| 05/12/2026 04:15:00 - INFO - accelerate.utils.modeling - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). |
| 05/12/2026 04:15:34 - INFO - root - number of sec samples before upsampling: 1806 |
| 05/12/2026 04:15:34 - INFO - root - number of sec samples after upsampling: 2394 |
| 05/12/2026 04:15:37 - INFO - root - Training args Namespace(output_name='codellama-7b-lora-safecoder', datasets=['evol', 'sec-desc', 'sec-new-desc'], pretrain_name='codellama-7b', loss_weight=1.0, sven=False, num_train_epochs=5, learning_rate=0.001, max_num_tokens=1024, batch_size=1, grad_acc_steps=16, weight_decay=0.01, adam_epsilon=1e-08, warmup_steps=0, max_grad_norm=1.0, dropout=0.1, kl_loss_weight=0, exclude_neg=False, no_weights=False, lora=True, r=16, lora_alpha=32, lora_dropout=0.1, sampling_size=20, sampling_method='minority', cwes=['all'], langs=['all'], logging_steps=50, save_epochs=10, seed=2, data_dir='../data_train_val', model_dir='../trained/', output_dir='../trained/codellama-7b-lora-safecoder', logger=<RootLogger root (INFO)>) |
| 05/12/2026 04:15:37 - INFO - root - ***** Running training ***** |
| 05/12/2026 04:15:37 - INFO - root - Num samples = 30692 |
| 05/12/2026 04:15:37 - INFO - root - Num epoch = 5 |
| 05/12/2026 04:15:37 - INFO - root - Batch size= 1 |
| 05/12/2026 04:15:37 - INFO - root - Total batch size (w. accumulation) = 16 |
| 05/12/2026 04:15:37 - INFO - root - Gradient Accumulation steps = 16 |
| 05/12/2026 04:15:37 - INFO - root - Total optimization steps = 9590 |
| 05/12/2026 04:15:37 - INFO - root - Num val samples = 3339 |
| 05/12/2026 04:15:37 - INFO - root - Num parameters = 6779101440 |
| 05/12/2026 04:15:37 - INFO - root - Num trainable parameters = 40554752 |
| 05/12/2026 04:21:02 - INFO - root - epochs: 1/5, steps: 50/9590, func: 0.050948, pos: 0.066863, neg: 0.102675, 0%: 17h 13m 50s |
| 05/12/2026 04:26:32 - INFO - root - epochs: 1/5, steps: 100/9590, func: 0.047577, pos: 0.074183, neg: 0.041983, 1%: 17h 15m 36s |
| 05/12/2026 04:31:56 - INFO - root - epochs: 1/5, steps: 150/9590, func: 0.048479, pos: 0.083375, neg: 0.044575, 1%: 17h 7m 9s |
| 05/12/2026 04:37:28 - INFO - root - epochs: 1/5, steps: 200/9590, func: 0.049801, pos: 0.100972, neg: 0.029368, 2%: 17h 5m 57s |
| 05/12/2026 04:42:57 - INFO - root - epochs: 1/5, steps: 250/9590, func: 0.048792, pos: 0.109971, neg: 0.047552, 2%: 17h 1m 3s |
| 05/12/2026 04:48:33 - INFO - root - epochs: 1/5, steps: 300/9590, func: 0.050624, pos: 0.096543, neg: 0.028878, 3%: 17h 0m 26s |
| 05/12/2026 04:53:57 - INFO - root - epochs: 1/5, steps: 350/9590, func: 0.049892, pos: 0.131824, neg: 0.033636, 3%: 16h 52m 16s |
| 05/12/2026 04:59:21 - INFO - root - epochs: 1/5, steps: 400/9590, func: 0.051175, pos: 0.098686, neg: 0.026805, 4%: 16h 45m 38s |
| 05/12/2026 05:04:53 - INFO - root - epochs: 1/5, steps: 450/9590, func: 0.050767, pos: 0.132716, neg: 0.029258, 4%: 16h 40m 58s |
| 05/12/2026 05:10:22 - INFO - root - epochs: 1/5, steps: 500/9590, func: 0.051894, pos: 0.139853, neg: 0.040111, 5%: 16h 35m 38s |
| 05/12/2026 05:15:46 - INFO - root - epochs: 1/5, steps: 550/9590, func: 0.050903, pos: 0.099576, neg: 0.036543, 5%: 16h 28m 50s |
| 05/12/2026 05:21:17 - INFO - root - epochs: 1/5, steps: 600/9590, func: 0.050571, pos: 0.105049, neg: 0.035279, 6%: 16h 24m 7s |
| 05/12/2026 05:26:49 - INFO - root - epochs: 1/5, steps: 650/9590, func: 0.051513, pos: 0.08535, neg: 0.026287, 6%: 16h 19m 19s |
| 05/12/2026 05:32:16 - INFO - root - epochs: 1/5, steps: 700/9590, func: 0.051382, pos: 0.11401, neg: 0.022054, 7%: 16h 13m 37s |
| 05/12/2026 05:37:42 - INFO - root - epochs: 1/5, steps: 750/9590, func: 0.052051, pos: 0.110181, neg: 0.022295, 7%: 16h 7m 50s |
| 05/12/2026 05:41:40 - INFO - accelerate.utils.modeling - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). |
| 05/12/2026 05:42:09 - INFO - root - number of sec samples before upsampling: 1806 |
| 05/12/2026 05:42:09 - INFO - root - number of sec samples after upsampling: 2394 |
| 05/12/2026 05:42:12 - INFO - root - Training args Namespace(output_name='codellama-7b-lora-safecoder', datasets=['evol', 'sec-desc', 'sec-new-desc'], pretrain_name='codellama-7b', loss_weight=1.0, sven=False, num_train_epochs=5, learning_rate=0.001, max_num_tokens=1024, batch_size=1, grad_acc_steps=16, weight_decay=0.01, adam_epsilon=1e-08, warmup_steps=0, max_grad_norm=1.0, dropout=0.1, kl_loss_weight=0, exclude_neg=False, no_weights=False, lora=True, r=16, lora_alpha=32, lora_dropout=0.1, sampling_size=20, sampling_method='minority', cwes=['all'], langs=['all'], logging_steps=50, save_epochs=10, seed=2, data_dir='../data_train_val', model_dir='../trained/', output_dir='../trained/codellama-7b-lora-safecoder', logger=<RootLogger root (INFO)>) |
| 05/12/2026 05:42:12 - INFO - root - ***** Running training ***** |
| 05/12/2026 05:42:12 - INFO - root - Num samples = 30692 |
| 05/12/2026 05:42:12 - INFO - root - Num epoch = 5 |
| 05/12/2026 05:42:12 - INFO - root - Batch size= 1 |
| 05/12/2026 05:42:12 - INFO - root - Total batch size (w. accumulation) = 16 |
| 05/12/2026 05:42:12 - INFO - root - Gradient Accumulation steps = 16 |
| 05/12/2026 05:42:12 - INFO - root - Total optimization steps = 9590 |
| 05/12/2026 05:42:12 - INFO - root - Num val samples = 3339 |
| 05/12/2026 05:42:12 - INFO - root - Num parameters = 6779101440 |
| 05/12/2026 05:42:12 - INFO - root - Num trainable parameters = 40554752 |
| 05/12/2026 05:46:16 - INFO - root - epochs: 1/5, steps: 50/9590, func: 0.05094, pos: 0.066244, neg: 0.104063, 0%: 12h 56m 45s |
| 05/12/2026 05:50:23 - INFO - root - epochs: 1/5, steps: 100/9590, func: 0.049307, pos: 0.077082, neg: 0.04401, 1%: 12h 55m 55s |
| 05/12/2026 05:54:25 - INFO - root - epochs: 1/5, steps: 150/9590, func: 0.051967, pos: 0.102716, neg: 0.041288, 1%: 12h 48m 36s |
| 05/12/2026 05:58:31 - INFO - root - epochs: 1/5, steps: 200/9590, func: 0.04968, pos: 0.089183, neg: 0.03749, 2%: 12h 45m 58s |
| 05/12/2026 06:02:37 - INFO - root - epochs: 1/5, steps: 250/9590, func: 0.048648, pos: 0.089534, neg: 0.056231, 2%: 12h 42m 50s |
| 05/12/2026 06:06:49 - INFO - root - epochs: 1/5, steps: 300/9590, func: 0.050689, pos: 0.087186, neg: 0.035415, 3%: 12h 42m 28s |
| 05/12/2026 06:10:50 - INFO - root - epochs: 1/5, steps: 350/9590, func: 0.050049, pos: 0.11521, neg: 0.036819, 3%: 12h 36m 12s |
| 05/12/2026 06:14:51 - INFO - root - epochs: 1/5, steps: 400/9590, func: 0.051514, pos: 0.094837, neg: 0.029605, 4%: 12h 30m 41s |
| 05/12/2026 06:18:58 - INFO - root - epochs: 1/5, steps: 450/9590, func: 0.050486, pos: 0.142797, neg: 0.023274, 4%: 12h 27m 11s |
| 05/12/2026 06:23:02 - INFO - root - epochs: 1/5, steps: 500/9590, func: 0.052427, pos: 0.131603, neg: 0.040929, 5%: 12h 22m 24s |
| 05/12/2026 06:27:00 - INFO - root - epochs: 1/5, steps: 550/9590, func: 0.051054, pos: 0.111602, neg: 0.036933, 5%: 12h 16m 23s |
| 05/12/2026 06:31:03 - INFO - root - epochs: 1/5, steps: 600/9590, func: 0.050244, pos: 0.093686, neg: 0.032851, 6%: 12h 11m 56s |
| 05/12/2026 06:35:05 - INFO - root - epochs: 1/5, steps: 650/9590, func: 0.051575, pos: 0.093165, neg: 0.028331, 6%: 12h 7m 26s |
| 05/12/2026 06:39:06 - INFO - root - epochs: 1/5, steps: 700/9590, func: 0.051052, pos: 0.127034, neg: 0.017673, 7%: 12h 2m 36s |
| 05/12/2026 06:43:09 - INFO - root - epochs: 1/5, steps: 750/9590, func: 0.051672, pos: 0.106718, neg: 0.021583, 7%: 11h 58m 27s |
| 05/12/2026 06:47:11 - INFO - root - epochs: 1/5, steps: 800/9590, func: 0.052223, pos: 0.199383, neg: 0.018326, 8%: 11h 54m 17s |
| 05/12/2026 06:51:14 - INFO - root - epochs: 1/5, steps: 850/9590, func: 0.051818, pos: 0.131503, neg: 0.017953, 8%: 11h 49m 55s |
| 05/12/2026 06:55:19 - INFO - root - epochs: 1/5, steps: 900/9590, func: 0.051805, pos: 0.095854, neg: 0.031777, 9%: 11h 46m 2s |
| 05/12/2026 06:59:20 - INFO - root - epochs: 1/5, steps: 950/9590, func: 0.051391, pos: 0.114702, neg: 0.024798, 9%: 11h 41m 38s |
| 05/12/2026 07:03:21 - INFO - root - epochs: 1/5, steps: 1000/9590, func: 0.052208, pos: 0.105047, neg: 0.025137, 10%: 11h 37m 13s |
| 05/12/2026 07:07:24 - INFO - root - epochs: 1/5, steps: 1050/9590, func: 0.052544, pos: 0.109283, neg: 0.023481, 10%: 11h 33m 8s |
| 05/12/2026 07:11:27 - INFO - root - epochs: 1/5, steps: 1100/9590, func: 0.052499, pos: 0.074911, neg: 0.017531, 11%: 11h 28m 54s |
| 05/12/2026 07:15:30 - INFO - root - epochs: 1/5, steps: 1150/9590, func: 0.052749, pos: 0.074735, neg: 0.034612, 11%: 11h 24m 47s |
| 05/12/2026 07:19:29 - INFO - root - epochs: 1/5, steps: 1200/9590, func: 0.05158, pos: 0.08104, neg: 0.030226, 12%: 11h 20m 21s |
| 05/12/2026 07:23:31 - INFO - root - epochs: 1/5, steps: 1250/9590, func: 0.05273, pos: 0.112143, neg: 0.023065, 13%: 11h 16m 6s |
| 05/12/2026 07:27:33 - INFO - root - epochs: 1/5, steps: 1300/9590, func: 0.051978, pos: 0.0801, neg: 0.018668, 13%: 11h 11m 56s |
| 05/12/2026 07:31:36 - INFO - root - epochs: 1/5, steps: 1350/9590, func: 0.053459, pos: 0.109475, neg: 0.021353, 14%: 11h 7m 53s |
| 05/12/2026 07:35:37 - INFO - root - epochs: 1/5, steps: 1400/9590, func: 0.051982, pos: 0.099747, neg: 0.017942, 14%: 11h 3m 32s |
| 05/12/2026 07:39:45 - INFO - root - epochs: 1/5, steps: 1450/9590, func: 0.052103, pos: 0.0787, neg: 0.018889, 15%: 10h 59m 57s |
| 05/12/2026 07:43:53 - INFO - root - epochs: 1/5, steps: 1500/9590, func: 0.053136, pos: 0.086926, neg: 0.022841, 15%: 10h 56m 18s |
| 05/12/2026 07:47:58 - INFO - root - epochs: 1/5, steps: 1550/9590, func: 0.051407, pos: 0.074462, neg: 0.033253, 16%: 10h 52m 29s |
| 05/12/2026 07:52:02 - INFO - root - epochs: 1/5, steps: 1600/9590, func: 0.051884, pos: 0.113117, neg: 0.013997, 16%: 10h 48m 21s |
| 05/12/2026 07:56:05 - INFO - root - epochs: 1/5, steps: 1650/9590, func: 0.051529, pos: 0.096809, neg: 0.034268, 17%: 10h 44m 22s |
| 05/12/2026 08:00:07 - INFO - root - epochs: 1/5, steps: 1700/9590, func: 0.053094, pos: 0.094909, neg: 0.025515, 17%: 10h 40m 11s |
| 05/12/2026 08:04:13 - INFO - root - epochs: 1/5, steps: 1750/9590, func: 0.051572, pos: 0.070656, neg: 0.018058, 18%: 10h 36m 16s |
| 05/12/2026 08:08:14 - INFO - root - epochs: 1/5, steps: 1800/9590, func: 0.053385, pos: 0.081258, neg: 0.021151, 18%: 10h 32m 3s |
| 05/12/2026 08:12:15 - INFO - root - epochs: 1/5, steps: 1850/9590, func: 0.051872, pos: 0.082147, neg: 0.025378, 19%: 10h 27m 52s |
| 05/12/2026 08:16:14 - INFO - root - epochs: 1/5, steps: 1900/9590, func: 0.051771, pos: 0.069222, neg: 0.02802, 19%: 10h 23m 33s |
| 05/12/2026 08:20:22 - INFO - root - epochs: 2/5, steps: 1950/9590, func: 0.049655, pos: 0.091716, neg: 0.017551, 20%: 10h 19m 51s |
| 05/12/2026 08:24:27 - INFO - root - epochs: 2/5, steps: 2000/9590, func: 0.048194, pos: 0.089666, neg: 0.016199, 20%: 10h 15m 51s |
| 05/12/2026 08:28:31 - INFO - root - epochs: 2/5, steps: 2050/9590, func: 0.047949, pos: 0.064842, neg: 0.016331, 21%: 10h 11m 50s |
| 05/12/2026 08:32:25 - INFO - root - epochs: 2/5, steps: 2100/9590, func: 0.047398, pos: 0.05705, neg: 0.022757, 21%: 10h 7m 14s |
| 05/12/2026 08:36:23 - INFO - root - epochs: 2/5, steps: 2150/9590, func: 0.046701, pos: 0.047835, neg: 0.007168, 22%: 10h 2m 49s |
| 05/12/2026 08:40:20 - INFO - root - epochs: 2/5, steps: 2200/9590, func: 0.047965, pos: 0.075317, neg: 0.016316, 22%: 9h 58m 28s |
| 05/12/2026 08:44:15 - INFO - root - epochs: 2/5, steps: 2250/9590, func: 0.049061, pos: 0.063372, neg: 0.013699, 23%: 9h 53m 59s |
| 05/12/2026 08:48:25 - INFO - root - epochs: 2/5, steps: 2300/9590, func: 0.049057, pos: 0.048502, neg: 0.018374, 23%: 9h 50m 15s |
| 05/12/2026 08:52:32 - INFO - root - epochs: 2/5, steps: 2350/9590, func: 0.048354, pos: 0.069101, neg: 0.026868, 24%: 9h 46m 26s |
| 05/12/2026 08:56:38 - INFO - root - epochs: 2/5, steps: 2400/9590, func: 0.049917, pos: 0.054647, neg: 0.015619, 25%: 9h 42m 34s |
| 05/12/2026 09:00:41 - INFO - root - epochs: 2/5, steps: 2450/9590, func: 0.049093, pos: 0.066494, neg: 0.018207, 25%: 9h 38m 31s |
| 05/12/2026 09:04:46 - INFO - root - epochs: 2/5, steps: 2500/9590, func: 0.048869, pos: 0.050998, neg: 0.01707, 26%: 9h 34m 33s |
| 05/12/2026 09:08:49 - INFO - root - epochs: 2/5, steps: 2550/9590, func: 0.049238, pos: 0.049718, neg: 0.021854, 26%: 9h 30m 32s |
| 05/12/2026 09:12:54 - INFO - root - epochs: 2/5, steps: 2600/9590, func: 0.048473, pos: 0.048989, neg: 0.010893, 27%: 9h 26m 33s |
| 05/12/2026 09:16:56 - INFO - root - epochs: 2/5, steps: 2650/9590, func: 0.047705, pos: 0.057008, neg: 0.013472, 27%: 9h 22m 26s |
| 05/12/2026 09:20:51 - INFO - root - epochs: 2/5, steps: 2700/9590, func: 0.048697, pos: 0.051007, neg: 0.020675, 28%: 9h 18m 3s |
| 05/12/2026 09:24:59 - INFO - root - epochs: 2/5, steps: 2750/9590, func: 0.049822, pos: 0.066192, neg: 0.019821, 28%: 9h 14m 14s |
| 05/12/2026 09:29:03 - INFO - root - epochs: 2/5, steps: 2800/9590, func: 0.048675, pos: 0.053753, neg: 0.013854, 29%: 9h 10m 12s |
| 05/12/2026 09:33:07 - INFO - root - epochs: 2/5, steps: 2850/9590, func: 0.049093, pos: 0.069586, neg: 0.016566, 29%: 9h 6m 10s |
| 05/12/2026 09:37:04 - INFO - root - epochs: 2/5, steps: 2900/9590, func: 0.048524, pos: 0.070572, neg: 0.017197, 30%: 9h 1m 56s |
| 05/12/2026 09:41:08 - INFO - root - epochs: 2/5, steps: 2950/9590, func: 0.049634, pos: 0.074833, neg: 0.014874, 30%: 8h 57m 53s |
| 05/12/2026 09:45:11 - INFO - root - epochs: 2/5, steps: 3000/9590, func: 0.050054, pos: 0.087303, neg: 0.010392, 31%: 8h 53m 50s |
| 05/12/2026 09:49:13 - INFO - root - epochs: 2/5, steps: 3050/9590, func: 0.050311, pos: 0.062351, neg: 0.018711, 31%: 8h 49m 46s |
| 05/12/2026 09:53:16 - INFO - root - epochs: 2/5, steps: 3100/9590, func: 0.04941, pos: 0.055028, neg: 0.014512, 32%: 8h 45m 44s |
| 05/12/2026 09:57:21 - INFO - root - epochs: 2/5, steps: 3150/9590, func: 0.048447, pos: 0.049718, neg: 0.010809, 32%: 8h 41m 45s |
| 05/12/2026 10:01:26 - INFO - root - epochs: 2/5, steps: 3200/9590, func: 0.048828, pos: 0.04025, neg: 0.011925, 33%: 8h 37m 45s |
| 05/12/2026 10:05:28 - INFO - root - epochs: 2/5, steps: 3250/9590, func: 0.049547, pos: 0.047331, neg: 0.016769, 33%: 8h 33m 40s |
| 05/12/2026 10:09:32 - INFO - root - epochs: 2/5, steps: 3300/9590, func: 0.049657, pos: 0.052612, neg: 0.01622, 34%: 8h 29m 38s |
| 05/12/2026 10:13:36 - INFO - root - epochs: 2/5, steps: 3350/9590, func: 0.048103, pos: 0.051177, neg: 0.016804, 34%: 8h 25m 37s |
| 05/12/2026 10:17:43 - INFO - root - epochs: 2/5, steps: 3400/9590, func: 0.049741, pos: 0.046914, neg: 0.00997, 35%: 8h 21m 39s |
| 05/12/2026 10:21:39 - INFO - root - epochs: 2/5, steps: 3450/9590, func: 0.049321, pos: 0.044237, neg: 0.021636, 35%: 8h 17m 24s |
| 05/12/2026 10:25:41 - INFO - root - epochs: 2/5, steps: 3500/9590, func: 0.048902, pos: 0.054882, neg: 0.014377, 36%: 8h 13m 20s |
| 05/12/2026 10:29:46 - INFO - root - epochs: 2/5, steps: 3550/9590, func: 0.048824, pos: 0.063807, neg: 0.014463, 37%: 8h 9m 20s |
| 05/12/2026 10:33:45 - INFO - root - epochs: 2/5, steps: 3600/9590, func: 0.048231, pos: 0.058499, neg: 0.024831, 37%: 8h 5m 11s |
| 05/12/2026 10:37:44 - INFO - root - epochs: 2/5, steps: 3650/9590, func: 0.048081, pos: 0.085183, neg: 0.014266, 38%: 8h 1m 1s |
| 05/12/2026 10:41:45 - INFO - root - epochs: 2/5, steps: 3700/9590, func: 0.049161, pos: 0.052952, neg: 0.017932, 38%: 7h 56m 57s |
| 05/12/2026 10:45:46 - INFO - root - epochs: 2/5, steps: 3750/9590, func: 0.0463, pos: 0.038567, neg: 0.024301, 39%: 7h 52m 49s |
| 05/12/2026 10:49:48 - INFO - root - epochs: 2/5, steps: 3800/9590, func: 0.049297, pos: 0.069484, neg: 0.014716, 39%: 7h 48m 46s |
| 05/12/2026 10:53:53 - INFO - root - epochs: 3/5, steps: 3850/9590, func: 0.046816, pos: 0.040204, neg: 0.01251, 40%: 7h 44m 46s |
| 05/12/2026 10:58:02 - INFO - root - epochs: 3/5, steps: 3900/9590, func: 0.043129, pos: 0.026737, neg: 0.005862, 40%: 7h 40m 51s |
| 05/12/2026 11:02:08 - INFO - root - epochs: 3/5, steps: 3950/9590, func: 0.042884, pos: 0.033689, neg: 0.018398, 41%: 7h 36m 55s |
| 05/12/2026 11:06:16 - INFO - root - epochs: 3/5, steps: 4000/9590, func: 0.04335, pos: 0.033484, neg: 0.011237, 41%: 7h 32m 57s |
| 05/12/2026 11:10:22 - INFO - root - epochs: 3/5, steps: 4050/9590, func: 0.043222, pos: 0.03106, neg: 0.009611, 42%: 7h 28m 58s |
| 05/12/2026 11:14:26 - INFO - root - epochs: 3/5, steps: 4100/9590, func: 0.04263, pos: 0.024914, neg: 0.0074, 42%: 7h 24m 56s |
| 05/12/2026 11:18:25 - INFO - root - epochs: 3/5, steps: 4150/9590, func: 0.042534, pos: 0.029838, neg: 0.00935, 43%: 7h 20m 48s |
| 05/12/2026 11:22:26 - INFO - root - epochs: 3/5, steps: 4200/9590, func: 0.043006, pos: 0.023594, neg: 0.003426, 43%: 7h 16m 44s |
| 05/12/2026 11:26:27 - INFO - root - epochs: 3/5, steps: 4250/9590, func: 0.043293, pos: 0.038818, neg: 0.0156, 44%: 7h 12m 37s |
| 05/12/2026 11:30:28 - INFO - root - epochs: 3/5, steps: 4300/9590, func: 0.043924, pos: 0.026801, neg: 0.013046, 44%: 7h 8m 32s |
| 05/12/2026 11:34:30 - INFO - root - epochs: 3/5, steps: 4350/9590, func: 0.043028, pos: 0.036002, neg: 0.007841, 45%: 7h 4m 27s |
| 05/12/2026 11:38:26 - INFO - root - epochs: 3/5, steps: 4400/9590, func: 0.04386, pos: 0.032908, neg: 0.013913, 45%: 7h 0m 15s |
| 05/12/2026 11:42:29 - INFO - root - epochs: 3/5, steps: 4450/9590, func: 0.044371, pos: 0.031435, neg: 0.011, 46%: 6h 56m 13s |
| 05/12/2026 11:46:32 - INFO - root - epochs: 3/5, steps: 4500/9590, func: 0.043781, pos: 0.026892, neg: 0.004409, 46%: 6h 52m 11s |
| 05/12/2026 11:50:35 - INFO - root - epochs: 3/5, steps: 4550/9590, func: 0.044126, pos: 0.03361, neg: 0.01439, 47%: 6h 48m 9s |
| 05/12/2026 11:54:34 - INFO - root - epochs: 3/5, steps: 4600/9590, func: 0.043945, pos: 0.042274, neg: 0.011236, 47%: 6h 44m 0s |
| 05/12/2026 11:58:32 - INFO - root - epochs: 3/5, steps: 4650/9590, func: 0.043599, pos: 0.020995, neg: 0.012674, 48%: 6h 39m 53s |
| 05/12/2026 12:02:32 - INFO - root - epochs: 3/5, steps: 4700/9590, func: 0.043737, pos: 0.032744, neg: 0.007529, 48%: 6h 35m 47s |
| 05/12/2026 12:06:32 - INFO - root - epochs: 3/5, steps: 4750/9590, func: 0.04433, pos: 0.018101, neg: 0.00986, 49%: 6h 31m 42s |
| 05/12/2026 12:10:37 - INFO - root - epochs: 3/5, steps: 4800/9590, func: 0.044883, pos: 0.031611, neg: 0.007338, 50%: 6h 27m 42s |
| 05/12/2026 12:14:40 - INFO - root - epochs: 3/5, steps: 4850/9590, func: 0.043752, pos: 0.036319, neg: 0.010377, 50%: 6h 23m 39s |
| 05/12/2026 12:18:40 - INFO - root - epochs: 3/5, steps: 4900/9590, func: 0.043916, pos: 0.026421, neg: 0.008696, 51%: 6h 19m 34s |
| 05/12/2026 12:22:44 - INFO - root - epochs: 3/5, steps: 4950/9590, func: 0.043717, pos: 0.036711, neg: 0.014496, 51%: 6h 15m 32s |
| 05/12/2026 12:26:45 - INFO - root - epochs: 3/5, steps: 5000/9590, func: 0.044367, pos: 0.041459, neg: 0.005121, 52%: 6h 11m 27s |
| 05/12/2026 12:30:49 - INFO - root - epochs: 3/5, steps: 5050/9590, func: 0.044552, pos: 0.030175, neg: 0.00822, 52%: 6h 7m 26s |
| 05/12/2026 12:34:59 - INFO - root - epochs: 3/5, steps: 5100/9590, func: 0.043727, pos: 0.031545, neg: 0.017947, 53%: 6h 3m 29s |
| 05/12/2026 12:39:08 - INFO - root - epochs: 3/5, steps: 5150/9590, func: 0.044665, pos: 0.020976, neg: 0.013421, 53%: 5h 59m 33s |
| 05/12/2026 12:43:13 - INFO - root - epochs: 3/5, steps: 5200/9590, func: 0.04315, pos: 0.035845, neg: 0.009733, 54%: 5h 55m 30s |
| 05/12/2026 12:47:15 - INFO - root - epochs: 3/5, steps: 5250/9590, func: 0.04466, pos: 0.037906, neg: 0.009849, 54%: 5h 51m 27s |
| 05/12/2026 12:51:14 - INFO - root - epochs: 3/5, steps: 5300/9590, func: 0.044784, pos: 0.034, neg: 0.015596, 55%: 5h 47m 21s |
| 05/12/2026 12:55:14 - INFO - root - epochs: 3/5, steps: 5350/9590, func: 0.043455, pos: 0.028191, neg: 0.010957, 55%: 5h 43m 16s |
| 05/12/2026 12:59:16 - INFO - root - epochs: 3/5, steps: 5400/9590, func: 0.042788, pos: 0.030653, neg: 0.011688, 56%: 5h 39m 12s |
| 05/12/2026 13:03:23 - INFO - root - epochs: 3/5, steps: 5450/9590, func: 0.044157, pos: 0.025905, neg: 0.009461, 56%: 5h 35m 13s |
| 05/12/2026 13:07:32 - INFO - root - epochs: 3/5, steps: 5500/9590, func: 0.045079, pos: 0.027724, neg: 0.009764, 57%: 5h 31m 15s |
| 05/12/2026 13:11:38 - INFO - root - epochs: 3/5, steps: 5550/9590, func: 0.043324, pos: 0.032279, neg: 0.014533, 57%: 5h 27m 13s |
| 05/12/2026 13:15:42 - INFO - root - epochs: 3/5, steps: 5600/9590, func: 0.043653, pos: 0.035368, neg: 0.005618, 58%: 5h 23m 11s |
| 05/12/2026 13:19:45 - INFO - root - epochs: 3/5, steps: 5650/9590, func: 0.043204, pos: 0.024611, neg: 0.017919, 58%: 5h 19m 9s |
| 05/12/2026 13:23:46 - INFO - root - epochs: 3/5, steps: 5700/9590, func: 0.04316, pos: 0.018795, neg: 0.010624, 59%: 5h 15m 4s |
| 05/12/2026 13:27:48 - INFO - root - epochs: 3/5, steps: 5750/9590, func: 0.044979, pos: 0.025781, neg: 0.020653, 59%: 5h 11m 1s |
| 05/12/2026 13:31:50 - INFO - root - epochs: 4/5, steps: 5800/9590, func: 0.037187, pos: 0.028788, neg: 0.006066, 60%: 5h 6m 58s |
| 05/12/2026 13:35:52 - INFO - root - epochs: 4/5, steps: 5850/9590, func: 0.037183, pos: 0.01936, neg: 0.004128, 60%: 5h 2m 53s |
| 05/12/2026 13:39:56 - INFO - root - epochs: 4/5, steps: 5900/9590, func: 0.036845, pos: 0.010634, neg: 0.006401, 61%: 4h 58m 51s |
| 05/12/2026 13:43:55 - INFO - root - epochs: 4/5, steps: 5950/9590, func: 0.035898, pos: 0.014306, neg: 0.001101, 62%: 4h 54m 46s |
| 05/12/2026 13:48:01 - INFO - root - epochs: 4/5, steps: 6000/9590, func: 0.036924, pos: 0.021029, neg: 0.003658, 62%: 4h 50m 45s |
| 05/12/2026 13:52:07 - INFO - root - epochs: 4/5, steps: 6050/9590, func: 0.037266, pos: 0.026165, neg: 0.007137, 63%: 4h 46m 44s |
| 05/12/2026 13:56:05 - INFO - root - epochs: 4/5, steps: 6100/9590, func: 0.03719, pos: 0.013228, neg: 0.004765, 63%: 4h 42m 38s |
| 05/12/2026 14:00:08 - INFO - root - epochs: 4/5, steps: 6150/9590, func: 0.037471, pos: 0.011627, neg: 0.003193, 64%: 4h 38m 36s |
| 05/12/2026 14:04:14 - INFO - root - epochs: 4/5, steps: 6200/9590, func: 0.037742, pos: 0.008895, neg: 0.007303, 64%: 4h 34m 34s |
| 05/12/2026 14:08:17 - INFO - root - epochs: 4/5, steps: 6250/9590, func: 0.037754, pos: 0.011739, neg: 0.004153, 65%: 4h 30m 32s |
| 05/12/2026 14:12:13 - INFO - root - epochs: 4/5, steps: 6300/9590, func: 0.036989, pos: 0.01173, neg: 0.008266, 65%: 4h 26m 25s |
| 05/12/2026 14:16:20 - INFO - root - epochs: 4/5, steps: 6350/9590, func: 0.037897, pos: 0.01403, neg: 0.005232, 66%: 4h 22m 24s |
| 05/12/2026 14:20:26 - INFO - root - epochs: 4/5, steps: 6400/9590, func: 0.037609, pos: 0.016425, neg: 0.002059, 66%: 4h 18m 23s |
| 05/12/2026 14:24:32 - INFO - root - epochs: 4/5, steps: 6450/9590, func: 0.038468, pos: 0.019632, neg: 0.013029, 67%: 4h 14m 21s |
| 05/12/2026 14:28:32 - INFO - root - epochs: 4/5, steps: 6500/9590, func: 0.038036, pos: 0.011861, neg: 0.003423, 67%: 4h 10m 17s |
| 05/12/2026 14:32:33 - INFO - root - epochs: 4/5, steps: 6550/9590, func: 0.037247, pos: 0.027833, neg: 0.005179, 68%: 4h 6m 13s |
| 05/12/2026 14:36:40 - INFO - root - epochs: 4/5, steps: 6600/9590, func: 0.037224, pos: 0.015212, neg: 0.006781, 68%: 4h 2m 12s |
| 05/12/2026 14:40:41 - INFO - root - epochs: 4/5, steps: 6650/9590, func: 0.038324, pos: 0.015693, neg: 0.005974, 69%: 3h 58m 8s |
| 05/12/2026 14:44:45 - INFO - root - epochs: 4/5, steps: 6700/9590, func: 0.039012, pos: 0.014201, neg: 0.00685, 69%: 3h 54m 6s |
| 05/12/2026 14:48:52 - INFO - root - epochs: 4/5, steps: 6750/9590, func: 0.037505, pos: 0.010282, neg: 0.002384, 70%: 3h 50m 5s |
| 05/12/2026 14:52:58 - INFO - root - epochs: 4/5, steps: 6800/9590, func: 0.037557, pos: 0.007854, neg: 0.003328, 70%: 3h 46m 3s |
| 05/12/2026 14:56:55 - INFO - root - epochs: 4/5, steps: 6850/9590, func: 0.037521, pos: 0.012866, neg: 0.003266, 71%: 3h 41m 58s |
| 05/12/2026 15:00:56 - INFO - root - epochs: 4/5, steps: 6900/9590, func: 0.037562, pos: 0.004959, neg: 0.003749, 71%: 3h 37m 54s |
| 05/12/2026 15:04:57 - INFO - root - epochs: 4/5, steps: 6950/9590, func: 0.038498, pos: 0.011588, neg: 0.004565, 72%: 3h 33m 50s |
| 05/12/2026 15:09:04 - INFO - root - epochs: 4/5, steps: 7000/9590, func: 0.037594, pos: 0.016966, neg: 0.006965, 72%: 3h 29m 49s |
| 05/12/2026 15:13:12 - INFO - root - epochs: 4/5, steps: 7050/9590, func: 0.039776, pos: 0.013159, neg: 0.006337, 73%: 3h 25m 48s |
| 05/12/2026 15:17:14 - INFO - root - epochs: 4/5, steps: 7100/9590, func: 0.037827, pos: 0.011383, neg: 0.004707, 74%: 3h 21m 44s |
| 05/12/2026 15:21:16 - INFO - root - epochs: 4/5, steps: 7150/9590, func: 0.038144, pos: 0.024477, neg: 0.008781, 74%: 3h 17m 41s |
| 05/12/2026 15:25:23 - INFO - root - epochs: 4/5, steps: 7200/9590, func: 0.039326, pos: 0.026087, neg: 0.008004, 75%: 3h 13m 39s |
| 05/12/2026 15:29:22 - INFO - root - epochs: 4/5, steps: 7250/9590, func: 0.038138, pos: 0.012713, neg: 0.008708, 75%: 3h 9m 35s |
| 05/12/2026 15:33:29 - INFO - root - epochs: 4/5, steps: 7300/9590, func: 0.037897, pos: 0.011754, neg: 0.003533, 76%: 3h 5m 34s |
| 05/12/2026 15:37:28 - INFO - root - epochs: 4/5, steps: 7350/9590, func: 0.037133, pos: 0.011942, neg: 0.01366, 76%: 3h 1m 29s |
| 05/12/2026 15:41:27 - INFO - root - epochs: 4/5, steps: 7400/9590, func: 0.03792, pos: 0.004823, neg: 0.002933, 77%: 2h 57m 25s |
| 05/12/2026 15:45:36 - INFO - root - epochs: 4/5, steps: 7450/9590, func: 0.039068, pos: 0.013343, neg: 0.002967, 77%: 2h 53m 24s |
| 05/12/2026 15:49:33 - INFO - root - epochs: 4/5, steps: 7500/9590, func: 0.03732, pos: 0.014963, neg: 0.00197, 78%: 2h 49m 19s |
| 05/12/2026 15:53:39 - INFO - root - epochs: 4/5, steps: 7550/9590, func: 0.038959, pos: 0.005567, neg: 0.008477, 78%: 2h 45m 17s |
| 05/12/2026 15:57:39 - INFO - root - epochs: 4/5, steps: 7600/9590, func: 0.036912, pos: 0.013687, neg: 0.004179, 79%: 2h 41m 14s |
| 05/12/2026 16:01:41 - INFO - root - epochs: 4/5, steps: 7650/9590, func: 0.039019, pos: 0.014941, neg: 0.004959, 79%: 2h 37m 10s |
| 05/12/2026 16:05:49 - INFO - root - epochs: 5/5, steps: 7700/9590, func: 0.033764, pos: 0.005057, neg: 0.003659, 80%: 2h 33m 9s |
| 05/12/2026 16:09:54 - INFO - root - epochs: 5/5, steps: 7750/9590, func: 0.029872, pos: 0.003296, neg: 0.00179, 80%: 2h 29m 6s |
| 05/12/2026 16:13:57 - INFO - root - epochs: 5/5, steps: 7800/9590, func: 0.030226, pos: 0.004068, neg: 0.000308, 81%: 2h 25m 3s |
| 05/12/2026 16:17:56 - INFO - root - epochs: 5/5, steps: 7850/9590, func: 0.028933, pos: 0.014822, neg: 0.004078, 81%: 2h 20m 59s |
| 05/12/2026 16:21:59 - INFO - root - epochs: 5/5, steps: 7900/9590, func: 0.030283, pos: 0.003466, neg: 0.003448, 82%: 2h 16m 56s |
| 05/12/2026 16:26:04 - INFO - root - epochs: 5/5, steps: 7950/9590, func: 0.029845, pos: 0.007248, neg: 0.001106, 82%: 2h 12m 54s |
| 05/12/2026 16:30:08 - INFO - root - epochs: 5/5, steps: 8000/9590, func: 0.031504, pos: 0.005889, neg: 0.001085, 83%: 2h 8m 51s |
| 05/12/2026 16:34:14 - INFO - root - epochs: 5/5, steps: 8050/9590, func: 0.031164, pos: 0.003975, neg: 0.00115, 83%: 2h 4m 49s |
| 05/12/2026 16:38:12 - INFO - root - epochs: 5/5, steps: 8100/9590, func: 0.030783, pos: 0.003097, neg: 0.001654, 84%: 2h 0m 45s |
| 05/12/2026 16:42:11 - INFO - root - epochs: 5/5, steps: 8150/9590, func: 0.030095, pos: 0.003739, neg: 0.001491, 84%: 1h 56m 41s |
| 05/12/2026 16:46:10 - INFO - root - epochs: 5/5, steps: 8200/9590, func: 0.029816, pos: 0.007938, neg: 0.000674, 85%: 1h 52m 37s |
| 05/12/2026 16:50:14 - INFO - root - epochs: 5/5, steps: 8250/9590, func: 0.031022, pos: 0.002691, neg: 0.002459, 86%: 1h 48m 35s |
| 05/12/2026 16:54:18 - INFO - root - epochs: 5/5, steps: 8300/9590, func: 0.030573, pos: 0.006589, neg: 0.00105, 86%: 1h 44m 32s |
| 05/12/2026 16:58:19 - INFO - root - epochs: 5/5, steps: 8350/9590, func: 0.030611, pos: 0.00893, neg: 0.001367, 87%: 1h 40m 29s |
| 05/12/2026 17:02:25 - INFO - root - epochs: 5/5, steps: 8400/9590, func: 0.03111, pos: 0.006094, neg: 0.003428, 87%: 1h 36m 26s |
| 05/12/2026 17:06:28 - INFO - root - epochs: 5/5, steps: 8450/9590, func: 0.031174, pos: 0.006896, neg: 0.001139, 88%: 1h 32m 23s |
| 05/12/2026 17:10:33 - INFO - root - epochs: 5/5, steps: 8500/9590, func: 0.03143, pos: 0.010165, neg: 0.001063, 88%: 1h 28m 21s |
| 05/12/2026 17:14:33 - INFO - root - epochs: 5/5, steps: 8550/9590, func: 0.02977, pos: 0.001661, neg: 0.000399, 89%: 1h 24m 17s |
| 05/12/2026 17:18:38 - INFO - root - epochs: 5/5, steps: 8600/9590, func: 0.030976, pos: 0.002311, neg: 0.001703, 89%: 1h 20m 14s |
| 05/12/2026 17:22:42 - INFO - root - epochs: 5/5, steps: 8650/9590, func: 0.029891, pos: 0.003819, neg: 0.002301, 90%: 1h 16m 12s |
| 05/12/2026 17:26:45 - INFO - root - epochs: 5/5, steps: 8700/9590, func: 0.030551, pos: 0.001962, neg: 0.000672, 90%: 1h 12m 9s |
| 05/12/2026 17:30:50 - INFO - root - epochs: 5/5, steps: 8750/9590, func: 0.03133, pos: 0.004639, neg: 0.015719, 91%: 1h 8m 6s |
| 05/12/2026 17:34:52 - INFO - root - epochs: 5/5, steps: 8800/9590, func: 0.030877, pos: 0.003829, neg: 0.002129, 91%: 1h 4m 3s |
| 05/12/2026 17:38:52 - INFO - root - epochs: 5/5, steps: 8850/9590, func: 0.029963, pos: 0.002877, neg: 0.000992, 92%: 1h 0m 0s |
| 05/12/2026 17:42:59 - INFO - root - epochs: 5/5, steps: 8900/9590, func: 0.030816, pos: 0.003824, neg: 0.000756, 92%: 0h 55m 57s |
| 05/12/2026 17:47:04 - INFO - root - epochs: 5/5, steps: 8950/9590, func: 0.031247, pos: 0.001944, neg: 0.005025, 93%: 0h 51m 54s |
| 05/12/2026 17:51:06 - INFO - root - epochs: 5/5, steps: 9000/9590, func: 0.030236, pos: 0.004118, neg: 0.00032, 93%: 0h 47m 51s |
| 05/12/2026 17:55:06 - INFO - root - epochs: 5/5, steps: 9050/9590, func: 0.030045, pos: 0.003925, neg: 0.006625, 94%: 0h 43m 48s |
| 05/12/2026 17:59:11 - INFO - root - epochs: 5/5, steps: 9100/9590, func: 0.030309, pos: 0.007086, neg: 0.001351, 94%: 0h 39m 45s |
| 05/12/2026 18:03:12 - INFO - root - epochs: 5/5, steps: 9150/9590, func: 0.030451, pos: 0.001467, neg: 0.004338, 95%: 0h 35m 42s |
| 05/12/2026 18:07:17 - INFO - root - epochs: 5/5, steps: 9200/9590, func: 0.030429, pos: 0.007513, neg: 0.003631, 95%: 0h 31m 39s |
| 05/12/2026 18:11:21 - INFO - root - epochs: 5/5, steps: 9250/9590, func: 0.030666, pos: 0.003335, neg: 0.003133, 96%: 0h 27m 37s |
| 05/12/2026 18:15:25 - INFO - root - epochs: 5/5, steps: 9300/9590, func: 0.030095, pos: 0.006037, neg: 0.001205, 96%: 0h 23m 34s |
| 05/12/2026 18:19:29 - INFO - root - epochs: 5/5, steps: 9350/9590, func: 0.030603, pos: 0.005101, neg: 0.001488, 97%: 0h 19m 31s |
| 05/12/2026 18:23:32 - INFO - root - epochs: 5/5, steps: 9400/9590, func: 0.031185, pos: 0.00453, neg: 0.000905, 98%: 0h 15m 28s |
| 05/12/2026 18:27:35 - INFO - root - epochs: 5/5, steps: 9450/9590, func: 0.031027, pos: 0.005386, neg: 0.00126, 98%: 0h 11m 25s |
| 05/12/2026 18:31:37 - INFO - root - epochs: 5/5, steps: 9500/9590, func: 0.030854, pos: 0.007732, neg: 0.00126, 99%: 0h 7m 22s |
| 05/12/2026 18:35:37 - INFO - root - epochs: 5/5, steps: 9550/9590, func: 0.031091, pos: 0.004284, neg: 0.000373, 99%: 0h 3m 19s |
| 05/12/2026 18:47:11 - INFO - root - final eval loss: func: 0.051988, pos: 0.0564, neg: 0.048031 |
| 05/12/2026 18:47:11 - INFO - root - Saving model checkpoint to ../trained/codellama-7b-lora-safecoder/checkpoint-last |
|
|
