| { | |
| "best_metric": 0.3158932328224182, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.5369127516778524, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021476510067114093, | |
| "grad_norm": 260.48162841796875, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021476510067114093, | |
| "eval_loss": 7.360443115234375, | |
| "eval_runtime": 15.4126, | |
| "eval_samples_per_second": 20.373, | |
| "eval_steps_per_second": 2.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.042953020134228186, | |
| "grad_norm": 297.0155334472656, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0084, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06442953020134229, | |
| "grad_norm": 275.2556457519531, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.6849, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08590604026845637, | |
| "grad_norm": 352.376708984375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.7447, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "grad_norm": 91.99493408203125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.502, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12885906040268458, | |
| "grad_norm": 46.79368591308594, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1112, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15033557046979865, | |
| "grad_norm": 24.683958053588867, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6324, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17181208053691274, | |
| "grad_norm": 29.150592803955078, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.947, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19328859060402684, | |
| "grad_norm": 47.48466491699219, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1741, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21476510067114093, | |
| "grad_norm": 216.91615295410156, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23624161073825503, | |
| "grad_norm": 94.46873474121094, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0293, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.25771812080536916, | |
| "grad_norm": 29.807615280151367, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1499, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2791946308724832, | |
| "grad_norm": 17.8881778717041, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6092, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3006711409395973, | |
| "grad_norm": 17.096132278442383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.487, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3221476510067114, | |
| "grad_norm": 16.282032012939453, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5441, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3436241610738255, | |
| "grad_norm": 17.785125732421875, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4419, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3651006711409396, | |
| "grad_norm": 15.897377967834473, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3437, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3865771812080537, | |
| "grad_norm": 12.955235481262207, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2397, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4080536912751678, | |
| "grad_norm": 14.379870414733887, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2507, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.42953020134228187, | |
| "grad_norm": 24.634723663330078, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.45100671140939597, | |
| "grad_norm": 24.113536834716797, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.343, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.47248322147651006, | |
| "grad_norm": 21.331897735595703, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3353, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.49395973154362416, | |
| "grad_norm": 30.45175552368164, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4716, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5154362416107383, | |
| "grad_norm": 57.83376693725586, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9978, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5369127516778524, | |
| "grad_norm": 33.72331237792969, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5804, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5369127516778524, | |
| "eval_loss": 0.3158932328224182, | |
| "eval_runtime": 15.3909, | |
| "eval_samples_per_second": 20.402, | |
| "eval_steps_per_second": 2.599, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.4965751695382938e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |