Training in progress, epoch 4

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70467105358a5c7a1abb750bcff0669c16cd72db78ff229d5078935e47ed9798
+oid sha256:4e1d234500fb499859d4c3d6ba49beee61e5f55e0e4e260d1ad5b43af279eab6
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d596f6a40a3ef7321967ec3d94561d8e4b1853995fb6bef3879740dbd32decb
+oid sha256:57eca3d5c66151db3755f51e52c270bec0407f36518882723cfb068f4d9a7509
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124a7b8d81a91e2b5d587ffd30826a0596de61c4e2c56670998632d44f02dd52
+oid sha256:86ef76e310461d188fd50ae6c88b8f54b29d1a3ef39a57271172e6f45eb2204e
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22ecb7069b1c5ee5662deab761d29f57133c649892929a3c5de65df14c855cd
+oid sha256:66c7b03b41edd8c36b8587576a7776fe7c1c5ab2705ad7e32e2e703fe41d5a2d
 size 1089994880

trainer_log.jsonl

@@ -193,3 +193,49 @@
 {"current_steps": 193, "total_steps": 240, "loss": 0.4527, "lr": 8.987517708741364e-06, "epoch": 3.9896640826873386, "percentage": 80.42, "elapsed_time": "5:29:19", "remaining_time": "1:20:12"}
 {"current_steps": 194, "total_steps": 240, "loss": 0.4428, "lr": 8.623373403216972e-06, "epoch": 4.010335917312662, "percentage": 80.83, "elapsed_time": "5:32:51", "remaining_time": "1:18:55"}
 {"current_steps": 195, "total_steps": 240, "loss": 0.434, "lr": 8.265866388350598e-06, "epoch": 4.0310077519379846, "percentage": 81.25, "elapsed_time": "5:34:30", "remaining_time": "1:17:11"}
+{"current_steps": 196, "total_steps": 240, "loss": 0.4242, "lr": 7.915072289798247e-06, "epoch": 4.051679586563307, "percentage": 81.67, "elapsed_time": "5:36:11", "remaining_time": "1:15:28"}
+{"current_steps": 197, "total_steps": 240, "loss": 0.4334, "lr": 7.5710653131915125e-06, "epoch": 4.072351421188631, "percentage": 82.08, "elapsed_time": "5:37:51", "remaining_time": "1:13:44"}
+{"current_steps": 198, "total_steps": 240, "loss": 0.4357, "lr": 7.233918228440324e-06, "epoch": 4.093023255813954, "percentage": 82.5, "elapsed_time": "5:39:31", "remaining_time": "1:12:01"}
+{"current_steps": 199, "total_steps": 240, "loss": 0.4281, "lr": 6.903702354339578e-06, "epoch": 4.113695090439276, "percentage": 82.92, "elapsed_time": "5:41:11", "remaining_time": "1:10:17"}
+{"current_steps": 200, "total_steps": 240, "loss": 0.4372, "lr": 6.58048754348255e-06, "epoch": 4.134366925064599, "percentage": 83.33, "elapsed_time": "5:42:51", "remaining_time": "1:08:34"}
+{"current_steps": 201, "total_steps": 240, "loss": 0.4274, "lr": 6.26434216748458e-06, "epoch": 4.155038759689923, "percentage": 83.75, "elapsed_time": "5:44:30", "remaining_time": "1:06:50"}
+{"current_steps": 202, "total_steps": 240, "loss": 0.4303, "lr": 5.955333102520011e-06, "epoch": 4.1757105943152455, "percentage": 84.17, "elapsed_time": "5:46:10", "remaining_time": "1:05:07"}
+{"current_steps": 203, "total_steps": 240, "loss": 0.4281, "lr": 5.653525715175483e-06, "epoch": 4.196382428940568, "percentage": 84.58, "elapsed_time": "5:47:50", "remaining_time": "1:03:24"}
+{"current_steps": 204, "total_steps": 240, "loss": 0.4282, "lr": 5.358983848622452e-06, "epoch": 4.217054263565892, "percentage": 85.0, "elapsed_time": "5:49:30", "remaining_time": "1:01:40"}
+{"current_steps": 205, "total_steps": 240, "loss": 0.434, "lr": 5.07176980911217e-06, "epoch": 4.237726098191215, "percentage": 85.42, "elapsed_time": "5:51:10", "remaining_time": "0:59:57"}
+{"current_steps": 206, "total_steps": 240, "loss": 0.4305, "lr": 4.791944352795561e-06, "epoch": 4.258397932816537, "percentage": 85.83, "elapsed_time": "5:52:50", "remaining_time": "0:58:14"}
+{"current_steps": 207, "total_steps": 240, "loss": 0.4314, "lr": 4.519566672871132e-06, "epoch": 4.27906976744186, "percentage": 86.25, "elapsed_time": "5:54:30", "remaining_time": "0:56:30"}
+{"current_steps": 208, "total_steps": 240, "loss": 0.4303, "lr": 4.254694387063514e-06, "epoch": 4.299741602067184, "percentage": 86.67, "elapsed_time": "5:56:10", "remaining_time": "0:54:47"}
+{"current_steps": 209, "total_steps": 240, "loss": 0.4244, "lr": 3.997383525435154e-06, "epoch": 4.320413436692506, "percentage": 87.08, "elapsed_time": "5:57:50", "remaining_time": "0:53:04"}
+{"current_steps": 210, "total_steps": 240, "loss": 0.4332, "lr": 3.747688518534003e-06, "epoch": 4.341085271317829, "percentage": 87.5, "elapsed_time": "5:59:29", "remaining_time": "0:51:21"}
+{"current_steps": 211, "total_steps": 240, "loss": 0.4226, "lr": 3.5056621858794393e-06, "epoch": 4.361757105943153, "percentage": 87.92, "elapsed_time": "6:01:09", "remaining_time": "0:49:38"}
+{"current_steps": 212, "total_steps": 240, "loss": 0.4325, "lr": 3.2713557247890447e-06, "epoch": 4.3824289405684755, "percentage": 88.33, "elapsed_time": "6:02:49", "remaining_time": "0:47:55"}
+{"current_steps": 213, "total_steps": 240, "loss": 0.4327, "lr": 3.0448186995485307e-06, "epoch": 4.403100775193798, "percentage": 88.75, "elapsed_time": "6:04:28", "remaining_time": "0:46:12"}
+{"current_steps": 214, "total_steps": 240, "loss": 0.4192, "lr": 2.8260990309270987e-06, "epoch": 4.423772609819121, "percentage": 89.17, "elapsed_time": "6:06:08", "remaining_time": "0:44:29"}
+{"current_steps": 215, "total_steps": 240, "loss": 0.4335, "lr": 2.6152429860404647e-06, "epoch": 4.444444444444445, "percentage": 89.58, "elapsed_time": "6:07:49", "remaining_time": "0:42:46"}
+{"current_steps": 216, "total_steps": 240, "loss": 0.4281, "lr": 2.4122951685636674e-06, "epoch": 4.465116279069767, "percentage": 90.0, "elapsed_time": "6:09:28", "remaining_time": "0:41:03"}
+{"current_steps": 217, "total_steps": 240, "loss": 0.4268, "lr": 2.217298509295813e-06, "epoch": 4.48578811369509, "percentage": 90.42, "elapsed_time": "6:11:08", "remaining_time": "0:39:20"}
+{"current_steps": 218, "total_steps": 240, "loss": 0.4286, "lr": 2.0302942570786446e-06, "epoch": 4.506459948320414, "percentage": 90.83, "elapsed_time": "6:12:48", "remaining_time": "0:37:37"}
+{"current_steps": 219, "total_steps": 240, "loss": 0.43, "lr": 1.8513219700709272e-06, "epoch": 4.5271317829457365, "percentage": 91.25, "elapsed_time": "6:14:28", "remaining_time": "0:35:54"}
+{"current_steps": 220, "total_steps": 240, "loss": 0.4249, "lr": 1.6804195073804442e-06, "epoch": 4.547803617571059, "percentage": 91.67, "elapsed_time": "6:16:07", "remaining_time": "0:34:11"}
+{"current_steps": 221, "total_steps": 240, "loss": 0.4236, "lr": 1.5176230210554744e-06, "epoch": 4.568475452196383, "percentage": 92.08, "elapsed_time": "6:17:47", "remaining_time": "0:32:28"}
+{"current_steps": 222, "total_steps": 240, "loss": 0.4291, "lr": 1.3629669484372722e-06, "epoch": 4.589147286821706, "percentage": 92.5, "elapsed_time": "6:19:27", "remaining_time": "0:30:46"}
+{"current_steps": 223, "total_steps": 240, "loss": 0.4295, "lr": 1.2164840048753602e-06, "epoch": 4.609819121447028, "percentage": 92.92, "elapsed_time": "6:21:07", "remaining_time": "0:29:03"}
+{"current_steps": 224, "total_steps": 240, "loss": 0.4308, "lr": 1.0782051768070477e-06, "epoch": 4.630490956072351, "percentage": 93.33, "elapsed_time": "6:22:46", "remaining_time": "0:27:20"}
+{"current_steps": 225, "total_steps": 240, "loss": 0.4211, "lr": 9.481597152026656e-07, "epoch": 4.651162790697675, "percentage": 93.75, "elapsed_time": "6:24:26", "remaining_time": "0:25:37"}
+{"current_steps": 226, "total_steps": 240, "loss": 0.4225, "lr": 8.263751293779409e-07, "epoch": 4.671834625322997, "percentage": 94.17, "elapsed_time": "6:26:06", "remaining_time": "0:23:55"}
+{"current_steps": 227, "total_steps": 240, "loss": 0.4245, "lr": 7.128771811747737e-07, "epoch": 4.69250645994832, "percentage": 94.58, "elapsed_time": "6:27:46", "remaining_time": "0:22:12"}
+{"current_steps": 228, "total_steps": 240, "loss": 0.4307, "lr": 6.076898795116792e-07, "epoch": 4.713178294573644, "percentage": 95.0, "elapsed_time": "6:29:26", "remaining_time": "0:20:29"}
+{"current_steps": 229, "total_steps": 240, "loss": 0.4266, "lr": 5.108354753050381e-07, "epoch": 4.7338501291989665, "percentage": 95.42, "elapsed_time": "6:31:06", "remaining_time": "0:18:47"}
+{"current_steps": 230, "total_steps": 240, "loss": 0.4219, "lr": 4.223344567622212e-07, "epoch": 4.754521963824289, "percentage": 95.83, "elapsed_time": "6:32:46", "remaining_time": "0:17:04"}
+{"current_steps": 231, "total_steps": 240, "loss": 0.4294, "lr": 3.4220554504758475e-07, "epoch": 4.775193798449612, "percentage": 96.25, "elapsed_time": "6:34:26", "remaining_time": "0:15:22"}
+{"current_steps": 232, "total_steps": 240, "loss": 0.4301, "lr": 2.704656903222791e-07, "epoch": 4.795865633074936, "percentage": 96.67, "elapsed_time": "6:36:06", "remaining_time": "0:13:39"}
+{"current_steps": 233, "total_steps": 240, "loss": 0.4305, "lr": 2.0713006815868075e-07, "epoch": 4.816537467700258, "percentage": 97.08, "elapsed_time": "6:37:47", "remaining_time": "0:11:57"}
+{"current_steps": 234, "total_steps": 240, "loss": 0.4303, "lr": 1.522120763301782e-07, "epoch": 4.837209302325581, "percentage": 97.5, "elapsed_time": "6:39:27", "remaining_time": "0:10:14"}
+{"current_steps": 235, "total_steps": 240, "loss": 0.4249, "lr": 1.0572333197711005e-07, "epoch": 4.857881136950905, "percentage": 97.92, "elapsed_time": "6:41:07", "remaining_time": "0:08:32"}
+{"current_steps": 236, "total_steps": 240, "loss": 0.4279, "lr": 6.767366914927298e-08, "epoch": 4.8785529715762275, "percentage": 98.33, "elapsed_time": "6:42:48", "remaining_time": "0:06:49"}
+{"current_steps": 237, "total_steps": 240, "loss": 0.4264, "lr": 3.8071136725688074e-08, "epoch": 4.89922480620155, "percentage": 98.75, "elapsed_time": "6:44:27", "remaining_time": "0:05:07"}
+{"current_steps": 238, "total_steps": 240, "loss": 0.4218, "lr": 1.6921996711976028e-08, "epoch": 4.919896640826874, "percentage": 99.17, "elapsed_time": "6:46:07", "remaining_time": "0:03:24"}
+{"current_steps": 239, "total_steps": 240, "loss": 0.4293, "lr": 4.230722915701257e-09, "epoch": 4.940568475452197, "percentage": 99.58, "elapsed_time": "6:47:47", "remaining_time": "0:01:42"}
+{"current_steps": 240, "total_steps": 240, "loss": 0.4271, "lr": 0.0, "epoch": 4.961240310077519, "percentage": 100.0, "elapsed_time": "6:49:27", "remaining_time": "0:00:00"}
+{"current_steps": 240, "total_steps": 240, "epoch": 4.961240310077519, "percentage": 100.0, "elapsed_time": "6:52:17", "remaining_time": "0:00:00"}