| { | |
| "best_metric": 2.251969814300537, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.1416179854841565, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005664719419366259, | |
| "grad_norm": 0.3443683981895447, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9168, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005664719419366259, | |
| "eval_loss": 2.444845676422119, | |
| "eval_runtime": 3.916, | |
| "eval_samples_per_second": 12.768, | |
| "eval_steps_per_second": 12.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011329438838732518, | |
| "grad_norm": 0.5582488179206848, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3278, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016994158258098777, | |
| "grad_norm": 0.483371376991272, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 2.0745, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022658877677465036, | |
| "grad_norm": 0.5079594850540161, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 2.2716, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0283235970968313, | |
| "grad_norm": 0.44041743874549866, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 2.192, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.033988316516197555, | |
| "grad_norm": 0.48330381512641907, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 2.3416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03965303593556382, | |
| "grad_norm": 0.4362412393093109, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 2.1494, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04531775535493007, | |
| "grad_norm": 0.49262771010398865, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 2.1951, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.050982474774296335, | |
| "grad_norm": 0.46403270959854126, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 2.2277, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0566471941936626, | |
| "grad_norm": 0.49751704931259155, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 2.4803, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06231191361302885, | |
| "grad_norm": 0.45801228284835815, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 2.2796, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06797663303239511, | |
| "grad_norm": 0.4925437569618225, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 2.2775, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07364135245176137, | |
| "grad_norm": 0.45191332697868347, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 2.1433, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07930607187112763, | |
| "grad_norm": 0.4636717438697815, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 2.2751, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0849707912904939, | |
| "grad_norm": 0.5389095544815063, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 2.2208, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09063551070986015, | |
| "grad_norm": 0.4916808605194092, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 2.2853, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09630023012922641, | |
| "grad_norm": 0.4722801148891449, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 2.2721, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10196494954859267, | |
| "grad_norm": 0.5063973069190979, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 2.1005, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10762966896795893, | |
| "grad_norm": 0.5103368759155273, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 2.2888, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1132943883873252, | |
| "grad_norm": 0.4835498332977295, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 2.3252, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11895910780669144, | |
| "grad_norm": 0.5425633788108826, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 2.1022, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1246238272260577, | |
| "grad_norm": 0.5605387687683105, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 2.302, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13028854664542397, | |
| "grad_norm": 0.5053781270980835, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 2.1258, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13595326606479022, | |
| "grad_norm": 0.556704580783844, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 2.3897, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1416179854841565, | |
| "grad_norm": 0.6257777810096741, | |
| "learning_rate": 1e-05, | |
| "loss": 2.343, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1416179854841565, | |
| "eval_loss": 2.251969814300537, | |
| "eval_runtime": 3.9167, | |
| "eval_samples_per_second": 12.766, | |
| "eval_steps_per_second": 12.766, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": 1.2876546834432e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |