| { | |
| "best_metric": 3.2202842235565186, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1983635011157947, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003967270022315894, | |
| "grad_norm": 0.8100353479385376, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003967270022315894, | |
| "eval_loss": 3.7426881790161133, | |
| "eval_runtime": 11.5565, | |
| "eval_samples_per_second": 147.016, | |
| "eval_steps_per_second": 18.431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007934540044631788, | |
| "grad_norm": 0.8411345481872559, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4657, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011901810066947682, | |
| "grad_norm": 0.9052443504333496, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.5402, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015869080089263576, | |
| "grad_norm": 0.7589433789253235, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.4572, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01983635011157947, | |
| "grad_norm": 0.8587386608123779, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.5274, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023803620133895365, | |
| "grad_norm": 0.9426459074020386, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.5125, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02777089015621126, | |
| "grad_norm": 0.9467688798904419, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.5663, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03173816017852715, | |
| "grad_norm": 1.0104401111602783, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4531, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03570543020084305, | |
| "grad_norm": 1.0469218492507935, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.4803, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03967270022315894, | |
| "grad_norm": 1.096985936164856, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.5365, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.043639970245474835, | |
| "grad_norm": 1.0697236061096191, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5104, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04760724026779073, | |
| "grad_norm": 1.215027928352356, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.472, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05157451029010662, | |
| "grad_norm": 1.1256529092788696, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.4123, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05554178031242252, | |
| "grad_norm": 1.0637106895446777, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.3022, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05950905033473841, | |
| "grad_norm": 1.1305065155029297, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.3346, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0634763203570543, | |
| "grad_norm": 0.8763689994812012, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.2566, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0674435903793702, | |
| "grad_norm": 0.7871897220611572, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.3037, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0714108604016861, | |
| "grad_norm": 0.8707305192947388, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.3393, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07537813042400199, | |
| "grad_norm": 0.8883684873580933, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.2778, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07934540044631788, | |
| "grad_norm": 1.0402384996414185, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.2926, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08331267046863378, | |
| "grad_norm": 1.2061767578125, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.4678, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08727994049094967, | |
| "grad_norm": 1.1715914011001587, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.3448, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09124721051326556, | |
| "grad_norm": 1.2525004148483276, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.3168, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09521448053558146, | |
| "grad_norm": 1.1802704334259033, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.2211, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09918175055789735, | |
| "grad_norm": 1.308222770690918, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.2855, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09918175055789735, | |
| "eval_loss": 3.268176555633545, | |
| "eval_runtime": 11.5559, | |
| "eval_samples_per_second": 147.024, | |
| "eval_steps_per_second": 18.432, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10314902058021325, | |
| "grad_norm": 0.9733558893203735, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2624, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10711629060252914, | |
| "grad_norm": 1.166012167930603, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.1748, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11108356062484503, | |
| "grad_norm": 1.3410450220108032, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.2613, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11505083064716093, | |
| "grad_norm": 1.3012003898620605, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.2793, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11901810066947682, | |
| "grad_norm": 1.0508790016174316, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.2646, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12298537069179272, | |
| "grad_norm": 0.9772084355354309, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.2421, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1269526407141086, | |
| "grad_norm": 0.8641189932823181, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.2449, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1309199107364245, | |
| "grad_norm": 0.8817277550697327, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.3813, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1348871807587404, | |
| "grad_norm": 0.8557921648025513, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.2187, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1388544507810563, | |
| "grad_norm": 0.9797968864440918, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.2734, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1428217208033722, | |
| "grad_norm": 0.9896147847175598, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.2438, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 1.0835036039352417, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.3002, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15075626084800398, | |
| "grad_norm": 0.842976987361908, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.2495, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15472353087031987, | |
| "grad_norm": 0.6773706078529358, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.2503, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15869080089263576, | |
| "grad_norm": 0.5887467861175537, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.2258, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16265807091495166, | |
| "grad_norm": 0.5568850040435791, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.1648, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16662534093726755, | |
| "grad_norm": 0.5692043900489807, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.2207, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17059261095958345, | |
| "grad_norm": 0.6383813619613647, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.2575, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17455988098189934, | |
| "grad_norm": 0.6307452917098999, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.2423, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17852715100421523, | |
| "grad_norm": 0.7243000268936157, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.2007, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18249442102653113, | |
| "grad_norm": 0.846513032913208, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.2938, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18646169104884702, | |
| "grad_norm": 0.951248824596405, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.3001, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.19042896107116292, | |
| "grad_norm": 0.9839473962783813, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.1855, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1943962310934788, | |
| "grad_norm": 1.0755198001861572, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.1702, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1983635011157947, | |
| "grad_norm": 1.5319169759750366, | |
| "learning_rate": 0.0, | |
| "loss": 3.2793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1983635011157947, | |
| "eval_loss": 3.2202842235565186, | |
| "eval_runtime": 11.5549, | |
| "eval_samples_per_second": 147.037, | |
| "eval_steps_per_second": 18.434, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |