sedrickkeh commited on
Commit
bf0268c
·
verified ·
1 Parent(s): 3506625

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:eaa517f491c3d3da314d6fc8d569d38e3531440f688007adfff23ac120c6e26f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338402fbe0bc309cc6ff04501479787704a977a07f029ceda52bf51e636ecff3
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:808dbe047d95738e1041d49f750773e21c25337195873976f1d9c5f26c7c8bce
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb09093bd56175cbbf1c0f4ff9923730c7aed24728b2997df33af86005d1f50
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ac9fea3dbb07440bc7f612eb89ad63ab225f4ab97fbf07f392e645e10d3ba7
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7bf2250f129014dcd4b3d1305790fa584b21de0a288aeeeb049a5bb3e0b0ba
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:da17dea92315d0547f945f1eaed4720041584a3fa4f1f86df3564806a241732b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baee0eabcd9db051bc15973841c3eed9fc961bd40108ea71b2e9c47ea48aafa8
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,31 +1,83 @@
1
- {"current_steps": 1, "total_steps": 30, "loss": 1.0596, "lr": 3.3333333333333333e-06, "epoch": 0.09375, "percentage": 3.33, "elapsed_time": "0:00:25", "remaining_time": "0:12:20"}
2
- {"current_steps": 2, "total_steps": 30, "loss": 1.0409, "lr": 6.666666666666667e-06, "epoch": 0.1875, "percentage": 6.67, "elapsed_time": "0:00:50", "remaining_time": "0:11:41"}
3
- {"current_steps": 3, "total_steps": 30, "loss": 1.0223, "lr": 1e-05, "epoch": 0.28125, "percentage": 10.0, "elapsed_time": "0:01:17", "remaining_time": "0:11:35"}
4
- {"current_steps": 4, "total_steps": 30, "loss": 0.8987, "lr": 9.966191788709716e-06, "epoch": 0.375, "percentage": 13.33, "elapsed_time": "0:01:52", "remaining_time": "0:12:09"}
5
- {"current_steps": 5, "total_steps": 30, "loss": 0.911, "lr": 9.86522435289912e-06, "epoch": 0.46875, "percentage": 16.67, "elapsed_time": "0:02:18", "remaining_time": "0:11:34"}
6
- {"current_steps": 6, "total_steps": 30, "loss": 0.9099, "lr": 9.698463103929542e-06, "epoch": 0.5625, "percentage": 20.0, "elapsed_time": "0:02:43", "remaining_time": "0:10:52"}
7
- {"current_steps": 7, "total_steps": 30, "loss": 0.8982, "lr": 9.468163201617063e-06, "epoch": 0.65625, "percentage": 23.33, "elapsed_time": "0:03:04", "remaining_time": "0:10:06"}
8
- {"current_steps": 8, "total_steps": 30, "loss": 0.897, "lr": 9.177439057064684e-06, "epoch": 0.75, "percentage": 26.67, "elapsed_time": "0:03:31", "remaining_time": "0:09:40"}
9
- {"current_steps": 9, "total_steps": 30, "loss": 0.8386, "lr": 8.83022221559489e-06, "epoch": 0.84375, "percentage": 30.0, "elapsed_time": "0:04:04", "remaining_time": "0:09:30"}
10
- {"current_steps": 10, "total_steps": 30, "loss": 0.8219, "lr": 8.43120818934367e-06, "epoch": 0.9375, "percentage": 33.33, "elapsed_time": "0:04:35", "remaining_time": "0:09:10"}
11
- {"current_steps": 11, "total_steps": 30, "loss": 1.3903, "lr": 7.985792958513932e-06, "epoch": 1.0625, "percentage": 36.67, "elapsed_time": "0:05:46", "remaining_time": "0:09:59"}
12
- {"current_steps": 12, "total_steps": 30, "loss": 0.7311, "lr": 7.500000000000001e-06, "epoch": 1.15625, "percentage": 40.0, "elapsed_time": "0:06:15", "remaining_time": "0:09:22"}
13
- {"current_steps": 13, "total_steps": 30, "loss": 0.7712, "lr": 6.980398830195785e-06, "epoch": 1.25, "percentage": 43.33, "elapsed_time": "0:06:45", "remaining_time": "0:08:50"}
14
- {"current_steps": 14, "total_steps": 30, "loss": 0.7208, "lr": 6.434016163555452e-06, "epoch": 1.34375, "percentage": 46.67, "elapsed_time": "0:07:06", "remaining_time": "0:08:07"}
15
- {"current_steps": 15, "total_steps": 30, "loss": 0.768, "lr": 5.8682408883346535e-06, "epoch": 1.4375, "percentage": 50.0, "elapsed_time": "0:07:37", "remaining_time": "0:07:37"}
16
- {"current_steps": 16, "total_steps": 30, "loss": 0.7986, "lr": 5.290724144552379e-06, "epoch": 1.53125, "percentage": 53.33, "elapsed_time": "0:08:06", "remaining_time": "0:07:05"}
17
- {"current_steps": 17, "total_steps": 30, "loss": 0.6939, "lr": 4.7092758554476215e-06, "epoch": 1.625, "percentage": 56.67, "elapsed_time": "0:08:41", "remaining_time": "0:06:38"}
18
- {"current_steps": 18, "total_steps": 30, "loss": 0.7287, "lr": 4.131759111665349e-06, "epoch": 1.71875, "percentage": 60.0, "elapsed_time": "0:09:09", "remaining_time": "0:06:06"}
19
- {"current_steps": 19, "total_steps": 30, "loss": 0.7368, "lr": 3.5659838364445505e-06, "epoch": 1.8125, "percentage": 63.33, "elapsed_time": "0:09:34", "remaining_time": "0:05:32"}
20
- {"current_steps": 20, "total_steps": 30, "loss": 0.6756, "lr": 3.019601169804216e-06, "epoch": 1.90625, "percentage": 66.67, "elapsed_time": "0:10:01", "remaining_time": "0:05:00"}
21
- {"current_steps": 21, "total_steps": 30, "loss": 1.1922, "lr": 2.5000000000000015e-06, "epoch": 2.03125, "percentage": 70.0, "elapsed_time": "0:11:14", "remaining_time": "0:04:48"}
22
- {"current_steps": 22, "total_steps": 30, "loss": 0.6695, "lr": 2.0142070414860704e-06, "epoch": 2.125, "percentage": 73.33, "elapsed_time": "0:11:46", "remaining_time": "0:04:16"}
23
- {"current_steps": 23, "total_steps": 30, "loss": 0.6786, "lr": 1.5687918106563326e-06, "epoch": 2.21875, "percentage": 76.67, "elapsed_time": "0:12:09", "remaining_time": "0:03:42"}
24
- {"current_steps": 24, "total_steps": 30, "loss": 0.7032, "lr": 1.1697777844051105e-06, "epoch": 2.3125, "percentage": 80.0, "elapsed_time": "0:12:35", "remaining_time": "0:03:08"}
25
- {"current_steps": 25, "total_steps": 30, "loss": 0.6561, "lr": 8.225609429353187e-07, "epoch": 2.40625, "percentage": 83.33, "elapsed_time": "0:13:07", "remaining_time": "0:02:37"}
26
- {"current_steps": 26, "total_steps": 30, "loss": 0.6628, "lr": 5.318367983829393e-07, "epoch": 2.5, "percentage": 86.67, "elapsed_time": "0:13:30", "remaining_time": "0:02:04"}
27
- {"current_steps": 27, "total_steps": 30, "loss": 0.7113, "lr": 3.015368960704584e-07, "epoch": 2.59375, "percentage": 90.0, "elapsed_time": "0:13:57", "remaining_time": "0:01:33"}
28
- {"current_steps": 28, "total_steps": 30, "loss": 0.6845, "lr": 1.3477564710088097e-07, "epoch": 2.6875, "percentage": 93.33, "elapsed_time": "0:14:29", "remaining_time": "0:01:02"}
29
- {"current_steps": 29, "total_steps": 30, "loss": 0.6777, "lr": 3.3808211290284886e-08, "epoch": 2.78125, "percentage": 96.67, "elapsed_time": "0:15:01", "remaining_time": "0:00:31"}
30
- {"current_steps": 30, "total_steps": 30, "loss": 0.6966, "lr": 0.0, "epoch": 2.875, "percentage": 100.0, "elapsed_time": "0:15:28", "remaining_time": "0:00:00"}
31
- {"current_steps": 30, "total_steps": 30, "epoch": 2.875, "percentage": 100.0, "elapsed_time": "0:16:56", "remaining_time": "0:00:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 156, "loss": 1.3429, "lr": 6.25e-07, "epoch": 0.01910828025477707, "percentage": 0.64, "elapsed_time": "0:00:15", "remaining_time": "0:39:54"}
2
+ {"current_steps": 2, "total_steps": 156, "loss": 1.3616, "lr": 1.25e-06, "epoch": 0.03821656050955414, "percentage": 1.28, "elapsed_time": "0:00:25", "remaining_time": "0:32:09"}
3
+ {"current_steps": 3, "total_steps": 156, "loss": 1.2959, "lr": 1.8750000000000003e-06, "epoch": 0.05732484076433121, "percentage": 1.92, "elapsed_time": "0:00:38", "remaining_time": "0:32:54"}
4
+ {"current_steps": 4, "total_steps": 156, "loss": 1.3065, "lr": 2.5e-06, "epoch": 0.07643312101910828, "percentage": 2.56, "elapsed_time": "0:00:52", "remaining_time": "0:33:22"}
5
+ {"current_steps": 5, "total_steps": 156, "loss": 1.3084, "lr": 3.125e-06, "epoch": 0.09554140127388536, "percentage": 3.21, "elapsed_time": "0:01:05", "remaining_time": "0:32:44"}
6
+ {"current_steps": 6, "total_steps": 156, "loss": 1.2614, "lr": 3.7500000000000005e-06, "epoch": 0.11464968152866242, "percentage": 3.85, "elapsed_time": "0:01:14", "remaining_time": "0:30:58"}
7
+ {"current_steps": 7, "total_steps": 156, "loss": 1.177, "lr": 4.3750000000000005e-06, "epoch": 0.1337579617834395, "percentage": 4.49, "elapsed_time": "0:01:26", "remaining_time": "0:30:30"}
8
+ {"current_steps": 8, "total_steps": 156, "loss": 1.2101, "lr": 5e-06, "epoch": 0.15286624203821655, "percentage": 5.13, "elapsed_time": "0:01:35", "remaining_time": "0:29:25"}
9
+ {"current_steps": 9, "total_steps": 156, "loss": 1.1228, "lr": 5.625e-06, "epoch": 0.17197452229299362, "percentage": 5.77, "elapsed_time": "0:01:49", "remaining_time": "0:29:53"}
10
+ {"current_steps": 10, "total_steps": 156, "loss": 1.0775, "lr": 6.25e-06, "epoch": 0.1910828025477707, "percentage": 6.41, "elapsed_time": "0:02:00", "remaining_time": "0:29:24"}
11
+ {"current_steps": 11, "total_steps": 156, "loss": 1.0759, "lr": 6.875e-06, "epoch": 0.21019108280254778, "percentage": 7.05, "elapsed_time": "0:02:11", "remaining_time": "0:28:51"}
12
+ {"current_steps": 12, "total_steps": 156, "loss": 1.0192, "lr": 7.500000000000001e-06, "epoch": 0.22929936305732485, "percentage": 7.69, "elapsed_time": "0:02:24", "remaining_time": "0:28:51"}
13
+ {"current_steps": 13, "total_steps": 156, "loss": 1.0476, "lr": 8.125000000000001e-06, "epoch": 0.2484076433121019, "percentage": 8.33, "elapsed_time": "0:02:36", "remaining_time": "0:28:44"}
14
+ {"current_steps": 14, "total_steps": 156, "loss": 1.0031, "lr": 8.750000000000001e-06, "epoch": 0.267515923566879, "percentage": 8.97, "elapsed_time": "0:02:50", "remaining_time": "0:28:50"}
15
+ {"current_steps": 15, "total_steps": 156, "loss": 0.9644, "lr": 9.375000000000001e-06, "epoch": 0.28662420382165604, "percentage": 9.62, "elapsed_time": "0:03:04", "remaining_time": "0:28:50"}
16
+ {"current_steps": 16, "total_steps": 156, "loss": 0.958, "lr": 1e-05, "epoch": 0.3057324840764331, "percentage": 10.26, "elapsed_time": "0:03:18", "remaining_time": "0:29:00"}
17
+ {"current_steps": 17, "total_steps": 156, "loss": 0.9512, "lr": 9.998741174712534e-06, "epoch": 0.3248407643312102, "percentage": 10.9, "elapsed_time": "0:03:29", "remaining_time": "0:28:36"}
18
+ {"current_steps": 18, "total_steps": 156, "loss": 0.9528, "lr": 9.994965332706574e-06, "epoch": 0.34394904458598724, "percentage": 11.54, "elapsed_time": "0:03:39", "remaining_time": "0:28:00"}
19
+ {"current_steps": 19, "total_steps": 156, "loss": 0.9513, "lr": 9.98867437523228e-06, "epoch": 0.3630573248407643, "percentage": 12.18, "elapsed_time": "0:03:55", "remaining_time": "0:28:14"}
20
+ {"current_steps": 20, "total_steps": 156, "loss": 0.9269, "lr": 9.979871469976197e-06, "epoch": 0.3821656050955414, "percentage": 12.82, "elapsed_time": "0:04:05", "remaining_time": "0:27:46"}
21
+ {"current_steps": 21, "total_steps": 156, "loss": 0.9384, "lr": 9.968561049466214e-06, "epoch": 0.4012738853503185, "percentage": 13.46, "elapsed_time": "0:04:18", "remaining_time": "0:27:43"}
22
+ {"current_steps": 22, "total_steps": 156, "loss": 0.8952, "lr": 9.954748808839675e-06, "epoch": 0.42038216560509556, "percentage": 14.1, "elapsed_time": "0:04:33", "remaining_time": "0:27:47"}
23
+ {"current_steps": 23, "total_steps": 156, "loss": 0.8937, "lr": 9.938441702975689e-06, "epoch": 0.4394904458598726, "percentage": 14.74, "elapsed_time": "0:04:46", "remaining_time": "0:27:39"}
24
+ {"current_steps": 24, "total_steps": 156, "loss": 0.9142, "lr": 9.91964794299315e-06, "epoch": 0.4585987261146497, "percentage": 15.38, "elapsed_time": "0:05:00", "remaining_time": "0:27:31"}
25
+ {"current_steps": 25, "total_steps": 156, "loss": 0.8876, "lr": 9.898376992116179e-06, "epoch": 0.47770700636942676, "percentage": 16.03, "elapsed_time": "0:05:17", "remaining_time": "0:27:42"}
26
+ {"current_steps": 26, "total_steps": 156, "loss": 0.8914, "lr": 9.874639560909118e-06, "epoch": 0.4968152866242038, "percentage": 16.67, "elapsed_time": "0:05:29", "remaining_time": "0:27:26"}
27
+ {"current_steps": 27, "total_steps": 156, "loss": 0.918, "lr": 9.848447601883436e-06, "epoch": 0.5159235668789809, "percentage": 17.31, "elapsed_time": "0:05:44", "remaining_time": "0:27:23"}
28
+ {"current_steps": 28, "total_steps": 156, "loss": 0.9226, "lr": 9.819814303479268e-06, "epoch": 0.535031847133758, "percentage": 17.95, "elapsed_time": "0:05:54", "remaining_time": "0:27:01"}
29
+ {"current_steps": 29, "total_steps": 156, "loss": 0.8652, "lr": 9.788754083424654e-06, "epoch": 0.554140127388535, "percentage": 18.59, "elapsed_time": "0:06:14", "remaining_time": "0:27:18"}
30
+ {"current_steps": 30, "total_steps": 156, "loss": 0.8734, "lr": 9.755282581475769e-06, "epoch": 0.5732484076433121, "percentage": 19.23, "elapsed_time": "0:06:27", "remaining_time": "0:27:09"}
31
+ {"current_steps": 31, "total_steps": 156, "loss": 0.8965, "lr": 9.719416651541839e-06, "epoch": 0.5923566878980892, "percentage": 19.87, "elapsed_time": "0:06:41", "remaining_time": "0:26:58"}
32
+ {"current_steps": 32, "total_steps": 156, "loss": 0.896, "lr": 9.681174353198687e-06, "epoch": 0.6114649681528662, "percentage": 20.51, "elapsed_time": "0:06:56", "remaining_time": "0:26:53"}
33
+ {"current_steps": 33, "total_steps": 156, "loss": 0.8808, "lr": 9.640574942595195e-06, "epoch": 0.6305732484076433, "percentage": 21.15, "elapsed_time": "0:07:08", "remaining_time": "0:26:36"}
34
+ {"current_steps": 34, "total_steps": 156, "loss": 0.8398, "lr": 9.597638862757255e-06, "epoch": 0.6496815286624203, "percentage": 21.79, "elapsed_time": "0:07:21", "remaining_time": "0:26:24"}
35
+ {"current_steps": 35, "total_steps": 156, "loss": 0.8645, "lr": 9.552387733294081e-06, "epoch": 0.6687898089171974, "percentage": 22.44, "elapsed_time": "0:07:32", "remaining_time": "0:26:03"}
36
+ {"current_steps": 36, "total_steps": 156, "loss": 0.8813, "lr": 9.504844339512096e-06, "epoch": 0.6878980891719745, "percentage": 23.08, "elapsed_time": "0:07:44", "remaining_time": "0:25:49"}
37
+ {"current_steps": 37, "total_steps": 156, "loss": 0.8801, "lr": 9.45503262094184e-06, "epoch": 0.7070063694267515, "percentage": 23.72, "elapsed_time": "0:07:57", "remaining_time": "0:25:34"}
38
+ {"current_steps": 38, "total_steps": 156, "loss": 0.8923, "lr": 9.40297765928369e-06, "epoch": 0.7261146496815286, "percentage": 24.36, "elapsed_time": "0:08:07", "remaining_time": "0:25:14"}
39
+ {"current_steps": 39, "total_steps": 156, "loss": 0.856, "lr": 9.348705665778479e-06, "epoch": 0.7452229299363057, "percentage": 25.0, "elapsed_time": "0:08:22", "remaining_time": "0:25:06"}
40
+ {"current_steps": 40, "total_steps": 156, "loss": 0.8046, "lr": 9.292243968009332e-06, "epoch": 0.7643312101910829, "percentage": 25.64, "elapsed_time": "0:08:32", "remaining_time": "0:24:47"}
41
+ {"current_steps": 41, "total_steps": 156, "loss": 0.8774, "lr": 9.233620996141421e-06, "epoch": 0.7834394904458599, "percentage": 26.28, "elapsed_time": "0:08:42", "remaining_time": "0:24:26"}
42
+ {"current_steps": 42, "total_steps": 156, "loss": 0.8529, "lr": 9.172866268606514e-06, "epoch": 0.802547770700637, "percentage": 26.92, "elapsed_time": "0:08:54", "remaining_time": "0:24:10"}
43
+ {"current_steps": 43, "total_steps": 156, "loss": 0.8878, "lr": 9.110010377239552e-06, "epoch": 0.821656050955414, "percentage": 27.56, "elapsed_time": "0:09:03", "remaining_time": "0:23:47"}
44
+ {"current_steps": 44, "total_steps": 156, "loss": 0.8456, "lr": 9.045084971874738e-06, "epoch": 0.8407643312101911, "percentage": 28.21, "elapsed_time": "0:09:18", "remaining_time": "0:23:41"}
45
+ {"current_steps": 45, "total_steps": 156, "loss": 0.8591, "lr": 8.978122744408905e-06, "epoch": 0.8598726114649682, "percentage": 28.85, "elapsed_time": "0:09:29", "remaining_time": "0:23:23"}
46
+ {"current_steps": 46, "total_steps": 156, "loss": 0.8302, "lr": 8.90915741234015e-06, "epoch": 0.8789808917197452, "percentage": 29.49, "elapsed_time": "0:09:41", "remaining_time": "0:23:10"}
47
+ {"current_steps": 47, "total_steps": 156, "loss": 0.8265, "lr": 8.838223701790057e-06, "epoch": 0.8980891719745223, "percentage": 30.13, "elapsed_time": "0:09:55", "remaining_time": "0:23:00"}
48
+ {"current_steps": 48, "total_steps": 156, "loss": 0.8239, "lr": 8.765357330018056e-06, "epoch": 0.9171974522292994, "percentage": 30.77, "elapsed_time": "0:10:13", "remaining_time": "0:22:59"}
49
+ {"current_steps": 49, "total_steps": 156, "loss": 0.8543, "lr": 8.690594987436705e-06, "epoch": 0.9363057324840764, "percentage": 31.41, "elapsed_time": "0:10:27", "remaining_time": "0:22:51"}
50
+ {"current_steps": 50, "total_steps": 156, "loss": 0.8486, "lr": 8.613974319136959e-06, "epoch": 0.9554140127388535, "percentage": 32.05, "elapsed_time": "0:10:38", "remaining_time": "0:22:34"}
51
+ {"current_steps": 51, "total_steps": 156, "loss": 0.8717, "lr": 8.535533905932739e-06, "epoch": 0.9745222929936306, "percentage": 32.69, "elapsed_time": "0:10:57", "remaining_time": "0:22:33"}
52
+ {"current_steps": 52, "total_steps": 156, "loss": 0.851, "lr": 8.455313244934324e-06, "epoch": 0.9936305732484076, "percentage": 33.33, "elapsed_time": "0:11:09", "remaining_time": "0:22:19"}
53
+ {"current_steps": 53, "total_steps": 156, "loss": 1.2804, "lr": 8.373352729660373e-06, "epoch": 1.0127388535031847, "percentage": 33.97, "elapsed_time": "0:12:05", "remaining_time": "0:23:30"}
54
+ {"current_steps": 54, "total_steps": 156, "loss": 0.736, "lr": 8.289693629698564e-06, "epoch": 1.0318471337579618, "percentage": 34.62, "elapsed_time": "0:12:17", "remaining_time": "0:23:12"}
55
+ {"current_steps": 55, "total_steps": 156, "loss": 0.7509, "lr": 8.204378069925121e-06, "epoch": 1.0509554140127388, "percentage": 35.26, "elapsed_time": "0:12:28", "remaining_time": "0:22:55"}
56
+ {"current_steps": 56, "total_steps": 156, "loss": 0.7378, "lr": 8.117449009293668e-06, "epoch": 1.070063694267516, "percentage": 35.9, "elapsed_time": "0:12:44", "remaining_time": "0:22:46"}
57
+ {"current_steps": 57, "total_steps": 156, "loss": 0.696, "lr": 8.0289502192041e-06, "epoch": 1.089171974522293, "percentage": 36.54, "elapsed_time": "0:12:55", "remaining_time": "0:22:26"}
58
+ {"current_steps": 58, "total_steps": 156, "loss": 0.7265, "lr": 7.938926261462366e-06, "epoch": 1.10828025477707, "percentage": 37.18, "elapsed_time": "0:13:16", "remaining_time": "0:22:25"}
59
+ {"current_steps": 59, "total_steps": 156, "loss": 0.7366, "lr": 7.84742246584226e-06, "epoch": 1.127388535031847, "percentage": 37.82, "elapsed_time": "0:13:31", "remaining_time": "0:22:14"}
60
+ {"current_steps": 60, "total_steps": 156, "loss": 0.6838, "lr": 7.754484907260513e-06, "epoch": 1.1464968152866242, "percentage": 38.46, "elapsed_time": "0:13:41", "remaining_time": "0:21:54"}
61
+ {"current_steps": 61, "total_steps": 156, "loss": 0.7569, "lr": 7.660160382576683e-06, "epoch": 1.1656050955414012, "percentage": 39.1, "elapsed_time": "0:13:51", "remaining_time": "0:21:34"}
62
+ {"current_steps": 62, "total_steps": 156, "loss": 0.6864, "lr": 7.564496387029532e-06, "epoch": 1.1847133757961783, "percentage": 39.74, "elapsed_time": "0:14:05", "remaining_time": "0:21:22"}
63
+ {"current_steps": 63, "total_steps": 156, "loss": 0.7402, "lr": 7.467541090321735e-06, "epoch": 1.2038216560509554, "percentage": 40.38, "elapsed_time": "0:14:18", "remaining_time": "0:21:06"}
64
+ {"current_steps": 64, "total_steps": 156, "loss": 0.6695, "lr": 7.369343312364994e-06, "epoch": 1.2229299363057324, "percentage": 41.03, "elapsed_time": "0:14:33", "remaining_time": "0:20:56"}
65
+ {"current_steps": 65, "total_steps": 156, "loss": 0.7511, "lr": 7.269952498697734e-06, "epoch": 1.2420382165605095, "percentage": 41.67, "elapsed_time": "0:14:42", "remaining_time": "0:20:36"}
66
+ {"current_steps": 66, "total_steps": 156, "loss": 0.7272, "lr": 7.169418695587791e-06, "epoch": 1.2611464968152866, "percentage": 42.31, "elapsed_time": "0:14:51", "remaining_time": "0:20:15"}
67
+ {"current_steps": 67, "total_steps": 156, "loss": 0.743, "lr": 7.067792524832604e-06, "epoch": 1.2802547770700636, "percentage": 42.95, "elapsed_time": "0:15:05", "remaining_time": "0:20:03"}
68
+ {"current_steps": 68, "total_steps": 156, "loss": 0.689, "lr": 6.965125158269619e-06, "epoch": 1.2993630573248407, "percentage": 43.59, "elapsed_time": "0:15:16", "remaining_time": "0:19:46"}
69
+ {"current_steps": 69, "total_steps": 156, "loss": 0.7515, "lr": 6.8614682920097265e-06, "epoch": 1.3184713375796178, "percentage": 44.23, "elapsed_time": "0:15:29", "remaining_time": "0:19:31"}
70
+ {"current_steps": 70, "total_steps": 156, "loss": 0.6767, "lr": 6.7568741204067145e-06, "epoch": 1.3375796178343948, "percentage": 44.87, "elapsed_time": "0:15:51", "remaining_time": "0:19:28"}
71
+ {"current_steps": 71, "total_steps": 156, "loss": 0.7164, "lr": 6.651395309775837e-06, "epoch": 1.356687898089172, "percentage": 45.51, "elapsed_time": "0:16:03", "remaining_time": "0:19:13"}
72
+ {"current_steps": 72, "total_steps": 156, "loss": 0.6844, "lr": 6.545084971874738e-06, "epoch": 1.3757961783439492, "percentage": 46.15, "elapsed_time": "0:16:18", "remaining_time": "0:19:02"}
73
+ {"current_steps": 73, "total_steps": 156, "loss": 0.7026, "lr": 6.437996637160086e-06, "epoch": 1.394904458598726, "percentage": 46.79, "elapsed_time": "0:16:33", "remaining_time": "0:18:49"}
74
+ {"current_steps": 74, "total_steps": 156, "loss": 0.6725, "lr": 6.330184227833376e-06, "epoch": 1.4140127388535033, "percentage": 47.44, "elapsed_time": "0:16:47", "remaining_time": "0:18:36"}
75
+ {"current_steps": 75, "total_steps": 156, "loss": 0.6793, "lr": 6.2217020306894705e-06, "epoch": 1.4331210191082802, "percentage": 48.08, "elapsed_time": "0:16:58", "remaining_time": "0:18:19"}
76
+ {"current_steps": 76, "total_steps": 156, "loss": 0.71, "lr": 6.112604669781572e-06, "epoch": 1.4522292993630574, "percentage": 48.72, "elapsed_time": "0:17:28", "remaining_time": "0:18:24"}
77
+ {"current_steps": 77, "total_steps": 156, "loss": 0.7449, "lr": 6.002947078916365e-06, "epoch": 1.4713375796178343, "percentage": 49.36, "elapsed_time": "0:17:41", "remaining_time": "0:18:09"}
78
+ {"current_steps": 78, "total_steps": 156, "loss": 0.6683, "lr": 5.892784473993184e-06, "epoch": 1.4904458598726116, "percentage": 50.0, "elapsed_time": "0:17:50", "remaining_time": "0:17:50"}
79
+ {"current_steps": 79, "total_steps": 156, "loss": 0.6617, "lr": 5.782172325201155e-06, "epoch": 1.5095541401273884, "percentage": 50.64, "elapsed_time": "0:18:00", "remaining_time": "0:17:33"}
80
+ {"current_steps": 80, "total_steps": 156, "loss": 0.7013, "lr": 5.671166329088278e-06, "epoch": 1.5286624203821657, "percentage": 51.28, "elapsed_time": "0:18:15", "remaining_time": "0:17:20"}
81
+ {"current_steps": 81, "total_steps": 156, "loss": 0.6928, "lr": 5.559822380516539e-06, "epoch": 1.5477707006369426, "percentage": 51.92, "elapsed_time": "0:18:23", "remaining_time": "0:17:01"}
82
+ {"current_steps": 82, "total_steps": 156, "loss": 0.7225, "lr": 5.448196544517168e-06, "epoch": 1.5668789808917198, "percentage": 52.56, "elapsed_time": "0:18:34", "remaining_time": "0:16:45"}
83
+ {"current_steps": 83, "total_steps": 156, "loss": 0.7372, "lr": 5.336345028060199e-06, "epoch": 1.5859872611464967, "percentage": 53.21, "elapsed_time": "0:18:48", "remaining_time": "0:16:32"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34c8271c7284c03fd965b45a9eb0d8d62b4387cfe5852de4159699fd6dd1ded8
3
  size 7352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b109afc1ae5660cff5a77a830db7e763d576e08c4ee70fa0f1470ea79d0e8f
3
  size 7352