| { | |
| "best_metric": 2.517580032348633, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.15791551519936833, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006316620607974733, | |
| "grad_norm": 1.0546115636825562, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1575, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006316620607974733, | |
| "eval_loss": 4.693485736846924, | |
| "eval_runtime": 12.1496, | |
| "eval_samples_per_second": 87.822, | |
| "eval_steps_per_second": 11.029, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012633241215949467, | |
| "grad_norm": 1.034112811088562, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4964, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0189498618239242, | |
| "grad_norm": 1.0966734886169434, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.4648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025266482431898933, | |
| "grad_norm": 1.093819260597229, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.257, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03158310303987367, | |
| "grad_norm": 1.0864986181259155, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.4582, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0378997236478484, | |
| "grad_norm": 1.3955763578414917, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.3022, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04421634425582313, | |
| "grad_norm": 1.4181126356124878, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.5895, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.050532964863797866, | |
| "grad_norm": 1.4454867839813232, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.3887, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0568495854717726, | |
| "grad_norm": 1.712357759475708, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.6758, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06316620607974734, | |
| "grad_norm": 1.7403721809387207, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.4681, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06948282668772207, | |
| "grad_norm": 1.7750122547149658, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5671, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0757994472956968, | |
| "grad_norm": 1.7761714458465576, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.612, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08211606790367154, | |
| "grad_norm": 1.295621633529663, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.9946, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08843268851164626, | |
| "grad_norm": 1.2954901456832886, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5626, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.094749309119621, | |
| "grad_norm": 1.24658203125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.456, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10106592972759573, | |
| "grad_norm": 1.1547346115112305, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.6964, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "grad_norm": 0.9776915311813354, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.5982, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1136991709435452, | |
| "grad_norm": 0.916656494140625, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.7325, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12001579155151994, | |
| "grad_norm": 1.0522651672363281, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.449, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12633241215949467, | |
| "grad_norm": 1.15105402469635, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.6179, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1326490327674694, | |
| "grad_norm": 1.0923116207122803, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.4007, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13896565337544414, | |
| "grad_norm": 1.48521089553833, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.6068, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14528227398341886, | |
| "grad_norm": 1.5622447729110718, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.1056, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1515988945913936, | |
| "grad_norm": 1.3226696252822876, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.8389, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15791551519936833, | |
| "grad_norm": 1.5947855710983276, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.1764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15791551519936833, | |
| "eval_loss": 2.517580032348633, | |
| "eval_runtime": 12.3821, | |
| "eval_samples_per_second": 86.172, | |
| "eval_steps_per_second": 10.822, | |
| "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": 5.29768176943104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |