| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03544776119402985, | |
| "eval_steps": 38, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009328358208955224, | |
| "grad_norm": 2.931856870651245, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1183, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009328358208955224, | |
| "eval_loss": 0.7989240884780884, | |
| "eval_runtime": 61.068, | |
| "eval_samples_per_second": 7.402, | |
| "eval_steps_per_second": 3.701, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018656716417910447, | |
| "grad_norm": 3.0857083797454834, | |
| "learning_rate": 8e-05, | |
| "loss": 3.3967, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002798507462686567, | |
| "grad_norm": 2.9495201110839844, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4361, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037313432835820895, | |
| "grad_norm": 2.4459776878356934, | |
| "learning_rate": 0.00016, | |
| "loss": 3.2275, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0046641791044776115, | |
| "grad_norm": 2.410581588745117, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0069, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005597014925373134, | |
| "grad_norm": 1.99094820022583, | |
| "learning_rate": 0.00024, | |
| "loss": 2.6997, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0065298507462686565, | |
| "grad_norm": 1.850408911705017, | |
| "learning_rate": 0.00028, | |
| "loss": 2.6469, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007462686567164179, | |
| "grad_norm": 2.972104072570801, | |
| "learning_rate": 0.00032, | |
| "loss": 3.351, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008395522388059701, | |
| "grad_norm": 2.8936173915863037, | |
| "learning_rate": 0.00036, | |
| "loss": 2.8041, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009328358208955223, | |
| "grad_norm": 2.354464530944824, | |
| "learning_rate": 0.0004, | |
| "loss": 2.7652, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010261194029850746, | |
| "grad_norm": 2.024070978164673, | |
| "learning_rate": 0.0003999496469885013, | |
| "loss": 2.8786, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011194029850746268, | |
| "grad_norm": 1.8775830268859863, | |
| "learning_rate": 0.00039979861330826294, | |
| "loss": 2.0356, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012126865671641791, | |
| "grad_norm": 1.7130846977233887, | |
| "learning_rate": 0.0003995469750092912, | |
| "loss": 2.6772, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013059701492537313, | |
| "grad_norm": 1.9945520162582397, | |
| "learning_rate": 0.00039919485879904784, | |
| "loss": 2.8959, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013992537313432836, | |
| "grad_norm": 1.6973563432693481, | |
| "learning_rate": 0.00039874244197864856, | |
| "loss": 2.3531, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014925373134328358, | |
| "grad_norm": 1.5936486721038818, | |
| "learning_rate": 0.00039818995235358696, | |
| "loss": 1.9481, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01585820895522388, | |
| "grad_norm": 1.828995943069458, | |
| "learning_rate": 0.00039753766811902755, | |
| "loss": 3.6787, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.016791044776119403, | |
| "grad_norm": 1.553421139717102, | |
| "learning_rate": 0.0003967859177197259, | |
| "loss": 2.2696, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017723880597014924, | |
| "grad_norm": 1.2893372774124146, | |
| "learning_rate": 0.00039593507968464716, | |
| "loss": 1.9452, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 1.674631953239441, | |
| "learning_rate": 0.0003949855824363647, | |
| "loss": 2.2916, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01958955223880597, | |
| "grad_norm": 1.4569449424743652, | |
| "learning_rate": 0.0003939379040753374, | |
| "loss": 2.1701, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.020522388059701493, | |
| "grad_norm": 1.438828468322754, | |
| "learning_rate": 0.00039279257213917066, | |
| "loss": 2.5621, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.021455223880597014, | |
| "grad_norm": 1.3770123720169067, | |
| "learning_rate": 0.0003915501633369861, | |
| "loss": 2.1366, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.022388059701492536, | |
| "grad_norm": 1.4712828397750854, | |
| "learning_rate": 0.00039021130325903074, | |
| "loss": 2.319, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02332089552238806, | |
| "grad_norm": 1.465248465538025, | |
| "learning_rate": 0.00038877666606167355, | |
| "loss": 2.3959, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024253731343283583, | |
| "grad_norm": 1.4384740591049194, | |
| "learning_rate": 0.00038724697412794747, | |
| "loss": 2.097, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.025186567164179104, | |
| "grad_norm": 1.3539812564849854, | |
| "learning_rate": 0.0003856229977038078, | |
| "loss": 2.2313, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.026119402985074626, | |
| "grad_norm": 1.3618801832199097, | |
| "learning_rate": 0.0003839055545102902, | |
| "loss": 2.1054, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.027052238805970148, | |
| "grad_norm": 1.422633409500122, | |
| "learning_rate": 0.00038209550933176323, | |
| "loss": 2.276, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027985074626865673, | |
| "grad_norm": 1.4232622385025024, | |
| "learning_rate": 0.0003801937735804838, | |
| "loss": 2.1735, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.028917910447761194, | |
| "grad_norm": 1.4555679559707642, | |
| "learning_rate": 0.0003782013048376736, | |
| "loss": 2.2706, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 1.2929563522338867, | |
| "learning_rate": 0.0003761191063713476, | |
| "loss": 1.9037, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.030783582089552237, | |
| "grad_norm": 1.2687627077102661, | |
| "learning_rate": 0.0003739482266311391, | |
| "loss": 2.1032, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03171641791044776, | |
| "grad_norm": 1.2993357181549072, | |
| "learning_rate": 0.00037168975872037323, | |
| "loss": 2.0062, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03264925373134328, | |
| "grad_norm": 1.3507018089294434, | |
| "learning_rate": 0.00036934483984565685, | |
| "loss": 2.1522, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.033582089552238806, | |
| "grad_norm": 1.4183921813964844, | |
| "learning_rate": 0.00036691465074426054, | |
| "loss": 1.845, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03451492537313433, | |
| "grad_norm": 1.3370906114578247, | |
| "learning_rate": 0.00036440041508958203, | |
| "loss": 1.9448, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03544776119402985, | |
| "grad_norm": 1.4249347448349, | |
| "learning_rate": 0.0003618033988749895, | |
| "loss": 2.4594, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03544776119402985, | |
| "eval_loss": 0.5035107135772705, | |
| "eval_runtime": 60.2427, | |
| "eval_samples_per_second": 7.503, | |
| "eval_steps_per_second": 3.751, | |
| "step": 38 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 38, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4981999911567360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |