Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b989ae2cd8dfbebf3600ae0d10a8be54576226a209dfc37065b4e75e7bf67c
+oid sha256:359ab46827567226a45733260a1e3efb688fe5a83b3b00d83feadb3401e9db0c
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d908104781f6476c9d6f32a4eb5e789c3b0267a2f924cd1d77e67cc8e0012707
+oid sha256:118fe442d44ade1d071ebd31e5c3c664c0ab118dce58f55f7c00feebfa67a25f
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3897a1df82203d62f7b172228700379345a52b78a4ef64bae7c4441cca634d50
+oid sha256:c3c011bfa2ec71a5cbaf5a9e273542385cb2d12ee51a93269701ac64eec3e25f
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfedd080e670864ae79e961bad567d768003994a16d0d47c0bee081880aee3c6
+oid sha256:cf4fd8a4d9b07245613401a1b4655c5cd4aeceaa20b798f75696685527f0fafe
 size 1089994880

trainer_log.jsonl

@@ -20,3 +20,14 @@
 {"current_steps": 20, "total_steps": 70, "loss": 0.7109, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:41:53", "remaining_time": "1:44:43"}
 {"current_steps": 21, "total_steps": 70, "loss": 0.7042, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:44:37", "remaining_time": "1:44:08"}
 {"current_steps": 22, "total_steps": 70, "loss": 0.6792, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:46:39", "remaining_time": "1:41:48"}
+{"current_steps": 23, "total_steps": 70, "loss": 0.6637, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:48:42", "remaining_time": "1:39:32"}
+{"current_steps": 24, "total_steps": 70, "loss": 0.664, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:50:37", "remaining_time": "1:37:02"}
+{"current_steps": 25, "total_steps": 70, "loss": 0.6436, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "0:52:38", "remaining_time": "1:34:46"}
+{"current_steps": 26, "total_steps": 70, "loss": 0.6395, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "0:54:33", "remaining_time": "1:32:19"}
+{"current_steps": 27, "total_steps": 70, "loss": 0.654, "lr": 1.5425462638657597e-05, "epoch": 2.592, "percentage": 38.57, "elapsed_time": "0:56:27", "remaining_time": "1:29:54"}
+{"current_steps": 28, "total_steps": 70, "loss": 0.6272, "lr": 1.5000000000000002e-05, "epoch": 2.6879999999999997, "percentage": 40.0, "elapsed_time": "0:58:40", "remaining_time": "1:28:01"}
+{"current_steps": 29, "total_steps": 70, "loss": 0.6459, "lr": 1.4562106573531632e-05, "epoch": 2.784, "percentage": 41.43, "elapsed_time": "1:00:52", "remaining_time": "1:26:04"}
+{"current_steps": 30, "total_steps": 70, "loss": 0.6232, "lr": 1.4112871031306118e-05, "epoch": 2.88, "percentage": 42.86, "elapsed_time": "1:02:56", "remaining_time": "1:23:55"}
+{"current_steps": 31, "total_steps": 70, "loss": 0.6246, "lr": 1.3653410243663953e-05, "epoch": 2.976, "percentage": 44.29, "elapsed_time": "1:04:57", "remaining_time": "1:21:42"}
+{"current_steps": 32, "total_steps": 70, "loss": 0.6002, "lr": 1.3184866502516846e-05, "epoch": 3.072, "percentage": 45.71, "elapsed_time": "1:07:42", "remaining_time": "1:20:24"}
+{"current_steps": 33, "total_steps": 70, "loss": 0.5944, "lr": 1.2708404681430054e-05, "epoch": 3.168, "percentage": 47.14, "elapsed_time": "1:09:47", "remaining_time": "1:18:15"}