| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.069857697283312, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04139715394566624, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04139715394566624, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.0994, | |
| "eval_samples_per_second": 16.132, | |
| "eval_steps_per_second": 4.194, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08279430789133248, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12419146183699871, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995595519339882e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16558861578266496, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.982390699337252e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2069857697283312, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.960411389047366e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24838292367399742, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.929700614002265e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2897800776196636, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.890318491986281e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3311772315653299, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.842342115352646e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.37257438551099614, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.785865400111593e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4139715394566624, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.720998902085355e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4553686934023286, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.647869600489953e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.49676584734799484, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.566620649367419e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.538163001293661, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.477411097355024e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5795601552393272, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.380415576340125e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6209573091849935, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.27582395961002e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6623544631306598, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.163840990166085e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.703751617076326, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.044685879929732e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7451487710219923, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.918591880624782e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7865459249676585, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.785805827176255e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8279430789133247, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.646587654519414e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.869340232858991, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.501209888764928e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9107373868046572, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.349957113716212e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9521345407503234, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.193125413783259e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9935316946959897, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.031021794383513e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.034928848641656, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.863963580964344e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.034928848641656, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.1148, | |
| "eval_samples_per_second": 16.053, | |
| "eval_steps_per_second": 4.174, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.076326002587322, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.692277797823585e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1177231565329884, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.516300527944104e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1591203104786545, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.336376255095591e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2005174644243208, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.152857189491406e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2419146183699872, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.96610257832053e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2833117723156533, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.776478002504335e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.3247089262613194, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.584354661054765e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3661060802069858, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.390108644434829e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.407503234152652, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.19412019834386e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.4489003880983182, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9967729793687156e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4902975420439843, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.798453303957968e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.5316946959896507, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.599549392189342e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.573091849935317, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.40045060781066e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6144890038809832, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.201546696042033e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.6558861578266493, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.003227020631287e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6972833117723156, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.805879801656139e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.738680465717982, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6098913555651725e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.780077619663648, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4156453389452354e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.8214747736093142, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.223521997495665e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.8628719275549805, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0338974216794725e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.9042690815006469, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.847142810508596e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.9456662354463132, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6636237449044076e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.9870633893919794, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.483699472055897e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.0284605433376455, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.307722202176417e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.069857697283312, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.136036419035656e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.069857697283312, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.1151, | |
| "eval_samples_per_second": 16.051, | |
| "eval_steps_per_second": 4.173, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 73, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658124417499136e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |