{'date': '2023-12-26 16:46:24.879553', 'elapsed': '0:32:28.115082', 'result': TrainOutput(global_step=250, training_loss=2.1802197647094728, metrics={'train_runtime': 1946.1446, 'train_samples_per_second': 0.514, 'train_steps_per_second': 0.128, 'train_loss': 2.1802197647094728, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=1000, N_SAMPLES_EVAL=250, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-26 19:34:53.379736', 'elapsed': '0:23:40.139495', 'result': TrainOutput(global_step=125, training_loss=2.3158225402832033, metrics={'train_runtime': 709.7197, 'train_samples_per_second': 0.705, 'train_steps_per_second': 0.176, 'train_loss': 2.3158225402832033, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-2', DATASET='ortega', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-26 20:17:10.548743', 'elapsed': '0:32:22.207478', 'result': TrainOutput(global_step=125, training_loss=2.1481434478759764, metrics={'train_runtime': 971.1875, 'train_samples_per_second': 0.515, 'train_steps_per_second': 0.129, 'train_loss': 2.1481434478759764, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-4', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-26 21:44:05.148185', 'elapsed': '1:09:41.207946', 'result': TrainOutput(global_step=250, training_loss=2.474770034790039, metrics={'train_runtime': 2094.6225, 'train_samples_per_second': 0.477, 'train_steps_per_second': 0.119, 'train_loss': 2.474770034790039, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-6', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=1000, N_SAMPLES_EVAL=250, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-26 21:51:04.553167', 'elapsed': '0:04:56.879946', 'result': TrainOutput(global_step=28, training_loss=1.7862514427730016, metrics={'train_runtime': 150.8639, 'train_samples_per_second': 0.729, 'train_steps_per_second': 0.186, 'train_loss': 1.7862514427730016, 'epoch': 2.0}), 'config': 'soft-ultrasoft', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-8', DATASET='eva_memory', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft', N_SAMPLES_TRAIN=55, N_SAMPLES_EVAL=13, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-26 22:23:16.482678', 'elapsed': '0:30:21.803988', 'result': TrainOutput(global_step=125, training_loss=2.205165969848633, metrics={'train_runtime': 910.7095, 'train_samples_per_second': 0.549, 'train_steps_per_second': 0.137, 'train_loss': 2.205165969848633, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-10', DATASET='novels-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 00:38:41.051536', 'elapsed': '1:07:06.093304', 'result': TrainOutput(global_step=250, training_loss=2.1788258056640624, metrics={'train_runtime': 2013.4984, 'train_samples_per_second': 0.497, 'train_steps_per_second': 0.124, 'train_loss': 2.1788258056640624, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-12', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=1000, N_SAMPLES_EVAL=250, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 01:18:50.437038', 'elapsed': '0:38:21.591849', 'result': TrainOutput(global_step=125, training_loss=2.152986862182617, metrics={'train_runtime': 1151.7468, 'train_samples_per_second': 0.434, 'train_steps_per_second': 0.109, 'train_loss': 2.152986862182617, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-14', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=65, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 01:25:45.075115', 'elapsed': '0:05:07.462787', 'result': TrainOutput(global_step=28, training_loss=0.9334086860929217, metrics={'train_runtime': 152.446, 'train_samples_per_second': 0.722, 'train_steps_per_second': 0.184, 'train_loss': 0.9334086860929217, 'epoch': 2.0}), 'config': 'soft-soft', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-16', DATASET='eva_memory', LORA_CONFIG='soft', TRAINING_CONFIG='soft', N_SAMPLES_TRAIN=55, N_SAMPLES_EVAL=13, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=0.00025, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 02:37:50.654457', 'elapsed': '1:10:16.101265', 'result': TrainOutput(global_step=250, training_loss=1.9339292373657226, metrics={'train_runtime': 2113.0599, 'train_samples_per_second': 0.473, 'train_steps_per_second': 0.118, 'train_loss': 1.9339292373657226, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-18', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 03:10:54.625704', 'elapsed': '0:31:30.108503', 'result': TrainOutput(global_step=125, training_loss=2.2331400146484377, metrics={'train_runtime': 944.4705, 'train_samples_per_second': 0.529, 'train_steps_per_second': 0.132, 'train_loss': 2.2331400146484377, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-20', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 03:47:20.518431', 'elapsed': '0:34:51.184005', 'result': TrainOutput(global_step=125, training_loss=2.529209671020508, metrics={'train_runtime': 1044.3901, 'train_samples_per_second': 0.479, 'train_steps_per_second': 0.12, 'train_loss': 2.529209671020508, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-22', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 04:27:09.695135', 'elapsed': '0:38:15.883128', 'result': TrainOutput(global_step=125, training_loss=2.149136177062988, metrics={'train_runtime': 1149.0996, 'train_samples_per_second': 0.435, 'train_steps_per_second': 0.109, 'train_loss': 2.149136177062988, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-24', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=65, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 09:57:53.434022', 'elapsed': '2:41:10.151135', 'result': TrainOutput(global_step=600, training_loss=1.9166389083862305, metrics={'train_runtime': 4851.8154, 'train_samples_per_second': 0.495, 'train_steps_per_second': 0.124, 'train_loss': 1.9166389083862305, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-26', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=1200, N_SAMPLES_EVAL=300, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 14:20:49.614525', 'elapsed': '0:58:40.384430', 'result': TrainOutput(global_step=250, training_loss=2.4223380126953127, metrics={'train_runtime': 1765.238, 'train_samples_per_second': 0.566, 'train_steps_per_second': 0.142, 'train_loss': 2.4223380126953127, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-28', DATASET='poesia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 15:22:53.239002', 'elapsed': '1:00:22.986497', 'result': TrainOutput(global_step=250, training_loss=2.3288601150512696, metrics={'train_runtime': 1818.8238, 'train_samples_per_second': 0.55, 'train_steps_per_second': 0.137, 'train_loss': 2.3288601150512696, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-30', DATASET='poesia2-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 15:59:39.032963', 'elapsed': '0:34:33.698399', 'result': TrainOutput(global_step=125, training_loss=2.528319564819336, metrics={'train_runtime': 1037.1024, 'train_samples_per_second': 0.482, 'train_steps_per_second': 0.121, 'train_loss': 2.528319564819336, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-32', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 16:49:48.235638', 'elapsed': '0:48:25.394378', 'result': TrainOutput(global_step=200, training_loss=2.1481187629699705, metrics={'train_runtime': 1455.4036, 'train_samples_per_second': 0.55, 'train_steps_per_second': 0.137, 'train_loss': 2.1481187629699705, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-34', DATASET='novels-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=800, N_SAMPLES_EVAL=200, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 17:47:03.506459', 'elapsed': '0:55:33.644222', 'result': TrainOutput(global_step=200, training_loss=2.1020443344116213, metrics={'train_runtime': 1667.2706, 'train_samples_per_second': 0.48, 'train_steps_per_second': 0.12, 'train_loss': 2.1020443344116213, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-36', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=800, N_SAMPLES_EVAL=200, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 18:22:31.597100', 'elapsed': '0:33:27.775479', 'result': TrainOutput(global_step=125, training_loss=2.2330916061401367, metrics={'train_runtime': 1004.008, 'train_samples_per_second': 0.498, 'train_steps_per_second': 0.125, 'train_loss': 2.2330916061401367, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-38', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 19:02:25.376896', 'elapsed': '0:38:16.595975', 'result': TrainOutput(global_step=125, training_loss=2.1526595001220703, metrics={'train_runtime': 1149.7064, 'train_samples_per_second': 0.435, 'train_steps_per_second': 0.109, 'train_loss': 2.1526595001220703, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-40', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=65, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-27 23:37:07.958414', 'elapsed': '0:23:46.518295', 'result': TrainOutput(global_step=125, training_loss=2.6810610275268556, metrics={'train_runtime': 712.8759, 'train_samples_per_second': 0.701, 'train_steps_per_second': 0.175, 'train_loss': 2.6810610275268556, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-42', DATASET='poesia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 00:10:55.648166', 'elapsed': '0:31:59.006185', 'result': TrainOutput(global_step=125, training_loss=2.5974924926757814, metrics={'train_runtime': 958.7126, 'train_samples_per_second': 0.522, 'train_steps_per_second': 0.13, 'train_loss': 2.5974924926757814, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-44', DATASET='poesia2-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 00:43:49.075325', 'elapsed': '0:31:21.592671', 'result': TrainOutput(global_step=125, training_loss=2.5334876403808595, metrics={'train_runtime': 941.381, 'train_samples_per_second': 0.531, 'train_steps_per_second': 0.133, 'train_loss': 2.5334876403808595, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-46', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 02:32:56.998770', 'elapsed': '1:47:35.939094', 'result': TrainOutput(global_step=400, training_loss=1.9089637327194213, metrics={'train_runtime': 3240.2609, 'train_samples_per_second': 0.494, 'train_steps_per_second': 0.123, 'train_loss': 1.9089637327194213, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-48', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=800, N_SAMPLES_EVAL=200, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 03:41:35.098836', 'elapsed': '1:07:07.173824', 'result': TrainOutput(global_step=250, training_loss=1.9852544631958007, metrics={'train_runtime': 2018.9219, 'train_samples_per_second': 0.495, 'train_steps_per_second': 0.124, 'train_loss': 1.9852544631958007, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-50', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=125, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 10:22:47.829294', 'elapsed': '0:38:14.571546', 'result': TrainOutput(global_step=125, training_loss=2.1425003967285154, metrics={'train_runtime': 1146.6342, 'train_samples_per_second': 0.436, 'train_steps_per_second': 0.109, 'train_loss': 2.1425003967285154, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-52', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=500, N_SAMPLES_EVAL=65, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 19:07:09.235072', 'elapsed': '0:11:53.938143', 'result': TrainOutput(global_step=63, training_loss=2.73664429074242, metrics={'train_runtime': 357.8052, 'train_samples_per_second': 0.699, 'train_steps_per_second': 0.176, 'train_loss': 2.73664429074242, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-54', DATASET='poesia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 19:24:30.032635', 'elapsed': '0:15:15.974954', 'result': TrainOutput(global_step=63, training_loss=2.274317907908606, metrics={'train_runtime': 456.4455, 'train_samples_per_second': 0.548, 'train_steps_per_second': 0.138, 'train_loss': 2.274317907908606, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-56', DATASET='novels-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 19:41:46.993115', 'elapsed': '0:15:15.382698', 'result': TrainOutput(global_step=63, training_loss=2.6192133615887356, metrics={'train_runtime': 457.9032, 'train_samples_per_second': 0.546, 'train_steps_per_second': 0.138, 'train_loss': 2.6192133615887356, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-58', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 22:17:57.285725', 'elapsed': '0:30:16.810659', 'result': TrainOutput(global_step=126, training_loss=2.0013014929635182, metrics={'train_runtime': 912.3694, 'train_samples_per_second': 0.548, 'train_steps_per_second': 0.138, 'train_loss': 2.0013014929635182, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-60', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 22:53:28.271572', 'elapsed': '0:33:46.606030', 'result': TrainOutput(global_step=126, training_loss=2.0920567588200645, metrics={'train_runtime': 1012.9334, 'train_samples_per_second': 0.494, 'train_steps_per_second': 0.124, 'train_loss': 2.0920567588200645, 'epoch': 2.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-62', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=2.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-28 23:14:30.238023', 'elapsed': '0:18:58.625462', 'result': TrainOutput(global_step=63, training_loss=2.2614496094839915, metrics={'train_runtime': 569.4004, 'train_samples_per_second': 0.439, 'train_steps_per_second': 0.111, 'train_loss': 2.2614496094839915, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-64', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-29 11:27:52.422711', 'elapsed': '0:20:27.009402', 'result': TrainOutput(global_step=63, training_loss=0.8857607614426386, metrics={'train_runtime': 611.2226, 'train_samples_per_second': 0.409, 'train_steps_per_second': 0.103, 'train_loss': 0.8857607614426386, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-66', DATASET='evol-instruct-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-29 11:45:55.818885', 'elapsed': '0:15:41.421223', 'result': TrainOutput(global_step=63, training_loss=2.586571988605318, metrics={'train_runtime': 468.4738, 'train_samples_per_second': 0.534, 'train_steps_per_second': 0.134, 'train_loss': 2.586571988605318, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-68', DATASET='clasicos-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-29 12:03:09.141156', 'elapsed': '0:15:07.377866', 'result': TrainOutput(global_step=63, training_loss=2.205605355520097, metrics={'train_runtime': 451.7584, 'train_samples_per_second': 0.553, 'train_steps_per_second': 0.139, 'train_loss': 2.205605355520097, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-70', DATASET='filosofia-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-29 12:15:49.725351', 'elapsed': '0:10:51.094495', 'result': TrainOutput(global_step=63, training_loss=2.405070910378108, metrics={'train_runtime': 325.2157, 'train_samples_per_second': 0.769, 'train_steps_per_second': 0.194, 'train_loss': 2.405070910378108, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-72', DATASET='ortega', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-29 12:33:54.589552', 'elapsed': '0:16:22.761513', 'result': TrainOutput(global_step=63, training_loss=2.308999606541225, metrics={'train_runtime': 490.5357, 'train_samples_per_second': 0.51, 'train_steps_per_second': 0.128, 'train_loss': 2.308999606541225, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-74', DATASET='novela-es', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"} {'date': '2023-12-29 12:54:46.289934', 'elapsed': '0:19:05.067157', 'result': TrainOutput(global_step=63, training_loss=2.2411288155449762, metrics={'train_runtime': 572.3977, 'train_samples_per_second': 0.437, 'train_steps_per_second': 0.11, 'train_loss': 2.2411288155449762, 'epoch': 1.0}), 'config': 'soft-ultrasoft2', 'cfg': "TrainingData(MODEL='CatMacaroni-Slerp-7b-trained-76', DATASET='ciencia_ficcion', LORA_CONFIG='soft', TRAINING_CONFIG='ultrasoft2', N_SAMPLES_TRAIN=250, N_SAMPLES_EVAL=62, LORA_R=32, LORA_ALPHA=16, LORA_DROPOUT=0.1, EPOCHS=1.0, LEARNING_RATE=2.5e-05, BATCH_SIZE=4, WARMUP_STEPS=10, DECAY=0, OPTIMIZER='adamw_bnb_8bit', DATASET_COLUMN_TEXT='text', MAX_LENGTH_CHARS=1280)"}