Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3428d0523b363502cc4f00511fe026a3e820b1be32445df5aef2d563c72c98c
+oid sha256:78fd94ad3968700809ca0e962ef45325ebb374cf76999877fcf72fc99231789f
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49bc32b02029f0bb9ac55fd8e940007a8fcff154d9946718560fc47afb0c6ff3
+oid sha256:6a28c7b7aa51e100c8798ccb28a9aa3fe9af3829bd52ed19bab34bb353f4c0cd
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b0a9855573e3163a512569f69ee9ad47c1781c584cf949517b9f5a188f0064d
+oid sha256:366f6f0412276de2cba9064f23c048c520697b19c3f7b80ea2b08d1b9f51db33
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e498390af8878812bf7941da3c5d7704ce1559aab9f3e557c11089b94a7aad
+oid sha256:4ef2051c3e4487831ff26c72af7cb550d3ac2433d172fcefc1845b6236bd64e8
 size 1168138808

trainer_log.jsonl

@@ -5,3 +5,10 @@
 {"current_steps": 50, "total_steps": 177, "loss": 0.7147, "lr": 5e-06, "epoch": 0.8385744234800838, "percentage": 28.25, "elapsed_time": "0:48:07", "remaining_time": "2:02:15"}
 {"current_steps": 59, "total_steps": 177, "eval_loss": 0.6969855427742004, "epoch": 0.989517819706499, "percentage": 33.33, "elapsed_time": "0:58:20", "remaining_time": "1:56:41"}
 {"current_steps": 60, "total_steps": 177, "loss": 0.7324, "lr": 5e-06, "epoch": 1.0083857442348008, "percentage": 33.9, "elapsed_time": "1:00:02", "remaining_time": "1:57:04"}
+{"current_steps": 70, "total_steps": 177, "loss": 0.6726, "lr": 5e-06, "epoch": 1.1761006289308176, "percentage": 39.55, "elapsed_time": "1:09:40", "remaining_time": "1:46:30"}
+{"current_steps": 80, "total_steps": 177, "loss": 0.6595, "lr": 5e-06, "epoch": 1.3438155136268344, "percentage": 45.2, "elapsed_time": "1:19:18", "remaining_time": "1:36:09"}
+{"current_steps": 90, "total_steps": 177, "loss": 0.6558, "lr": 5e-06, "epoch": 1.5115303983228512, "percentage": 50.85, "elapsed_time": "1:28:54", "remaining_time": "1:25:56"}
+{"current_steps": 100, "total_steps": 177, "loss": 0.6525, "lr": 5e-06, "epoch": 1.6792452830188678, "percentage": 56.5, "elapsed_time": "1:38:31", "remaining_time": "1:15:51"}
+{"current_steps": 110, "total_steps": 177, "loss": 0.6543, "lr": 5e-06, "epoch": 1.8469601677148848, "percentage": 62.15, "elapsed_time": "1:48:08", "remaining_time": "1:05:52"}
+{"current_steps": 119, "total_steps": 177, "eval_loss": 0.6759442090988159, "epoch": 1.9979035639412999, "percentage": 67.23, "elapsed_time": "1:57:51", "remaining_time": "0:57:26"}
+{"current_steps": 120, "total_steps": 177, "loss": 0.6821, "lr": 5e-06, "epoch": 2.0167714884696015, "percentage": 67.8, "elapsed_time": "2:00:03", "remaining_time": "0:57:01"}