| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0038322741353431482, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012774247117810494, | |
| "eval_loss": 4.265634536743164, | |
| "eval_runtime": 367.944, | |
| "eval_samples_per_second": 8.961, | |
| "eval_steps_per_second": 4.482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00038322741353431485, | |
| "grad_norm": 8.026169776916504, | |
| "learning_rate": 6e-05, | |
| "loss": 14.7151, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007664548270686297, | |
| "grad_norm": 14.828211784362793, | |
| "learning_rate": 0.00012, | |
| "loss": 22.9284, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010219397694248395, | |
| "eval_loss": 2.717600107192993, | |
| "eval_runtime": 369.4354, | |
| "eval_samples_per_second": 8.924, | |
| "eval_steps_per_second": 4.464, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011496822406029444, | |
| "grad_norm": 13.35394287109375, | |
| "learning_rate": 0.00018, | |
| "loss": 11.4639, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015329096541372594, | |
| "grad_norm": 10.815381050109863, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.6564, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0019161370676715741, | |
| "grad_norm": 9.865994453430176, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.6544, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002043879538849679, | |
| "eval_loss": 1.126829743385315, | |
| "eval_runtime": 369.8831, | |
| "eval_samples_per_second": 8.914, | |
| "eval_steps_per_second": 4.458, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002299364481205889, | |
| "grad_norm": 7.193143367767334, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.3582, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0026825918947402036, | |
| "grad_norm": 9.606064796447754, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 3.7334, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0030658193082745188, | |
| "grad_norm": 8.248322486877441, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.5828, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0030658193082745188, | |
| "eval_loss": 0.8723397254943848, | |
| "eval_runtime": 369.6879, | |
| "eval_samples_per_second": 8.918, | |
| "eval_steps_per_second": 4.461, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0034490467218088335, | |
| "grad_norm": 28.229259490966797, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.2489, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0038322741353431482, | |
| "grad_norm": 6.48671293258667, | |
| "learning_rate": 0.0, | |
| "loss": 3.6725, | |
| "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": 9801873028546560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |