Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f391dfb31b56bc5bc8b67b6b6619732899c435cc5991f0ecbf12a34b372b63e
+oid sha256:e8e111d5a53a681077249d3ef299d72b4fa054179483501c69140a0f56f99a97
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b867a29a425fddf48ee94c854f1cd9c3713f694776f6fb35f95fa7758170c73
+oid sha256:341205820aaeabf259de33ea820aeed3a7b708dc015636a3fc2cf5e2f15cb9ec
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98cd112da290b98485015f8ca15b956446adb8cc451e95f10e16ee9547516805
+oid sha256:33b139ffaa9b6ecbc7fa28c2476e1b95df4e09547e1484360685f36425cb7d44
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb3f80debd375500f334923e2fb09129ff81897dc31146e6b61122cd2dbaa03
+oid sha256:05b6da9d962c0d2c3d9af4c766e38fbb5bdf0b26e9cefdca373c2e5b4d367edc
 size 1168138808

trainer_log.jsonl

@@ -13,3 +13,12 @@
 {"current_steps": 120, "total_steps": 204, "loss": 0.4379, "lr": 5e-06, "epoch": 1.7568555758683728, "percentage": 58.82, "elapsed_time": "1:06:20", "remaining_time": "0:46:26"}
 {"current_steps": 130, "total_steps": 204, "loss": 0.4325, "lr": 5e-06, "epoch": 1.9031078610603291, "percentage": 63.73, "elapsed_time": "1:11:41", "remaining_time": "0:40:48"}
 {"current_steps": 136, "total_steps": 204, "eval_loss": 0.46772316098213196, "epoch": 1.9908592321755028, "percentage": 66.67, "elapsed_time": "1:15:56", "remaining_time": "0:37:58"}
+{"current_steps": 140, "total_steps": 204, "loss": 0.4489, "lr": 5e-06, "epoch": 2.0511882998171846, "percentage": 68.63, "elapsed_time": "1:19:06", "remaining_time": "0:36:10"}
+{"current_steps": 150, "total_steps": 204, "loss": 0.3845, "lr": 5e-06, "epoch": 2.197440585009141, "percentage": 73.53, "elapsed_time": "1:24:25", "remaining_time": "0:30:23"}
+{"current_steps": 160, "total_steps": 204, "loss": 0.3819, "lr": 5e-06, "epoch": 2.343692870201097, "percentage": 78.43, "elapsed_time": "1:29:47", "remaining_time": "0:24:41"}
+{"current_steps": 170, "total_steps": 204, "loss": 0.3839, "lr": 5e-06, "epoch": 2.489945155393053, "percentage": 83.33, "elapsed_time": "1:35:09", "remaining_time": "0:19:01"}
+{"current_steps": 180, "total_steps": 204, "loss": 0.3867, "lr": 5e-06, "epoch": 2.636197440585009, "percentage": 88.24, "elapsed_time": "1:40:31", "remaining_time": "0:13:24"}
+{"current_steps": 190, "total_steps": 204, "loss": 0.3815, "lr": 5e-06, "epoch": 2.7824497257769654, "percentage": 93.14, "elapsed_time": "1:45:53", "remaining_time": "0:07:48"}
+{"current_steps": 200, "total_steps": 204, "loss": 0.3893, "lr": 5e-06, "epoch": 2.9287020109689212, "percentage": 98.04, "elapsed_time": "1:51:15", "remaining_time": "0:02:13"}
+{"current_steps": 204, "total_steps": 204, "eval_loss": 0.46915486454963684, "epoch": 2.987202925045704, "percentage": 100.0, "elapsed_time": "1:55:28", "remaining_time": "0:00:00"}
+{"current_steps": 204, "total_steps": 204, "epoch": 2.987202925045704, "percentage": 100.0, "elapsed_time": "1:56:40", "remaining_time": "0:00:00"}