| { | |
| "best_metric": 1.3011465072631836, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.00909194226616661, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004545971133083305, | |
| "eval_loss": 3.4812397956848145, | |
| "eval_runtime": 12.463, | |
| "eval_samples_per_second": 74.38, | |
| "eval_steps_per_second": 37.23, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013637913399249914, | |
| "grad_norm": 42.1223030090332, | |
| "learning_rate": 6e-05, | |
| "loss": 14.3799, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022729855665416525, | |
| "eval_loss": 3.24287486076355, | |
| "eval_runtime": 11.9382, | |
| "eval_samples_per_second": 77.65, | |
| "eval_steps_per_second": 38.867, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002727582679849983, | |
| "grad_norm": 31.056917190551758, | |
| "learning_rate": 0.00012, | |
| "loss": 13.294, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004091374019774974, | |
| "grad_norm": 36.295265197753906, | |
| "learning_rate": 0.00018, | |
| "loss": 11.7909, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004545971133083305, | |
| "eval_loss": 2.3080296516418457, | |
| "eval_runtime": 12.0584, | |
| "eval_samples_per_second": 76.876, | |
| "eval_steps_per_second": 38.479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005455165359699966, | |
| "grad_norm": 39.956539154052734, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 8.7746, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006818956699624957, | |
| "grad_norm": 54.049015045166016, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.4937, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006818956699624957, | |
| "eval_loss": 1.537344217300415, | |
| "eval_runtime": 12.1276, | |
| "eval_samples_per_second": 76.437, | |
| "eval_steps_per_second": 38.26, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008182748039549948, | |
| "grad_norm": 91.98859405517578, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.0859, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00909194226616661, | |
| "eval_loss": 1.3011465072631836, | |
| "eval_runtime": 12.0011, | |
| "eval_samples_per_second": 77.243, | |
| "eval_steps_per_second": 38.663, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "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": 354006639575040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |