| { | |
| "best_metric": 2.552751302719116, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.30983733539891556, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006196746707978312, | |
| "grad_norm": 14.360746383666992, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6413, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006196746707978312, | |
| "eval_loss": 6.478263854980469, | |
| "eval_runtime": 15.4514, | |
| "eval_samples_per_second": 140.764, | |
| "eval_steps_per_second": 17.604, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012393493415956624, | |
| "grad_norm": 18.92182731628418, | |
| "learning_rate": 0.0001, | |
| "loss": 5.4248, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018590240123934933, | |
| "grad_norm": 15.343290328979492, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.1554, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024786986831913247, | |
| "grad_norm": 18.209632873535156, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.0991, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.030983733539891558, | |
| "grad_norm": 15.062034606933594, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.1656, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.037180480247869865, | |
| "grad_norm": 5.35574197769165, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9608, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.043377226955848176, | |
| "grad_norm": 5.235628604888916, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.8272, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.049573973663826494, | |
| "grad_norm": 3.016737461090088, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6595, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.055770720371804805, | |
| "grad_norm": 3.0546302795410156, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.8264, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.061967467079783116, | |
| "grad_norm": 2.4571104049682617, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.5294, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06816421378776143, | |
| "grad_norm": 2.7798690795898438, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.7008, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07436096049573973, | |
| "grad_norm": 3.247927188873291, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.652, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08055770720371805, | |
| "grad_norm": 5.538148880004883, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.8895, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08675445391169635, | |
| "grad_norm": 4.032698631286621, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.6867, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09295120061967467, | |
| "grad_norm": 2.231078624725342, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.4594, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09914794732765299, | |
| "grad_norm": 3.496612548828125, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.9015, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10534469403563129, | |
| "grad_norm": 4.154210090637207, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.846, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11154144074360961, | |
| "grad_norm": 3.124022960662842, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.8184, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11773818745158791, | |
| "grad_norm": 2.524756908416748, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.726, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12393493415956623, | |
| "grad_norm": 1.9664084911346436, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.5206, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13013168086754454, | |
| "grad_norm": 2.3225109577178955, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.5722, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13632842757552285, | |
| "grad_norm": 2.9485130310058594, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.542, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14252517428350117, | |
| "grad_norm": 2.1408677101135254, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.649, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14872192099147946, | |
| "grad_norm": 2.554943561553955, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.5232, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15491866769945778, | |
| "grad_norm": 2.2532289028167725, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.8101, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15491866769945778, | |
| "eval_loss": 2.583543539047241, | |
| "eval_runtime": 15.4093, | |
| "eval_samples_per_second": 141.148, | |
| "eval_steps_per_second": 17.652, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1611154144074361, | |
| "grad_norm": 4.529732704162598, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3753, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16731216111541442, | |
| "grad_norm": 2.579380750656128, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.4678, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1735089078233927, | |
| "grad_norm": 1.9617533683776855, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.5855, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17970565453137102, | |
| "grad_norm": 1.853303074836731, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.5252, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18590240123934934, | |
| "grad_norm": 1.9760549068450928, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.4801, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19209914794732766, | |
| "grad_norm": 2.2307536602020264, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.5646, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.19829589465530598, | |
| "grad_norm": 2.7033464908599854, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.5902, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20449264136328427, | |
| "grad_norm": 3.0382657051086426, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.6213, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21068938807126258, | |
| "grad_norm": 2.862405776977539, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.7111, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2168861347792409, | |
| "grad_norm": 2.6279330253601074, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.5787, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22308288148721922, | |
| "grad_norm": 2.5714271068573, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.4985, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2292796281951975, | |
| "grad_norm": 2.269505739212036, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.6654, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.23547637490317583, | |
| "grad_norm": 2.5545523166656494, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3506, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24167312161115415, | |
| "grad_norm": 2.985491991043091, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.3224, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.24786986831913246, | |
| "grad_norm": 3.0667636394500732, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.5096, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25406661502711075, | |
| "grad_norm": 2.111599922180176, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.1927, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.26026336173508907, | |
| "grad_norm": 2.4113497734069824, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.4784, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2664601084430674, | |
| "grad_norm": 2.488245964050293, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.4202, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2726568551510457, | |
| "grad_norm": 2.6854028701782227, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.6167, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.278853601859024, | |
| "grad_norm": 2.37113881111145, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.5015, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.28505034856700234, | |
| "grad_norm": 2.303887128829956, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.6882, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.29124709527498066, | |
| "grad_norm": 2.164066791534424, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.638, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2974438419829589, | |
| "grad_norm": 2.1155331134796143, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.5897, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.30364058869093724, | |
| "grad_norm": 1.9562890529632568, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.5368, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.30983733539891556, | |
| "grad_norm": 2.3450493812561035, | |
| "learning_rate": 0.0, | |
| "loss": 2.5672, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.30983733539891556, | |
| "eval_loss": 2.552751302719116, | |
| "eval_runtime": 15.44, | |
| "eval_samples_per_second": 140.868, | |
| "eval_steps_per_second": 17.617, | |
| "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": 5.90601825288192e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |