Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578c8e2c4da3b850a713f99afc961a815161da5c7379d1e865d60b525b338636
+oid sha256:06f07ef4b7a50d5f2d32360e7bb6e732c0e2e3f69f4751dd404663ae1988dc4b
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f3b48e637a25e099d837a9da3349ba881ba4e5808f71b2ad8f7f0a08114c00
+oid sha256:c27a2a0ce09e6abaa70ff2b21fae2cbc1af70bf039e31f648cdda4241f6412ce
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8906b0b1e681eeb5e1c7455cf8bf60cb456cf1c5f71ca9102c58241ab464c6cd
+oid sha256:6ae2ab72f8b5152aebfd2c74d0b83515579e7b2e0916aa82b1d5a31cfb70f3c0
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489b85346139e0560d8042c251848b48b835240d95582a3817eff9579bac83df
+oid sha256:f7b30daf4e5815c4388fb555bf3eb7f947edb5470bff1de63dcaffd2e7672ff8
 size 1168138808

trainer_log.jsonl

@@ -5,3 +5,11 @@
 {"current_steps": 50, "total_steps": 198, "loss": 0.7441, "lr": 5e-06, "epoch": 0.7518796992481203, "percentage": 25.25, "elapsed_time": "0:48:38", "remaining_time": "2:23:59"}
 {"current_steps": 60, "total_steps": 198, "loss": 0.7377, "lr": 5e-06, "epoch": 0.9022556390977443, "percentage": 30.3, "elapsed_time": "0:58:20", "remaining_time": "2:14:11"}
 {"current_steps": 66, "total_steps": 198, "eval_loss": 0.7360510230064392, "epoch": 0.9924812030075187, "percentage": 33.33, "elapsed_time": "1:05:49", "remaining_time": "2:11:39"}
+{"current_steps": 70, "total_steps": 198, "loss": 0.7494, "lr": 5e-06, "epoch": 1.0526315789473684, "percentage": 35.35, "elapsed_time": "1:10:23", "remaining_time": "2:08:43"}
+{"current_steps": 80, "total_steps": 198, "loss": 0.6823, "lr": 5e-06, "epoch": 1.2030075187969924, "percentage": 40.4, "elapsed_time": "1:20:06", "remaining_time": "1:58:10"}
+{"current_steps": 90, "total_steps": 198, "loss": 0.6835, "lr": 5e-06, "epoch": 1.3533834586466165, "percentage": 45.45, "elapsed_time": "1:29:48", "remaining_time": "1:47:46"}
+{"current_steps": 100, "total_steps": 198, "loss": 0.6778, "lr": 5e-06, "epoch": 1.5037593984962405, "percentage": 50.51, "elapsed_time": "1:39:30", "remaining_time": "1:37:31"}
+{"current_steps": 110, "total_steps": 198, "loss": 0.6741, "lr": 5e-06, "epoch": 1.6541353383458648, "percentage": 55.56, "elapsed_time": "1:49:12", "remaining_time": "1:27:22"}
+{"current_steps": 120, "total_steps": 198, "loss": 0.6786, "lr": 5e-06, "epoch": 1.8045112781954886, "percentage": 60.61, "elapsed_time": "1:58:52", "remaining_time": "1:17:16"}
+{"current_steps": 130, "total_steps": 198, "loss": 0.6668, "lr": 5e-06, "epoch": 1.954887218045113, "percentage": 65.66, "elapsed_time": "2:08:34", "remaining_time": "1:07:15"}
+{"current_steps": 133, "total_steps": 198, "eval_loss": 0.7167445421218872, "epoch": 2.0, "percentage": 67.17, "elapsed_time": "2:12:35", "remaining_time": "1:04:48"}