Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3364e522668c18d68a3c1579bf61d1efcb65c55616504e81ff48237a764f00
+oid sha256:e0dd1183301cb3672a558c009ae130e81a496730864a6ab5404d19b5c63c9687
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c22ba248fa0485dc895a6b1463180c40660ed8717173f284bf8ccd912598d9
+oid sha256:730a5f79316302612263f921968b249a530b6c97cd5a24d959d9bfb9c41186b5
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15de77a2e94894cdd0f7a214fbe95cc2be034f0d8e584699f19e53e873cea959
+oid sha256:cddbeac07a7d5669c296cf5c967b31fb277cf234b5127279305e4ba9d49d6a37
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a8f47086291cc7ff0958219eb6615fe1a8fcf1537a63aebcfd83b66309ff351
+oid sha256:e6b33e1e192a3fe11961d0308fa50f1eacd0dccce5ff464112764aefb6ed40d3
 size 1089994880

trainer_log.jsonl

@@ -87,3 +87,47 @@
 {"current_steps": 860, "total_steps": 1314, "loss": 0.6322, "learning_rate": 1e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:40:25", "remaining_time": "6:41:25"}
 {"current_steps": 870, "total_steps": 1314, "loss": 0.6297, "learning_rate": 1e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:49:09", "remaining_time": "6:32:32"}
 {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6338208317756653, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:02:36", "remaining_time": "6:29:57"}
+{"current_steps": 880, "total_steps": 1314, "loss": 0.6567, "learning_rate": 1e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:06:22", "remaining_time": "6:27:49"}
+{"current_steps": 890, "total_steps": 1314, "loss": 0.6093, "learning_rate": 1e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:15:05", "remaining_time": "6:18:47"}
+{"current_steps": 900, "total_steps": 1314, "loss": 0.6259, "learning_rate": 1e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:23:48", "remaining_time": "6:09:44"}
+{"current_steps": 910, "total_steps": 1314, "loss": 0.6235, "learning_rate": 1e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:32:33", "remaining_time": "6:00:44"}
+{"current_steps": 920, "total_steps": 1314, "loss": 0.6269, "learning_rate": 1e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:41:17", "remaining_time": "5:51:43"}
+{"current_steps": 930, "total_steps": 1314, "loss": 0.6239, "learning_rate": 1e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:50:02", "remaining_time": "5:42:43"}
+{"current_steps": 940, "total_steps": 1314, "loss": 0.6184, "learning_rate": 1e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:58:47", "remaining_time": "5:33:44"}
+{"current_steps": 950, "total_steps": 1314, "loss": 0.6196, "learning_rate": 1e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:07:31", "remaining_time": "5:24:44"}
+{"current_steps": 960, "total_steps": 1314, "loss": 0.6245, "learning_rate": 1e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:16:14", "remaining_time": "5:15:44"}
+{"current_steps": 970, "total_steps": 1314, "loss": 0.6233, "learning_rate": 1e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:24:58", "remaining_time": "5:06:45"}
+{"current_steps": 980, "total_steps": 1314, "loss": 0.6119, "learning_rate": 1e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:33:43", "remaining_time": "4:57:46"}
+{"current_steps": 990, "total_steps": 1314, "loss": 0.6209, "learning_rate": 1e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:42:26", "remaining_time": "4:48:47"}
+{"current_steps": 1000, "total_steps": 1314, "loss": 0.6211, "learning_rate": 1e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:51:11", "remaining_time": "4:39:49"}
+{"current_steps": 1010, "total_steps": 1314, "loss": 0.6183, "learning_rate": 1e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "14:59:55", "remaining_time": "4:30:52"}
+{"current_steps": 1020, "total_steps": 1314, "loss": 0.6216, "learning_rate": 1e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:08:40", "remaining_time": "4:21:54"}
+{"current_steps": 1030, "total_steps": 1314, "loss": 0.6233, "learning_rate": 1e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:17:23", "remaining_time": "4:12:56"}
+{"current_steps": 1040, "total_steps": 1314, "loss": 0.6201, "learning_rate": 1e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:26:07", "remaining_time": "4:03:59"}
+{"current_steps": 1050, "total_steps": 1314, "loss": 0.6195, "learning_rate": 1e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:34:52", "remaining_time": "3:55:03"}
+{"current_steps": 1060, "total_steps": 1314, "loss": 0.6284, "learning_rate": 1e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:43:36", "remaining_time": "3:46:06"}
+{"current_steps": 1070, "total_steps": 1314, "loss": 0.6316, "learning_rate": 1e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:52:21", "remaining_time": "3:37:10"}
+{"current_steps": 1080, "total_steps": 1314, "loss": 0.6264, "learning_rate": 1e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:01:04", "remaining_time": "3:28:13"}
+{"current_steps": 1090, "total_steps": 1314, "loss": 0.6233, "learning_rate": 1e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:09:48", "remaining_time": "3:19:18"}
+{"current_steps": 1100, "total_steps": 1314, "loss": 0.6307, "learning_rate": 1e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:18:33", "remaining_time": "3:10:22"}
+{"current_steps": 1110, "total_steps": 1314, "loss": 0.6229, "learning_rate": 1e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:27:18", "remaining_time": "3:01:27"}
+{"current_steps": 1120, "total_steps": 1314, "loss": 0.621, "learning_rate": 1e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:36:02", "remaining_time": "2:52:31"}
+{"current_steps": 1130, "total_steps": 1314, "loss": 0.62, "learning_rate": 1e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:44:47", "remaining_time": "2:43:36"}
+{"current_steps": 1140, "total_steps": 1314, "loss": 0.6197, "learning_rate": 1e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:53:31", "remaining_time": "2:34:41"}
+{"current_steps": 1150, "total_steps": 1314, "loss": 0.6198, "learning_rate": 1e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:02:13", "remaining_time": "2:25:46"}
+{"current_steps": 1160, "total_steps": 1314, "loss": 0.6202, "learning_rate": 1e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:10:57", "remaining_time": "2:16:52"}
+{"current_steps": 1170, "total_steps": 1314, "loss": 0.6238, "learning_rate": 1e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:19:42", "remaining_time": "2:07:57"}
+{"current_steps": 1180, "total_steps": 1314, "loss": 0.6185, "learning_rate": 1e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:28:24", "remaining_time": "1:59:03"}
+{"current_steps": 1190, "total_steps": 1314, "loss": 0.6191, "learning_rate": 1e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:37:08", "remaining_time": "1:50:09"}
+{"current_steps": 1200, "total_steps": 1314, "loss": 0.6227, "learning_rate": 1e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:45:53", "remaining_time": "1:41:15"}
+{"current_steps": 1210, "total_steps": 1314, "loss": 0.6259, "learning_rate": 1e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:54:38", "remaining_time": "1:32:21"}
+{"current_steps": 1220, "total_steps": 1314, "loss": 0.6152, "learning_rate": 1e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:03:22", "remaining_time": "1:23:28"}
+{"current_steps": 1230, "total_steps": 1314, "loss": 0.6136, "learning_rate": 1e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:12:07", "remaining_time": "1:14:35"}
+{"current_steps": 1240, "total_steps": 1314, "loss": 0.6293, "learning_rate": 1e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:20:49", "remaining_time": "1:05:41"}
+{"current_steps": 1250, "total_steps": 1314, "loss": 0.6258, "learning_rate": 1e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:29:32", "remaining_time": "0:56:48"}
+{"current_steps": 1260, "total_steps": 1314, "loss": 0.6225, "learning_rate": 1e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:38:16", "remaining_time": "0:47:55"}
+{"current_steps": 1270, "total_steps": 1314, "loss": 0.6233, "learning_rate": 1e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:46:59", "remaining_time": "0:39:02"}
+{"current_steps": 1280, "total_steps": 1314, "loss": 0.6132, "learning_rate": 1e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:55:45", "remaining_time": "0:30:10"}
+{"current_steps": 1290, "total_steps": 1314, "loss": 0.6129, "learning_rate": 1e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:04:29", "remaining_time": "0:21:17"}
+{"current_steps": 1300, "total_steps": 1314, "loss": 0.6144, "learning_rate": 1e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:13:12", "remaining_time": "0:12:25"}
+{"current_steps": 1310, "total_steps": 1314, "loss": 0.625, "learning_rate": 1e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:21:56", "remaining_time": "0:03:32"}