| { |
| "best_metric": 43.6441, |
| "best_model_checkpoint": "opus_big_adapt_wce_gloss_unsampled_bands_7_ubweight_1.5/checkpoint-80000", |
| "epoch": 1.9716574245224892, |
| "global_step": 80000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2, |
| "learning_rate": 1.9753635243376465e-05, |
| "loss": 0.1779, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_bleu": 42.3466, |
| "eval_gen_len": 34.1314, |
| "eval_loss": 0.09819881618022919, |
| "eval_runtime": 147.9956, |
| "eval_samples_per_second": 7.048, |
| "eval_steps_per_second": 0.446, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 1.9507270486752928e-05, |
| "loss": 0.1471, |
| "step": 16000 |
| }, |
| { |
| "epoch": 0.39, |
| "eval_bleu": 42.6127, |
| "eval_gen_len": 34.3682, |
| "eval_loss": 0.09763215482234955, |
| "eval_runtime": 92.3945, |
| "eval_samples_per_second": 11.289, |
| "eval_steps_per_second": 0.714, |
| "step": 16000 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 1.9260844115834877e-05, |
| "loss": 0.143, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.59, |
| "eval_bleu": 42.3437, |
| "eval_gen_len": 33.6031, |
| "eval_loss": 0.09766430407762527, |
| "eval_runtime": 84.1375, |
| "eval_samples_per_second": 12.396, |
| "eval_steps_per_second": 0.784, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 1.901447935921134e-05, |
| "loss": 0.1391, |
| "step": 32000 |
| }, |
| { |
| "epoch": 0.79, |
| "eval_bleu": 42.6785, |
| "eval_gen_len": 33.7076, |
| "eval_loss": 0.0967756137251854, |
| "eval_runtime": 80.1108, |
| "eval_samples_per_second": 13.019, |
| "eval_steps_per_second": 0.824, |
| "step": 32000 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 1.8768083795440544e-05, |
| "loss": 0.1377, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.99, |
| "eval_bleu": 42.593, |
| "eval_gen_len": 34.2493, |
| "eval_loss": 0.09624858945608139, |
| "eval_runtime": 89.2577, |
| "eval_samples_per_second": 11.685, |
| "eval_steps_per_second": 0.739, |
| "step": 40000 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 1.8521749845964266e-05, |
| "loss": 0.1226, |
| "step": 48000 |
| }, |
| { |
| "epoch": 1.18, |
| "eval_bleu": 43.0072, |
| "eval_gen_len": 33.9262, |
| "eval_loss": 0.09690112620592117, |
| "eval_runtime": 81.2861, |
| "eval_samples_per_second": 12.831, |
| "eval_steps_per_second": 0.812, |
| "step": 48000 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 1.827535428219347e-05, |
| "loss": 0.1229, |
| "step": 56000 |
| }, |
| { |
| "epoch": 1.38, |
| "eval_bleu": 42.0603, |
| "eval_gen_len": 34.1515, |
| "eval_loss": 0.09700236469507217, |
| "eval_runtime": 106.3162, |
| "eval_samples_per_second": 9.81, |
| "eval_steps_per_second": 0.621, |
| "step": 56000 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 1.8028989525569933e-05, |
| "loss": 0.1235, |
| "step": 64000 |
| }, |
| { |
| "epoch": 1.58, |
| "eval_bleu": 43.1273, |
| "eval_gen_len": 34.5503, |
| "eval_loss": 0.09687265008687973, |
| "eval_runtime": 104.2899, |
| "eval_samples_per_second": 10.001, |
| "eval_steps_per_second": 0.633, |
| "step": 64000 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 1.7782655576093655e-05, |
| "loss": 0.123, |
| "step": 72000 |
| }, |
| { |
| "epoch": 1.77, |
| "eval_bleu": 42.8922, |
| "eval_gen_len": 34.3643, |
| "eval_loss": 0.09673970192670822, |
| "eval_runtime": 85.0152, |
| "eval_samples_per_second": 12.268, |
| "eval_steps_per_second": 0.776, |
| "step": 72000 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 1.753626001232286e-05, |
| "loss": 0.1227, |
| "step": 80000 |
| }, |
| { |
| "epoch": 1.97, |
| "eval_bleu": 43.6441, |
| "eval_gen_len": 33.999, |
| "eval_loss": 0.09602336585521698, |
| "eval_runtime": 92.3918, |
| "eval_samples_per_second": 11.289, |
| "eval_steps_per_second": 0.714, |
| "step": 80000 |
| } |
| ], |
| "max_steps": 649200, |
| "num_train_epochs": 16, |
| "total_flos": 2.5844916958632346e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
