| { | |
| "best_metric": 0.9899536967277527, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02226737551145378, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00044534751022907564, | |
| "grad_norm": 2.8276917934417725, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8112, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044534751022907564, | |
| "eval_loss": 5.671816349029541, | |
| "eval_runtime": 717.2706, | |
| "eval_samples_per_second": 21.091, | |
| "eval_steps_per_second": 2.636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008906950204581513, | |
| "grad_norm": 2.7265748977661133, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7965, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001336042530687227, | |
| "grad_norm": 3.0665526390075684, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.2311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017813900409163026, | |
| "grad_norm": 3.4613454341888428, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.9631, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002226737551145378, | |
| "grad_norm": 3.618037223815918, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.0883, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002672085061374454, | |
| "grad_norm": 4.402898788452148, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.8872, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031174325716035295, | |
| "grad_norm": 4.327027320861816, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.3736, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003562780081832605, | |
| "grad_norm": 3.5984373092651367, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.9661, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00400812759206168, | |
| "grad_norm": 3.438178062438965, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.7311, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004453475102290756, | |
| "grad_norm": 2.9747960567474365, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2812, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0048988226125198315, | |
| "grad_norm": 3.2812952995300293, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.1423, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005344170122748908, | |
| "grad_norm": 2.491504192352295, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1319, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0057895176329779835, | |
| "grad_norm": 3.0720109939575195, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.1362, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006234865143207059, | |
| "grad_norm": 2.5356032848358154, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8235, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006680212653436135, | |
| "grad_norm": 2.01210355758667, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4036, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00712556016366521, | |
| "grad_norm": 2.219619035720825, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.2764, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007570907673894286, | |
| "grad_norm": 2.376666784286499, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4623, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00801625518412336, | |
| "grad_norm": 2.15566086769104, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2256, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008461602694352437, | |
| "grad_norm": 2.290947675704956, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.2893, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008906950204581512, | |
| "grad_norm": 2.1057028770446777, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009352297714810588, | |
| "grad_norm": 2.296193838119507, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0817, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009797645225039663, | |
| "grad_norm": 3.104779005050659, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2445, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01024299273526874, | |
| "grad_norm": 2.067246437072754, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3216, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010688340245497816, | |
| "grad_norm": 2.378101110458374, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.2393, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01113368775572689, | |
| "grad_norm": 2.0262579917907715, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01113368775572689, | |
| "eval_loss": 1.124017596244812, | |
| "eval_runtime": 719.2298, | |
| "eval_samples_per_second": 21.034, | |
| "eval_steps_per_second": 2.629, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011579035265955967, | |
| "grad_norm": 1.7371728420257568, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3708, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012024382776185042, | |
| "grad_norm": 1.6122159957885742, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.3295, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012469730286414118, | |
| "grad_norm": 1.6537405252456665, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.0579, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012915077796643193, | |
| "grad_norm": 1.7590739727020264, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9833, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01336042530687227, | |
| "grad_norm": 1.4219406843185425, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9743, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013805772817101344, | |
| "grad_norm": 1.4464205503463745, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8225, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01425112032733042, | |
| "grad_norm": 1.3641613721847534, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8066, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014696467837559495, | |
| "grad_norm": 1.4936997890472412, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9581, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015141815347788572, | |
| "grad_norm": 1.404656171798706, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7723, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.015587162858017646, | |
| "grad_norm": 2.1803853511810303, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.9384, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01603251036824672, | |
| "grad_norm": 2.4153835773468018, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0157, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.016477857878475798, | |
| "grad_norm": 1.6833958625793457, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9205, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.016923205388704874, | |
| "grad_norm": 1.9868228435516357, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1589, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01736855289893395, | |
| "grad_norm": 1.3428561687469482, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0347, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.017813900409163023, | |
| "grad_norm": 1.3924375772476196, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9026, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0182592479193921, | |
| "grad_norm": 1.322308897972107, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.94, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.018704595429621176, | |
| "grad_norm": 1.5756248235702515, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7711, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.019149942939850253, | |
| "grad_norm": 1.912229299545288, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0106, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.019595290450079326, | |
| "grad_norm": 1.682334065437317, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8101, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.020040637960308402, | |
| "grad_norm": 1.701161503791809, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02048598547053748, | |
| "grad_norm": 1.8976212739944458, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0663, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.020931332980766555, | |
| "grad_norm": 1.8541693687438965, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9436, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02137668049099563, | |
| "grad_norm": 2.434173822402954, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2097, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.021822028001224705, | |
| "grad_norm": 2.1513125896453857, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9393, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02226737551145378, | |
| "grad_norm": 2.3237390518188477, | |
| "learning_rate": 0.0, | |
| "loss": 1.2021, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02226737551145378, | |
| "eval_loss": 0.9899536967277527, | |
| "eval_runtime": 719.3135, | |
| "eval_samples_per_second": 21.031, | |
| "eval_steps_per_second": 2.629, | |
| "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": 1.0228361536208896e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |