Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d1027d26119826caac6934944810bf0c9b53627ba69d3353bdcecc21957bc53
+oid sha256:27b785c7a7f645cff45613063180f16d7b8f1e1edae94f7887776a56bde2740b
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b230e7df6f8deb2f8195cb816d96db4e4f0cf91729173b266c0116177f4cec
+oid sha256:d3a7d8efc16a1f997a0c7610cfbbe50ccd204f771472b26d2134285c5bf050c6
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e49ecf85ad652aeabf5dac32b1b5e3bcc18edef4e15f08818017f14e6bf2a2be
+oid sha256:d6104da7a6336ab03e5bcc5b1c330db8165d10a7ea89da852036b9528e0181fd
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:233f390d70c03b4cdfe9e7c04ec3f39f10707e330756a159dca6c12f389cb91b
+oid sha256:8d29ca54bcf8dcb5147ec2fe1ded2153eb0980531e27ea3c45e08d70ff36875a
 size 1089994880

trainer_log.jsonl

@@ -34,3 +34,20 @@
 {"current_steps": 330, "total_steps": 510, "loss": 0.6166, "learning_rate": 5e-06, "epoch": 1.934162399414777, "percentage": 64.71, "elapsed_time": "4:54:29", "remaining_time": "2:40:37"}
 {"current_steps": 340, "total_steps": 510, "loss": 0.6126, "learning_rate": 5e-06, "epoch": 1.9926847110460864, "percentage": 66.67, "elapsed_time": "5:03:18", "remaining_time": "2:31:39"}
 {"current_steps": 340, "total_steps": 510, "eval_loss": 0.6363422274589539, "epoch": 1.9926847110460864, "percentage": 66.67, "elapsed_time": "5:06:47", "remaining_time": "2:33:23"}
+{"current_steps": 350, "total_steps": 510, "loss": 0.6297, "learning_rate": 5e-06, "epoch": 2.0541331382589614, "percentage": 68.63, "elapsed_time": "5:15:59", "remaining_time": "2:24:27"}
+{"current_steps": 360, "total_steps": 510, "loss": 0.5897, "learning_rate": 5e-06, "epoch": 2.1126554498902705, "percentage": 70.59, "elapsed_time": "5:24:47", "remaining_time": "2:15:19"}
+{"current_steps": 370, "total_steps": 510, "loss": 0.5946, "learning_rate": 5e-06, "epoch": 2.17117776152158, "percentage": 72.55, "elapsed_time": "5:33:35", "remaining_time": "2:06:13"}
+{"current_steps": 380, "total_steps": 510, "loss": 0.594, "learning_rate": 5e-06, "epoch": 2.2297000731528893, "percentage": 74.51, "elapsed_time": "5:42:24", "remaining_time": "1:57:08"}
+{"current_steps": 390, "total_steps": 510, "loss": 0.588, "learning_rate": 5e-06, "epoch": 2.288222384784199, "percentage": 76.47, "elapsed_time": "5:51:13", "remaining_time": "1:48:04"}
+{"current_steps": 400, "total_steps": 510, "loss": 0.5943, "learning_rate": 5e-06, "epoch": 2.3467446964155085, "percentage": 78.43, "elapsed_time": "6:00:01", "remaining_time": "1:39:00"}
+{"current_steps": 410, "total_steps": 510, "loss": 0.5933, "learning_rate": 5e-06, "epoch": 2.4052670080468177, "percentage": 80.39, "elapsed_time": "6:08:50", "remaining_time": "1:29:57"}
+{"current_steps": 420, "total_steps": 510, "loss": 0.5898, "learning_rate": 5e-06, "epoch": 2.4637893196781273, "percentage": 82.35, "elapsed_time": "6:17:38", "remaining_time": "1:20:55"}
+{"current_steps": 430, "total_steps": 510, "loss": 0.588, "learning_rate": 5e-06, "epoch": 2.522311631309437, "percentage": 84.31, "elapsed_time": "6:26:27", "remaining_time": "1:11:54"}
+{"current_steps": 440, "total_steps": 510, "loss": 0.5883, "learning_rate": 5e-06, "epoch": 2.580833942940746, "percentage": 86.27, "elapsed_time": "6:35:16", "remaining_time": "1:02:53"}
+{"current_steps": 450, "total_steps": 510, "loss": 0.5951, "learning_rate": 5e-06, "epoch": 2.6393562545720557, "percentage": 88.24, "elapsed_time": "6:44:05", "remaining_time": "0:53:52"}
+{"current_steps": 460, "total_steps": 510, "loss": 0.5914, "learning_rate": 5e-06, "epoch": 2.6978785662033653, "percentage": 90.2, "elapsed_time": "6:52:54", "remaining_time": "0:44:52"}
+{"current_steps": 470, "total_steps": 510, "loss": 0.5917, "learning_rate": 5e-06, "epoch": 2.7564008778346745, "percentage": 92.16, "elapsed_time": "7:01:43", "remaining_time": "0:35:53"}
+{"current_steps": 480, "total_steps": 510, "loss": 0.5923, "learning_rate": 5e-06, "epoch": 2.8149231894659836, "percentage": 94.12, "elapsed_time": "7:10:32", "remaining_time": "0:26:54"}
+{"current_steps": 490, "total_steps": 510, "loss": 0.5888, "learning_rate": 5e-06, "epoch": 2.8734455010972932, "percentage": 96.08, "elapsed_time": "7:19:21", "remaining_time": "0:17:55"}
+{"current_steps": 500, "total_steps": 510, "loss": 0.5865, "learning_rate": 5e-06, "epoch": 2.931967812728603, "percentage": 98.04, "elapsed_time": "7:28:11", "remaining_time": "0:08:57"}
+{"current_steps": 510, "total_steps": 510, "loss": 0.5898, "learning_rate": 5e-06, "epoch": 2.990490124359912, "percentage": 100.0, "elapsed_time": "7:37:00", "remaining_time": "0:00:00"}