| { | |
| "best_metric": 0.2082, | |
| "best_model_checkpoint": "mt0-xl_russian_natprompt_adafactor/checkpoint-2562", | |
| "epoch": 8.0, | |
| "global_step": 4100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.75e-05, | |
| "loss": 2.0449, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 16.75809549945115, | |
| "eval_loss": 1.6754746437072754, | |
| "eval_rouge1": 0.0817, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0778, | |
| "eval_rougeLsum": 0.0817, | |
| "eval_runtime": 196.0938, | |
| "eval_samples_per_second": 37.166, | |
| "eval_steps_per_second": 1.163, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.4995117187500005e-05, | |
| "loss": 1.707, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 15.862102085620197, | |
| "eval_loss": 1.6181610822677612, | |
| "eval_rouge1": 0.096, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.097, | |
| "eval_rougeLsum": 0.1, | |
| "eval_runtime": 171.5849, | |
| "eval_samples_per_second": 42.475, | |
| "eval_steps_per_second": 1.329, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.24951171875e-05, | |
| "loss": 1.5398, | |
| "step": 1537 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 16.47653677277717, | |
| "eval_loss": 1.6085278987884521, | |
| "eval_rouge1": 0.1394, | |
| "eval_rouge2": 0.0034, | |
| "eval_rougeL": 0.1401, | |
| "eval_rougeLsum": 0.1416, | |
| "eval_runtime": 171.9932, | |
| "eval_samples_per_second": 42.374, | |
| "eval_steps_per_second": 1.326, | |
| "step": 1537 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.9990234375e-05, | |
| "loss": 1.4142, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 16.273188803512625, | |
| "eval_loss": 1.6016370058059692, | |
| "eval_rouge1": 0.1132, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.1132, | |
| "eval_rougeLsum": 0.1098, | |
| "eval_runtime": 171.2054, | |
| "eval_samples_per_second": 42.569, | |
| "eval_steps_per_second": 1.332, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.7490234375e-05, | |
| "loss": 1.3102, | |
| "step": 2562 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 16.287733260153676, | |
| "eval_loss": 1.6240657567977905, | |
| "eval_rouge1": 0.2082, | |
| "eval_rouge2": 0.0034, | |
| "eval_rougeL": 0.2054, | |
| "eval_rougeLsum": 0.2061, | |
| "eval_runtime": 170.3025, | |
| "eval_samples_per_second": 42.794, | |
| "eval_steps_per_second": 1.339, | |
| "step": 2562 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.49853515625e-05, | |
| "loss": 1.2162, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_gen_len": 16.158068057080133, | |
| "eval_loss": 1.6281158924102783, | |
| "eval_rouge1": 0.1549, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.1549, | |
| "eval_rougeLsum": 0.1549, | |
| "eval_runtime": 171.3659, | |
| "eval_samples_per_second": 42.529, | |
| "eval_steps_per_second": 1.33, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.2485351562499996e-05, | |
| "loss": 1.1364, | |
| "step": 3587 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_gen_len": 15.992453347969265, | |
| "eval_loss": 1.6622037887573242, | |
| "eval_rouge1": 0.1583, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.1575, | |
| "eval_rougeLsum": 0.1589, | |
| "eval_runtime": 254.3332, | |
| "eval_samples_per_second": 28.655, | |
| "eval_steps_per_second": 0.896, | |
| "step": 3587 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.998046875e-05, | |
| "loss": 1.0649, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_gen_len": 16.509879253567508, | |
| "eval_loss": 1.6811630725860596, | |
| "eval_rouge1": 0.2033, | |
| "eval_rouge2": 0.0137, | |
| "eval_rougeL": 0.2012, | |
| "eval_rougeLsum": 0.2027, | |
| "eval_runtime": 173.1353, | |
| "eval_samples_per_second": 42.094, | |
| "eval_steps_per_second": 1.317, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 4100, | |
| "total_flos": 9.102827646479237e+17, | |
| "train_loss": 1.429130665848895, | |
| "train_runtime": 9768.8261, | |
| "train_samples_per_second": 134.272, | |
| "train_steps_per_second": 1.048 | |
| } | |
| ], | |
| "max_steps": 10240, | |
| "num_train_epochs": 20, | |
| "total_flos": 9.102827646479237e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |