| { | |
| "best_metric": 1.3445146083831787, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.1299435028248588, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 0.44638949632644653, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "eval_loss": 1.8486380577087402, | |
| "eval_runtime": 2.6606, | |
| "eval_samples_per_second": 56.378, | |
| "eval_steps_per_second": 7.141, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 0.6294108033180237, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6111, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 0.6636074185371399, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.731, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 0.650401771068573, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7914, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 0.7133181691169739, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7302, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 0.3775063157081604, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.5634, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3163841807909605, | |
| "grad_norm": 0.31381529569625854, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.484, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 0.43298181891441345, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4775, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 0.6578243374824524, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4816, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 1.1834920644760132, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4971751412429379, | |
| "grad_norm": 1.7032532691955566, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4201, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 0.25004395842552185, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4841, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5875706214689266, | |
| "grad_norm": 0.2866630256175995, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3962, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.632768361581921, | |
| "grad_norm": 0.6441053748130798, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3796, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 1.2238999605178833, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.3343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7231638418079096, | |
| "grad_norm": 0.8174284100532532, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.3046, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.768361581920904, | |
| "grad_norm": 0.1801910400390625, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4167, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 0.23991882801055908, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3859, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8587570621468926, | |
| "grad_norm": 0.3171876072883606, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3732, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 0.4910401701927185, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3878, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 0.6115542650222778, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3144, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9943502824858758, | |
| "grad_norm": 0.7648242115974426, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3021, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.03954802259887, | |
| "grad_norm": 0.49429404735565186, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.6061, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 0.2421720325946808, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3316, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1299435028248588, | |
| "grad_norm": 0.25602591037750244, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3211, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1299435028248588, | |
| "eval_loss": 1.3445146083831787, | |
| "eval_runtime": 2.654, | |
| "eval_samples_per_second": 56.518, | |
| "eval_steps_per_second": 7.159, | |
| "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": 1.114626154561536e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |