Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a01a92e205a7148cab7aa1a7b49b02de4825c8c970d95bd2bc78ca1caeaa4f
+oid sha256:3d170f359a680075db96ad17b6503a25d0efdae26a59d9380a766e0092382209
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b355350f79b0b2c05003e1e9843e9c05aae3cbe59cba1d5bb9b16ffa975b99
+oid sha256:0e9bb581880ee4628bd3575a05174570eb2d6e9a92e03e5fb52f9480e5136183
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a3bc37d54bec29a0c221371979c21e304dc31b6349f20cf8c3ccda919ae273
+oid sha256:12ce5ec31d7cd6919f37a1bf5c890b86ef29b49e2284d75826210a25e5b2bca6
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8db8b6f8fac07719bc1aad252f929e765e1c697b64d71199fceec3b812a942c
+oid sha256:5a8bacf7641ff203195518849e098a79e919748e9972bfd3820dd7c3c907f4b5
 size 1168138808

trainer_log.jsonl

@@ -17,3 +17,14 @@
 {"current_steps": 160, "total_steps": 264, "loss": 0.7414, "lr": 5e-06, "epoch": 1.8156028368794326, "percentage": 60.61, "elapsed_time": "1:27:10", "remaining_time": "0:56:40"}
 {"current_steps": 170, "total_steps": 264, "loss": 0.7481, "lr": 5e-06, "epoch": 1.9290780141843973, "percentage": 64.39, "elapsed_time": "1:32:29", "remaining_time": "0:51:08"}
 {"current_steps": 176, "total_steps": 264, "eval_loss": 0.7898643016815186, "epoch": 1.9971631205673759, "percentage": 66.67, "elapsed_time": "1:36:49", "remaining_time": "0:48:24"}
+{"current_steps": 180, "total_steps": 264, "loss": 0.7818, "lr": 5e-06, "epoch": 2.0425531914893615, "percentage": 68.18, "elapsed_time": "1:40:05", "remaining_time": "0:46:42"}
+{"current_steps": 190, "total_steps": 264, "loss": 0.6863, "lr": 5e-06, "epoch": 2.1560283687943262, "percentage": 71.97, "elapsed_time": "1:45:22", "remaining_time": "0:41:02"}
+{"current_steps": 200, "total_steps": 264, "loss": 0.6798, "lr": 5e-06, "epoch": 2.269503546099291, "percentage": 75.76, "elapsed_time": "1:50:39", "remaining_time": "0:35:24"}
+{"current_steps": 210, "total_steps": 264, "loss": 0.6826, "lr": 5e-06, "epoch": 2.382978723404255, "percentage": 79.55, "elapsed_time": "1:55:57", "remaining_time": "0:29:49"}
+{"current_steps": 220, "total_steps": 264, "loss": 0.6839, "lr": 5e-06, "epoch": 2.49645390070922, "percentage": 83.33, "elapsed_time": "2:01:15", "remaining_time": "0:24:15"}
+{"current_steps": 230, "total_steps": 264, "loss": 0.687, "lr": 5e-06, "epoch": 2.6099290780141846, "percentage": 87.12, "elapsed_time": "2:06:32", "remaining_time": "0:18:42"}
+{"current_steps": 240, "total_steps": 264, "loss": 0.6902, "lr": 5e-06, "epoch": 2.723404255319149, "percentage": 90.91, "elapsed_time": "2:11:51", "remaining_time": "0:13:11"}
+{"current_steps": 250, "total_steps": 264, "loss": 0.6873, "lr": 5e-06, "epoch": 2.8368794326241136, "percentage": 94.7, "elapsed_time": "2:17:08", "remaining_time": "0:07:40"}
+{"current_steps": 260, "total_steps": 264, "loss": 0.6866, "lr": 5e-06, "epoch": 2.950354609929078, "percentage": 98.48, "elapsed_time": "2:22:24", "remaining_time": "0:02:11"}
+{"current_steps": 264, "total_steps": 264, "eval_loss": 0.7845782041549683, "epoch": 2.9957446808510637, "percentage": 100.0, "elapsed_time": "2:26:48", "remaining_time": "0:00:00"}
+{"current_steps": 264, "total_steps": 264, "epoch": 2.9957446808510637, "percentage": 100.0, "elapsed_time": "2:28:01", "remaining_time": "0:00:00"}