| { | |
| "best_metric": 2.967562437057495, | |
| "best_model_checkpoint": "flan-t5-base-flant5-apple-support/checkpoint-5785", | |
| "epoch": 5.0, | |
| "global_step": 5785, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.567847882454624e-05, | |
| "loss": 3.3318, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.135695764909248e-05, | |
| "loss": 3.2673, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 18.972318339100347, | |
| "eval_loss": 3.0350406169891357, | |
| "eval_rouge1": 12.4094, | |
| "eval_rouge2": 2.1794, | |
| "eval_rougeL": 9.5255, | |
| "eval_rougeLsum": 10.9739, | |
| "eval_runtime": 319.5992, | |
| "eval_samples_per_second": 14.468, | |
| "eval_steps_per_second": 1.809, | |
| "step": 1157 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.7035436473638726e-05, | |
| "loss": 3.2145, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.271391529818496e-05, | |
| "loss": 3.1854, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 18.964749134948097, | |
| "eval_loss": 2.9991722106933594, | |
| "eval_rouge1": 12.4579, | |
| "eval_rouge2": 2.1512, | |
| "eval_rougeL": 9.5232, | |
| "eval_rougeLsum": 11.0049, | |
| "eval_runtime": 319.123, | |
| "eval_samples_per_second": 14.49, | |
| "eval_steps_per_second": 1.811, | |
| "step": 2314 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.8392394122731204e-05, | |
| "loss": 3.1388, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.4070872947277444e-05, | |
| "loss": 3.1006, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 18.9435553633218, | |
| "eval_loss": 2.9792306423187256, | |
| "eval_rouge1": 12.9794, | |
| "eval_rouge2": 2.2794, | |
| "eval_rougeL": 9.9245, | |
| "eval_rougeLsum": 11.5019, | |
| "eval_runtime": 317.3217, | |
| "eval_samples_per_second": 14.572, | |
| "eval_steps_per_second": 1.821, | |
| "step": 3471 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.9749351771823683e-05, | |
| "loss": 3.1209, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.5427830596369925e-05, | |
| "loss": 3.0729, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.1106309420916162e-05, | |
| "loss": 3.0751, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 18.91371107266436, | |
| "eval_loss": 2.971137762069702, | |
| "eval_rouge1": 12.6779, | |
| "eval_rouge2": 2.1828, | |
| "eval_rougeL": 9.6962, | |
| "eval_rougeLsum": 11.221, | |
| "eval_runtime": 320.2879, | |
| "eval_samples_per_second": 14.437, | |
| "eval_steps_per_second": 1.805, | |
| "step": 4628 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 6.784788245462403e-06, | |
| "loss": 3.0641, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.4632670700086435e-06, | |
| "loss": 3.0532, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 18.908737024221452, | |
| "eval_loss": 2.967562437057495, | |
| "eval_rouge1": 12.7991, | |
| "eval_rouge2": 2.244, | |
| "eval_rougeL": 9.8075, | |
| "eval_rougeLsum": 11.3618, | |
| "eval_runtime": 318.8859, | |
| "eval_samples_per_second": 14.5, | |
| "eval_steps_per_second": 1.813, | |
| "step": 5785 | |
| } | |
| ], | |
| "max_steps": 5785, | |
| "num_train_epochs": 5, | |
| "total_flos": 3.166660376395776e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |