Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8454cf8736a5523a2d56413862d68c4724fcca03b5bc2fb041a0973ba60658c
+oid sha256:1318a1bcfdee31bc1b003ae95c6909d331852fd42216e93c5206e00197c7a864
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2fe15899951aae4292dfa05af3ac2f9e3a9e3a239433dcd37b55e8cd1f26cd
+oid sha256:5ed6b3c86b88bd406398907edca4f8776e7725a0d769800dadca1e3cb1f4c96e
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f923ddac1d9de60f3059d228589950883aa72ac1c53c25e2e5559dd03c44f9
+oid sha256:1b1706786e7076f88274f0f1d6b01c686ea11122bcede8c2dde3c2c3adda19e4
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce77f49733d54a177e3b98f136ad8233dc8747cfc071be749d139bd1f763fa57
+oid sha256:2acc545a2cb5fac4097c730fc60932ca14b7367f2fe0c6f7553ccbe975955098
 size 1168138808

trainer_log.jsonl

@@ -22,3 +22,26 @@
 {"current_steps": 220, "total_steps": 675, "loss": 0.4061, "lr": 5e-06, "epoch": 0.9750692520775623, "percentage": 32.59, "elapsed_time": "1:57:26", "remaining_time": "4:02:52"}
 {"current_steps": 225, "total_steps": 675, "eval_loss": 0.4077036678791046, "epoch": 0.997229916897507, "percentage": 33.33, "elapsed_time": "2:03:03", "remaining_time": "4:06:07"}
 {"current_steps": 230, "total_steps": 675, "loss": 0.4093, "lr": 5e-06, "epoch": 1.0193905817174516, "percentage": 34.07, "elapsed_time": "2:06:40", "remaining_time": "4:05:04"}
+{"current_steps": 240, "total_steps": 675, "loss": 0.3815, "lr": 5e-06, "epoch": 1.0637119113573408, "percentage": 35.56, "elapsed_time": "2:12:01", "remaining_time": "3:59:17"}
+{"current_steps": 250, "total_steps": 675, "loss": 0.3761, "lr": 5e-06, "epoch": 1.10803324099723, "percentage": 37.04, "elapsed_time": "2:17:22", "remaining_time": "3:53:31"}
+{"current_steps": 260, "total_steps": 675, "loss": 0.3818, "lr": 5e-06, "epoch": 1.1523545706371192, "percentage": 38.52, "elapsed_time": "2:22:45", "remaining_time": "3:47:51"}
+{"current_steps": 270, "total_steps": 675, "loss": 0.3792, "lr": 5e-06, "epoch": 1.1966759002770084, "percentage": 40.0, "elapsed_time": "2:28:07", "remaining_time": "3:42:11"}
+{"current_steps": 280, "total_steps": 675, "loss": 0.3768, "lr": 5e-06, "epoch": 1.2409972299168974, "percentage": 41.48, "elapsed_time": "2:33:29", "remaining_time": "3:36:32"}
+{"current_steps": 290, "total_steps": 675, "loss": 0.3813, "lr": 5e-06, "epoch": 1.2853185595567866, "percentage": 42.96, "elapsed_time": "2:38:51", "remaining_time": "3:30:53"}
+{"current_steps": 300, "total_steps": 675, "loss": 0.3819, "lr": 5e-06, "epoch": 1.3296398891966759, "percentage": 44.44, "elapsed_time": "2:44:12", "remaining_time": "3:25:15"}
+{"current_steps": 310, "total_steps": 675, "loss": 0.38, "lr": 5e-06, "epoch": 1.373961218836565, "percentage": 45.93, "elapsed_time": "2:49:34", "remaining_time": "3:19:39"}
+{"current_steps": 320, "total_steps": 675, "loss": 0.3755, "lr": 5e-06, "epoch": 1.4182825484764543, "percentage": 47.41, "elapsed_time": "2:54:57", "remaining_time": "3:14:05"}
+{"current_steps": 330, "total_steps": 675, "loss": 0.3808, "lr": 5e-06, "epoch": 1.4626038781163435, "percentage": 48.89, "elapsed_time": "3:00:19", "remaining_time": "3:08:31"}
+{"current_steps": 340, "total_steps": 675, "loss": 0.3778, "lr": 5e-06, "epoch": 1.5069252077562327, "percentage": 50.37, "elapsed_time": "3:05:41", "remaining_time": "3:02:57"}
+{"current_steps": 350, "total_steps": 675, "loss": 0.3779, "lr": 5e-06, "epoch": 1.5512465373961217, "percentage": 51.85, "elapsed_time": "3:11:03", "remaining_time": "2:57:24"}
+{"current_steps": 360, "total_steps": 675, "loss": 0.374, "lr": 5e-06, "epoch": 1.595567867036011, "percentage": 53.33, "elapsed_time": "3:16:24", "remaining_time": "2:51:51"}
+{"current_steps": 370, "total_steps": 675, "loss": 0.3776, "lr": 5e-06, "epoch": 1.6398891966759002, "percentage": 54.81, "elapsed_time": "3:21:46", "remaining_time": "2:46:19"}
+{"current_steps": 380, "total_steps": 675, "loss": 0.3805, "lr": 5e-06, "epoch": 1.6842105263157894, "percentage": 56.3, "elapsed_time": "3:27:08", "remaining_time": "2:40:48"}
+{"current_steps": 390, "total_steps": 675, "loss": 0.3776, "lr": 5e-06, "epoch": 1.7285318559556786, "percentage": 57.78, "elapsed_time": "3:32:30", "remaining_time": "2:35:17"}
+{"current_steps": 400, "total_steps": 675, "loss": 0.3759, "lr": 5e-06, "epoch": 1.7728531855955678, "percentage": 59.26, "elapsed_time": "3:37:52", "remaining_time": "2:29:47"}
+{"current_steps": 410, "total_steps": 675, "loss": 0.3797, "lr": 5e-06, "epoch": 1.817174515235457, "percentage": 60.74, "elapsed_time": "3:43:12", "remaining_time": "2:24:16"}
+{"current_steps": 420, "total_steps": 675, "loss": 0.3736, "lr": 5e-06, "epoch": 1.8614958448753463, "percentage": 62.22, "elapsed_time": "3:48:33", "remaining_time": "2:18:46"}
+{"current_steps": 430, "total_steps": 675, "loss": 0.3761, "lr": 5e-06, "epoch": 1.9058171745152355, "percentage": 63.7, "elapsed_time": "3:53:56", "remaining_time": "2:13:17"}
+{"current_steps": 440, "total_steps": 675, "loss": 0.3731, "lr": 5e-06, "epoch": 1.9501385041551247, "percentage": 65.19, "elapsed_time": "3:59:17", "remaining_time": "2:07:48"}
+{"current_steps": 450, "total_steps": 675, "loss": 0.3726, "lr": 5e-06, "epoch": 1.994459833795014, "percentage": 66.67, "elapsed_time": "4:04:37", "remaining_time": "2:02:18"}
+{"current_steps": 451, "total_steps": 675, "eval_loss": 0.3975733816623688, "epoch": 1.9988919667590028, "percentage": 66.81, "elapsed_time": "4:07:48", "remaining_time": "2:03:04"}