| { | |
| "best_metric": 0.16587750613689423, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5445881552076243, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010891763104152484, | |
| "grad_norm": 28.75968360900879, | |
| "learning_rate": 5e-05, | |
| "loss": 12.5864, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010891763104152484, | |
| "eval_loss": 12.764678001403809, | |
| "eval_runtime": 12.7735, | |
| "eval_samples_per_second": 48.46, | |
| "eval_steps_per_second": 6.106, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021783526208304968, | |
| "grad_norm": 28.662094116210938, | |
| "learning_rate": 0.0001, | |
| "loss": 12.7415, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03267528931245745, | |
| "grad_norm": 29.574182510375977, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.8154, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043567052416609936, | |
| "grad_norm": 17.31101417541504, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.6392, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05445881552076242, | |
| "grad_norm": 13.541991233825684, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.1811, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0653505786249149, | |
| "grad_norm": 11.794838905334473, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.5217, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0762423417290674, | |
| "grad_norm": 7.424805641174316, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5871, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08713410483321987, | |
| "grad_norm": 6.943188190460205, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0732, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09802586793737236, | |
| "grad_norm": 20.18202018737793, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9517, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10891763104152484, | |
| "grad_norm": 8.790501594543457, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.695, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11980939414567733, | |
| "grad_norm": 3.5396814346313477, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6084, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1307011572498298, | |
| "grad_norm": 2.165926456451416, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6215, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1415929203539823, | |
| "grad_norm": 1.313301682472229, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5894, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1524846834581348, | |
| "grad_norm": 1.1743314266204834, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5612, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16337644656228728, | |
| "grad_norm": 1.1539360284805298, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5283, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17426820966643974, | |
| "grad_norm": 1.2591698169708252, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5093, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18515997277059223, | |
| "grad_norm": 2.5328752994537354, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4869, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19605173587474473, | |
| "grad_norm": 2.8118677139282227, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4226, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20694349897889722, | |
| "grad_norm": 3.584213972091675, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3765, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21783526208304968, | |
| "grad_norm": 4.752110004425049, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3473, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22872702518720217, | |
| "grad_norm": 2.8016960620880127, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3038, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23961878829135466, | |
| "grad_norm": 2.771104574203491, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3159, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25051055139550715, | |
| "grad_norm": 2.1360843181610107, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2692, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2614023144996596, | |
| "grad_norm": 1.6023329496383667, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2478, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.27229407760381213, | |
| "grad_norm": 1.636376142501831, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1794, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27229407760381213, | |
| "eval_loss": 0.21203623712062836, | |
| "eval_runtime": 12.7659, | |
| "eval_samples_per_second": 48.488, | |
| "eval_steps_per_second": 6.11, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 1.9654167890548706, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2569, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29407760381211706, | |
| "grad_norm": 1.501623272895813, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2404, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3049693669162696, | |
| "grad_norm": 1.7291406393051147, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2169, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31586113002042204, | |
| "grad_norm": 1.3261122703552246, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2232, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32675289312457456, | |
| "grad_norm": 1.0543931722640991, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1568, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.337644656228727, | |
| "grad_norm": 1.1441091299057007, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2081, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3485364193328795, | |
| "grad_norm": 1.2155985832214355, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.169, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.359428182437032, | |
| "grad_norm": 1.9344199895858765, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1921, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.37031994554118447, | |
| "grad_norm": 1.575245976448059, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1606, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.381211708645337, | |
| "grad_norm": 1.478620171546936, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2003, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39210347174948945, | |
| "grad_norm": 2.045692205429077, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.181, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4029952348536419, | |
| "grad_norm": 1.66561758518219, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2042, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.41388699795779443, | |
| "grad_norm": 1.607456088066101, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2265, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": 1.426287293434143, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1721, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.43567052416609936, | |
| "grad_norm": 1.4206467866897583, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1766, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4465622872702519, | |
| "grad_norm": 1.2468781471252441, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1932, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45745405037440434, | |
| "grad_norm": 1.3370360136032104, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2293, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.46834581347855686, | |
| "grad_norm": 1.1221462488174438, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1564, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4792375765827093, | |
| "grad_norm": 0.933812141418457, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1989, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4901293396868618, | |
| "grad_norm": 1.0940755605697632, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.161, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5010211027910143, | |
| "grad_norm": 1.0236101150512695, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1711, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5119128658951668, | |
| "grad_norm": 0.8983817100524902, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1697, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5228046289993192, | |
| "grad_norm": 1.1592609882354736, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1596, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5336963921034718, | |
| "grad_norm": 1.2694193124771118, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1864, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5445881552076243, | |
| "grad_norm": 1.018462896347046, | |
| "learning_rate": 0.0, | |
| "loss": 0.1808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5445881552076243, | |
| "eval_loss": 0.16587750613689423, | |
| "eval_runtime": 12.7544, | |
| "eval_samples_per_second": 48.532, | |
| "eval_steps_per_second": 6.116, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |