| { | |
| "best_metric": 1.3332951068878174, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4784688995215311, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009569377990430622, | |
| "grad_norm": 11.937773704528809, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1329, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009569377990430622, | |
| "eval_loss": 3.596569538116455, | |
| "eval_runtime": 12.6061, | |
| "eval_samples_per_second": 55.925, | |
| "eval_steps_per_second": 7.06, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019138755980861243, | |
| "grad_norm": 17.06051254272461, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3973, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028708133971291867, | |
| "grad_norm": 11.530879020690918, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.33, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03827751196172249, | |
| "grad_norm": 4.863895416259766, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.1504, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04784688995215311, | |
| "grad_norm": 2.389549732208252, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0503, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05741626794258373, | |
| "grad_norm": 2.973436117172241, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0484, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06698564593301436, | |
| "grad_norm": 4.2277750968933105, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.1132, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07655502392344497, | |
| "grad_norm": 4.570304870605469, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1499, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0861244019138756, | |
| "grad_norm": 4.366866588592529, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9868, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09569377990430622, | |
| "grad_norm": 3.77494215965271, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0331, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 3.6135013103485107, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0213, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11483253588516747, | |
| "grad_norm": 2.0240023136138916, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1091, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12440191387559808, | |
| "grad_norm": 1.4828696250915527, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.4722, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1339712918660287, | |
| "grad_norm": 1.236854910850525, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4059, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14354066985645933, | |
| "grad_norm": 1.3019099235534668, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4493, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15311004784688995, | |
| "grad_norm": 0.9599061012268066, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5469, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16267942583732056, | |
| "grad_norm": 0.923953115940094, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.529, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1722488038277512, | |
| "grad_norm": 2.454759359359741, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5621, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 2.7847657203674316, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.604, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19138755980861244, | |
| "grad_norm": 1.7721953392028809, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5582, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20095693779904306, | |
| "grad_norm": 1.2390673160552979, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.6738, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 2.5946755409240723, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5537, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22009569377990432, | |
| "grad_norm": 4.381129741668701, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5657, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22966507177033493, | |
| "grad_norm": 4.085587501525879, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.614, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23923444976076555, | |
| "grad_norm": 3.1173250675201416, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6821, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23923444976076555, | |
| "eval_loss": 1.4000091552734375, | |
| "eval_runtime": 12.5686, | |
| "eval_samples_per_second": 56.092, | |
| "eval_steps_per_second": 7.081, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24880382775119617, | |
| "grad_norm": 0.5103795528411865, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0142, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2583732057416268, | |
| "grad_norm": 0.6568211317062378, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.3947, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2679425837320574, | |
| "grad_norm": 0.5069567561149597, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3821, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27751196172248804, | |
| "grad_norm": 0.45003873109817505, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4252, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.28708133971291866, | |
| "grad_norm": 0.38148233294487, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.4354, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2966507177033493, | |
| "grad_norm": 0.42671704292297363, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4432, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3062200956937799, | |
| "grad_norm": 0.38906577229499817, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4877, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.5056963562965393, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.4736, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3253588516746411, | |
| "grad_norm": 0.6899903416633606, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.5067, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3349282296650718, | |
| "grad_norm": 0.6205446720123291, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4979, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3444976076555024, | |
| "grad_norm": 0.7472631335258484, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4706, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.35406698564593303, | |
| "grad_norm": 0.8322171568870544, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.587, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.5657007098197937, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0921, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.37320574162679426, | |
| "grad_norm": 0.6003439426422119, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.1843, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3827751196172249, | |
| "grad_norm": 0.3574884533882141, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.374, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3923444976076555, | |
| "grad_norm": 0.7085531949996948, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3693, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4019138755980861, | |
| "grad_norm": 0.42259854078292847, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3471, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.41148325358851673, | |
| "grad_norm": 0.34592199325561523, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.4339, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.3229917585849762, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.4168, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.430622009569378, | |
| "grad_norm": 0.38954058289527893, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.4106, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.44019138755980863, | |
| "grad_norm": 0.5214857459068298, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.4866, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.44976076555023925, | |
| "grad_norm": 0.47968587279319763, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4853, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.45933014354066987, | |
| "grad_norm": 0.5608012676239014, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.5451, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4688995215311005, | |
| "grad_norm": 0.6561995148658752, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5704, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4784688995215311, | |
| "grad_norm": 0.9207837581634521, | |
| "learning_rate": 0.0, | |
| "loss": 1.6039, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4784688995215311, | |
| "eval_loss": 1.3332951068878174, | |
| "eval_runtime": 12.776, | |
| "eval_samples_per_second": 55.182, | |
| "eval_steps_per_second": 6.966, | |
| "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": 8.368021483552768e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |