| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07075888908544135, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014151777817088271, | |
| "grad_norm": 0.20514807105064392, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9175, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014151777817088271, | |
| "eval_loss": 11.916790962219238, | |
| "eval_runtime": 8.5875, | |
| "eval_samples_per_second": 69.403, | |
| "eval_steps_per_second": 34.702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028303555634176542, | |
| "grad_norm": 0.23273983597755432, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9373, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004245533345126481, | |
| "grad_norm": 0.2802961468696594, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9104, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0056607111268353084, | |
| "grad_norm": 0.23625600337982178, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9218, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0070758889085441356, | |
| "grad_norm": 0.22699324786663055, | |
| "learning_rate": 0.0001, | |
| "loss": 11.915, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0070758889085441356, | |
| "eval_loss": 11.916035652160645, | |
| "eval_runtime": 8.7182, | |
| "eval_samples_per_second": 68.362, | |
| "eval_steps_per_second": 34.181, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008491066690252963, | |
| "grad_norm": 0.21260926127433777, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9222, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00990624447196179, | |
| "grad_norm": 0.2168704867362976, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9087, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011321422253670617, | |
| "grad_norm": 0.2431064248085022, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9209, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012736600035379445, | |
| "grad_norm": 0.19750989973545074, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9141, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014151777817088271, | |
| "grad_norm": 0.21232645213603973, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9101, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014151777817088271, | |
| "eval_loss": 11.913423538208008, | |
| "eval_runtime": 8.7577, | |
| "eval_samples_per_second": 68.054, | |
| "eval_steps_per_second": 34.027, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015566955598797099, | |
| "grad_norm": 0.2188003957271576, | |
| "learning_rate": 0.0001996917333733128, | |
| "loss": 11.9215, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016982133380505925, | |
| "grad_norm": 0.19326922297477722, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 11.9316, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01839731116221475, | |
| "grad_norm": 0.22555257380008698, | |
| "learning_rate": 0.00019723699203976766, | |
| "loss": 11.9136, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01981248894392358, | |
| "grad_norm": 0.2110656350851059, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.8945, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.021227666725632408, | |
| "grad_norm": 0.20976051688194275, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 11.9, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021227666725632408, | |
| "eval_loss": 11.909821510314941, | |
| "eval_runtime": 8.6935, | |
| "eval_samples_per_second": 68.557, | |
| "eval_steps_per_second": 34.279, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022642844507341234, | |
| "grad_norm": 0.24981027841567993, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 11.8935, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024058022289050063, | |
| "grad_norm": 0.2591237723827362, | |
| "learning_rate": 0.00018526401643540922, | |
| "loss": 11.905, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02547320007075889, | |
| "grad_norm": 0.22017155587673187, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 11.9214, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026888377852467716, | |
| "grad_norm": 0.25297868251800537, | |
| "learning_rate": 0.0001760405965600031, | |
| "loss": 11.9002, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.028303555634176542, | |
| "grad_norm": 0.25911155343055725, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 11.9091, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028303555634176542, | |
| "eval_loss": 11.90591049194336, | |
| "eval_runtime": 8.6221, | |
| "eval_samples_per_second": 69.125, | |
| "eval_steps_per_second": 34.562, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029718733415885372, | |
| "grad_norm": 0.24711765348911285, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 11.9044, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.031133911197594198, | |
| "grad_norm": 0.2823926508426666, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 11.8933, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.032549088979303024, | |
| "grad_norm": 0.2736799418926239, | |
| "learning_rate": 0.0001522498564715949, | |
| "loss": 11.9053, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03396426676101185, | |
| "grad_norm": 0.31680405139923096, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 11.9123, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03537944454272068, | |
| "grad_norm": 0.31065115332603455, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 11.9045, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03537944454272068, | |
| "eval_loss": 11.901829719543457, | |
| "eval_runtime": 8.5918, | |
| "eval_samples_per_second": 69.369, | |
| "eval_steps_per_second": 34.684, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0367946223244295, | |
| "grad_norm": 0.326715886592865, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.8983, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.038209800106138336, | |
| "grad_norm": 0.2866935133934021, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 11.9096, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03962497788784716, | |
| "grad_norm": 0.30991116166114807, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 11.8994, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04104015566955599, | |
| "grad_norm": 0.3176131248474121, | |
| "learning_rate": 0.0001078459095727845, | |
| "loss": 11.9071, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.042455333451264815, | |
| "grad_norm": 0.29141172766685486, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9017, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042455333451264815, | |
| "eval_loss": 11.898274421691895, | |
| "eval_runtime": 8.8396, | |
| "eval_samples_per_second": 67.424, | |
| "eval_steps_per_second": 33.712, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04387051123297364, | |
| "grad_norm": 0.3455469608306885, | |
| "learning_rate": 9.215409042721552e-05, | |
| "loss": 11.9159, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04528568901468247, | |
| "grad_norm": 0.3515758812427521, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 11.8921, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.046700866796391294, | |
| "grad_norm": 0.40223929286003113, | |
| "learning_rate": 7.66554636144095e-05, | |
| "loss": 11.9068, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04811604457810013, | |
| "grad_norm": 0.3547143042087555, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 11.9044, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04953122235980895, | |
| "grad_norm": 0.38809290528297424, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 11.8962, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04953122235980895, | |
| "eval_loss": 11.895332336425781, | |
| "eval_runtime": 8.7389, | |
| "eval_samples_per_second": 68.201, | |
| "eval_steps_per_second": 34.1, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05094640014151778, | |
| "grad_norm": 0.4227261543273926, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 11.8829, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.052361577923226606, | |
| "grad_norm": 0.38113293051719666, | |
| "learning_rate": 4.7750143528405126e-05, | |
| "loss": 11.8836, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05377675570493543, | |
| "grad_norm": 0.39981311559677124, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 11.8975, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05519193348664426, | |
| "grad_norm": 0.41320478916168213, | |
| "learning_rate": 3.5055195166981645e-05, | |
| "loss": 11.8876, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.056607111268353084, | |
| "grad_norm": 0.40017077326774597, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 11.892, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.056607111268353084, | |
| "eval_loss": 11.89357852935791, | |
| "eval_runtime": 8.5747, | |
| "eval_samples_per_second": 69.506, | |
| "eval_steps_per_second": 34.753, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05802228905006191, | |
| "grad_norm": 0.3937678337097168, | |
| "learning_rate": 2.3959403439996907e-05, | |
| "loss": 11.9013, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.059437466831770744, | |
| "grad_norm": 0.4014483392238617, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 11.886, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06085264461347957, | |
| "grad_norm": 0.38292697072029114, | |
| "learning_rate": 1.4735983564590783e-05, | |
| "loss": 11.8971, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.062267822395188396, | |
| "grad_norm": 0.38425660133361816, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 11.898, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06368300017689722, | |
| "grad_norm": 0.41762810945510864, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 11.8841, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06368300017689722, | |
| "eval_loss": 11.892833709716797, | |
| "eval_runtime": 8.6566, | |
| "eval_samples_per_second": 68.849, | |
| "eval_steps_per_second": 34.425, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06509817795860605, | |
| "grad_norm": 0.3865891396999359, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 11.8881, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06651335574031488, | |
| "grad_norm": 0.37985795736312866, | |
| "learning_rate": 2.7630079602323442e-06, | |
| "loss": 11.8981, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0679285335220237, | |
| "grad_norm": 0.4050770401954651, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 11.8896, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06934371130373253, | |
| "grad_norm": 0.3997718095779419, | |
| "learning_rate": 3.0826662668720364e-07, | |
| "loss": 11.9002, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07075888908544135, | |
| "grad_norm": 0.401860773563385, | |
| "learning_rate": 0.0, | |
| "loss": 11.8901, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07075888908544135, | |
| "eval_loss": 11.892694473266602, | |
| "eval_runtime": 8.599, | |
| "eval_samples_per_second": 69.31, | |
| "eval_steps_per_second": 34.655, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 74946969600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |