| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0057553956834532375, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000639488409272582, | |
| "grad_norm": 0.550638735294342, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6359, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000639488409272582, | |
| "eval_loss": 3.0662050247192383, | |
| "eval_runtime": 129.359, | |
| "eval_samples_per_second": 20.362, | |
| "eval_steps_per_second": 10.181, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001278976818545164, | |
| "grad_norm": 0.5973834991455078, | |
| "learning_rate": 2e-05, | |
| "loss": 2.746, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019184652278177458, | |
| "grad_norm": 0.5987102389335632, | |
| "learning_rate": 3e-05, | |
| "loss": 2.7733, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019184652278177458, | |
| "eval_loss": 3.031294107437134, | |
| "eval_runtime": 65.2068, | |
| "eval_samples_per_second": 40.395, | |
| "eval_steps_per_second": 20.197, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002557953637090328, | |
| "grad_norm": 0.5510293245315552, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6618, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031974420463629096, | |
| "grad_norm": 0.5740846991539001, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7497, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0038369304556354917, | |
| "grad_norm": 0.5723321437835693, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6459, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0038369304556354917, | |
| "eval_loss": 2.958235025405884, | |
| "eval_runtime": 82.818, | |
| "eval_samples_per_second": 31.805, | |
| "eval_steps_per_second": 15.902, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004476418864908073, | |
| "grad_norm": 0.630357027053833, | |
| "learning_rate": 7e-05, | |
| "loss": 2.6365, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005115907274180656, | |
| "grad_norm": 0.6484892964363098, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5914, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0057553956834532375, | |
| "grad_norm": 0.7151474952697754, | |
| "learning_rate": 9e-05, | |
| "loss": 2.5751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0057553956834532375, | |
| "eval_loss": 2.7833847999572754, | |
| "eval_runtime": 101.2113, | |
| "eval_samples_per_second": 26.025, | |
| "eval_steps_per_second": 13.012, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3526209259438080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |