| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 58, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 2108.397216796875, | |
| "learning_rate": 2.5454545454545454e-08, | |
| "loss": 1035.4573, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 2107.33642578125, | |
| "learning_rate": 5.727272727272728e-08, | |
| "loss": 1065.6187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 2219.214111328125, | |
| "learning_rate": 8.90909090909091e-08, | |
| "loss": 1036.3791, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 1936.712890625, | |
| "learning_rate": 1.2090909090909092e-07, | |
| "loss": 1035.5998, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 2196.76318359375, | |
| "learning_rate": 1.5272727272727273e-07, | |
| "loss": 1064.9285, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 2548.19189453125, | |
| "learning_rate": 1.8454545454545454e-07, | |
| "loss": 1048.6884, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 2420.173828125, | |
| "learning_rate": 2.1636363636363637e-07, | |
| "loss": 1050.2486, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 2168.558349609375, | |
| "learning_rate": 2.481818181818182e-07, | |
| "loss": 1027.9692, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5517241379310345, | |
| "grad_norm": 2378.92431640625, | |
| "learning_rate": 2.8e-07, | |
| "loss": 1043.8671, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 2213.712158203125, | |
| "learning_rate": 3.1181818181818186e-07, | |
| "loss": 1042.2683, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.896551724137931, | |
| "grad_norm": 2194.255615234375, | |
| "learning_rate": 3.436363636363636e-07, | |
| "loss": 1032.4518, | |
| "step": 55 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 58, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7211980486851994e+17, | |
| "train_batch_size": 14, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |