| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.075313807531381, | |
| "eval_steps": 50, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06694560669456066, | |
| "grad_norm": 27.560821533203125, | |
| "learning_rate": 5e-06, | |
| "loss": 10.1223, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06694560669456066, | |
| "eval_loss": 10.099274635314941, | |
| "eval_runtime": 0.2689, | |
| "eval_samples_per_second": 747.449, | |
| "eval_steps_per_second": 48.342, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13389121338912133, | |
| "grad_norm": 28.028085708618164, | |
| "learning_rate": 1e-05, | |
| "loss": 10.0918, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.200836820083682, | |
| "grad_norm": 26.342453002929688, | |
| "learning_rate": 1.5e-05, | |
| "loss": 10.097, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.26778242677824265, | |
| "grad_norm": 26.227397918701172, | |
| "learning_rate": 2e-05, | |
| "loss": 10.038, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.33472803347280333, | |
| "grad_norm": 28.014986038208008, | |
| "learning_rate": 2.5e-05, | |
| "loss": 9.9078, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.401673640167364, | |
| "grad_norm": 25.674665451049805, | |
| "learning_rate": 3e-05, | |
| "loss": 9.7148, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4686192468619247, | |
| "grad_norm": 25.88928985595703, | |
| "learning_rate": 3.5e-05, | |
| "loss": 9.4521, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5355648535564853, | |
| "grad_norm": 22.087249755859375, | |
| "learning_rate": 4e-05, | |
| "loss": 9.3105, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.602510460251046, | |
| "grad_norm": 21.283077239990234, | |
| "learning_rate": 4.5e-05, | |
| "loss": 9.0043, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6694560669456067, | |
| "grad_norm": 21.313087463378906, | |
| "learning_rate": 5e-05, | |
| "loss": 8.7409, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7364016736401674, | |
| "grad_norm": 20.148950576782227, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 8.4883, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.803347280334728, | |
| "grad_norm": 20.127819061279297, | |
| "learning_rate": 6e-05, | |
| "loss": 8.1642, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8702928870292888, | |
| "grad_norm": 20.053115844726562, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 7.8865, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9372384937238494, | |
| "grad_norm": 20.051658630371094, | |
| "learning_rate": 7e-05, | |
| "loss": 7.5385, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0251046025104602, | |
| "grad_norm": 26.823057174682617, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 9.9643, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0920502092050208, | |
| "grad_norm": 17.49614143371582, | |
| "learning_rate": 8e-05, | |
| "loss": 6.9635, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1589958158995817, | |
| "grad_norm": 15.299077033996582, | |
| "learning_rate": 8.5e-05, | |
| "loss": 6.481, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2259414225941423, | |
| "grad_norm": 14.408894538879395, | |
| "learning_rate": 9e-05, | |
| "loss": 6.2407, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.292887029288703, | |
| "grad_norm": 13.718225479125977, | |
| "learning_rate": 9.5e-05, | |
| "loss": 5.9908, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.3598326359832635, | |
| "grad_norm": 12.873955726623535, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6383, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4267782426778242, | |
| "grad_norm": 11.39185619354248, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 5.525, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.493723849372385, | |
| "grad_norm": 10.285475730895996, | |
| "learning_rate": 9.842915805643155e-05, | |
| "loss": 5.0268, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.5606694560669456, | |
| "grad_norm": 9.467267036437988, | |
| "learning_rate": 9.648882429441257e-05, | |
| "loss": 5.0979, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6276150627615062, | |
| "grad_norm": 9.132113456726074, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 5.0314, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.694560669456067, | |
| "grad_norm": 7.965480804443359, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.7873, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7615062761506275, | |
| "grad_norm": 6.717679023742676, | |
| "learning_rate": 8.644843137107059e-05, | |
| "loss": 4.7389, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8284518828451883, | |
| "grad_norm": 6.294735431671143, | |
| "learning_rate": 8.18711994874345e-05, | |
| "loss": 4.4523, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.895397489539749, | |
| "grad_norm": 5.053362846374512, | |
| "learning_rate": 7.679133974894983e-05, | |
| "loss": 4.5132, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.9623430962343096, | |
| "grad_norm": 5.998095989227295, | |
| "learning_rate": 7.128896457825364e-05, | |
| "loss": 5.5026, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.0502092050209204, | |
| "grad_norm": 5.140533447265625, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.16, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.1171548117154813, | |
| "grad_norm": 4.294057369232178, | |
| "learning_rate": 5.9369065729286245e-05, | |
| "loss": 4.1192, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.1841004184100417, | |
| "grad_norm": 4.689243793487549, | |
| "learning_rate": 5.313952597646568e-05, | |
| "loss": 4.1063, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.2510460251046025, | |
| "grad_norm": 4.195860385894775, | |
| "learning_rate": 4.6860474023534335e-05, | |
| "loss": 4.2288, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.3179916317991633, | |
| "grad_norm": 4.730858325958252, | |
| "learning_rate": 4.063093427071376e-05, | |
| "loss": 4.3229, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.3849372384937237, | |
| "grad_norm": 3.84011173248291, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.1128, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.4518828451882846, | |
| "grad_norm": 3.5080318450927734, | |
| "learning_rate": 2.8711035421746367e-05, | |
| "loss": 4.0789, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.518828451882845, | |
| "grad_norm": 3.859924554824829, | |
| "learning_rate": 2.3208660251050158e-05, | |
| "loss": 4.1502, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.585774058577406, | |
| "grad_norm": 3.6729748249053955, | |
| "learning_rate": 1.8128800512565513e-05, | |
| "loss": 3.9726, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.6527196652719667, | |
| "grad_norm": 2.9506115913391113, | |
| "learning_rate": 1.3551568628929434e-05, | |
| "loss": 4.0159, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.719665271966527, | |
| "grad_norm": 3.1066789627075195, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 4.1407, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.786610878661088, | |
| "grad_norm": 2.8327407836914062, | |
| "learning_rate": 6.184665997806832e-06, | |
| "loss": 3.9974, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.8535564853556483, | |
| "grad_norm": 2.8391292095184326, | |
| "learning_rate": 3.511175705587433e-06, | |
| "loss": 3.9826, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.920502092050209, | |
| "grad_norm": 3.0579187870025635, | |
| "learning_rate": 1.5708419435684462e-06, | |
| "loss": 3.8871, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.00836820083682, | |
| "grad_norm": 3.730663299560547, | |
| "learning_rate": 3.9426493427611177e-07, | |
| "loss": 5.4636, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.075313807531381, | |
| "grad_norm": 2.6881635189056396, | |
| "learning_rate": 0.0, | |
| "loss": 3.9492, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 45, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 470968329830400.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |