| { | |
| "best_metric": 0.08091000467538834, | |
| "best_model_checkpoint": "/kaggle/working/trainer/checkpoint-472", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 472, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.388888888888889e-05, | |
| "loss": 0.7936, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.1481190025806427, | |
| "eval_runtime": 37.3733, | |
| "eval_samples_per_second": 0.696, | |
| "eval_steps_per_second": 0.348, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.2962962962962964e-05, | |
| "loss": 0.1048, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.1020423024892807, | |
| "eval_runtime": 37.3813, | |
| "eval_samples_per_second": 0.696, | |
| "eval_steps_per_second": 0.348, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.2037037037037038e-05, | |
| "loss": 0.0731, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.08479975163936615, | |
| "eval_runtime": 37.4565, | |
| "eval_samples_per_second": 0.694, | |
| "eval_steps_per_second": 0.347, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0518, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.08091000467538834, | |
| "eval_runtime": 37.3984, | |
| "eval_samples_per_second": 0.695, | |
| "eval_steps_per_second": 0.348, | |
| "step": 472 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 1.748999270993756e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |