| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005075455099140556, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6918183663801855e-05, | |
| "eval_loss": 0.2189994901418686, | |
| "eval_runtime": 1263.3794, | |
| "eval_samples_per_second": 19.7, | |
| "eval_steps_per_second": 9.85, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.075455099140556e-05, | |
| "grad_norm": 1.5588386058807373, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1905, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010150910198281112, | |
| "grad_norm": 0.6940944790840149, | |
| "learning_rate": 0.00012, | |
| "loss": 0.1677, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013534546931041484, | |
| "eval_loss": 0.13315555453300476, | |
| "eval_runtime": 1263.5211, | |
| "eval_samples_per_second": 19.697, | |
| "eval_steps_per_second": 9.849, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001522636529742167, | |
| "grad_norm": 0.9706745147705078, | |
| "learning_rate": 0.00018, | |
| "loss": 0.3327, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00020301820396562224, | |
| "grad_norm": 0.374950110912323, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.1078, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002537727549570278, | |
| "grad_norm": 0.29398947954177856, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.1129, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002706909386208297, | |
| "eval_loss": 0.07761387526988983, | |
| "eval_runtime": 1263.0933, | |
| "eval_samples_per_second": 19.704, | |
| "eval_steps_per_second": 9.852, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003045273059484334, | |
| "grad_norm": 0.24593223631381989, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0773, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00035528185693983896, | |
| "grad_norm": 0.19737200438976288, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.045, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0004060364079312445, | |
| "grad_norm": 0.22253718972206116, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0293, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004060364079312445, | |
| "eval_loss": 0.06464230269193649, | |
| "eval_runtime": 1263.0193, | |
| "eval_samples_per_second": 19.705, | |
| "eval_steps_per_second": 9.853, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00045679095892265005, | |
| "grad_norm": 0.43239113688468933, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0639, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005075455099140556, | |
| "grad_norm": 0.3265659213066101, | |
| "learning_rate": 0.0, | |
| "loss": 0.0522, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2200275750223872.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |