| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9902912621359223, | |
| "eval_steps": 500, | |
| "global_step": 462, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06472491909385113, | |
| "grad_norm": 0.09439529478549957, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5099, | |
| "num_input_tokens_seen": 1296736, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12944983818770225, | |
| "grad_norm": 0.11287413537502289, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5115, | |
| "num_input_tokens_seen": 2603088, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1941747572815534, | |
| "grad_norm": 0.13694792985916138, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4846, | |
| "num_input_tokens_seen": 3884384, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2588996763754045, | |
| "grad_norm": 0.14105218648910522, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4076, | |
| "num_input_tokens_seen": 5275424, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32362459546925565, | |
| "grad_norm": 0.09946475923061371, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3073, | |
| "num_input_tokens_seen": 6672576, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3883495145631068, | |
| "grad_norm": 0.11918677389621735, | |
| "learning_rate": 4.992735514089577e-05, | |
| "loss": 0.2516, | |
| "num_input_tokens_seen": 7942496, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.45307443365695793, | |
| "grad_norm": 0.07622148096561432, | |
| "learning_rate": 4.970984274562741e-05, | |
| "loss": 0.2256, | |
| "num_input_tokens_seen": 9300240, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.517799352750809, | |
| "grad_norm": 0.07995602488517761, | |
| "learning_rate": 4.934872690677953e-05, | |
| "loss": 0.2146, | |
| "num_input_tokens_seen": 10674880, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5825242718446602, | |
| "grad_norm": 0.07474230229854584, | |
| "learning_rate": 4.884610628109082e-05, | |
| "loss": 0.2018, | |
| "num_input_tokens_seen": 12052928, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6472491909385113, | |
| "grad_norm": 0.07976042479276657, | |
| "learning_rate": 4.820490189292415e-05, | |
| "loss": 0.1958, | |
| "num_input_tokens_seen": 13387616, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7119741100323624, | |
| "grad_norm": 0.08398651331663132, | |
| "learning_rate": 4.742884015847436e-05, | |
| "loss": 0.1912, | |
| "num_input_tokens_seen": 14676976, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7766990291262136, | |
| "grad_norm": 0.088481605052948, | |
| "learning_rate": 4.652243122936986e-05, | |
| "loss": 0.1876, | |
| "num_input_tokens_seen": 15991008, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8414239482200647, | |
| "grad_norm": 0.09539451450109482, | |
| "learning_rate": 4.5490942781526316e-05, | |
| "loss": 0.1802, | |
| "num_input_tokens_seen": 17281840, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9061488673139159, | |
| "grad_norm": 0.08230065554380417, | |
| "learning_rate": 4.434036940158062e-05, | |
| "loss": 0.1793, | |
| "num_input_tokens_seen": 18603200, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.970873786407767, | |
| "grad_norm": 0.09070578217506409, | |
| "learning_rate": 4.307739774881878e-05, | |
| "loss": 0.1759, | |
| "num_input_tokens_seen": 19844160, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.035598705501618, | |
| "grad_norm": 0.09057565778493881, | |
| "learning_rate": 4.170936769506222e-05, | |
| "loss": 0.1746, | |
| "num_input_tokens_seen": 21111168, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.1003236245954693, | |
| "grad_norm": 0.08840323239564896, | |
| "learning_rate": 4.024422966835136e-05, | |
| "loss": 0.1699, | |
| "num_input_tokens_seen": 22442800, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1650485436893203, | |
| "grad_norm": 0.10438356548547745, | |
| "learning_rate": 3.86904984483277e-05, | |
| "loss": 0.168, | |
| "num_input_tokens_seen": 23815072, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2297734627831716, | |
| "grad_norm": 0.09192164242267609, | |
| "learning_rate": 3.7057203681836406e-05, | |
| "loss": 0.1646, | |
| "num_input_tokens_seen": 25064672, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.2944983818770226, | |
| "grad_norm": 0.08962567150592804, | |
| "learning_rate": 3.535383740633246e-05, | |
| "loss": 0.1667, | |
| "num_input_tokens_seen": 26380864, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3592233009708738, | |
| "grad_norm": 0.1008475124835968, | |
| "learning_rate": 3.3590298886062833e-05, | |
| "loss": 0.1664, | |
| "num_input_tokens_seen": 27735952, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4239482200647249, | |
| "grad_norm": 0.09535906463861465, | |
| "learning_rate": 3.177683708161389e-05, | |
| "loss": 0.1622, | |
| "num_input_tokens_seen": 28991248, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.4886731391585761, | |
| "grad_norm": 0.09163232892751694, | |
| "learning_rate": 2.9923991087167658e-05, | |
| "loss": 0.1623, | |
| "num_input_tokens_seen": 30313776, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.5533980582524272, | |
| "grad_norm": 0.09542625397443771, | |
| "learning_rate": 2.804252888162079e-05, | |
| "loss": 0.1616, | |
| "num_input_tokens_seen": 31667088, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.6181229773462782, | |
| "grad_norm": 0.09714806824922562, | |
| "learning_rate": 2.6143384749519866e-05, | |
| "loss": 0.159, | |
| "num_input_tokens_seen": 32942832, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.6828478964401294, | |
| "grad_norm": 0.10313564538955688, | |
| "learning_rate": 2.423759573549647e-05, | |
| "loss": 0.1619, | |
| "num_input_tokens_seen": 34263264, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.7475728155339807, | |
| "grad_norm": 0.09954512119293213, | |
| "learning_rate": 2.23362375015031e-05, | |
| "loss": 0.1616, | |
| "num_input_tokens_seen": 35603952, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.8122977346278317, | |
| "grad_norm": 0.1067601814866066, | |
| "learning_rate": 2.0450359959620967e-05, | |
| "loss": 0.1604, | |
| "num_input_tokens_seen": 36890768, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.8770226537216828, | |
| "grad_norm": 0.09286054223775864, | |
| "learning_rate": 1.8590923054515503e-05, | |
| "loss": 0.1563, | |
| "num_input_tokens_seen": 38275536, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.941747572815534, | |
| "grad_norm": 0.09992893040180206, | |
| "learning_rate": 1.676873306874547e-05, | |
| "loss": 0.1548, | |
| "num_input_tokens_seen": 39648800, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0064724919093853, | |
| "grad_norm": 0.09988085925579071, | |
| "learning_rate": 1.4994379821093049e-05, | |
| "loss": 0.1555, | |
| "num_input_tokens_seen": 40991008, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.071197411003236, | |
| "grad_norm": 0.09905947744846344, | |
| "learning_rate": 1.3278175122892416e-05, | |
| "loss": 0.1526, | |
| "num_input_tokens_seen": 42342880, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.1359223300970873, | |
| "grad_norm": 0.10081404447555542, | |
| "learning_rate": 1.1630092850023147e-05, | |
| "loss": 0.1526, | |
| "num_input_tokens_seen": 43654784, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.2006472491909386, | |
| "grad_norm": 0.10631163418292999, | |
| "learning_rate": 1.005971097884561e-05, | |
| "loss": 0.1516, | |
| "num_input_tokens_seen": 45039744, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.26537216828479, | |
| "grad_norm": 0.10914473235607147, | |
| "learning_rate": 8.576155922941548e-06, | |
| "loss": 0.1524, | |
| "num_input_tokens_seen": 46331568, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.3300970873786406, | |
| "grad_norm": 0.10382701456546783, | |
| "learning_rate": 7.1880494941517026e-06, | |
| "loss": 0.1502, | |
| "num_input_tokens_seen": 47685808, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.394822006472492, | |
| "grad_norm": 0.10681454837322235, | |
| "learning_rate": 5.903458796151381e-06, | |
| "loss": 0.1506, | |
| "num_input_tokens_seen": 49011728, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.459546925566343, | |
| "grad_norm": 0.10908275097608566, | |
| "learning_rate": 4.729849341761602e-06, | |
| "loss": 0.1479, | |
| "num_input_tokens_seen": 50327504, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.524271844660194, | |
| "grad_norm": 0.1181163340806961, | |
| "learning_rate": 3.674041666458963e-06, | |
| "loss": 0.1501, | |
| "num_input_tokens_seen": 51620256, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.588996763754045, | |
| "grad_norm": 0.09960592538118362, | |
| "learning_rate": 2.7421716902285623e-06, | |
| "loss": 0.1504, | |
| "num_input_tokens_seen": 52952880, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.6537216828478964, | |
| "grad_norm": 0.10874225944280624, | |
| "learning_rate": 1.939655058120521e-06, | |
| "loss": 0.1524, | |
| "num_input_tokens_seen": 54225632, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.7184466019417477, | |
| "grad_norm": 0.10990295559167862, | |
| "learning_rate": 1.271155666748311e-06, | |
| "loss": 0.1494, | |
| "num_input_tokens_seen": 55561888, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.783171521035599, | |
| "grad_norm": 0.10411816090345383, | |
| "learning_rate": 7.405585596397313e-07, | |
| "loss": 0.1515, | |
| "num_input_tokens_seen": 56900512, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.8478964401294498, | |
| "grad_norm": 0.10403899103403091, | |
| "learning_rate": 3.5094734896174987e-07, | |
| "loss": 0.1504, | |
| "num_input_tokens_seen": 58197632, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.912621359223301, | |
| "grad_norm": 0.1029229462146759, | |
| "learning_rate": 1.0458629483476867e-07, | |
| "loss": 0.1498, | |
| "num_input_tokens_seen": 59523808, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.9773462783171523, | |
| "grad_norm": 0.10788564383983612, | |
| "learning_rate": 2.9071463840540935e-09, | |
| "loss": 0.1469, | |
| "num_input_tokens_seen": 60787344, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.9902912621359223, | |
| "num_input_tokens_seen": 61072080, | |
| "step": 462, | |
| "total_flos": 5.065534456681464e+18, | |
| "train_loss": 0.1973544524990635, | |
| "train_runtime": 23852.8939, | |
| "train_samples_per_second": 0.622, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 462, | |
| "num_input_tokens_seen": 61072080, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.065534456681464e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |