| { | |
| "best_metric": 2.953709840774536, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.01811922449719152, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.05961224859576e-05, | |
| "eval_loss": 5.916714191436768, | |
| "eval_runtime": 778.909, | |
| "eval_samples_per_second": 5.967, | |
| "eval_steps_per_second": 2.984, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000905961224859576, | |
| "grad_norm": 7.96359395980835, | |
| "learning_rate": 1e-05, | |
| "loss": 5.5292, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001811922449719152, | |
| "grad_norm": 7.275904655456543, | |
| "learning_rate": 2e-05, | |
| "loss": 4.9062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002717883674578728, | |
| "grad_norm": 6.696507453918457, | |
| "learning_rate": 3e-05, | |
| "loss": 3.6854, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003623844899438304, | |
| "grad_norm": 8.084734916687012, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3666, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00452980612429788, | |
| "grad_norm": 5.354772090911865, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0034, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005435767349157456, | |
| "grad_norm": 5.084025859832764, | |
| "learning_rate": 6e-05, | |
| "loss": 3.0904, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.006341728574017032, | |
| "grad_norm": 6.143799781799316, | |
| "learning_rate": 7e-05, | |
| "loss": 3.0085, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.007247689798876608, | |
| "grad_norm": 4.883930206298828, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0715, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.008153651023736184, | |
| "grad_norm": 5.013826847076416, | |
| "learning_rate": 9e-05, | |
| "loss": 2.8267, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.00905961224859576, | |
| "grad_norm": 4.358269214630127, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1339, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00905961224859576, | |
| "eval_loss": 3.037921667098999, | |
| "eval_runtime": 785.1635, | |
| "eval_samples_per_second": 5.92, | |
| "eval_steps_per_second": 2.96, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.009965573473455336, | |
| "grad_norm": 4.184726238250732, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.1687, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.010871534698314912, | |
| "grad_norm": 5.467559814453125, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.0523, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.011777495923174489, | |
| "grad_norm": 4.539832592010498, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.9123, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.012683457148034065, | |
| "grad_norm": 6.541698932647705, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 3.0405, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01358941837289364, | |
| "grad_norm": 4.431535243988037, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1148, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.014495379597753216, | |
| "grad_norm": 4.524734020233154, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 3.0427, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.015401340822612792, | |
| "grad_norm": 4.3518385887146, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.9297, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01630730204747237, | |
| "grad_norm": 3.8135385513305664, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.9592, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.017213263272331945, | |
| "grad_norm": 3.840271472930908, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 2.7632, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01811922449719152, | |
| "grad_norm": 4.834849834442139, | |
| "learning_rate": 0.0, | |
| "loss": 2.9525, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01811922449719152, | |
| "eval_loss": 2.953709840774536, | |
| "eval_runtime": 784.593, | |
| "eval_samples_per_second": 5.924, | |
| "eval_steps_per_second": 2.962, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 1.541498927579136e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |