Training in progress, epoch 3

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a07963d3036e90a675f05387fa9bb6c43eeb623e9e084bbde253fd38a5e2d8
+oid sha256:b161373ef5a44bcc6e0cdd088b6105e941089fa4f1ab7e86d4fe4365ce5b51e1
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9141e2d9a8587f290457a9478882587620f3d3f35b60f2c82ada6dab6e330b
+oid sha256:37b593f087584e6189b26da462075bc37a91be7d431044129cd2a83e6e3fb2bf
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd3b2907932dbf3a61cca99001eb0adc8ac1b8907694309d76a7d6dc0fc1f27
+oid sha256:0b385f7dc6279ccfe020d1c9f1e537295607bbdfd15a9b2ea7c0dafe9e4b430b
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3694c43e3155a1fe41616341c3b4bd1d3792c3408b9522946384e58166daab3a
+oid sha256:3a4167ab79b9ef9e92d684350619f1c8952b1c5b27128456c7574b3eaf2691da
 size 1089994880

trainer_log.jsonl

@@ -22,3 +22,13 @@
 {"current_steps": 22, "total_steps": 150, "loss": 0.4665, "lr": 3.973523064225159e-05, "epoch": 2.2, "percentage": 14.67, "elapsed_time": "0:14:41", "remaining_time": "1:25:28"}
 {"current_steps": 23, "total_steps": 150, "loss": 0.4194, "lr": 3.965441293412827e-05, "epoch": 2.3, "percentage": 15.33, "elapsed_time": "0:15:15", "remaining_time": "1:24:16"}
 {"current_steps": 24, "total_steps": 150, "loss": 0.4105, "lr": 3.9562952014676116e-05, "epoch": 2.4, "percentage": 16.0, "elapsed_time": "0:15:51", "remaining_time": "1:23:13"}
+{"current_steps": 25, "total_steps": 150, "loss": 0.433, "lr": 3.946089741159648e-05, "epoch": 2.5, "percentage": 16.67, "elapsed_time": "0:16:33", "remaining_time": "1:22:49"}
+{"current_steps": 26, "total_steps": 150, "loss": 0.4056, "lr": 3.934830438925728e-05, "epoch": 2.6, "percentage": 17.33, "elapsed_time": "0:17:12", "remaining_time": "1:22:05"}
+{"current_steps": 27, "total_steps": 150, "loss": 0.4483, "lr": 3.922523391876638e-05, "epoch": 2.7, "percentage": 18.0, "elapsed_time": "0:17:44", "remaining_time": "1:20:50"}
+{"current_steps": 28, "total_steps": 150, "loss": 0.4313, "lr": 3.909175264495464e-05, "epoch": 2.8, "percentage": 18.67, "elapsed_time": "0:18:13", "remaining_time": "1:19:23"}
+{"current_steps": 29, "total_steps": 150, "loss": 0.3754, "lr": 3.8947932850286585e-05, "epoch": 2.9, "percentage": 19.33, "elapsed_time": "0:18:47", "remaining_time": "1:18:23"}
+{"current_steps": 30, "total_steps": 150, "loss": 0.4333, "lr": 3.879385241571817e-05, "epoch": 3.0, "percentage": 20.0, "elapsed_time": "0:19:22", "remaining_time": "1:17:30"}
+{"current_steps": 31, "total_steps": 150, "loss": 0.295, "lr": 3.862959477852285e-05, "epoch": 3.1, "percentage": 20.67, "elapsed_time": "0:21:05", "remaining_time": "1:20:57"}
+{"current_steps": 32, "total_steps": 150, "loss": 0.2472, "lr": 3.845524888710885e-05, "epoch": 3.2, "percentage": 21.33, "elapsed_time": "0:21:36", "remaining_time": "1:19:40"}
+{"current_steps": 33, "total_steps": 150, "loss": 0.2934, "lr": 3.827090915285202e-05, "epoch": 3.3, "percentage": 22.0, "elapsed_time": "0:22:11", "remaining_time": "1:18:40"}
+{"current_steps": 34, "total_steps": 150, "loss": 0.3205, "lr": 3.807667539897041e-05, "epoch": 3.4, "percentage": 22.67, "elapsed_time": "0:22:53", "remaining_time": "1:18:04"}