Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d889bde9824b885949fca79df5cc2c06dd92372d312bb8c2b73e0a8e5d8a7eb
+oid sha256:ad255bcedbb511599e1bedcd8e8cf9305c27d989004329da6b8bd3aed7b4798c
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b60c1c0aaeb6f9ddbde99fcb2d0e90856d435713398b1dc652e86b552bbbd44a
+oid sha256:4dc401136cf31c6ddcf5d956214a10e191aa405943de5d19951137c896f0cb36
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4c1d3c6a04b9e03b68ae4fe27514136d96afba921d74c3b1c1c6cb856a5436
+oid sha256:4f60161d27bb92605fc5a38fd8e339f080a37c4089e970a937871f8080e728e9
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f7ee762c2f99a9c8dd7d4fd1c82dbec258322c68c3edf75add10c7bebaac95
+oid sha256:1f67b28bcfcc5ca34f746f705c84dd049735f917a0b64e79b8a9e9ec9041f33f
 size 1168138808

trainer_log.jsonl

@@ -55,3 +55,30 @@
 {"current_steps": 540, "total_steps": 816, "loss": 0.6845, "lr": 5e-06, "epoch": 1.9816681943171401, "percentage": 66.18, "elapsed_time": "2:33:43", "remaining_time": "1:18:34"}
 {"current_steps": 544, "total_steps": 816, "eval_loss": 0.7305116057395935, "epoch": 1.996333638863428, "percentage": 66.67, "elapsed_time": "2:36:33", "remaining_time": "1:18:16"}
 {"current_steps": 550, "total_steps": 816, "loss": 0.707, "lr": 5e-06, "epoch": 2.020164986251146, "percentage": 67.4, "elapsed_time": "2:39:11", "remaining_time": "1:16:59"}
+{"current_steps": 560, "total_steps": 816, "loss": 0.6313, "lr": 5e-06, "epoch": 2.056828597616865, "percentage": 68.63, "elapsed_time": "2:41:58", "remaining_time": "1:14:02"}
+{"current_steps": 570, "total_steps": 816, "loss": 0.6281, "lr": 5e-06, "epoch": 2.093492208982585, "percentage": 69.85, "elapsed_time": "2:44:46", "remaining_time": "1:11:06"}
+{"current_steps": 580, "total_steps": 816, "loss": 0.631, "lr": 5e-06, "epoch": 2.130155820348304, "percentage": 71.08, "elapsed_time": "2:47:34", "remaining_time": "1:08:11"}
+{"current_steps": 590, "total_steps": 816, "loss": 0.6351, "lr": 5e-06, "epoch": 2.166819431714024, "percentage": 72.3, "elapsed_time": "2:50:21", "remaining_time": "1:05:15"}
+{"current_steps": 600, "total_steps": 816, "loss": 0.634, "lr": 5e-06, "epoch": 2.203483043079743, "percentage": 73.53, "elapsed_time": "2:53:07", "remaining_time": "1:02:19"}
+{"current_steps": 610, "total_steps": 816, "loss": 0.6327, "lr": 5e-06, "epoch": 2.240146654445463, "percentage": 74.75, "elapsed_time": "2:55:53", "remaining_time": "0:59:24"}
+{"current_steps": 620, "total_steps": 816, "loss": 0.6339, "lr": 5e-06, "epoch": 2.276810265811182, "percentage": 75.98, "elapsed_time": "2:58:40", "remaining_time": "0:56:28"}
+{"current_steps": 630, "total_steps": 816, "loss": 0.636, "lr": 5e-06, "epoch": 2.313473877176902, "percentage": 77.21, "elapsed_time": "3:01:26", "remaining_time": "0:53:34"}
+{"current_steps": 640, "total_steps": 816, "loss": 0.6342, "lr": 5e-06, "epoch": 2.3501374885426216, "percentage": 78.43, "elapsed_time": "3:04:13", "remaining_time": "0:50:39"}
+{"current_steps": 650, "total_steps": 816, "loss": 0.637, "lr": 5e-06, "epoch": 2.386801099908341, "percentage": 79.66, "elapsed_time": "3:06:59", "remaining_time": "0:47:45"}
+{"current_steps": 660, "total_steps": 816, "loss": 0.63, "lr": 5e-06, "epoch": 2.4234647112740606, "percentage": 80.88, "elapsed_time": "3:09:44", "remaining_time": "0:44:50"}
+{"current_steps": 670, "total_steps": 816, "loss": 0.6288, "lr": 5e-06, "epoch": 2.46012832263978, "percentage": 82.11, "elapsed_time": "3:12:30", "remaining_time": "0:41:57"}
+{"current_steps": 680, "total_steps": 816, "loss": 0.6381, "lr": 5e-06, "epoch": 2.4967919340054996, "percentage": 83.33, "elapsed_time": "3:15:19", "remaining_time": "0:39:03"}
+{"current_steps": 690, "total_steps": 816, "loss": 0.6332, "lr": 5e-06, "epoch": 2.5334555453712193, "percentage": 84.56, "elapsed_time": "3:18:05", "remaining_time": "0:36:10"}
+{"current_steps": 700, "total_steps": 816, "loss": 0.6351, "lr": 5e-06, "epoch": 2.5701191567369386, "percentage": 85.78, "elapsed_time": "3:20:53", "remaining_time": "0:33:17"}
+{"current_steps": 710, "total_steps": 816, "loss": 0.6363, "lr": 5e-06, "epoch": 2.606782768102658, "percentage": 87.01, "elapsed_time": "3:23:40", "remaining_time": "0:30:24"}
+{"current_steps": 720, "total_steps": 816, "loss": 0.6355, "lr": 5e-06, "epoch": 2.6434463794683776, "percentage": 88.24, "elapsed_time": "3:26:27", "remaining_time": "0:27:31"}
+{"current_steps": 730, "total_steps": 816, "loss": 0.6351, "lr": 5e-06, "epoch": 2.6801099908340973, "percentage": 89.46, "elapsed_time": "3:29:12", "remaining_time": "0:24:38"}
+{"current_steps": 740, "total_steps": 816, "loss": 0.638, "lr": 5e-06, "epoch": 2.7167736021998166, "percentage": 90.69, "elapsed_time": "3:31:58", "remaining_time": "0:21:46"}
+{"current_steps": 750, "total_steps": 816, "loss": 0.6388, "lr": 5e-06, "epoch": 2.7534372135655363, "percentage": 91.91, "elapsed_time": "3:34:44", "remaining_time": "0:18:53"}
+{"current_steps": 760, "total_steps": 816, "loss": 0.6364, "lr": 5e-06, "epoch": 2.7901008249312556, "percentage": 93.14, "elapsed_time": "3:37:32", "remaining_time": "0:16:01"}
+{"current_steps": 770, "total_steps": 816, "loss": 0.6421, "lr": 5e-06, "epoch": 2.8267644362969753, "percentage": 94.36, "elapsed_time": "3:40:18", "remaining_time": "0:13:09"}
+{"current_steps": 780, "total_steps": 816, "loss": 0.6379, "lr": 5e-06, "epoch": 2.863428047662695, "percentage": 95.59, "elapsed_time": "3:43:05", "remaining_time": "0:10:17"}
+{"current_steps": 790, "total_steps": 816, "loss": 0.6414, "lr": 5e-06, "epoch": 2.9000916590284143, "percentage": 96.81, "elapsed_time": "3:45:51", "remaining_time": "0:07:25"}
+{"current_steps": 800, "total_steps": 816, "loss": 0.6361, "lr": 5e-06, "epoch": 2.936755270394134, "percentage": 98.04, "elapsed_time": "3:48:38", "remaining_time": "0:04:34"}
+{"current_steps": 810, "total_steps": 816, "loss": 0.6373, "lr": 5e-06, "epoch": 2.9734188817598532, "percentage": 99.26, "elapsed_time": "3:51:25", "remaining_time": "0:01:42"}
+{"current_steps": 816, "total_steps": 816, "eval_loss": 0.7332214117050171, "epoch": 2.9954170485792853, "percentage": 100.0, "elapsed_time": "3:55:44", "remaining_time": "0:00:00"}