| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993906154783668, | |
| "eval_steps": 500, | |
| "global_step": 410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02437538086532602, | |
| "grad_norm": 0.7390244007110596, | |
| "learning_rate": 1.0975609756097562e-05, | |
| "loss": 3.3584, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04875076173065204, | |
| "grad_norm": 0.30350491404533386, | |
| "learning_rate": 2.1951219512195124e-05, | |
| "loss": 3.1749, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07312614259597806, | |
| "grad_norm": 0.3087550699710846, | |
| "learning_rate": 3.292682926829269e-05, | |
| "loss": 2.9963, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09750152346130408, | |
| "grad_norm": 0.20843257009983063, | |
| "learning_rate": 4.51219512195122e-05, | |
| "loss": 2.8865, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1218769043266301, | |
| "grad_norm": 0.2306743711233139, | |
| "learning_rate": 4.996738892723075e-05, | |
| "loss": 2.8482, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14625228519195613, | |
| "grad_norm": 0.37552645802497864, | |
| "learning_rate": 4.976840705816688e-05, | |
| "loss": 2.8334, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17062766605728213, | |
| "grad_norm": 0.207833930850029, | |
| "learning_rate": 4.939000027687756e-05, | |
| "loss": 2.7419, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19500304692260817, | |
| "grad_norm": 0.213443323969841, | |
| "learning_rate": 4.8834909801373264e-05, | |
| "loss": 2.6897, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21937842778793418, | |
| "grad_norm": 0.31744861602783203, | |
| "learning_rate": 4.810715676468894e-05, | |
| "loss": 2.6547, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2437538086532602, | |
| "grad_norm": 0.3662812113761902, | |
| "learning_rate": 4.7212013085378824e-05, | |
| "loss": 2.6865, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2681291895185862, | |
| "grad_norm": 0.2681748867034912, | |
| "learning_rate": 4.615596327719111e-05, | |
| "loss": 2.6123, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.29250457038391225, | |
| "grad_norm": 0.22331994771957397, | |
| "learning_rate": 4.507424333013069e-05, | |
| "loss": 2.5791, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3168799512492383, | |
| "grad_norm": 0.3823238015174866, | |
| "learning_rate": 4.373446685572683e-05, | |
| "loss": 2.5722, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34125533211456427, | |
| "grad_norm": 1.0558502674102783, | |
| "learning_rate": 4.225897595837744e-05, | |
| "loss": 2.5763, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3656307129798903, | |
| "grad_norm": 0.2607211470603943, | |
| "learning_rate": 4.0658459247330766e-05, | |
| "loss": 2.5901, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39000609384521634, | |
| "grad_norm": 0.5509762763977051, | |
| "learning_rate": 3.8944511031809865e-05, | |
| "loss": 2.5185, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4143814747105424, | |
| "grad_norm": 0.2571032643318176, | |
| "learning_rate": 3.712954733063284e-05, | |
| "loss": 2.4729, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43875685557586835, | |
| "grad_norm": 0.25064775347709656, | |
| "learning_rate": 3.5226715929283506e-05, | |
| "loss": 2.5748, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4631322364411944, | |
| "grad_norm": 0.2534530758857727, | |
| "learning_rate": 3.324980113598824e-05, | |
| "loss": 2.5046, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4875076173065204, | |
| "grad_norm": 0.5358842015266418, | |
| "learning_rate": 3.121312392675618e-05, | |
| "loss": 2.5345, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5118829981718465, | |
| "grad_norm": 0.22321267426013947, | |
| "learning_rate": 2.9131438202742124e-05, | |
| "loss": 2.4931, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5362583790371724, | |
| "grad_norm": 0.48219671845436096, | |
| "learning_rate": 2.7019823911454812e-05, | |
| "loss": 2.4892, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5606337599024985, | |
| "grad_norm": 0.22396139800548553, | |
| "learning_rate": 2.4893577806051537e-05, | |
| "loss": 2.5281, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5850091407678245, | |
| "grad_norm": 0.28134435415267944, | |
| "learning_rate": 2.2768102634070147e-05, | |
| "loss": 2.4737, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6093845216331505, | |
| "grad_norm": 0.32630693912506104, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 2.4923, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6337599024984766, | |
| "grad_norm": 0.27705642580986023, | |
| "learning_rate": 1.8580936618269696e-05, | |
| "loss": 2.4491, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6581352833638026, | |
| "grad_norm": 1.0377610921859741, | |
| "learning_rate": 1.6549578039787436e-05, | |
| "loss": 2.5303, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6825106642291285, | |
| "grad_norm": 0.212926983833313, | |
| "learning_rate": 1.4579435195321434e-05, | |
| "loss": 2.4304, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7068860450944546, | |
| "grad_norm": 1.0300441980361938, | |
| "learning_rate": 1.2684780004180414e-05, | |
| "loss": 2.4408, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7312614259597806, | |
| "grad_norm": 0.33628296852111816, | |
| "learning_rate": 1.0879337545275165e-05, | |
| "loss": 2.4091, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7556368068251066, | |
| "grad_norm": 0.2797647714614868, | |
| "learning_rate": 9.176186631221958e-06, | |
| "loss": 2.3872, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7800121876904327, | |
| "grad_norm": 0.21739082038402557, | |
| "learning_rate": 7.587665064066085e-06, | |
| "loss": 2.4045, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8043875685557587, | |
| "grad_norm": 0.508171796798706, | |
| "learning_rate": 6.125280258962873e-06, | |
| "loss": 2.4953, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8287629494210847, | |
| "grad_norm": 0.2408667802810669, | |
| "learning_rate": 4.799625883267672e-06, | |
| "loss": 2.3752, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8531383302864107, | |
| "grad_norm": 0.2731145918369293, | |
| "learning_rate": 3.6203051149095973e-06, | |
| "loss": 2.3658, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8775137111517367, | |
| "grad_norm": 0.3211069703102112, | |
| "learning_rate": 2.595861075973613e-06, | |
| "loss": 2.4198, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9018890920170628, | |
| "grad_norm": 0.2237868458032608, | |
| "learning_rate": 1.733714945437212e-06, | |
| "loss": 2.4113, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9262644728823888, | |
| "grad_norm": 0.2606222629547119, | |
| "learning_rate": 1.0401121993794033e-06, | |
| "loss": 2.4011, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9506398537477148, | |
| "grad_norm": 0.47373390197753906, | |
| "learning_rate": 5.20077368103597e-07, | |
| "loss": 2.4523, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9750152346130408, | |
| "grad_norm": 0.5579819679260254, | |
| "learning_rate": 1.77377637918405e-07, | |
| "loss": 2.4289, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9993906154783668, | |
| "grad_norm": 0.25126489996910095, | |
| "learning_rate": 1.4495561248931145e-08, | |
| "loss": 2.4421, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9993906154783668, | |
| "step": 410, | |
| "total_flos": 5.610936315118879e+18, | |
| "train_loss": 2.5786649890062288, | |
| "train_runtime": 34559.7112, | |
| "train_samples_per_second": 0.38, | |
| "train_steps_per_second": 0.012 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 410, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.610936315118879e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |