| { | |
| "best_metric": 0.3183044195175171, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.023789699060306885, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009515879624122755, | |
| "grad_norm": 1.2617084980010986, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3938, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009515879624122755, | |
| "eval_loss": 2.1877427101135254, | |
| "eval_runtime": 315.3854, | |
| "eval_samples_per_second": 22.449, | |
| "eval_steps_per_second": 2.806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001903175924824551, | |
| "grad_norm": 1.568479299545288, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0028547638872368263, | |
| "grad_norm": 1.221531629562378, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.3665, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003806351849649102, | |
| "grad_norm": 1.238847255706787, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1355, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0047579398120613774, | |
| "grad_norm": 0.9942885637283325, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8837, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005709527774473653, | |
| "grad_norm": 1.0231456756591797, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8066, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006661115736885929, | |
| "grad_norm": 1.036026954650879, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6627, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007612703699298204, | |
| "grad_norm": 0.6074243783950806, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.545, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00856429166171048, | |
| "grad_norm": 0.550236165523529, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5915, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009515879624122755, | |
| "grad_norm": 0.5943599939346313, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01046746758653503, | |
| "grad_norm": 0.4384642243385315, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.3643, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011419055548947305, | |
| "grad_norm": 0.45704734325408936, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4361, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012370643511359582, | |
| "grad_norm": 0.5538807511329651, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4251, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013322231473771857, | |
| "grad_norm": 0.5436851382255554, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.338, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014273819436184132, | |
| "grad_norm": 0.4750663936138153, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3306, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015225407398596407, | |
| "grad_norm": 0.4531807601451874, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.359, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016176995361008684, | |
| "grad_norm": 0.4036747217178345, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3712, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01712858332342096, | |
| "grad_norm": 0.3267797827720642, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3468, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018080171285833235, | |
| "grad_norm": 0.3159548044204712, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3777, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01903175924824551, | |
| "grad_norm": 0.33993765711784363, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3737, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019983347210657785, | |
| "grad_norm": 0.3903323709964752, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3492, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02093493517307006, | |
| "grad_norm": 0.3195224404335022, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3458, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.021886523135482335, | |
| "grad_norm": 0.36553213000297546, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3071, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02283811109789461, | |
| "grad_norm": 0.35281142592430115, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3406, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023789699060306885, | |
| "grad_norm": 0.3317332863807678, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3355, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023789699060306885, | |
| "eval_loss": 0.3183044195175171, | |
| "eval_runtime": 316.909, | |
| "eval_samples_per_second": 22.341, | |
| "eval_steps_per_second": 2.793, | |
| "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": 5.102842054443008e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |