001261, | |
| "grad_norm": 4.1637468338012695, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.7835, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.062211013030685165, | |
| "grad_norm": 5.5191144943237305, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.7005, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06389239176124423, | |
| "grad_norm": 4.147561073303223, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.5857, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 4.230316638946533, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8089, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06725514922236234, | |
| "grad_norm": 4.044164180755615, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.5085, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06893652795292139, | |
| "grad_norm": 4.815402507781982, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.6942, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07061790668348046, | |
| "grad_norm": 4.001568794250488, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.473, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07229928541403952, | |
| "grad_norm": 4.6987504959106445, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7146, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07398066414459857, | |
| "grad_norm": 4.370215892791748, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.6669, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07566204287515763, | |
| "grad_norm": 4.669373035430908, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.549, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0773434216057167, | |
| "grad_norm": 3.481714963912964, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.246, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07902480033627575, | |
| "grad_norm": 4.119218826293945, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.5097, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0807061790668348, | |
| "grad_norm": 4.261626243591309, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.262, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08238755779739386, | |
| "grad_norm": 4.05534553527832, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.2714, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08406893652795293, | |
| "grad_norm": 4.904563903808594, | |
| "learning_rate": 0.0, | |
| "loss": 1.3498, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08406893652795293, | |
| "eval_loss": 1.764018177986145, | |
| "eval_runtime": 53.8465, | |
| "eval_samples_per_second": 18.608, | |
| "eval_steps_per_second": 2.34, | |
| "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": 5, | |
| "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": 4.86582113009664e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |