Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6e4dede40ed2c470cd5516c076703fc136ca54fc423251694a795f8e54f7eed
+oid sha256:3c9f716ec9c551becf4f86d32e89036fd3e994acb780a1dfb2680bf727324cc4
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66db8969babdd57984e687252f472e4f523f4a0236b821962e61ab18e46b5250
+oid sha256:1e5c0b9ce486b524fe5795b42bc9654e79fb5cb8c531d2bb72f3f592af75fff9
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8c631a27a2bd63a595d2b88d5b9137efc89a1f1598b378186fbbb8d893f5fd
+oid sha256:e87872e3e229816d00fa34f0593006966cffaa9bfa20686b790a427eaed4e428
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:513bce7d17878bc7e1da0499bc1a2c7af26647b8096044a7869c028ceb5558e3
+oid sha256:a32284f4bd38cb691e5381f4349a0d5e2fbcba03305e84a3f07046a55d56d22c
 size 1168138808

trainer_log.jsonl

@@ -19,3 +19,24 @@
 {"current_steps": 190, "total_steps": 600, "loss": 0.8062, "lr": 5e-06, "epoch": 0.9488139825218477, "percentage": 31.67, "elapsed_time": "3:01:58", "remaining_time": "6:32:41"}
 {"current_steps": 200, "total_steps": 600, "loss": 0.7992, "lr": 5e-06, "epoch": 0.9987515605493134, "percentage": 33.33, "elapsed_time": "3:11:31", "remaining_time": "6:23:03"}
 {"current_steps": 200, "total_steps": 600, "eval_loss": 0.8015628457069397, "epoch": 0.9987515605493134, "percentage": 33.33, "elapsed_time": "3:15:18", "remaining_time": "6:30:36"}
+{"current_steps": 210, "total_steps": 600, "loss": 0.8245, "lr": 5e-06, "epoch": 1.048689138576779, "percentage": 35.0, "elapsed_time": "3:25:47", "remaining_time": "6:22:11"}
+{"current_steps": 220, "total_steps": 600, "loss": 0.7537, "lr": 5e-06, "epoch": 1.0986267166042447, "percentage": 36.67, "elapsed_time": "3:35:22", "remaining_time": "6:12:01"}
+{"current_steps": 230, "total_steps": 600, "loss": 0.7617, "lr": 5e-06, "epoch": 1.1485642946317103, "percentage": 38.33, "elapsed_time": "3:44:57", "remaining_time": "6:01:53"}
+{"current_steps": 240, "total_steps": 600, "loss": 0.7635, "lr": 5e-06, "epoch": 1.198501872659176, "percentage": 40.0, "elapsed_time": "3:54:31", "remaining_time": "5:51:46"}
+{"current_steps": 250, "total_steps": 600, "loss": 0.7623, "lr": 5e-06, "epoch": 1.2484394506866416, "percentage": 41.67, "elapsed_time": "4:04:05", "remaining_time": "5:41:43"}
+{"current_steps": 260, "total_steps": 600, "loss": 0.7567, "lr": 5e-06, "epoch": 1.2983770287141074, "percentage": 43.33, "elapsed_time": "4:13:39", "remaining_time": "5:31:42"}
+{"current_steps": 270, "total_steps": 600, "loss": 0.7606, "lr": 5e-06, "epoch": 1.348314606741573, "percentage": 45.0, "elapsed_time": "4:23:14", "remaining_time": "5:21:44"}
+{"current_steps": 280, "total_steps": 600, "loss": 0.7553, "lr": 5e-06, "epoch": 1.3982521847690386, "percentage": 46.67, "elapsed_time": "4:32:49", "remaining_time": "5:11:47"}
+{"current_steps": 290, "total_steps": 600, "loss": 0.7575, "lr": 5e-06, "epoch": 1.4481897627965044, "percentage": 48.33, "elapsed_time": "4:42:24", "remaining_time": "5:01:52"}
+{"current_steps": 300, "total_steps": 600, "loss": 0.7523, "lr": 5e-06, "epoch": 1.4981273408239701, "percentage": 50.0, "elapsed_time": "4:51:59", "remaining_time": "4:51:59"}
+{"current_steps": 310, "total_steps": 600, "loss": 0.759, "lr": 5e-06, "epoch": 1.5480649188514357, "percentage": 51.67, "elapsed_time": "5:01:34", "remaining_time": "4:42:07"}
+{"current_steps": 320, "total_steps": 600, "loss": 0.7532, "lr": 5e-06, "epoch": 1.5980024968789013, "percentage": 53.33, "elapsed_time": "5:11:10", "remaining_time": "4:32:16"}
+{"current_steps": 330, "total_steps": 600, "loss": 0.7652, "lr": 5e-06, "epoch": 1.647940074906367, "percentage": 55.0, "elapsed_time": "5:20:45", "remaining_time": "4:22:26"}
+{"current_steps": 340, "total_steps": 600, "loss": 0.7554, "lr": 5e-06, "epoch": 1.6978776529338329, "percentage": 56.67, "elapsed_time": "5:30:21", "remaining_time": "4:12:37"}
+{"current_steps": 350, "total_steps": 600, "loss": 0.757, "lr": 5e-06, "epoch": 1.7478152309612984, "percentage": 58.33, "elapsed_time": "5:39:57", "remaining_time": "4:02:49"}
+{"current_steps": 360, "total_steps": 600, "loss": 0.7576, "lr": 5e-06, "epoch": 1.797752808988764, "percentage": 60.0, "elapsed_time": "5:49:32", "remaining_time": "3:53:01"}
+{"current_steps": 370, "total_steps": 600, "loss": 0.7584, "lr": 5e-06, "epoch": 1.8476903870162298, "percentage": 61.67, "elapsed_time": "5:59:08", "remaining_time": "3:43:14"}
+{"current_steps": 380, "total_steps": 600, "loss": 0.755, "lr": 5e-06, "epoch": 1.8976279650436954, "percentage": 63.33, "elapsed_time": "6:08:43", "remaining_time": "3:33:28"}
+{"current_steps": 390, "total_steps": 600, "loss": 0.7478, "lr": 5e-06, "epoch": 1.947565543071161, "percentage": 65.0, "elapsed_time": "6:18:18", "remaining_time": "3:23:42"}
+{"current_steps": 400, "total_steps": 600, "loss": 0.7538, "lr": 5e-06, "epoch": 1.9975031210986267, "percentage": 66.67, "elapsed_time": "6:27:52", "remaining_time": "3:13:56"}
+{"current_steps": 400, "total_steps": 600, "eval_loss": 0.7874204516410828, "epoch": 1.9975031210986267, "percentage": 66.67, "elapsed_time": "6:31:51", "remaining_time": "3:15:55"}