| { | |
| "best_metric": 12.171875, | |
| "best_model_checkpoint": "model_bloomz_7b_en_v2/checkpoint-12000", | |
| "epoch": 1.0, | |
| "eval_steps": 6000, | |
| "global_step": 24000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.95e-05, | |
| "loss": 12.4199, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 12.1875, | |
| "eval_runtime": 6207.4138, | |
| "eval_samples_per_second": 0.967, | |
| "eval_steps_per_second": 0.967, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.9e-05, | |
| "loss": 12.2527, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 12.171875, | |
| "eval_runtime": 6397.7336, | |
| "eval_samples_per_second": 0.938, | |
| "eval_steps_per_second": 0.938, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8500000000000002e-05, | |
| "loss": 12.2629, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 12.171875, | |
| "eval_runtime": 5615.1984, | |
| "eval_samples_per_second": 1.069, | |
| "eval_steps_per_second": 1.069, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.8e-05, | |
| "loss": 12.275, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 12.171875, | |
| "eval_runtime": 4298.2404, | |
| "eval_samples_per_second": 1.396, | |
| "eval_steps_per_second": 1.396, | |
| "step": 24000 | |
| } | |
| ], | |
| "logging_steps": 6000, | |
| "max_steps": 240000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 6000, | |
| "total_flos": 1.781684773060608e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |