izzcw commited on
Commit
6742a96
·
verified ·
1 Parent(s): e752c14

Training in progress, step 500

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15ed7f2f1016b890f6d451f4e6fb66fdb0601fb77f2f27b4ff99b33f1d7a5ca8
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f2c00fb20ab2c1de369419690a1fe4e43013bfd89ffc05a4de60b913217c32
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec0ade0b401be3318449d5261673b5b661bdcf4a1b81ea998415351f921546fa
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b93db076e2ef01205195379c69a9987229efe7272e86b6a7e0e3f04380e726ec
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:043a06f4f3806d6564582fffcfe515de5b66b2e172c6e3e7d1ff8c573711dbe8
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5424a293418d014ce4aea7a1edaa9856a9e465dc19e3e9712ac1bc64b359e8c
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d03e86d2cda1aa7f9cc26f150a579ef6f2bfde05fb2f82d209bd1eb1c6a3533d
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acea9f062cc998176a2e895edb93c7208fbb581426abe893090899aaf25f9afb
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,120 +1,60 @@
1
- {"current_steps": 10, "total_steps": 1548, "loss": 1.4777, "lr": 6.451612903225807e-07, "epoch": 0.006457341189765114, "percentage": 0.65, "elapsed_time": "0:02:09", "remaining_time": "5:32:06"}
2
- {"current_steps": 20, "total_steps": 1548, "loss": 1.0086, "lr": 1.2903225806451614e-06, "epoch": 0.012914682379530229, "percentage": 1.29, "elapsed_time": "0:04:15", "remaining_time": "5:25:53"}
3
- {"current_steps": 30, "total_steps": 1548, "loss": 0.702, "lr": 1.935483870967742e-06, "epoch": 0.019372023569295342, "percentage": 1.94, "elapsed_time": "0:06:21", "remaining_time": "5:21:33"}
4
- {"current_steps": 40, "total_steps": 1548, "loss": 0.6118, "lr": 2.580645161290323e-06, "epoch": 0.025829364759060457, "percentage": 2.58, "elapsed_time": "0:08:28", "remaining_time": "5:19:22"}
5
- {"current_steps": 50, "total_steps": 1548, "loss": 0.5416, "lr": 3.225806451612903e-06, "epoch": 0.03228670594882557, "percentage": 3.23, "elapsed_time": "0:10:34", "remaining_time": "5:16:59"}
6
- {"current_steps": 50, "total_steps": 1548, "eval_loss": 0.4988793432712555, "epoch": 0.03228670594882557, "percentage": 3.23, "elapsed_time": "0:12:27", "remaining_time": "6:13:10"}
7
- {"current_steps": 60, "total_steps": 1548, "loss": 0.5313, "lr": 3.870967741935484e-06, "epoch": 0.038744047138590684, "percentage": 3.88, "elapsed_time": "0:14:34", "remaining_time": "6:01:32"}
8
- {"current_steps": 70, "total_steps": 1548, "loss": 0.5473, "lr": 4.516129032258065e-06, "epoch": 0.0452013883283558, "percentage": 4.52, "elapsed_time": "0:16:40", "remaining_time": "5:51:59"}
9
- {"current_steps": 80, "total_steps": 1548, "loss": 0.5393, "lr": 5.161290322580646e-06, "epoch": 0.051658729518120915, "percentage": 5.17, "elapsed_time": "0:18:46", "remaining_time": "5:44:22"}
10
- {"current_steps": 90, "total_steps": 1548, "loss": 0.5156, "lr": 5.806451612903226e-06, "epoch": 0.058116070707886026, "percentage": 5.81, "elapsed_time": "0:20:53", "remaining_time": "5:38:29"}
11
- {"current_steps": 100, "total_steps": 1548, "loss": 0.5376, "lr": 6.451612903225806e-06, "epoch": 0.06457341189765115, "percentage": 6.46, "elapsed_time": "0:22:59", "remaining_time": "5:32:53"}
12
- {"current_steps": 100, "total_steps": 1548, "eval_loss": 0.4726952016353607, "epoch": 0.06457341189765115, "percentage": 6.46, "elapsed_time": "0:24:51", "remaining_time": "6:00:03"}
13
- {"current_steps": 110, "total_steps": 1548, "loss": 0.5432, "lr": 7.096774193548388e-06, "epoch": 0.07103075308741626, "percentage": 7.11, "elapsed_time": "0:26:58", "remaining_time": "5:52:35"}
14
- {"current_steps": 120, "total_steps": 1548, "loss": 0.5261, "lr": 7.741935483870968e-06, "epoch": 0.07748809427718137, "percentage": 7.75, "elapsed_time": "0:29:03", "remaining_time": "5:45:50"}
15
- {"current_steps": 130, "total_steps": 1548, "loss": 0.5615, "lr": 8.387096774193549e-06, "epoch": 0.08394543546694648, "percentage": 8.4, "elapsed_time": "0:31:09", "remaining_time": "5:39:54"}
16
- {"current_steps": 140, "total_steps": 1548, "loss": 0.5563, "lr": 9.03225806451613e-06, "epoch": 0.0904027766567116, "percentage": 9.04, "elapsed_time": "0:33:17", "remaining_time": "5:34:45"}
17
- {"current_steps": 150, "total_steps": 1548, "loss": 0.5458, "lr": 9.67741935483871e-06, "epoch": 0.09686011784647672, "percentage": 9.69, "elapsed_time": "0:35:21", "remaining_time": "5:29:33"}
18
- {"current_steps": 150, "total_steps": 1548, "eval_loss": 0.4868322014808655, "epoch": 0.09686011784647672, "percentage": 9.69, "elapsed_time": "0:37:14", "remaining_time": "5:47:01"}
19
- {"current_steps": 160, "total_steps": 1548, "loss": 0.5586, "lr": 9.999682112882774e-06, "epoch": 0.10331745903624183, "percentage": 10.34, "elapsed_time": "0:39:20", "remaining_time": "5:41:17"}
20
- {"current_steps": 170, "total_steps": 1548, "loss": 0.5564, "lr": 9.997139258465151e-06, "epoch": 0.10977480022600694, "percentage": 10.98, "elapsed_time": "0:41:28", "remaining_time": "5:36:09"}
21
- {"current_steps": 180, "total_steps": 1548, "loss": 0.5527, "lr": 9.992054842933846e-06, "epoch": 0.11623214141577205, "percentage": 11.63, "elapsed_time": "0:43:34", "remaining_time": "5:31:09"}
22
- {"current_steps": 190, "total_steps": 1548, "loss": 0.5231, "lr": 9.984431452238968e-06, "epoch": 0.12268948260553716, "percentage": 12.27, "elapsed_time": "0:45:40", "remaining_time": "5:26:30"}
23
- {"current_steps": 200, "total_steps": 1548, "loss": 0.5295, "lr": 9.974272963661561e-06, "epoch": 0.1291468237953023, "percentage": 12.92, "elapsed_time": "0:47:47", "remaining_time": "5:22:04"}
24
- {"current_steps": 200, "total_steps": 1548, "eval_loss": 0.48299747705459595, "epoch": 0.1291468237953023, "percentage": 12.92, "elapsed_time": "0:49:39", "remaining_time": "5:34:41"}
25
- {"current_steps": 210, "total_steps": 1548, "loss": 0.5327, "lr": 9.961584543841625e-06, "epoch": 0.1356041649850674, "percentage": 13.57, "elapsed_time": "0:51:46", "remaining_time": "5:29:49"}
26
- {"current_steps": 220, "total_steps": 1548, "loss": 0.5503, "lr": 9.946372646150322e-06, "epoch": 0.1420615061748325, "percentage": 14.21, "elapsed_time": "0:53:51", "remaining_time": "5:25:04"}
27
- {"current_steps": 230, "total_steps": 1548, "loss": 0.5333, "lr": 9.928645007407791e-06, "epoch": 0.14851884736459764, "percentage": 14.86, "elapsed_time": "0:55:58", "remaining_time": "5:20:43"}
28
- {"current_steps": 240, "total_steps": 1548, "loss": 0.5087, "lr": 9.908410643948162e-06, "epoch": 0.15497618855436274, "percentage": 15.5, "elapsed_time": "0:58:03", "remaining_time": "5:16:23"}
29
- {"current_steps": 250, "total_steps": 1548, "loss": 0.5256, "lr": 9.885679847033832e-06, "epoch": 0.16143352974412786, "percentage": 16.15, "elapsed_time": "1:00:08", "remaining_time": "5:12:16"}
30
- {"current_steps": 250, "total_steps": 1548, "eval_loss": 0.4716261327266693, "epoch": 0.16143352974412786, "percentage": 16.15, "elapsed_time": "1:02:01", "remaining_time": "5:22:00"}
31
- {"current_steps": 260, "total_steps": 1548, "loss": 0.5384, "lr": 9.860464177621286e-06, "epoch": 0.16789087093389296, "percentage": 16.8, "elapsed_time": "1:04:08", "remaining_time": "5:17:42"}
32
- {"current_steps": 270, "total_steps": 1548, "loss": 0.504, "lr": 9.832776460481162e-06, "epoch": 0.1743482121236581, "percentage": 17.44, "elapsed_time": "1:06:14", "remaining_time": "5:13:31"}
33
- {"current_steps": 280, "total_steps": 1548, "loss": 0.5363, "lr": 9.802630777675528e-06, "epoch": 0.1808055533134232, "percentage": 18.09, "elapsed_time": "1:08:19", "remaining_time": "5:09:25"}
34
- {"current_steps": 290, "total_steps": 1548, "loss": 0.5249, "lr": 9.770042461395705e-06, "epoch": 0.1872628945031883, "percentage": 18.73, "elapsed_time": "1:10:25", "remaining_time": "5:05:29"}
35
- {"current_steps": 300, "total_steps": 1548, "loss": 0.5331, "lr": 9.735028086164265e-06, "epoch": 0.19372023569295344, "percentage": 19.38, "elapsed_time": "1:12:33", "remaining_time": "5:01:48"}
36
- {"current_steps": 300, "total_steps": 1548, "eval_loss": 0.44979438185691833, "epoch": 0.19372023569295344, "percentage": 19.38, "elapsed_time": "1:14:25", "remaining_time": "5:09:36"}
37
- {"current_steps": 310, "total_steps": 1548, "loss": 0.5263, "lr": 9.697605460405162e-06, "epoch": 0.20017757688271853, "percentage": 20.03, "elapsed_time": "1:16:31", "remaining_time": "5:05:36"}
38
- {"current_steps": 320, "total_steps": 1548, "loss": 0.5215, "lr": 9.657793617386337e-06, "epoch": 0.20663491807248366, "percentage": 20.67, "elapsed_time": "1:18:36", "remaining_time": "5:01:41"}
39
- {"current_steps": 330, "total_steps": 1548, "loss": 0.5163, "lr": 9.615612805539305e-06, "epoch": 0.21309225926224876, "percentage": 21.32, "elapsed_time": "1:20:44", "remaining_time": "4:57:59"}
40
- {"current_steps": 340, "total_steps": 1548, "loss": 0.5053, "lr": 9.571084478160763e-06, "epoch": 0.21954960045201388, "percentage": 21.96, "elapsed_time": "1:22:50", "remaining_time": "4:54:19"}
41
- {"current_steps": 350, "total_steps": 1548, "loss": 0.5256, "lr": 9.524231282501362e-06, "epoch": 0.226006941641779, "percentage": 22.61, "elapsed_time": "1:24:58", "remaining_time": "4:50:50"}
42
- {"current_steps": 350, "total_steps": 1548, "eval_loss": 0.4477861225605011, "epoch": 0.226006941641779, "percentage": 22.61, "elapsed_time": "1:26:50", "remaining_time": "4:57:15"}
43
- {"current_steps": 360, "total_steps": 1548, "loss": 0.48, "lr": 9.475077048247243e-06, "epoch": 0.2324642828315441, "percentage": 23.26, "elapsed_time": "1:28:56", "remaining_time": "4:53:30"}
44
- {"current_steps": 370, "total_steps": 1548, "loss": 0.5087, "lr": 9.423646775400186e-06, "epoch": 0.23892162402130923, "percentage": 23.9, "elapsed_time": "1:31:02", "remaining_time": "4:49:49"}
45
- {"current_steps": 380, "total_steps": 1548, "loss": 0.4941, "lr": 9.369966621562525e-06, "epoch": 0.24537896521107433, "percentage": 24.55, "elapsed_time": "1:33:07", "remaining_time": "4:46:14"}
46
- {"current_steps": 390, "total_steps": 1548, "loss": 0.5018, "lr": 9.314063888633312e-06, "epoch": 0.2518363064008394, "percentage": 25.19, "elapsed_time": "1:35:13", "remaining_time": "4:42:44"}
47
- {"current_steps": 400, "total_steps": 1548, "loss": 0.5078, "lr": 9.255967008922475e-06, "epoch": 0.2582936475906046, "percentage": 25.84, "elapsed_time": "1:37:20", "remaining_time": "4:39:21"}
48
- {"current_steps": 400, "total_steps": 1548, "eval_loss": 0.4282528758049011, "epoch": 0.2582936475906046, "percentage": 25.84, "elapsed_time": "1:39:12", "remaining_time": "4:44:43"}
49
- {"current_steps": 410, "total_steps": 1548, "loss": 0.4985, "lr": 9.19570553069006e-06, "epoch": 0.2647509887803697, "percentage": 26.49, "elapsed_time": "1:41:20", "remaining_time": "4:41:15"}
50
- {"current_steps": 420, "total_steps": 1548, "loss": 0.4784, "lr": 9.133310103117891e-06, "epoch": 0.2712083299701348, "percentage": 27.13, "elapsed_time": "1:43:26", "remaining_time": "4:37:48"}
51
- {"current_steps": 430, "total_steps": 1548, "loss": 0.4789, "lr": 9.068812460721296e-06, "epoch": 0.27766567115989993, "percentage": 27.78, "elapsed_time": "1:45:32", "remaining_time": "4:34:25"}
52
- {"current_steps": 440, "total_steps": 1548, "loss": 0.5099, "lr": 9.002245407208831e-06, "epoch": 0.284123012349665, "percentage": 28.42, "elapsed_time": "1:47:37", "remaining_time": "4:31:02"}
53
- {"current_steps": 450, "total_steps": 1548, "loss": 0.4749, "lr": 8.9336427987982e-06, "epoch": 0.2905803535394301, "percentage": 29.07, "elapsed_time": "1:49:45", "remaining_time": "4:27:47"}
54
- {"current_steps": 450, "total_steps": 1548, "eval_loss": 0.4206688702106476, "epoch": 0.2905803535394301, "percentage": 29.07, "elapsed_time": "1:51:37", "remaining_time": "4:32:22"}
55
- {"current_steps": 460, "total_steps": 1548, "loss": 0.4705, "lr": 8.863039526996891e-06, "epoch": 0.2970376947291953, "percentage": 29.72, "elapsed_time": "1:53:44", "remaining_time": "4:29:00"}
56
- {"current_steps": 470, "total_steps": 1548, "loss": 0.4893, "lr": 8.790471500856229e-06, "epoch": 0.3034950359189604, "percentage": 30.36, "elapsed_time": "1:55:49", "remaining_time": "4:25:39"}
57
- {"current_steps": 480, "total_steps": 1548, "loss": 0.507, "lr": 8.715975628707917e-06, "epoch": 0.3099523771087255, "percentage": 31.01, "elapsed_time": "1:57:55", "remaining_time": "4:22:22"}
58
- {"current_steps": 490, "total_steps": 1548, "loss": 0.4845, "lr": 8.63958979939235e-06, "epoch": 0.31640971829849057, "percentage": 31.65, "elapsed_time": "2:00:01", "remaining_time": "4:19:08"}
59
- {"current_steps": 500, "total_steps": 1548, "loss": 0.4645, "lr": 8.56135286298822e-06, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:02:07", "remaining_time": "4:15:58"}
60
- {"current_steps": 500, "total_steps": 1548, "eval_loss": 0.4184779226779938, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:03:59", "remaining_time": "4:19:53"}
61
- {"current_steps": 510, "total_steps": 1548, "loss": 0.4967, "lr": 8.48130461105324e-06, "epoch": 0.3293244006780208, "percentage": 32.95, "elapsed_time": "2:07:12", "remaining_time": "4:18:53"}
62
- {"current_steps": 520, "total_steps": 1548, "loss": 0.4553, "lr": 8.399485756386038e-06, "epoch": 0.3357817418677859, "percentage": 33.59, "elapsed_time": "2:09:18", "remaining_time": "4:15:37"}
63
- {"current_steps": 530, "total_steps": 1548, "loss": 0.4713, "lr": 8.315937912319493e-06, "epoch": 0.3422390830575511, "percentage": 34.24, "elapsed_time": "2:11:25", "remaining_time": "4:12:26"}
64
- {"current_steps": 540, "total_steps": 1548, "loss": 0.4698, "lr": 8.23070357155605e-06, "epoch": 0.3486964242473162, "percentage": 34.88, "elapsed_time": "2:13:31", "remaining_time": "4:09:15"}
65
- {"current_steps": 550, "total_steps": 1548, "loss": 0.4547, "lr": 8.143826084555809e-06, "epoch": 0.35515376543708127, "percentage": 35.53, "elapsed_time": "2:15:37", "remaining_time": "4:06:06"}
66
- {"current_steps": 550, "total_steps": 1548, "eval_loss": 0.4105076193809509, "epoch": 0.35515376543708127, "percentage": 35.53, "elapsed_time": "2:17:30", "remaining_time": "4:09:30"}
67
- {"current_steps": 560, "total_steps": 1548, "loss": 0.4626, "lr": 8.055349637488336e-06, "epoch": 0.3616111066268464, "percentage": 36.18, "elapsed_time": "2:19:36", "remaining_time": "4:06:18"}
68
- {"current_steps": 570, "total_steps": 1548, "loss": 0.4597, "lr": 7.965319229759435e-06, "epoch": 0.3680684478166115, "percentage": 36.82, "elapsed_time": "2:21:43", "remaining_time": "4:03:10"}
69
- {"current_steps": 580, "total_steps": 1548, "loss": 0.4742, "lr": 7.873780651124302e-06, "epoch": 0.3745257890063766, "percentage": 37.47, "elapsed_time": "2:23:50", "remaining_time": "4:00:03"}
70
- {"current_steps": 590, "total_steps": 1548, "loss": 0.4471, "lr": 7.78078045839871e-06, "epoch": 0.3809831301961417, "percentage": 38.11, "elapsed_time": "2:25:55", "remaining_time": "3:56:55"}
71
- {"current_steps": 600, "total_steps": 1548, "loss": 0.4583, "lr": 7.686365951780071e-06, "epoch": 0.38744047138590687, "percentage": 38.76, "elapsed_time": "2:28:01", "remaining_time": "3:53:53"}
72
- {"current_steps": 600, "total_steps": 1548, "eval_loss": 0.4018101692199707, "epoch": 0.38744047138590687, "percentage": 38.76, "elapsed_time": "2:29:54", "remaining_time": "3:56:51"}
73
- {"current_steps": 610, "total_steps": 1548, "loss": 0.4417, "lr": 7.590585150790388e-06, "epoch": 0.39389781257567197, "percentage": 39.41, "elapsed_time": "2:32:00", "remaining_time": "3:53:45"}
74
- {"current_steps": 620, "total_steps": 1548, "loss": 0.4654, "lr": 7.493486769853383e-06, "epoch": 0.40035515376543707, "percentage": 40.05, "elapsed_time": "2:34:06", "remaining_time": "3:50:39"}
75
- {"current_steps": 630, "total_steps": 1548, "loss": 0.4527, "lr": 7.39512019351818e-06, "epoch": 0.4068124949552022, "percentage": 40.7, "elapsed_time": "2:36:11", "remaining_time": "3:47:35"}
76
- {"current_steps": 640, "total_steps": 1548, "loss": 0.4319, "lr": 7.295535451342166e-06, "epoch": 0.4132698361449673, "percentage": 41.34, "elapsed_time": "2:38:16", "remaining_time": "3:44:33"}
77
- {"current_steps": 650, "total_steps": 1548, "loss": 0.4604, "lr": 7.194783192445795e-06, "epoch": 0.4197271773347324, "percentage": 41.99, "elapsed_time": "2:40:23", "remaining_time": "3:41:34"}
78
- {"current_steps": 650, "total_steps": 1548, "eval_loss": 0.3958105742931366, "epoch": 0.4197271773347324, "percentage": 41.99, "elapsed_time": "2:42:15", "remaining_time": "3:44:10"}
79
- {"current_steps": 660, "total_steps": 1548, "loss": 0.4513, "lr": 7.092914659752286e-06, "epoch": 0.4261845185244975, "percentage": 42.64, "elapsed_time": "2:44:23", "remaining_time": "3:41:10"}
80
- {"current_steps": 670, "total_steps": 1548, "loss": 0.4522, "lr": 6.989981663925301e-06, "epoch": 0.43264185971426267, "percentage": 43.28, "elapsed_time": "2:46:29", "remaining_time": "3:38:11"}
81
- {"current_steps": 680, "total_steps": 1548, "loss": 0.4663, "lr": 6.886036557017881e-06, "epoch": 0.43909920090402776, "percentage": 43.93, "elapsed_time": "2:48:34", "remaining_time": "3:35:11"}
82
- {"current_steps": 690, "total_steps": 1548, "loss": 0.4463, "lr": 6.781132205846019e-06, "epoch": 0.44555654209379286, "percentage": 44.57, "elapsed_time": "2:50:41", "remaining_time": "3:32:15"}
83
- {"current_steps": 700, "total_steps": 1548, "loss": 0.4275, "lr": 6.675321965100431e-06, "epoch": 0.452013883283558, "percentage": 45.22, "elapsed_time": "2:52:48", "remaining_time": "3:29:21"}
84
- {"current_steps": 700, "total_steps": 1548, "eval_loss": 0.38591721653938293, "epoch": 0.452013883283558, "percentage": 45.22, "elapsed_time": "2:54:41", "remaining_time": "3:31:37"}
85
- {"current_steps": 710, "total_steps": 1548, "loss": 0.4383, "lr": 6.568659650210184e-06, "epoch": 0.4584712244733231, "percentage": 45.87, "elapsed_time": "2:56:46", "remaining_time": "3:28:39"}
86
- {"current_steps": 720, "total_steps": 1548, "loss": 0.4251, "lr": 6.461199509972001e-06, "epoch": 0.4649285656630882, "percentage": 46.51, "elapsed_time": "2:58:54", "remaining_time": "3:25:44"}
87
- {"current_steps": 730, "total_steps": 1548, "loss": 0.4102, "lr": 6.35299619895914e-06, "epoch": 0.47138590685285336, "percentage": 47.16, "elapsed_time": "3:00:59", "remaining_time": "3:22:49"}
88
- {"current_steps": 740, "total_steps": 1548, "loss": 0.436, "lr": 6.244104749723916e-06, "epoch": 0.47784324804261846, "percentage": 47.8, "elapsed_time": "3:03:04", "remaining_time": "3:19:54"}
89
- {"current_steps": 750, "total_steps": 1548, "loss": 0.4507, "lr": 6.134580544807951e-06, "epoch": 0.48430058923238356, "percentage": 48.45, "elapsed_time": "3:05:11", "remaining_time": "3:17:02"}
90
- {"current_steps": 750, "total_steps": 1548, "eval_loss": 0.3814530670642853, "epoch": 0.48430058923238356, "percentage": 48.45, "elapsed_time": "3:07:03", "remaining_time": "3:19:01"}
91
- {"current_steps": 760, "total_steps": 1548, "loss": 0.4373, "lr": 6.024479288574448e-06, "epoch": 0.49075793042214866, "percentage": 49.1, "elapsed_time": "3:09:08", "remaining_time": "3:16:06"}
92
- {"current_steps": 770, "total_steps": 1548, "loss": 0.4187, "lr": 5.9138569788767645e-06, "epoch": 0.4972152716119138, "percentage": 49.74, "elapsed_time": "3:11:14", "remaining_time": "3:13:13"}
93
- {"current_steps": 780, "total_steps": 1548, "loss": 0.4172, "lr": 5.802769878577729e-06, "epoch": 0.5036726128016789, "percentage": 50.39, "elapsed_time": "3:13:22", "remaining_time": "3:10:23"}
94
- {"current_steps": 790, "total_steps": 1548, "loss": 0.4273, "lr": 5.691274486934166e-06, "epoch": 0.510129953991444, "percentage": 51.03, "elapsed_time": "3:15:27", "remaining_time": "3:07:32"}
95
- {"current_steps": 800, "total_steps": 1548, "loss": 0.4193, "lr": 5.579427510861194e-06, "epoch": 0.5165872951812092, "percentage": 51.68, "elapsed_time": "3:17:33", "remaining_time": "3:04:42"}
96
- {"current_steps": 800, "total_steps": 1548, "eval_loss": 0.36689069867134094, "epoch": 0.5165872951812092, "percentage": 51.68, "elapsed_time": "3:19:25", "remaining_time": "3:06:27"}
97
- {"current_steps": 810, "total_steps": 1548, "loss": 0.4263, "lr": 5.4672858360909e-06, "epoch": 0.5230446363709742, "percentage": 52.33, "elapsed_time": "3:21:30", "remaining_time": "3:03:35"}
98
- {"current_steps": 820, "total_steps": 1548, "loss": 0.4221, "lr": 5.35490649824008e-06, "epoch": 0.5295019775607394, "percentage": 52.97, "elapsed_time": "3:23:38", "remaining_time": "3:00:47"}
99
- {"current_steps": 830, "total_steps": 1548, "loss": 0.4484, "lr": 5.242346653801739e-06, "epoch": 0.5359593187505045, "percentage": 53.62, "elapsed_time": "3:25:44", "remaining_time": "2:57:58"}
100
- {"current_steps": 840, "total_steps": 1548, "loss": 0.423, "lr": 5.129663551075109e-06, "epoch": 0.5424166599402696, "percentage": 54.26, "elapsed_time": "3:27:50", "remaining_time": "2:55:10"}
101
- {"current_steps": 850, "total_steps": 1548, "loss": 0.4198, "lr": 5.016914501048988e-06, "epoch": 0.5488740011300347, "percentage": 54.91, "elapsed_time": "3:29:58", "remaining_time": "2:52:25"}
102
- {"current_steps": 850, "total_steps": 1548, "eval_loss": 0.3651440143585205, "epoch": 0.5488740011300347, "percentage": 54.91, "elapsed_time": "3:31:50", "remaining_time": "2:53:57"}
103
- {"current_steps": 860, "total_steps": 1548, "loss": 0.4133, "lr": 4.904156848253184e-06, "epoch": 0.5553313423197999, "percentage": 55.56, "elapsed_time": "3:33:58", "remaining_time": "2:51:10"}
104
- {"current_steps": 870, "total_steps": 1548, "loss": 0.4232, "lr": 4.791447941592896e-06, "epoch": 0.5617886835095649, "percentage": 56.2, "elapsed_time": "3:36:05", "remaining_time": "2:48:24"}
105
- {"current_steps": 880, "total_steps": 1548, "loss": 0.4057, "lr": 4.678845105180886e-06, "epoch": 0.56824602469933, "percentage": 56.85, "elapsed_time": "3:38:12", "remaining_time": "2:45:38"}
106
- {"current_steps": 890, "total_steps": 1548, "loss": 0.406, "lr": 4.566405609182247e-06, "epoch": 0.5747033658890952, "percentage": 57.49, "elapsed_time": "3:40:18", "remaining_time": "2:42:52"}
107
- {"current_steps": 900, "total_steps": 1548, "loss": 0.4375, "lr": 4.454186640686607e-06, "epoch": 0.5811607070788603, "percentage": 58.14, "elapsed_time": "3:42:24", "remaining_time": "2:40:08"}
108
- {"current_steps": 900, "total_steps": 1548, "eval_loss": 0.36162474751472473, "epoch": 0.5811607070788603, "percentage": 58.14, "elapsed_time": "3:44:17", "remaining_time": "2:41:29"}
109
- {"current_steps": 910, "total_steps": 1548, "loss": 0.4009, "lr": 4.3422452746226e-06, "epoch": 0.5876180482686254, "percentage": 58.79, "elapsed_time": "3:46:22", "remaining_time": "2:38:42"}
110
- {"current_steps": 920, "total_steps": 1548, "loss": 0.4373, "lr": 4.230638444729368e-06, "epoch": 0.5940753894583906, "percentage": 59.43, "elapsed_time": "3:48:27", "remaining_time": "2:35:56"}
111
- {"current_steps": 930, "total_steps": 1548, "loss": 0.4032, "lr": 4.1194229145998795e-06, "epoch": 0.6005327306481556, "percentage": 60.08, "elapsed_time": "3:50:32", "remaining_time": "2:33:11"}
112
- {"current_steps": 940, "total_steps": 1548, "loss": 0.4054, "lr": 4.008655248810787e-06, "epoch": 0.6069900718379208, "percentage": 60.72, "elapsed_time": "3:52:40", "remaining_time": "2:30:29"}
113
- {"current_steps": 950, "total_steps": 1548, "loss": 0.4048, "lr": 3.898391784153494e-06, "epoch": 0.6134474130276858, "percentage": 61.37, "elapsed_time": "3:54:45", "remaining_time": "2:27:46"}
114
- {"current_steps": 950, "total_steps": 1548, "eval_loss": 0.35559317469596863, "epoch": 0.6134474130276858, "percentage": 61.37, "elapsed_time": "3:56:38", "remaining_time": "2:28:57"}
115
- {"current_steps": 960, "total_steps": 1548, "loss": 0.4069, "lr": 3.788688600981085e-06, "epoch": 0.619904754217451, "percentage": 62.02, "elapsed_time": "3:58:44", "remaining_time": "2:26:13"}
116
- {"current_steps": 970, "total_steps": 1548, "loss": 0.4141, "lr": 3.679601494685679e-06, "epoch": 0.6263620954072161, "percentage": 62.66, "elapsed_time": "4:00:51", "remaining_time": "2:23:31"}
117
- {"current_steps": 980, "total_steps": 1548, "loss": 0.4069, "lr": 3.571185947320712e-06, "epoch": 0.6328194365969811, "percentage": 63.31, "elapsed_time": "4:02:58", "remaining_time": "2:20:49"}
118
- {"current_steps": 990, "total_steps": 1548, "loss": 0.3975, "lr": 3.4634970993825854e-06, "epoch": 0.6392767777867463, "percentage": 63.95, "elapsed_time": "4:05:05", "remaining_time": "2:18:08"}
119
- {"current_steps": 1000, "total_steps": 1548, "loss": 0.4147, "lr": 3.356589721766034e-06, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:07:10", "remaining_time": "2:15:27"}
120
- {"current_steps": 1000, "total_steps": 1548, "eval_loss": 0.34971049427986145, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:09:03", "remaining_time": "2:16:28"}
 
1
+ {"current_steps": 10, "total_steps": 1548, "loss": 1.4776, "lr": 6.451612903225807e-07, "epoch": 0.006457341189765114, "percentage": 0.65, "elapsed_time": "0:02:09", "remaining_time": "5:31:39"}
2
+ {"current_steps": 20, "total_steps": 1548, "loss": 1.0088, "lr": 1.2903225806451614e-06, "epoch": 0.012914682379530229, "percentage": 1.29, "elapsed_time": "0:04:15", "remaining_time": "5:25:00"}
3
+ {"current_steps": 30, "total_steps": 1548, "loss": 0.7032, "lr": 1.935483870967742e-06, "epoch": 0.019372023569295342, "percentage": 1.94, "elapsed_time": "0:06:20", "remaining_time": "5:20:32"}
4
+ {"current_steps": 40, "total_steps": 1548, "loss": 0.6113, "lr": 2.580645161290323e-06, "epoch": 0.025829364759060457, "percentage": 2.58, "elapsed_time": "0:08:26", "remaining_time": "5:18:20"}
5
+ {"current_steps": 50, "total_steps": 1548, "loss": 0.5429, "lr": 3.225806451612903e-06, "epoch": 0.03228670594882557, "percentage": 3.23, "elapsed_time": "0:10:32", "remaining_time": "5:15:55"}
6
+ {"current_steps": 50, "total_steps": 1548, "eval_loss": 0.4979822635650635, "epoch": 0.03228670594882557, "percentage": 3.23, "elapsed_time": "0:12:24", "remaining_time": "6:11:50"}
7
+ {"current_steps": 60, "total_steps": 1548, "loss": 0.5324, "lr": 3.870967741935484e-06, "epoch": 0.038744047138590684, "percentage": 3.88, "elapsed_time": "0:14:31", "remaining_time": "6:00:14"}
8
+ {"current_steps": 70, "total_steps": 1548, "loss": 0.5465, "lr": 4.516129032258065e-06, "epoch": 0.0452013883283558, "percentage": 4.52, "elapsed_time": "0:16:36", "remaining_time": "5:50:41"}
9
+ {"current_steps": 80, "total_steps": 1548, "loss": 0.5395, "lr": 5.161290322580646e-06, "epoch": 0.051658729518120915, "percentage": 5.17, "elapsed_time": "0:18:41", "remaining_time": "5:43:05"}
10
+ {"current_steps": 90, "total_steps": 1548, "loss": 0.5142, "lr": 5.806451612903226e-06, "epoch": 0.058116070707886026, "percentage": 5.81, "elapsed_time": "0:20:49", "remaining_time": "5:37:13"}
11
+ {"current_steps": 100, "total_steps": 1548, "loss": 0.5398, "lr": 6.451612903225806e-06, "epoch": 0.06457341189765115, "percentage": 6.46, "elapsed_time": "0:22:54", "remaining_time": "5:31:36"}
12
+ {"current_steps": 100, "total_steps": 1548, "eval_loss": 0.4740481972694397, "epoch": 0.06457341189765115, "percentage": 6.46, "elapsed_time": "0:24:45", "remaining_time": "5:58:36"}
13
+ {"current_steps": 110, "total_steps": 1548, "loss": 0.5428, "lr": 7.096774193548388e-06, "epoch": 0.07103075308741626, "percentage": 7.11, "elapsed_time": "0:26:52", "remaining_time": "5:51:13"}
14
+ {"current_steps": 120, "total_steps": 1548, "loss": 0.5282, "lr": 7.741935483870968e-06, "epoch": 0.07748809427718137, "percentage": 7.75, "elapsed_time": "0:28:57", "remaining_time": "5:44:31"}
15
+ {"current_steps": 130, "total_steps": 1548, "loss": 0.559, "lr": 8.387096774193549e-06, "epoch": 0.08394543546694648, "percentage": 8.4, "elapsed_time": "0:31:02", "remaining_time": "5:38:36"}
16
+ {"current_steps": 140, "total_steps": 1548, "loss": 0.5582, "lr": 9.03225806451613e-06, "epoch": 0.0904027766567116, "percentage": 9.04, "elapsed_time": "0:33:09", "remaining_time": "5:33:29"}
17
+ {"current_steps": 150, "total_steps": 1548, "loss": 0.5484, "lr": 9.67741935483871e-06, "epoch": 0.09686011784647672, "percentage": 9.69, "elapsed_time": "0:35:13", "remaining_time": "5:28:17"}
18
+ {"current_steps": 150, "total_steps": 1548, "eval_loss": 0.4832856059074402, "epoch": 0.09686011784647672, "percentage": 9.69, "elapsed_time": "0:37:05", "remaining_time": "5:45:40"}
19
+ {"current_steps": 160, "total_steps": 1548, "loss": 0.5607, "lr": 9.999682112882774e-06, "epoch": 0.10331745903624183, "percentage": 10.34, "elapsed_time": "0:39:11", "remaining_time": "5:39:57"}
20
+ {"current_steps": 170, "total_steps": 1548, "loss": 0.5586, "lr": 9.997139258465151e-06, "epoch": 0.10977480022600694, "percentage": 10.98, "elapsed_time": "0:41:18", "remaining_time": "5:34:52"}
21
+ {"current_steps": 180, "total_steps": 1548, "loss": 0.5564, "lr": 9.992054842933846e-06, "epoch": 0.11623214141577205, "percentage": 11.63, "elapsed_time": "0:43:24", "remaining_time": "5:29:52"}
22
+ {"current_steps": 190, "total_steps": 1548, "loss": 0.5253, "lr": 9.984431452238968e-06, "epoch": 0.12268948260553716, "percentage": 12.27, "elapsed_time": "0:45:30", "remaining_time": "5:25:13"}
23
+ {"current_steps": 200, "total_steps": 1548, "loss": 0.5265, "lr": 9.974272963661561e-06, "epoch": 0.1291468237953023, "percentage": 12.92, "elapsed_time": "0:47:36", "remaining_time": "5:20:50"}
24
+ {"current_steps": 200, "total_steps": 1548, "eval_loss": 0.47804030776023865, "epoch": 0.1291468237953023, "percentage": 12.92, "elapsed_time": "0:49:28", "remaining_time": "5:33:24"}
25
+ {"current_steps": 210, "total_steps": 1548, "loss": 0.5329, "lr": 9.961584543841625e-06, "epoch": 0.1356041649850674, "percentage": 13.57, "elapsed_time": "0:51:34", "remaining_time": "5:28:34"}
26
+ {"current_steps": 220, "total_steps": 1548, "loss": 0.5534, "lr": 9.946372646150322e-06, "epoch": 0.1420615061748325, "percentage": 14.21, "elapsed_time": "0:53:38", "remaining_time": "5:23:50"}
27
+ {"current_steps": 230, "total_steps": 1548, "loss": 0.5365, "lr": 9.928645007407791e-06, "epoch": 0.14851884736459764, "percentage": 14.86, "elapsed_time": "0:55:45", "remaining_time": "5:19:30"}
28
+ {"current_steps": 240, "total_steps": 1548, "loss": 0.5118, "lr": 9.908410643948162e-06, "epoch": 0.15497618855436274, "percentage": 15.5, "elapsed_time": "0:57:50", "remaining_time": "5:15:11"}
29
+ {"current_steps": 250, "total_steps": 1548, "loss": 0.5278, "lr": 9.885679847033832e-06, "epoch": 0.16143352974412786, "percentage": 16.15, "elapsed_time": "0:59:55", "remaining_time": "5:11:06"}
30
+ {"current_steps": 250, "total_steps": 1548, "eval_loss": 0.47931385040283203, "epoch": 0.16143352974412786, "percentage": 16.15, "elapsed_time": "1:01:47", "remaining_time": "5:20:47"}
31
+ {"current_steps": 260, "total_steps": 1548, "loss": 0.5422, "lr": 9.860464177621286e-06, "epoch": 0.16789087093389296, "percentage": 16.8, "elapsed_time": "1:03:53", "remaining_time": "5:16:31"}
32
+ {"current_steps": 270, "total_steps": 1548, "loss": 0.4994, "lr": 9.832776460481162e-06, "epoch": 0.1743482121236581, "percentage": 17.44, "elapsed_time": "1:05:59", "remaining_time": "5:12:20"}
33
+ {"current_steps": 280, "total_steps": 1548, "loss": 0.5331, "lr": 9.802630777675528e-06, "epoch": 0.1808055533134232, "percentage": 18.09, "elapsed_time": "1:08:04", "remaining_time": "5:08:16"}
34
+ {"current_steps": 290, "total_steps": 1548, "loss": 0.5277, "lr": 9.770042461395705e-06, "epoch": 0.1872628945031883, "percentage": 18.73, "elapsed_time": "1:10:09", "remaining_time": "5:04:21"}
35
+ {"current_steps": 300, "total_steps": 1548, "loss": 0.5259, "lr": 9.735028086164265e-06, "epoch": 0.19372023569295344, "percentage": 19.38, "elapsed_time": "1:12:17", "remaining_time": "5:00:43"}
36
+ {"current_steps": 300, "total_steps": 1548, "eval_loss": 0.45192769169807434, "epoch": 0.19372023569295344, "percentage": 19.38, "elapsed_time": "1:14:09", "remaining_time": "5:08:28"}
37
+ {"current_steps": 310, "total_steps": 1548, "loss": 0.5184, "lr": 9.697605460405162e-06, "epoch": 0.20017757688271853, "percentage": 20.03, "elapsed_time": "1:16:14", "remaining_time": "5:04:30"}
38
+ {"current_steps": 320, "total_steps": 1548, "loss": 0.5183, "lr": 9.657793617386337e-06, "epoch": 0.20663491807248366, "percentage": 20.67, "elapsed_time": "1:18:19", "remaining_time": "5:00:34"}
39
+ {"current_steps": 330, "total_steps": 1548, "loss": 0.5109, "lr": 9.615612805539305e-06, "epoch": 0.21309225926224876, "percentage": 21.32, "elapsed_time": "1:20:26", "remaining_time": "4:56:53"}
40
+ {"current_steps": 340, "total_steps": 1548, "loss": 0.5056, "lr": 9.571084478160763e-06, "epoch": 0.21954960045201388, "percentage": 21.96, "elapsed_time": "1:22:32", "remaining_time": "4:53:14"}
41
+ {"current_steps": 350, "total_steps": 1548, "loss": 0.5293, "lr": 9.524231282501362e-06, "epoch": 0.226006941641779, "percentage": 22.61, "elapsed_time": "1:24:39", "remaining_time": "4:49:46"}
42
+ {"current_steps": 350, "total_steps": 1548, "eval_loss": 0.4497073292732239, "epoch": 0.226006941641779, "percentage": 22.61, "elapsed_time": "1:26:31", "remaining_time": "4:56:09"}
43
+ {"current_steps": 360, "total_steps": 1548, "loss": 0.4857, "lr": 9.475077048247243e-06, "epoch": 0.2324642828315441, "percentage": 23.26, "elapsed_time": "1:28:36", "remaining_time": "4:52:25"}
44
+ {"current_steps": 370, "total_steps": 1548, "loss": 0.5132, "lr": 9.423646775400186e-06, "epoch": 0.23892162402130923, "percentage": 23.9, "elapsed_time": "1:30:41", "remaining_time": "4:48:45"}
45
+ {"current_steps": 380, "total_steps": 1548, "loss": 0.494, "lr": 9.369966621562525e-06, "epoch": 0.24537896521107433, "percentage": 24.55, "elapsed_time": "1:32:47", "remaining_time": "4:45:12"}
46
+ {"current_steps": 390, "total_steps": 1548, "loss": 0.5045, "lr": 9.314063888633312e-06, "epoch": 0.2518363064008394, "percentage": 25.19, "elapsed_time": "1:34:52", "remaining_time": "4:41:43"}
47
+ {"current_steps": 400, "total_steps": 1548, "loss": 0.5098, "lr": 9.255967008922475e-06, "epoch": 0.2582936475906046, "percentage": 25.84, "elapsed_time": "1:36:59", "remaining_time": "4:38:20"}
48
+ {"current_steps": 400, "total_steps": 1548, "eval_loss": 0.43027767539024353, "epoch": 0.2582936475906046, "percentage": 25.84, "elapsed_time": "1:38:51", "remaining_time": "4:43:42"}
49
+ {"current_steps": 410, "total_steps": 1548, "loss": 0.5018, "lr": 9.19570553069006e-06, "epoch": 0.2647509887803697, "percentage": 26.49, "elapsed_time": "1:40:58", "remaining_time": "4:40:14"}
50
+ {"current_steps": 420, "total_steps": 1548, "loss": 0.4794, "lr": 9.133310103117891e-06, "epoch": 0.2712083299701348, "percentage": 27.13, "elapsed_time": "1:43:03", "remaining_time": "4:36:47"}
51
+ {"current_steps": 430, "total_steps": 1548, "loss": 0.477, "lr": 9.068812460721296e-06, "epoch": 0.27766567115989993, "percentage": 27.78, "elapsed_time": "1:45:09", "remaining_time": "4:33:25"}
52
+ {"current_steps": 440, "total_steps": 1548, "loss": 0.5121, "lr": 9.002245407208831e-06, "epoch": 0.284123012349665, "percentage": 28.42, "elapsed_time": "1:47:14", "remaining_time": "4:30:03"}
53
+ {"current_steps": 450, "total_steps": 1548, "loss": 0.482, "lr": 8.9336427987982e-06, "epoch": 0.2905803535394301, "percentage": 29.07, "elapsed_time": "1:49:21", "remaining_time": "4:26:49"}
54
+ {"current_steps": 450, "total_steps": 1548, "eval_loss": 0.4249188303947449, "epoch": 0.2905803535394301, "percentage": 29.07, "elapsed_time": "1:51:13", "remaining_time": "4:31:22"}
55
+ {"current_steps": 460, "total_steps": 1548, "loss": 0.4717, "lr": 8.863039526996891e-06, "epoch": 0.2970376947291953, "percentage": 29.72, "elapsed_time": "1:53:19", "remaining_time": "4:28:01"}
56
+ {"current_steps": 470, "total_steps": 1548, "loss": 0.4905, "lr": 8.790471500856229e-06, "epoch": 0.3034950359189604, "percentage": 30.36, "elapsed_time": "1:55:24", "remaining_time": "4:24:41"}
57
+ {"current_steps": 480, "total_steps": 1548, "loss": 0.5077, "lr": 8.715975628707917e-06, "epoch": 0.3099523771087255, "percentage": 31.01, "elapsed_time": "1:57:29", "remaining_time": "4:21:25"}
58
+ {"current_steps": 490, "total_steps": 1548, "loss": 0.485, "lr": 8.63958979939235e-06, "epoch": 0.31640971829849057, "percentage": 31.65, "elapsed_time": "1:59:34", "remaining_time": "4:18:11"}
59
+ {"current_steps": 500, "total_steps": 1548, "loss": 0.4683, "lr": 8.56135286298822e-06, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:01:40", "remaining_time": "4:15:02"}
60
+ {"current_steps": 500, "total_steps": 1548, "eval_loss": 0.4224134683609009, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:03:32", "remaining_time": "4:18:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:209393e9e0bb2411c311755e4b962e1189c1937fdd6bd21d782b430003318669
3
  size 7544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:901d474d660c54332b0355b1c64aa5804cdb26c290d514ff376fa252b525284f
3
  size 7544