Training in progress, epoch 2

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d027ef296f8f81aec7701e696cfa92375a2afb2685e6235a6ce79d92f41f04
+oid sha256:0124aedd7cba1285a307da8b9109520e8a4f8b90749fe759ee50d3905da63670
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28fc8da213b137dd03f89a2913a699b3ca1b73bcf7446c989759318e5138ed84
+oid sha256:60e024be4c8eb9794ae9c99d49b61904688ad04f5990bf159f9178f362da9b27
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b027a4dd7560f1273571d1ad213489cfe4b104d0b88e244a73745cfa1565fe
+oid sha256:9a9fbb504297a4cfef414964aef0a0f01510c60b4c05a572964811f11d8d680a
 size 4540516344

trainer_log.jsonl

@@ -25,3 +25,15 @@
 {"current_steps": 240, "total_steps": 369, "loss": 0.5102, "learning_rate": 5e-06, "epoch": 1.9433198380566803, "percentage": 65.04, "elapsed_time": "3:51:28", "remaining_time": "2:04:25"}
 {"current_steps": 247, "total_steps": 369, "eval_loss": 0.06831000745296478, "epoch": 2.0, "percentage": 66.94, "elapsed_time": "4:00:11", "remaining_time": "1:58:38"}
 {"current_steps": 250, "total_steps": 369, "loss": 0.4952, "learning_rate": 5e-06, "epoch": 2.0242914979757085, "percentage": 67.75, "elapsed_time": "4:03:49", "remaining_time": "1:56:03"}
+{"current_steps": 260, "total_steps": 369, "loss": 0.4582, "learning_rate": 5e-06, "epoch": 2.1052631578947367, "percentage": 70.46, "elapsed_time": "4:13:20", "remaining_time": "1:46:12"}
+{"current_steps": 270, "total_steps": 369, "loss": 0.4596, "learning_rate": 5e-06, "epoch": 2.1862348178137654, "percentage": 73.17, "elapsed_time": "4:22:51", "remaining_time": "1:36:23"}
+{"current_steps": 280, "total_steps": 369, "loss": 0.4599, "learning_rate": 5e-06, "epoch": 2.2672064777327936, "percentage": 75.88, "elapsed_time": "4:32:23", "remaining_time": "1:26:34"}
+{"current_steps": 290, "total_steps": 369, "loss": 0.4623, "learning_rate": 5e-06, "epoch": 2.348178137651822, "percentage": 78.59, "elapsed_time": "4:41:53", "remaining_time": "1:16:47"}
+{"current_steps": 300, "total_steps": 369, "loss": 0.4637, "learning_rate": 5e-06, "epoch": 2.42914979757085, "percentage": 81.3, "elapsed_time": "4:51:24", "remaining_time": "1:07:01"}
+{"current_steps": 310, "total_steps": 369, "loss": 0.4649, "learning_rate": 5e-06, "epoch": 2.5101214574898787, "percentage": 84.01, "elapsed_time": "5:00:56", "remaining_time": "0:57:16"}
+{"current_steps": 320, "total_steps": 369, "loss": 0.4618, "learning_rate": 5e-06, "epoch": 2.591093117408907, "percentage": 86.72, "elapsed_time": "5:10:27", "remaining_time": "0:47:32"}
+{"current_steps": 330, "total_steps": 369, "loss": 0.4669, "learning_rate": 5e-06, "epoch": 2.672064777327935, "percentage": 89.43, "elapsed_time": "5:19:59", "remaining_time": "0:37:49"}
+{"current_steps": 340, "total_steps": 369, "loss": 0.4674, "learning_rate": 5e-06, "epoch": 2.753036437246964, "percentage": 92.14, "elapsed_time": "5:29:31", "remaining_time": "0:28:06"}
+{"current_steps": 350, "total_steps": 369, "loss": 0.4647, "learning_rate": 5e-06, "epoch": 2.834008097165992, "percentage": 94.85, "elapsed_time": "5:39:02", "remaining_time": "0:18:24"}
+{"current_steps": 360, "total_steps": 369, "loss": 0.4643, "learning_rate": 5e-06, "epoch": 2.91497975708502, "percentage": 97.56, "elapsed_time": "5:48:33", "remaining_time": "0:08:42"}
+{"current_steps": 369, "total_steps": 369, "eval_loss": 0.06875835359096527, "epoch": 2.9878542510121457, "percentage": 100.0, "elapsed_time": "6:00:01", "remaining_time": "0:00:00"}