| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23894862604540024, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0047789725209080045, | |
| "grad_norm": 29.860979080200195, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009557945041816009, | |
| "grad_norm": 41.60591125488281, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5924, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014336917562724014, | |
| "grad_norm": 24.83574867248535, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.0081, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019115890083632018, | |
| "grad_norm": 33.22587966918945, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.3764, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023894862604540025, | |
| "grad_norm": 22.539419174194336, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.1704, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02867383512544803, | |
| "grad_norm": 14.312341690063477, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9104, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03345280764635603, | |
| "grad_norm": 17.781652450561523, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.3272, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.038231780167264036, | |
| "grad_norm": 12.963604927062988, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1321, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 10.790444374084473, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.578, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04778972520908005, | |
| "grad_norm": 10.303182601928711, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.052568697729988054, | |
| "grad_norm": 6.428194046020508, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1103, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05734767025089606, | |
| "grad_norm": 5.339355945587158, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1186, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06212664277180406, | |
| "grad_norm": 6.168482780456543, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1289, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06690561529271206, | |
| "grad_norm": 4.216828346252441, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.968, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07168458781362007, | |
| "grad_norm": 7.057809352874756, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0331, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07646356033452807, | |
| "grad_norm": 2.287396192550659, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7894, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08124253285543608, | |
| "grad_norm": 3.8414762020111084, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9566, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 3.5896944999694824, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8654, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0908004778972521, | |
| "grad_norm": 3.577658176422119, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8182, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0955794504181601, | |
| "grad_norm": 1.9313331842422485, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7824, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1003584229390681, | |
| "grad_norm": 1.5410723686218262, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7631, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10513739545997611, | |
| "grad_norm": 1.6046820878982544, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7609, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10991636798088411, | |
| "grad_norm": 1.0689406394958496, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7945, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11469534050179211, | |
| "grad_norm": 2.764364719390869, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8136, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11947431302270012, | |
| "grad_norm": 2.4890427589416504, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7866, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12425328554360812, | |
| "grad_norm": 1.4815928936004639, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7417, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 10.614400863647461, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2693, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13381123058542413, | |
| "grad_norm": 1.6795942783355713, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7986, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13859020310633213, | |
| "grad_norm": 4.867892742156982, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9343, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14336917562724014, | |
| "grad_norm": 1.466898798942566, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7445, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 1.7136328220367432, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7513, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15292712066905614, | |
| "grad_norm": 2.540726900100708, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8221, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.15770609318996415, | |
| "grad_norm": 2.1124532222747803, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6479, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.16248506571087215, | |
| "grad_norm": 2.1766419410705566, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5888, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16726403823178015, | |
| "grad_norm": 2.80724835395813, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8106, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 2.6843466758728027, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7662, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1768219832735962, | |
| "grad_norm": 2.474299430847168, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7363, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1816009557945042, | |
| "grad_norm": 3.97478985786438, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9892, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1863799283154122, | |
| "grad_norm": 3.161835193634033, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8426, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1911589008363202, | |
| "grad_norm": 2.354658603668213, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8038, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1959378733572282, | |
| "grad_norm": 1.6853210926055908, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6407, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2007168458781362, | |
| "grad_norm": 2.6386783123016357, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8132, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2054958183990442, | |
| "grad_norm": 2.421684503555298, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.747, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.21027479091995221, | |
| "grad_norm": 4.235150337219238, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9646, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": 1.983854055404663, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.712, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21983273596176822, | |
| "grad_norm": 2.297694206237793, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7587, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.22461170848267623, | |
| "grad_norm": 3.1081526279449463, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7924, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22939068100358423, | |
| "grad_norm": 3.886089324951172, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9513, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.23416965352449223, | |
| "grad_norm": 2.9046790599823, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7454, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.23894862604540024, | |
| "grad_norm": 4.309676647186279, | |
| "learning_rate": 0.0, | |
| "loss": 1.0171, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1590283783372800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |