| { | |
| "best_metric": 1.0091651678085327, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.43859649122807015, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": 0.6256651282310486, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "eval_loss": 1.606587529182434, | |
| "eval_runtime": 25.304, | |
| "eval_samples_per_second": 30.351, | |
| "eval_steps_per_second": 3.794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 0.7196914553642273, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4337, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 0.8423077464103699, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.5552, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 0.7354693412780762, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.44, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.043859649122807015, | |
| "grad_norm": 0.6117159128189087, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.3088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 0.6964637637138367, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3782, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06140350877192982, | |
| "grad_norm": 0.7088603973388672, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.2632, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.6772552728652954, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2607, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 0.6299393773078918, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1953, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "grad_norm": 0.6959410905838013, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.2019, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09649122807017543, | |
| "grad_norm": 0.6858323216438293, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1642, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.6745652556419373, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2065, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11403508771929824, | |
| "grad_norm": 0.5991556644439697, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9052, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12280701754385964, | |
| "grad_norm": 0.5269864201545715, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0334, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 0.4674125015735626, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0057, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.43285074830055237, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0698, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14912280701754385, | |
| "grad_norm": 0.43010246753692627, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0519, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 0.4448522627353668, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.062, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.41968226432800293, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1014, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 0.411808580160141, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0831, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 0.42560112476348877, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0465, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19298245614035087, | |
| "grad_norm": 0.4564867615699768, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.058, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20175438596491227, | |
| "grad_norm": 0.4590471386909485, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1247, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.4467829167842865, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0775, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21929824561403508, | |
| "grad_norm": 0.49387234449386597, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.15, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21929824561403508, | |
| "eval_loss": 1.0383129119873047, | |
| "eval_runtime": 25.3278, | |
| "eval_samples_per_second": 30.322, | |
| "eval_steps_per_second": 3.79, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22807017543859648, | |
| "grad_norm": 0.5108039975166321, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8292, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 0.40441370010375977, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9462, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 0.4196081757545471, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.0118, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2543859649122807, | |
| "grad_norm": 0.4395890235900879, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.0664, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 0.38672029972076416, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.0271, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2719298245614035, | |
| "grad_norm": 0.3793441355228424, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0811, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 0.4024253189563751, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0329, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 0.4041074514389038, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0725, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2982456140350877, | |
| "grad_norm": 0.41783076524734497, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1259, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.30701754385964913, | |
| "grad_norm": 0.43029075860977173, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1461, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.42224910855293274, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0811, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32456140350877194, | |
| "grad_norm": 0.45067015290260315, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0835, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.4447973072528839, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.853, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 0.4372630715370178, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.9161, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 0.38782182335853577, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9418, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35964912280701755, | |
| "grad_norm": 0.33929508924484253, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.9558, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 0.390170156955719, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.985, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37719298245614036, | |
| "grad_norm": 0.37908726930618286, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.95, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 0.3707427382469177, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0245, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 0.37403151392936707, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.0319, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40350877192982454, | |
| "grad_norm": 0.3797858655452728, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0585, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41228070175438597, | |
| "grad_norm": 0.39287111163139343, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0661, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.3905193507671356, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0028, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4298245614035088, | |
| "grad_norm": 0.4534038007259369, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1291, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.43859649122807015, | |
| "grad_norm": 0.4350319504737854, | |
| "learning_rate": 0.0, | |
| "loss": 1.0738, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43859649122807015, | |
| "eval_loss": 1.0091651678085327, | |
| "eval_runtime": 25.3044, | |
| "eval_samples_per_second": 30.35, | |
| "eval_steps_per_second": 3.794, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |