{ "best_metric": 1.1622098684310913, "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_irq_1.5/checkpoint-5285", "epoch": 10.0, "eval_steps": 500, "global_step": 10570, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 0.9448983073234558, "learning_rate": 4.865067829457365e-05, "loss": 2.1843, "step": 1057 }, { "epoch": 1.0, "eval_bleu": 0.32059447298359617, "eval_loss": 1.250288486480713, "eval_rouge1": 0.4317992213146498, "eval_rouge2": 0.17666011159565037, "eval_rougeL": 0.42939906088943486, "eval_runtime": 57.4393, "eval_samples_per_second": 36.787, "eval_steps_per_second": 4.614, "step": 1057 }, { "epoch": 2.0, "grad_norm": 0.9019042253494263, "learning_rate": 4.609011627906977e-05, "loss": 0.6485, "step": 2114 }, { "epoch": 2.0, "eval_bleu": 0.33426327412457646, "eval_loss": 1.1708217859268188, "eval_rouge1": 0.467300193070487, "eval_rouge2": 0.20644532227230164, "eval_rougeL": 0.4650745009842402, "eval_runtime": 57.7779, "eval_samples_per_second": 36.571, "eval_steps_per_second": 4.587, "step": 2114 }, { "epoch": 3.0, "grad_norm": 0.9029839038848877, "learning_rate": 4.3529554263565894e-05, "loss": 0.5688, "step": 3171 }, { "epoch": 3.0, "eval_bleu": 0.34132680263228726, "eval_loss": 1.1971228122711182, "eval_rouge1": 0.48735678632841767, "eval_rouge2": 0.2243137926840742, "eval_rougeL": 0.4850815732515227, "eval_runtime": 57.4731, "eval_samples_per_second": 36.765, "eval_steps_per_second": 4.611, "step": 3171 }, { "epoch": 4.0, "grad_norm": 1.0017938613891602, "learning_rate": 4.096899224806201e-05, "loss": 0.5047, "step": 4228 }, { "epoch": 4.0, "eval_bleu": 0.35003996586498176, "eval_loss": 1.197810173034668, "eval_rouge1": 0.5054128473867857, "eval_rouge2": 0.2430653416823758, "eval_rougeL": 0.5030122857034254, "eval_runtime": 72.8161, "eval_samples_per_second": 29.018, "eval_steps_per_second": 3.639, "step": 4228 }, { "epoch": 5.0, "grad_norm": 1.0304298400878906, "learning_rate": 3.840843023255814e-05, "loss": 0.4482, "step": 5285 }, { "epoch": 5.0, "eval_bleu": 0.3502421699944588, "eval_loss": 1.1622098684310913, "eval_rouge1": 0.5096445443599783, "eval_rouge2": 0.24692932072035692, "eval_rougeL": 0.5075533735060334, "eval_runtime": 61.0964, "eval_samples_per_second": 34.585, "eval_steps_per_second": 4.337, "step": 5285 }, { "epoch": 6.0, "grad_norm": 1.1523360013961792, "learning_rate": 3.5847868217054265e-05, "loss": 0.3971, "step": 6342 }, { "epoch": 6.0, "eval_bleu": 0.3536202464127507, "eval_loss": 1.2058446407318115, "eval_rouge1": 0.5150055128188905, "eval_rouge2": 0.25352326254776286, "eval_rougeL": 0.5127629511333613, "eval_runtime": 57.6879, "eval_samples_per_second": 36.628, "eval_steps_per_second": 4.594, "step": 6342 }, { "epoch": 7.0, "grad_norm": 0.8643929958343506, "learning_rate": 3.328730620155039e-05, "loss": 0.3513, "step": 7399 }, { "epoch": 7.0, "eval_bleu": 0.3518598607895297, "eval_loss": 1.2158491611480713, "eval_rouge1": 0.5180154682612823, "eval_rouge2": 0.25664229580394476, "eval_rougeL": 0.5154649421568362, "eval_runtime": 121.1214, "eval_samples_per_second": 17.445, "eval_steps_per_second": 2.188, "step": 7399 }, { "epoch": 8.0, "grad_norm": 1.1156113147735596, "learning_rate": 3.0726744186046517e-05, "loss": 0.3105, "step": 8456 }, { "epoch": 8.0, "eval_bleu": 0.35342870570348306, "eval_loss": 1.2344255447387695, "eval_rouge1": 0.5225097884447725, "eval_rouge2": 0.2629872301742399, "eval_rougeL": 0.5202162260924711, "eval_runtime": 57.6564, "eval_samples_per_second": 36.648, "eval_steps_per_second": 4.596, "step": 8456 }, { "epoch": 9.0, "grad_norm": 1.2186470031738281, "learning_rate": 2.816618217054264e-05, "loss": 0.2743, "step": 9513 }, { "epoch": 9.0, "eval_bleu": 0.35543765162196594, "eval_loss": 1.2988064289093018, "eval_rouge1": 0.5277394207696515, "eval_rouge2": 0.26929133120484805, "eval_rougeL": 0.5249418411792439, "eval_runtime": 57.8354, "eval_samples_per_second": 36.535, "eval_steps_per_second": 4.582, "step": 9513 }, { "epoch": 10.0, "grad_norm": 1.028747797012329, "learning_rate": 2.560562015503876e-05, "loss": 0.2426, "step": 10570 }, { "epoch": 10.0, "eval_bleu": 0.3550745821213054, "eval_loss": 1.3222092390060425, "eval_rouge1": 0.5235234737619403, "eval_rouge2": 0.26498166415837476, "eval_rougeL": 0.5206776898832342, "eval_runtime": 57.289, "eval_samples_per_second": 36.883, "eval_steps_per_second": 4.626, "step": 10570 }, { "epoch": 10.0, "step": 10570, "total_flos": 9.5780710219776e+16, "train_loss": 0.5930478791640181, "train_runtime": 28339.5203, "train_samples_per_second": 5.965, "train_steps_per_second": 0.746 } ], "logging_steps": 500, "max_steps": 21140, "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": 9.5780710219776e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }