| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 11.965708791795748, |
| "global_step": 21000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5735206007957458, |
| "eval_runtime": 226.9724, |
| "eval_samples_per_second": 109.67, |
| "eval_steps_per_second": 27.417, |
| "step": 1755 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.5326883792877197, |
| "eval_runtime": 225.773, |
| "eval_samples_per_second": 110.252, |
| "eval_steps_per_second": 27.563, |
| "step": 3510 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.5004657506942749, |
| "eval_runtime": 223.9431, |
| "eval_samples_per_second": 111.153, |
| "eval_steps_per_second": 27.788, |
| "step": 5265 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.48436784744262695, |
| "eval_runtime": 223.6051, |
| "eval_samples_per_second": 111.321, |
| "eval_steps_per_second": 27.83, |
| "step": 7020 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.4659739136695862, |
| "eval_runtime": 221.9535, |
| "eval_samples_per_second": 112.15, |
| "eval_steps_per_second": 28.037, |
| "step": 8775 |
| }, |
| { |
| "epoch": 5.7, |
| "learning_rate": 5.251661918328585e-05, |
| "loss": 0.4274, |
| "step": 10000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.4595305621623993, |
| "eval_runtime": 232.1017, |
| "eval_samples_per_second": 107.246, |
| "eval_steps_per_second": 26.812, |
| "step": 10530 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.44809117913246155, |
| "eval_runtime": 230.3824, |
| "eval_samples_per_second": 108.046, |
| "eval_steps_per_second": 27.012, |
| "step": 12285 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.44372686743736267, |
| "eval_runtime": 220.8242, |
| "eval_samples_per_second": 112.723, |
| "eval_steps_per_second": 28.181, |
| "step": 14040 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.4426543712615967, |
| "eval_runtime": 226.8705, |
| "eval_samples_per_second": 109.719, |
| "eval_steps_per_second": 27.43, |
| "step": 15795 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.4342004656791687, |
| "eval_runtime": 221.9982, |
| "eval_samples_per_second": 112.127, |
| "eval_steps_per_second": 28.032, |
| "step": 17550 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.43299490213394165, |
| "eval_runtime": 221.9453, |
| "eval_samples_per_second": 112.154, |
| "eval_steps_per_second": 28.038, |
| "step": 19305 |
| }, |
| { |
| "epoch": 11.4, |
| "learning_rate": 5.0332383665717e-06, |
| "loss": 0.2777, |
| "step": 20000 |
| } |
| ], |
| "max_steps": 21060, |
| "num_train_epochs": 12, |
| "total_flos": 4.092582190428979e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
