| { | |
| "best_metric": 0.6245766282081604, | |
| "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_dj/checkpoint-8037", | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 21432, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.1291303634643555, | |
| "learning_rate": 4.7947437829691034e-05, | |
| "loss": 1.2336, | |
| "step": 2679 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.3526371485696729, | |
| "eval_loss": 0.7061845660209656, | |
| "eval_rouge1": 0.5198447201202445, | |
| "eval_rouge2": 0.25470674188424197, | |
| "eval_rougeL": 0.516986428368343, | |
| "eval_runtime": 17.6993, | |
| "eval_samples_per_second": 303.967, | |
| "eval_steps_per_second": 38.024, | |
| "step": 2679 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.4575163125991821, | |
| "learning_rate": 4.542388847023361e-05, | |
| "loss": 0.634, | |
| "step": 5358 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.37564617349393215, | |
| "eval_loss": 0.6422649025917053, | |
| "eval_rouge1": 0.5739420026060218, | |
| "eval_rouge2": 0.3114152854574803, | |
| "eval_rougeL": 0.571389088656927, | |
| "eval_runtime": 17.5523, | |
| "eval_samples_per_second": 306.513, | |
| "eval_steps_per_second": 38.343, | |
| "step": 5358 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.237191915512085, | |
| "learning_rate": 4.290033911077619e-05, | |
| "loss": 0.5299, | |
| "step": 8037 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.3877191285680082, | |
| "eval_loss": 0.6245766282081604, | |
| "eval_rouge1": 0.5957940125562868, | |
| "eval_rouge2": 0.3370143004573494, | |
| "eval_rougeL": 0.5934967085426222, | |
| "eval_runtime": 17.5587, | |
| "eval_samples_per_second": 306.401, | |
| "eval_steps_per_second": 38.329, | |
| "step": 8037 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.5628466606140137, | |
| "learning_rate": 4.0376789751318766e-05, | |
| "loss": 0.4492, | |
| "step": 10716 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.39048560865149107, | |
| "eval_loss": 0.6246171593666077, | |
| "eval_rouge1": 0.6081397458304423, | |
| "eval_rouge2": 0.3525706786064172, | |
| "eval_rougeL": 0.6056655214414464, | |
| "eval_runtime": 17.6128, | |
| "eval_samples_per_second": 305.459, | |
| "eval_steps_per_second": 38.211, | |
| "step": 10716 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.8470176458358765, | |
| "learning_rate": 3.785324039186134e-05, | |
| "loss": 0.3829, | |
| "step": 13395 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.3963490407851369, | |
| "eval_loss": 0.6300457715988159, | |
| "eval_rouge1": 0.6145424292978614, | |
| "eval_rouge2": 0.3620910031723723, | |
| "eval_rougeL": 0.6124537005851034, | |
| "eval_runtime": 17.4259, | |
| "eval_samples_per_second": 308.735, | |
| "eval_steps_per_second": 38.621, | |
| "step": 13395 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.5765687227249146, | |
| "learning_rate": 3.532969103240392e-05, | |
| "loss": 0.328, | |
| "step": 16074 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.3960700684284105, | |
| "eval_loss": 0.6383510231971741, | |
| "eval_rouge1": 0.6213431858539703, | |
| "eval_rouge2": 0.36997070576967905, | |
| "eval_rougeL": 0.6194073222098655, | |
| "eval_runtime": 17.7673, | |
| "eval_samples_per_second": 302.803, | |
| "eval_steps_per_second": 37.879, | |
| "step": 16074 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 1.960555076599121, | |
| "learning_rate": 3.28061416729465e-05, | |
| "loss": 0.2832, | |
| "step": 18753 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.3998604582987598, | |
| "eval_loss": 0.6490957736968994, | |
| "eval_rouge1": 0.623202150680765, | |
| "eval_rouge2": 0.3741196322885935, | |
| "eval_rougeL": 0.6209434708040459, | |
| "eval_runtime": 17.3486, | |
| "eval_samples_per_second": 310.112, | |
| "eval_steps_per_second": 38.793, | |
| "step": 18753 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.4162492752075195, | |
| "learning_rate": 3.028259231348907e-05, | |
| "loss": 0.2453, | |
| "step": 21432 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.3967586062831279, | |
| "eval_loss": 0.660749614238739, | |
| "eval_rouge1": 0.6231513583077875, | |
| "eval_rouge2": 0.37461482860421447, | |
| "eval_rougeL": 0.6211860899632824, | |
| "eval_runtime": 17.8295, | |
| "eval_samples_per_second": 301.747, | |
| "eval_steps_per_second": 37.746, | |
| "step": 21432 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 21432, | |
| "total_flos": 1.1198453907456e+16, | |
| "train_loss": 0.5107668242644979, | |
| "train_runtime": 1728.8387, | |
| "train_samples_per_second": 247.901, | |
| "train_steps_per_second": 30.992 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 53580, | |
| "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": 1.1198453907456e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |