| { | |
| "best_metric": 10.361577987670898, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.006680584551148226, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026722338204592904, | |
| "grad_norm": 0.06674302369356155, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026722338204592904, | |
| "eval_loss": 10.367379188537598, | |
| "eval_runtime": 0.3778, | |
| "eval_samples_per_second": 132.361, | |
| "eval_steps_per_second": 132.361, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005344467640918581, | |
| "grad_norm": 0.08114143460988998, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3732, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008016701461377871, | |
| "grad_norm": 0.08357888460159302, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 10.3716, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010688935281837162, | |
| "grad_norm": 0.09477096796035767, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 10.3757, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013361169102296452, | |
| "grad_norm": 0.09584014117717743, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 10.378, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016033402922755742, | |
| "grad_norm": 0.09918414801359177, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 10.3785, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018705636743215031, | |
| "grad_norm": 0.0860179215669632, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 10.3759, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021377870563674324, | |
| "grad_norm": 0.1027856394648552, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 10.3695, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002405010438413361, | |
| "grad_norm": 0.10903847217559814, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 10.3724, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026722338204592903, | |
| "grad_norm": 0.09630134701728821, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 10.3704, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002939457202505219, | |
| "grad_norm": 0.09631078690290451, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 10.3733, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0032066805845511483, | |
| "grad_norm": 0.12749169766902924, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 10.3723, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003473903966597077, | |
| "grad_norm": 0.10507537424564362, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 10.368, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0037411273486430063, | |
| "grad_norm": 0.12678252160549164, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 10.3739, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0040083507306889355, | |
| "grad_norm": 0.11397404223680496, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 10.3731, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004275574112734865, | |
| "grad_norm": 0.11261963844299316, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 10.3742, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004542797494780793, | |
| "grad_norm": 0.13305383920669556, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 10.3719, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004810020876826722, | |
| "grad_norm": 0.15136480331420898, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 10.3702, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0050772442588726515, | |
| "grad_norm": 0.13255803287029266, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 10.3729, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005344467640918581, | |
| "grad_norm": 0.13422603905200958, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 10.3734, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005611691022964509, | |
| "grad_norm": 0.1134297102689743, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 10.3697, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005878914405010438, | |
| "grad_norm": 0.13355958461761475, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 10.3664, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006146137787056367, | |
| "grad_norm": 0.1270226091146469, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 10.371, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006413361169102297, | |
| "grad_norm": 0.14561836421489716, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 10.3746, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006680584551148226, | |
| "grad_norm": 0.09184999763965607, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3726, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006680584551148226, | |
| "eval_loss": 10.361577987670898, | |
| "eval_runtime": 0.3833, | |
| "eval_samples_per_second": 130.45, | |
| "eval_steps_per_second": 130.45, | |
| "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": 5599942803456.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |