| { | |
| "best_metric": 1.272352933883667, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.003279226102639777, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010930753675465924, | |
| "eval_loss": 2.349029064178467, | |
| "eval_runtime": 535.0854, | |
| "eval_samples_per_second": 14.398, | |
| "eval_steps_per_second": 3.599, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003279226102639777, | |
| "grad_norm": 1.6508804559707642, | |
| "learning_rate": 0.00012, | |
| "loss": 8.3983, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005465376837732962, | |
| "eval_loss": 2.2002480030059814, | |
| "eval_runtime": 535.5422, | |
| "eval_samples_per_second": 14.385, | |
| "eval_steps_per_second": 3.596, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006558452205279554, | |
| "grad_norm": 1.2677751779556274, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 8.2811, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000983767830791933, | |
| "grad_norm": 2.299318552017212, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 8.1526, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010930753675465923, | |
| "eval_loss": 1.7959991693496704, | |
| "eval_runtime": 534.2285, | |
| "eval_samples_per_second": 14.421, | |
| "eval_steps_per_second": 3.605, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013116904410559109, | |
| "grad_norm": 2.7058610916137695, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 7.2496, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0016396130513198885, | |
| "grad_norm": 2.855307102203369, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.4188, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016396130513198885, | |
| "eval_loss": 1.5014851093292236, | |
| "eval_runtime": 535.2673, | |
| "eval_samples_per_second": 14.393, | |
| "eval_steps_per_second": 3.598, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001967535661583866, | |
| "grad_norm": 2.154188394546509, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 5.6362, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0021861507350931847, | |
| "eval_loss": 1.33818519115448, | |
| "eval_runtime": 534.8762, | |
| "eval_samples_per_second": 14.403, | |
| "eval_steps_per_second": 3.601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002295458271847844, | |
| "grad_norm": 2.25827956199646, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 6.1886, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0026233808821118218, | |
| "grad_norm": 1.7416315078735352, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 5.4143, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002732688418866481, | |
| "eval_loss": 1.2895269393920898, | |
| "eval_runtime": 534.2014, | |
| "eval_samples_per_second": 14.422, | |
| "eval_steps_per_second": 3.605, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002951303492375799, | |
| "grad_norm": 2.217322826385498, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 4.8088, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003279226102639777, | |
| "grad_norm": 2.894871234893799, | |
| "learning_rate": 0.0, | |
| "loss": 4.8256, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003279226102639777, | |
| "eval_loss": 1.272352933883667, | |
| "eval_runtime": 535.3969, | |
| "eval_samples_per_second": 14.389, | |
| "eval_steps_per_second": 3.597, | |
| "step": 30 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6512572694003712.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |