| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.794044665012407, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01588089330024814, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01588089330024814, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5733, | |
| "eval_samples_per_second": 270.132, | |
| "eval_steps_per_second": 68.01, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03176178660049628, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04764267990074442, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06352357320099256, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0794044665012407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09528535980148883, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11116625310173697, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1270471464019851, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14292803970223325, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1588089330024814, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17468982630272953, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19057071960297767, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.08, | |
| "eval_samples_per_second": 393.51, | |
| "eval_steps_per_second": 99.072, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.22233250620347395, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23821339950372208, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2540942928039702, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2699751861042184, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2858560794044665, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.30173697270471467, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3176178660049628, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33349875930521095, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34937965260545906, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3652605459057072, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.38114143920595533, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3970223325062035, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.0823, | |
| "eval_samples_per_second": 392.688, | |
| "eval_steps_per_second": 98.865, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4287841191066998, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4446650124069479, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.46054590570719606, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.47642679900744417, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.49230769230769234, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5081885856079404, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5240694789081886, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5399503722084368, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5558312655086849, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.571712158808933, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5875930521091811, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6034739454094293, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6193548387096774, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6193548387096774, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.1208, | |
| "eval_samples_per_second": 379.182, | |
| "eval_steps_per_second": 95.465, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6352357320099256, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6511166253101737, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6669975186104219, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.68287841191067, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6987593052109181, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7146401985111662, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7305210918114144, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7464019851116626, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7622828784119107, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7781637717121588, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.794044665012407, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 166884645273600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |