Training in progress, epoch 3

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba67c5686d5703c30bfc1094d764bf34f8ae3888803080686eada74ceee7f13f
+oid sha256:9a3a87857433ba861f5188ffcfe05dcf83585161642a43c9e3815dc05affa988
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c870e52c061e49ef65ae8b0ba1c10d010edf4943c4e40dea5d446eb1f28cbe
+oid sha256:f9d214328d1972083f8699acad5e3d953dd2e266ef07360c61cf52cdad2a41c8
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:940683dbbecf9fe1f21591a6769154b4e2b2a1108bc369dbe612ccc4421a44b3
+oid sha256:6dcf69ea3a169df232519c5b679e5119efff07083dc680bf630cfc6fbfc225bf
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8bd62101a93c368d47c6a0ee6cb3c35e59f14a1dfb9c230bedc46f820ca37fa
+oid sha256:6d2a0de8fd8ca21ff48bce41ce31ebcda30a43fdb45c86643449cefa7566c536
 size 1089994880

trainer_log.jsonl

@@ -233,3 +233,81 @@
 {"current_steps": 233, "total_steps": 390, "loss": 0.3562, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:26:40", "remaining_time": "7:02:15"}
 {"current_steps": 234, "total_steps": 390, "loss": 0.3532, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:29:19", "remaining_time": "6:59:33"}
 {"current_steps": 235, "total_steps": 390, "loss": 0.3085, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:32:46", "remaining_time": "6:57:21"}
+{"current_steps": 236, "total_steps": 390, "loss": 0.2972, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:35:22", "remaining_time": "6:54:36"}
+{"current_steps": 237, "total_steps": 390, "loss": 0.304, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:38:06", "remaining_time": "6:51:56"}
+{"current_steps": 238, "total_steps": 390, "loss": 0.2983, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:40:19", "remaining_time": "6:48:56"}
+{"current_steps": 239, "total_steps": 390, "loss": 0.293, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:42:57", "remaining_time": "6:46:13"}
+{"current_steps": 240, "total_steps": 390, "loss": 0.2974, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:45:40", "remaining_time": "6:43:32"}
+{"current_steps": 241, "total_steps": 390, "loss": 0.2958, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:48:09", "remaining_time": "6:40:43"}
+{"current_steps": 242, "total_steps": 390, "loss": 0.2973, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:50:49", "remaining_time": "6:38:01"}
+{"current_steps": 243, "total_steps": 390, "loss": 0.3037, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "10:53:20", "remaining_time": "6:35:13"}
+{"current_steps": 244, "total_steps": 390, "loss": 0.3108, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "10:56:00", "remaining_time": "6:32:31"}
+{"current_steps": 245, "total_steps": 390, "loss": 0.3022, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "10:58:38", "remaining_time": "6:29:48"}
+{"current_steps": 246, "total_steps": 390, "loss": 0.3012, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "11:01:20", "remaining_time": "6:27:07"}
+{"current_steps": 247, "total_steps": 390, "loss": 0.2871, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "11:03:40", "remaining_time": "6:24:13"}
+{"current_steps": 248, "total_steps": 390, "loss": 0.2935, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:06:11", "remaining_time": "6:21:27"}
+{"current_steps": 249, "total_steps": 390, "loss": 0.3101, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:08:50", "remaining_time": "6:18:44"}
+{"current_steps": 250, "total_steps": 390, "loss": 0.2981, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:11:25", "remaining_time": "6:15:59"}
+{"current_steps": 251, "total_steps": 390, "loss": 0.2989, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:14:04", "remaining_time": "6:13:17"}
+{"current_steps": 252, "total_steps": 390, "loss": 0.2985, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:16:57", "remaining_time": "6:10:42"}
+{"current_steps": 253, "total_steps": 390, "loss": 0.2962, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:19:27", "remaining_time": "6:07:55"}
+{"current_steps": 254, "total_steps": 390, "loss": 0.2907, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:22:00", "remaining_time": "6:05:10"}
+{"current_steps": 255, "total_steps": 390, "loss": 0.3063, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:24:51", "remaining_time": "6:02:34"}
+{"current_steps": 256, "total_steps": 390, "loss": 0.2968, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:27:28", "remaining_time": "5:59:50"}
+{"current_steps": 257, "total_steps": 390, "loss": 0.2943, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:30:11", "remaining_time": "5:57:10"}
+{"current_steps": 258, "total_steps": 390, "loss": 0.2968, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:33:00", "remaining_time": "5:54:33"}
+{"current_steps": 259, "total_steps": 390, "loss": 0.2979, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:35:40", "remaining_time": "5:51:52"}
+{"current_steps": 260, "total_steps": 390, "loss": 0.295, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:38:29", "remaining_time": "5:49:14"}
+{"current_steps": 261, "total_steps": 390, "loss": 0.2954, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:41:10", "remaining_time": "5:46:33"}
+{"current_steps": 262, "total_steps": 390, "loss": 0.2964, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:43:57", "remaining_time": "5:43:55"}
+{"current_steps": 263, "total_steps": 390, "loss": 0.2923, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:46:33", "remaining_time": "5:41:11"}
+{"current_steps": 264, "total_steps": 390, "loss": 0.3036, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:49:10", "remaining_time": "5:38:28"}
+{"current_steps": 265, "total_steps": 390, "loss": 0.3029, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "11:51:55", "remaining_time": "5:35:48"}
+{"current_steps": 266, "total_steps": 390, "loss": 0.2976, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "11:54:43", "remaining_time": "5:33:10"}
+{"current_steps": 267, "total_steps": 390, "loss": 0.2969, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "11:57:20", "remaining_time": "5:30:27"}
+{"current_steps": 268, "total_steps": 390, "loss": 0.2942, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "12:00:01", "remaining_time": "5:27:46"}
+{"current_steps": 269, "total_steps": 390, "loss": 0.3007, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "12:02:21", "remaining_time": "5:24:55"}
+{"current_steps": 270, "total_steps": 390, "loss": 0.3013, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "12:04:58", "remaining_time": "5:22:12"}
+{"current_steps": 271, "total_steps": 390, "loss": 0.3034, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:07:29", "remaining_time": "5:19:26"}
+{"current_steps": 272, "total_steps": 390, "loss": 0.3106, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:10:15", "remaining_time": "5:16:48"}
+{"current_steps": 273, "total_steps": 390, "loss": 0.2957, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:12:53", "remaining_time": "5:14:05"}
+{"current_steps": 274, "total_steps": 390, "loss": 0.3009, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:15:28", "remaining_time": "5:11:22"}
+{"current_steps": 275, "total_steps": 390, "loss": 0.2986, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:17:59", "remaining_time": "5:08:36"}
+{"current_steps": 276, "total_steps": 390, "loss": 0.298, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:20:36", "remaining_time": "5:05:54"}
+{"current_steps": 277, "total_steps": 390, "loss": 0.3001, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:23:09", "remaining_time": "5:03:09"}
+{"current_steps": 278, "total_steps": 390, "loss": 0.3027, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:25:35", "remaining_time": "5:00:23"}
+{"current_steps": 279, "total_steps": 390, "loss": 0.3002, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:28:22", "remaining_time": "4:57:44"}
+{"current_steps": 280, "total_steps": 390, "loss": 0.2955, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:30:53", "remaining_time": "4:54:59"}
+{"current_steps": 281, "total_steps": 390, "loss": 0.298, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:33:31", "remaining_time": "4:52:17"}
+{"current_steps": 282, "total_steps": 390, "loss": 0.2998, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:36:10", "remaining_time": "4:49:35"}
+{"current_steps": 283, "total_steps": 390, "loss": 0.2921, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:38:49", "remaining_time": "4:46:54"}
+{"current_steps": 284, "total_steps": 390, "loss": 0.3086, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:41:10", "remaining_time": "4:44:06"}
+{"current_steps": 285, "total_steps": 390, "loss": 0.2949, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:43:52", "remaining_time": "4:41:25"}
+{"current_steps": 286, "total_steps": 390, "loss": 0.296, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:46:19", "remaining_time": "4:38:39"}
+{"current_steps": 287, "total_steps": 390, "loss": 0.2985, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "12:49:12", "remaining_time": "4:36:03"}
+{"current_steps": 288, "total_steps": 390, "loss": 0.3019, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "12:52:02", "remaining_time": "4:33:25"}
+{"current_steps": 289, "total_steps": 390, "loss": 0.2933, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "12:54:42", "remaining_time": "4:30:44"}
+{"current_steps": 290, "total_steps": 390, "loss": 0.3022, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "12:57:34", "remaining_time": "4:28:07"}
+{"current_steps": 291, "total_steps": 390, "loss": 0.2992, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "13:00:04", "remaining_time": "4:25:23"}
+{"current_steps": 292, "total_steps": 390, "loss": 0.2966, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "13:02:52", "remaining_time": "4:22:44"}
+{"current_steps": 293, "total_steps": 390, "loss": 0.2998, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "13:05:31", "remaining_time": "4:20:03"}
+{"current_steps": 294, "total_steps": 390, "loss": 0.2922, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:08:16", "remaining_time": "4:17:23"}
+{"current_steps": 295, "total_steps": 390, "loss": 0.3114, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:11:12", "remaining_time": "4:14:47"}
+{"current_steps": 296, "total_steps": 390, "loss": 0.3029, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:13:45", "remaining_time": "4:12:04"}
+{"current_steps": 297, "total_steps": 390, "loss": 0.3044, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:16:30", "remaining_time": "4:09:24"}
+{"current_steps": 298, "total_steps": 390, "loss": 0.2983, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:18:59", "remaining_time": "4:06:40"}
+{"current_steps": 299, "total_steps": 390, "loss": 0.3004, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:21:35", "remaining_time": "4:03:57"}
+{"current_steps": 300, "total_steps": 390, "loss": 0.2919, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:24:19", "remaining_time": "4:01:17"}
+{"current_steps": 301, "total_steps": 390, "loss": 0.3015, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:27:04", "remaining_time": "3:58:38"}
+{"current_steps": 302, "total_steps": 390, "loss": 0.2981, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:29:46", "remaining_time": "3:55:57"}
+{"current_steps": 303, "total_steps": 390, "loss": 0.3008, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:32:13", "remaining_time": "3:53:12"}
+{"current_steps": 304, "total_steps": 390, "loss": 0.3052, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:34:50", "remaining_time": "3:50:30"}
+{"current_steps": 305, "total_steps": 390, "loss": 0.2981, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:37:30", "remaining_time": "3:47:49"}
+{"current_steps": 306, "total_steps": 390, "loss": 0.3002, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:40:12", "remaining_time": "3:45:09"}
+{"current_steps": 307, "total_steps": 390, "loss": 0.2925, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:42:52", "remaining_time": "3:42:28"}
+{"current_steps": 308, "total_steps": 390, "loss": 0.2959, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:45:36", "remaining_time": "3:39:48"}
+{"current_steps": 309, "total_steps": 390, "loss": 0.2933, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "13:48:10", "remaining_time": "3:37:05"}
+{"current_steps": 310, "total_steps": 390, "loss": 0.3002, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "13:50:41", "remaining_time": "3:34:22"}
+{"current_steps": 311, "total_steps": 390, "loss": 0.2938, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:53:22", "remaining_time": "3:31:41"}
+{"current_steps": 312, "total_steps": 390, "loss": 0.3017, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:56:08", "remaining_time": "3:29:02"}
+{"current_steps": 313, "total_steps": 390, "loss": 0.2866, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:59:32", "remaining_time": "3:26:31"}