Training in progress, epoch 6

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf0127afb1384753b82df08e7b3a1a242d123a05168962cd7577070f9a99bf8
+oid sha256:9b4ac4eb32f31dd2550665464b9a4d2c8590a9bbaaf47c594c03dc2409a24eee
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d18c6369f1b24577c1b54f6c0e8da634f111be9f0349b60788a1d7e20ce749e
+oid sha256:3cd2a411383ca158893ced50f4bb69e50b7b05f1f7aca0c8cf17d1f2fa4e8d1e
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5144ce42cbbc7af46a3421d1f4eeab383da76caff83eb08b03c774ddaed13f
+oid sha256:9f6afdf81206a949b4bf9640e7e841acaf29f01c1deaaa1ea17083cb32477fc9
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd863766433ef8e9f95af1aacaaa3ca43085302f895658698276ecb27295190
+oid sha256:622159e69e7f77594d2bb496ff33394e12cd7bfe7fcd7d0f2368e1c45b181148
 size 1089994880

trainer_log.jsonl

@@ -166,3 +166,36 @@
 {"current_steps": 166, "total_steps": 231, "loss": 0.2883, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:44:03", "remaining_time": "0:40:44"}
 {"current_steps": 167, "total_steps": 231, "loss": 0.2825, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:44:37", "remaining_time": "0:40:05"}
 {"current_steps": 168, "total_steps": 231, "loss": 0.2785, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:45:11", "remaining_time": "0:39:26"}
+{"current_steps": 169, "total_steps": 231, "loss": 0.2728, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:45:43", "remaining_time": "0:38:47"}
+{"current_steps": 170, "total_steps": 231, "loss": 0.2863, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:46:17", "remaining_time": "0:38:08"}
+{"current_steps": 171, "total_steps": 231, "loss": 0.299, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:46:51", "remaining_time": "0:37:29"}
+{"current_steps": 172, "total_steps": 231, "loss": 0.2813, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:47:24", "remaining_time": "0:36:50"}
+{"current_steps": 173, "total_steps": 231, "loss": 0.2755, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:47:59", "remaining_time": "0:36:12"}
+{"current_steps": 174, "total_steps": 231, "loss": 0.2863, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:48:33", "remaining_time": "0:35:33"}
+{"current_steps": 175, "total_steps": 231, "loss": 0.2817, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:49:08", "remaining_time": "0:34:55"}
+{"current_steps": 176, "total_steps": 231, "loss": 0.28, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:49:41", "remaining_time": "0:34:16"}
+{"current_steps": 177, "total_steps": 231, "loss": 0.2766, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:50:16", "remaining_time": "0:33:38"}
+{"current_steps": 178, "total_steps": 231, "loss": 0.2764, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:50:49", "remaining_time": "0:32:59"}
+{"current_steps": 179, "total_steps": 231, "loss": 0.2824, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:51:23", "remaining_time": "0:32:21"}
+{"current_steps": 180, "total_steps": 231, "loss": 0.2809, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:51:56", "remaining_time": "0:31:42"}
+{"current_steps": 181, "total_steps": 231, "loss": 0.2762, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:52:29", "remaining_time": "0:31:04"}
+{"current_steps": 182, "total_steps": 231, "loss": 0.2857, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:53:02", "remaining_time": "0:30:26"}
+{"current_steps": 183, "total_steps": 231, "loss": 0.2803, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:53:35", "remaining_time": "0:29:47"}
+{"current_steps": 184, "total_steps": 231, "loss": 0.2843, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:54:09", "remaining_time": "0:29:09"}
+{"current_steps": 185, "total_steps": 231, "loss": 0.2733, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:54:42", "remaining_time": "0:28:31"}
+{"current_steps": 186, "total_steps": 231, "loss": 0.2859, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:55:16", "remaining_time": "0:27:53"}
+{"current_steps": 187, "total_steps": 231, "loss": 0.2776, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:55:50", "remaining_time": "0:27:15"}
+{"current_steps": 188, "total_steps": 231, "loss": 0.2674, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:56:23", "remaining_time": "0:26:37"}
+{"current_steps": 189, "total_steps": 231, "loss": 0.2734, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "1:56:56", "remaining_time": "0:25:59"}
+{"current_steps": 190, "total_steps": 231, "loss": 0.2797, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:57:28", "remaining_time": "0:25:21"}
+{"current_steps": 191, "total_steps": 231, "loss": 0.279, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "1:58:02", "remaining_time": "0:24:43"}
+{"current_steps": 192, "total_steps": 231, "loss": 0.2608, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "1:58:36", "remaining_time": "0:24:05"}
+{"current_steps": 193, "total_steps": 231, "loss": 0.2775, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "1:59:09", "remaining_time": "0:23:27"}
+{"current_steps": 194, "total_steps": 231, "loss": 0.298, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "1:59:42", "remaining_time": "0:22:49"}
+{"current_steps": 195, "total_steps": 231, "loss": 0.2721, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "2:00:15", "remaining_time": "0:22:12"}
+{"current_steps": 196, "total_steps": 231, "loss": 0.2745, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "2:00:47", "remaining_time": "0:21:34"}
+{"current_steps": 197, "total_steps": 231, "loss": 0.2866, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "2:01:18", "remaining_time": "0:20:56"}
+{"current_steps": 198, "total_steps": 231, "loss": 0.2675, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "2:01:49", "remaining_time": "0:20:18"}
+{"current_steps": 199, "total_steps": 231, "loss": 0.2609, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "2:04:15", "remaining_time": "0:19:58"}
+{"current_steps": 200, "total_steps": 231, "loss": 0.2696, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "2:04:46", "remaining_time": "0:19:20"}
+{"current_steps": 201, "total_steps": 231, "loss": 0.26, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "2:05:20", "remaining_time": "0:18:42"}