| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9961568024596464, |
| "eval_steps": 10, |
| "global_step": 36, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03, |
| "learning_rate": 3.9923893961834914e-05, |
| "loss": 1.3268, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 3.812615574073301e-05, |
| "loss": 1.2548, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 3.285575219373079e-05, |
| "loss": 1.1912, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_loss": 1.109934687614441, |
| "eval_runtime": 9.2946, |
| "eval_samples_per_second": 5.057, |
| "eval_steps_per_second": 1.291, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 2.5176380902050418e-05, |
| "loss": 1.1433, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 1.6527036446661396e-05, |
| "loss": 1.1238, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.55, |
| "eval_loss": 1.065536379814148, |
| "eval_runtime": 9.2887, |
| "eval_samples_per_second": 5.06, |
| "eval_steps_per_second": 1.292, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 8.528471272979083e-06, |
| "loss": 1.1102, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 2.679491924311226e-06, |
| "loss": 1.1258, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.83, |
| "eval_loss": 1.055001974105835, |
| "eval_runtime": 9.2909, |
| "eval_samples_per_second": 5.059, |
| "eval_steps_per_second": 1.292, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 7.61060381650891e-08, |
| "loss": 1.1272, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 36, |
| "total_flos": 1.0010669722946765e+17, |
| "train_loss": 1.1544433269235823, |
| "train_runtime": 5078.5964, |
| "train_samples_per_second": 1.537, |
| "train_steps_per_second": 0.007 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 36, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 20, |
| "total_flos": 1.0010669722946765e+17, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
