Training in progress, epoch 2

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd258e6a0570d6dd607347d69b39f1926cac2bc4513aa3014a3d035165e8567
+oid sha256:4741f7e789cbe835ca5afd15db6e5b962c55615daf6b4c9ebcb3a9179593c3ca
 size 4891730992

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2bdda09d0eeb7368f24226062794c3c8dfefc5574381e021175b64eed9149cd
+oid sha256:636c0d6d1c1ca0e93e048dcf9dae2a0bc210be51a1a22a7999903ca254d69ff2
 size 4876059352

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afa6697f480f789496a74e735b88d3633e2d21d176358b6ebbd97e602bf9818
+oid sha256:771abf431c41751f47a76fffe3c2aaaba1984f98ef6a9d8eacc0eb68d40ad1db
 size 4876059384

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd4ab45e97800a652e9a3ef54b94b760a1eee000d73d400052a20a7f4e83ca8
+oid sha256:84c13970f1431cfbd9ce6b14e1ce4e12e40eeb71777c3c26a61963e1df2876d4
 size 4876059416

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cdc7e84f7642e235c9d4423434da549f7aba4527ad4067a45c650b19feb466d
+oid sha256:fad9b29536808b8ff32ec5cd3bb06c2eb3cf80d12380dd358e5c251cf76099e1
 size 4876059416

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8c93c733e7013528b43aac6e9ce53a2e257f72c8959294f68a54ef55b738b7
+oid sha256:d43232873b47fb3a984f4b6bc75a3894edc039326cb8f0009dbd64d086192469
 size 4876059416

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bfdd5a8fe6349a28d630ddf812281ccbf1b9576c3b9cef00d1f24a48f7c08ca
+oid sha256:836ac301a2e83ec6c108aaece9e4cc9526c24a6d7babf9e28b19d12538a55c5e
 size 4876059416

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d73da6afcb07ff84632c6da57b115a8f3166009a6bf22e1e9b1bf81bf6781483
+oid sha256:2e66b9ced4e2db6b7f64d8809d46aa2644813b48e8df01662eb36d0e1e9c8570
 size 4876059416

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71582a484dec40ae132f93129f6c4d6ca9e6db3ebcba00583cff3a492519df15
+oid sha256:cdbb35ea74ffb5d45461e74bfd99239919194910a748458792b3b87d8afb8dce
 size 4876059416

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73dde4c66bb23abe068366ab3010342b3934003e877829d215bfbc8c3ec70a7
+oid sha256:3226df592c7c99b4e395ce9af5358d6b105d48a758a5990a8c4aa4d32269b354
 size 4876059416

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:395a5fd358568dca846bc223e2b3da7d14d9705123eb9a2b2bd6b9faff291996
+oid sha256:ea2d1abb15bfaa5325c584b16f73ea84da8b035c76af656c7d3ab9cfe540f707
 size 4876059416

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ed10f8e9d916180407dd1331293c106985740e7108ba2a037a06616290a498
+oid sha256:9e30fe19ec6aff4e03d68eb778aa957232542322c1f0ec3f93854f0e14945788
 size 4876059416

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae1e8d9886a3af62635e58daedfda83bc2afefa508e9e85353537e19523f594
+oid sha256:bf4db43150a3495621e5ba85a18c7b84e8dc9984dc04432cdc143d2d63a302a6
 size 4876059416

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a4051ff1107e8aff068053594100e78ca891b8ed4337c3f6b74fdf5e262cfa
+oid sha256:f1399acf53c0688d628995bfa59f8b32becce5f233e6c41ae54433f52ce7e3b7
 size 2123397800

trainer_log.jsonl

@@ -96,3 +96,75 @@
 {"current_steps": 96, "total_steps": 390, "loss": 0.3941, "lr": 3.745319917751229e-05, "epoch": 1.2229299363057324, "percentage": 24.62, "elapsed_time": "1:05:08", "remaining_time": "3:19:31"}
 {"current_steps": 97, "total_steps": 390, "loss": 0.3995, "lr": 3.736508651595188e-05, "epoch": 1.2356687898089171, "percentage": 24.87, "elapsed_time": "1:05:39", "remaining_time": "3:18:18"}
 {"current_steps": 98, "total_steps": 390, "loss": 0.4138, "lr": 3.727558275050301e-05, "epoch": 1.2484076433121019, "percentage": 25.13, "elapsed_time": "1:06:19", "remaining_time": "3:17:37"}
+{"current_steps": 99, "total_steps": 390, "loss": 0.385, "lr": 3.718469505124434e-05, "epoch": 1.2611464968152866, "percentage": 25.38, "elapsed_time": "1:06:51", "remaining_time": "3:16:31"}
+{"current_steps": 100, "total_steps": 390, "loss": 0.3757, "lr": 3.709243069912041e-05, "epoch": 1.2738853503184713, "percentage": 25.64, "elapsed_time": "1:07:12", "remaining_time": "3:14:53"}
+{"current_steps": 101, "total_steps": 390, "loss": 0.3774, "lr": 3.699879708535838e-05, "epoch": 1.286624203821656, "percentage": 25.9, "elapsed_time": "1:07:45", "remaining_time": "3:13:52"}
+{"current_steps": 102, "total_steps": 390, "loss": 0.4095, "lr": 3.69038017108759e-05, "epoch": 1.2993630573248407, "percentage": 26.15, "elapsed_time": "1:08:18", "remaining_time": "3:12:52"}
+{"current_steps": 103, "total_steps": 390, "loss": 0.4061, "lr": 3.680745218568026e-05, "epoch": 1.3121019108280254, "percentage": 26.41, "elapsed_time": "1:08:52", "remaining_time": "3:11:54"}
+{"current_steps": 104, "total_steps": 390, "loss": 0.3851, "lr": 3.6709756228258735e-05, "epoch": 1.3248407643312101, "percentage": 26.67, "elapsed_time": "1:09:24", "remaining_time": "3:10:51"}
+{"current_steps": 105, "total_steps": 390, "loss": 0.4005, "lr": 3.6610721664960236e-05, "epoch": 1.3375796178343948, "percentage": 26.92, "elapsed_time": "1:10:05", "remaining_time": "3:10:15"}
+{"current_steps": 106, "total_steps": 390, "loss": 0.3841, "lr": 3.65103564293684e-05, "epoch": 1.3503184713375795, "percentage": 27.18, "elapsed_time": "1:10:36", "remaining_time": "3:09:10"}
+{"current_steps": 107, "total_steps": 390, "loss": 0.3815, "lr": 3.640866856166601e-05, "epoch": 1.3630573248407643, "percentage": 27.44, "elapsed_time": "1:11:17", "remaining_time": "3:08:34"}
+{"current_steps": 108, "total_steps": 390, "loss": 0.4173, "lr": 3.6305666207990886e-05, "epoch": 1.3757961783439492, "percentage": 27.69, "elapsed_time": "1:11:58", "remaining_time": "3:07:56"}
+{"current_steps": 109, "total_steps": 390, "loss": 0.4035, "lr": 3.6201357619783336e-05, "epoch": 1.388535031847134, "percentage": 27.95, "elapsed_time": "1:12:39", "remaining_time": "3:07:17"}
+{"current_steps": 110, "total_steps": 390, "loss": 0.3795, "lr": 3.609575115312511e-05, "epoch": 1.4012738853503186, "percentage": 28.21, "elapsed_time": "1:13:12", "remaining_time": "3:06:20"}
+{"current_steps": 111, "total_steps": 390, "loss": 0.4079, "lr": 3.598885526807003e-05, "epoch": 1.4140127388535033, "percentage": 28.46, "elapsed_time": "1:13:45", "remaining_time": "3:05:24"}
+{"current_steps": 112, "total_steps": 390, "loss": 0.3843, "lr": 3.5880678527966224e-05, "epoch": 1.426751592356688, "percentage": 28.72, "elapsed_time": "1:14:28", "remaining_time": "3:04:51"}
+{"current_steps": 113, "total_steps": 390, "loss": 0.3774, "lr": 3.577122959877017e-05, "epoch": 1.4394904458598727, "percentage": 28.97, "elapsed_time": "1:15:04", "remaining_time": "3:04:00"}
+{"current_steps": 114, "total_steps": 390, "loss": 0.3724, "lr": 3.566051724835245e-05, "epoch": 1.4522292993630574, "percentage": 29.23, "elapsed_time": "1:15:41", "remaining_time": "3:03:14"}
+{"current_steps": 115, "total_steps": 390, "loss": 0.3908, "lr": 3.554855034579532e-05, "epoch": 1.4649681528662422, "percentage": 29.49, "elapsed_time": "1:16:08", "remaining_time": "3:02:05"}
+{"current_steps": 116, "total_steps": 390, "loss": 0.3966, "lr": 3.5435337860682304e-05, "epoch": 1.4777070063694269, "percentage": 29.74, "elapsed_time": "1:16:45", "remaining_time": "3:01:18"}
+{"current_steps": 117, "total_steps": 390, "loss": 0.3996, "lr": 3.532088886237956e-05, "epoch": 1.4904458598726116, "percentage": 30.0, "elapsed_time": "1:17:25", "remaining_time": "3:00:40"}
+{"current_steps": 118, "total_steps": 390, "loss": 0.4019, "lr": 3.520521251930941e-05, "epoch": 1.5031847133757963, "percentage": 30.26, "elapsed_time": "1:18:02", "remaining_time": "2:59:52"}
+{"current_steps": 119, "total_steps": 390, "loss": 0.3884, "lr": 3.5088318098215805e-05, "epoch": 1.515923566878981, "percentage": 30.51, "elapsed_time": "1:18:37", "remaining_time": "2:59:03"}
+{"current_steps": 120, "total_steps": 390, "loss": 0.3643, "lr": 3.497021496342203e-05, "epoch": 1.5286624203821657, "percentage": 30.77, "elapsed_time": "1:19:09", "remaining_time": "2:58:07"}
+{"current_steps": 121, "total_steps": 390, "loss": 0.3916, "lr": 3.485091257608047e-05, "epoch": 1.5414012738853504, "percentage": 31.03, "elapsed_time": "1:19:36", "remaining_time": "2:56:59"}
+{"current_steps": 122, "total_steps": 390, "loss": 0.3793, "lr": 3.473042049341474e-05, "epoch": 1.5541401273885351, "percentage": 31.28, "elapsed_time": "1:20:03", "remaining_time": "2:55:51"}
+{"current_steps": 123, "total_steps": 390, "loss": 0.4004, "lr": 3.4608748367954064e-05, "epoch": 1.5668789808917198, "percentage": 31.54, "elapsed_time": "1:20:41", "remaining_time": "2:55:09"}
+{"current_steps": 124, "total_steps": 390, "loss": 0.3724, "lr": 3.4485905946759965e-05, "epoch": 1.5796178343949046, "percentage": 31.79, "elapsed_time": "1:21:20", "remaining_time": "2:54:29"}
+{"current_steps": 125, "total_steps": 390, "loss": 0.3854, "lr": 3.4361903070645484e-05, "epoch": 1.5923566878980893, "percentage": 32.05, "elapsed_time": "1:21:46", "remaining_time": "2:53:22"}
+{"current_steps": 126, "total_steps": 390, "loss": 0.3833, "lr": 3.423674967338681e-05, "epoch": 1.605095541401274, "percentage": 32.31, "elapsed_time": "1:22:21", "remaining_time": "2:52:34"}
+{"current_steps": 127, "total_steps": 390, "loss": 0.3819, "lr": 3.411045578092754e-05, "epoch": 1.6178343949044587, "percentage": 32.56, "elapsed_time": "1:22:58", "remaining_time": "2:51:48"}
+{"current_steps": 128, "total_steps": 390, "loss": 0.3872, "lr": 3.398303151057543e-05, "epoch": 1.6305732484076434, "percentage": 32.82, "elapsed_time": "1:23:37", "remaining_time": "2:51:09"}
+{"current_steps": 129, "total_steps": 390, "loss": 0.3932, "lr": 3.385448707019199e-05, "epoch": 1.643312101910828, "percentage": 33.08, "elapsed_time": "1:24:11", "remaining_time": "2:50:19"}
+{"current_steps": 130, "total_steps": 390, "loss": 0.4039, "lr": 3.372483275737468e-05, "epoch": 1.6560509554140128, "percentage": 33.33, "elapsed_time": "1:24:44", "remaining_time": "2:49:28"}
+{"current_steps": 131, "total_steps": 390, "loss": 0.383, "lr": 3.359407895863199e-05, "epoch": 1.6687898089171975, "percentage": 33.59, "elapsed_time": "1:25:22", "remaining_time": "2:48:48"}
+{"current_steps": 132, "total_steps": 390, "loss": 0.3994, "lr": 3.34622361485514e-05, "epoch": 1.6815286624203822, "percentage": 33.85, "elapsed_time": "1:25:56", "remaining_time": "2:47:59"}
+{"current_steps": 133, "total_steps": 390, "loss": 0.4126, "lr": 3.332931488896029e-05, "epoch": 1.694267515923567, "percentage": 34.1, "elapsed_time": "1:26:29", "remaining_time": "2:47:07"}
+{"current_steps": 134, "total_steps": 390, "loss": 0.4027, "lr": 3.319532582807977e-05, "epoch": 1.7070063694267517, "percentage": 34.36, "elapsed_time": "1:27:11", "remaining_time": "2:46:35"}
+{"current_steps": 135, "total_steps": 390, "loss": 0.3989, "lr": 3.30602796996717e-05, "epoch": 1.7197452229299364, "percentage": 34.62, "elapsed_time": "1:27:52", "remaining_time": "2:45:59"}
+{"current_steps": 136, "total_steps": 390, "loss": 0.3875, "lr": 3.2924187322178865e-05, "epoch": 1.732484076433121, "percentage": 34.87, "elapsed_time": "1:28:29", "remaining_time": "2:45:15"}
+{"current_steps": 137, "total_steps": 390, "loss": 0.4068, "lr": 3.278705959785821e-05, "epoch": 1.7452229299363058, "percentage": 35.13, "elapsed_time": "1:29:06", "remaining_time": "2:44:33"}
+{"current_steps": 138, "total_steps": 390, "loss": 0.3906, "lr": 3.2648907511907544e-05, "epoch": 1.7579617834394905, "percentage": 35.38, "elapsed_time": "1:29:31", "remaining_time": "2:43:28"}
+{"current_steps": 139, "total_steps": 390, "loss": 0.3882, "lr": 3.250974213158555e-05, "epoch": 1.7707006369426752, "percentage": 35.64, "elapsed_time": "1:30:02", "remaining_time": "2:42:36"}
+{"current_steps": 140, "total_steps": 390, "loss": 0.3957, "lr": 3.23695746053251e-05, "epoch": 1.78343949044586, "percentage": 35.9, "elapsed_time": "1:30:44", "remaining_time": "2:42:02"}
+{"current_steps": 141, "total_steps": 390, "loss": 0.4266, "lr": 3.222841616184025e-05, "epoch": 1.7961783439490446, "percentage": 36.15, "elapsed_time": "1:31:14", "remaining_time": "2:41:07"}
+{"current_steps": 142, "total_steps": 390, "loss": 0.3936, "lr": 3.208627810922665e-05, "epoch": 1.8089171974522293, "percentage": 36.41, "elapsed_time": "1:31:55", "remaining_time": "2:40:32"}
+{"current_steps": 143, "total_steps": 390, "loss": 0.3542, "lr": 3.194317183405573e-05, "epoch": 1.821656050955414, "percentage": 36.67, "elapsed_time": "1:32:32", "remaining_time": "2:39:50"}
+{"current_steps": 144, "total_steps": 390, "loss": 0.3753, "lr": 3.1799108800462466e-05, "epoch": 1.8343949044585988, "percentage": 36.92, "elapsed_time": "1:33:09", "remaining_time": "2:39:08"}
+{"current_steps": 145, "total_steps": 390, "loss": 0.3828, "lr": 3.1654100549227024e-05, "epoch": 1.8471337579617835, "percentage": 37.18, "elapsed_time": "1:33:47", "remaining_time": "2:38:28"}
+{"current_steps": 146, "total_steps": 390, "loss": 0.373, "lr": 3.1508158696850275e-05, "epoch": 1.8598726114649682, "percentage": 37.44, "elapsed_time": "1:34:20", "remaining_time": "2:37:39"}
+{"current_steps": 147, "total_steps": 390, "loss": 0.4177, "lr": 3.136129493462312e-05, "epoch": 1.872611464968153, "percentage": 37.69, "elapsed_time": "1:34:58", "remaining_time": "2:36:59"}
+{"current_steps": 148, "total_steps": 390, "loss": 0.3777, "lr": 3.121352102768998e-05, "epoch": 1.8853503184713376, "percentage": 37.95, "elapsed_time": "1:35:33", "remaining_time": "2:36:15"}
+{"current_steps": 149, "total_steps": 390, "loss": 0.3929, "lr": 3.106484881410628e-05, "epoch": 1.8980891719745223, "percentage": 38.21, "elapsed_time": "1:36:08", "remaining_time": "2:35:29"}
+{"current_steps": 150, "total_steps": 390, "loss": 0.4097, "lr": 3.091529020389009e-05, "epoch": 1.910828025477707, "percentage": 38.46, "elapsed_time": "1:36:34", "remaining_time": "2:34:30"}
+{"current_steps": 151, "total_steps": 390, "loss": 0.3861, "lr": 3.076485717806808e-05, "epoch": 1.9235668789808917, "percentage": 38.72, "elapsed_time": "1:37:16", "remaining_time": "2:33:58"}
+{"current_steps": 152, "total_steps": 390, "loss": 0.404, "lr": 3.061356178771564e-05, "epoch": 1.9363057324840764, "percentage": 38.97, "elapsed_time": "1:37:52", "remaining_time": "2:33:15"}
+{"current_steps": 153, "total_steps": 390, "loss": 0.3864, "lr": 3.0461416152991555e-05, "epoch": 1.9490445859872612, "percentage": 39.23, "elapsed_time": "1:38:32", "remaining_time": "2:32:38"}
+{"current_steps": 154, "total_steps": 390, "loss": 0.3889, "lr": 3.0308432462167045e-05, "epoch": 1.9617834394904459, "percentage": 39.49, "elapsed_time": "1:39:11", "remaining_time": "2:32:00"}
+{"current_steps": 155, "total_steps": 390, "loss": 0.3927, "lr": 3.015462297064936e-05, "epoch": 1.9745222929936306, "percentage": 39.74, "elapsed_time": "1:39:43", "remaining_time": "2:31:11"}
+{"current_steps": 156, "total_steps": 390, "loss": 0.3835, "lr": 3.0000000000000004e-05, "epoch": 1.9872611464968153, "percentage": 40.0, "elapsed_time": "1:40:18", "remaining_time": "2:30:28"}
+{"current_steps": 157, "total_steps": 390, "loss": 0.3532, "lr": 2.98445759369477e-05, "epoch": 2.0, "percentage": 40.26, "elapsed_time": "1:40:47", "remaining_time": "2:29:35"}
+{"current_steps": 158, "total_steps": 390, "loss": 0.2745, "lr": 2.9688363232396056e-05, "epoch": 2.0127388535031847, "percentage": 40.51, "elapsed_time": "1:50:59", "remaining_time": "2:42:57"}
+{"current_steps": 159, "total_steps": 390, "loss": 0.2453, "lr": 2.9531374400426158e-05, "epoch": 2.0254777070063694, "percentage": 40.77, "elapsed_time": "1:51:37", "remaining_time": "2:42:10"}
+{"current_steps": 160, "total_steps": 390, "loss": 0.2427, "lr": 2.9373622017294075e-05, "epoch": 2.038216560509554, "percentage": 41.03, "elapsed_time": "1:52:19", "remaining_time": "2:41:28"}
+{"current_steps": 161, "total_steps": 390, "loss": 0.2456, "lr": 2.9215118720423375e-05, "epoch": 2.050955414012739, "percentage": 41.28, "elapsed_time": "1:53:00", "remaining_time": "2:40:44"}
+{"current_steps": 162, "total_steps": 390, "loss": 0.2398, "lr": 2.9055877207392752e-05, "epoch": 2.0636942675159236, "percentage": 41.54, "elapsed_time": "1:53:41", "remaining_time": "2:40:00"}
+{"current_steps": 163, "total_steps": 390, "loss": 0.2424, "lr": 2.8895910234918828e-05, "epoch": 2.0764331210191083, "percentage": 41.79, "elapsed_time": "1:54:09", "remaining_time": "2:38:58"}
+{"current_steps": 164, "total_steps": 390, "loss": 0.2521, "lr": 2.873523061783426e-05, "epoch": 2.089171974522293, "percentage": 42.05, "elapsed_time": "1:54:49", "remaining_time": "2:38:13"}
+{"current_steps": 165, "total_steps": 390, "loss": 0.2379, "lr": 2.8573851228061084e-05, "epoch": 2.1019108280254777, "percentage": 42.31, "elapsed_time": "1:55:25", "remaining_time": "2:37:23"}
+{"current_steps": 166, "total_steps": 390, "loss": 0.2502, "lr": 2.8411784993579633e-05, "epoch": 2.1146496815286624, "percentage": 42.56, "elapsed_time": "1:56:01", "remaining_time": "2:36:34"}
+{"current_steps": 167, "total_steps": 390, "loss": 0.2704, "lr": 2.8249044897392814e-05, "epoch": 2.127388535031847, "percentage": 42.82, "elapsed_time": "1:56:43", "remaining_time": "2:35:51"}
+{"current_steps": 168, "total_steps": 390, "loss": 0.2305, "lr": 2.80856439764861e-05, "epoch": 2.140127388535032, "percentage": 43.08, "elapsed_time": "1:57:15", "remaining_time": "2:34:56"}
+{"current_steps": 169, "total_steps": 390, "loss": 0.2458, "lr": 2.792159532078314e-05, "epoch": 2.1528662420382165, "percentage": 43.33, "elapsed_time": "1:57:49", "remaining_time": "2:34:05"}
+{"current_steps": 170, "total_steps": 390, "loss": 0.2588, "lr": 2.77569120720971e-05, "epoch": 2.1656050955414012, "percentage": 43.59, "elapsed_time": "1:58:20", "remaining_time": "2:33:08"}