| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2074688796680498, | |
| "eval_steps": 9, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027662517289073307, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027662517289073307, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.7764, | |
| "eval_samples_per_second": 171.695, | |
| "eval_steps_per_second": 21.954, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005532503457814661, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011065006915629323, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013831258644536652, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019363762102351315, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.022130013831258646, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024896265560165973, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024896265560165973, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3918, | |
| "eval_samples_per_second": 219.137, | |
| "eval_steps_per_second": 28.021, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027662517289073305, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.030428769017980636, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.035961272475795295, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03872752420470263, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04149377593360996, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04426002766251729, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04702627939142462, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04979253112033195, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04979253112033195, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3236, | |
| "eval_samples_per_second": 230.435, | |
| "eval_steps_per_second": 29.465, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05255878284923928, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05532503457814661, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.058091286307053944, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06085753803596127, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0636237897648686, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06639004149377593, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06915629322268327, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07192254495159059, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07468879668049792, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07468879668049792, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3404, | |
| "eval_samples_per_second": 227.548, | |
| "eval_steps_per_second": 29.096, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07745504840940526, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08022130013831259, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08298755186721991, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08575380359612725, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08852005532503458, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0912863070539419, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09405255878284924, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09681881051175657, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0995850622406639, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0995850622406639, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3267, | |
| "eval_samples_per_second": 229.886, | |
| "eval_steps_per_second": 29.395, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10235131396957123, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10511756569847856, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1078838174273859, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11065006915629322, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11341632088520055, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11618257261410789, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11894882434301521, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12171507607192254, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12448132780082988, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12448132780082988, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3855, | |
| "eval_samples_per_second": 220.135, | |
| "eval_steps_per_second": 28.148, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1272475795297372, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13001383125864455, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13278008298755187, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1355463347164592, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13831258644536654, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14107883817427386, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.14384508990318118, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.14661134163208853, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.14937759336099585, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.14937759336099585, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3923, | |
| "eval_samples_per_second": 219.069, | |
| "eval_steps_per_second": 28.012, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.15214384508990317, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15491009681881052, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.15767634854771784, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.16044260027662519, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1632088520055325, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16874135546334718, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1715076071922545, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.17427385892116182, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.17427385892116182, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3375, | |
| "eval_samples_per_second": 228.043, | |
| "eval_steps_per_second": 29.16, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.17704011065006917, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1798063623789765, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1825726141078838, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.18533886583679116, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.18810511756569848, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1908713692946058, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.19363762102351315, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19640387275242047, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1991701244813278, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1991701244813278, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3248, | |
| "eval_samples_per_second": 230.225, | |
| "eval_steps_per_second": 29.439, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.20193637621023514, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.20470262793914246, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2074688796680498, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 649093290393600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |