| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1261.8181818181818, | |
| "eval_steps": 500, | |
| "global_step": 3470, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 36.36363636363637, | |
| "grad_norm": 4.233419895172119, | |
| "learning_rate": 0.00019995452431006844, | |
| "loss": 3.7823, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 72.72727272727273, | |
| "grad_norm": 9.719901084899902, | |
| "learning_rate": 0.00019981048452912364, | |
| "loss": 1.3042, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 109.0909090909091, | |
| "grad_norm": 4.322120666503906, | |
| "learning_rate": 0.00019956794385021442, | |
| "loss": 0.7792, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 145.45454545454547, | |
| "grad_norm": 5.652794361114502, | |
| "learning_rate": 0.0001992271416317086, | |
| "loss": 0.5389, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 181.8181818181818, | |
| "grad_norm": 5.370779514312744, | |
| "learning_rate": 0.00019878841420425023, | |
| "loss": 0.3919, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 218.1818181818182, | |
| "grad_norm": 6.141811847686768, | |
| "learning_rate": 0.00019825219453884207, | |
| "loss": 0.2818, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 254.54545454545453, | |
| "grad_norm": 4.134015083312988, | |
| "learning_rate": 0.0001976190118195553, | |
| "loss": 0.1966, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 290.90909090909093, | |
| "grad_norm": 7.964496612548828, | |
| "learning_rate": 0.0001968894909212887, | |
| "loss": 0.1349, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 327.27272727272725, | |
| "grad_norm": 1.0434647798538208, | |
| "learning_rate": 0.0001960643517930928, | |
| "loss": 0.0931, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 363.6363636363636, | |
| "grad_norm": 4.57155179977417, | |
| "learning_rate": 0.0001951444087476669, | |
| "loss": 0.0594, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "grad_norm": 0.8262210488319397, | |
| "learning_rate": 0.0001941411696251397, | |
| "loss": 0.0473, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 436.3636363636364, | |
| "grad_norm": 2.0997166633605957, | |
| "learning_rate": 0.000193035358728009, | |
| "loss": 0.0226, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 472.72727272727275, | |
| "grad_norm": 8.319884300231934, | |
| "learning_rate": 0.00019183773316410876, | |
| "loss": 0.0183, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 509.09090909090907, | |
| "grad_norm": 0.06114543229341507, | |
| "learning_rate": 0.00019054947484527945, | |
| "loss": 0.0115, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 545.4545454545455, | |
| "grad_norm": 0.19133609533309937, | |
| "learning_rate": 0.00018917185512694839, | |
| "loss": 0.0159, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 581.8181818181819, | |
| "grad_norm": 0.4022941291332245, | |
| "learning_rate": 0.00018770623355345562, | |
| "loss": 0.0143, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 618.1818181818181, | |
| "grad_norm": 3.1849958896636963, | |
| "learning_rate": 0.00018615405651634746, | |
| "loss": 0.0107, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 654.5454545454545, | |
| "grad_norm": 0.0581185445189476, | |
| "learning_rate": 0.00018451685582696297, | |
| "loss": 0.0084, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 690.9090909090909, | |
| "grad_norm": 0.1319303661584854, | |
| "learning_rate": 0.00018279624720472093, | |
| "loss": 0.0109, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 727.2727272727273, | |
| "grad_norm": 3.9375159740448, | |
| "learning_rate": 0.00018099392868259988, | |
| "loss": 0.0053, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 763.6363636363636, | |
| "grad_norm": 0.0051200115121901035, | |
| "learning_rate": 0.00017911167893138466, | |
| "loss": 0.0144, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 800.0, | |
| "grad_norm": 0.0055800010450184345, | |
| "learning_rate": 0.00017715135550433285, | |
| "loss": 0.0076, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 836.3636363636364, | |
| "grad_norm": 0.03737466782331467, | |
| "learning_rate": 0.00017511489300399432, | |
| "loss": 0.0084, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 872.7272727272727, | |
| "grad_norm": 0.06793994456529617, | |
| "learning_rate": 0.0001730043011729918, | |
| "loss": 0.0063, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 909.0909090909091, | |
| "grad_norm": 0.0068795159459114075, | |
| "learning_rate": 0.0001708216629106476, | |
| "loss": 0.0107, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 945.4545454545455, | |
| "grad_norm": 0.5895256996154785, | |
| "learning_rate": 0.0001685691322174136, | |
| "loss": 0.0091, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 981.8181818181819, | |
| "grad_norm": 0.1091279685497284, | |
| "learning_rate": 0.00016624893206913265, | |
| "loss": 0.0024, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1018.1818181818181, | |
| "grad_norm": 0.04799462854862213, | |
| "learning_rate": 0.00016386335222322998, | |
| "loss": 0.0089, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1054.5454545454545, | |
| "grad_norm": 0.011366182006895542, | |
| "learning_rate": 0.00016141474695899894, | |
| "loss": 0.0083, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1090.909090909091, | |
| "grad_norm": 0.010076832957565784, | |
| "learning_rate": 0.00015890553275421163, | |
| "loss": 0.0059, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1127.2727272727273, | |
| "grad_norm": 0.0046064723283052444, | |
| "learning_rate": 0.00015633818590034704, | |
| "loss": 0.0033, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1163.6363636363637, | |
| "grad_norm": 0.09949818253517151, | |
| "learning_rate": 0.00015374173627698756, | |
| "loss": 0.0066, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1200.0, | |
| "grad_norm": 0.009247034788131714, | |
| "learning_rate": 0.00015106629709603283, | |
| "loss": 0.0018, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1236.3636363636363, | |
| "grad_norm": 2.8236868381500244, | |
| "learning_rate": 0.00014834046164515305, | |
| "loss": 0.0046, | |
| "step": 3400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 10000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5000, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0175353452509184e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |