sedrickkeh commited on
Commit
87e2e32
·
verified ·
1 Parent(s): eb34c54

Training in progress, epoch 0

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63956f47d93b100574dcd32f4c07f2199279e7f1641e05c8275df492391f03b7
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e4b47b4955c5fbe7a3b5b838a9ea5b8ef793402528728b6334a221b3166704
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2be6f42a2650ea38b4f5bbd27943d4fe7eeef2ecc250e183e5ea9642a1d0619e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2be5b306e10ef26d62ff8b4122e71273cc3db9835be1c503b4419cd27ae6c5
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:271d3a317b0a4326bc9bdaf1f1d7c2c7a819cb88ab57786f59def1d2d8e8d5fb
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0932d5dbbc55dda7b178cd5e170d0c9f8aed50a83295719140f04acd27004bc
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70d0cdf3d9b1838a29a451cadc5b2fe6a27ee803abb3950b809f27b976c36c73
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e948610dbed21b368ecb5333fcdf6a9f68b1e7bd72e0629545e87846fd74f7c
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,135 +1,133 @@
1
- {"current_steps": 1, "total_steps": 655, "loss": 0.9243, "lr": 1.2121212121212122e-06, "epoch": 0.007593735168485999, "percentage": 0.15, "elapsed_time": "0:02:08", "remaining_time": "23:19:40"}
2
- {"current_steps": 2, "total_steps": 655, "loss": 0.9318, "lr": 2.4242424242424244e-06, "epoch": 0.015187470336971999, "percentage": 0.31, "elapsed_time": "0:04:01", "remaining_time": "21:54:34"}
3
- {"current_steps": 3, "total_steps": 655, "loss": 0.9363, "lr": 3.6363636363636366e-06, "epoch": 0.022781205505457997, "percentage": 0.46, "elapsed_time": "0:05:57", "remaining_time": "21:34:59"}
4
- {"current_steps": 1, "total_steps": 655, "loss": 0.9243, "lr": 1.2121212121212122e-06, "epoch": 0.007593735168485999, "percentage": 0.15, "elapsed_time": "0:03:35", "remaining_time": "1 day, 15:08:34"}
5
- {"current_steps": 2, "total_steps": 655, "loss": 0.9318, "lr": 2.4242424242424244e-06, "epoch": 0.015187470336971999, "percentage": 0.31, "elapsed_time": "0:06:58", "remaining_time": "1 day, 13:58:42"}
6
- {"current_steps": 3, "total_steps": 655, "loss": 0.9361, "lr": 3.6363636363636366e-06, "epoch": 0.022781205505457997, "percentage": 0.46, "elapsed_time": "0:10:22", "remaining_time": "1 day, 13:36:04"}
7
- {"current_steps": 4, "total_steps": 655, "loss": 0.9154, "lr": 4.848484848484849e-06, "epoch": 0.030374940673943997, "percentage": 0.61, "elapsed_time": "0:13:47", "remaining_time": "1 day, 13:25:33"}
8
- {"current_steps": 5, "total_steps": 655, "loss": 0.8636, "lr": 6.060606060606061e-06, "epoch": 0.037968675842429994, "percentage": 0.76, "elapsed_time": "0:17:13", "remaining_time": "1 day, 13:20:08"}
9
- {"current_steps": 6, "total_steps": 655, "loss": 0.862, "lr": 7.272727272727273e-06, "epoch": 0.045562411010915994, "percentage": 0.92, "elapsed_time": "0:20:39", "remaining_time": "1 day, 13:15:17"}
10
- {"current_steps": 7, "total_steps": 655, "loss": 0.8645, "lr": 8.484848484848486e-06, "epoch": 0.053156146179401995, "percentage": 1.07, "elapsed_time": "0:24:05", "remaining_time": "1 day, 13:10:08"}
11
- {"current_steps": 8, "total_steps": 655, "loss": 0.8681, "lr": 9.696969696969698e-06, "epoch": 0.060749881347887995, "percentage": 1.22, "elapsed_time": "0:27:30", "remaining_time": "1 day, 13:04:40"}
12
- {"current_steps": 9, "total_steps": 655, "loss": 0.8197, "lr": 1.0909090909090909e-05, "epoch": 0.068343616516374, "percentage": 1.37, "elapsed_time": "0:30:54", "remaining_time": "1 day, 12:58:17"}
13
- {"current_steps": 10, "total_steps": 655, "loss": 0.8183, "lr": 1.2121212121212122e-05, "epoch": 0.07593735168485999, "percentage": 1.53, "elapsed_time": "0:34:18", "remaining_time": "1 day, 12:52:37"}
14
- {"current_steps": 11, "total_steps": 655, "loss": 0.7842, "lr": 1.3333333333333333e-05, "epoch": 0.083531086853346, "percentage": 1.68, "elapsed_time": "0:37:42", "remaining_time": "1 day, 12:47:34"}
15
- {"current_steps": 12, "total_steps": 655, "loss": 0.7673, "lr": 1.4545454545454546e-05, "epoch": 0.09112482202183199, "percentage": 1.83, "elapsed_time": "0:41:07", "remaining_time": "1 day, 12:43:11"}
16
- {"current_steps": 13, "total_steps": 655, "loss": 0.7501, "lr": 1.575757575757576e-05, "epoch": 0.09871855719031798, "percentage": 1.98, "elapsed_time": "0:44:31", "remaining_time": "1 day, 12:39:11"}
17
- {"current_steps": 14, "total_steps": 655, "loss": 0.7264, "lr": 1.6969696969696972e-05, "epoch": 0.10631229235880399, "percentage": 2.14, "elapsed_time": "0:48:00", "remaining_time": "1 day, 12:37:56"}
18
- {"current_steps": 15, "total_steps": 655, "loss": 0.712, "lr": 1.8181818181818182e-05, "epoch": 0.11390602752728998, "percentage": 2.29, "elapsed_time": "0:51:23", "remaining_time": "1 day, 12:32:57"}
19
- {"current_steps": 16, "total_steps": 655, "loss": 0.7044, "lr": 1.9393939393939395e-05, "epoch": 0.12149976269577599, "percentage": 2.44, "elapsed_time": "0:54:48", "remaining_time": "1 day, 12:29:04"}
20
- {"current_steps": 17, "total_steps": 655, "loss": 0.6939, "lr": 2.0606060606060608e-05, "epoch": 0.129093497864262, "percentage": 2.6, "elapsed_time": "0:58:14", "remaining_time": "1 day, 12:25:51"}
21
- {"current_steps": 18, "total_steps": 655, "loss": 0.6806, "lr": 2.1818181818181818e-05, "epoch": 0.136687233032748, "percentage": 2.75, "elapsed_time": "1:01:39", "remaining_time": "1 day, 12:22:01"}
22
- {"current_steps": 19, "total_steps": 655, "loss": 0.6785, "lr": 2.3030303030303034e-05, "epoch": 0.14428096820123398, "percentage": 2.9, "elapsed_time": "1:05:05", "remaining_time": "1 day, 12:18:55"}
23
- {"current_steps": 20, "total_steps": 655, "loss": 0.6675, "lr": 2.4242424242424244e-05, "epoch": 0.15187470336971998, "percentage": 3.05, "elapsed_time": "1:08:30", "remaining_time": "1 day, 12:14:59"}
24
- {"current_steps": 21, "total_steps": 655, "loss": 0.6646, "lr": 2.5454545454545457e-05, "epoch": 0.15946843853820597, "percentage": 3.21, "elapsed_time": "1:11:54", "remaining_time": "1 day, 12:11:11"}
25
- {"current_steps": 22, "total_steps": 655, "loss": 0.6656, "lr": 2.6666666666666667e-05, "epoch": 0.167062173706692, "percentage": 3.36, "elapsed_time": "1:15:19", "remaining_time": "1 day, 12:07:05"}
26
- {"current_steps": 23, "total_steps": 655, "loss": 0.6505, "lr": 2.7878787878787883e-05, "epoch": 0.17465590887517798, "percentage": 3.51, "elapsed_time": "1:18:43", "remaining_time": "1 day, 12:03:12"}
27
- {"current_steps": 24, "total_steps": 655, "loss": 0.6597, "lr": 2.9090909090909093e-05, "epoch": 0.18224964404366398, "percentage": 3.66, "elapsed_time": "1:22:07", "remaining_time": "1 day, 11:59:06"}
28
- {"current_steps": 25, "total_steps": 655, "loss": 0.6521, "lr": 3.0303030303030306e-05, "epoch": 0.18984337921214997, "percentage": 3.82, "elapsed_time": "1:25:32", "remaining_time": "1 day, 11:55:38"}
29
- {"current_steps": 26, "total_steps": 655, "loss": 0.6354, "lr": 3.151515151515152e-05, "epoch": 0.19743711438063596, "percentage": 3.97, "elapsed_time": "1:28:56", "remaining_time": "1 day, 11:51:48"}
30
- {"current_steps": 27, "total_steps": 655, "loss": 0.6444, "lr": 3.272727272727273e-05, "epoch": 0.20503084954912199, "percentage": 4.12, "elapsed_time": "1:32:23", "remaining_time": "1 day, 11:48:55"}
31
- {"current_steps": 28, "total_steps": 655, "loss": 0.6328, "lr": 3.3939393939393945e-05, "epoch": 0.21262458471760798, "percentage": 4.27, "elapsed_time": "1:35:48", "remaining_time": "1 day, 11:45:30"}
32
- {"current_steps": 29, "total_steps": 655, "loss": 0.6295, "lr": 3.515151515151515e-05, "epoch": 0.22021831988609397, "percentage": 4.43, "elapsed_time": "1:39:13", "remaining_time": "1 day, 11:42:03"}
33
- {"current_steps": 30, "total_steps": 655, "loss": 0.6306, "lr": 3.6363636363636364e-05, "epoch": 0.22781205505457996, "percentage": 4.58, "elapsed_time": "1:42:39", "remaining_time": "1 day, 11:38:47"}
34
- {"current_steps": 31, "total_steps": 655, "loss": 0.6275, "lr": 3.7575757575757584e-05, "epoch": 0.23540579022306596, "percentage": 4.73, "elapsed_time": "1:46:05", "remaining_time": "1 day, 11:35:34"}
35
- {"current_steps": 32, "total_steps": 655, "loss": 0.6153, "lr": 3.878787878787879e-05, "epoch": 0.24299952539155198, "percentage": 4.89, "elapsed_time": "1:49:33", "remaining_time": "1 day, 11:32:49"}
36
- {"current_steps": 33, "total_steps": 655, "loss": 0.6151, "lr": 4e-05, "epoch": 0.25059326056003794, "percentage": 5.04, "elapsed_time": "1:52:58", "remaining_time": "1 day, 11:29:16"}
37
- {"current_steps": 34, "total_steps": 655, "loss": 0.6106, "lr": 4.1212121212121216e-05, "epoch": 0.258186995728524, "percentage": 5.19, "elapsed_time": "1:56:22", "remaining_time": "1 day, 11:25:38"}
38
- {"current_steps": 35, "total_steps": 655, "loss": 0.6155, "lr": 4.242424242424242e-05, "epoch": 0.26578073089701, "percentage": 5.34, "elapsed_time": "1:59:46", "remaining_time": "1 day, 11:21:46"}
39
- {"current_steps": 36, "total_steps": 655, "loss": 0.6143, "lr": 4.3636363636363636e-05, "epoch": 0.273374466065496, "percentage": 5.5, "elapsed_time": "2:03:10", "remaining_time": "1 day, 11:17:59"}
40
- {"current_steps": 37, "total_steps": 655, "loss": 0.6088, "lr": 4.484848484848485e-05, "epoch": 0.280968201233982, "percentage": 5.65, "elapsed_time": "2:06:34", "remaining_time": "1 day, 11:14:01"}
41
- {"current_steps": 38, "total_steps": 655, "loss": 0.6179, "lr": 4.606060606060607e-05, "epoch": 0.28856193640246797, "percentage": 5.8, "elapsed_time": "2:09:58", "remaining_time": "1 day, 11:10:29"}
42
- {"current_steps": 39, "total_steps": 655, "loss": 0.6028, "lr": 4.727272727272728e-05, "epoch": 0.29615567157095396, "percentage": 5.95, "elapsed_time": "2:13:23", "remaining_time": "1 day, 11:06:48"}
43
- {"current_steps": 40, "total_steps": 655, "loss": 0.6205, "lr": 4.848484848484849e-05, "epoch": 0.30374940673943995, "percentage": 6.11, "elapsed_time": "2:16:49", "remaining_time": "1 day, 11:03:39"}
44
- {"current_steps": 41, "total_steps": 655, "loss": 0.5991, "lr": 4.96969696969697e-05, "epoch": 0.31134314190792595, "percentage": 6.26, "elapsed_time": "2:20:15", "remaining_time": "1 day, 11:00:29"}
45
- {"current_steps": 42, "total_steps": 655, "loss": 0.6011, "lr": 5.0909090909090914e-05, "epoch": 0.31893687707641194, "percentage": 6.41, "elapsed_time": "2:23:41", "remaining_time": "1 day, 10:57:10"}
46
- {"current_steps": 43, "total_steps": 655, "loss": 0.6011, "lr": 5.212121212121213e-05, "epoch": 0.32653061224489793, "percentage": 6.56, "elapsed_time": "2:27:08", "remaining_time": "1 day, 10:54:08"}
47
- {"current_steps": 44, "total_steps": 655, "loss": 0.6106, "lr": 5.333333333333333e-05, "epoch": 0.334124347413384, "percentage": 6.72, "elapsed_time": "2:30:34", "remaining_time": "1 day, 10:51:01"}
48
- {"current_steps": 45, "total_steps": 655, "loss": 0.5958, "lr": 5.4545454545454546e-05, "epoch": 0.34171808258187, "percentage": 6.87, "elapsed_time": "2:34:00", "remaining_time": "1 day, 10:47:44"}
49
- {"current_steps": 46, "total_steps": 655, "loss": 0.6014, "lr": 5.5757575757575766e-05, "epoch": 0.34931181775035597, "percentage": 7.02, "elapsed_time": "2:37:24", "remaining_time": "1 day, 10:43:51"}
50
- {"current_steps": 47, "total_steps": 655, "loss": 0.6116, "lr": 5.696969696969698e-05, "epoch": 0.35690555291884196, "percentage": 7.18, "elapsed_time": "2:40:48", "remaining_time": "1 day, 10:40:16"}
51
- {"current_steps": 48, "total_steps": 655, "loss": 0.5979, "lr": 5.8181818181818185e-05, "epoch": 0.36449928808732796, "percentage": 7.33, "elapsed_time": "2:44:13", "remaining_time": "1 day, 10:36:44"}
52
- {"current_steps": 49, "total_steps": 655, "loss": 0.6048, "lr": 5.93939393939394e-05, "epoch": 0.37209302325581395, "percentage": 7.48, "elapsed_time": "2:47:37", "remaining_time": "1 day, 10:33:06"}
53
- {"current_steps": 50, "total_steps": 655, "loss": 0.5894, "lr": 6.060606060606061e-05, "epoch": 0.37968675842429994, "percentage": 7.63, "elapsed_time": "2:51:01", "remaining_time": "1 day, 10:29:25"}
54
- {"current_steps": 51, "total_steps": 655, "loss": 0.6091, "lr": 6.181818181818182e-05, "epoch": 0.38728049359278593, "percentage": 7.79, "elapsed_time": "2:54:25", "remaining_time": "1 day, 10:25:46"}
55
- {"current_steps": 52, "total_steps": 655, "loss": 0.5994, "lr": 6.303030303030304e-05, "epoch": 0.39487422876127193, "percentage": 7.94, "elapsed_time": "2:57:51", "remaining_time": "1 day, 10:22:23"}
56
- {"current_steps": 53, "total_steps": 655, "loss": 0.5873, "lr": 6.424242424242424e-05, "epoch": 0.402467963929758, "percentage": 8.09, "elapsed_time": "3:01:15", "remaining_time": "1 day, 10:18:53"}
57
- {"current_steps": 54, "total_steps": 655, "loss": 0.5843, "lr": 6.545454545454546e-05, "epoch": 0.41006169909824397, "percentage": 8.24, "elapsed_time": "3:04:40", "remaining_time": "1 day, 10:15:25"}
58
- {"current_steps": 55, "total_steps": 655, "loss": 0.6029, "lr": 6.666666666666667e-05, "epoch": 0.41765543426672996, "percentage": 8.4, "elapsed_time": "3:08:06", "remaining_time": "1 day, 10:12:00"}
59
- {"current_steps": 56, "total_steps": 655, "loss": 0.5792, "lr": 6.787878787878789e-05, "epoch": 0.42524916943521596, "percentage": 8.55, "elapsed_time": "3:11:30", "remaining_time": "1 day, 10:08:23"}
60
- {"current_steps": 57, "total_steps": 655, "loss": 0.5831, "lr": 6.90909090909091e-05, "epoch": 0.43284290460370195, "percentage": 8.7, "elapsed_time": "3:14:54", "remaining_time": "1 day, 10:04:52"}
61
- {"current_steps": 58, "total_steps": 655, "loss": 0.6006, "lr": 7.03030303030303e-05, "epoch": 0.44043663977218794, "percentage": 8.85, "elapsed_time": "3:18:18", "remaining_time": "1 day, 10:01:13"}
62
- {"current_steps": 59, "total_steps": 655, "loss": 0.5906, "lr": 7.151515151515152e-05, "epoch": 0.44803037494067394, "percentage": 9.01, "elapsed_time": "3:21:42", "remaining_time": "1 day, 9:57:39"}
63
- {"current_steps": 60, "total_steps": 655, "loss": 0.5863, "lr": 7.272727272727273e-05, "epoch": 0.45562411010915993, "percentage": 9.16, "elapsed_time": "3:25:07", "remaining_time": "1 day, 9:54:04"}
64
- {"current_steps": 61, "total_steps": 655, "loss": 0.5905, "lr": 7.393939393939395e-05, "epoch": 0.4632178452776459, "percentage": 9.31, "elapsed_time": "3:28:32", "remaining_time": "1 day, 9:50:41"}
65
- {"current_steps": 62, "total_steps": 655, "loss": 0.5928, "lr": 7.515151515151517e-05, "epoch": 0.4708115804461319, "percentage": 9.47, "elapsed_time": "3:31:57", "remaining_time": "1 day, 9:47:17"}
66
- {"current_steps": 63, "total_steps": 655, "loss": 0.5819, "lr": 7.636363636363637e-05, "epoch": 0.47840531561461797, "percentage": 9.62, "elapsed_time": "3:35:21", "remaining_time": "1 day, 9:43:38"}
67
- {"current_steps": 64, "total_steps": 655, "loss": 0.5813, "lr": 7.757575757575758e-05, "epoch": 0.48599905078310396, "percentage": 9.77, "elapsed_time": "3:38:47", "remaining_time": "1 day, 9:40:24"}
68
- {"current_steps": 65, "total_steps": 655, "loss": 0.5776, "lr": 7.87878787878788e-05, "epoch": 0.49359278595158995, "percentage": 9.92, "elapsed_time": "3:42:12", "remaining_time": "1 day, 9:36:57"}
69
- {"current_steps": 66, "total_steps": 655, "loss": 0.5819, "lr": 8e-05, "epoch": 0.5011865211200759, "percentage": 10.08, "elapsed_time": "3:45:36", "remaining_time": "1 day, 9:33:26"}
70
- {"current_steps": 67, "total_steps": 655, "loss": 0.5695, "lr": 7.999943101853146e-05, "epoch": 0.5087802562885619, "percentage": 10.23, "elapsed_time": "3:49:01", "remaining_time": "1 day, 9:29:52"}
71
- {"current_steps": 68, "total_steps": 655, "loss": 0.581, "lr": 7.999772409031277e-05, "epoch": 0.516373991457048, "percentage": 10.38, "elapsed_time": "3:52:25", "remaining_time": "1 day, 9:26:26"}
72
- {"current_steps": 69, "total_steps": 655, "loss": 0.5851, "lr": 7.999487926390452e-05, "epoch": 0.5239677266255339, "percentage": 10.53, "elapsed_time": "3:55:50", "remaining_time": "1 day, 9:22:58"}
73
- {"current_steps": 70, "total_steps": 655, "loss": 0.5828, "lr": 7.999089662023934e-05, "epoch": 0.53156146179402, "percentage": 10.69, "elapsed_time": "3:59:15", "remaining_time": "1 day, 9:19:27"}
74
- {"current_steps": 71, "total_steps": 655, "loss": 0.5836, "lr": 7.99857762726198e-05, "epoch": 0.5391551969625059, "percentage": 10.84, "elapsed_time": "4:02:38", "remaining_time": "1 day, 9:15:50"}
75
- {"current_steps": 72, "total_steps": 655, "loss": 0.5679, "lr": 7.997951836671498e-05, "epoch": 0.546748932130992, "percentage": 10.99, "elapsed_time": "4:06:04", "remaining_time": "1 day, 9:12:30"}
76
- {"current_steps": 73, "total_steps": 655, "loss": 0.5905, "lr": 7.997212308055656e-05, "epoch": 0.5543426672994779, "percentage": 11.15, "elapsed_time": "4:09:38", "remaining_time": "1 day, 9:10:20"}
77
- {"current_steps": 74, "total_steps": 655, "loss": 0.575, "lr": 7.996359062453354e-05, "epoch": 0.561936402467964, "percentage": 11.3, "elapsed_time": "4:13:03", "remaining_time": "1 day, 9:06:47"}
78
- {"current_steps": 75, "total_steps": 655, "loss": 0.5768, "lr": 7.995392124138642e-05, "epoch": 0.5695301376364499, "percentage": 11.45, "elapsed_time": "4:16:29", "remaining_time": "1 day, 9:03:29"}
79
- {"current_steps": 76, "total_steps": 655, "loss": 0.5675, "lr": 7.994311520620017e-05, "epoch": 0.5771238728049359, "percentage": 11.6, "elapsed_time": "4:19:54", "remaining_time": "1 day, 9:00:08"}
80
- {"current_steps": 77, "total_steps": 655, "loss": 0.5756, "lr": 7.993117282639648e-05, "epoch": 0.584717607973422, "percentage": 11.76, "elapsed_time": "4:23:20", "remaining_time": "1 day, 8:56:43"}
81
- {"current_steps": 78, "total_steps": 655, "loss": 0.572, "lr": 7.9918094441725e-05, "epoch": 0.5923113431419079, "percentage": 11.91, "elapsed_time": "4:26:46", "remaining_time": "1 day, 8:53:28"}
82
- {"current_steps": 79, "total_steps": 655, "loss": 0.5601, "lr": 7.990388042425367e-05, "epoch": 0.599905078310394, "percentage": 12.06, "elapsed_time": "4:30:12", "remaining_time": "1 day, 8:50:06"}
83
- {"current_steps": 80, "total_steps": 655, "loss": 0.5646, "lr": 7.988853117835806e-05, "epoch": 0.6074988134788799, "percentage": 12.21, "elapsed_time": "4:33:38", "remaining_time": "1 day, 8:46:48"}
84
- {"current_steps": 81, "total_steps": 655, "loss": 0.5664, "lr": 7.987204714071006e-05, "epoch": 0.615092548647366, "percentage": 12.37, "elapsed_time": "4:37:05", "remaining_time": "1 day, 8:43:33"}
85
- {"current_steps": 82, "total_steps": 655, "loss": 0.5578, "lr": 7.985442878026524e-05, "epoch": 0.6226862838158519, "percentage": 12.52, "elapsed_time": "4:40:31", "remaining_time": "1 day, 8:40:15"}
86
- {"current_steps": 83, "total_steps": 655, "loss": 0.5633, "lr": 7.983567659824962e-05, "epoch": 0.6302800189843379, "percentage": 12.67, "elapsed_time": "4:43:54", "remaining_time": "1 day, 8:36:36"}
87
- {"current_steps": 84, "total_steps": 655, "loss": 0.5713, "lr": 7.981579112814541e-05, "epoch": 0.6378737541528239, "percentage": 12.82, "elapsed_time": "4:47:20", "remaining_time": "1 day, 8:33:11"}
88
- {"current_steps": 85, "total_steps": 655, "loss": 0.5631, "lr": 7.97947729356758e-05, "epoch": 0.6454674893213099, "percentage": 12.98, "elapsed_time": "4:50:44", "remaining_time": "1 day, 8:29:43"}
89
- {"current_steps": 86, "total_steps": 655, "loss": 0.5626, "lr": 7.977262261878892e-05, "epoch": 0.6530612244897959, "percentage": 13.13, "elapsed_time": "4:54:09", "remaining_time": "1 day, 8:26:15"}
90
- {"current_steps": 87, "total_steps": 655, "loss": 0.5558, "lr": 7.974934080764075e-05, "epoch": 0.6606549596582819, "percentage": 13.28, "elapsed_time": "4:57:34", "remaining_time": "1 day, 8:22:47"}
91
- {"current_steps": 88, "total_steps": 655, "loss": 0.5517, "lr": 7.972492816457723e-05, "epoch": 0.668248694826768, "percentage": 13.44, "elapsed_time": "5:00:59", "remaining_time": "1 day, 8:19:17"}
92
- {"current_steps": 89, "total_steps": 655, "loss": 0.5511, "lr": 7.969938538411543e-05, "epoch": 0.6758424299952539, "percentage": 13.59, "elapsed_time": "5:04:23", "remaining_time": "1 day, 8:15:44"}
93
- {"current_steps": 90, "total_steps": 655, "loss": 0.5643, "lr": 7.967271319292382e-05, "epoch": 0.68343616516374, "percentage": 13.74, "elapsed_time": "5:07:49", "remaining_time": "1 day, 8:12:24"}
94
- {"current_steps": 91, "total_steps": 655, "loss": 0.5798, "lr": 7.96449123498015e-05, "epoch": 0.6910299003322259, "percentage": 13.89, "elapsed_time": "5:11:15", "remaining_time": "1 day, 8:09:06"}
95
- {"current_steps": 92, "total_steps": 655, "loss": 0.5657, "lr": 7.96159836456567e-05, "epoch": 0.6986236355007119, "percentage": 14.05, "elapsed_time": "5:14:41", "remaining_time": "1 day, 8:05:47"}
96
- {"current_steps": 93, "total_steps": 655, "loss": 0.5652, "lr": 7.958592790348425e-05, "epoch": 0.7062173706691979, "percentage": 14.2, "elapsed_time": "5:18:07", "remaining_time": "1 day, 8:02:23"}
97
- {"current_steps": 94, "total_steps": 655, "loss": 0.5583, "lr": 7.955474597834217e-05, "epoch": 0.7138111058376839, "percentage": 14.35, "elapsed_time": "5:21:33", "remaining_time": "1 day, 7:59:02"}
98
- {"current_steps": 95, "total_steps": 655, "loss": 0.5583, "lr": 7.952243875732735e-05, "epoch": 0.7214048410061699, "percentage": 14.5, "elapsed_time": "5:24:57", "remaining_time": "1 day, 7:55:30"}
99
- {"current_steps": 96, "total_steps": 655, "loss": 0.5568, "lr": 7.948900715955025e-05, "epoch": 0.7289985761746559, "percentage": 14.66, "elapsed_time": "5:28:21", "remaining_time": "1 day, 7:51:58"}
100
- {"current_steps": 97, "total_steps": 655, "loss": 0.5471, "lr": 7.94544521361089e-05, "epoch": 0.736592311343142, "percentage": 14.81, "elapsed_time": "5:31:45", "remaining_time": "1 day, 7:48:27"}
101
- {"current_steps": 98, "total_steps": 655, "loss": 0.5543, "lr": 7.941877467006168e-05, "epoch": 0.7441860465116279, "percentage": 14.96, "elapsed_time": "5:35:09", "remaining_time": "1 day, 7:44:56"}
102
- {"current_steps": 99, "total_steps": 655, "loss": 0.5485, "lr": 7.938197577639942e-05, "epoch": 0.751779781680114, "percentage": 15.11, "elapsed_time": "5:38:34", "remaining_time": "1 day, 7:41:30"}
103
- {"current_steps": 100, "total_steps": 655, "loss": 0.5638, "lr": 7.934405650201658e-05, "epoch": 0.7593735168485999, "percentage": 15.27, "elapsed_time": "5:42:01", "remaining_time": "1 day, 7:38:16"}
104
- {"current_steps": 101, "total_steps": 655, "loss": 0.5466, "lr": 7.930501792568138e-05, "epoch": 0.7669672520170859, "percentage": 15.42, "elapsed_time": "5:45:27", "remaining_time": "1 day, 7:34:51"}
105
- {"current_steps": 102, "total_steps": 655, "loss": 0.5512, "lr": 7.926486115800511e-05, "epoch": 0.7745609871855719, "percentage": 15.57, "elapsed_time": "5:48:51", "remaining_time": "1 day, 7:31:24"}
106
- {"current_steps": 103, "total_steps": 655, "loss": 0.5501, "lr": 7.922358734141064e-05, "epoch": 0.7821547223540579, "percentage": 15.73, "elapsed_time": "5:52:16", "remaining_time": "1 day, 7:27:57"}
107
- {"current_steps": 104, "total_steps": 655, "loss": 0.5534, "lr": 7.918119765009979e-05, "epoch": 0.7897484575225439, "percentage": 15.88, "elapsed_time": "5:55:42", "remaining_time": "1 day, 7:24:34"}
108
- {"current_steps": 105, "total_steps": 655, "loss": 0.542, "lr": 7.913769329002e-05, "epoch": 0.7973421926910299, "percentage": 16.03, "elapsed_time": "5:59:08", "remaining_time": "1 day, 7:21:10"}
109
- {"current_steps": 106, "total_steps": 655, "loss": 0.5579, "lr": 7.909307549883002e-05, "epoch": 0.804935927859516, "percentage": 16.18, "elapsed_time": "6:02:33", "remaining_time": "1 day, 7:17:48"}
110
- {"current_steps": 107, "total_steps": 655, "loss": 0.5484, "lr": 7.904734554586464e-05, "epoch": 0.8125296630280019, "percentage": 16.34, "elapsed_time": "6:05:58", "remaining_time": "1 day, 7:14:18"}
111
- {"current_steps": 108, "total_steps": 655, "loss": 0.5413, "lr": 7.900050473209868e-05, "epoch": 0.8201233981964879, "percentage": 16.49, "elapsed_time": "6:09:22", "remaining_time": "1 day, 7:10:48"}
112
- {"current_steps": 109, "total_steps": 655, "loss": 0.5388, "lr": 7.895255439010987e-05, "epoch": 0.8277171333649739, "percentage": 16.64, "elapsed_time": "6:12:47", "remaining_time": "1 day, 7:07:20"}
113
- {"current_steps": 110, "total_steps": 655, "loss": 0.5439, "lr": 7.890349588404102e-05, "epoch": 0.8353108685334599, "percentage": 16.79, "elapsed_time": "6:16:11", "remaining_time": "1 day, 7:03:49"}
114
- {"current_steps": 111, "total_steps": 655, "loss": 0.551, "lr": 7.885333060956117e-05, "epoch": 0.8429046037019459, "percentage": 16.95, "elapsed_time": "6:19:35", "remaining_time": "1 day, 7:00:22"}
115
- {"current_steps": 112, "total_steps": 655, "loss": 0.5391, "lr": 7.88020599938259e-05, "epoch": 0.8504983388704319, "percentage": 17.1, "elapsed_time": "6:22:58", "remaining_time": "1 day, 6:56:46"}
116
- {"current_steps": 113, "total_steps": 655, "loss": 0.5423, "lr": 7.87496854954367e-05, "epoch": 0.8580920740389179, "percentage": 17.25, "elapsed_time": "6:26:24", "remaining_time": "1 day, 6:53:25"}
117
- {"current_steps": 114, "total_steps": 655, "loss": 0.5351, "lr": 7.869620860439956e-05, "epoch": 0.8656858092074039, "percentage": 17.4, "elapsed_time": "6:29:50", "remaining_time": "1 day, 6:50:00"}
118
- {"current_steps": 115, "total_steps": 655, "loss": 0.5481, "lr": 7.864163084208245e-05, "epoch": 0.8732795443758898, "percentage": 17.56, "elapsed_time": "6:33:14", "remaining_time": "1 day, 6:46:31"}
119
- {"current_steps": 116, "total_steps": 655, "loss": 0.5439, "lr": 7.858595376117214e-05, "epoch": 0.8808732795443759, "percentage": 17.71, "elapsed_time": "6:36:40", "remaining_time": "1 day, 6:43:10"}
120
- {"current_steps": 117, "total_steps": 655, "loss": 0.5528, "lr": 7.852917894563e-05, "epoch": 0.8884670147128619, "percentage": 17.86, "elapsed_time": "6:40:04", "remaining_time": "1 day, 6:39:41"}
121
- {"current_steps": 118, "total_steps": 655, "loss": 0.5489, "lr": 7.847130801064694e-05, "epoch": 0.8960607498813479, "percentage": 18.02, "elapsed_time": "6:43:29", "remaining_time": "1 day, 6:36:12"}
122
- {"current_steps": 119, "total_steps": 655, "loss": 0.5422, "lr": 7.84123426025974e-05, "epoch": 0.9036544850498339, "percentage": 18.17, "elapsed_time": "6:46:53", "remaining_time": "1 day, 6:32:42"}
123
- {"current_steps": 120, "total_steps": 655, "loss": 0.5383, "lr": 7.835228439899264e-05, "epoch": 0.9112482202183199, "percentage": 18.32, "elapsed_time": "6:50:17", "remaining_time": "1 day, 6:29:14"}
124
- {"current_steps": 121, "total_steps": 655, "loss": 0.5462, "lr": 7.829113510843288e-05, "epoch": 0.9188419553868059, "percentage": 18.47, "elapsed_time": "6:53:42", "remaining_time": "1 day, 6:25:47"}
125
- {"current_steps": 122, "total_steps": 655, "loss": 0.5344, "lr": 7.82288964705588e-05, "epoch": 0.9264356905552918, "percentage": 18.63, "elapsed_time": "6:57:07", "remaining_time": "1 day, 6:22:20"}
126
- {"current_steps": 123, "total_steps": 655, "loss": 0.5349, "lr": 7.816557025600196e-05, "epoch": 0.9340294257237779, "percentage": 18.78, "elapsed_time": "7:00:31", "remaining_time": "1 day, 6:18:52"}
127
- {"current_steps": 124, "total_steps": 655, "loss": 0.5484, "lr": 7.81011582663345e-05, "epoch": 0.9416231608922638, "percentage": 18.93, "elapsed_time": "7:03:57", "remaining_time": "1 day, 6:15:30"}
128
- {"current_steps": 125, "total_steps": 655, "loss": 0.5404, "lr": 7.803566233401784e-05, "epoch": 0.9492168960607499, "percentage": 19.08, "elapsed_time": "7:07:22", "remaining_time": "1 day, 6:12:05"}
129
- {"current_steps": 126, "total_steps": 655, "loss": 0.5499, "lr": 7.796908432235056e-05, "epoch": 0.9568106312292359, "percentage": 19.24, "elapsed_time": "7:10:47", "remaining_time": "1 day, 6:08:36"}
130
- {"current_steps": 127, "total_steps": 655, "loss": 0.539, "lr": 7.79014261254154e-05, "epoch": 0.9644043663977219, "percentage": 19.39, "elapsed_time": "7:14:13", "remaining_time": "1 day, 6:05:18"}
131
- {"current_steps": 128, "total_steps": 655, "loss": 0.5426, "lr": 7.783268966802539e-05, "epoch": 0.9719981015662079, "percentage": 19.54, "elapsed_time": "7:17:38", "remaining_time": "1 day, 6:01:49"}
132
- {"current_steps": 129, "total_steps": 655, "loss": 0.5436, "lr": 7.776287690566906e-05, "epoch": 0.9795918367346939, "percentage": 19.69, "elapsed_time": "7:21:02", "remaining_time": "1 day, 5:58:19"}
133
- {"current_steps": 130, "total_steps": 655, "loss": 0.549, "lr": 7.769198982445478e-05, "epoch": 0.9871855719031799, "percentage": 19.85, "elapsed_time": "7:24:25", "remaining_time": "1 day, 5:54:48"}
134
- {"current_steps": 131, "total_steps": 655, "loss": 0.5273, "lr": 7.762003044105435e-05, "epoch": 0.9947793070716658, "percentage": 20.0, "elapsed_time": "7:27:50", "remaining_time": "1 day, 5:51:23"}
135
- {"current_steps": 132, "total_steps": 655, "loss": 0.5272, "lr": 7.754700080264554e-05, "epoch": 1.0023730422401518, "percentage": 20.15, "elapsed_time": "7:33:29", "remaining_time": "1 day, 5:56:45"}
 
1
+ {"current_steps": 1, "total_steps": 655, "loss": 0.9218, "lr": 1.2121212121212122e-06, "epoch": 0.007590132827324478, "percentage": 0.15, "elapsed_time": "0:02:29", "remaining_time": "1 day, 3:14:38"}
2
+ {"current_steps": 2, "total_steps": 655, "loss": 0.9293, "lr": 2.4242424242424244e-06, "epoch": 0.015180265654648957, "percentage": 0.31, "elapsed_time": "0:04:06", "remaining_time": "22:23:09"}
3
+ {"current_steps": 3, "total_steps": 655, "loss": 0.9311, "lr": 3.6363636363636366e-06, "epoch": 0.022770398481973434, "percentage": 0.46, "elapsed_time": "0:05:44", "remaining_time": "20:47:08"}
4
+ {"current_steps": 4, "total_steps": 655, "loss": 0.9125, "lr": 4.848484848484849e-06, "epoch": 0.030360531309297913, "percentage": 0.61, "elapsed_time": "0:07:21", "remaining_time": "19:58:09"}
5
+ {"current_steps": 5, "total_steps": 655, "loss": 0.8611, "lr": 6.060606060606061e-06, "epoch": 0.03795066413662239, "percentage": 0.76, "elapsed_time": "0:08:58", "remaining_time": "19:27:42"}
6
+ {"current_steps": 6, "total_steps": 655, "loss": 0.8592, "lr": 7.272727272727273e-06, "epoch": 0.04554079696394687, "percentage": 0.92, "elapsed_time": "0:10:36", "remaining_time": "19:07:42"}
7
+ {"current_steps": 7, "total_steps": 655, "loss": 0.8607, "lr": 8.484848484848486e-06, "epoch": 0.05313092979127135, "percentage": 1.07, "elapsed_time": "0:12:13", "remaining_time": "18:52:05"}
8
+ {"current_steps": 8, "total_steps": 655, "loss": 0.8652, "lr": 9.696969696969698e-06, "epoch": 0.06072106261859583, "percentage": 1.22, "elapsed_time": "0:13:50", "remaining_time": "18:39:49"}
9
+ {"current_steps": 9, "total_steps": 655, "loss": 0.8177, "lr": 1.0909090909090909e-05, "epoch": 0.0683111954459203, "percentage": 1.37, "elapsed_time": "0:15:27", "remaining_time": "18:30:06"}
10
+ {"current_steps": 10, "total_steps": 655, "loss": 0.8151, "lr": 1.2121212121212122e-05, "epoch": 0.07590132827324478, "percentage": 1.53, "elapsed_time": "0:17:05", "remaining_time": "18:22:00"}
11
+ {"current_steps": 11, "total_steps": 655, "loss": 0.7815, "lr": 1.3333333333333333e-05, "epoch": 0.08349146110056926, "percentage": 1.68, "elapsed_time": "0:18:42", "remaining_time": "18:15:06"}
12
+ {"current_steps": 12, "total_steps": 655, "loss": 0.7618, "lr": 1.4545454545454546e-05, "epoch": 0.09108159392789374, "percentage": 1.83, "elapsed_time": "0:20:19", "remaining_time": "18:08:57"}
13
+ {"current_steps": 13, "total_steps": 655, "loss": 0.7486, "lr": 1.575757575757576e-05, "epoch": 0.09867172675521822, "percentage": 1.98, "elapsed_time": "0:21:57", "remaining_time": "18:04:14"}
14
+ {"current_steps": 14, "total_steps": 655, "loss": 0.7247, "lr": 1.6969696969696972e-05, "epoch": 0.1062618595825427, "percentage": 2.14, "elapsed_time": "0:23:34", "remaining_time": "17:59:16"}
15
+ {"current_steps": 15, "total_steps": 655, "loss": 0.711, "lr": 1.8181818181818182e-05, "epoch": 0.11385199240986717, "percentage": 2.29, "elapsed_time": "0:25:11", "remaining_time": "17:54:48"}
16
+ {"current_steps": 16, "total_steps": 655, "loss": 0.7028, "lr": 1.9393939393939395e-05, "epoch": 0.12144212523719165, "percentage": 2.44, "elapsed_time": "0:26:48", "remaining_time": "17:50:25"}
17
+ {"current_steps": 17, "total_steps": 655, "loss": 0.6918, "lr": 2.0606060606060608e-05, "epoch": 0.12903225806451613, "percentage": 2.6, "elapsed_time": "0:28:25", "remaining_time": "17:46:28"}
18
+ {"current_steps": 18, "total_steps": 655, "loss": 0.6782, "lr": 2.1818181818181818e-05, "epoch": 0.1366223908918406, "percentage": 2.75, "elapsed_time": "0:30:01", "remaining_time": "17:42:46"}
19
+ {"current_steps": 19, "total_steps": 655, "loss": 0.6772, "lr": 2.3030303030303034e-05, "epoch": 0.1442125237191651, "percentage": 2.9, "elapsed_time": "0:31:39", "remaining_time": "17:39:29"}
20
+ {"current_steps": 20, "total_steps": 655, "loss": 0.6644, "lr": 2.4242424242424244e-05, "epoch": 0.15180265654648956, "percentage": 3.05, "elapsed_time": "0:33:16", "remaining_time": "17:36:25"}
21
+ {"current_steps": 21, "total_steps": 655, "loss": 0.6628, "lr": 2.5454545454545457e-05, "epoch": 0.15939278937381404, "percentage": 3.21, "elapsed_time": "0:34:53", "remaining_time": "17:33:23"}
22
+ {"current_steps": 22, "total_steps": 655, "loss": 0.6579, "lr": 2.6666666666666667e-05, "epoch": 0.16698292220113853, "percentage": 3.36, "elapsed_time": "0:36:30", "remaining_time": "17:30:30"}
23
+ {"current_steps": 23, "total_steps": 655, "loss": 0.6488, "lr": 2.7878787878787883e-05, "epoch": 0.174573055028463, "percentage": 3.51, "elapsed_time": "0:38:07", "remaining_time": "17:27:41"}
24
+ {"current_steps": 24, "total_steps": 655, "loss": 0.6545, "lr": 2.9090909090909093e-05, "epoch": 0.18216318785578747, "percentage": 3.66, "elapsed_time": "0:39:44", "remaining_time": "17:24:55"}
25
+ {"current_steps": 25, "total_steps": 655, "loss": 0.6505, "lr": 3.0303030303030306e-05, "epoch": 0.18975332068311196, "percentage": 3.82, "elapsed_time": "0:41:21", "remaining_time": "17:22:22"}
26
+ {"current_steps": 26, "total_steps": 655, "loss": 0.6317, "lr": 3.151515151515152e-05, "epoch": 0.19734345351043645, "percentage": 3.97, "elapsed_time": "0:42:58", "remaining_time": "17:19:50"}
27
+ {"current_steps": 27, "total_steps": 655, "loss": 0.6432, "lr": 3.272727272727273e-05, "epoch": 0.2049335863377609, "percentage": 4.12, "elapsed_time": "0:44:36", "remaining_time": "17:17:22"}
28
+ {"current_steps": 28, "total_steps": 655, "loss": 0.6312, "lr": 3.3939393939393945e-05, "epoch": 0.2125237191650854, "percentage": 4.27, "elapsed_time": "0:46:13", "remaining_time": "17:14:56"}
29
+ {"current_steps": 29, "total_steps": 655, "loss": 0.6285, "lr": 3.515151515151515e-05, "epoch": 0.22011385199240988, "percentage": 4.43, "elapsed_time": "0:47:50", "remaining_time": "17:12:36"}
30
+ {"current_steps": 30, "total_steps": 655, "loss": 0.6275, "lr": 3.6363636363636364e-05, "epoch": 0.22770398481973433, "percentage": 4.58, "elapsed_time": "0:49:27", "remaining_time": "17:10:15"}
31
+ {"current_steps": 31, "total_steps": 655, "loss": 0.6264, "lr": 3.7575757575757584e-05, "epoch": 0.23529411764705882, "percentage": 4.73, "elapsed_time": "0:51:04", "remaining_time": "17:07:58"}
32
+ {"current_steps": 32, "total_steps": 655, "loss": 0.6144, "lr": 3.878787878787879e-05, "epoch": 0.2428842504743833, "percentage": 4.89, "elapsed_time": "0:52:41", "remaining_time": "17:05:45"}
33
+ {"current_steps": 33, "total_steps": 655, "loss": 0.6141, "lr": 4e-05, "epoch": 0.2504743833017078, "percentage": 5.04, "elapsed_time": "0:54:18", "remaining_time": "17:03:36"}
34
+ {"current_steps": 34, "total_steps": 655, "loss": 0.6092, "lr": 4.1212121212121216e-05, "epoch": 0.25806451612903225, "percentage": 5.19, "elapsed_time": "0:55:55", "remaining_time": "17:01:29"}
35
+ {"current_steps": 35, "total_steps": 655, "loss": 0.6134, "lr": 4.242424242424242e-05, "epoch": 0.2656546489563567, "percentage": 5.34, "elapsed_time": "0:57:32", "remaining_time": "16:59:25"}
36
+ {"current_steps": 36, "total_steps": 655, "loss": 0.6164, "lr": 4.3636363636363636e-05, "epoch": 0.2732447817836812, "percentage": 5.5, "elapsed_time": "0:59:09", "remaining_time": "16:57:20"}
37
+ {"current_steps": 37, "total_steps": 655, "loss": 0.6011, "lr": 4.484848484848485e-05, "epoch": 0.2808349146110057, "percentage": 5.65, "elapsed_time": "1:00:46", "remaining_time": "16:55:14"}
38
+ {"current_steps": 38, "total_steps": 655, "loss": 0.6094, "lr": 4.606060606060607e-05, "epoch": 0.2884250474383302, "percentage": 5.8, "elapsed_time": "1:02:24", "remaining_time": "16:53:12"}
39
+ {"current_steps": 39, "total_steps": 655, "loss": 0.6011, "lr": 4.727272727272728e-05, "epoch": 0.29601518026565465, "percentage": 5.95, "elapsed_time": "1:04:01", "remaining_time": "16:51:14"}
40
+ {"current_steps": 40, "total_steps": 655, "loss": 0.615, "lr": 4.848484848484849e-05, "epoch": 0.3036053130929791, "percentage": 6.11, "elapsed_time": "1:05:38", "remaining_time": "16:49:15"}
41
+ {"current_steps": 41, "total_steps": 655, "loss": 0.5974, "lr": 4.96969696969697e-05, "epoch": 0.3111954459203036, "percentage": 6.26, "elapsed_time": "1:07:15", "remaining_time": "16:47:19"}
42
+ {"current_steps": 42, "total_steps": 655, "loss": 0.6002, "lr": 5.0909090909090914e-05, "epoch": 0.3187855787476281, "percentage": 6.41, "elapsed_time": "1:08:53", "remaining_time": "16:45:22"}
43
+ {"current_steps": 43, "total_steps": 655, "loss": 0.6062, "lr": 5.212121212121213e-05, "epoch": 0.32637571157495254, "percentage": 6.56, "elapsed_time": "1:10:30", "remaining_time": "16:43:28"}
44
+ {"current_steps": 44, "total_steps": 655, "loss": 0.6068, "lr": 5.333333333333333e-05, "epoch": 0.33396584440227706, "percentage": 6.72, "elapsed_time": "1:12:07", "remaining_time": "16:41:31"}
45
+ {"current_steps": 45, "total_steps": 655, "loss": 0.5993, "lr": 5.4545454545454546e-05, "epoch": 0.3415559772296015, "percentage": 6.87, "elapsed_time": "1:13:44", "remaining_time": "16:39:39"}
46
+ {"current_steps": 46, "total_steps": 655, "loss": 0.5967, "lr": 5.5757575757575766e-05, "epoch": 0.349146110056926, "percentage": 7.02, "elapsed_time": "1:15:21", "remaining_time": "16:37:46"}
47
+ {"current_steps": 47, "total_steps": 655, "loss": 0.6048, "lr": 5.696969696969698e-05, "epoch": 0.3567362428842505, "percentage": 7.18, "elapsed_time": "1:16:59", "remaining_time": "16:35:55"}
48
+ {"current_steps": 48, "total_steps": 655, "loss": 0.5991, "lr": 5.8181818181818185e-05, "epoch": 0.36432637571157495, "percentage": 7.33, "elapsed_time": "1:18:36", "remaining_time": "16:34:03"}
49
+ {"current_steps": 49, "total_steps": 655, "loss": 0.5973, "lr": 5.93939393939394e-05, "epoch": 0.3719165085388994, "percentage": 7.48, "elapsed_time": "1:20:13", "remaining_time": "16:32:12"}
50
+ {"current_steps": 50, "total_steps": 655, "loss": 0.5839, "lr": 6.060606060606061e-05, "epoch": 0.3795066413662239, "percentage": 7.63, "elapsed_time": "1:21:50", "remaining_time": "16:30:20"}
51
+ {"current_steps": 51, "total_steps": 655, "loss": 0.6014, "lr": 6.181818181818182e-05, "epoch": 0.3870967741935484, "percentage": 7.79, "elapsed_time": "1:23:27", "remaining_time": "16:28:30"}
52
+ {"current_steps": 52, "total_steps": 655, "loss": 0.5903, "lr": 6.303030303030304e-05, "epoch": 0.3946869070208729, "percentage": 7.94, "elapsed_time": "1:25:05", "remaining_time": "16:26:44"}
53
+ {"current_steps": 53, "total_steps": 655, "loss": 0.5787, "lr": 6.424242424242424e-05, "epoch": 0.40227703984819735, "percentage": 8.09, "elapsed_time": "1:26:42", "remaining_time": "16:24:57"}
54
+ {"current_steps": 54, "total_steps": 655, "loss": 0.5836, "lr": 6.545454545454546e-05, "epoch": 0.4098671726755218, "percentage": 8.24, "elapsed_time": "1:28:20", "remaining_time": "16:23:08"}
55
+ {"current_steps": 55, "total_steps": 655, "loss": 0.6021, "lr": 6.666666666666667e-05, "epoch": 0.4174573055028463, "percentage": 8.4, "elapsed_time": "1:29:57", "remaining_time": "16:21:20"}
56
+ {"current_steps": 56, "total_steps": 655, "loss": 0.5745, "lr": 6.787878787878789e-05, "epoch": 0.4250474383301708, "percentage": 8.55, "elapsed_time": "1:31:34", "remaining_time": "16:19:32"}
57
+ {"current_steps": 57, "total_steps": 655, "loss": 0.5802, "lr": 6.90909090909091e-05, "epoch": 0.43263757115749524, "percentage": 8.7, "elapsed_time": "1:33:11", "remaining_time": "16:17:44"}
58
+ {"current_steps": 58, "total_steps": 655, "loss": 0.5967, "lr": 7.03030303030303e-05, "epoch": 0.44022770398481975, "percentage": 8.85, "elapsed_time": "1:34:49", "remaining_time": "16:15:58"}
59
+ {"current_steps": 59, "total_steps": 655, "loss": 0.5873, "lr": 7.151515151515152e-05, "epoch": 0.4478178368121442, "percentage": 9.01, "elapsed_time": "1:36:26", "remaining_time": "16:14:11"}
60
+ {"current_steps": 60, "total_steps": 655, "loss": 0.5822, "lr": 7.272727272727273e-05, "epoch": 0.45540796963946867, "percentage": 9.16, "elapsed_time": "1:38:03", "remaining_time": "16:12:23"}
61
+ {"current_steps": 61, "total_steps": 655, "loss": 0.5892, "lr": 7.393939393939395e-05, "epoch": 0.4629981024667932, "percentage": 9.31, "elapsed_time": "1:39:40", "remaining_time": "16:10:37"}
62
+ {"current_steps": 62, "total_steps": 655, "loss": 0.5888, "lr": 7.515151515151517e-05, "epoch": 0.47058823529411764, "percentage": 9.47, "elapsed_time": "1:41:17", "remaining_time": "16:08:51"}
63
+ {"current_steps": 63, "total_steps": 655, "loss": 0.5748, "lr": 7.636363636363637e-05, "epoch": 0.4781783681214421, "percentage": 9.62, "elapsed_time": "1:42:55", "remaining_time": "16:07:06"}
64
+ {"current_steps": 64, "total_steps": 655, "loss": 0.5752, "lr": 7.757575757575758e-05, "epoch": 0.4857685009487666, "percentage": 9.77, "elapsed_time": "1:44:32", "remaining_time": "16:05:21"}
65
+ {"current_steps": 65, "total_steps": 655, "loss": 0.5991, "lr": 7.87878787878788e-05, "epoch": 0.49335863377609107, "percentage": 9.92, "elapsed_time": "1:46:09", "remaining_time": "16:03:36"}
66
+ {"current_steps": 66, "total_steps": 655, "loss": 0.587, "lr": 8e-05, "epoch": 0.5009487666034156, "percentage": 10.08, "elapsed_time": "1:47:46", "remaining_time": "16:01:50"}
67
+ {"current_steps": 67, "total_steps": 655, "loss": 0.5968, "lr": 7.999943101853146e-05, "epoch": 0.50853889943074, "percentage": 10.23, "elapsed_time": "1:49:23", "remaining_time": "16:00:06"}
68
+ {"current_steps": 68, "total_steps": 655, "loss": 0.6063, "lr": 7.999772409031277e-05, "epoch": 0.5161290322580645, "percentage": 10.38, "elapsed_time": "1:51:01", "remaining_time": "15:58:20"}
69
+ {"current_steps": 69, "total_steps": 655, "loss": 0.5968, "lr": 7.999487926390452e-05, "epoch": 0.523719165085389, "percentage": 10.53, "elapsed_time": "1:52:38", "remaining_time": "15:56:38"}
70
+ {"current_steps": 70, "total_steps": 655, "loss": 0.5976, "lr": 7.999089662023934e-05, "epoch": 0.5313092979127134, "percentage": 10.69, "elapsed_time": "1:54:15", "remaining_time": "15:54:53"}
71
+ {"current_steps": 71, "total_steps": 655, "loss": 0.5892, "lr": 7.99857762726198e-05, "epoch": 0.538899430740038, "percentage": 10.84, "elapsed_time": "1:55:52", "remaining_time": "15:53:09"}
72
+ {"current_steps": 72, "total_steps": 655, "loss": 0.5763, "lr": 7.997951836671498e-05, "epoch": 0.5464895635673624, "percentage": 10.99, "elapsed_time": "1:57:30", "remaining_time": "15:51:29"}
73
+ {"current_steps": 73, "total_steps": 655, "loss": 0.5885, "lr": 7.997212308055656e-05, "epoch": 0.5540796963946869, "percentage": 11.15, "elapsed_time": "1:59:07", "remaining_time": "15:49:45"}
74
+ {"current_steps": 74, "total_steps": 655, "loss": 0.5816, "lr": 7.996359062453354e-05, "epoch": 0.5616698292220114, "percentage": 11.3, "elapsed_time": "2:00:44", "remaining_time": "15:48:02"}
75
+ {"current_steps": 75, "total_steps": 655, "loss": 0.5815, "lr": 7.995392124138642e-05, "epoch": 0.5692599620493358, "percentage": 11.45, "elapsed_time": "2:02:22", "remaining_time": "15:46:22"}
76
+ {"current_steps": 76, "total_steps": 655, "loss": 0.5782, "lr": 7.994311520620017e-05, "epoch": 0.5768500948766604, "percentage": 11.6, "elapsed_time": "2:03:59", "remaining_time": "15:44:39"}
77
+ {"current_steps": 77, "total_steps": 655, "loss": 0.5782, "lr": 7.993117282639648e-05, "epoch": 0.5844402277039848, "percentage": 11.76, "elapsed_time": "2:05:37", "remaining_time": "15:42:56"}
78
+ {"current_steps": 78, "total_steps": 655, "loss": 0.5861, "lr": 7.9918094441725e-05, "epoch": 0.5920303605313093, "percentage": 11.91, "elapsed_time": "2:07:14", "remaining_time": "15:41:12"}
79
+ {"current_steps": 79, "total_steps": 655, "loss": 0.58, "lr": 7.990388042425367e-05, "epoch": 0.5996204933586338, "percentage": 12.06, "elapsed_time": "2:08:51", "remaining_time": "15:39:30"}
80
+ {"current_steps": 80, "total_steps": 655, "loss": 0.5814, "lr": 7.988853117835806e-05, "epoch": 0.6072106261859582, "percentage": 12.21, "elapsed_time": "2:10:28", "remaining_time": "15:37:47"}
81
+ {"current_steps": 81, "total_steps": 655, "loss": 0.5826, "lr": 7.987204714071006e-05, "epoch": 0.6148007590132827, "percentage": 12.37, "elapsed_time": "2:12:05", "remaining_time": "15:36:04"}
82
+ {"current_steps": 82, "total_steps": 655, "loss": 0.5754, "lr": 7.985442878026524e-05, "epoch": 0.6223908918406073, "percentage": 12.52, "elapsed_time": "2:13:42", "remaining_time": "15:34:22"}
83
+ {"current_steps": 83, "total_steps": 655, "loss": 0.5845, "lr": 7.983567659824962e-05, "epoch": 0.6299810246679317, "percentage": 12.67, "elapsed_time": "2:15:20", "remaining_time": "15:32:40"}
84
+ {"current_steps": 84, "total_steps": 655, "loss": 0.585, "lr": 7.981579112814541e-05, "epoch": 0.6375711574952562, "percentage": 12.82, "elapsed_time": "2:16:57", "remaining_time": "15:30:57"}
85
+ {"current_steps": 85, "total_steps": 655, "loss": 0.5777, "lr": 7.97947729356758e-05, "epoch": 0.6451612903225806, "percentage": 12.98, "elapsed_time": "2:18:34", "remaining_time": "15:29:16"}
86
+ {"current_steps": 86, "total_steps": 655, "loss": 0.5763, "lr": 7.977262261878892e-05, "epoch": 0.6527514231499051, "percentage": 13.13, "elapsed_time": "2:20:11", "remaining_time": "15:27:34"}
87
+ {"current_steps": 87, "total_steps": 655, "loss": 0.5662, "lr": 7.974934080764075e-05, "epoch": 0.6603415559772297, "percentage": 13.28, "elapsed_time": "2:21:49", "remaining_time": "15:25:53"}
88
+ {"current_steps": 88, "total_steps": 655, "loss": 0.5627, "lr": 7.972492816457723e-05, "epoch": 0.6679316888045541, "percentage": 13.44, "elapsed_time": "2:23:26", "remaining_time": "15:24:11"}
89
+ {"current_steps": 89, "total_steps": 655, "loss": 0.5611, "lr": 7.969938538411543e-05, "epoch": 0.6755218216318786, "percentage": 13.59, "elapsed_time": "2:25:03", "remaining_time": "15:22:30"}
90
+ {"current_steps": 90, "total_steps": 655, "loss": 0.5715, "lr": 7.967271319292382e-05, "epoch": 0.683111954459203, "percentage": 13.74, "elapsed_time": "2:26:40", "remaining_time": "15:20:49"}
91
+ {"current_steps": 91, "total_steps": 655, "loss": 0.5712, "lr": 7.96449123498015e-05, "epoch": 0.6907020872865275, "percentage": 13.89, "elapsed_time": "2:28:17", "remaining_time": "15:19:07"}
92
+ {"current_steps": 92, "total_steps": 655, "loss": 0.5675, "lr": 7.96159836456567e-05, "epoch": 0.698292220113852, "percentage": 14.05, "elapsed_time": "2:29:54", "remaining_time": "15:17:24"}
93
+ {"current_steps": 93, "total_steps": 655, "loss": 0.5755, "lr": 7.958592790348425e-05, "epoch": 0.7058823529411765, "percentage": 14.2, "elapsed_time": "2:31:33", "remaining_time": "15:15:49"}
94
+ {"current_steps": 94, "total_steps": 655, "loss": 0.5604, "lr": 7.955474597834217e-05, "epoch": 0.713472485768501, "percentage": 14.35, "elapsed_time": "2:33:10", "remaining_time": "15:14:11"}
95
+ {"current_steps": 95, "total_steps": 655, "loss": 0.5655, "lr": 7.952243875732735e-05, "epoch": 0.7210626185958254, "percentage": 14.5, "elapsed_time": "2:34:49", "remaining_time": "15:12:37"}
96
+ {"current_steps": 96, "total_steps": 655, "loss": 0.5629, "lr": 7.948900715955025e-05, "epoch": 0.7286527514231499, "percentage": 14.66, "elapsed_time": "2:36:27", "remaining_time": "15:11:00"}
97
+ {"current_steps": 97, "total_steps": 655, "loss": 0.5589, "lr": 7.94544521361089e-05, "epoch": 0.7362428842504743, "percentage": 14.81, "elapsed_time": "2:38:05", "remaining_time": "15:09:28"}
98
+ {"current_steps": 98, "total_steps": 655, "loss": 0.5644, "lr": 7.941877467006168e-05, "epoch": 0.7438330170777988, "percentage": 14.96, "elapsed_time": "2:39:44", "remaining_time": "15:07:56"}
99
+ {"current_steps": 99, "total_steps": 655, "loss": 0.5559, "lr": 7.938197577639942e-05, "epoch": 0.7514231499051234, "percentage": 15.11, "elapsed_time": "2:41:23", "remaining_time": "15:06:22"}
100
+ {"current_steps": 100, "total_steps": 655, "loss": 0.5723, "lr": 7.934405650201658e-05, "epoch": 0.7590132827324478, "percentage": 15.27, "elapsed_time": "2:43:00", "remaining_time": "15:04:43"}
101
+ {"current_steps": 101, "total_steps": 655, "loss": 0.5545, "lr": 7.930501792568138e-05, "epoch": 0.7666034155597723, "percentage": 15.42, "elapsed_time": "2:44:38", "remaining_time": "15:03:07"}
102
+ {"current_steps": 102, "total_steps": 655, "loss": 0.556, "lr": 7.926486115800511e-05, "epoch": 0.7741935483870968, "percentage": 15.57, "elapsed_time": "2:46:16", "remaining_time": "15:01:29"}
103
+ {"current_steps": 103, "total_steps": 655, "loss": 0.5596, "lr": 7.922358734141064e-05, "epoch": 0.7817836812144212, "percentage": 15.73, "elapsed_time": "2:47:54", "remaining_time": "14:59:53"}
104
+ {"current_steps": 104, "total_steps": 655, "loss": 0.5598, "lr": 7.918119765009979e-05, "epoch": 0.7893738140417458, "percentage": 15.88, "elapsed_time": "2:49:32", "remaining_time": "14:58:17"}
105
+ {"current_steps": 105, "total_steps": 655, "loss": 0.5489, "lr": 7.913769329002e-05, "epoch": 0.7969639468690702, "percentage": 16.03, "elapsed_time": "2:51:10", "remaining_time": "14:56:38"}
106
+ {"current_steps": 106, "total_steps": 655, "loss": 0.5646, "lr": 7.909307549883002e-05, "epoch": 0.8045540796963947, "percentage": 16.18, "elapsed_time": "2:52:48", "remaining_time": "14:54:59"}
107
+ {"current_steps": 107, "total_steps": 655, "loss": 0.5556, "lr": 7.904734554586464e-05, "epoch": 0.8121442125237192, "percentage": 16.34, "elapsed_time": "2:54:25", "remaining_time": "14:53:20"}
108
+ {"current_steps": 108, "total_steps": 655, "loss": 0.5483, "lr": 7.900050473209868e-05, "epoch": 0.8197343453510436, "percentage": 16.49, "elapsed_time": "2:56:03", "remaining_time": "14:51:42"}
109
+ {"current_steps": 109, "total_steps": 655, "loss": 0.5479, "lr": 7.895255439010987e-05, "epoch": 0.8273244781783681, "percentage": 16.64, "elapsed_time": "2:57:41", "remaining_time": "14:50:05"}
110
+ {"current_steps": 110, "total_steps": 655, "loss": 0.5499, "lr": 7.890349588404102e-05, "epoch": 0.8349146110056926, "percentage": 16.79, "elapsed_time": "2:59:19", "remaining_time": "14:48:26"}
111
+ {"current_steps": 111, "total_steps": 655, "loss": 0.5571, "lr": 7.885333060956117e-05, "epoch": 0.8425047438330171, "percentage": 16.95, "elapsed_time": "3:00:56", "remaining_time": "14:46:46"}
112
+ {"current_steps": 112, "total_steps": 655, "loss": 0.5449, "lr": 7.88020599938259e-05, "epoch": 0.8500948766603416, "percentage": 17.1, "elapsed_time": "3:02:33", "remaining_time": "14:45:07"}
113
+ {"current_steps": 113, "total_steps": 655, "loss": 0.5491, "lr": 7.87496854954367e-05, "epoch": 0.857685009487666, "percentage": 17.25, "elapsed_time": "3:04:11", "remaining_time": "14:43:29"}
114
+ {"current_steps": 114, "total_steps": 655, "loss": 0.543, "lr": 7.869620860439956e-05, "epoch": 0.8652751423149905, "percentage": 17.4, "elapsed_time": "3:05:49", "remaining_time": "14:41:50"}
115
+ {"current_steps": 115, "total_steps": 655, "loss": 0.5622, "lr": 7.864163084208245e-05, "epoch": 0.872865275142315, "percentage": 17.56, "elapsed_time": "3:07:27", "remaining_time": "14:40:12"}
116
+ {"current_steps": 116, "total_steps": 655, "loss": 0.5515, "lr": 7.858595376117214e-05, "epoch": 0.8804554079696395, "percentage": 17.71, "elapsed_time": "3:09:05", "remaining_time": "14:38:35"}
117
+ {"current_steps": 117, "total_steps": 655, "loss": 0.5599, "lr": 7.852917894563e-05, "epoch": 0.888045540796964, "percentage": 17.86, "elapsed_time": "3:10:42", "remaining_time": "14:36:56"}
118
+ {"current_steps": 118, "total_steps": 655, "loss": 0.5605, "lr": 7.847130801064694e-05, "epoch": 0.8956356736242884, "percentage": 18.02, "elapsed_time": "3:12:20", "remaining_time": "14:35:16"}
119
+ {"current_steps": 119, "total_steps": 655, "loss": 0.5494, "lr": 7.84123426025974e-05, "epoch": 0.9032258064516129, "percentage": 18.17, "elapsed_time": "3:13:57", "remaining_time": "14:33:36"}
120
+ {"current_steps": 120, "total_steps": 655, "loss": 0.546, "lr": 7.835228439899264e-05, "epoch": 0.9108159392789373, "percentage": 18.32, "elapsed_time": "3:15:35", "remaining_time": "14:31:58"}
121
+ {"current_steps": 121, "total_steps": 655, "loss": 0.5551, "lr": 7.829113510843288e-05, "epoch": 0.9184060721062619, "percentage": 18.47, "elapsed_time": "3:17:13", "remaining_time": "14:30:21"}
122
+ {"current_steps": 122, "total_steps": 655, "loss": 0.5454, "lr": 7.82288964705588e-05, "epoch": 0.9259962049335864, "percentage": 18.63, "elapsed_time": "3:18:51", "remaining_time": "14:28:45"}
123
+ {"current_steps": 123, "total_steps": 655, "loss": 0.5403, "lr": 7.816557025600196e-05, "epoch": 0.9335863377609108, "percentage": 18.78, "elapsed_time": "3:20:28", "remaining_time": "14:27:06"}
124
+ {"current_steps": 124, "total_steps": 655, "loss": 0.5551, "lr": 7.81011582663345e-05, "epoch": 0.9411764705882353, "percentage": 18.93, "elapsed_time": "3:22:06", "remaining_time": "14:25:28"}
125
+ {"current_steps": 125, "total_steps": 655, "loss": 0.5468, "lr": 7.803566233401784e-05, "epoch": 0.9487666034155597, "percentage": 19.08, "elapsed_time": "3:23:43", "remaining_time": "14:23:48"}
126
+ {"current_steps": 126, "total_steps": 655, "loss": 0.5588, "lr": 7.796908432235056e-05, "epoch": 0.9563567362428842, "percentage": 19.24, "elapsed_time": "3:25:21", "remaining_time": "14:22:08"}
127
+ {"current_steps": 127, "total_steps": 655, "loss": 0.5457, "lr": 7.79014261254154e-05, "epoch": 0.9639468690702088, "percentage": 19.39, "elapsed_time": "3:26:58", "remaining_time": "14:20:29"}
128
+ {"current_steps": 128, "total_steps": 655, "loss": 0.5482, "lr": 7.783268966802539e-05, "epoch": 0.9715370018975332, "percentage": 19.54, "elapsed_time": "3:28:35", "remaining_time": "14:18:49"}
129
+ {"current_steps": 129, "total_steps": 655, "loss": 0.5516, "lr": 7.776287690566906e-05, "epoch": 0.9791271347248577, "percentage": 19.69, "elapsed_time": "3:30:12", "remaining_time": "14:17:09"}
130
+ {"current_steps": 130, "total_steps": 655, "loss": 0.5644, "lr": 7.769198982445478e-05, "epoch": 0.9867172675521821, "percentage": 19.85, "elapsed_time": "3:31:49", "remaining_time": "14:15:28"}
131
+ {"current_steps": 131, "total_steps": 655, "loss": 0.5333, "lr": 7.762003044105435e-05, "epoch": 0.9943074003795066, "percentage": 20.0, "elapsed_time": "3:33:27", "remaining_time": "14:13:48"}
132
+ {"current_steps": 132, "total_steps": 655, "loss": 0.6801, "lr": 7.754700080264554e-05, "epoch": 1.0018975332068312, "percentage": 20.15, "elapsed_time": "3:36:32", "remaining_time": "14:17:56"}
133
+ {"current_steps": 133, "total_steps": 655, "loss": 0.5231, "lr": 7.747290298685392e-05, "epoch": 1.0094876660341556, "percentage": 20.31, "elapsed_time": "3:38:09", "remaining_time": "14:16:12"}
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2951b3b4f42cf6da6903f73d0c2238de12184da88c2c2b3451b7a6ec328a6d63
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28637e672253e32d85f253659a4b4b2d74f948898c5a84103d920efca6ab5e1
3
+ size 7160