| { | |
| "best_metric": 1.975742220878601, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.4564564564564564, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04804804804804805, | |
| "grad_norm": 0.9264801740646362, | |
| "learning_rate": 5e-05, | |
| "loss": 31.5308, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04804804804804805, | |
| "eval_loss": 2.056973457336426, | |
| "eval_runtime": 8.7495, | |
| "eval_samples_per_second": 16.001, | |
| "eval_steps_per_second": 2.057, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0960960960960961, | |
| "grad_norm": 0.9089482426643372, | |
| "learning_rate": 0.0001, | |
| "loss": 31.0744, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 1.0403860807418823, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 32.0292, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1921921921921922, | |
| "grad_norm": 1.198567271232605, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 33.8766, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24024024024024024, | |
| "grad_norm": 4.076196193695068, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 37.1433, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 0.7010602951049805, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 30.8883, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.33633633633633636, | |
| "grad_norm": 0.5662339329719543, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 31.4161, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3843843843843844, | |
| "grad_norm": 0.8049856424331665, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 32.271, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.7874720692634583, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 32.842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4804804804804805, | |
| "grad_norm": 3.7253880500793457, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 36.3232, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5285285285285285, | |
| "grad_norm": 0.8905734419822693, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 31.1471, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 0.7487469911575317, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 31.397, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6246246246246246, | |
| "grad_norm": 0.6790052056312561, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 31.5109, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6726726726726727, | |
| "grad_norm": 0.8097109198570251, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 32.8427, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 2.2386648654937744, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 34.7417, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7687687687687688, | |
| "grad_norm": 2.866621971130371, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 30.6373, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8168168168168168, | |
| "grad_norm": 0.4617374837398529, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 31.4736, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.6390979290008545, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 32.3816, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9129129129129129, | |
| "grad_norm": 0.6818099021911621, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 32.0514, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.960960960960961, | |
| "grad_norm": 2.074115037918091, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 34.9599, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0360360360360361, | |
| "grad_norm": 0.5945106148719788, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 30.2793, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0840840840840842, | |
| "grad_norm": 0.5013795495033264, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 30.7225, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.132132132132132, | |
| "grad_norm": 0.5023598670959473, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 31.8592, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1801801801801801, | |
| "grad_norm": 0.5675609111785889, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 32.6675, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2282282282282282, | |
| "grad_norm": 1.0741078853607178, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 33.3222, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2282282282282282, | |
| "eval_loss": 1.9849716424942017, | |
| "eval_runtime": 8.6894, | |
| "eval_samples_per_second": 16.112, | |
| "eval_steps_per_second": 2.071, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2762762762762763, | |
| "grad_norm": 1.8273707628250122, | |
| "learning_rate": 5e-05, | |
| "loss": 31.9574, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3243243243243243, | |
| "grad_norm": 0.3835039436817169, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 30.7649, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3723723723723724, | |
| "grad_norm": 0.4291238486766815, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 30.7455, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4204204204204205, | |
| "grad_norm": 0.8780869841575623, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 32.1305, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4684684684684686, | |
| "grad_norm": 0.8173553347587585, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 32.4201, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.5165165165165164, | |
| "grad_norm": 1.8756839036941528, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 31.9964, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5645645645645647, | |
| "grad_norm": 0.5796070694923401, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 31.4211, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6126126126126126, | |
| "grad_norm": 0.5456942319869995, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 30.4474, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6606606606606606, | |
| "grad_norm": 0.5846412777900696, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 32.8379, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.7087087087087087, | |
| "grad_norm": 0.9131438136100769, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 33.014, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7567567567567568, | |
| "grad_norm": 1.9769388437271118, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 31.248, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.8048048048048049, | |
| "grad_norm": 1.053635835647583, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 31.7611, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8528528528528527, | |
| "grad_norm": 0.49638527631759644, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 32.2847, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.900900900900901, | |
| "grad_norm": 0.571926474571228, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 32.4141, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9489489489489489, | |
| "grad_norm": 0.9473947286605835, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 32.4951, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.024024024024024, | |
| "grad_norm": 2.7117865085601807, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 31.7703, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.0720720720720722, | |
| "grad_norm": 0.4527989625930786, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 30.8804, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.12012012012012, | |
| "grad_norm": 0.4707128405570984, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 30.7912, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1681681681681684, | |
| "grad_norm": 0.5620436668395996, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 31.8568, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.2162162162162162, | |
| "grad_norm": 0.8135024905204773, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 32.5255, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.264264264264264, | |
| "grad_norm": 2.222813606262207, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 31.1272, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.3123123123123124, | |
| "grad_norm": 0.4300619661808014, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 30.4856, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.3603603603603602, | |
| "grad_norm": 0.4539353549480438, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 30.6673, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.4084084084084085, | |
| "grad_norm": 0.5699998140335083, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 32.4255, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.4564564564564564, | |
| "grad_norm": 0.7823691368103027, | |
| "learning_rate": 0.0, | |
| "loss": 32.8661, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4564564564564564, | |
| "eval_loss": 1.975742220878601, | |
| "eval_runtime": 8.705, | |
| "eval_samples_per_second": 16.083, | |
| "eval_steps_per_second": 2.068, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.291397765695275e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |