Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1318a1bcfdee31bc1b003ae95c6909d331852fd42216e93c5206e00197c7a864
+oid sha256:b6d7a102ad9a8b598ae2325fed66a75f7789364eaa4836a5218f6f9d3c285265
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed6b3c86b88bd406398907edca4f8776e7725a0d769800dadca1e3cb1f4c96e
+oid sha256:9b0489bab64b1ed59f3aeed670895dad9c872505544813d61a21ea49622c1994
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1706786e7076f88274f0f1d6b01c686ea11122bcede8c2dde3c2c3adda19e4
+oid sha256:66cb9091869a3b9a6582c458c300697d9e84b1841eb919e1d356231a79d9e0d0
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2acc545a2cb5fac4097c730fc60932ca14b7367f2fe0c6f7553ccbe975955098
+oid sha256:760d6aad32fa3d64996cf67d8d9434ef071825fe0d9e93661066b2278aa9bdbf
 size 1168138808

trainer_log.jsonl

@@ -45,3 +45,26 @@
 {"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"}
+{"current_steps": 460, "total_steps": 675, "loss": 0.3629, "lr": 5e-06, "epoch": 2.038781163434903, "percentage": 68.15, "elapsed_time": "4:13:44", "remaining_time": "1:58:35"}
+{"current_steps": 470, "total_steps": 675, "loss": 0.3425, "lr": 5e-06, "epoch": 2.0831024930747923, "percentage": 69.63, "elapsed_time": "4:19:04", "remaining_time": "1:53:00"}
+{"current_steps": 480, "total_steps": 675, "loss": 0.3458, "lr": 5e-06, "epoch": 2.1274238227146816, "percentage": 71.11, "elapsed_time": "4:24:24", "remaining_time": "1:47:25"}
+{"current_steps": 490, "total_steps": 675, "loss": 0.3487, "lr": 5e-06, "epoch": 2.1717451523545708, "percentage": 72.59, "elapsed_time": "4:29:45", "remaining_time": "1:41:50"}
+{"current_steps": 500, "total_steps": 675, "loss": 0.344, "lr": 5e-06, "epoch": 2.21606648199446, "percentage": 74.07, "elapsed_time": "4:35:05", "remaining_time": "1:36:16"}
+{"current_steps": 510, "total_steps": 675, "loss": 0.3469, "lr": 5e-06, "epoch": 2.260387811634349, "percentage": 75.56, "elapsed_time": "4:40:25", "remaining_time": "1:30:43"}
+{"current_steps": 520, "total_steps": 675, "loss": 0.344, "lr": 5e-06, "epoch": 2.3047091412742384, "percentage": 77.04, "elapsed_time": "4:45:45", "remaining_time": "1:25:10"}
+{"current_steps": 530, "total_steps": 675, "loss": 0.3422, "lr": 5e-06, "epoch": 2.349030470914127, "percentage": 78.52, "elapsed_time": "4:51:05", "remaining_time": "1:19:38"}
+{"current_steps": 540, "total_steps": 675, "loss": 0.3481, "lr": 5e-06, "epoch": 2.393351800554017, "percentage": 80.0, "elapsed_time": "4:56:26", "remaining_time": "1:14:06"}
+{"current_steps": 550, "total_steps": 675, "loss": 0.3475, "lr": 5e-06, "epoch": 2.4376731301939056, "percentage": 81.48, "elapsed_time": "5:01:47", "remaining_time": "1:08:35"}
+{"current_steps": 560, "total_steps": 675, "loss": 0.35, "lr": 5e-06, "epoch": 2.481994459833795, "percentage": 82.96, "elapsed_time": "5:07:07", "remaining_time": "1:03:04"}
+{"current_steps": 570, "total_steps": 675, "loss": 0.3466, "lr": 5e-06, "epoch": 2.526315789473684, "percentage": 84.44, "elapsed_time": "5:12:27", "remaining_time": "0:57:33"}
+{"current_steps": 580, "total_steps": 675, "loss": 0.3459, "lr": 5e-06, "epoch": 2.5706371191135733, "percentage": 85.93, "elapsed_time": "5:17:46", "remaining_time": "0:52:02"}
+{"current_steps": 590, "total_steps": 675, "loss": 0.3448, "lr": 5e-06, "epoch": 2.6149584487534625, "percentage": 87.41, "elapsed_time": "5:23:07", "remaining_time": "0:46:33"}
+{"current_steps": 600, "total_steps": 675, "loss": 0.3482, "lr": 5e-06, "epoch": 2.6592797783933517, "percentage": 88.89, "elapsed_time": "5:28:29", "remaining_time": "0:41:03"}
+{"current_steps": 610, "total_steps": 675, "loss": 0.3481, "lr": 5e-06, "epoch": 2.703601108033241, "percentage": 90.37, "elapsed_time": "5:33:49", "remaining_time": "0:35:34"}
+{"current_steps": 620, "total_steps": 675, "loss": 0.3474, "lr": 5e-06, "epoch": 2.74792243767313, "percentage": 91.85, "elapsed_time": "5:39:11", "remaining_time": "0:30:05"}
+{"current_steps": 630, "total_steps": 675, "loss": 0.3429, "lr": 5e-06, "epoch": 2.7922437673130194, "percentage": 93.33, "elapsed_time": "5:44:32", "remaining_time": "0:24:36"}
+{"current_steps": 640, "total_steps": 675, "loss": 0.3491, "lr": 5e-06, "epoch": 2.8365650969529086, "percentage": 94.81, "elapsed_time": "5:49:53", "remaining_time": "0:19:08"}
+{"current_steps": 650, "total_steps": 675, "loss": 0.3479, "lr": 5e-06, "epoch": 2.880886426592798, "percentage": 96.3, "elapsed_time": "5:55:13", "remaining_time": "0:13:39"}
+{"current_steps": 660, "total_steps": 675, "loss": 0.3472, "lr": 5e-06, "epoch": 2.925207756232687, "percentage": 97.78, "elapsed_time": "6:00:33", "remaining_time": "0:08:11"}
+{"current_steps": 670, "total_steps": 675, "loss": 0.3467, "lr": 5e-06, "epoch": 2.9695290858725762, "percentage": 99.26, "elapsed_time": "6:05:53", "remaining_time": "0:02:43"}
+{"current_steps": 675, "total_steps": 675, "eval_loss": 0.39780595898628235, "epoch": 2.9916897506925206, "percentage": 100.0, "elapsed_time": "6:12:28", "remaining_time": "0:00:00"}