| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8761073308512004, | |
| "global_step": 5600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 3.641, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 1.9178, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.7533, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.9066718816757202, | |
| "eval_rouge2_fmeasure": 0.1762, | |
| "eval_rouge2_precision": 0.1696, | |
| "eval_rouge2_recall": 0.2103, | |
| "eval_runtime": 1724.6841, | |
| "eval_samples_per_second": 0.252, | |
| "eval_steps_per_second": 0.252, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 1.6872, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.6179, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.6207, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.9220949411392212, | |
| "eval_rouge2_fmeasure": 0.1758, | |
| "eval_rouge2_precision": 0.1798, | |
| "eval_rouge2_recall": 0.1946, | |
| "eval_runtime": 1498.1119, | |
| "eval_samples_per_second": 0.29, | |
| "eval_steps_per_second": 0.29, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.917069799585349e-05, | |
| "loss": 1.6178, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.806496199032481e-05, | |
| "loss": 1.5584, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.695922598479613e-05, | |
| "loss": 1.335, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.585348997926745e-05, | |
| "loss": 1.3719, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 1.7529886960983276, | |
| "eval_rouge2_fmeasure": 0.2175, | |
| "eval_rouge2_precision": 0.2233, | |
| "eval_rouge2_recall": 0.2326, | |
| "eval_runtime": 1473.4895, | |
| "eval_samples_per_second": 0.295, | |
| "eval_steps_per_second": 0.295, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.4747753973738772e-05, | |
| "loss": 1.3211, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.3642017968210091e-05, | |
| "loss": 1.3276, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.2536281962681412e-05, | |
| "loss": 1.2702, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.668319821357727, | |
| "eval_rouge2_fmeasure": 0.2329, | |
| "eval_rouge2_precision": 0.2476, | |
| "eval_rouge2_recall": 0.2394, | |
| "eval_runtime": 1458.0732, | |
| "eval_samples_per_second": 0.298, | |
| "eval_steps_per_second": 0.298, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.143054595715273e-05, | |
| "loss": 1.2236, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.0324809951624052e-05, | |
| "loss": 1.2533, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.21907394609537e-06, | |
| "loss": 1.2119, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 1.6909013986587524, | |
| "eval_rouge2_fmeasure": 0.2427, | |
| "eval_rouge2_precision": 0.2552, | |
| "eval_rouge2_recall": 0.2507, | |
| "eval_runtime": 1496.8818, | |
| "eval_samples_per_second": 0.29, | |
| "eval_steps_per_second": 0.29, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.11333794056669e-06, | |
| "loss": 1.0075, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.00760193503801e-06, | |
| "loss": 0.9473, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5.901865929509331e-06, | |
| "loss": 0.9265, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 4.796129923980651e-06, | |
| "loss": 0.9583, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 1.6477222442626953, | |
| "eval_rouge2_fmeasure": 0.253, | |
| "eval_rouge2_precision": 0.2591, | |
| "eval_rouge2_recall": 0.2655, | |
| "eval_runtime": 1466.7648, | |
| "eval_samples_per_second": 0.296, | |
| "eval_steps_per_second": 0.296, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.69039391845197e-06, | |
| "loss": 0.8958, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.5846579129232894e-06, | |
| "loss": 0.9714, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.4789219073946095e-06, | |
| "loss": 0.8989, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 1.6045594215393066, | |
| "eval_rouge2_fmeasure": 0.264, | |
| "eval_rouge2_precision": 0.2695, | |
| "eval_rouge2_recall": 0.2781, | |
| "eval_runtime": 1496.2313, | |
| "eval_samples_per_second": 0.29, | |
| "eval_steps_per_second": 0.29, | |
| "step": 5600 | |
| } | |
| ], | |
| "max_steps": 5841, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.3748207477325824e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |