| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05959475566150179, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011918951132300357, | |
| "grad_norm": 3.1771470700380333, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023837902264600714, | |
| "grad_norm": 3.1161312627163005, | |
| "learning_rate": 1.9979453927503366e-05, | |
| "loss": 2.138, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003575685339690107, | |
| "grad_norm": 1.264785017261071, | |
| "learning_rate": 1.991790013823246e-05, | |
| "loss": 2.0438, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004767580452920143, | |
| "grad_norm": 3.409228751017024, | |
| "learning_rate": 1.9815591569910654e-05, | |
| "loss": 2.0838, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0059594755661501785, | |
| "grad_norm": 2.7305256748776907, | |
| "learning_rate": 1.9672948630390296e-05, | |
| "loss": 2.0696, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007151370679380214, | |
| "grad_norm": 1.8763103868114503, | |
| "learning_rate": 1.949055747010669e-05, | |
| "loss": 2.0977, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00834326579261025, | |
| "grad_norm": 1.5468453869545318, | |
| "learning_rate": 1.926916757346022e-05, | |
| "loss": 2.0518, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009535160905840286, | |
| "grad_norm": 1.0642293866767805, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 2.0096, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010727056019070322, | |
| "grad_norm": 0.780500699075983, | |
| "learning_rate": 1.8713187041233896e-05, | |
| "loss": 2.0271, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011918951132300357, | |
| "grad_norm": 0.764005329228154, | |
| "learning_rate": 1.8380881048918406e-05, | |
| "loss": 2.0058, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013110846245530394, | |
| "grad_norm": 0.6241582333904159, | |
| "learning_rate": 1.8014136218679566e-05, | |
| "loss": 2.01, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014302741358760428, | |
| "grad_norm": 0.5902053742685855, | |
| "learning_rate": 1.7614459583691346e-05, | |
| "loss": 2.0019, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015494636471990465, | |
| "grad_norm": 0.6425310694189268, | |
| "learning_rate": 1.7183493500977277e-05, | |
| "loss": 1.9932, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0166865315852205, | |
| "grad_norm": 0.5309446367223852, | |
| "learning_rate": 1.672300890261317e-05, | |
| "loss": 1.9988, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017878426698450536, | |
| "grad_norm": 0.5138876585539982, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 2.0101, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01907032181168057, | |
| "grad_norm": 0.5392570440013659, | |
| "learning_rate": 1.5721166601221697e-05, | |
| "loss": 1.9911, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02026221692491061, | |
| "grad_norm": 0.5029299842352577, | |
| "learning_rate": 1.5183925683105254e-05, | |
| "loss": 2.0116, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.021454112038140644, | |
| "grad_norm": 0.43594035780610685, | |
| "learning_rate": 1.4625382902408356e-05, | |
| "loss": 2.0073, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02264600715137068, | |
| "grad_norm": 0.41696447792308583, | |
| "learning_rate": 1.4047833431223938e-05, | |
| "loss": 2.0208, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023837902264600714, | |
| "grad_norm": 0.3892062305227489, | |
| "learning_rate": 1.3453650544213078e-05, | |
| "loss": 2.031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025029797377830752, | |
| "grad_norm": 0.3632073887411339, | |
| "learning_rate": 1.2845275866310325e-05, | |
| "loss": 1.9957, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026221692491060787, | |
| "grad_norm": 0.33796099940642593, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 2.0049, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027413587604290822, | |
| "grad_norm": 0.32832752521945185, | |
| "learning_rate": 1.1595998950333794e-05, | |
| "loss": 2.02, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.028605482717520857, | |
| "grad_norm": 0.31678859599430514, | |
| "learning_rate": 1.0960230259076819e-05, | |
| "loss": 2.0122, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029797377830750895, | |
| "grad_norm": 0.3054795643275271, | |
| "learning_rate": 1.0320515775716556e-05, | |
| "loss": 2.0194, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03098927294398093, | |
| "grad_norm": 0.30476969314662167, | |
| "learning_rate": 9.67948422428345e-06, | |
| "loss": 2.0244, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03218116805721097, | |
| "grad_norm": 0.3397762952406562, | |
| "learning_rate": 9.039769740923183e-06, | |
| "loss": 2.0301, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.033373063170441, | |
| "grad_norm": 0.28294935774392, | |
| "learning_rate": 8.404001049666211e-06, | |
| "loss": 2.039, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03456495828367104, | |
| "grad_norm": 0.2677495861482238, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 2.0065, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03575685339690107, | |
| "grad_norm": 0.2523404664659208, | |
| "learning_rate": 7.154724133689677e-06, | |
| "loss": 1.9824, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03694874851013111, | |
| "grad_norm": 0.2677420506485163, | |
| "learning_rate": 6.546349455786926e-06, | |
| "loss": 2.0211, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03814064362336114, | |
| "grad_norm": 0.25403279083921193, | |
| "learning_rate": 5.952166568776062e-06, | |
| "loss": 2.0364, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03933253873659118, | |
| "grad_norm": 0.23827255140088083, | |
| "learning_rate": 5.37461709759165e-06, | |
| "loss": 2.0124, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04052443384982122, | |
| "grad_norm": 0.21241476817661348, | |
| "learning_rate": 4.81607431689475e-06, | |
| "loss": 2.0512, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.041716328963051254, | |
| "grad_norm": 0.209552693603396, | |
| "learning_rate": 4.278833398778306e-06, | |
| "loss": 2.0375, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04290822407628129, | |
| "grad_norm": 0.21360560735074388, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 2.0665, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04410011918951132, | |
| "grad_norm": 0.2182223081631352, | |
| "learning_rate": 3.2769910973868314e-06, | |
| "loss": 2.0289, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04529201430274136, | |
| "grad_norm": 0.21248420749052188, | |
| "learning_rate": 2.8165064990227255e-06, | |
| "loss": 2.0451, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04648390941597139, | |
| "grad_norm": 0.20688489883738986, | |
| "learning_rate": 2.3855404163086558e-06, | |
| "loss": 2.0445, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04767580452920143, | |
| "grad_norm": 0.20278373082128726, | |
| "learning_rate": 1.9858637813204352e-06, | |
| "loss": 2.0017, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04886769964243146, | |
| "grad_norm": 0.20097941188780546, | |
| "learning_rate": 1.6191189510815942e-06, | |
| "loss": 2.0239, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.050059594755661505, | |
| "grad_norm": 0.19492229623743026, | |
| "learning_rate": 1.286812958766106e-06, | |
| "loss": 1.9878, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05125148986889154, | |
| "grad_norm": 0.19191563010483195, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 2.0205, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.052443384982121574, | |
| "grad_norm": 0.18895682704532601, | |
| "learning_rate": 7.308324265397837e-07, | |
| "loss": 2.0377, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05363528009535161, | |
| "grad_norm": 0.2270168441556834, | |
| "learning_rate": 5.094425298933136e-07, | |
| "loss": 2.034, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.054827175208581644, | |
| "grad_norm": 0.1944028112406021, | |
| "learning_rate": 3.2705136960970554e-07, | |
| "loss": 2.0496, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05601907032181168, | |
| "grad_norm": 0.18999114531888883, | |
| "learning_rate": 1.844084300893456e-07, | |
| "loss": 2.0299, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.057210965435041714, | |
| "grad_norm": 0.19083668329491307, | |
| "learning_rate": 8.209986176753947e-08, | |
| "loss": 2.0317, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.058402860548271755, | |
| "grad_norm": 0.19161290816553783, | |
| "learning_rate": 2.054607249663665e-08, | |
| "loss": 2.0296, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05959475566150179, | |
| "grad_norm": 0.19193914325325095, | |
| "learning_rate": 0.0, | |
| "loss": 2.068, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05959475566150179, | |
| "step": 50, | |
| "total_flos": 106890730143744.0, | |
| "train_loss": 2.030773923397064, | |
| "train_runtime": 1597.0722, | |
| "train_samples_per_second": 58.106, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 106890730143744.0, | |
| "train_batch_size": 58, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |