Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d26db20409a2a127258cb3fc6e5dc255993b1bf1f4f34a67f6175951b8fdac8
+oid sha256:2de9de7281c675a53a66955d5ed1cc396f91d1c0aca7e09d9eb8098352c253c3
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff880e97d3c886926dfa1fc715677d2e94a5940fb850aa528e8acbde99aebc4
+oid sha256:6e3feaf6705ef7f7cd3dc8482e47cc71c41c1a307681a59c714a594f179bf29e
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3ce5afef9ae8cd3afbb076efdaff020ed0c75d40fd6cdd7232751078244625
+oid sha256:dda930595bb1fe2783cb0c30dd31b63786d95a1c447167b9d7264c285d4051a7
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddf909890ef13c44cec560aede09440b167668de9ea22b6a26a291532acb564
+oid sha256:6ab898e02acf426e550bf98d6058d1297673dc113d1b297765e740283887753b
 size 1168138808

trainer_log.jsonl

@@ -47,3 +47,26 @@
 {"current_steps": 460, "total_steps": 705, "loss": 0.5468, "lr": 5e-06, "epoch": 1.953365129835718, "percentage": 65.25, "elapsed_time": "4:08:56", "remaining_time": "2:12:35"}
 {"current_steps": 470, "total_steps": 705, "loss": 0.5378, "lr": 5e-06, "epoch": 1.9957604663487016, "percentage": 66.67, "elapsed_time": "4:14:17", "remaining_time": "2:07:08"}
 {"current_steps": 470, "total_steps": 705, "eval_loss": 0.5872675180435181, "epoch": 1.9957604663487016, "percentage": 66.67, "elapsed_time": "4:17:10", "remaining_time": "2:08:35"}
+{"current_steps": 480, "total_steps": 705, "loss": 0.5322, "lr": 5e-06, "epoch": 2.041335453100159, "percentage": 68.09, "elapsed_time": "4:23:40", "remaining_time": "2:03:35"}
+{"current_steps": 490, "total_steps": 705, "loss": 0.4803, "lr": 5e-06, "epoch": 2.0837307896131425, "percentage": 69.5, "elapsed_time": "4:29:00", "remaining_time": "1:58:01"}
+{"current_steps": 500, "total_steps": 705, "loss": 0.4798, "lr": 5e-06, "epoch": 2.126126126126126, "percentage": 70.92, "elapsed_time": "4:34:17", "remaining_time": "1:52:27"}
+{"current_steps": 510, "total_steps": 705, "loss": 0.4835, "lr": 5e-06, "epoch": 2.16852146263911, "percentage": 72.34, "elapsed_time": "4:39:35", "remaining_time": "1:46:54"}
+{"current_steps": 520, "total_steps": 705, "loss": 0.4882, "lr": 5e-06, "epoch": 2.210916799152093, "percentage": 73.76, "elapsed_time": "4:44:54", "remaining_time": "1:41:21"}
+{"current_steps": 530, "total_steps": 705, "loss": 0.4915, "lr": 5e-06, "epoch": 2.2533121356650767, "percentage": 75.18, "elapsed_time": "4:50:14", "remaining_time": "1:35:50"}
+{"current_steps": 540, "total_steps": 705, "loss": 0.4829, "lr": 5e-06, "epoch": 2.2957074721780604, "percentage": 76.6, "elapsed_time": "4:55:34", "remaining_time": "1:30:18"}
+{"current_steps": 550, "total_steps": 705, "loss": 0.4853, "lr": 5e-06, "epoch": 2.338102808691044, "percentage": 78.01, "elapsed_time": "5:00:52", "remaining_time": "1:24:47"}
+{"current_steps": 560, "total_steps": 705, "loss": 0.4841, "lr": 5e-06, "epoch": 2.3804981452040277, "percentage": 79.43, "elapsed_time": "5:06:12", "remaining_time": "1:19:17"}
+{"current_steps": 570, "total_steps": 705, "loss": 0.4821, "lr": 5e-06, "epoch": 2.4228934817170114, "percentage": 80.85, "elapsed_time": "5:11:31", "remaining_time": "1:13:47"}
+{"current_steps": 580, "total_steps": 705, "loss": 0.4951, "lr": 5e-06, "epoch": 2.4652888182299946, "percentage": 82.27, "elapsed_time": "5:16:50", "remaining_time": "1:08:17"}
+{"current_steps": 590, "total_steps": 705, "loss": 0.4808, "lr": 5e-06, "epoch": 2.5076841547429782, "percentage": 83.69, "elapsed_time": "5:22:10", "remaining_time": "1:02:47"}
+{"current_steps": 600, "total_steps": 705, "loss": 0.4858, "lr": 5e-06, "epoch": 2.550079491255962, "percentage": 85.11, "elapsed_time": "5:27:30", "remaining_time": "0:57:18"}
+{"current_steps": 610, "total_steps": 705, "loss": 0.4862, "lr": 5e-06, "epoch": 2.5924748277689456, "percentage": 86.52, "elapsed_time": "5:32:49", "remaining_time": "0:51:50"}
+{"current_steps": 620, "total_steps": 705, "loss": 0.4837, "lr": 5e-06, "epoch": 2.6348701642819288, "percentage": 87.94, "elapsed_time": "5:38:08", "remaining_time": "0:46:21"}
+{"current_steps": 630, "total_steps": 705, "loss": 0.4863, "lr": 5e-06, "epoch": 2.6772655007949124, "percentage": 89.36, "elapsed_time": "5:43:26", "remaining_time": "0:40:53"}
+{"current_steps": 640, "total_steps": 705, "loss": 0.4851, "lr": 5e-06, "epoch": 2.719660837307896, "percentage": 90.78, "elapsed_time": "5:48:43", "remaining_time": "0:35:25"}
+{"current_steps": 650, "total_steps": 705, "loss": 0.4834, "lr": 5e-06, "epoch": 2.7620561738208798, "percentage": 92.2, "elapsed_time": "5:54:01", "remaining_time": "0:29:57"}
+{"current_steps": 660, "total_steps": 705, "loss": 0.4813, "lr": 5e-06, "epoch": 2.8044515103338634, "percentage": 93.62, "elapsed_time": "5:59:20", "remaining_time": "0:24:30"}
+{"current_steps": 670, "total_steps": 705, "loss": 0.4839, "lr": 5e-06, "epoch": 2.846846846846847, "percentage": 95.04, "elapsed_time": "6:04:41", "remaining_time": "0:19:03"}
+{"current_steps": 680, "total_steps": 705, "loss": 0.4889, "lr": 5e-06, "epoch": 2.8892421833598303, "percentage": 96.45, "elapsed_time": "6:10:01", "remaining_time": "0:13:36"}
+{"current_steps": 690, "total_steps": 705, "loss": 0.4859, "lr": 5e-06, "epoch": 2.931637519872814, "percentage": 97.87, "elapsed_time": "6:15:20", "remaining_time": "0:08:09"}
+{"current_steps": 700, "total_steps": 705, "loss": 0.4895, "lr": 5e-06, "epoch": 2.9740328563857976, "percentage": 99.29, "elapsed_time": "6:20:41", "remaining_time": "0:02:43"}