Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75b84c1c263fc2c000a96b480e7c2e6f845e1ca917925035e70062a3f61436aa
+oid sha256:e9877ce938479c4eaf628a048c2d6a765e5b5d9618348f83b934655227f327c1
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eef6618b18e1934c6dc5ac9e58d43f5c43d872c3549db23c16e20ffd97f20ae8
+oid sha256:516d727548312eb11c6c92ceef1d90ea3dc1b7d80d506f8461048cd4bd1e00f8
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df1124d1eb3272384ae11a342e03879d3109de75935c6a1e4ecf0c3820adbc8
+oid sha256:05c5439420d39bcb7a87bd46d3c934180935b998b264afd06741ac20563d1d02
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec1f03af7554ec9f94b51f8fd38540327bcdfd1a552595b039262d1872a4edf
+oid sha256:cfb7c50167481551b4274d9edb3edf0c8bd0f223e8b011a30843726f93ec2f33
 size 1168138808

trainer_log.jsonl

@@ -18,3 +18,14 @@
 {"current_steps": 170, "total_steps": 276, "loss": 0.9161, "lr": 5e-06, "epoch": 1.8428184281842819, "percentage": 61.59, "elapsed_time": "2:43:18", "remaining_time": "1:41:49"}
 {"current_steps": 180, "total_steps": 276, "loss": 0.917, "lr": 5e-06, "epoch": 1.951219512195122, "percentage": 65.22, "elapsed_time": "2:52:45", "remaining_time": "1:32:08"}
 {"current_steps": 184, "total_steps": 276, "eval_loss": 0.9558340907096863, "epoch": 1.994579945799458, "percentage": 66.67, "elapsed_time": "2:58:37", "remaining_time": "1:29:18"}
+{"current_steps": 190, "total_steps": 276, "loss": 0.9576, "lr": 5e-06, "epoch": 2.059620596205962, "percentage": 68.84, "elapsed_time": "3:05:03", "remaining_time": "1:23:45"}
+{"current_steps": 200, "total_steps": 276, "loss": 0.8711, "lr": 5e-06, "epoch": 2.168021680216802, "percentage": 72.46, "elapsed_time": "3:14:30", "remaining_time": "1:13:54"}
+{"current_steps": 210, "total_steps": 276, "loss": 0.8692, "lr": 5e-06, "epoch": 2.2764227642276422, "percentage": 76.09, "elapsed_time": "3:23:57", "remaining_time": "1:04:05"}
+{"current_steps": 220, "total_steps": 276, "loss": 0.8727, "lr": 5e-06, "epoch": 2.3848238482384825, "percentage": 79.71, "elapsed_time": "3:33:24", "remaining_time": "0:54:19"}
+{"current_steps": 230, "total_steps": 276, "loss": 0.8714, "lr": 5e-06, "epoch": 2.4932249322493227, "percentage": 83.33, "elapsed_time": "3:42:51", "remaining_time": "0:44:34"}
+{"current_steps": 240, "total_steps": 276, "loss": 0.8675, "lr": 5e-06, "epoch": 2.6016260162601625, "percentage": 86.96, "elapsed_time": "3:52:18", "remaining_time": "0:34:50"}
+{"current_steps": 250, "total_steps": 276, "loss": 0.8694, "lr": 5e-06, "epoch": 2.710027100271003, "percentage": 90.58, "elapsed_time": "4:01:44", "remaining_time": "0:25:08"}
+{"current_steps": 260, "total_steps": 276, "loss": 0.8728, "lr": 5e-06, "epoch": 2.818428184281843, "percentage": 94.2, "elapsed_time": "4:11:09", "remaining_time": "0:15:27"}
+{"current_steps": 270, "total_steps": 276, "loss": 0.8735, "lr": 5e-06, "epoch": 2.926829268292683, "percentage": 97.83, "elapsed_time": "4:20:36", "remaining_time": "0:05:47"}
+{"current_steps": 276, "total_steps": 276, "eval_loss": 0.9591670632362366, "epoch": 2.991869918699187, "percentage": 100.0, "elapsed_time": "4:29:06", "remaining_time": "0:00:00"}
+{"current_steps": 276, "total_steps": 276, "epoch": 2.991869918699187, "percentage": 100.0, "elapsed_time": "4:30:20", "remaining_time": "0:00:00"}