Training in progress, step 100
Browse files- model-00001-of-00014.safetensors +1 -1
- model-00002-of-00014.safetensors +1 -1
- model-00003-of-00014.safetensors +1 -1
- model-00004-of-00014.safetensors +1 -1
- model-00005-of-00014.safetensors +1 -1
- model-00006-of-00014.safetensors +1 -1
- model-00007-of-00014.safetensors +1 -1
- model-00008-of-00014.safetensors +1 -1
- model-00009-of-00014.safetensors +1 -1
- model-00010-of-00014.safetensors +1 -1
- model-00011-of-00014.safetensors +1 -1
- model-00012-of-00014.safetensors +1 -1
- model-00013-of-00014.safetensors +1 -1
- model-00014-of-00014.safetensors +1 -1
- trainer_log.jsonl +101 -86
- training_args.bin +2 -2
model-00001-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4891730992
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:354b3f16c3cea2e01e79b7f1c13c08c97a733a7e86463f609c96a3edd3c21345
|
3 |
size 4891730992
|
model-00002-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea4477801af24da7e9e909249e73ca2d531c4d58e78d7f2c20267670ed0fe545
|
3 |
size 4876059352
|
model-00003-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059384
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:276f2ab067b1d54136833ee6d533afbaeacf4dc0c4f2b993543d9dd738b6f98e
|
3 |
size 4876059384
|
model-00004-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c87cdb7a1dd78e6b1dbab4c4f5b14a14be6c0c63dfad805c5761c1db7414472d
|
3 |
size 4876059416
|
model-00005-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb41af132ae479ad9dd272ccf1c4fc5d466bd6b28f5a49f5315096d754ce9f2a
|
3 |
size 4876059416
|
model-00006-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c738694f366d8a76a75571d27f16b733c4a1db7ac0ca67159a44998e1928a6da
|
3 |
size 4876059416
|
model-00007-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8864635523761b47c45077bd76bedd40e314b18306beff6a8657eac1bfd33e7
|
3 |
size 4876059416
|
model-00008-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fed8f217eaabc1ddace4a647451fbae79ecad0631c8cab6e498154f77eae4edc
|
3 |
size 4876059416
|
model-00009-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58393825247ee5e96393b42cd1b3b70325784a313d73e00125052972587c5ce1
|
3 |
size 4876059416
|
model-00010-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15d221b39656041c050816b8a5c3a0cb0294f4f8ad87f6f83ea35cad7bb0a7c4
|
3 |
size 4876059416
|
model-00011-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cea27efc63cda0892c910cf08648c2dd460a65417a23f7ada95ad1582a23258
|
3 |
size 4876059416
|
model-00012-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6d683ea5fc1d7ebcdd44304c029c3f71ff6e672901a2b37ee62f0db181fd54a
|
3 |
size 4876059416
|
model-00013-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e2ff0d8f2b9e367dc6d86ca6b087e8b84f5857885bddc5895d8232738a384ae
|
3 |
size 4876059416
|
model-00014-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2123397800
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e73301b2aaba460a22522ce7aa9e6a71bdf020e8b619dddd2e8e7ae30af6a297
|
3 |
size 2123397800
|
trainer_log.jsonl
CHANGED
@@ -1,86 +1,101 @@
|
|
1 |
-
{"current_steps":
|
2 |
-
{"current_steps":
|
3 |
-
{"current_steps":
|
4 |
-
{"current_steps":
|
5 |
-
{"current_steps":
|
6 |
-
{"current_steps":
|
7 |
-
{"current_steps":
|
8 |
-
{"current_steps":
|
9 |
-
{"current_steps":
|
10 |
-
{"current_steps":
|
11 |
-
{"current_steps":
|
12 |
-
{"current_steps":
|
13 |
-
{"current_steps":
|
14 |
-
{"current_steps":
|
15 |
-
{"current_steps":
|
16 |
-
{"current_steps":
|
17 |
-
{"current_steps":
|
18 |
-
{"current_steps":
|
19 |
-
{"current_steps":
|
20 |
-
{"current_steps":
|
21 |
-
{"current_steps":
|
22 |
-
{"current_steps":
|
23 |
-
{"current_steps":
|
24 |
-
{"current_steps":
|
25 |
-
{"current_steps":
|
26 |
-
{"current_steps":
|
27 |
-
{"current_steps":
|
28 |
-
{"current_steps":
|
29 |
-
{"current_steps":
|
30 |
-
{"current_steps":
|
31 |
-
{"current_steps":
|
32 |
-
{"current_steps":
|
33 |
-
{"current_steps":
|
34 |
-
{"current_steps":
|
35 |
-
{"current_steps":
|
36 |
-
{"current_steps":
|
37 |
-
{"current_steps":
|
38 |
-
{"current_steps":
|
39 |
-
{"current_steps":
|
40 |
-
{"current_steps":
|
41 |
-
{"current_steps":
|
42 |
-
{"current_steps":
|
43 |
-
{"current_steps":
|
44 |
-
{"current_steps":
|
45 |
-
{"current_steps":
|
46 |
-
{"current_steps":
|
47 |
-
{"current_steps":
|
48 |
-
{"current_steps":
|
49 |
-
{"current_steps":
|
50 |
-
{"current_steps":
|
51 |
-
{"current_steps":
|
52 |
-
{"current_steps":
|
53 |
-
{"current_steps":
|
54 |
-
{"current_steps":
|
55 |
-
{"current_steps":
|
56 |
-
{"current_steps":
|
57 |
-
{"current_steps":
|
58 |
-
{"current_steps":
|
59 |
-
{"current_steps":
|
60 |
-
{"current_steps":
|
61 |
-
{"current_steps":
|
62 |
-
{"current_steps":
|
63 |
-
{"current_steps":
|
64 |
-
{"current_steps":
|
65 |
-
{"current_steps":
|
66 |
-
{"current_steps":
|
67 |
-
{"current_steps":
|
68 |
-
{"current_steps":
|
69 |
-
{"current_steps":
|
70 |
-
{"current_steps":
|
71 |
-
{"current_steps":
|
72 |
-
{"current_steps":
|
73 |
-
{"current_steps":
|
74 |
-
{"current_steps":
|
75 |
-
{"current_steps":
|
76 |
-
{"current_steps":
|
77 |
-
{"current_steps":
|
78 |
-
{"current_steps":
|
79 |
-
{"current_steps":
|
80 |
-
{"current_steps":
|
81 |
-
{"current_steps":
|
82 |
-
{"current_steps":
|
83 |
-
{"current_steps":
|
84 |
-
{"current_steps":
|
85 |
-
{"current_steps":
|
86 |
-
{"current_steps":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 118, "loss": 1.6351, "lr": 4.9999999999999996e-06, "epoch": 0.008434370057986295, "percentage": 0.85, "elapsed_time": "0:07:05", "remaining_time": "13:49:24"}
|
2 |
+
{"current_steps": 2, "total_steps": 118, "loss": 1.6405, "lr": 9.999999999999999e-06, "epoch": 0.01686874011597259, "percentage": 1.69, "elapsed_time": "0:13:53", "remaining_time": "13:26:02"}
|
3 |
+
{"current_steps": 3, "total_steps": 118, "loss": 1.6264, "lr": 1.5e-05, "epoch": 0.025303110173958882, "percentage": 2.54, "elapsed_time": "0:20:29", "remaining_time": "13:05:30"}
|
4 |
+
{"current_steps": 4, "total_steps": 118, "loss": 1.6233, "lr": 1.9999999999999998e-05, "epoch": 0.03373748023194518, "percentage": 3.39, "elapsed_time": "0:27:06", "remaining_time": "12:52:24"}
|
5 |
+
{"current_steps": 5, "total_steps": 118, "loss": 1.62, "lr": 2.5e-05, "epoch": 0.04217185028993147, "percentage": 4.24, "elapsed_time": "0:33:45", "remaining_time": "12:43:04"}
|
6 |
+
{"current_steps": 6, "total_steps": 118, "loss": 1.6134, "lr": 3e-05, "epoch": 0.050606220347917764, "percentage": 5.08, "elapsed_time": "0:40:22", "remaining_time": "12:33:35"}
|
7 |
+
{"current_steps": 7, "total_steps": 118, "loss": 1.6169, "lr": 3.5000000000000004e-05, "epoch": 0.05904059040590406, "percentage": 5.93, "elapsed_time": "0:46:57", "remaining_time": "12:24:33"}
|
8 |
+
{"current_steps": 8, "total_steps": 118, "loss": 1.6143, "lr": 3.9999999999999996e-05, "epoch": 0.06747496046389036, "percentage": 6.78, "elapsed_time": "0:53:36", "remaining_time": "12:17:04"}
|
9 |
+
{"current_steps": 9, "total_steps": 118, "loss": 1.6104, "lr": 4.5e-05, "epoch": 0.07590933052187665, "percentage": 7.63, "elapsed_time": "1:00:09", "remaining_time": "12:08:40"}
|
10 |
+
{"current_steps": 10, "total_steps": 118, "loss": 1.6028, "lr": 5e-05, "epoch": 0.08434370057986294, "percentage": 8.47, "elapsed_time": "1:06:42", "remaining_time": "12:00:21"}
|
11 |
+
{"current_steps": 11, "total_steps": 118, "loss": 1.5949, "lr": 5.5e-05, "epoch": 0.09277807063784924, "percentage": 9.32, "elapsed_time": "1:13:18", "remaining_time": "11:53:03"}
|
12 |
+
{"current_steps": 12, "total_steps": 118, "loss": 1.5966, "lr": 6e-05, "epoch": 0.10121244069583553, "percentage": 10.17, "elapsed_time": "1:19:56", "remaining_time": "11:46:06"}
|
13 |
+
{"current_steps": 13, "total_steps": 118, "loss": 1.601, "lr": 5.998682509526384e-05, "epoch": 0.10964681075382182, "percentage": 11.02, "elapsed_time": "1:26:28", "remaining_time": "11:38:28"}
|
14 |
+
{"current_steps": 14, "total_steps": 118, "loss": 1.6015, "lr": 5.994731195292965e-05, "epoch": 0.11808118081180811, "percentage": 11.86, "elapsed_time": "1:33:06", "remaining_time": "11:31:37"}
|
15 |
+
{"current_steps": 15, "total_steps": 118, "loss": 1.5992, "lr": 5.988149527845651e-05, "epoch": 0.1265155508697944, "percentage": 12.71, "elapsed_time": "1:39:44", "remaining_time": "11:24:55"}
|
16 |
+
{"current_steps": 16, "total_steps": 118, "loss": 1.5932, "lr": 5.978943288040551e-05, "epoch": 0.13494992092778071, "percentage": 13.56, "elapsed_time": "1:46:24", "remaining_time": "11:18:21"}
|
17 |
+
{"current_steps": 17, "total_steps": 118, "loss": 1.5873, "lr": 5.967120561966492e-05, "epoch": 0.143384290985767, "percentage": 14.41, "elapsed_time": "1:53:00", "remaining_time": "11:11:22"}
|
18 |
+
{"current_steps": 18, "total_steps": 118, "loss": 1.5845, "lr": 5.952691733842791e-05, "epoch": 0.1518186610437533, "percentage": 15.25, "elapsed_time": "1:59:32", "remaining_time": "11:04:06"}
|
19 |
+
{"current_steps": 19, "total_steps": 118, "loss": 1.5942, "lr": 5.935669476898512e-05, "epoch": 0.16025303110173958, "percentage": 16.1, "elapsed_time": "2:06:10", "remaining_time": "10:57:26"}
|
20 |
+
{"current_steps": 20, "total_steps": 118, "loss": 1.5976, "lr": 5.9160687422412324e-05, "epoch": 0.16868740115972589, "percentage": 16.95, "elapsed_time": "2:12:48", "remaining_time": "10:50:45"}
|
21 |
+
{"current_steps": 21, "total_steps": 118, "loss": 1.5862, "lr": 5.893906745725076e-05, "epoch": 0.17712177121771217, "percentage": 17.8, "elapsed_time": "2:19:18", "remaining_time": "10:43:30"}
|
22 |
+
{"current_steps": 22, "total_steps": 118, "loss": 1.5877, "lr": 5.8692029528295675e-05, "epoch": 0.18555614127569847, "percentage": 18.64, "elapsed_time": "2:25:55", "remaining_time": "10:36:45"}
|
23 |
+
{"current_steps": 23, "total_steps": 118, "loss": 1.584, "lr": 5.841979061562574e-05, "epoch": 0.19399051133368478, "percentage": 19.49, "elapsed_time": "2:32:34", "remaining_time": "10:30:11"}
|
24 |
+
{"current_steps": 24, "total_steps": 118, "loss": 1.5841, "lr": 5.8122589834023634e-05, "epoch": 0.20242488139167106, "percentage": 20.34, "elapsed_time": "2:39:06", "remaining_time": "10:23:09"}
|
25 |
+
{"current_steps": 25, "total_steps": 118, "loss": 1.5845, "lr": 5.7800688222955e-05, "epoch": 0.21085925144965736, "percentage": 21.19, "elapsed_time": "2:45:44", "remaining_time": "10:16:32"}
|
26 |
+
{"current_steps": 26, "total_steps": 118, "loss": 1.594, "lr": 5.745436851729055e-05, "epoch": 0.21929362150764364, "percentage": 22.03, "elapsed_time": "2:52:19", "remaining_time": "10:09:45"}
|
27 |
+
{"current_steps": 27, "total_steps": 118, "loss": 1.5903, "lr": 5.708393489897231e-05, "epoch": 0.22772799156562995, "percentage": 22.88, "elapsed_time": "2:58:50", "remaining_time": "10:02:47"}
|
28 |
+
{"current_steps": 28, "total_steps": 118, "loss": 1.5804, "lr": 5.668971272984242e-05, "epoch": 0.23616236162361623, "percentage": 23.73, "elapsed_time": "3:05:28", "remaining_time": "9:56:09"}
|
29 |
+
{"current_steps": 29, "total_steps": 118, "loss": 1.5798, "lr": 5.6272048265869104e-05, "epoch": 0.24459673168160254, "percentage": 24.58, "elapsed_time": "3:12:02", "remaining_time": "9:49:21"}
|
30 |
+
{"current_steps": 30, "total_steps": 118, "loss": 1.5848, "lr": 5.583130835302066e-05, "epoch": 0.2530311017395888, "percentage": 25.42, "elapsed_time": "3:18:35", "remaining_time": "9:42:30"}
|
31 |
+
{"current_steps": 31, "total_steps": 118, "loss": 1.5751, "lr": 5.536788010505478e-05, "epoch": 0.2614654717975751, "percentage": 26.27, "elapsed_time": "3:25:09", "remaining_time": "9:35:46"}
|
32 |
+
{"current_steps": 32, "total_steps": 118, "loss": 1.5799, "lr": 5.4882170563506055e-05, "epoch": 0.26989984185556143, "percentage": 27.12, "elapsed_time": "3:31:41", "remaining_time": "9:28:56"}
|
33 |
+
{"current_steps": 33, "total_steps": 118, "loss": 1.5758, "lr": 5.437460634017044e-05, "epoch": 0.2783342119135477, "percentage": 27.97, "elapsed_time": "3:38:13", "remaining_time": "9:22:06"}
|
34 |
+
{"current_steps": 34, "total_steps": 118, "loss": 1.5774, "lr": 5.3845633242400604e-05, "epoch": 0.286768581971534, "percentage": 28.81, "elapsed_time": "3:44:47", "remaining_time": "9:15:20"}
|
35 |
+
{"current_steps": 35, "total_steps": 118, "loss": 1.5748, "lr": 5.329571588154127e-05, "epoch": 0.2952029520295203, "percentage": 29.66, "elapsed_time": "3:51:18", "remaining_time": "9:08:32"}
|
36 |
+
{"current_steps": 36, "total_steps": 118, "loss": 1.5772, "lr": 5.2725337264848605e-05, "epoch": 0.3036373220875066, "percentage": 30.51, "elapsed_time": "3:57:52", "remaining_time": "9:01:50"}
|
37 |
+
{"current_steps": 37, "total_steps": 118, "loss": 1.5697, "lr": 5.213499837125182e-05, "epoch": 0.3120716921454929, "percentage": 31.36, "elapsed_time": "4:04:23", "remaining_time": "8:55:01"}
|
38 |
+
{"current_steps": 38, "total_steps": 118, "loss": 1.5761, "lr": 5.152521771132993e-05, "epoch": 0.32050606220347916, "percentage": 32.2, "elapsed_time": "4:10:56", "remaining_time": "8:48:17"}
|
39 |
+
{"current_steps": 39, "total_steps": 118, "loss": 1.5793, "lr": 5.0896530871889914e-05, "epoch": 0.32894043226146547, "percentage": 33.05, "elapsed_time": "4:17:25", "remaining_time": "8:41:27"}
|
40 |
+
{"current_steps": 40, "total_steps": 118, "loss": 1.5658, "lr": 5.024949004554632e-05, "epoch": 0.33737480231945177, "percentage": 33.9, "elapsed_time": "4:23:57", "remaining_time": "8:34:43"}
|
41 |
+
{"current_steps": 41, "total_steps": 118, "loss": 1.5762, "lr": 4.958466354571565e-05, "epoch": 0.3458091723774381, "percentage": 34.75, "elapsed_time": "4:30:32", "remaining_time": "8:28:05"}
|
42 |
+
{"current_steps": 42, "total_steps": 118, "loss": 1.5703, "lr": 4.890263530745134e-05, "epoch": 0.35424354243542433, "percentage": 35.59, "elapsed_time": "4:37:05", "remaining_time": "8:21:24"}
|
43 |
+
{"current_steps": 43, "total_steps": 118, "loss": 1.577, "lr": 4.8204004374557806e-05, "epoch": 0.36267791249341064, "percentage": 36.44, "elapsed_time": "4:43:37", "remaining_time": "8:14:41"}
|
44 |
+
{"current_steps": 44, "total_steps": 118, "loss": 1.5726, "lr": 4.748938437343416e-05, "epoch": 0.37111228255139694, "percentage": 37.29, "elapsed_time": "4:50:07", "remaining_time": "8:07:55"}
|
45 |
+
{"current_steps": 45, "total_steps": 118, "loss": 1.579, "lr": 4.675940297410958e-05, "epoch": 0.37954665260938325, "percentage": 38.14, "elapsed_time": "4:56:44", "remaining_time": "8:01:23"}
|
46 |
+
{"current_steps": 46, "total_steps": 118, "loss": 1.5611, "lr": 4.601470133894373e-05, "epoch": 0.38798102266736956, "percentage": 38.98, "elapsed_time": "5:03:16", "remaining_time": "7:54:42"}
|
47 |
+
{"current_steps": 47, "total_steps": 118, "loss": 1.5725, "lr": 4.525593355947662e-05, "epoch": 0.3964153927253558, "percentage": 39.83, "elapsed_time": "5:09:51", "remaining_time": "7:48:04"}
|
48 |
+
{"current_steps": 48, "total_steps": 118, "loss": 1.5679, "lr": 4.448376608192235e-05, "epoch": 0.4048497627833421, "percentage": 40.68, "elapsed_time": "5:16:22", "remaining_time": "7:41:22"}
|
49 |
+
{"current_steps": 49, "total_steps": 118, "loss": 1.5712, "lr": 4.3698877121811395e-05, "epoch": 0.4132841328413284, "percentage": 41.53, "elapsed_time": "5:22:53", "remaining_time": "7:34:41"}
|
50 |
+
{"current_steps": 50, "total_steps": 118, "loss": 1.5683, "lr": 4.290195606829562e-05, "epoch": 0.42171850289931473, "percentage": 42.37, "elapsed_time": "5:29:23", "remaining_time": "7:27:58"}
|
51 |
+
{"current_steps": 51, "total_steps": 118, "loss": 1.5784, "lr": 4.2093702878639174e-05, "epoch": 0.430152872957301, "percentage": 43.22, "elapsed_time": "5:35:55", "remaining_time": "7:21:18"}
|
52 |
+
{"current_steps": 52, "total_steps": 118, "loss": 1.5648, "lr": 4.127482746342714e-05, "epoch": 0.4385872430152873, "percentage": 44.07, "elapsed_time": "5:42:25", "remaining_time": "7:14:36"}
|
53 |
+
{"current_steps": 53, "total_steps": 118, "loss": 1.5671, "lr": 4.044604906303197e-05, "epoch": 0.4470216130732736, "percentage": 44.92, "elapsed_time": "5:48:55", "remaining_time": "7:07:55"}
|
54 |
+
{"current_steps": 54, "total_steps": 118, "loss": 1.5759, "lr": 3.960809561588513e-05, "epoch": 0.4554559831312599, "percentage": 45.76, "elapsed_time": "5:55:24", "remaining_time": "7:01:13"}
|
55 |
+
{"current_steps": 55, "total_steps": 118, "loss": 1.5672, "lr": 3.876170311910928e-05, "epoch": 0.46389035318924615, "percentage": 46.61, "elapsed_time": "6:01:56", "remaining_time": "6:54:35"}
|
56 |
+
{"current_steps": 56, "total_steps": 118, "loss": 1.5744, "lr": 3.790761498207203e-05, "epoch": 0.47232472324723246, "percentage": 47.46, "elapsed_time": "6:08:32", "remaining_time": "6:48:02"}
|
57 |
+
{"current_steps": 57, "total_steps": 118, "loss": 1.5688, "lr": 3.704658137342952e-05, "epoch": 0.48075909330521877, "percentage": 48.31, "elapsed_time": "6:15:09", "remaining_time": "6:41:29"}
|
58 |
+
{"current_steps": 58, "total_steps": 118, "loss": 1.5742, "lr": 3.617935856223295e-05, "epoch": 0.48919346336320507, "percentage": 49.15, "elapsed_time": "6:21:45", "remaining_time": "6:34:55"}
|
59 |
+
{"current_steps": 59, "total_steps": 118, "loss": 1.5615, "lr": 3.5306708253677186e-05, "epoch": 0.4976278334211914, "percentage": 50.0, "elapsed_time": "6:28:18", "remaining_time": "6:28:18"}
|
60 |
+
{"current_steps": 60, "total_steps": 118, "loss": 1.5456, "lr": 3.442939692007444e-05, "epoch": 0.5060622034791776, "percentage": 50.85, "elapsed_time": "6:34:51", "remaining_time": "6:21:42"}
|
61 |
+
{"current_steps": 61, "total_steps": 118, "loss": 1.5579, "lr": 3.354819512764097e-05, "epoch": 0.5144965735371639, "percentage": 51.69, "elapsed_time": "6:41:28", "remaining_time": "6:15:08"}
|
62 |
+
{"current_steps": 62, "total_steps": 118, "loss": 1.5606, "lr": 3.2663876859688045e-05, "epoch": 0.5229309435951502, "percentage": 52.54, "elapsed_time": "6:48:08", "remaining_time": "6:08:38"}
|
63 |
+
{"current_steps": 63, "total_steps": 118, "loss": 1.5631, "lr": 3.177721883681143e-05, "epoch": 0.5313653136531366, "percentage": 53.39, "elapsed_time": "6:54:40", "remaining_time": "6:02:01"}
|
64 |
+
{"current_steps": 64, "total_steps": 118, "loss": 1.5606, "lr": 3.0888999834676796e-05, "epoch": 0.5397996837111229, "percentage": 54.24, "elapsed_time": "7:01:14", "remaining_time": "5:55:25"}
|
65 |
+
{"current_steps": 65, "total_steps": 118, "loss": 1.5638, "lr": 3e-05, "epoch": 0.5482340537691092, "percentage": 55.08, "elapsed_time": "7:07:45", "remaining_time": "5:48:47"}
|
66 |
+
{"current_steps": 66, "total_steps": 118, "loss": 1.5656, "lr": 2.9111000165323206e-05, "epoch": 0.5566684238270954, "percentage": 55.93, "elapsed_time": "7:14:19", "remaining_time": "5:42:11"}
|
67 |
+
{"current_steps": 67, "total_steps": 118, "loss": 1.5595, "lr": 2.8222781163188573e-05, "epoch": 0.5651027938850817, "percentage": 56.78, "elapsed_time": "7:20:52", "remaining_time": "5:35:35"}
|
68 |
+
{"current_steps": 68, "total_steps": 118, "loss": 1.5627, "lr": 2.7336123140311957e-05, "epoch": 0.573537163943068, "percentage": 57.63, "elapsed_time": "7:27:27", "remaining_time": "5:29:00"}
|
69 |
+
{"current_steps": 69, "total_steps": 118, "loss": 1.5707, "lr": 2.645180487235903e-05, "epoch": 0.5819715340010543, "percentage": 58.47, "elapsed_time": "7:33:59", "remaining_time": "5:22:23"}
|
70 |
+
{"current_steps": 70, "total_steps": 118, "loss": 1.5635, "lr": 2.557060307992557e-05, "epoch": 0.5904059040590406, "percentage": 59.32, "elapsed_time": "7:40:30", "remaining_time": "5:15:46"}
|
71 |
+
{"current_steps": 71, "total_steps": 118, "loss": 1.5635, "lr": 2.469329174632282e-05, "epoch": 0.5988402741170269, "percentage": 60.17, "elapsed_time": "7:47:03", "remaining_time": "5:09:10"}
|
72 |
+
{"current_steps": 72, "total_steps": 118, "loss": 1.5607, "lr": 2.3820641437767053e-05, "epoch": 0.6072746441750132, "percentage": 61.02, "elapsed_time": "7:53:37", "remaining_time": "5:02:35"}
|
73 |
+
{"current_steps": 73, "total_steps": 118, "loss": 1.5524, "lr": 2.2953418626570494e-05, "epoch": 0.6157090142329995, "percentage": 61.86, "elapsed_time": "8:00:11", "remaining_time": "4:56:00"}
|
74 |
+
{"current_steps": 74, "total_steps": 118, "loss": 1.555, "lr": 2.209238501792798e-05, "epoch": 0.6241433842909858, "percentage": 62.71, "elapsed_time": "8:06:50", "remaining_time": "4:49:28"}
|
75 |
+
{"current_steps": 75, "total_steps": 118, "loss": 1.5514, "lr": 2.123829688089073e-05, "epoch": 0.632577754348972, "percentage": 63.56, "elapsed_time": "8:13:20", "remaining_time": "4:42:50"}
|
76 |
+
{"current_steps": 76, "total_steps": 118, "loss": 1.5614, "lr": 2.0391904384114877e-05, "epoch": 0.6410121244069583, "percentage": 64.41, "elapsed_time": "8:19:54", "remaining_time": "4:36:16"}
|
77 |
+
{"current_steps": 77, "total_steps": 118, "loss": 1.541, "lr": 1.9553950936968042e-05, "epoch": 0.6494464944649446, "percentage": 65.25, "elapsed_time": "8:26:28", "remaining_time": "4:29:41"}
|
78 |
+
{"current_steps": 78, "total_steps": 118, "loss": 1.556, "lr": 1.8725172536572863e-05, "epoch": 0.6578808645229309, "percentage": 66.1, "elapsed_time": "8:33:08", "remaining_time": "4:23:09"}
|
79 |
+
{"current_steps": 79, "total_steps": 118, "loss": 1.5638, "lr": 1.7906297121360838e-05, "epoch": 0.6663152345809172, "percentage": 66.95, "elapsed_time": "8:39:42", "remaining_time": "4:16:33"}
|
80 |
+
{"current_steps": 80, "total_steps": 118, "loss": 1.5508, "lr": 1.7098043931704396e-05, "epoch": 0.6747496046389035, "percentage": 67.8, "elapsed_time": "8:46:12", "remaining_time": "4:09:57"}
|
81 |
+
{"current_steps": 81, "total_steps": 118, "loss": 1.5567, "lr": 1.6301122878188607e-05, "epoch": 0.6831839746968899, "percentage": 68.64, "elapsed_time": "8:52:44", "remaining_time": "4:03:20"}
|
82 |
+
{"current_steps": 82, "total_steps": 118, "loss": 1.5484, "lr": 1.551623391807766e-05, "epoch": 0.6916183447548762, "percentage": 69.49, "elapsed_time": "8:59:19", "remaining_time": "3:56:46"}
|
83 |
+
{"current_steps": 83, "total_steps": 118, "loss": 1.5591, "lr": 1.4744066440523391e-05, "epoch": 0.7000527148128625, "percentage": 70.34, "elapsed_time": "9:05:52", "remaining_time": "3:50:11"}
|
84 |
+
{"current_steps": 84, "total_steps": 118, "loss": 1.569, "lr": 1.3985298661056292e-05, "epoch": 0.7084870848708487, "percentage": 71.19, "elapsed_time": "9:12:23", "remaining_time": "3:43:35"}
|
85 |
+
{"current_steps": 85, "total_steps": 118, "loss": 1.5631, "lr": 1.324059702589043e-05, "epoch": 0.716921454928835, "percentage": 72.03, "elapsed_time": "9:19:02", "remaining_time": "3:37:02"}
|
86 |
+
{"current_steps": 86, "total_steps": 118, "loss": 1.5561, "lr": 1.2510615626565844e-05, "epoch": 0.7253558249868213, "percentage": 72.88, "elapsed_time": "9:25:38", "remaining_time": "3:30:28"}
|
87 |
+
{"current_steps": 87, "total_steps": 118, "loss": 1.5471, "lr": 1.1795995625442208e-05, "epoch": 0.7337901950448076, "percentage": 73.73, "elapsed_time": "9:32:16", "remaining_time": "3:23:54"}
|
88 |
+
{"current_steps": 88, "total_steps": 118, "loss": 1.5583, "lr": 1.109736469254867e-05, "epoch": 0.7422245651027939, "percentage": 74.58, "elapsed_time": "9:38:49", "remaining_time": "3:17:19"}
|
89 |
+
{"current_steps": 89, "total_steps": 118, "loss": 1.5531, "lr": 1.0415336454284356e-05, "epoch": 0.7506589351607802, "percentage": 75.42, "elapsed_time": "9:45:21", "remaining_time": "3:10:44"}
|
90 |
+
{"current_steps": 90, "total_steps": 118, "loss": 1.5559, "lr": 9.75050995445369e-06, "epoch": 0.7590933052187665, "percentage": 76.27, "elapsed_time": "9:51:52", "remaining_time": "3:04:08"}
|
91 |
+
{"current_steps": 91, "total_steps": 118, "loss": 1.5527, "lr": 9.103469128110098e-06, "epoch": 0.7675276752767528, "percentage": 77.12, "elapsed_time": "9:58:26", "remaining_time": "2:57:33"}
|
92 |
+
{"current_steps": 92, "total_steps": 118, "loss": 1.5514, "lr": 8.474782288670058e-06, "epoch": 0.7759620453347391, "percentage": 77.97, "elapsed_time": "10:04:58", "remaining_time": "2:50:58"}
|
93 |
+
{"current_steps": 93, "total_steps": 118, "loss": 1.5536, "lr": 7.86500162874818e-06, "epoch": 0.7843964153927253, "percentage": 78.81, "elapsed_time": "10:11:30", "remaining_time": "2:44:23"}
|
94 |
+
{"current_steps": 94, "total_steps": 118, "loss": 1.5541, "lr": 7.274662735151396e-06, "epoch": 0.7928307854507116, "percentage": 79.66, "elapsed_time": "10:18:03", "remaining_time": "2:37:48"}
|
95 |
+
{"current_steps": 95, "total_steps": 118, "loss": 1.5512, "lr": 6.704284118458731e-06, "epoch": 0.8012651555086979, "percentage": 80.51, "elapsed_time": "10:24:34", "remaining_time": "2:31:12"}
|
96 |
+
{"current_steps": 96, "total_steps": 118, "loss": 1.5492, "lr": 6.154366757599399e-06, "epoch": 0.8096995255666842, "percentage": 81.36, "elapsed_time": "10:31:03", "remaining_time": "2:24:37"}
|
97 |
+
{"current_steps": 97, "total_steps": 118, "loss": 1.5472, "lr": 5.625393659829561e-06, "epoch": 0.8181338956246705, "percentage": 82.2, "elapsed_time": "10:37:33", "remaining_time": "2:18:01"}
|
98 |
+
{"current_steps": 98, "total_steps": 118, "loss": 1.551, "lr": 5.117829436493947e-06, "epoch": 0.8265682656826568, "percentage": 83.05, "elapsed_time": "10:44:05", "remaining_time": "2:11:26"}
|
99 |
+
{"current_steps": 99, "total_steps": 118, "loss": 1.5599, "lr": 4.632119894945215e-06, "epoch": 0.8350026357406432, "percentage": 83.9, "elapsed_time": "10:50:40", "remaining_time": "2:04:52"}
|
100 |
+
{"current_steps": 100, "total_steps": 118, "loss": 1.5552, "lr": 4.1686916469793335e-06, "epoch": 0.8434370057986295, "percentage": 84.75, "elapsed_time": "10:57:11", "remaining_time": "1:58:17"}
|
101 |
+
{"current_steps": 101, "total_steps": 118, "loss": 1.5645, "lr": 3.7279517341308977e-06, "epoch": 0.8518713758566157, "percentage": 85.59, "elapsed_time": "11:10:39", "remaining_time": "1:52:52"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6366e84faf47da8ea0af81088ba6e57f9a634d47c9518713d6b0a7bd95f63459
|
3 |
+
size 7672
|