| { | |
| "best_metric": 0.32214125990867615, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.034934497816593885, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013973799126637554, | |
| "grad_norm": 7.820697784423828, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1805, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013973799126637554, | |
| "eval_loss": 4.933597087860107, | |
| "eval_runtime": 375.1559, | |
| "eval_samples_per_second": 12.851, | |
| "eval_steps_per_second": 1.607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027947598253275107, | |
| "grad_norm": 9.600098609924316, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7853, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004192139737991266, | |
| "grad_norm": 8.434110641479492, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.0426, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0055895196506550214, | |
| "grad_norm": 8.16626262664795, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.6923, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0069868995633187774, | |
| "grad_norm": 5.467092514038086, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9109, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008384279475982533, | |
| "grad_norm": 2.6859490871429443, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.4587, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009781659388646289, | |
| "grad_norm": 1.7486851215362549, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.4249, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011179039301310043, | |
| "grad_norm": 2.7364816665649414, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4906, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012576419213973799, | |
| "grad_norm": 1.3542873859405518, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.3368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013973799126637555, | |
| "grad_norm": 1.4736709594726562, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3635, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015371179039301311, | |
| "grad_norm": 1.2249358892440796, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4126, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016768558951965065, | |
| "grad_norm": 1.3233370780944824, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5093, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01816593886462882, | |
| "grad_norm": 1.3505288362503052, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4471, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019563318777292577, | |
| "grad_norm": 1.5364714860916138, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3427, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02096069868995633, | |
| "grad_norm": 1.421094536781311, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022358078602620086, | |
| "grad_norm": 0.996880292892456, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3136, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023755458515283844, | |
| "grad_norm": 0.9842157363891602, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3173, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.025152838427947598, | |
| "grad_norm": 0.9777435064315796, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2663, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026550218340611352, | |
| "grad_norm": 0.8460299372673035, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3064, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02794759825327511, | |
| "grad_norm": 1.1061911582946777, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4295, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029344978165938864, | |
| "grad_norm": 0.8015987277030945, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2112, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030742358078602622, | |
| "grad_norm": 0.916122317314148, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3314, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.032139737991266376, | |
| "grad_norm": 1.1163928508758545, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3573, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03353711790393013, | |
| "grad_norm": 1.1232202053070068, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3437, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.034934497816593885, | |
| "grad_norm": 1.200721263885498, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4829, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034934497816593885, | |
| "eval_loss": 0.32214125990867615, | |
| "eval_runtime": 374.0514, | |
| "eval_samples_per_second": 12.889, | |
| "eval_steps_per_second": 1.612, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.315690861756416e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |