| { | |
| "best_metric": 1.5350492000579834, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.1718213058419244, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000859106529209622, | |
| "eval_loss": 2.4528794288635254, | |
| "eval_runtime": 36.5626, | |
| "eval_samples_per_second": 13.402, | |
| "eval_steps_per_second": 3.364, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00859106529209622, | |
| "grad_norm": 3.842317581176758, | |
| "learning_rate": 5.05e-06, | |
| "loss": 2.3208, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01718213058419244, | |
| "grad_norm": 1.7511423826217651, | |
| "learning_rate": 1.01e-05, | |
| "loss": 2.1038, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02577319587628866, | |
| "grad_norm": 0.6390647292137146, | |
| "learning_rate": 9.538888888888889e-06, | |
| "loss": 1.6949, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03436426116838488, | |
| "grad_norm": 0.8226912617683411, | |
| "learning_rate": 8.977777777777778e-06, | |
| "loss": 1.6081, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0429553264604811, | |
| "grad_norm": 1.4054566621780396, | |
| "learning_rate": 8.416666666666667e-06, | |
| "loss": 1.7309, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0429553264604811, | |
| "eval_loss": 1.6015360355377197, | |
| "eval_runtime": 36.8118, | |
| "eval_samples_per_second": 13.311, | |
| "eval_steps_per_second": 3.341, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05154639175257732, | |
| "grad_norm": 0.49393361806869507, | |
| "learning_rate": 7.855555555555556e-06, | |
| "loss": 1.5143, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06013745704467354, | |
| "grad_norm": 0.4182685911655426, | |
| "learning_rate": 7.294444444444444e-06, | |
| "loss": 1.5843, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06872852233676977, | |
| "grad_norm": 0.5429704785346985, | |
| "learning_rate": 6.733333333333333e-06, | |
| "loss": 1.5534, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07731958762886598, | |
| "grad_norm": 0.7752597332000732, | |
| "learning_rate": 6.172222222222223e-06, | |
| "loss": 1.5595, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0859106529209622, | |
| "grad_norm": 1.1356843709945679, | |
| "learning_rate": 5.611111111111111e-06, | |
| "loss": 1.6458, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0859106529209622, | |
| "eval_loss": 1.5543313026428223, | |
| "eval_runtime": 36.4615, | |
| "eval_samples_per_second": 13.439, | |
| "eval_steps_per_second": 3.373, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09450171821305842, | |
| "grad_norm": 0.41234856843948364, | |
| "learning_rate": 5.05e-06, | |
| "loss": 1.4694, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10309278350515463, | |
| "grad_norm": 0.45751872658729553, | |
| "learning_rate": 4.488888888888889e-06, | |
| "loss": 1.5459, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.11168384879725086, | |
| "grad_norm": 0.4848977327346802, | |
| "learning_rate": 3.927777777777778e-06, | |
| "loss": 1.4818, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.12027491408934708, | |
| "grad_norm": 0.6670855283737183, | |
| "learning_rate": 3.3666666666666665e-06, | |
| "loss": 1.5387, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12886597938144329, | |
| "grad_norm": 1.1316231489181519, | |
| "learning_rate": 2.8055555555555555e-06, | |
| "loss": 1.5887, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12886597938144329, | |
| "eval_loss": 1.5382037162780762, | |
| "eval_runtime": 36.6812, | |
| "eval_samples_per_second": 13.358, | |
| "eval_steps_per_second": 3.353, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13745704467353953, | |
| "grad_norm": 0.4882570207118988, | |
| "learning_rate": 2.2444444444444445e-06, | |
| "loss": 1.4184, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14604810996563575, | |
| "grad_norm": 0.4242735207080841, | |
| "learning_rate": 1.6833333333333332e-06, | |
| "loss": 1.5099, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15463917525773196, | |
| "grad_norm": 0.5443804860115051, | |
| "learning_rate": 1.1222222222222222e-06, | |
| "loss": 1.4786, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.16323024054982818, | |
| "grad_norm": 0.6373876929283142, | |
| "learning_rate": 5.611111111111111e-07, | |
| "loss": 1.5083, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1718213058419244, | |
| "grad_norm": 1.4106392860412598, | |
| "learning_rate": 0.0, | |
| "loss": 1.5946, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1718213058419244, | |
| "eval_loss": 1.5350492000579834, | |
| "eval_runtime": 36.6428, | |
| "eval_samples_per_second": 13.372, | |
| "eval_steps_per_second": 3.357, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.925036081152e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |