| { | |
| "best_metric": 1.1354840993881226, | |
| "best_model_checkpoint": "./outputs/checkpoint-1000", | |
| "epoch": 1.3333333333333333, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1585, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.2452774047851562, | |
| "eval_runtime": 180.3075, | |
| "eval_samples_per_second": 10.704, | |
| "eval_steps_per_second": 1.342, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0217, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.2180681228637695, | |
| "eval_runtime": 177.5054, | |
| "eval_samples_per_second": 10.873, | |
| "eval_steps_per_second": 1.363, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0048, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.203295350074768, | |
| "eval_runtime": 177.4062, | |
| "eval_samples_per_second": 10.879, | |
| "eval_steps_per_second": 1.364, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.992, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.190936803817749, | |
| "eval_runtime": 177.5627, | |
| "eval_samples_per_second": 10.869, | |
| "eval_steps_per_second": 1.363, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9767, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.1756863594055176, | |
| "eval_runtime": 177.0747, | |
| "eval_samples_per_second": 10.899, | |
| "eval_steps_per_second": 1.367, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9715, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.1637059450149536, | |
| "eval_runtime": 177.4052, | |
| "eval_samples_per_second": 10.879, | |
| "eval_steps_per_second": 1.364, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9653, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.1604684591293335, | |
| "eval_runtime": 177.5251, | |
| "eval_samples_per_second": 10.872, | |
| "eval_steps_per_second": 1.363, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9517, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.1489245891571045, | |
| "eval_runtime": 180.9559, | |
| "eval_samples_per_second": 10.666, | |
| "eval_steps_per_second": 1.337, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9397, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.1430203914642334, | |
| "eval_runtime": 178.7234, | |
| "eval_samples_per_second": 10.799, | |
| "eval_steps_per_second": 1.354, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9313, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.1354840993881226, | |
| "eval_runtime": 177.5002, | |
| "eval_samples_per_second": 10.873, | |
| "eval_steps_per_second": 1.363, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 7.474685431062528e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |