| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015417228753131625, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0030834457506263247, | |
| "grad_norm": 0.21250227093696594, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030834457506263247, | |
| "eval_loss": 6.927585601806641, | |
| "eval_runtime": 18.5124, | |
| "eval_samples_per_second": 29.548, | |
| "eval_steps_per_second": 14.801, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0061668915012526495, | |
| "grad_norm": 0.2152594029903412, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9299, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0061668915012526495, | |
| "eval_loss": 6.927536964416504, | |
| "eval_runtime": 1.5987, | |
| "eval_samples_per_second": 342.151, | |
| "eval_steps_per_second": 171.388, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009250337251878975, | |
| "grad_norm": 0.23285658657550812, | |
| "learning_rate": 3e-05, | |
| "loss": 6.9273, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012333783002505299, | |
| "grad_norm": 0.2242552936077118, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9307, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012333783002505299, | |
| "eval_loss": 6.92720890045166, | |
| "eval_runtime": 1.6311, | |
| "eval_samples_per_second": 335.36, | |
| "eval_steps_per_second": 167.986, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015417228753131625, | |
| "grad_norm": 0.20901034772396088, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9333, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 52733214720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |