| { | |
| "best_metric": 0.024566762149333954, | |
| "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific/sum/checkpoint-75", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.5065, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.4397, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4209679365158081, | |
| "eval_runtime": 5.755, | |
| "eval_samples_per_second": 34.753, | |
| "eval_steps_per_second": 4.344, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.8483, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.1766, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0503, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.045773524791002274, | |
| "eval_runtime": 5.7905, | |
| "eval_samples_per_second": 34.539, | |
| "eval_steps_per_second": 4.317, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.000285, | |
| "loss": 0.0382, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0355, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.024566762149333954, | |
| "eval_runtime": 5.7985, | |
| "eval_samples_per_second": 34.492, | |
| "eval_steps_per_second": 4.311, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 4450719301632000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |