| { | |
| "best_metric": 6395.94580078125, | |
| "best_model_checkpoint": "./coco_outputs/checkpoint-72", | |
| "epoch": 20.0, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6398.77734375, | |
| "eval_runtime": 0.5241, | |
| "eval_samples_per_second": 15.264, | |
| "eval_steps_per_second": 1.908, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6398.435546875, | |
| "eval_runtime": 0.5241, | |
| "eval_samples_per_second": 15.265, | |
| "eval_steps_per_second": 1.908, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 6176.0926, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6398.2265625, | |
| "eval_runtime": 0.5251, | |
| "eval_samples_per_second": 15.235, | |
| "eval_steps_per_second": 1.904, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6397.8564453125, | |
| "eval_runtime": 0.5329, | |
| "eval_samples_per_second": 15.013, | |
| "eval_steps_per_second": 1.877, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 6292.8656, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6397.6298828125, | |
| "eval_runtime": 0.5291, | |
| "eval_samples_per_second": 15.121, | |
| "eval_steps_per_second": 1.89, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 6397.31787109375, | |
| "eval_runtime": 0.5319, | |
| "eval_samples_per_second": 15.042, | |
| "eval_steps_per_second": 1.88, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 6396.95263671875, | |
| "eval_runtime": 0.5129, | |
| "eval_samples_per_second": 15.596, | |
| "eval_steps_per_second": 1.95, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 6.25e-06, | |
| "loss": 6231.0688, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 6396.79052734375, | |
| "eval_runtime": 0.5163, | |
| "eval_samples_per_second": 15.494, | |
| "eval_steps_per_second": 1.937, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 6396.6748046875, | |
| "eval_runtime": 0.5303, | |
| "eval_samples_per_second": 15.085, | |
| "eval_steps_per_second": 1.886, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5e-06, | |
| "loss": 6090.4715, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 6396.595703125, | |
| "eval_runtime": 0.5278, | |
| "eval_samples_per_second": 15.158, | |
| "eval_steps_per_second": 1.895, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 6396.53466796875, | |
| "eval_runtime": 0.5332, | |
| "eval_samples_per_second": 15.004, | |
| "eval_steps_per_second": 1.876, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 6396.41064453125, | |
| "eval_runtime": 0.5371, | |
| "eval_samples_per_second": 14.895, | |
| "eval_steps_per_second": 1.862, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 6268.359, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 6396.3232421875, | |
| "eval_runtime": 0.521, | |
| "eval_samples_per_second": 15.354, | |
| "eval_steps_per_second": 1.919, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 6396.234375, | |
| "eval_runtime": 0.5384, | |
| "eval_samples_per_second": 14.858, | |
| "eval_steps_per_second": 1.857, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.5e-06, | |
| "loss": 6384.7945, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 6396.095703125, | |
| "eval_runtime": 0.5186, | |
| "eval_samples_per_second": 15.426, | |
| "eval_steps_per_second": 1.928, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 6396.09033203125, | |
| "eval_runtime": 0.5163, | |
| "eval_samples_per_second": 15.496, | |
| "eval_steps_per_second": 1.937, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 6396.0029296875, | |
| "eval_runtime": 0.5253, | |
| "eval_samples_per_second": 15.228, | |
| "eval_steps_per_second": 1.904, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 1.25e-06, | |
| "loss": 6325.7992, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 6395.94580078125, | |
| "eval_runtime": 0.5319, | |
| "eval_samples_per_second": 15.042, | |
| "eval_steps_per_second": 1.88, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 6395.97802734375, | |
| "eval_runtime": 0.5298, | |
| "eval_samples_per_second": 15.099, | |
| "eval_steps_per_second": 1.887, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 6265.4016, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 6395.9765625, | |
| "eval_runtime": 0.5361, | |
| "eval_samples_per_second": 14.924, | |
| "eval_steps_per_second": 1.865, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 80, | |
| "total_flos": 3.060008460288e+17, | |
| "train_loss": 6254.356591796875, | |
| "train_runtime": 330.5487, | |
| "train_samples_per_second": 1.936, | |
| "train_steps_per_second": 0.242 | |
| } | |
| ], | |
| "max_steps": 80, | |
| "num_train_epochs": 20, | |
| "total_flos": 3.060008460288e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |