| { | |
| "best_metric": 0.4183219075202942, | |
| "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_gulf/checkpoint-3352", | |
| "epoch": 14.0, | |
| "eval_steps": 500, | |
| "global_step": 11732, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.1270569562911987, | |
| "learning_rate": 4.8960639606396064e-05, | |
| "loss": 1.9575, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.17899151773967856, | |
| "eval_loss": 0.4805418848991394, | |
| "eval_rouge1": 0.5300700267573193, | |
| "eval_rouge2": 0.25846419107204655, | |
| "eval_rougeL": 0.5287371290578213, | |
| "eval_runtime": 26.4765, | |
| "eval_samples_per_second": 63.264, | |
| "eval_steps_per_second": 7.932, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.8918192982673645, | |
| "learning_rate": 4.6383763837638376e-05, | |
| "loss": 0.422, | |
| "step": 1676 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.2111987576275603, | |
| "eval_loss": 0.4326799809932709, | |
| "eval_rouge1": 0.5789346222407353, | |
| "eval_rouge2": 0.3115433580134526, | |
| "eval_rougeL": 0.5777838651600141, | |
| "eval_runtime": 36.5489, | |
| "eval_samples_per_second": 45.829, | |
| "eval_steps_per_second": 5.746, | |
| "step": 1676 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.1533405780792236, | |
| "learning_rate": 4.380688806888069e-05, | |
| "loss": 0.331, | |
| "step": 2514 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.22887638181669745, | |
| "eval_loss": 0.41845184564590454, | |
| "eval_rouge1": 0.6066983915980586, | |
| "eval_rouge2": 0.34626660980048474, | |
| "eval_rougeL": 0.6055721645591957, | |
| "eval_runtime": 25.3383, | |
| "eval_samples_per_second": 66.106, | |
| "eval_steps_per_second": 8.288, | |
| "step": 2514 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.3615330457687378, | |
| "learning_rate": 4.123001230012301e-05, | |
| "loss": 0.2638, | |
| "step": 3352 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.23736106874390867, | |
| "eval_loss": 0.4183219075202942, | |
| "eval_rouge1": 0.6213217050496613, | |
| "eval_rouge2": 0.3629928034660268, | |
| "eval_rougeL": 0.6194945230812778, | |
| "eval_runtime": 16.1799, | |
| "eval_samples_per_second": 103.524, | |
| "eval_steps_per_second": 12.979, | |
| "step": 3352 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.29606294631958, | |
| "learning_rate": 3.865313653136531e-05, | |
| "loss": 0.2131, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.24225546513762886, | |
| "eval_loss": 0.42484816908836365, | |
| "eval_rouge1": 0.6280394265150125, | |
| "eval_rouge2": 0.3718667234148674, | |
| "eval_rougeL": 0.6264526155291095, | |
| "eval_runtime": 25.4283, | |
| "eval_samples_per_second": 65.872, | |
| "eval_steps_per_second": 8.259, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.9162726402282715, | |
| "learning_rate": 3.6076260762607624e-05, | |
| "loss": 0.1756, | |
| "step": 5028 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.25110200021461276, | |
| "eval_loss": 0.4322951138019562, | |
| "eval_rouge1": 0.6329099900871186, | |
| "eval_rouge2": 0.3818443278310246, | |
| "eval_rougeL": 0.6311516008372622, | |
| "eval_runtime": 13.3457, | |
| "eval_samples_per_second": 125.508, | |
| "eval_steps_per_second": 15.735, | |
| "step": 5028 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 1.2213388681411743, | |
| "learning_rate": 3.349938499384994e-05, | |
| "loss": 0.148, | |
| "step": 5866 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.24584223218153298, | |
| "eval_loss": 0.4369480013847351, | |
| "eval_rouge1": 0.6346640667719812, | |
| "eval_rouge2": 0.3890963668887653, | |
| "eval_rougeL": 0.6326978702709232, | |
| "eval_runtime": 6.3313, | |
| "eval_samples_per_second": 264.559, | |
| "eval_steps_per_second": 33.169, | |
| "step": 5866 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.774276852607727, | |
| "learning_rate": 3.092250922509225e-05, | |
| "loss": 0.1285, | |
| "step": 6704 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.2499016538097514, | |
| "eval_loss": 0.4447513520717621, | |
| "eval_rouge1": 0.6380175687280993, | |
| "eval_rouge2": 0.38845767776215345, | |
| "eval_rougeL": 0.6368182514454324, | |
| "eval_runtime": 5.4681, | |
| "eval_samples_per_second": 306.322, | |
| "eval_steps_per_second": 38.405, | |
| "step": 6704 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.779574990272522, | |
| "learning_rate": 2.8345633456334564e-05, | |
| "loss": 0.1152, | |
| "step": 7542 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 0.2538776211394201, | |
| "eval_loss": 0.45251065492630005, | |
| "eval_rouge1": 0.6407467681145795, | |
| "eval_rouge2": 0.3976657405838769, | |
| "eval_rougeL": 0.6393461853572592, | |
| "eval_runtime": 6.3546, | |
| "eval_samples_per_second": 263.59, | |
| "eval_steps_per_second": 33.047, | |
| "step": 7542 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.159719705581665, | |
| "learning_rate": 2.5768757687576876e-05, | |
| "loss": 0.105, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 0.2555335148067654, | |
| "eval_loss": 0.45896273851394653, | |
| "eval_rouge1": 0.6440840106866277, | |
| "eval_rouge2": 0.3998364161836553, | |
| "eval_rougeL": 0.6425824451349154, | |
| "eval_runtime": 5.4849, | |
| "eval_samples_per_second": 305.385, | |
| "eval_steps_per_second": 38.287, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 0.923600435256958, | |
| "learning_rate": 2.3191881918819188e-05, | |
| "loss": 0.0982, | |
| "step": 9218 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 0.25802091175426106, | |
| "eval_loss": 0.46457362174987793, | |
| "eval_rouge1": 0.6455262594531862, | |
| "eval_rouge2": 0.40187791063551404, | |
| "eval_rougeL": 0.6445205006389869, | |
| "eval_runtime": 6.4432, | |
| "eval_samples_per_second": 259.965, | |
| "eval_steps_per_second": 32.593, | |
| "step": 9218 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.9120431542396545, | |
| "learning_rate": 2.0615006150061504e-05, | |
| "loss": 0.0936, | |
| "step": 10056 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 0.257202175451904, | |
| "eval_loss": 0.470233678817749, | |
| "eval_rouge1": 0.6456936789584837, | |
| "eval_rouge2": 0.4045772651416589, | |
| "eval_rougeL": 0.6445820832270409, | |
| "eval_runtime": 13.7399, | |
| "eval_samples_per_second": 121.907, | |
| "eval_steps_per_second": 15.284, | |
| "step": 10056 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 0.6435267329216003, | |
| "learning_rate": 1.8038130381303812e-05, | |
| "loss": 0.0899, | |
| "step": 10894 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 0.25765634141938715, | |
| "eval_loss": 0.47367072105407715, | |
| "eval_rouge1": 0.6488279078084271, | |
| "eval_rouge2": 0.40534740561340493, | |
| "eval_rougeL": 0.6478436883847489, | |
| "eval_runtime": 17.2761, | |
| "eval_samples_per_second": 96.955, | |
| "eval_steps_per_second": 12.156, | |
| "step": 10894 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.7371336221694946, | |
| "learning_rate": 1.5461254612546124e-05, | |
| "loss": 0.0871, | |
| "step": 11732 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 0.2606034683461693, | |
| "eval_loss": 0.4779162108898163, | |
| "eval_rouge1": 0.6491650390141908, | |
| "eval_rouge2": 0.40618585329089035, | |
| "eval_rougeL": 0.6482221321240169, | |
| "eval_runtime": 5.371, | |
| "eval_samples_per_second": 311.859, | |
| "eval_steps_per_second": 39.099, | |
| "step": 11732 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "step": 11732, | |
| "total_flos": 6127298150400000.0, | |
| "train_loss": 0.03383859399638808, | |
| "train_runtime": 1080.9024, | |
| "train_samples_per_second": 123.97, | |
| "train_steps_per_second": 15.506 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 16760, | |
| "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": 6127298150400000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |