Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38e348bfbb2ec3a0da3ff57e390c5da768660ad08e48b5701283e0ab59522c9
+oid sha256:1c376e64fb5f34160ee951d397ea4a38ad3dd5c06122aadc3446a3b2148c3c6d
 size 4903351912

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6666343f113fc44ea86be205ed643aa1f4f257df0c37ecf57835224cd4e3f475
+oid sha256:fae28ba6a3e5800497381a302934f8026e9d634555cfa60da6fddefeb27beac9
 size 4947570872

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ce4d338162ea7672300255cb65aa8910baeb0fe0b23c54c992d6e5686bbacb
+oid sha256:97ae89cc41315d0c8fe8ddddfbe3f03f77042e7c64247e20da81a7d7088ed5c0
 size 4962221464

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf890cc71ce38e73b9b7a769dcc61ce33fa9e38521855babaeba5ffcbb72345a
+oid sha256:d261735f2da7cbfdfea5f65236c90287e425e92e0ee71f3133fea13be73a292e
 size 3670322200

trainer_log.jsonl

@@ -21,3 +21,26 @@
 {"current_steps": 210, "total_steps": 663, "loss": 0.5975, "learning_rate": 5e-06, "epoch": 0.9478138222849083, "percentage": 31.67, "elapsed_time": "5:16:48", "remaining_time": "11:23:23"}
 {"current_steps": 220, "total_steps": 663, "loss": 0.5944, "learning_rate": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.18, "elapsed_time": "5:31:53", "remaining_time": "11:08:18"}
 {"current_steps": 221, "total_steps": 663, "eval_loss": 0.5952667593955994, "epoch": 0.9974612129760225, "percentage": 33.33, "elapsed_time": "5:39:46", "remaining_time": "11:19:32"}
+{"current_steps": 230, "total_steps": 663, "loss": 0.5957, "learning_rate": 5e-06, "epoch": 1.039210155148096, "percentage": 34.69, "elapsed_time": "5:53:55", "remaining_time": "11:06:18"}
+{"current_steps": 240, "total_steps": 663, "loss": 0.5546, "learning_rate": 5e-06, "epoch": 1.0843441466854724, "percentage": 36.2, "elapsed_time": "6:09:01", "remaining_time": "10:50:24"}
+{"current_steps": 250, "total_steps": 663, "loss": 0.5576, "learning_rate": 5e-06, "epoch": 1.1294781382228491, "percentage": 37.71, "elapsed_time": "6:24:09", "remaining_time": "10:34:37"}
+{"current_steps": 260, "total_steps": 663, "loss": 0.5531, "learning_rate": 5e-06, "epoch": 1.1746121297602257, "percentage": 39.22, "elapsed_time": "6:39:15", "remaining_time": "10:18:51"}
+{"current_steps": 270, "total_steps": 663, "loss": 0.5549, "learning_rate": 5e-06, "epoch": 1.2197461212976022, "percentage": 40.72, "elapsed_time": "6:54:21", "remaining_time": "10:03:06"}
+{"current_steps": 280, "total_steps": 663, "loss": 0.5572, "learning_rate": 5e-06, "epoch": 1.264880112834979, "percentage": 42.23, "elapsed_time": "7:09:26", "remaining_time": "9:47:25"}
+{"current_steps": 290, "total_steps": 663, "loss": 0.5565, "learning_rate": 5e-06, "epoch": 1.3100141043723554, "percentage": 43.74, "elapsed_time": "7:24:32", "remaining_time": "9:31:46"}
+{"current_steps": 300, "total_steps": 663, "loss": 0.5587, "learning_rate": 5e-06, "epoch": 1.355148095909732, "percentage": 45.25, "elapsed_time": "7:39:38", "remaining_time": "9:16:10"}
+{"current_steps": 310, "total_steps": 663, "loss": 0.5557, "learning_rate": 5e-06, "epoch": 1.4002820874471085, "percentage": 46.76, "elapsed_time": "7:54:45", "remaining_time": "9:00:36"}
+{"current_steps": 320, "total_steps": 663, "loss": 0.555, "learning_rate": 5e-06, "epoch": 1.4454160789844852, "percentage": 48.27, "elapsed_time": "8:09:51", "remaining_time": "8:45:03"}
+{"current_steps": 330, "total_steps": 663, "loss": 0.5578, "learning_rate": 5e-06, "epoch": 1.4905500705218617, "percentage": 49.77, "elapsed_time": "8:24:58", "remaining_time": "8:29:33"}
+{"current_steps": 340, "total_steps": 663, "loss": 0.5519, "learning_rate": 5e-06, "epoch": 1.5356840620592385, "percentage": 51.28, "elapsed_time": "8:40:04", "remaining_time": "8:14:04"}
+{"current_steps": 350, "total_steps": 663, "loss": 0.5523, "learning_rate": 5e-06, "epoch": 1.580818053596615, "percentage": 52.79, "elapsed_time": "8:55:09", "remaining_time": "7:58:35"}
+{"current_steps": 360, "total_steps": 663, "loss": 0.561, "learning_rate": 5e-06, "epoch": 1.6259520451339915, "percentage": 54.3, "elapsed_time": "9:10:16", "remaining_time": "7:43:08"}
+{"current_steps": 370, "total_steps": 663, "loss": 0.5562, "learning_rate": 5e-06, "epoch": 1.671086036671368, "percentage": 55.81, "elapsed_time": "9:25:22", "remaining_time": "7:27:42"}
+{"current_steps": 380, "total_steps": 663, "loss": 0.5552, "learning_rate": 5e-06, "epoch": 1.7162200282087448, "percentage": 57.32, "elapsed_time": "9:40:28", "remaining_time": "7:12:18"}
+{"current_steps": 390, "total_steps": 663, "loss": 0.5528, "learning_rate": 5e-06, "epoch": 1.7613540197461213, "percentage": 58.82, "elapsed_time": "9:55:34", "remaining_time": "6:56:54"}
+{"current_steps": 400, "total_steps": 663, "loss": 0.5517, "learning_rate": 5e-06, "epoch": 1.806488011283498, "percentage": 60.33, "elapsed_time": "10:10:39", "remaining_time": "6:41:30"}
+{"current_steps": 410, "total_steps": 663, "loss": 0.5543, "learning_rate": 5e-06, "epoch": 1.8516220028208745, "percentage": 61.84, "elapsed_time": "10:25:45", "remaining_time": "6:26:08"}
+{"current_steps": 420, "total_steps": 663, "loss": 0.5578, "learning_rate": 5e-06, "epoch": 1.896755994358251, "percentage": 63.35, "elapsed_time": "10:40:52", "remaining_time": "6:10:47"}
+{"current_steps": 430, "total_steps": 663, "loss": 0.5486, "learning_rate": 5e-06, "epoch": 1.9418899858956276, "percentage": 64.86, "elapsed_time": "10:55:58", "remaining_time": "5:55:26"}
+{"current_steps": 440, "total_steps": 663, "loss": 0.5591, "learning_rate": 5e-06, "epoch": 1.987023977433004, "percentage": 66.37, "elapsed_time": "11:11:04", "remaining_time": "5:40:06"}
+{"current_steps": 442, "total_steps": 663, "eval_loss": 0.5866958498954773, "epoch": 1.9960507757404795, "percentage": 66.67, "elapsed_time": "11:20:56", "remaining_time": "5:40:28"}