| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18248175182481752, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036496350364963502, | |
| "grad_norm": 0.014942636713385582, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036496350364963502, | |
| "eval_loss": 11.937646865844727, | |
| "eval_runtime": 0.4523, | |
| "eval_samples_per_second": 256.465, | |
| "eval_steps_per_second": 128.233, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0072992700729927005, | |
| "grad_norm": 0.012954114004969597, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9353, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010948905109489052, | |
| "grad_norm": 0.012448250316083431, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9411, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014598540145985401, | |
| "grad_norm": 0.00847446545958519, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9396, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01824817518248175, | |
| "grad_norm": 0.010436758399009705, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9398, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021897810218978103, | |
| "grad_norm": 0.01240889634937048, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9398, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025547445255474453, | |
| "grad_norm": 0.012278017587959766, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9363, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.029197080291970802, | |
| "grad_norm": 0.01409133430570364, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9362, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.032846715328467155, | |
| "grad_norm": 0.010964547283947468, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9383, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0364963503649635, | |
| "grad_norm": 0.01435481570661068, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9375, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.040145985401459854, | |
| "grad_norm": 0.00981847196817398, | |
| "learning_rate": 0.0001996917333733128, | |
| "loss": 11.9376, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.043795620437956206, | |
| "grad_norm": 0.009977707639336586, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 11.9376, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04744525547445255, | |
| "grad_norm": 0.01374763622879982, | |
| "learning_rate": 0.00019723699203976766, | |
| "loss": 11.9375, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04744525547445255, | |
| "eval_loss": 11.937407493591309, | |
| "eval_runtime": 0.461, | |
| "eval_samples_per_second": 251.611, | |
| "eval_steps_per_second": 125.805, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.051094890510948905, | |
| "grad_norm": 0.011579697951674461, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.9379, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05474452554744526, | |
| "grad_norm": 0.010436128824949265, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 11.9376, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.058394160583941604, | |
| "grad_norm": 0.01555589772760868, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 11.937, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06204379562043796, | |
| "grad_norm": 0.012454457581043243, | |
| "learning_rate": 0.00018526401643540922, | |
| "loss": 11.9363, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06569343065693431, | |
| "grad_norm": 0.016757259145379066, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 11.9351, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06934306569343066, | |
| "grad_norm": 0.012486481107771397, | |
| "learning_rate": 0.0001760405965600031, | |
| "loss": 11.9399, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 0.018843721598386765, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 11.9363, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07664233576642336, | |
| "grad_norm": 0.012065412476658821, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 11.935, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08029197080291971, | |
| "grad_norm": 0.013166313990950584, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 11.9383, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08394160583941605, | |
| "grad_norm": 0.016667328774929047, | |
| "learning_rate": 0.0001522498564715949, | |
| "loss": 11.9342, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08759124087591241, | |
| "grad_norm": 0.012548817321658134, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 11.9384, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09124087591240876, | |
| "grad_norm": 0.012698717415332794, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 11.9366, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0948905109489051, | |
| "grad_norm": 0.012354554608464241, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.937, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0948905109489051, | |
| "eval_loss": 11.93701171875, | |
| "eval_runtime": 0.4615, | |
| "eval_samples_per_second": 251.328, | |
| "eval_steps_per_second": 125.664, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09854014598540146, | |
| "grad_norm": 0.011796779930591583, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 11.9357, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10218978102189781, | |
| "grad_norm": 0.014917504042387009, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 11.9356, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10583941605839416, | |
| "grad_norm": 0.01455847267061472, | |
| "learning_rate": 0.0001078459095727845, | |
| "loss": 11.9375, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10948905109489052, | |
| "grad_norm": 0.010509638115763664, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9371, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11313868613138686, | |
| "grad_norm": 0.010377367027103901, | |
| "learning_rate": 9.215409042721552e-05, | |
| "loss": 11.9354, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11678832116788321, | |
| "grad_norm": 0.014895463362336159, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 11.9354, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12043795620437957, | |
| "grad_norm": 0.01482429075986147, | |
| "learning_rate": 7.66554636144095e-05, | |
| "loss": 11.9347, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12408759124087591, | |
| "grad_norm": 0.020593857392668724, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 11.9365, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12773722627737227, | |
| "grad_norm": 0.013053865171968937, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 11.9348, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13138686131386862, | |
| "grad_norm": 0.014818524941802025, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 11.9374, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.13503649635036497, | |
| "grad_norm": 0.018579095602035522, | |
| "learning_rate": 4.7750143528405126e-05, | |
| "loss": 11.9358, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1386861313868613, | |
| "grad_norm": 0.014956467784941196, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 11.936, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14233576642335766, | |
| "grad_norm": 0.009931315667927265, | |
| "learning_rate": 3.5055195166981645e-05, | |
| "loss": 11.9358, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14233576642335766, | |
| "eval_loss": 11.936786651611328, | |
| "eval_runtime": 0.4619, | |
| "eval_samples_per_second": 251.13, | |
| "eval_steps_per_second": 125.565, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 0.010320533998310566, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 11.9364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14963503649635038, | |
| "grad_norm": 0.015699736773967743, | |
| "learning_rate": 2.3959403439996907e-05, | |
| "loss": 11.9369, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15328467153284672, | |
| "grad_norm": 0.015644729137420654, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 11.9351, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15693430656934307, | |
| "grad_norm": 0.016171997413039207, | |
| "learning_rate": 1.4735983564590783e-05, | |
| "loss": 11.9347, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16058394160583941, | |
| "grad_norm": 0.01559949479997158, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 11.9351, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16423357664233576, | |
| "grad_norm": 0.010892484337091446, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 11.939, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1678832116788321, | |
| "grad_norm": 0.012285547330975533, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 11.9399, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.17153284671532848, | |
| "grad_norm": 0.011205232702195644, | |
| "learning_rate": 2.7630079602323442e-06, | |
| "loss": 11.9356, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17518248175182483, | |
| "grad_norm": 0.011147280223667622, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 11.9377, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.17883211678832117, | |
| "grad_norm": 0.012826742604374886, | |
| "learning_rate": 3.0826662668720364e-07, | |
| "loss": 11.9364, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18248175182481752, | |
| "grad_norm": 0.01375089306384325, | |
| "learning_rate": 0.0, | |
| "loss": 11.9352, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5908070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |