Training in progress, epoch 3

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d7c6a3ee67585da16d2e083f3b2b9d10f85ca9997fab1f9b2bb4f653a6aa191
+oid sha256:7706e2610e3491c74a1466695843fad4b9867399d023de0acc93b271ac9426ab
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8b1b450e78262567a014e2f77628d27a48d9a211e5a9a83603274a5b850634
+oid sha256:7bda2e3f42cc73bb4f324352bd93ce023254e8bf11a0a198365622610a0c62fd
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a192f30760b2748972436cf7e3d57baeb5ff793bfb52a86691d020bf3d3f8d31
+oid sha256:b289a382021097966093b189ccc0f45a7e880497bbf66a8f18640299beb20f5c
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b25ea3795eae37c70c307cf6fcb53d9e7e4983a37820dffb3cb39de891db36
+oid sha256:e5d990eb555a627b4731d20f58887c3302d93b61329ec39cedad28142fc0f142
 size 1168138808

trainer_log.jsonl

@@ -48,3 +48,24 @@
 {"current_steps": 460, "total_steps": 678, "loss": 0.3519, "learning_rate": 5e-06, "epoch": 2.0353982300884956, "percentage": 67.85, "elapsed_time": "0:49:29", "remaining_time": "0:23:27"}
 {"current_steps": 470, "total_steps": 678, "loss": 0.343, "learning_rate": 5e-06, "epoch": 2.079646017699115, "percentage": 69.32, "elapsed_time": "0:50:28", "remaining_time": "0:22:20"}
 {"current_steps": 480, "total_steps": 678, "loss": 0.3441, "learning_rate": 5e-06, "epoch": 2.1238938053097347, "percentage": 70.8, "elapsed_time": "0:51:28", "remaining_time": "0:21:13"}
+{"current_steps": 490, "total_steps": 678, "loss": 0.3481, "learning_rate": 5e-06, "epoch": 2.168141592920354, "percentage": 72.27, "elapsed_time": "0:52:28", "remaining_time": "0:20:07"}
+{"current_steps": 500, "total_steps": 678, "loss": 0.3461, "learning_rate": 5e-06, "epoch": 2.2123893805309733, "percentage": 73.75, "elapsed_time": "0:53:27", "remaining_time": "0:19:01"}
+{"current_steps": 510, "total_steps": 678, "loss": 0.3466, "learning_rate": 5e-06, "epoch": 2.256637168141593, "percentage": 75.22, "elapsed_time": "0:54:26", "remaining_time": "0:17:56"}
+{"current_steps": 520, "total_steps": 678, "loss": 0.3463, "learning_rate": 5e-06, "epoch": 2.3008849557522124, "percentage": 76.7, "elapsed_time": "0:55:27", "remaining_time": "0:16:50"}
+{"current_steps": 530, "total_steps": 678, "loss": 0.3415, "learning_rate": 5e-06, "epoch": 2.3451327433628317, "percentage": 78.17, "elapsed_time": "0:56:28", "remaining_time": "0:15:46"}
+{"current_steps": 540, "total_steps": 678, "loss": 0.3493, "learning_rate": 5e-06, "epoch": 2.3893805309734515, "percentage": 79.65, "elapsed_time": "0:57:28", "remaining_time": "0:14:41"}
+{"current_steps": 550, "total_steps": 678, "loss": 0.3457, "learning_rate": 5e-06, "epoch": 2.433628318584071, "percentage": 81.12, "elapsed_time": "0:58:27", "remaining_time": "0:13:36"}
+{"current_steps": 560, "total_steps": 678, "loss": 0.351, "learning_rate": 5e-06, "epoch": 2.47787610619469, "percentage": 82.6, "elapsed_time": "0:59:27", "remaining_time": "0:12:31"}
+{"current_steps": 570, "total_steps": 678, "loss": 0.3474, "learning_rate": 5e-06, "epoch": 2.52212389380531, "percentage": 84.07, "elapsed_time": "1:00:26", "remaining_time": "0:11:27"}
+{"current_steps": 580, "total_steps": 678, "loss": 0.3468, "learning_rate": 5e-06, "epoch": 2.566371681415929, "percentage": 85.55, "elapsed_time": "1:01:26", "remaining_time": "0:10:22"}
+{"current_steps": 590, "total_steps": 678, "loss": 0.344, "learning_rate": 5e-06, "epoch": 2.6106194690265485, "percentage": 87.02, "elapsed_time": "1:02:26", "remaining_time": "0:09:18"}
+{"current_steps": 600, "total_steps": 678, "loss": 0.349, "learning_rate": 5e-06, "epoch": 2.6548672566371683, "percentage": 88.5, "elapsed_time": "1:03:25", "remaining_time": "0:08:14"}
+{"current_steps": 610, "total_steps": 678, "loss": 0.3492, "learning_rate": 5e-06, "epoch": 2.6991150442477876, "percentage": 89.97, "elapsed_time": "1:04:25", "remaining_time": "0:07:10"}
+{"current_steps": 620, "total_steps": 678, "loss": 0.3464, "learning_rate": 5e-06, "epoch": 2.7433628318584073, "percentage": 91.45, "elapsed_time": "1:05:25", "remaining_time": "0:06:07"}
+{"current_steps": 630, "total_steps": 678, "loss": 0.342, "learning_rate": 5e-06, "epoch": 2.7876106194690267, "percentage": 92.92, "elapsed_time": "1:06:26", "remaining_time": "0:05:03"}
+{"current_steps": 640, "total_steps": 678, "loss": 0.3506, "learning_rate": 5e-06, "epoch": 2.831858407079646, "percentage": 94.4, "elapsed_time": "1:07:26", "remaining_time": "0:04:00"}
+{"current_steps": 650, "total_steps": 678, "loss": 0.3482, "learning_rate": 5e-06, "epoch": 2.8761061946902657, "percentage": 95.87, "elapsed_time": "1:08:26", "remaining_time": "0:02:56"}
+{"current_steps": 660, "total_steps": 678, "loss": 0.3481, "learning_rate": 5e-06, "epoch": 2.920353982300885, "percentage": 97.35, "elapsed_time": "1:09:25", "remaining_time": "0:01:53"}
+{"current_steps": 670, "total_steps": 678, "loss": 0.3471, "learning_rate": 5e-06, "epoch": 2.9646017699115044, "percentage": 98.82, "elapsed_time": "1:10:25", "remaining_time": "0:00:50"}
+{"current_steps": 678, "total_steps": 678, "eval_loss": 0.3990846872329712, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:13:09", "remaining_time": "0:00:00"}
+{"current_steps": 678, "total_steps": 678, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:14:37", "remaining_time": "0:00:00"}