| { | |
| "best_metric": 0.3890952467918396, | |
| "best_model_checkpoint": "model_llama_2_7b_chat_en_v1/checkpoint-24000", | |
| "epoch": 2.0, | |
| "eval_steps": 6000, | |
| "global_step": 24000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.9e-05, | |
| "loss": 1.1006, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.3964994251728058, | |
| "eval_runtime": 5565.0211, | |
| "eval_samples_per_second": 1.078, | |
| "eval_steps_per_second": 1.078, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.3742, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.3896908760070801, | |
| "eval_runtime": 5514.7798, | |
| "eval_samples_per_second": 1.088, | |
| "eval_steps_per_second": 1.088, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.7e-05, | |
| "loss": 0.3454, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 0.38943949341773987, | |
| "eval_runtime": 5571.6554, | |
| "eval_samples_per_second": 1.077, | |
| "eval_steps_per_second": 1.077, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.3463, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3890952467918396, | |
| "eval_runtime": 5531.3063, | |
| "eval_samples_per_second": 1.085, | |
| "eval_steps_per_second": 1.085, | |
| "step": 24000 | |
| } | |
| ], | |
| "logging_steps": 6000, | |
| "max_steps": 120000, | |
| "num_train_epochs": 10, | |
| "save_steps": 6000, | |
| "total_flos": 3.897169840963584e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |