| { | |
| "best_metric": 0.8298296928405762, | |
| "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_eg/checkpoint-21315", | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 56840, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.2983179092407227, | |
| "learning_rate": 4.766772598870057e-05, | |
| "loss": 1.1362, | |
| "step": 7105 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.3024315492316285, | |
| "eval_loss": 0.9122783541679382, | |
| "eval_rouge1": 0.5275815926361394, | |
| "eval_rouge2": 0.250835305590573, | |
| "eval_rougeL": 0.5227642919859343, | |
| "eval_runtime": 82.2039, | |
| "eval_samples_per_second": 172.851, | |
| "eval_steps_per_second": 21.617, | |
| "step": 7105 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.6412582397460938, | |
| "learning_rate": 4.515889830508475e-05, | |
| "loss": 0.7501, | |
| "step": 14210 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.3299343390399215, | |
| "eval_loss": 0.8436459302902222, | |
| "eval_rouge1": 0.5753620498690527, | |
| "eval_rouge2": 0.30552900678559713, | |
| "eval_rougeL": 0.5712795722916149, | |
| "eval_runtime": 47.3241, | |
| "eval_samples_per_second": 300.248, | |
| "eval_steps_per_second": 37.55, | |
| "step": 14210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.4929105043411255, | |
| "learning_rate": 4.265007062146893e-05, | |
| "loss": 0.6462, | |
| "step": 21315 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.3389516198368023, | |
| "eval_loss": 0.8298296928405762, | |
| "eval_rouge1": 0.5961824107324037, | |
| "eval_rouge2": 0.32984558195042607, | |
| "eval_rougeL": 0.5921451862516953, | |
| "eval_runtime": 46.7775, | |
| "eval_samples_per_second": 303.757, | |
| "eval_steps_per_second": 37.988, | |
| "step": 21315 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 2.472024440765381, | |
| "learning_rate": 4.014124293785311e-05, | |
| "loss": 0.5705, | |
| "step": 28420 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.3443865327631572, | |
| "eval_loss": 0.8327584862709045, | |
| "eval_rouge1": 0.6048121716287991, | |
| "eval_rouge2": 0.3411757857050619, | |
| "eval_rougeL": 0.6010600637633374, | |
| "eval_runtime": 51.9902, | |
| "eval_samples_per_second": 273.301, | |
| "eval_steps_per_second": 34.18, | |
| "step": 28420 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.5785757303237915, | |
| "learning_rate": 3.763241525423729e-05, | |
| "loss": 0.5087, | |
| "step": 35525 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.3480087983574886, | |
| "eval_loss": 0.8406437635421753, | |
| "eval_rouge1": 0.6133106901142944, | |
| "eval_rouge2": 0.3512185978691529, | |
| "eval_rougeL": 0.6095993795603691, | |
| "eval_runtime": 46.8243, | |
| "eval_samples_per_second": 303.453, | |
| "eval_steps_per_second": 37.95, | |
| "step": 35525 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.7464922666549683, | |
| "learning_rate": 3.5123587570621466e-05, | |
| "loss": 0.4559, | |
| "step": 42630 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.34779219505501374, | |
| "eval_loss": 0.8647022843360901, | |
| "eval_rouge1": 0.6132791748034587, | |
| "eval_rouge2": 0.35198863487088, | |
| "eval_rougeL": 0.6093736659279629, | |
| "eval_runtime": 46.987, | |
| "eval_samples_per_second": 302.403, | |
| "eval_steps_per_second": 37.819, | |
| "step": 42630 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 2.2738301753997803, | |
| "learning_rate": 3.261475988700565e-05, | |
| "loss": 0.4104, | |
| "step": 49735 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.3484641332073553, | |
| "eval_loss": 0.8769952058792114, | |
| "eval_rouge1": 0.6147660525828296, | |
| "eval_rouge2": 0.3532593327836824, | |
| "eval_rougeL": 0.6107018352641345, | |
| "eval_runtime": 47.1718, | |
| "eval_samples_per_second": 301.218, | |
| "eval_steps_per_second": 37.671, | |
| "step": 49735 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.9538367986679077, | |
| "learning_rate": 3.010593220338983e-05, | |
| "loss": 0.3708, | |
| "step": 56840 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.3478035270510471, | |
| "eval_loss": 0.9003333449363708, | |
| "eval_rouge1": 0.6165900788913368, | |
| "eval_rouge2": 0.3548552782268418, | |
| "eval_rougeL": 0.6124632709173936, | |
| "eval_runtime": 47.008, | |
| "eval_samples_per_second": 302.268, | |
| "eval_steps_per_second": 37.802, | |
| "step": 56840 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 56840, | |
| "total_flos": 2.9701587861504e+16, | |
| "train_loss": 0.6060978588128408, | |
| "train_runtime": 4864.2589, | |
| "train_samples_per_second": 233.688, | |
| "train_steps_per_second": 29.213 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 142100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.9701587861504e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |