Training in progress, epoch 2

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc78bc39a06b0ce29e356430ea6d2da6390337fb5a51807efee7c3e33f2ba82
+oid sha256:011c075800c4c0b7befe99425856dafc9820566c17307e20b95c846aad608d71
 size 4891730992

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc55e36e1c4d4c1254b59acb5ef74a41dce8eeb4a90000c3f6a082fdab2631e
+oid sha256:0557067ccc5d67c91c4fbdb3a3d77ebfa432499184bd5e8ad16489b8a75a10a9
 size 4876059352

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31469160589b44186fdc5cd79b30ded16af8cab552d36e8e21cb7cc416ff1c19
+oid sha256:bd0b42bb2de0a780514470bf53c5a4f68606382126b8ef1b9e1798eccb3cf9ba
 size 4876059384

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c83a57b2b727f50055e850616baec5f5032bb0441541364e01deac677178d1
+oid sha256:8d64ac05d11039058d737e54b3fcc5818e4f41cdfed737583372f72161a26bc8
 size 4876059416

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeba17dc8dbd4f47ce62205c106612f2855a8831f317e8c45c7e89bd7e284a9a
+oid sha256:f5b07482d4d399629cd5142ea466436c746e74157d56c47bcb3aff69bb5393d8
 size 4876059416

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254055d98cb6269a356b93105471642ec5c3356d5780c9d2de88237d48bfa58b
+oid sha256:945075fd0edc359357a71b54dffa71b5c6ec1a58ccf45ee13bcdd138991dce5c
 size 4876059416

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ca2f3bb29dd445173578f050323f4330b835fa064eead60de51d9d7e44d94d
+oid sha256:f938bcf2991396e3130a046772029a9bce85b6fd4e50935b2954b8a3450d5fb3
 size 4876059416

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c02f0cd42fb8cd592a9cc582c204bd47e215b9559f538c2f8d4f37331f79ef7b
+oid sha256:6fd0ca8640c6d2d110358cefe5ee215598e7ca2c8de14b799f4dca67c3878ee5
 size 4876059416

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc0aa21c7206451ddc70ab4acade4f484cd8ae6aa05b32e958a115c241ebf3d
+oid sha256:246f9fcec00aebffd0da0847a7385dc7d3a8992adaa6c06290ccd72e2d0b4dde
 size 4876059416

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b22336555eb183b3db2a7eff3ed111a7b84b0307b2165a5e161ca091c7c2fe2e
+oid sha256:de92076bfd161bb54d50f69b81104296405b10291f4f1614c1999da17eac6938
 size 4876059416

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:255519e4ee80c1a5d314c2c1dfaa00b206cb7a00395af542c1a7ab8a49dbad29
+oid sha256:f771bf9b5974facf151b806d334c12776068a76f71e0547cbdd55c6292aaf156
 size 4876059416

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68df3f458b168ee9846be2e1ad2bec747f8860b110a562699ac4446b8739e7b3
+oid sha256:85d3ffad64f7bc677618108cf0844f96ba34f6e7e515cbace6b9bb6a6a7acb7f
 size 4876059416

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84066bde0f94e0764d7d1ad85e126ada855b0f084f378a3e9e7a62dbbb15d895
+oid sha256:c8a9a3e5738f8f69c5111e44f9708e84ed0143bbed046d20983d9f48067e593d
 size 4876059416

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741dfba9d3d8eefc7bef9bd596d518eff73ac9f62076c25e68fc3824e2f92245
+oid sha256:564af1c2ce4b91d28bbd3d6bb919fe686fc06a39168b244830790d634fd4c5e4
 size 2123397800

trainer_log.jsonl

@@ -100,3 +100,69 @@
 {"current_steps": 100, "total_steps": 315, "loss": 0.0964, "lr": 8.175772078190706e-06, "epoch": 1.5873015873015874, "percentage": 31.75, "elapsed_time": "0:24:20", "remaining_time": "0:52:19"}
 {"current_steps": 101, "total_steps": 315, "loss": 0.1436, "lr": 8.135020277480933e-06, "epoch": 1.6031746031746033, "percentage": 32.06, "elapsed_time": "0:24:32", "remaining_time": "0:52:00"}
 {"current_steps": 102, "total_steps": 315, "loss": 0.1875, "lr": 8.093922383044293e-06, "epoch": 1.619047619047619, "percentage": 32.38, "elapsed_time": "0:24:44", "remaining_time": "0:51:40"}
+{"current_steps": 103, "total_steps": 315, "loss": 0.1381, "lr": 8.052482931924307e-06, "epoch": 1.6349206349206349, "percentage": 32.7, "elapsed_time": "0:24:57", "remaining_time": "0:51:21"}
+{"current_steps": 104, "total_steps": 315, "loss": 0.1783, "lr": 8.010706498870997e-06, "epoch": 1.6507936507936507, "percentage": 33.02, "elapsed_time": "0:25:09", "remaining_time": "0:51:02"}
+{"current_steps": 105, "total_steps": 315, "loss": 0.1491, "lr": 7.968597695835845e-06, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "0:25:21", "remaining_time": "0:50:43"}
+{"current_steps": 106, "total_steps": 315, "loss": 0.1216, "lr": 7.926161171462647e-06, "epoch": 1.6825396825396826, "percentage": 33.65, "elapsed_time": "0:25:33", "remaining_time": "0:50:24"}
+{"current_steps": 107, "total_steps": 315, "loss": 0.1496, "lr": 7.883401610574338e-06, "epoch": 1.6984126984126984, "percentage": 33.97, "elapsed_time": "0:25:46", "remaining_time": "0:50:05"}
+{"current_steps": 108, "total_steps": 315, "loss": 0.1509, "lr": 7.84032373365578e-06, "epoch": 1.7142857142857144, "percentage": 34.29, "elapsed_time": "0:25:58", "remaining_time": "0:49:46"}
+{"current_steps": 109, "total_steps": 315, "loss": 0.16, "lr": 7.796932296332666e-06, "epoch": 1.7301587301587302, "percentage": 34.6, "elapsed_time": "0:26:10", "remaining_time": "0:49:28"}
+{"current_steps": 110, "total_steps": 315, "loss": 0.0972, "lr": 7.753232088846505e-06, "epoch": 1.746031746031746, "percentage": 34.92, "elapsed_time": "0:26:22", "remaining_time": "0:49:09"}
+{"current_steps": 111, "total_steps": 315, "loss": 0.1837, "lr": 7.709227935525796e-06, "epoch": 1.7619047619047619, "percentage": 35.24, "elapsed_time": "0:26:35", "remaining_time": "0:48:51"}
+{"current_steps": 112, "total_steps": 315, "loss": 0.1472, "lr": 7.664924694253444e-06, "epoch": 1.7777777777777777, "percentage": 35.56, "elapsed_time": "0:26:47", "remaining_time": "0:48:33"}
+{"current_steps": 113, "total_steps": 315, "loss": 0.123, "lr": 7.620327255930475e-06, "epoch": 1.7936507936507935, "percentage": 35.87, "elapsed_time": "0:26:59", "remaining_time": "0:48:15"}
+{"current_steps": 114, "total_steps": 315, "loss": 0.1329, "lr": 7.575440543936092e-06, "epoch": 1.8095238095238095, "percentage": 36.19, "elapsed_time": "0:27:11", "remaining_time": "0:47:57"}
+{"current_steps": 115, "total_steps": 315, "loss": 0.1268, "lr": 7.530269513584158e-06, "epoch": 1.8253968253968254, "percentage": 36.51, "elapsed_time": "0:27:24", "remaining_time": "0:47:39"}
+{"current_steps": 116, "total_steps": 315, "loss": 0.128, "lr": 7.484819151576148e-06, "epoch": 1.8412698412698414, "percentage": 36.83, "elapsed_time": "0:27:36", "remaining_time": "0:47:21"}
+{"current_steps": 117, "total_steps": 315, "loss": 0.1732, "lr": 7.439094475450638e-06, "epoch": 1.8571428571428572, "percentage": 37.14, "elapsed_time": "0:27:48", "remaining_time": "0:47:03"}
+{"current_steps": 118, "total_steps": 315, "loss": 0.1608, "lr": 7.393100533029383e-06, "epoch": 1.873015873015873, "percentage": 37.46, "elapsed_time": "0:28:00", "remaining_time": "0:46:46"}
+{"current_steps": 119, "total_steps": 315, "loss": 0.1534, "lr": 7.346842401860069e-06, "epoch": 1.8888888888888888, "percentage": 37.78, "elapsed_time": "0:28:13", "remaining_time": "0:46:28"}
+{"current_steps": 120, "total_steps": 315, "loss": 0.1705, "lr": 7.300325188655762e-06, "epoch": 1.9047619047619047, "percentage": 38.1, "elapsed_time": "0:28:25", "remaining_time": "0:46:11"}
+{"current_steps": 121, "total_steps": 315, "loss": 0.1453, "lr": 7.253554028731149e-06, "epoch": 1.9206349206349205, "percentage": 38.41, "elapsed_time": "0:28:37", "remaining_time": "0:45:54"}
+{"current_steps": 122, "total_steps": 315, "loss": 0.2008, "lr": 7.206534085435626e-06, "epoch": 1.9365079365079365, "percentage": 38.73, "elapsed_time": "0:28:50", "remaining_time": "0:45:36"}
+{"current_steps": 123, "total_steps": 315, "loss": 0.1793, "lr": 7.159270549583278e-06, "epoch": 1.9523809523809523, "percentage": 39.05, "elapsed_time": "0:29:02", "remaining_time": "0:45:19"}
+{"current_steps": 124, "total_steps": 315, "loss": 0.1783, "lr": 7.111768638879834e-06, "epoch": 1.9682539682539684, "percentage": 39.37, "elapsed_time": "0:29:14", "remaining_time": "0:45:02"}
+{"current_steps": 125, "total_steps": 315, "loss": 0.1472, "lr": 7.064033597346658e-06, "epoch": 1.9841269841269842, "percentage": 39.68, "elapsed_time": "0:29:27", "remaining_time": "0:44:45"}
+{"current_steps": 126, "total_steps": 315, "loss": 0.0907, "lr": 7.016070694741824e-06, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:29:39", "remaining_time": "0:44:28"}
+{"current_steps": 127, "total_steps": 315, "loss": 0.0541, "lr": 6.967885225978366e-06, "epoch": 2.015873015873016, "percentage": 40.32, "elapsed_time": "0:33:57", "remaining_time": "0:50:16"}
+{"current_steps": 128, "total_steps": 315, "loss": 0.0553, "lr": 6.919482510539723e-06, "epoch": 2.0317460317460316, "percentage": 40.63, "elapsed_time": "0:34:09", "remaining_time": "0:49:54"}
+{"current_steps": 129, "total_steps": 315, "loss": 0.0539, "lr": 6.870867891892511e-06, "epoch": 2.0476190476190474, "percentage": 40.95, "elapsed_time": "0:34:22", "remaining_time": "0:49:33"}
+{"current_steps": 130, "total_steps": 315, "loss": 0.0446, "lr": 6.822046736896607e-06, "epoch": 2.0634920634920633, "percentage": 41.27, "elapsed_time": "0:34:34", "remaining_time": "0:49:11"}
+{"current_steps": 131, "total_steps": 315, "loss": 0.0474, "lr": 6.773024435212678e-06, "epoch": 2.0793650793650795, "percentage": 41.59, "elapsed_time": "0:34:46", "remaining_time": "0:48:50"}
+{"current_steps": 132, "total_steps": 315, "loss": 0.0472, "lr": 6.723806398707186e-06, "epoch": 2.0952380952380953, "percentage": 41.9, "elapsed_time": "0:34:58", "remaining_time": "0:48:29"}
+{"current_steps": 133, "total_steps": 315, "loss": 0.042, "lr": 6.674398060854931e-06, "epoch": 2.111111111111111, "percentage": 42.22, "elapsed_time": "0:35:11", "remaining_time": "0:48:09"}
+{"current_steps": 134, "total_steps": 315, "loss": 0.0647, "lr": 6.624804876139227e-06, "epoch": 2.126984126984127, "percentage": 42.54, "elapsed_time": "0:35:23", "remaining_time": "0:47:48"}
+{"current_steps": 135, "total_steps": 315, "loss": 0.0559, "lr": 6.57503231944974e-06, "epoch": 2.142857142857143, "percentage": 42.86, "elapsed_time": "0:35:36", "remaining_time": "0:47:28"}
+{"current_steps": 136, "total_steps": 315, "loss": 0.0482, "lr": 6.525085885478088e-06, "epoch": 2.1587301587301586, "percentage": 43.17, "elapsed_time": "0:35:49", "remaining_time": "0:47:08"}
+{"current_steps": 137, "total_steps": 315, "loss": 0.0599, "lr": 6.4749710881112485e-06, "epoch": 2.1746031746031744, "percentage": 43.49, "elapsed_time": "0:36:01", "remaining_time": "0:46:48"}
+{"current_steps": 138, "total_steps": 315, "loss": 0.0642, "lr": 6.424693459822843e-06, "epoch": 2.1904761904761907, "percentage": 43.81, "elapsed_time": "0:36:14", "remaining_time": "0:46:29"}
+{"current_steps": 139, "total_steps": 315, "loss": 0.0514, "lr": 6.374258551062377e-06, "epoch": 2.2063492063492065, "percentage": 44.13, "elapsed_time": "0:36:27", "remaining_time": "0:46:09"}
+{"current_steps": 140, "total_steps": 315, "loss": 0.0464, "lr": 6.3236719296424985e-06, "epoch": 2.2222222222222223, "percentage": 44.44, "elapsed_time": "0:36:40", "remaining_time": "0:45:51"}
+{"current_steps": 141, "total_steps": 315, "loss": 0.0407, "lr": 6.272939180124316e-06, "epoch": 2.238095238095238, "percentage": 44.76, "elapsed_time": "0:36:53", "remaining_time": "0:45:31"}
+{"current_steps": 142, "total_steps": 315, "loss": 0.0487, "lr": 6.222065903200909e-06, "epoch": 2.253968253968254, "percentage": 45.08, "elapsed_time": "0:37:05", "remaining_time": "0:45:11"}
+{"current_steps": 143, "total_steps": 315, "loss": 0.0568, "lr": 6.171057715079012e-06, "epoch": 2.2698412698412698, "percentage": 45.4, "elapsed_time": "0:37:18", "remaining_time": "0:44:52"}
+{"current_steps": 144, "total_steps": 315, "loss": 0.0363, "lr": 6.119920246859025e-06, "epoch": 2.2857142857142856, "percentage": 45.71, "elapsed_time": "0:37:30", "remaining_time": "0:44:32"}
+{"current_steps": 145, "total_steps": 315, "loss": 0.0303, "lr": 6.068659143913349e-06, "epoch": 2.3015873015873014, "percentage": 46.03, "elapsed_time": "0:37:43", "remaining_time": "0:44:13"}
+{"current_steps": 146, "total_steps": 315, "loss": 0.074, "lr": 6.0172800652631706e-06, "epoch": 2.317460317460317, "percentage": 46.35, "elapsed_time": "0:37:55", "remaining_time": "0:43:53"}
+{"current_steps": 147, "total_steps": 315, "loss": 0.047, "lr": 5.965788682953717e-06, "epoch": 2.3333333333333335, "percentage": 46.67, "elapsed_time": "0:38:07", "remaining_time": "0:43:34"}
+{"current_steps": 148, "total_steps": 315, "loss": 0.0354, "lr": 5.914190681428098e-06, "epoch": 2.3492063492063493, "percentage": 46.98, "elapsed_time": "0:38:20", "remaining_time": "0:43:15"}
+{"current_steps": 149, "total_steps": 315, "loss": 0.0605, "lr": 5.862491756899753e-06, "epoch": 2.365079365079365, "percentage": 47.3, "elapsed_time": "0:38:32", "remaining_time": "0:42:56"}
+{"current_steps": 150, "total_steps": 315, "loss": 0.0443, "lr": 5.8106976167236236e-06, "epoch": 2.380952380952381, "percentage": 47.62, "elapsed_time": "0:38:45", "remaining_time": "0:42:37"}
+{"current_steps": 151, "total_steps": 315, "loss": 0.0554, "lr": 5.758813978766077e-06, "epoch": 2.3968253968253967, "percentage": 47.94, "elapsed_time": "0:38:57", "remaining_time": "0:42:18"}
+{"current_steps": 152, "total_steps": 315, "loss": 0.0629, "lr": 5.706846570773677e-06, "epoch": 2.4126984126984126, "percentage": 48.25, "elapsed_time": "0:39:10", "remaining_time": "0:42:00"}
+{"current_steps": 153, "total_steps": 315, "loss": 0.0395, "lr": 5.654801129740863e-06, "epoch": 2.4285714285714284, "percentage": 48.57, "elapsed_time": "0:39:23", "remaining_time": "0:41:42"}
+{"current_steps": 154, "total_steps": 315, "loss": 0.0517, "lr": 5.6026834012766155e-06, "epoch": 2.4444444444444446, "percentage": 48.89, "elapsed_time": "0:39:36", "remaining_time": "0:41:24"}
+{"current_steps": 155, "total_steps": 315, "loss": 0.0416, "lr": 5.550499138970158e-06, "epoch": 2.4603174603174605, "percentage": 49.21, "elapsed_time": "0:39:49", "remaining_time": "0:41:06"}
+{"current_steps": 156, "total_steps": 315, "loss": 0.0416, "lr": 5.4982541037557825e-06, "epoch": 2.4761904761904763, "percentage": 49.52, "elapsed_time": "0:40:01", "remaining_time": "0:40:47"}
+{"current_steps": 157, "total_steps": 315, "loss": 0.0499, "lr": 5.44595406327687e-06, "epoch": 2.492063492063492, "percentage": 49.84, "elapsed_time": "0:40:13", "remaining_time": "0:40:29"}
+{"current_steps": 158, "total_steps": 315, "loss": 0.0617, "lr": 5.393604791249158e-06, "epoch": 2.507936507936508, "percentage": 50.16, "elapsed_time": "0:40:25", "remaining_time": "0:40:10"}
+{"current_steps": 159, "total_steps": 315, "loss": 0.0341, "lr": 5.341212066823356e-06, "epoch": 2.5238095238095237, "percentage": 50.48, "elapsed_time": "0:40:38", "remaining_time": "0:39:52"}
+{"current_steps": 160, "total_steps": 315, "loss": 0.0818, "lr": 5.288781673947143e-06, "epoch": 2.5396825396825395, "percentage": 50.79, "elapsed_time": "0:40:50", "remaining_time": "0:39:33"}
+{"current_steps": 161, "total_steps": 315, "loss": 0.0533, "lr": 5.2363194007266435e-06, "epoch": 2.5555555555555554, "percentage": 51.11, "elapsed_time": "0:41:02", "remaining_time": "0:39:15"}
+{"current_steps": 162, "total_steps": 315, "loss": 0.0308, "lr": 5.183831038787449e-06, "epoch": 2.571428571428571, "percentage": 51.43, "elapsed_time": "0:41:14", "remaining_time": "0:38:57"}
+{"current_steps": 163, "total_steps": 315, "loss": 0.0393, "lr": 5.131322382635236e-06, "epoch": 2.5873015873015874, "percentage": 51.75, "elapsed_time": "0:41:26", "remaining_time": "0:38:38"}
+{"current_steps": 164, "total_steps": 315, "loss": 0.0379, "lr": 5.078799229016083e-06, "epoch": 2.6031746031746033, "percentage": 52.06, "elapsed_time": "0:41:38", "remaining_time": "0:38:20"}
+{"current_steps": 165, "total_steps": 315, "loss": 0.042, "lr": 5.0262673762765316e-06, "epoch": 2.619047619047619, "percentage": 52.38, "elapsed_time": "0:41:50", "remaining_time": "0:38:02"}
+{"current_steps": 166, "total_steps": 315, "loss": 0.0494, "lr": 4.973732623723471e-06, "epoch": 2.634920634920635, "percentage": 52.7, "elapsed_time": "0:42:03", "remaining_time": "0:37:44"}
+{"current_steps": 167, "total_steps": 315, "loss": 0.0364, "lr": 4.921200770983919e-06, "epoch": 2.6507936507936507, "percentage": 53.02, "elapsed_time": "0:42:15", "remaining_time": "0:37:26"}
+{"current_steps": 168, "total_steps": 315, "loss": 0.0554, "lr": 4.8686776173647655e-06, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "0:42:27", "remaining_time": "0:37:08"}