| { | |
| "best_metric": 0.8677180409431458, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.049782202862476664, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002489110143123833, | |
| "eval_loss": 1.071514368057251, | |
| "eval_runtime": 26.2873, | |
| "eval_samples_per_second": 6.467, | |
| "eval_steps_per_second": 3.234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0074673304293715, | |
| "grad_norm": 1.1961745023727417, | |
| "learning_rate": 0.00012, | |
| "loss": 4.1553, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012445550715619166, | |
| "eval_loss": 0.9948152303695679, | |
| "eval_runtime": 26.9512, | |
| "eval_samples_per_second": 6.308, | |
| "eval_steps_per_second": 3.154, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014934660858743, | |
| "grad_norm": 0.9607791900634766, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 4.028, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0224019912881145, | |
| "grad_norm": 1.9440590143203735, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 3.8453, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024891101431238332, | |
| "eval_loss": 0.9185737371444702, | |
| "eval_runtime": 27.0548, | |
| "eval_samples_per_second": 6.284, | |
| "eval_steps_per_second": 3.142, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029869321717486, | |
| "grad_norm": 1.371448278427124, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 3.636, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.037336652146857496, | |
| "grad_norm": 1.3308101892471313, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.5174, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.037336652146857496, | |
| "eval_loss": 0.8843600749969482, | |
| "eval_runtime": 27.1081, | |
| "eval_samples_per_second": 6.271, | |
| "eval_steps_per_second": 3.136, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.044803982576229, | |
| "grad_norm": 1.197558045387268, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 3.4537, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.049782202862476664, | |
| "eval_loss": 0.8677180409431458, | |
| "eval_runtime": 26.9775, | |
| "eval_samples_per_second": 6.302, | |
| "eval_steps_per_second": 3.151, | |
| "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": 1.14344142569472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |