| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7023705004389815, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014047410008779631, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014047410008779631, | |
| "eval_loss": NaN, | |
| "eval_runtime": 31.5356, | |
| "eval_samples_per_second": 15.221, | |
| "eval_steps_per_second": 3.805, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028094820017559263, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04214223002633889, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.056189640035118525, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07023705004389816, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08428446005267778, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09833187006145742, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11237928007023705, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1264266900790167, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14047410008779632, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15452151009657594, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16856892010535557, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1826163301141352, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1826163301141352, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.8963, | |
| "eval_samples_per_second": 15.536, | |
| "eval_steps_per_second": 3.884, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19666374012291485, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21071115013169447, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2247585601404741, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2528533801580334, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.266900790166813, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.28094820017559263, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.29499561018437226, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3090430201931519, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3230904302019315, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.33713784021071114, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.35118525021949076, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3652326602282704, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3652326602282704, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.8724, | |
| "eval_samples_per_second": 15.548, | |
| "eval_steps_per_second": 3.887, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.37928007023705007, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3933274802458297, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4073748902546093, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.42142230026338895, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4354697102721686, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4495171202809482, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4635645302897278, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4916593503072871, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5057067603160668, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5197541703248464, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.533801580333626, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5478489903424056, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5478489903424056, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.9187, | |
| "eval_samples_per_second": 15.525, | |
| "eval_steps_per_second": 3.881, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5618964003511853, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5759438103599649, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5899912203687445, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6040386303775241, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6180860403863038, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6321334503950834, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.646180860403863, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6602282704126426, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6742756804214223, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6883230904302019, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7023705004389815, | |
| "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": 4.411423186747392e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |