| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.4527629233511585, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.318, | |
| "eval_samples_per_second": 11.579, | |
| "eval_steps_per_second": 3.011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1140819964349376, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991464979316699e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2281639928698752, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.965892293523712e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.28520499108734404, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.923378948577559e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3422459893048128, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.864086212157544e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.39928698752228164, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.788239001922206e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4563279857397504, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6961250323196e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5133689839572193, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.588093723187857e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5704099821746881, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.46455487428603e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.325977110783264e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6844919786096256, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.172886105602998e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7415329768270945, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.005862585365517e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7985739750445633, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.825540127492967e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8556149732620321, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.632602756833172e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9126559714795008, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.42778235091909e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.211855863706654e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.053475935828877, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.985642378322276e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1105169340463459, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1675579322638145, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.505822600994424e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2245989304812834, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.254036429817058e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2816399286987523, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.995596597658468e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.338680926916221, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.731483455324374e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3957219251336899, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.462698874429239e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4527629233511585, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.190262446954085e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4527629233511585, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3166, | |
| "eval_samples_per_second": 11.583, | |
| "eval_steps_per_second": 3.012, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 53, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8346698791124992e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |