Training in progress, epoch 4

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74b25e5b29f284ed71f23860444119f913e82949b0dc812f24da3ee3b86e37de
+oid sha256:c81bb22de01143e017ace4c8d43fee96eaa5123be1dbd2b6f52384c1074097d2
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e6531ba6ed948fdde99be92554613a652818dfec78d99a72ac1aec444287ab
+oid sha256:073ae97440720c946e5ad6c9440e5002fbdfc813001771eb222dd8f0d86314a8
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f673db7ab2b300ddbeb86777657c3e5b44aed2eb8e424ad3f411cc40558a7cf7
+oid sha256:d73fa91cadf3c47185227bb6155a4262a8c665dd862a1fb4e8031e917a0f6b85
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f86956297be90e0faf7583749f3e00be897a293098d6a5eb9aa62f2c446db2
+oid sha256:5701f8eff67371d7d8f7a77480b49132de204c9ae7e77f0c38423c136de36faf
 size 1089994880

trainer_log.jsonl

@@ -314,3 +314,78 @@
 {"current_steps": 314, "total_steps": 390, "loss": 0.394, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "4:02:52", "remaining_time": "0:58:47"}
 {"current_steps": 315, "total_steps": 390, "loss": 0.3843, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "4:03:36", "remaining_time": "0:58:00"}
 {"current_steps": 316, "total_steps": 390, "loss": 0.3924, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "4:04:20", "remaining_time": "0:57:13"}
+{"current_steps": 317, "total_steps": 390, "loss": 0.3921, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "4:05:06", "remaining_time": "0:56:26"}
+{"current_steps": 318, "total_steps": 390, "loss": 0.3724, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "4:05:51", "remaining_time": "0:55:39"}
+{"current_steps": 319, "total_steps": 390, "loss": 0.3721, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "4:06:35", "remaining_time": "0:54:53"}
+{"current_steps": 320, "total_steps": 390, "loss": 0.383, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "4:07:19", "remaining_time": "0:54:06"}
+{"current_steps": 321, "total_steps": 390, "loss": 0.3851, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "4:08:05", "remaining_time": "0:53:19"}
+{"current_steps": 322, "total_steps": 390, "loss": 0.3762, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "4:08:49", "remaining_time": "0:52:32"}
+{"current_steps": 323, "total_steps": 390, "loss": 0.3727, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "4:09:34", "remaining_time": "0:51:46"}
+{"current_steps": 324, "total_steps": 390, "loss": 0.384, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "4:10:20", "remaining_time": "0:50:59"}
+{"current_steps": 325, "total_steps": 390, "loss": 0.3945, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "4:11:04", "remaining_time": "0:50:12"}
+{"current_steps": 326, "total_steps": 390, "loss": 0.3529, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "4:11:49", "remaining_time": "0:49:26"}
+{"current_steps": 327, "total_steps": 390, "loss": 0.3759, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "4:12:31", "remaining_time": "0:48:39"}
+{"current_steps": 328, "total_steps": 390, "loss": 0.4087, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "4:13:17", "remaining_time": "0:47:52"}
+{"current_steps": 329, "total_steps": 390, "loss": 0.3923, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "4:14:02", "remaining_time": "0:47:06"}
+{"current_steps": 330, "total_steps": 390, "loss": 0.382, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "4:14:47", "remaining_time": "0:46:19"}
+{"current_steps": 331, "total_steps": 390, "loss": 0.3852, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "4:15:34", "remaining_time": "0:45:33"}
+{"current_steps": 332, "total_steps": 390, "loss": 0.3727, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "4:16:18", "remaining_time": "0:44:46"}
+{"current_steps": 333, "total_steps": 390, "loss": 0.381, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "4:17:03", "remaining_time": "0:44:00"}
+{"current_steps": 334, "total_steps": 390, "loss": 0.3782, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "4:17:49", "remaining_time": "0:43:13"}
+{"current_steps": 335, "total_steps": 390, "loss": 0.3659, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "4:18:34", "remaining_time": "0:42:27"}
+{"current_steps": 336, "total_steps": 390, "loss": 0.3651, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "4:19:19", "remaining_time": "0:41:40"}
+{"current_steps": 337, "total_steps": 390, "loss": 0.3783, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "4:20:05", "remaining_time": "0:40:54"}
+{"current_steps": 338, "total_steps": 390, "loss": 0.3778, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "4:20:51", "remaining_time": "0:40:07"}
+{"current_steps": 339, "total_steps": 390, "loss": 0.3767, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "4:21:37", "remaining_time": "0:39:21"}
+{"current_steps": 340, "total_steps": 390, "loss": 0.3985, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "4:22:21", "remaining_time": "0:38:34"}
+{"current_steps": 341, "total_steps": 390, "loss": 0.3703, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "4:23:08", "remaining_time": "0:37:48"}
+{"current_steps": 342, "total_steps": 390, "loss": 0.3867, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "4:23:51", "remaining_time": "0:37:02"}
+{"current_steps": 343, "total_steps": 390, "loss": 0.3839, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "4:24:35", "remaining_time": "0:36:15"}
+{"current_steps": 344, "total_steps": 390, "loss": 0.3825, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "4:25:19", "remaining_time": "0:35:28"}
+{"current_steps": 345, "total_steps": 390, "loss": 0.3757, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "4:26:05", "remaining_time": "0:34:42"}
+{"current_steps": 346, "total_steps": 390, "loss": 0.3808, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "4:26:50", "remaining_time": "0:33:56"}
+{"current_steps": 347, "total_steps": 390, "loss": 0.3922, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "4:27:36", "remaining_time": "0:33:09"}
+{"current_steps": 348, "total_steps": 390, "loss": 0.3889, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "4:28:21", "remaining_time": "0:32:23"}
+{"current_steps": 349, "total_steps": 390, "loss": 0.3701, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "4:29:06", "remaining_time": "0:31:36"}
+{"current_steps": 350, "total_steps": 390, "loss": 0.3891, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "4:29:49", "remaining_time": "0:30:50"}
+{"current_steps": 351, "total_steps": 390, "loss": 0.39, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "4:30:35", "remaining_time": "0:30:03"}
+{"current_steps": 352, "total_steps": 390, "loss": 0.3889, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "4:31:19", "remaining_time": "0:29:17"}
+{"current_steps": 353, "total_steps": 390, "loss": 0.398, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "4:32:01", "remaining_time": "0:28:30"}
+{"current_steps": 354, "total_steps": 390, "loss": 0.3764, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "4:32:47", "remaining_time": "0:27:44"}
+{"current_steps": 355, "total_steps": 390, "loss": 0.3796, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "4:33:31", "remaining_time": "0:26:58"}
+{"current_steps": 356, "total_steps": 390, "loss": 0.391, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "4:34:15", "remaining_time": "0:26:11"}
+{"current_steps": 357, "total_steps": 390, "loss": 0.3785, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "4:35:00", "remaining_time": "0:25:25"}
+{"current_steps": 358, "total_steps": 390, "loss": 0.384, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "4:35:45", "remaining_time": "0:24:38"}
+{"current_steps": 359, "total_steps": 390, "loss": 0.3839, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "4:36:29", "remaining_time": "0:23:52"}
+{"current_steps": 360, "total_steps": 390, "loss": 0.3926, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "4:37:16", "remaining_time": "0:23:06"}
+{"current_steps": 361, "total_steps": 390, "loss": 0.3906, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "4:37:59", "remaining_time": "0:22:19"}
+{"current_steps": 362, "total_steps": 390, "loss": 0.3807, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "4:38:44", "remaining_time": "0:21:33"}
+{"current_steps": 363, "total_steps": 390, "loss": 0.3775, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "4:39:29", "remaining_time": "0:20:47"}
+{"current_steps": 364, "total_steps": 390, "loss": 0.3954, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "4:40:14", "remaining_time": "0:20:01"}
+{"current_steps": 365, "total_steps": 390, "loss": 0.3671, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "4:40:58", "remaining_time": "0:19:14"}
+{"current_steps": 366, "total_steps": 390, "loss": 0.3819, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "4:41:44", "remaining_time": "0:18:28"}
+{"current_steps": 367, "total_steps": 390, "loss": 0.3699, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "4:42:30", "remaining_time": "0:17:42"}
+{"current_steps": 368, "total_steps": 390, "loss": 0.3806, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "4:43:13", "remaining_time": "0:16:55"}
+{"current_steps": 369, "total_steps": 390, "loss": 0.3777, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "4:43:58", "remaining_time": "0:16:09"}
+{"current_steps": 370, "total_steps": 390, "loss": 0.3895, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "4:44:44", "remaining_time": "0:15:23"}
+{"current_steps": 371, "total_steps": 390, "loss": 0.3928, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "4:45:29", "remaining_time": "0:14:37"}
+{"current_steps": 372, "total_steps": 390, "loss": 0.3742, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "4:46:14", "remaining_time": "0:13:51"}
+{"current_steps": 373, "total_steps": 390, "loss": 0.3863, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "4:46:59", "remaining_time": "0:13:04"}
+{"current_steps": 374, "total_steps": 390, "loss": 0.3994, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "4:47:45", "remaining_time": "0:12:18"}
+{"current_steps": 375, "total_steps": 390, "loss": 0.3873, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "4:48:30", "remaining_time": "0:11:32"}
+{"current_steps": 376, "total_steps": 390, "loss": 0.3963, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "4:49:16", "remaining_time": "0:10:46"}
+{"current_steps": 377, "total_steps": 390, "loss": 0.3778, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "4:50:03", "remaining_time": "0:10:00"}
+{"current_steps": 378, "total_steps": 390, "loss": 0.395, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "4:50:47", "remaining_time": "0:09:13"}
+{"current_steps": 379, "total_steps": 390, "loss": 0.3836, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "4:51:31", "remaining_time": "0:08:27"}
+{"current_steps": 380, "total_steps": 390, "loss": 0.3828, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "4:52:17", "remaining_time": "0:07:41"}
+{"current_steps": 381, "total_steps": 390, "loss": 0.3794, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "4:53:03", "remaining_time": "0:06:55"}
+{"current_steps": 382, "total_steps": 390, "loss": 0.3728, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "4:53:49", "remaining_time": "0:06:09"}
+{"current_steps": 383, "total_steps": 390, "loss": 0.3876, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "4:54:34", "remaining_time": "0:05:23"}
+{"current_steps": 384, "total_steps": 390, "loss": 0.3873, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "4:55:19", "remaining_time": "0:04:36"}
+{"current_steps": 385, "total_steps": 390, "loss": 0.3724, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "4:56:04", "remaining_time": "0:03:50"}
+{"current_steps": 386, "total_steps": 390, "loss": 0.3618, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "4:56:49", "remaining_time": "0:03:04"}
+{"current_steps": 387, "total_steps": 390, "loss": 0.3838, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "4:57:34", "remaining_time": "0:02:18"}
+{"current_steps": 388, "total_steps": 390, "loss": 0.3786, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "4:58:19", "remaining_time": "0:01:32"}
+{"current_steps": 389, "total_steps": 390, "loss": 0.3673, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "4:59:04", "remaining_time": "0:00:46"}
+{"current_steps": 390, "total_steps": 390, "loss": 0.384, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "4:59:46", "remaining_time": "0:00:00"}
+{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "5:03:10", "remaining_time": "0:00:00"}