| { |
| "best_metric": 0.030991671606898308, |
| "best_model_checkpoint": "/home/media/felipe/Internal_2TB/multimodal18/image-captioning-output/checkpoint-9342", |
| "epoch": 2.0, |
| "global_step": 9342, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11, |
| "learning_rate": 4.9464782701776926e-05, |
| "loss": 0.1645, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 4.892956540355384e-05, |
| "loss": 0.0359, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 4.8394348105330766e-05, |
| "loss": 0.034, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 4.785913080710769e-05, |
| "loss": 0.033, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 4.732391350888461e-05, |
| "loss": 0.0322, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 4.678869621066153e-05, |
| "loss": 0.0314, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 4.625347891243845e-05, |
| "loss": 0.0309, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 4.5718261614215376e-05, |
| "loss": 0.0304, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 4.518304431599229e-05, |
| "loss": 0.0302, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_gen_len": 19.0, |
| "eval_loss": 0.031059330329298973, |
| "eval_rouge1": 36.8379, |
| "eval_rouge2": 34.6599, |
| "eval_rougeL": 36.8396, |
| "eval_rougeLsum": 36.8368, |
| "eval_runtime": 17.4471, |
| "eval_samples_per_second": 11.578, |
| "eval_steps_per_second": 0.745, |
| "step": 4671 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 4.4647827017769217e-05, |
| "loss": 0.0298, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 4.411260971954614e-05, |
| "loss": 0.0296, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 4.357739242132306e-05, |
| "loss": 0.0296, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 4.304217512309998e-05, |
| "loss": 0.0292, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 4.2506957824876904e-05, |
| "loss": 0.0295, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 4.197174052665383e-05, |
| "loss": 0.0283, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 4.1436523228430744e-05, |
| "loss": 0.0286, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 4.090130593020767e-05, |
| "loss": 0.0286, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 4.036608863198459e-05, |
| "loss": 0.0291, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_gen_len": 19.0, |
| "eval_loss": 0.030991671606898308, |
| "eval_rouge1": 36.8379, |
| "eval_rouge2": 34.6599, |
| "eval_rougeL": 36.8396, |
| "eval_rougeLsum": 36.8368, |
| "eval_runtime": 17.3145, |
| "eval_samples_per_second": 11.666, |
| "eval_steps_per_second": 0.751, |
| "step": 9342 |
| } |
| ], |
| "max_steps": 46710, |
| "num_train_epochs": 10, |
| "total_flos": 7.93871901414245e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
