| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.2980251346499103, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05745062836624776, | |
| "grad_norm": 3.1636736392974854, | |
| "learning_rate": 5e-06, | |
| "loss": 2.3037, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11490125673249552, | |
| "grad_norm": 3.3778610229492188, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3337, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17235188509874327, | |
| "grad_norm": 3.0278897285461426, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.2715, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22980251346499103, | |
| "grad_norm": 2.5405051708221436, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2422, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2872531418312388, | |
| "grad_norm": 1.789209246635437, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.2079, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.34470377019748655, | |
| "grad_norm": 1.653626561164856, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2231, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4021543985637343, | |
| "grad_norm": 2.006115436553955, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.2855, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.45960502692998206, | |
| "grad_norm": 2.322628974914551, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2126, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5170556552962298, | |
| "grad_norm": 2.069558620452881, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.2389, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5745062836624776, | |
| "grad_norm": 1.7339693307876587, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1964, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6319569120287253, | |
| "grad_norm": 1.6608643531799316, | |
| "learning_rate": 4.992664502959351e-05, | |
| "loss": 2.2079, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6894075403949731, | |
| "grad_norm": 1.642751932144165, | |
| "learning_rate": 4.970701059450872e-05, | |
| "loss": 2.2359, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7468581687612208, | |
| "grad_norm": 1.6817108392715454, | |
| "learning_rate": 4.934238559694448e-05, | |
| "loss": 2.2229, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8043087971274686, | |
| "grad_norm": 1.6007517576217651, | |
| "learning_rate": 4.8834909801373264e-05, | |
| "loss": 2.203, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8617594254937163, | |
| "grad_norm": 1.457571029663086, | |
| "learning_rate": 4.8187561277552374e-05, | |
| "loss": 2.0994, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9192100538599641, | |
| "grad_norm": 1.486559271812439, | |
| "learning_rate": 4.740413892402639e-05, | |
| "loss": 2.1777, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9766606822262118, | |
| "grad_norm": 1.5398966073989868, | |
| "learning_rate": 4.648924017468003e-05, | |
| "loss": 2.2126, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0341113105924595, | |
| "grad_norm": 1.4850305318832397, | |
| "learning_rate": 4.5448234019167945e-05, | |
| "loss": 2.1019, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0915619389587075, | |
| "grad_norm": 1.4637010097503662, | |
| "learning_rate": 4.428722949554857e-05, | |
| "loss": 2.1119, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1490125673249552, | |
| "grad_norm": 1.3282859325408936, | |
| "learning_rate": 4.301303984001967e-05, | |
| "loss": 2.0976, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2064631956912029, | |
| "grad_norm": 1.2366828918457031, | |
| "learning_rate": 4.163314250413913e-05, | |
| "loss": 2.0682, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2639138240574506, | |
| "grad_norm": 1.3221453428268433, | |
| "learning_rate": 4.015563527416595e-05, | |
| "loss": 2.0266, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3213644524236985, | |
| "grad_norm": 1.269490122795105, | |
| "learning_rate": 3.858918875003053e-05, | |
| "loss": 2.011, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3788150807899462, | |
| "grad_norm": 1.2723491191864014, | |
| "learning_rate": 3.694299546280657e-05, | |
| "loss": 2.0503, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.436265709156194, | |
| "grad_norm": 1.3157715797424316, | |
| "learning_rate": 3.5226715929283506e-05, | |
| "loss": 2.0297, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4937163375224416, | |
| "grad_norm": 1.367810606956482, | |
| "learning_rate": 3.3450421960212566e-05, | |
| "loss": 2.03, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5511669658886893, | |
| "grad_norm": 1.4925018548965454, | |
| "learning_rate": 3.162453755491655e-05, | |
| "loss": 2.0478, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.608617594254937, | |
| "grad_norm": 1.350865125656128, | |
| "learning_rate": 2.975977772911671e-05, | |
| "loss": 2.1047, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.666068222621185, | |
| "grad_norm": 1.3046050071716309, | |
| "learning_rate": 2.7867085634960016e-05, | |
| "loss": 2.0175, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7235188509874326, | |
| "grad_norm": 1.3713139295578003, | |
| "learning_rate": 2.595756834225089e-05, | |
| "loss": 2.0437, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7809694793536806, | |
| "grad_norm": 1.2804160118103027, | |
| "learning_rate": 2.4042431657749117e-05, | |
| "loss": 2.0573, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8384201077199283, | |
| "grad_norm": 1.257683277130127, | |
| "learning_rate": 2.2132914365039993e-05, | |
| "loss": 2.0105, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.895870736086176, | |
| "grad_norm": 1.2399568557739258, | |
| "learning_rate": 2.0240222270883288e-05, | |
| "loss": 2.0335, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9533213644524237, | |
| "grad_norm": 1.1331653594970703, | |
| "learning_rate": 1.8375462445083464e-05, | |
| "loss": 2.0217, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0107719928186714, | |
| "grad_norm": 1.219581961631775, | |
| "learning_rate": 1.6549578039787436e-05, | |
| "loss": 2.0096, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.068222621184919, | |
| "grad_norm": 1.239498257637024, | |
| "learning_rate": 1.4773284070716503e-05, | |
| "loss": 2.0598, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1256732495511668, | |
| "grad_norm": 1.2558954954147339, | |
| "learning_rate": 1.3057004537193423e-05, | |
| "loss": 2.0412, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.183123877917415, | |
| "grad_norm": 1.0945749282836914, | |
| "learning_rate": 1.1410811249969475e-05, | |
| "loss": 1.959, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2405745062836626, | |
| "grad_norm": 1.0557724237442017, | |
| "learning_rate": 9.844364725834057e-06, | |
| "loss": 1.9716, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.2980251346499103, | |
| "grad_norm": 1.1883456707000732, | |
| "learning_rate": 8.36685749586087e-06, | |
| "loss": 1.9485, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 51, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7513920113127424e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |