| { | |
| "best_metric": 1.1274107694625854, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.004597436928912131, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.2987184644560657e-05, | |
| "eval_loss": 2.365870714187622, | |
| "eval_runtime": 520.553, | |
| "eval_samples_per_second": 35.188, | |
| "eval_steps_per_second": 17.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022987184644560657, | |
| "grad_norm": 6.934662342071533, | |
| "learning_rate": 2.5e-06, | |
| "loss": 2.1972, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00045974369289121313, | |
| "grad_norm": 6.904849052429199, | |
| "learning_rate": 5e-06, | |
| "loss": 2.213, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006896155393368198, | |
| "grad_norm": 4.1402997970581055, | |
| "learning_rate": 7.5e-06, | |
| "loss": 2.1982, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009194873857824263, | |
| "grad_norm": 4.010258674621582, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6513, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0011493592322280328, | |
| "grad_norm": 4.718471527099609, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.2747, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0013792310786736395, | |
| "grad_norm": 3.8932864665985107, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.2147, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.001609102925119246, | |
| "grad_norm": 5.198622703552246, | |
| "learning_rate": 1.75e-05, | |
| "loss": 1.2063, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0018389747715648525, | |
| "grad_norm": 4.243978500366211, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1345, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0020688466180104593, | |
| "grad_norm": 4.224928379058838, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.1293, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0022987184644560656, | |
| "grad_norm": 5.764342784881592, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1988, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0022987184644560656, | |
| "eval_loss": 1.184658408164978, | |
| "eval_runtime": 520.0761, | |
| "eval_samples_per_second": 35.22, | |
| "eval_steps_per_second": 17.611, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0025285903109016723, | |
| "grad_norm": 3.7343056201934814, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 1.0981, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.002758462157347279, | |
| "grad_norm": 4.652059078216553, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2341, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0029883340037928853, | |
| "grad_norm": 4.9458231925964355, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 1.1237, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.003218205850238492, | |
| "grad_norm": 3.449315309524536, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.0449, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0034480776966840988, | |
| "grad_norm": 4.949376106262207, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.1911, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003677949543129705, | |
| "grad_norm": 5.409412384033203, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0661, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.003907821389575312, | |
| "grad_norm": 3.166673421859741, | |
| "learning_rate": 4.25e-05, | |
| "loss": 1.1751, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0041376932360209185, | |
| "grad_norm": 3.628138303756714, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.1335, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.004367565082466525, | |
| "grad_norm": 3.710859775543213, | |
| "learning_rate": 4.75e-05, | |
| "loss": 1.1087, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004597436928912131, | |
| "grad_norm": 3.711989164352417, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2195, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004597436928912131, | |
| "eval_loss": 1.1274107694625854, | |
| "eval_runtime": 521.4205, | |
| "eval_samples_per_second": 35.129, | |
| "eval_steps_per_second": 17.565, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "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": 2.13314785247232e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |