| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010311670232785956, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010311670232785956, | |
| "eval_loss": 2.0299148559570312, | |
| "eval_runtime": 1157.9003, | |
| "eval_samples_per_second": 14.107, | |
| "eval_steps_per_second": 1.764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003093501069835787, | |
| "grad_norm": 23.948354721069336, | |
| "learning_rate": 1.5e-05, | |
| "loss": 8.1239, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006187002139671574, | |
| "grad_norm": 19.15797996520996, | |
| "learning_rate": 3e-05, | |
| "loss": 9.1409, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000928050320950736, | |
| "grad_norm": 9.434832572937012, | |
| "learning_rate": 4.5e-05, | |
| "loss": 7.1953, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000928050320950736, | |
| "eval_loss": 1.6139401197433472, | |
| "eval_runtime": 1163.807, | |
| "eval_samples_per_second": 14.035, | |
| "eval_steps_per_second": 1.755, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012374004279343148, | |
| "grad_norm": 6.820188522338867, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 6.3209, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0015467505349178933, | |
| "grad_norm": 8.132386207580566, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 6.0845, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001856100641901472, | |
| "grad_norm": 6.336308479309082, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 5.3419, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001856100641901472, | |
| "eval_loss": 1.508717656135559, | |
| "eval_runtime": 1164.3323, | |
| "eval_samples_per_second": 14.029, | |
| "eval_steps_per_second": 1.754, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0021654507488850505, | |
| "grad_norm": 8.175219535827637, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 5.8257, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0024748008558686295, | |
| "grad_norm": 11.247066497802734, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 6.2536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002784150962852208, | |
| "grad_norm": 6.052129745483398, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 6.0575, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002784150962852208, | |
| "eval_loss": 1.4805811643600464, | |
| "eval_runtime": 1164.3067, | |
| "eval_samples_per_second": 14.029, | |
| "eval_steps_per_second": 1.754, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0030935010698357867, | |
| "grad_norm": 8.591585159301758, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 6.1041, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0034028511768193653, | |
| "grad_norm": 8.520772933959961, | |
| "learning_rate": 4.2366459261474933e-05, | |
| "loss": 6.4861, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.003712201283802944, | |
| "grad_norm": 7.190521717071533, | |
| "learning_rate": 4.039153688314145e-05, | |
| "loss": 5.586, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.003712201283802944, | |
| "eval_loss": 1.4635615348815918, | |
| "eval_runtime": 1164.1403, | |
| "eval_samples_per_second": 14.031, | |
| "eval_steps_per_second": 1.754, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004021551390786523, | |
| "grad_norm": 5.165075302124023, | |
| "learning_rate": 3.824798160583012e-05, | |
| "loss": 5.4859, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.004330901497770101, | |
| "grad_norm": 7.677441596984863, | |
| "learning_rate": 3.5959278669726935e-05, | |
| "loss": 5.9298, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.00464025160475368, | |
| "grad_norm": 6.484046936035156, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 5.9238, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00464025160475368, | |
| "eval_loss": 1.4534233808517456, | |
| "eval_runtime": 1164.252, | |
| "eval_samples_per_second": 14.03, | |
| "eval_steps_per_second": 1.754, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004949601711737259, | |
| "grad_norm": 4.873887538909912, | |
| "learning_rate": 3.104804738999169e-05, | |
| "loss": 5.3023, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005258951818720837, | |
| "grad_norm": 7.830043792724609, | |
| "learning_rate": 2.8479327524001636e-05, | |
| "loss": 6.1552, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.005568301925704416, | |
| "grad_norm": 7.771931171417236, | |
| "learning_rate": 2.587248741756253e-05, | |
| "loss": 6.3556, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.005568301925704416, | |
| "eval_loss": 1.4463921785354614, | |
| "eval_runtime": 1163.8809, | |
| "eval_samples_per_second": 14.034, | |
| "eval_steps_per_second": 1.754, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.005877652032687994, | |
| "grad_norm": 5.285118579864502, | |
| "learning_rate": 2.3256088156396868e-05, | |
| "loss": 5.7694, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.006187002139671573, | |
| "grad_norm": 9.575898170471191, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 6.0135, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0064963522466551515, | |
| "grad_norm": 9.870296478271484, | |
| "learning_rate": 1.8109066104575023e-05, | |
| "loss": 6.1081, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0064963522466551515, | |
| "eval_loss": 1.4420286417007446, | |
| "eval_runtime": 1162.2128, | |
| "eval_samples_per_second": 14.054, | |
| "eval_steps_per_second": 1.757, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0068057023536387306, | |
| "grad_norm": 7.1199116706848145, | |
| "learning_rate": 1.56348351646022e-05, | |
| "loss": 6.1846, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.00711505246062231, | |
| "grad_norm": 6.888105869293213, | |
| "learning_rate": 1.3263210930352737e-05, | |
| "loss": 6.4734, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.007424402567605888, | |
| "grad_norm": 5.968530654907227, | |
| "learning_rate": 1.1020177413231334e-05, | |
| "loss": 6.0026, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.007424402567605888, | |
| "eval_loss": 1.4391638040542603, | |
| "eval_runtime": 1164.1161, | |
| "eval_samples_per_second": 14.031, | |
| "eval_steps_per_second": 1.754, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.007733752674589467, | |
| "grad_norm": 6.3695597648620605, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 4.9832, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.008043102781573046, | |
| "grad_norm": 7.817237854003906, | |
| "learning_rate": 7.016504991533726e-06, | |
| "loss": 5.7256, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.008352452888556624, | |
| "grad_norm": 10.837445259094238, | |
| "learning_rate": 5.299731159831953e-06, | |
| "loss": 5.7465, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.008352452888556624, | |
| "eval_loss": 1.4371966123580933, | |
| "eval_runtime": 1164.2518, | |
| "eval_samples_per_second": 14.03, | |
| "eval_steps_per_second": 1.754, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.008661802995540202, | |
| "grad_norm": 9.557851791381836, | |
| "learning_rate": 3.798797596089351e-06, | |
| "loss": 6.1063, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.008971153102523782, | |
| "grad_norm": 6.9002885818481445, | |
| "learning_rate": 2.5301488425208296e-06, | |
| "loss": 5.9132, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.00928050320950736, | |
| "grad_norm": 5.555031776428223, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 5.4556, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.00928050320950736, | |
| "eval_loss": 1.4364467859268188, | |
| "eval_runtime": 1163.3776, | |
| "eval_samples_per_second": 14.04, | |
| "eval_steps_per_second": 1.755, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.009589853316490938, | |
| "grad_norm": 4.54183292388916, | |
| "learning_rate": 7.426068431000882e-07, | |
| "loss": 4.9895, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.009899203423474518, | |
| "grad_norm": 4.971656799316406, | |
| "learning_rate": 2.4329828146074095e-07, | |
| "loss": 5.1195, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.010208553530458096, | |
| "grad_norm": 9.999255180358887, | |
| "learning_rate": 1.522932452260595e-08, | |
| "loss": 6.2284, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.010208553530458096, | |
| "eval_loss": 1.4362521171569824, | |
| "eval_runtime": 1163.4, | |
| "eval_samples_per_second": 14.04, | |
| "eval_steps_per_second": 1.755, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4625093572571955e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |