Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d3e66244400c07c7deecdee98c4ba77be796b95050f25c266f5e65c886c888
+oid sha256:792279c4d2ff83dbfb1e61d99b28e0241cfb7625d7d01ebd0e972ea93460ad31
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14dff97fa050e4c6b0dfcb19b96df3ed1309d3faedefc52892dd495a845fa1d6
+oid sha256:ca856ebb3e9a32b80fa0eca38bd150673efa3e95793439c5223cff8e1d336dd0
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74c58b6bc8e4a5a9fb215c6e3579c38616ae2cb3a9824bde5f11a28a18fce34
+oid sha256:4a945256896afb89c92908fafbacb1302c839423ff7201089860a018d75caf67
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32be6e7e1ab00456879c9083d5f0b5b1568f7bff0c09077ad546537b5f5d11e1
+oid sha256:92dfe9236600ce0e29a2bd16226e2d9acfd994853e6ab8c897b19caea5aeb304
 size 1168138808

trainer_log.jsonl

@@ -13,3 +13,12 @@
 {"current_steps": 120, "total_steps": 201, "loss": 0.5709, "lr": 5e-06, "epoch": 1.784786641929499, "percentage": 59.7, "elapsed_time": "1:57:29", "remaining_time": "1:19:18"}
 {"current_steps": 130, "total_steps": 201, "loss": 0.568, "lr": 5e-06, "epoch": 1.9332096474953617, "percentage": 64.68, "elapsed_time": "2:07:05", "remaining_time": "1:09:24"}
 {"current_steps": 134, "total_steps": 201, "eval_loss": 0.6242453455924988, "epoch": 1.9925788497217067, "percentage": 66.67, "elapsed_time": "2:12:23", "remaining_time": "1:06:11"}
+{"current_steps": 140, "total_steps": 201, "loss": 0.5879, "lr": 5e-06, "epoch": 2.085343228200371, "percentage": 69.65, "elapsed_time": "2:19:04", "remaining_time": "1:00:35"}
+{"current_steps": 150, "total_steps": 201, "loss": 0.507, "lr": 5e-06, "epoch": 2.2337662337662336, "percentage": 74.63, "elapsed_time": "2:28:40", "remaining_time": "0:50:33"}
+{"current_steps": 160, "total_steps": 201, "loss": 0.5063, "lr": 5e-06, "epoch": 2.3821892393320967, "percentage": 79.6, "elapsed_time": "2:38:16", "remaining_time": "0:40:33"}
+{"current_steps": 170, "total_steps": 201, "loss": 0.5001, "lr": 5e-06, "epoch": 2.5306122448979593, "percentage": 84.58, "elapsed_time": "2:47:52", "remaining_time": "0:30:36"}
+{"current_steps": 180, "total_steps": 201, "loss": 0.5013, "lr": 5e-06, "epoch": 2.679035250463822, "percentage": 89.55, "elapsed_time": "2:57:28", "remaining_time": "0:20:42"}
+{"current_steps": 190, "total_steps": 201, "loss": 0.5063, "lr": 5e-06, "epoch": 2.8274582560296846, "percentage": 94.53, "elapsed_time": "3:07:03", "remaining_time": "0:10:49"}
+{"current_steps": 200, "total_steps": 201, "loss": 0.5028, "lr": 5e-06, "epoch": 2.9758812615955472, "percentage": 99.5, "elapsed_time": "3:16:39", "remaining_time": "0:00:58"}
+{"current_steps": 201, "total_steps": 201, "eval_loss": 0.6297215223312378, "epoch": 2.9907235621521338, "percentage": 100.0, "elapsed_time": "3:20:02", "remaining_time": "0:00:00"}
+{"current_steps": 201, "total_steps": 201, "epoch": 2.9907235621521338, "percentage": 100.0, "elapsed_time": "3:21:16", "remaining_time": "0:00:00"}