| { | |
| "best_metric": 0.08991359174251556, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.3498349834983498, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.052805280528052806, | |
| "grad_norm": 240.3042449951172, | |
| "learning_rate": 5e-05, | |
| "loss": 61.3338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.052805280528052806, | |
| "eval_loss": 3.5627546310424805, | |
| "eval_runtime": 4.3018, | |
| "eval_samples_per_second": 29.755, | |
| "eval_steps_per_second": 3.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10561056105610561, | |
| "grad_norm": 312.2116394042969, | |
| "learning_rate": 0.0001, | |
| "loss": 55.4131, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 184.56300354003906, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 35.5412, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21122112211221122, | |
| "grad_norm": 111.88742065429688, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 19.9948, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.264026402640264, | |
| "grad_norm": 86.86764526367188, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 24.8855, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 132.280029296875, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 18.4034, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3696369636963696, | |
| "grad_norm": 144.69395446777344, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 15.066, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42244224422442245, | |
| "grad_norm": 64.07872772216797, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.6669, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 71.51905822753906, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 9.8098, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.528052805280528, | |
| "grad_norm": 96.21553802490234, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 19.7731, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5808580858085809, | |
| "grad_norm": 66.71566772460938, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.8857, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 56.84700393676758, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.1991, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6864686468646864, | |
| "grad_norm": 57.972469329833984, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 8.0601, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7392739273927392, | |
| "grad_norm": 61.932777404785156, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.777, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 61.04229736328125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 8.4654, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8448844884488449, | |
| "grad_norm": 55.51152801513672, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 5.9386, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8976897689768977, | |
| "grad_norm": 43.309749603271484, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.4815, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 49.29344177246094, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.9009, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.033003300330033, | |
| "grad_norm": 71.64353942871094, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 5.4645, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0858085808580857, | |
| "grad_norm": 54.31509017944336, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0766, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1386138613861387, | |
| "grad_norm": 80.26276397705078, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1301, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1914191419141915, | |
| "grad_norm": 56.407894134521484, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.6217, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2442244224422443, | |
| "grad_norm": 45.19135284423828, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4165, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.297029702970297, | |
| "grad_norm": 74.26824951171875, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.6401, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3498349834983498, | |
| "grad_norm": 48.40488052368164, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3498349834983498, | |
| "eval_loss": 0.08991359174251556, | |
| "eval_runtime": 4.5659, | |
| "eval_samples_per_second": 28.034, | |
| "eval_steps_per_second": 3.504, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.975768971501896e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |