| { | |
| "best_metric": 0.2623326778411865, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.3714020427112349, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014856081708449397, | |
| "grad_norm": 12.877364158630371, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014856081708449397, | |
| "eval_loss": 2.4801716804504395, | |
| "eval_runtime": 3.1845, | |
| "eval_samples_per_second": 15.701, | |
| "eval_steps_per_second": 4.082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029712163416898793, | |
| "grad_norm": 13.52737045288086, | |
| "learning_rate": 0.0001, | |
| "loss": 2.497, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04456824512534819, | |
| "grad_norm": 11.447822570800781, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 1.6155, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.059424326833797586, | |
| "grad_norm": 4.801721096038818, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.4131, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07428040854224698, | |
| "grad_norm": 6.5657267570495605, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08913649025069638, | |
| "grad_norm": 1.8930745124816895, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.2925, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10399257195914577, | |
| "grad_norm": 2.2727997303009033, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.3141, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11884865366759517, | |
| "grad_norm": 0.4426746070384979, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.2571, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13370473537604458, | |
| "grad_norm": 1.8637906312942505, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.2943, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14856081708449395, | |
| "grad_norm": 0.5470730066299438, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.2635, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16341689879294335, | |
| "grad_norm": 0.6328050494194031, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.2608, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17827298050139276, | |
| "grad_norm": 1.073302984237671, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.3126, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19312906220984216, | |
| "grad_norm": 0.916024386882782, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.2678, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20798514391829154, | |
| "grad_norm": 0.5357609391212463, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.2662, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22284122562674094, | |
| "grad_norm": 0.5085605978965759, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.266, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23769730733519034, | |
| "grad_norm": 0.2650889456272125, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.2618, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2525533890436397, | |
| "grad_norm": 0.7138887643814087, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.2805, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26740947075208915, | |
| "grad_norm": 0.6649295687675476, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.2886, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2822655524605385, | |
| "grad_norm": 0.572088360786438, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.2651, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2971216341689879, | |
| "grad_norm": 0.5603142380714417, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.2658, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.31197771587743733, | |
| "grad_norm": 0.5217267870903015, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.2673, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3268337975858867, | |
| "grad_norm": 0.8165284395217896, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.2576, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.34168987929433614, | |
| "grad_norm": 0.42604365944862366, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.2482, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3565459610027855, | |
| "grad_norm": 0.24891525506973267, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.2606, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3714020427112349, | |
| "grad_norm": 0.43413084745407104, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2612, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3714020427112349, | |
| "eval_loss": 0.2623326778411865, | |
| "eval_runtime": 3.2444, | |
| "eval_samples_per_second": 15.411, | |
| "eval_steps_per_second": 4.007, | |
| "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": 2.984041808658432e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |