| { | |
| "best_metric": 0.47385331988334656, | |
| "best_model_checkpoint": "output/checkpoint-150", | |
| "epoch": 0.32844093195114443, | |
| "eval_steps": 50, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.8903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.2222222222222224e-05, | |
| "loss": 0.7189, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.8228571428571428, | |
| "eval_loss": 0.5415178537368774, | |
| "eval_runtime": 28.5756, | |
| "eval_samples_per_second": 6.124, | |
| "eval_steps_per_second": 1.54, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8658536585365855e-05, | |
| "loss": 0.5723, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.49520450830459595, | |
| "eval_runtime": 28.516, | |
| "eval_samples_per_second": 6.137, | |
| "eval_steps_per_second": 1.543, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.5609756097560978e-05, | |
| "loss": 0.5122, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.7885714285714286, | |
| "eval_loss": 0.47385331988334656, | |
| "eval_runtime": 28.2004, | |
| "eval_samples_per_second": 6.206, | |
| "eval_steps_per_second": 1.56, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.2560975609756098e-05, | |
| "loss": 0.4831, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.7942857142857143, | |
| "eval_loss": 0.49147841334342957, | |
| "eval_runtime": 28.6363, | |
| "eval_samples_per_second": 6.111, | |
| "eval_steps_per_second": 1.537, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.51219512195122e-06, | |
| "loss": 0.5009, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.501244068145752, | |
| "eval_runtime": 27.6943, | |
| "eval_samples_per_second": 6.319, | |
| "eval_steps_per_second": 1.589, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.463414634146342e-06, | |
| "loss": 0.4883, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.7885714285714286, | |
| "eval_loss": 0.49123460054397583, | |
| "eval_runtime": 28.0924, | |
| "eval_samples_per_second": 6.229, | |
| "eval_steps_per_second": 1.566, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.414634146341464e-06, | |
| "loss": 0.4979, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.4914019703865051, | |
| "eval_runtime": 28.7942, | |
| "eval_samples_per_second": 6.078, | |
| "eval_steps_per_second": 1.528, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.6585365853658536e-07, | |
| "loss": 0.5208, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.8057142857142857, | |
| "eval_loss": 0.49244898557662964, | |
| "eval_runtime": 28.8556, | |
| "eval_samples_per_second": 6.065, | |
| "eval_steps_per_second": 1.525, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 400, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 1.4827795775901696e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |