Training in progress, epoch 5

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d07c508e5ed1e87fe7b20be9c94c44d5894a1644f284a589b7d65caf4b1214
+oid sha256:4c8f0b31a9171cf140b406249e40c435a116e784a53339c063d93687b599776b
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a76a7f22ba97508e19406ab9cc110857d58d4ce2eca3dfe752acd5e3c763f4e
+oid sha256:8de240848b8c5d50f016657c383c842859d874a69252457f97839a9a279fb90e
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8407819e448add54fc838865094880efa892c494f0b9ba05eb738e99abf8cacf
+oid sha256:ad8d5911f73d304c01f44cf594c0b78e1d8bd7f7049a731fc6b648e902863358
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f173146e907841c6f3c3856410ec6a267592727d1ca2c51697e02c808dff863
+oid sha256:055d635c01f5b023a8baa4e91ba674e3cbab4784bd85b63695943cde45d8aefd
 size 1089994880

trainer_log.jsonl

@@ -162,3 +162,36 @@
 {"current_steps": 162, "total_steps": 224, "loss": 0.4664, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:31:30", "remaining_time": "2:06:52"}
 {"current_steps": 163, "total_steps": 224, "loss": 0.4652, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:33:32", "remaining_time": "2:04:49"}
 {"current_steps": 164, "total_steps": 224, "loss": 0.4434, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:36:40", "remaining_time": "2:03:10"}
+{"current_steps": 165, "total_steps": 224, "loss": 0.4173, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "5:38:32", "remaining_time": "2:01:03"}
+{"current_steps": 166, "total_steps": 224, "loss": 0.4278, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "5:40:33", "remaining_time": "1:58:59"}
+{"current_steps": 167, "total_steps": 224, "loss": 0.4399, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "5:42:22", "remaining_time": "1:56:51"}
+{"current_steps": 168, "total_steps": 224, "loss": 0.4347, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "5:44:28", "remaining_time": "1:54:49"}
+{"current_steps": 169, "total_steps": 224, "loss": 0.4362, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "5:46:20", "remaining_time": "1:52:42"}
+{"current_steps": 170, "total_steps": 224, "loss": 0.4277, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "5:48:29", "remaining_time": "1:50:41"}
+{"current_steps": 171, "total_steps": 224, "loss": 0.425, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "5:50:32", "remaining_time": "1:48:38"}
+{"current_steps": 172, "total_steps": 224, "loss": 0.4177, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "5:52:35", "remaining_time": "1:46:35"}
+{"current_steps": 173, "total_steps": 224, "loss": 0.4194, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "5:54:38", "remaining_time": "1:44:32"}
+{"current_steps": 174, "total_steps": 224, "loss": 0.4345, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "5:56:35", "remaining_time": "1:42:28"}
+{"current_steps": 175, "total_steps": 224, "loss": 0.4324, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "5:58:40", "remaining_time": "1:40:25"}
+{"current_steps": 176, "total_steps": 224, "loss": 0.4175, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "6:00:51", "remaining_time": "1:38:25"}
+{"current_steps": 177, "total_steps": 224, "loss": 0.4375, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "6:02:54", "remaining_time": "1:36:21"}
+{"current_steps": 178, "total_steps": 224, "loss": 0.4247, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "6:04:50", "remaining_time": "1:34:17"}
+{"current_steps": 179, "total_steps": 224, "loss": 0.4427, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "6:07:00", "remaining_time": "1:32:15"}
+{"current_steps": 180, "total_steps": 224, "loss": 0.4336, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "6:08:59", "remaining_time": "1:30:11"}
+{"current_steps": 181, "total_steps": 224, "loss": 0.4144, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "6:11:05", "remaining_time": "1:28:09"}
+{"current_steps": 182, "total_steps": 224, "loss": 0.4214, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "6:13:13", "remaining_time": "1:26:07"}
+{"current_steps": 183, "total_steps": 224, "loss": 0.4213, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "6:15:18", "remaining_time": "1:24:05"}
+{"current_steps": 184, "total_steps": 224, "loss": 0.4117, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "6:17:24", "remaining_time": "1:22:02"}
+{"current_steps": 185, "total_steps": 224, "loss": 0.4173, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "6:19:26", "remaining_time": "1:19:59"}
+{"current_steps": 186, "total_steps": 224, "loss": 0.4463, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "6:21:28", "remaining_time": "1:17:56"}
+{"current_steps": 187, "total_steps": 224, "loss": 0.4206, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "6:23:27", "remaining_time": "1:15:52"}
+{"current_steps": 188, "total_steps": 224, "loss": 0.4101, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "6:25:34", "remaining_time": "1:13:49"}
+{"current_steps": 189, "total_steps": 224, "loss": 0.4155, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "6:27:31", "remaining_time": "1:11:45"}
+{"current_steps": 190, "total_steps": 224, "loss": 0.4138, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "6:29:20", "remaining_time": "1:09:40"}
+{"current_steps": 191, "total_steps": 224, "loss": 0.4058, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "6:31:29", "remaining_time": "1:07:38"}
+{"current_steps": 192, "total_steps": 224, "loss": 0.4126, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "6:33:38", "remaining_time": "1:05:36"}
+{"current_steps": 193, "total_steps": 224, "loss": 0.4442, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "6:35:37", "remaining_time": "1:03:32"}
+{"current_steps": 194, "total_steps": 224, "loss": 0.4289, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "6:37:45", "remaining_time": "1:01:30"}
+{"current_steps": 195, "total_steps": 224, "loss": 0.4321, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "6:39:52", "remaining_time": "0:59:28"}
+{"current_steps": 196, "total_steps": 224, "loss": 0.4228, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "6:41:51", "remaining_time": "0:57:24"}
+{"current_steps": 197, "total_steps": 224, "loss": 0.4075, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "6:45:01", "remaining_time": "0:55:30"}