| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 29, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 2.067214871055153, | |
| "learning_rate": 0.0, | |
| "loss": 0.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 2.2902974488934356, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 1.043, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 1.8959065809264741, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.9429, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 1.7531397239789308, | |
| "learning_rate": 1.2857142857142857e-05, | |
| "loss": 0.9852, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 1.9134009040538502, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.9898, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 2.4981051959996017, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.9729, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 2.1259191076410326, | |
| "learning_rate": 2.5714285714285714e-05, | |
| "loss": 0.9501, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 2.6083028457024127, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9957, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 2.2174618708678193, | |
| "learning_rate": 2.999581555818041e-05, | |
| "loss": 1.003, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 1.310512297596868, | |
| "learning_rate": 2.9983264567328756e-05, | |
| "loss": 0.9666, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 1.0417774774374975, | |
| "learning_rate": 2.9962354029963835e-05, | |
| "loss": 0.8532, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 1.096319575622801, | |
| "learning_rate": 2.9933095612609253e-05, | |
| "loss": 0.8722, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.45614035087719296, | |
| "grad_norm": 1.051828485887936, | |
| "learning_rate": 2.989550563928436e-05, | |
| "loss": 0.94, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 0.7880955122292899, | |
| "learning_rate": 2.9849605082396678e-05, | |
| "loss": 0.8454, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.6655179120990646, | |
| "learning_rate": 2.9795419551040836e-05, | |
| "loss": 0.8716, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.6709188694271632, | |
| "learning_rate": 2.973297927671063e-05, | |
| "loss": 0.8177, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5964912280701754, | |
| "grad_norm": 0.7681555199843141, | |
| "learning_rate": 2.966231909643208e-05, | |
| "loss": 0.9286, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.6474330407996667, | |
| "learning_rate": 2.958347843332696e-05, | |
| "loss": 0.8274, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.5325702575478014, | |
| "learning_rate": 2.949650127461764e-05, | |
| "loss": 0.8929, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.5849013227799386, | |
| "learning_rate": 2.940143614708549e-05, | |
| "loss": 0.891, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.6549654089627338, | |
| "learning_rate": 2.9298336089996538e-05, | |
| "loss": 0.8568, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 0.5258630198755742, | |
| "learning_rate": 2.9187258625509518e-05, | |
| "loss": 0.8109, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8070175438596491, | |
| "grad_norm": 0.4998629934118094, | |
| "learning_rate": 2.906826572658278e-05, | |
| "loss": 0.875, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.42855717754389155, | |
| "learning_rate": 2.8941423782397987e-05, | |
| "loss": 0.8454, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.50628059004859, | |
| "learning_rate": 2.8806803561319903e-05, | |
| "loss": 0.8334, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 0.5060863985075719, | |
| "learning_rate": 2.866448017141291e-05, | |
| "loss": 0.8989, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.8609761967398525, | |
| "learning_rate": 2.8514533018536286e-05, | |
| "loss": 0.7991, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 0.48863408976007106, | |
| "learning_rate": 2.835704576204167e-05, | |
| "loss": 0.8282, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.48863408976007106, | |
| "learning_rate": 2.8192106268097336e-05, | |
| "loss": 0.7073, | |
| "step": 29 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 12946871943168.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |