| { | |
| "best_metric": 0.025279613211750984, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03390692548953124, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013562770195812495, | |
| "grad_norm": 8.829853057861328, | |
| "learning_rate": 5e-05, | |
| "loss": 5.48, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013562770195812495, | |
| "eval_loss": 5.35487174987793, | |
| "eval_runtime": 178.9569, | |
| "eval_samples_per_second": 27.755, | |
| "eval_steps_per_second": 3.47, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002712554039162499, | |
| "grad_norm": 8.493329048156738, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3874, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004068831058743749, | |
| "grad_norm": 8.060304641723633, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.1312, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005425108078324998, | |
| "grad_norm": 7.588632106781006, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.652, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006781385097906247, | |
| "grad_norm": 8.079386711120605, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008137662117487498, | |
| "grad_norm": 13.640036582946777, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1052, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009493939137068747, | |
| "grad_norm": 3.801544189453125, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.209, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010850216156649996, | |
| "grad_norm": 4.697356224060059, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1661, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012206493176231245, | |
| "grad_norm": 2.2616631984710693, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1281, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013562770195812495, | |
| "grad_norm": 1.0779037475585938, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0734, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014919047215393744, | |
| "grad_norm": 1.0886865854263306, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.057, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016275324234974995, | |
| "grad_norm": 1.1330660581588745, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0881, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017631601254556244, | |
| "grad_norm": 2.9014949798583984, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2475, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018987878274137494, | |
| "grad_norm": 2.011962413787842, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0849, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020344155293718743, | |
| "grad_norm": 1.3376178741455078, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0453, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021700432313299992, | |
| "grad_norm": 1.0635402202606201, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.044, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02305670933288124, | |
| "grad_norm": 0.9886969327926636, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0533, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02441298635246249, | |
| "grad_norm": 0.8168627619743347, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0379, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02576926337204374, | |
| "grad_norm": 0.34220975637435913, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0313, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02712554039162499, | |
| "grad_norm": 0.5813488960266113, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0297, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02848181741120624, | |
| "grad_norm": 0.6970713138580322, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0564, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029838094430787488, | |
| "grad_norm": 0.5031370520591736, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0281, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031194371450368737, | |
| "grad_norm": 0.43404918909072876, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0374, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03255064846994999, | |
| "grad_norm": 0.3055057227611542, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0205, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03390692548953124, | |
| "grad_norm": 0.399833083152771, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0298, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03390692548953124, | |
| "eval_loss": 0.025279613211750984, | |
| "eval_runtime": 178.8888, | |
| "eval_samples_per_second": 27.766, | |
| "eval_steps_per_second": 3.471, | |
| "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": 3.411614392909824e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |