| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00026424704456196095, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.2849408912392196e-05, | |
| "grad_norm": 0.5534868836402893, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9604, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.2849408912392196e-05, | |
| "eval_loss": 6.9467291831970215, | |
| "eval_runtime": 52.4951, | |
| "eval_samples_per_second": 607.086, | |
| "eval_steps_per_second": 303.552, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010569881782478439, | |
| "grad_norm": 0.5524201393127441, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9555, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010569881782478439, | |
| "eval_loss": 6.9465436935424805, | |
| "eval_runtime": 38.2492, | |
| "eval_samples_per_second": 833.194, | |
| "eval_steps_per_second": 416.61, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001585482267371766, | |
| "grad_norm": 0.6071205735206604, | |
| "learning_rate": 3e-05, | |
| "loss": 6.9376, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00021139763564956878, | |
| "grad_norm": 0.6302489638328552, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9417, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021139763564956878, | |
| "eval_loss": 6.945753574371338, | |
| "eval_runtime": 38.2795, | |
| "eval_samples_per_second": 832.534, | |
| "eval_steps_per_second": 416.28, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00026424704456196095, | |
| "grad_norm": 0.5645687580108643, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9428, | |
| "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": 26366607360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |