| { | |
| "best_metric": 1.0816909074783325, | |
| "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_irq/checkpoint-2114", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 7399, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.3965729475021362, | |
| "learning_rate": 4.865067829457365e-05, | |
| "loss": 1.7995, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.3157163520866108, | |
| "eval_loss": 1.1331889629364014, | |
| "eval_rouge1": 0.45516049357610144, | |
| "eval_rouge2": 0.2017132883532014, | |
| "eval_rougeL": 0.453144508008762, | |
| "eval_runtime": 20.354, | |
| "eval_samples_per_second": 103.812, | |
| "eval_steps_per_second": 13.02, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.2999993562698364, | |
| "learning_rate": 4.609011627906977e-05, | |
| "loss": 0.5906, | |
| "step": 2114 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.34996698643265867, | |
| "eval_loss": 1.0816909074783325, | |
| "eval_rouge1": 0.5070888923629823, | |
| "eval_rouge2": 0.24860353236577704, | |
| "eval_rougeL": 0.5048066808619132, | |
| "eval_runtime": 18.5352, | |
| "eval_samples_per_second": 113.999, | |
| "eval_steps_per_second": 14.297, | |
| "step": 2114 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.494644284248352, | |
| "learning_rate": 4.3529554263565894e-05, | |
| "loss": 0.484, | |
| "step": 3171 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.3592334262176334, | |
| "eval_loss": 1.1038055419921875, | |
| "eval_rouge1": 0.5329660042734197, | |
| "eval_rouge2": 0.2737288088550716, | |
| "eval_rougeL": 0.530301732660456, | |
| "eval_runtime": 11.0163, | |
| "eval_samples_per_second": 191.807, | |
| "eval_steps_per_second": 24.055, | |
| "step": 3171 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 2.169060230255127, | |
| "learning_rate": 4.096899224806201e-05, | |
| "loss": 0.4017, | |
| "step": 4228 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.3664876357280857, | |
| "eval_loss": 1.1117204427719116, | |
| "eval_rouge1": 0.5470701344699284, | |
| "eval_rouge2": 0.29154846104100973, | |
| "eval_rougeL": 0.5448816975696349, | |
| "eval_runtime": 11.4837, | |
| "eval_samples_per_second": 184.001, | |
| "eval_steps_per_second": 23.076, | |
| "step": 4228 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.5656139850616455, | |
| "learning_rate": 3.840843023255814e-05, | |
| "loss": 0.3357, | |
| "step": 5285 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.36951226807058296, | |
| "eval_loss": 1.1360507011413574, | |
| "eval_rouge1": 0.5552416771197572, | |
| "eval_rouge2": 0.300977455987009, | |
| "eval_rougeL": 0.5533455418855034, | |
| "eval_runtime": 7.2292, | |
| "eval_samples_per_second": 292.287, | |
| "eval_steps_per_second": 36.657, | |
| "step": 5285 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.9493229389190674, | |
| "learning_rate": 3.5847868217054265e-05, | |
| "loss": 0.2832, | |
| "step": 6342 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.37209002173126987, | |
| "eval_loss": 1.1256883144378662, | |
| "eval_rouge1": 0.5606510219414631, | |
| "eval_rouge2": 0.3089222128154705, | |
| "eval_rougeL": 0.5584217258440263, | |
| "eval_runtime": 7.0098, | |
| "eval_samples_per_second": 301.433, | |
| "eval_steps_per_second": 37.804, | |
| "step": 6342 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 1.3939344882965088, | |
| "learning_rate": 3.328730620155039e-05, | |
| "loss": 0.2404, | |
| "step": 7399 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.37399333863753975, | |
| "eval_loss": 1.1580852270126343, | |
| "eval_rouge1": 0.5622192023319419, | |
| "eval_rouge2": 0.3102334124697639, | |
| "eval_rougeL": 0.5600347361241877, | |
| "eval_runtime": 7.2059, | |
| "eval_samples_per_second": 293.233, | |
| "eval_steps_per_second": 36.776, | |
| "step": 7399 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 7399, | |
| "total_flos": 3864770445312000.0, | |
| "train_loss": 0.5907337587255773, | |
| "train_runtime": 1774.4968, | |
| "train_samples_per_second": 95.261, | |
| "train_steps_per_second": 11.913 | |
| } | |
| ], | |
| "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": 3864770445312000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |