| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03827751196172249, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": 7.915914058685303, | |
| "learning_rate": 1e-05, | |
| "loss": 6.993, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "eval_loss": 7.515360355377197, | |
| "eval_runtime": 120.9594, | |
| "eval_samples_per_second": 1.819, | |
| "eval_steps_per_second": 0.909, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015311004784688996, | |
| "grad_norm": 7.573098659515381, | |
| "learning_rate": 2e-05, | |
| "loss": 7.5631, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015311004784688996, | |
| "eval_loss": 7.446014881134033, | |
| "eval_runtime": 5.539, | |
| "eval_samples_per_second": 39.718, | |
| "eval_steps_per_second": 19.859, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022966507177033493, | |
| "grad_norm": 9.778457641601562, | |
| "learning_rate": 3e-05, | |
| "loss": 7.8903, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03062200956937799, | |
| "grad_norm": 9.943881034851074, | |
| "learning_rate": 4e-05, | |
| "loss": 7.5538, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03062200956937799, | |
| "eval_loss": 7.305823802947998, | |
| "eval_runtime": 5.6005, | |
| "eval_samples_per_second": 39.282, | |
| "eval_steps_per_second": 19.641, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03827751196172249, | |
| "grad_norm": 8.075981140136719, | |
| "learning_rate": 5e-05, | |
| "loss": 7.5417, | |
| "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": 184754189893632.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |