Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49862f6d6e13536142b2f58e97582c188051f216723e2337447dfa82fb7d884e
+oid sha256:b08b2efedb963a297454b19b9a93b84c55c66611a8fd5c4401e8a0aaa0f22005
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a245702381a5f07e4f3aad08b3da2d25f19a3cf0977d85626a16485e75c84a
+oid sha256:ac2d95a09d4c3b39e6f62419c954b2abb9acc6ad86d50850a123fe18884e8c62
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae15f7e116d3f090241c908a21a5d6966366074f4a0e862fec1ed98f62be575
+oid sha256:6b3f3c1a14d52e37be4c8cb799f9df3e79bdff8a99b6e6c72357d17f075ea08c
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:954e643f30c675956db4a92c1e0b79616f328eb35460b5a6ca1b4e0ddc25d275
+oid sha256:8409661ef7c3b5a47b468f5e4462d8d7f5affeee69dbedf8e9500a5935b0078d
 size 1168138808

trainer_log.jsonl

@@ -14,3 +14,13 @@
 {"current_steps": 130, "total_steps": 246, "loss": 0.4991, "lr": 5e-06, "epoch": 1.5811836115326252, "percentage": 52.85, "elapsed_time": "0:52:45", "remaining_time": "0:47:04"}
 {"current_steps": 140, "total_steps": 246, "loss": 0.4973, "lr": 5e-06, "epoch": 1.7025796661608497, "percentage": 56.91, "elapsed_time": "0:56:38", "remaining_time": "0:42:53"}
 {"current_steps": 150, "total_steps": 246, "loss": 0.501, "lr": 5e-06, "epoch": 1.8239757207890743, "percentage": 60.98, "elapsed_time": "1:00:35", "remaining_time": "0:38:46"}
+{"current_steps": 160, "total_steps": 246, "loss": 0.4963, "lr": 5e-06, "epoch": 1.945371775417299, "percentage": 65.04, "elapsed_time": "1:04:29", "remaining_time": "0:34:39"}
+{"current_steps": 164, "total_steps": 246, "eval_loss": 0.5243988037109375, "epoch": 1.9939301972685888, "percentage": 66.67, "elapsed_time": "1:06:39", "remaining_time": "0:33:19"}
+{"current_steps": 170, "total_steps": 246, "loss": 0.5178, "lr": 5e-06, "epoch": 2.069802731411229, "percentage": 69.11, "elapsed_time": "1:10:34", "remaining_time": "0:31:33"}
+{"current_steps": 180, "total_steps": 246, "loss": 0.4477, "lr": 5e-06, "epoch": 2.191198786039454, "percentage": 73.17, "elapsed_time": "1:14:27", "remaining_time": "0:27:18"}
+{"current_steps": 190, "total_steps": 246, "loss": 0.4478, "lr": 5e-06, "epoch": 2.3125948406676784, "percentage": 77.24, "elapsed_time": "1:18:20", "remaining_time": "0:23:05"}
+{"current_steps": 200, "total_steps": 246, "loss": 0.45, "lr": 5e-06, "epoch": 2.433990895295903, "percentage": 81.3, "elapsed_time": "1:22:13", "remaining_time": "0:18:54"}
+{"current_steps": 210, "total_steps": 246, "loss": 0.4474, "lr": 5e-06, "epoch": 2.5553869499241273, "percentage": 85.37, "elapsed_time": "1:26:06", "remaining_time": "0:14:45"}
+{"current_steps": 220, "total_steps": 246, "loss": 0.4493, "lr": 5e-06, "epoch": 2.676783004552352, "percentage": 89.43, "elapsed_time": "1:30:01", "remaining_time": "0:10:38"}
+{"current_steps": 230, "total_steps": 246, "loss": 0.4476, "lr": 5e-06, "epoch": 2.7981790591805766, "percentage": 93.5, "elapsed_time": "1:33:54", "remaining_time": "0:06:31"}
+{"current_steps": 240, "total_steps": 246, "loss": 0.4507, "lr": 5e-06, "epoch": 2.919575113808801, "percentage": 97.56, "elapsed_time": "1:37:47", "remaining_time": "0:02:26"}