| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.362204724409449, |
| "eval_steps": 100, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07874015748031496, |
| "grad_norm": 3.9880661873949093, |
| "learning_rate": 2.564102564102564e-06, |
| "loss": 0.8813, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.15748031496062992, |
| "grad_norm": 3.6693616620597256, |
| "learning_rate": 5.128205128205128e-06, |
| "loss": 0.6636, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.23622047244094488, |
| "grad_norm": 2.199540616164596, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.4772, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.31496062992125984, |
| "grad_norm": 1.967802188964899, |
| "learning_rate": 9.999789047591563e-06, |
| "loss": 0.416, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3937007874015748, |
| "grad_norm": 1.9989660316683298, |
| "learning_rate": 9.974496289936769e-06, |
| "loss": 0.3917, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.47244094488188976, |
| "grad_norm": 2.0075383328381164, |
| "learning_rate": 9.90725746626209e-06, |
| "loss": 0.3851, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5511811023622047, |
| "grad_norm": 1.8508299028417263, |
| "learning_rate": 9.798639549376946e-06, |
| "loss": 0.3912, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6299212598425197, |
| "grad_norm": 2.02221509797565, |
| "learning_rate": 9.64955842986544e-06, |
| "loss": 0.3666, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7086614173228346, |
| "grad_norm": 2.074540853778448, |
| "learning_rate": 9.461271193091971e-06, |
| "loss": 0.3573, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7874015748031497, |
| "grad_norm": 1.7251665239071, |
| "learning_rate": 9.23536551917611e-06, |
| "loss": 0.367, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7874015748031497, |
| "eval_loss": 0.35987070202827454, |
| "eval_runtime": 44.8478, |
| "eval_samples_per_second": 5.017, |
| "eval_steps_per_second": 0.647, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8661417322834646, |
| "grad_norm": 1.797771958721456, |
| "learning_rate": 8.973746295318499e-06, |
| "loss": 0.3645, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9448818897637795, |
| "grad_norm": 1.8039826304958573, |
| "learning_rate": 8.67861955336566e-06, |
| "loss": 0.3521, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0236220472440944, |
| "grad_norm": 4.883591010598164, |
| "learning_rate": 8.352473868055746e-06, |
| "loss": 0.3345, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.1023622047244095, |
| "grad_norm": 1.4568352538600138, |
| "learning_rate": 7.998059372799409e-06, |
| "loss": 0.2637, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.1811023622047245, |
| "grad_norm": 1.5145500701439651, |
| "learning_rate": 7.61836456993939e-06, |
| "loss": 0.2607, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.2598425196850394, |
| "grad_norm": 1.6758721014591884, |
| "learning_rate": 7.2165911310299305e-06, |
| "loss": 0.2653, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.3385826771653544, |
| "grad_norm": 1.4962522667578417, |
| "learning_rate": 6.796126899625688e-06, |
| "loss": 0.2614, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.4173228346456692, |
| "grad_norm": 1.662185871879351, |
| "learning_rate": 6.360517324226676e-06, |
| "loss": 0.2528, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.4960629921259843, |
| "grad_norm": 1.5992237972859082, |
| "learning_rate": 5.913435562263036e-06, |
| "loss": 0.2614, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.574803149606299, |
| "grad_norm": 1.6376215727810626, |
| "learning_rate": 5.458651507209518e-06, |
| "loss": 0.2476, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.574803149606299, |
| "eval_loss": 0.35231101512908936, |
| "eval_runtime": 44.7548, |
| "eval_samples_per_second": 5.027, |
| "eval_steps_per_second": 0.648, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.6535433070866141, |
| "grad_norm": 1.5292608519655557, |
| "learning_rate": 5e-06, |
| "loss": 0.2528, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.7322834645669292, |
| "grad_norm": 1.5751478691748728, |
| "learning_rate": 4.541348492790482e-06, |
| "loss": 0.2432, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.811023622047244, |
| "grad_norm": 1.5142862198021734, |
| "learning_rate": 4.0865644377369666e-06, |
| "loss": 0.2498, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.889763779527559, |
| "grad_norm": 1.4779231579448862, |
| "learning_rate": 3.639482675773324e-06, |
| "loss": 0.2525, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.968503937007874, |
| "grad_norm": 1.4163589243219818, |
| "learning_rate": 3.203873100374314e-06, |
| "loss": 0.2503, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.047244094488189, |
| "grad_norm": 1.1803155886068133, |
| "learning_rate": 2.783408868970071e-06, |
| "loss": 0.1876, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.1259842519685037, |
| "grad_norm": 1.2574667771327577, |
| "learning_rate": 2.381635430060611e-06, |
| "loss": 0.1608, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.204724409448819, |
| "grad_norm": 1.3942256471439354, |
| "learning_rate": 2.0019406272005913e-06, |
| "loss": 0.1622, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.283464566929134, |
| "grad_norm": 1.1867880815644567, |
| "learning_rate": 1.6475261319442553e-06, |
| "loss": 0.1618, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.362204724409449, |
| "grad_norm": 1.2093026133477982, |
| "learning_rate": 1.321380446634342e-06, |
| "loss": 0.1736, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.362204724409449, |
| "eval_loss": 0.37573304772377014, |
| "eval_runtime": 45.0097, |
| "eval_samples_per_second": 4.999, |
| "eval_steps_per_second": 0.644, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 381, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 93586546753536.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
