Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5670aa7cc168211e78ea76df333d6169b65c354e9598f779393fdadb22456c73
+oid sha256:0fac9c05f0f132f24574b6c6588d7cd254f305c559a47d71baa45caaef6b986b
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f87ef8d491a86038d35b88c3b56b3d9a65c78e15c0b7c01b564a74d6db905f23
+oid sha256:8774f2f42ceafa8e719bd25691caeb08b13b6b1589190ffc34c3e4f6ec965e88
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff9f06324d884c8dad5239084ccbc386b198ef97dabd8c2d15c3a8e12cff546
+oid sha256:3e4e6dfb459ec12824e370a304a846a3447d746507e9c84821f3e2642a5106ca
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf3a93f29896fcc363af787319c798727a9d3ae6510d034154dcb5ed0a3e159
+oid sha256:db88f626450d54ca25f90876ce7526e587dfa9d35c862ab7c8d28353cc4d9480
 size 1168138808

trainer_log.jsonl

@@ -16,3 +16,20 @@
 {"current_steps": 160, "total_steps": 504, "loss": 0.6088, "lr": 5e-06, "epoch": 0.9488510007412898, "percentage": 31.75, "elapsed_time": "2:33:09", "remaining_time": "5:29:16"}
 {"current_steps": 168, "total_steps": 504, "eval_loss": 0.6123025417327881, "epoch": 0.9962935507783544, "percentage": 33.33, "elapsed_time": "2:44:08", "remaining_time": "5:28:16"}
 {"current_steps": 170, "total_steps": 504, "loss": 0.6323, "lr": 5e-06, "epoch": 1.0096367679762788, "percentage": 33.73, "elapsed_time": "2:46:51", "remaining_time": "5:27:50"}
+{"current_steps": 180, "total_steps": 504, "loss": 0.5587, "lr": 5e-06, "epoch": 1.0689399555226093, "percentage": 35.71, "elapsed_time": "2:56:26", "remaining_time": "5:17:35"}
+{"current_steps": 190, "total_steps": 504, "loss": 0.5532, "lr": 5e-06, "epoch": 1.12824314306894, "percentage": 37.7, "elapsed_time": "3:06:01", "remaining_time": "5:07:25"}
+{"current_steps": 200, "total_steps": 504, "loss": 0.5449, "lr": 5e-06, "epoch": 1.1875463306152705, "percentage": 39.68, "elapsed_time": "3:15:36", "remaining_time": "4:57:19"}
+{"current_steps": 210, "total_steps": 504, "loss": 0.5506, "lr": 5e-06, "epoch": 1.2468495181616013, "percentage": 41.67, "elapsed_time": "3:25:10", "remaining_time": "4:47:14"}
+{"current_steps": 220, "total_steps": 504, "loss": 0.5518, "lr": 5e-06, "epoch": 1.3061527057079318, "percentage": 43.65, "elapsed_time": "3:34:46", "remaining_time": "4:37:14"}
+{"current_steps": 230, "total_steps": 504, "loss": 0.543, "lr": 5e-06, "epoch": 1.3654558932542624, "percentage": 45.63, "elapsed_time": "3:44:20", "remaining_time": "4:27:15"}
+{"current_steps": 240, "total_steps": 504, "loss": 0.5563, "lr": 5e-06, "epoch": 1.424759080800593, "percentage": 47.62, "elapsed_time": "3:53:55", "remaining_time": "4:17:19"}
+{"current_steps": 250, "total_steps": 504, "loss": 0.5517, "lr": 5e-06, "epoch": 1.4840622683469236, "percentage": 49.6, "elapsed_time": "4:03:30", "remaining_time": "4:07:23"}
+{"current_steps": 260, "total_steps": 504, "loss": 0.5512, "lr": 5e-06, "epoch": 1.5433654558932544, "percentage": 51.59, "elapsed_time": "4:13:04", "remaining_time": "3:57:30"}
+{"current_steps": 270, "total_steps": 504, "loss": 0.55, "lr": 5e-06, "epoch": 1.602668643439585, "percentage": 53.57, "elapsed_time": "4:22:39", "remaining_time": "3:47:38"}
+{"current_steps": 280, "total_steps": 504, "loss": 0.5472, "lr": 5e-06, "epoch": 1.6619718309859155, "percentage": 55.56, "elapsed_time": "4:32:15", "remaining_time": "3:37:48"}
+{"current_steps": 290, "total_steps": 504, "loss": 0.5451, "lr": 5e-06, "epoch": 1.721275018532246, "percentage": 57.54, "elapsed_time": "4:41:50", "remaining_time": "3:27:59"}
+{"current_steps": 300, "total_steps": 504, "loss": 0.5477, "lr": 5e-06, "epoch": 1.7805782060785766, "percentage": 59.52, "elapsed_time": "4:51:26", "remaining_time": "3:18:10"}
+{"current_steps": 310, "total_steps": 504, "loss": 0.5558, "lr": 5e-06, "epoch": 1.8398813936249074, "percentage": 61.51, "elapsed_time": "5:00:59", "remaining_time": "3:08:21"}
+{"current_steps": 320, "total_steps": 504, "loss": 0.5533, "lr": 5e-06, "epoch": 1.899184581171238, "percentage": 63.49, "elapsed_time": "5:10:34", "remaining_time": "2:58:34"}
+{"current_steps": 330, "total_steps": 504, "loss": 0.5487, "lr": 5e-06, "epoch": 1.9584877687175686, "percentage": 65.48, "elapsed_time": "5:20:08", "remaining_time": "2:48:48"}
+{"current_steps": 336, "total_steps": 504, "eval_loss": 0.6003267765045166, "epoch": 1.9940696812453669, "percentage": 66.67, "elapsed_time": "5:29:31", "remaining_time": "2:44:45"}