| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 22079, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022645953168168847, | |
| "grad_norm": 6.0433220863342285, | |
| "learning_rate": 1.9547080936636626e-05, | |
| "loss": 1.9021, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.045291906336337694, | |
| "grad_norm": 5.967625617980957, | |
| "learning_rate": 1.9094161873273246e-05, | |
| "loss": 1.312, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06793785950450655, | |
| "grad_norm": 6.04085636138916, | |
| "learning_rate": 1.864124280990987e-05, | |
| "loss": 1.079, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09058381267267539, | |
| "grad_norm": 4.7192912101745605, | |
| "learning_rate": 1.8188323746546494e-05, | |
| "loss": 0.919, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.11322976584084424, | |
| "grad_norm": 5.109660625457764, | |
| "learning_rate": 1.7735404683183118e-05, | |
| "loss": 0.8596, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1358757190090131, | |
| "grad_norm": 4.687028884887695, | |
| "learning_rate": 1.728248561981974e-05, | |
| "loss": 0.7987, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.15852167217718194, | |
| "grad_norm": 3.7766010761260986, | |
| "learning_rate": 1.6829566556456363e-05, | |
| "loss": 0.7281, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.18116762534535077, | |
| "grad_norm": 4.304531574249268, | |
| "learning_rate": 1.6376647493092987e-05, | |
| "loss": 0.6821, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.20381357851351964, | |
| "grad_norm": 5.7325968742370605, | |
| "learning_rate": 1.5923728429729607e-05, | |
| "loss": 0.6425, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.22645953168168848, | |
| "grad_norm": 5.178163051605225, | |
| "learning_rate": 1.547080936636623e-05, | |
| "loss": 0.6295, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.24910548484985734, | |
| "grad_norm": 3.056478500366211, | |
| "learning_rate": 1.5017890303002855e-05, | |
| "loss": 0.6005, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.2717514380180262, | |
| "grad_norm": 4.0474467277526855, | |
| "learning_rate": 1.4564971239639478e-05, | |
| "loss": 0.5868, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.294397391186195, | |
| "grad_norm": 3.2683613300323486, | |
| "learning_rate": 1.4112052176276102e-05, | |
| "loss": 0.5647, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.3170433443543639, | |
| "grad_norm": 3.586979627609253, | |
| "learning_rate": 1.3659133112912724e-05, | |
| "loss": 0.5415, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.33968929752253274, | |
| "grad_norm": 4.297875881195068, | |
| "learning_rate": 1.3206214049549346e-05, | |
| "loss": 0.5294, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.36233525069070155, | |
| "grad_norm": 3.461622714996338, | |
| "learning_rate": 1.2753294986185968e-05, | |
| "loss": 0.5211, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.3849812038588704, | |
| "grad_norm": 3.42155385017395, | |
| "learning_rate": 1.2300375922822592e-05, | |
| "loss": 0.505, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.4076271570270393, | |
| "grad_norm": 3.385619878768921, | |
| "learning_rate": 1.1847456859459216e-05, | |
| "loss": 0.4997, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.43027311019520814, | |
| "grad_norm": 3.422764778137207, | |
| "learning_rate": 1.1394537796095839e-05, | |
| "loss": 0.484, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.45291906336337695, | |
| "grad_norm": 2.883808135986328, | |
| "learning_rate": 1.0941618732732463e-05, | |
| "loss": 0.4775, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.4755650165315458, | |
| "grad_norm": 3.6908833980560303, | |
| "learning_rate": 1.0488699669369085e-05, | |
| "loss": 0.4739, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.4982109696997147, | |
| "grad_norm": 3.540358066558838, | |
| "learning_rate": 1.0035780606005707e-05, | |
| "loss": 0.4584, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.5208569228678835, | |
| "grad_norm": 3.336552858352661, | |
| "learning_rate": 9.582861542642331e-06, | |
| "loss": 0.4445, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.5435028760360524, | |
| "grad_norm": 2.803347110748291, | |
| "learning_rate": 9.129942479278953e-06, | |
| "loss": 0.4435, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.5661488292042212, | |
| "grad_norm": 3.0676352977752686, | |
| "learning_rate": 8.677023415915576e-06, | |
| "loss": 0.4312, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.58879478237239, | |
| "grad_norm": 3.1657562255859375, | |
| "learning_rate": 8.2241043525522e-06, | |
| "loss": 0.4349, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.6114407355405589, | |
| "grad_norm": 3.551663398742676, | |
| "learning_rate": 7.771185289188824e-06, | |
| "loss": 0.4255, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.6340866887087278, | |
| "grad_norm": 2.3778510093688965, | |
| "learning_rate": 7.318266225825446e-06, | |
| "loss": 0.4148, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.6567326418768966, | |
| "grad_norm": 3.684070587158203, | |
| "learning_rate": 6.865347162462068e-06, | |
| "loss": 0.4151, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.6793785950450655, | |
| "grad_norm": 3.859379529953003, | |
| "learning_rate": 6.412428099098692e-06, | |
| "loss": 0.4113, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.7020245482132343, | |
| "grad_norm": 3.526158094406128, | |
| "learning_rate": 5.9595090357353145e-06, | |
| "loss": 0.4124, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.7246705013814031, | |
| "grad_norm": 3.6779990196228027, | |
| "learning_rate": 5.506589972371938e-06, | |
| "loss": 0.4032, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.747316454549572, | |
| "grad_norm": 6.240302085876465, | |
| "learning_rate": 5.05367090900856e-06, | |
| "loss": 0.4019, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.7699624077177408, | |
| "grad_norm": 3.5423877239227295, | |
| "learning_rate": 4.600751845645184e-06, | |
| "loss": 0.3845, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.7926083608859097, | |
| "grad_norm": 3.668982982635498, | |
| "learning_rate": 4.147832782281806e-06, | |
| "loss": 0.3948, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.8152543140540786, | |
| "grad_norm": 4.242081642150879, | |
| "learning_rate": 3.6949137189184298e-06, | |
| "loss": 0.3826, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.8379002672222474, | |
| "grad_norm": 3.223057270050049, | |
| "learning_rate": 3.2419946555550525e-06, | |
| "loss": 0.3867, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.8605462203904163, | |
| "grad_norm": 2.9004533290863037, | |
| "learning_rate": 2.7890755921916756e-06, | |
| "loss": 0.3894, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.883192173558585, | |
| "grad_norm": 3.2891807556152344, | |
| "learning_rate": 2.3361565288282987e-06, | |
| "loss": 0.3793, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.9058381267267539, | |
| "grad_norm": 2.6867599487304688, | |
| "learning_rate": 1.8832374654649217e-06, | |
| "loss": 0.3732, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.9284840798949228, | |
| "grad_norm": 2.811148166656494, | |
| "learning_rate": 1.4303184021015446e-06, | |
| "loss": 0.3794, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.9511300330630916, | |
| "grad_norm": 3.6918985843658447, | |
| "learning_rate": 9.773993387381675e-07, | |
| "loss": 0.3767, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.9737759862312605, | |
| "grad_norm": 2.762467622756958, | |
| "learning_rate": 5.244802753747906e-07, | |
| "loss": 0.3741, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.9964219393994294, | |
| "grad_norm": 2.7618136405944824, | |
| "learning_rate": 7.156121201141356e-08, | |
| "loss": 0.3751, | |
| "step": 22000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 22079, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 6.147503784984576e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |