| { | |
| "best_metric": 0.8158317804336548, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.39940089865202194, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01597603594608088, | |
| "grad_norm": 3.754645824432373, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8213, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01597603594608088, | |
| "eval_loss": 4.774369239807129, | |
| "eval_runtime": 0.8733, | |
| "eval_samples_per_second": 57.257, | |
| "eval_steps_per_second": 14.887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03195207189216176, | |
| "grad_norm": 4.066346645355225, | |
| "learning_rate": 0.0001, | |
| "loss": 4.008, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04792810783824263, | |
| "grad_norm": 3.6833364963531494, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 3.9832, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06390414378432352, | |
| "grad_norm": 7.125794887542725, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 3.95, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0798801797304044, | |
| "grad_norm": 7.377561569213867, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 3.2631, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09585621567648527, | |
| "grad_norm": 7.788794040679932, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 2.3484, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11183225162256615, | |
| "grad_norm": 5.947895050048828, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 2.084, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12780828756864704, | |
| "grad_norm": 6.4907050132751465, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 2.8501, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14378432351472792, | |
| "grad_norm": 8.412772178649902, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 3.5651, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1597603594608088, | |
| "grad_norm": 10.891843795776367, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 3.5416, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17573639540688968, | |
| "grad_norm": 11.607494354248047, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 2.8788, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19171243135297053, | |
| "grad_norm": 9.564980506896973, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 1.7524, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2076884672990514, | |
| "grad_norm": 6.569855690002441, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 1.7455, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2236645032451323, | |
| "grad_norm": 2.3155879974365234, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 1.5254, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23964053919121317, | |
| "grad_norm": 2.168813943862915, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 1.5916, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2556165751372941, | |
| "grad_norm": 2.051868438720703, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 1.2706, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.27159261108337496, | |
| "grad_norm": 3.016422986984253, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.7138, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.28756864702945584, | |
| "grad_norm": 3.377518653869629, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.5013, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3035446829755367, | |
| "grad_norm": 5.198056221008301, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.3902, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3195207189216176, | |
| "grad_norm": 5.946393013000488, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.6247, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3354967548676985, | |
| "grad_norm": 4.9002532958984375, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 1.6558, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.35147279081377936, | |
| "grad_norm": 7.489260673522949, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 2.4167, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.36744882675986024, | |
| "grad_norm": 8.54692554473877, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 1.8753, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.38342486270594106, | |
| "grad_norm": 7.267559051513672, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 1.7638, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39940089865202194, | |
| "grad_norm": 7.053504467010498, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5409, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39940089865202194, | |
| "eval_loss": 0.8158317804336548, | |
| "eval_runtime": 0.8858, | |
| "eval_samples_per_second": 56.445, | |
| "eval_steps_per_second": 14.676, | |
| "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": 4.172290816212992e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |