| { | |
| "best_metric": 1.727027177810669, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008390845587464077, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.1954227937320384e-05, | |
| "eval_loss": 1.8378162384033203, | |
| "eval_runtime": 453.393, | |
| "eval_samples_per_second": 11.068, | |
| "eval_steps_per_second": 2.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041954227937320384, | |
| "grad_norm": 2.091989755630493, | |
| "learning_rate": 4.22e-05, | |
| "loss": 1.6646, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008390845587464077, | |
| "grad_norm": 2.7637720108032227, | |
| "learning_rate": 8.44e-05, | |
| "loss": 1.6956, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012586268381196116, | |
| "grad_norm": 1.8225716352462769, | |
| "learning_rate": 0.0001266, | |
| "loss": 1.4925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016781691174928154, | |
| "grad_norm": 2.2302634716033936, | |
| "learning_rate": 0.0001688, | |
| "loss": 1.7316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002097711396866019, | |
| "grad_norm": 3.6677043437957764, | |
| "learning_rate": 0.000211, | |
| "loss": 1.6306, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002097711396866019, | |
| "eval_loss": 1.727027177810669, | |
| "eval_runtime": 452.3372, | |
| "eval_samples_per_second": 11.093, | |
| "eval_steps_per_second": 2.774, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002517253676239223, | |
| "grad_norm": 4.509883403778076, | |
| "learning_rate": 0.00021074300730241147, | |
| "loss": 1.6763, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0029367959556124267, | |
| "grad_norm": 2.8632655143737793, | |
| "learning_rate": 0.00020997328125223568, | |
| "loss": 1.8204, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0033563382349856307, | |
| "grad_norm": 2.905240297317505, | |
| "learning_rate": 0.0002086945718774165, | |
| "loss": 1.822, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0037758805143588347, | |
| "grad_norm": 5.918646812438965, | |
| "learning_rate": 0.00020691310892149265, | |
| "loss": 1.7552, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004195422793732038, | |
| "grad_norm": 7.395406723022461, | |
| "learning_rate": 0.00020463757149291335, | |
| "loss": 1.5701, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004195422793732038, | |
| "eval_loss": 1.9698339700698853, | |
| "eval_runtime": 457.466, | |
| "eval_samples_per_second": 10.969, | |
| "eval_steps_per_second": 2.743, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004614965073105242, | |
| "grad_norm": 2.087064504623413, | |
| "learning_rate": 0.0002018790457812944, | |
| "loss": 1.7137, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.005034507352478446, | |
| "grad_norm": 1.7459348440170288, | |
| "learning_rate": 0.0001986509710466168, | |
| "loss": 1.7363, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.00545404963185165, | |
| "grad_norm": 2.1844427585601807, | |
| "learning_rate": 0.00019496907414450293, | |
| "loss": 1.7358, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0058735919112248534, | |
| "grad_norm": 2.2916972637176514, | |
| "learning_rate": 0.00019085129290655697, | |
| "loss": 1.7705, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.006293134190598058, | |
| "grad_norm": 2.5905094146728516, | |
| "learning_rate": 0.00018631768874905217, | |
| "loss": 1.7402, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006293134190598058, | |
| "eval_loss": 1.7718510627746582, | |
| "eval_runtime": 452.7846, | |
| "eval_samples_per_second": 11.083, | |
| "eval_steps_per_second": 2.772, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0067126764699712614, | |
| "grad_norm": 3.6152729988098145, | |
| "learning_rate": 0.0001813903489357277, | |
| "loss": 1.7279, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.007132218749344465, | |
| "grad_norm": 2.7611238956451416, | |
| "learning_rate": 0.00017609327897085954, | |
| "loss": 1.7047, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0075517610287176695, | |
| "grad_norm": 3.315603256225586, | |
| "learning_rate": 0.00017045228564685694, | |
| "loss": 1.8601, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.007971303308090873, | |
| "grad_norm": 4.356021881103516, | |
| "learning_rate": 0.0001644948513161638, | |
| "loss": 1.8429, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.008390845587464077, | |
| "grad_norm": 6.690892219543457, | |
| "learning_rate": 0.00015825, | |
| "loss": 1.5689, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.008390845587464077, | |
| "eval_loss": 1.9429612159729004, | |
| "eval_runtime": 452.8314, | |
| "eval_samples_per_second": 11.081, | |
| "eval_steps_per_second": 2.771, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.203800670568448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |