Upload folder using huggingface_hub
Browse files- control_789/epoch1/metadata.json +6 -0
- control_789/epoch1/metrics.json +1102 -0
- control_789/epoch1/model.pt +3 -0
- control_789/epoch1/optimizer.pt +3 -0
- control_789/epoch1/scheduler.pt +3 -0
- control_789/epoch1/tokenizer/merges.txt +0 -0
- control_789/epoch1/tokenizer/special_tokens_map.json +6 -0
- control_789/epoch1/tokenizer/tokenizer.json +0 -0
- control_789/epoch1/tokenizer/tokenizer_config.json +21 -0
- control_789/epoch1/tokenizer/vocab.json +0 -0
control_789/epoch1/metadata.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch_num": 1,
|
| 3 |
+
"global_batch_num": 268,
|
| 4 |
+
"device": "cuda",
|
| 5 |
+
"dtype": "bfloat16"
|
| 6 |
+
}
|
control_789/epoch1/metrics.json
ADDED
|
@@ -0,0 +1,1102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"training": {
|
| 3 |
+
"effective_batch_nums": [
|
| 4 |
+
1,
|
| 5 |
+
2,
|
| 6 |
+
3,
|
| 7 |
+
4,
|
| 8 |
+
5,
|
| 9 |
+
6,
|
| 10 |
+
7,
|
| 11 |
+
8,
|
| 12 |
+
9,
|
| 13 |
+
10,
|
| 14 |
+
11,
|
| 15 |
+
12,
|
| 16 |
+
13,
|
| 17 |
+
14,
|
| 18 |
+
15,
|
| 19 |
+
16,
|
| 20 |
+
17,
|
| 21 |
+
18,
|
| 22 |
+
19,
|
| 23 |
+
20,
|
| 24 |
+
21,
|
| 25 |
+
22,
|
| 26 |
+
23,
|
| 27 |
+
24,
|
| 28 |
+
25,
|
| 29 |
+
26,
|
| 30 |
+
27,
|
| 31 |
+
28,
|
| 32 |
+
29,
|
| 33 |
+
30,
|
| 34 |
+
31,
|
| 35 |
+
32,
|
| 36 |
+
33,
|
| 37 |
+
34,
|
| 38 |
+
35,
|
| 39 |
+
36,
|
| 40 |
+
37,
|
| 41 |
+
38,
|
| 42 |
+
39,
|
| 43 |
+
40,
|
| 44 |
+
41,
|
| 45 |
+
42,
|
| 46 |
+
43,
|
| 47 |
+
44,
|
| 48 |
+
45,
|
| 49 |
+
46,
|
| 50 |
+
47,
|
| 51 |
+
48,
|
| 52 |
+
49,
|
| 53 |
+
50,
|
| 54 |
+
51,
|
| 55 |
+
52,
|
| 56 |
+
53,
|
| 57 |
+
54,
|
| 58 |
+
55,
|
| 59 |
+
56,
|
| 60 |
+
57,
|
| 61 |
+
58,
|
| 62 |
+
59,
|
| 63 |
+
60,
|
| 64 |
+
61,
|
| 65 |
+
62,
|
| 66 |
+
63,
|
| 67 |
+
64,
|
| 68 |
+
65,
|
| 69 |
+
66,
|
| 70 |
+
67,
|
| 71 |
+
68,
|
| 72 |
+
69,
|
| 73 |
+
70,
|
| 74 |
+
71,
|
| 75 |
+
72,
|
| 76 |
+
73,
|
| 77 |
+
74,
|
| 78 |
+
75,
|
| 79 |
+
76,
|
| 80 |
+
77,
|
| 81 |
+
78,
|
| 82 |
+
79,
|
| 83 |
+
80,
|
| 84 |
+
81,
|
| 85 |
+
82,
|
| 86 |
+
83,
|
| 87 |
+
84,
|
| 88 |
+
85,
|
| 89 |
+
86,
|
| 90 |
+
87,
|
| 91 |
+
88,
|
| 92 |
+
89,
|
| 93 |
+
90,
|
| 94 |
+
91,
|
| 95 |
+
92,
|
| 96 |
+
93,
|
| 97 |
+
94,
|
| 98 |
+
95,
|
| 99 |
+
96,
|
| 100 |
+
97,
|
| 101 |
+
98,
|
| 102 |
+
99,
|
| 103 |
+
100,
|
| 104 |
+
101,
|
| 105 |
+
102,
|
| 106 |
+
103,
|
| 107 |
+
104,
|
| 108 |
+
105,
|
| 109 |
+
106,
|
| 110 |
+
107,
|
| 111 |
+
108,
|
| 112 |
+
109,
|
| 113 |
+
110,
|
| 114 |
+
111,
|
| 115 |
+
112,
|
| 116 |
+
113,
|
| 117 |
+
114,
|
| 118 |
+
115,
|
| 119 |
+
116,
|
| 120 |
+
117,
|
| 121 |
+
118,
|
| 122 |
+
119,
|
| 123 |
+
120,
|
| 124 |
+
121,
|
| 125 |
+
122,
|
| 126 |
+
123,
|
| 127 |
+
124,
|
| 128 |
+
125,
|
| 129 |
+
126,
|
| 130 |
+
127,
|
| 131 |
+
128,
|
| 132 |
+
129,
|
| 133 |
+
130,
|
| 134 |
+
131,
|
| 135 |
+
132,
|
| 136 |
+
133,
|
| 137 |
+
134,
|
| 138 |
+
135,
|
| 139 |
+
136,
|
| 140 |
+
137,
|
| 141 |
+
138,
|
| 142 |
+
139,
|
| 143 |
+
140,
|
| 144 |
+
141,
|
| 145 |
+
142,
|
| 146 |
+
143,
|
| 147 |
+
144,
|
| 148 |
+
145,
|
| 149 |
+
146,
|
| 150 |
+
147,
|
| 151 |
+
148,
|
| 152 |
+
149,
|
| 153 |
+
150,
|
| 154 |
+
151,
|
| 155 |
+
152,
|
| 156 |
+
153,
|
| 157 |
+
154,
|
| 158 |
+
155,
|
| 159 |
+
156,
|
| 160 |
+
157,
|
| 161 |
+
158,
|
| 162 |
+
159,
|
| 163 |
+
160,
|
| 164 |
+
161,
|
| 165 |
+
162,
|
| 166 |
+
163,
|
| 167 |
+
164,
|
| 168 |
+
165,
|
| 169 |
+
166,
|
| 170 |
+
167,
|
| 171 |
+
168,
|
| 172 |
+
169,
|
| 173 |
+
170,
|
| 174 |
+
171,
|
| 175 |
+
172,
|
| 176 |
+
173,
|
| 177 |
+
174,
|
| 178 |
+
175,
|
| 179 |
+
176,
|
| 180 |
+
177,
|
| 181 |
+
178,
|
| 182 |
+
179,
|
| 183 |
+
180,
|
| 184 |
+
181,
|
| 185 |
+
182,
|
| 186 |
+
183,
|
| 187 |
+
184,
|
| 188 |
+
185,
|
| 189 |
+
186,
|
| 190 |
+
187,
|
| 191 |
+
188,
|
| 192 |
+
189,
|
| 193 |
+
190,
|
| 194 |
+
191,
|
| 195 |
+
192,
|
| 196 |
+
193,
|
| 197 |
+
194,
|
| 198 |
+
195,
|
| 199 |
+
196,
|
| 200 |
+
197,
|
| 201 |
+
198,
|
| 202 |
+
199,
|
| 203 |
+
200,
|
| 204 |
+
201,
|
| 205 |
+
202,
|
| 206 |
+
203,
|
| 207 |
+
204,
|
| 208 |
+
205,
|
| 209 |
+
206,
|
| 210 |
+
207,
|
| 211 |
+
208,
|
| 212 |
+
209,
|
| 213 |
+
210,
|
| 214 |
+
211,
|
| 215 |
+
212,
|
| 216 |
+
213,
|
| 217 |
+
214,
|
| 218 |
+
215,
|
| 219 |
+
216,
|
| 220 |
+
217,
|
| 221 |
+
218,
|
| 222 |
+
219,
|
| 223 |
+
220,
|
| 224 |
+
221,
|
| 225 |
+
222,
|
| 226 |
+
223,
|
| 227 |
+
224,
|
| 228 |
+
225,
|
| 229 |
+
226,
|
| 230 |
+
227,
|
| 231 |
+
228,
|
| 232 |
+
229,
|
| 233 |
+
230,
|
| 234 |
+
231,
|
| 235 |
+
232,
|
| 236 |
+
233,
|
| 237 |
+
234,
|
| 238 |
+
235,
|
| 239 |
+
236,
|
| 240 |
+
237,
|
| 241 |
+
238,
|
| 242 |
+
239,
|
| 243 |
+
240,
|
| 244 |
+
241,
|
| 245 |
+
242,
|
| 246 |
+
243,
|
| 247 |
+
244,
|
| 248 |
+
245,
|
| 249 |
+
246,
|
| 250 |
+
247,
|
| 251 |
+
248,
|
| 252 |
+
249,
|
| 253 |
+
250,
|
| 254 |
+
251,
|
| 255 |
+
252,
|
| 256 |
+
253,
|
| 257 |
+
254,
|
| 258 |
+
255,
|
| 259 |
+
256,
|
| 260 |
+
257,
|
| 261 |
+
258,
|
| 262 |
+
259,
|
| 263 |
+
260,
|
| 264 |
+
261,
|
| 265 |
+
262,
|
| 266 |
+
263,
|
| 267 |
+
264,
|
| 268 |
+
265,
|
| 269 |
+
266,
|
| 270 |
+
267,
|
| 271 |
+
268
|
| 272 |
+
],
|
| 273 |
+
"losses": [
|
| 274 |
+
11.0,
|
| 275 |
+
10.6875,
|
| 276 |
+
10.125,
|
| 277 |
+
9.6875,
|
| 278 |
+
9.375,
|
| 279 |
+
9.125,
|
| 280 |
+
8.875,
|
| 281 |
+
8.6875,
|
| 282 |
+
8.625,
|
| 283 |
+
8.5625,
|
| 284 |
+
8.4375,
|
| 285 |
+
8.5,
|
| 286 |
+
8.4375,
|
| 287 |
+
8.375,
|
| 288 |
+
8.375,
|
| 289 |
+
8.375,
|
| 290 |
+
8.375,
|
| 291 |
+
8.3125,
|
| 292 |
+
8.25,
|
| 293 |
+
8.25,
|
| 294 |
+
8.25,
|
| 295 |
+
8.25,
|
| 296 |
+
8.1875,
|
| 297 |
+
8.3125,
|
| 298 |
+
8.1875,
|
| 299 |
+
8.125,
|
| 300 |
+
8.1875,
|
| 301 |
+
8.0625,
|
| 302 |
+
8.125,
|
| 303 |
+
8.1875,
|
| 304 |
+
8.0625,
|
| 305 |
+
8.1875,
|
| 306 |
+
8.0625,
|
| 307 |
+
8.125,
|
| 308 |
+
8.0,
|
| 309 |
+
8.0625,
|
| 310 |
+
8.0625,
|
| 311 |
+
8.125,
|
| 312 |
+
8.0625,
|
| 313 |
+
8.0,
|
| 314 |
+
8.0,
|
| 315 |
+
8.0,
|
| 316 |
+
8.0,
|
| 317 |
+
8.0625,
|
| 318 |
+
8.0,
|
| 319 |
+
8.0,
|
| 320 |
+
7.96875,
|
| 321 |
+
7.96875,
|
| 322 |
+
8.0,
|
| 323 |
+
8.0,
|
| 324 |
+
7.96875,
|
| 325 |
+
7.96875,
|
| 326 |
+
7.96875,
|
| 327 |
+
7.96875,
|
| 328 |
+
8.0,
|
| 329 |
+
7.90625,
|
| 330 |
+
7.875,
|
| 331 |
+
7.9375,
|
| 332 |
+
7.90625,
|
| 333 |
+
7.90625,
|
| 334 |
+
7.84375,
|
| 335 |
+
7.875,
|
| 336 |
+
7.84375,
|
| 337 |
+
7.90625,
|
| 338 |
+
7.875,
|
| 339 |
+
7.84375,
|
| 340 |
+
7.84375,
|
| 341 |
+
7.8125,
|
| 342 |
+
7.84375,
|
| 343 |
+
7.78125,
|
| 344 |
+
7.78125,
|
| 345 |
+
7.78125,
|
| 346 |
+
7.84375,
|
| 347 |
+
7.8125,
|
| 348 |
+
7.78125,
|
| 349 |
+
7.75,
|
| 350 |
+
7.78125,
|
| 351 |
+
7.78125,
|
| 352 |
+
7.75,
|
| 353 |
+
7.71875,
|
| 354 |
+
7.78125,
|
| 355 |
+
7.71875,
|
| 356 |
+
7.78125,
|
| 357 |
+
7.6875,
|
| 358 |
+
7.71875,
|
| 359 |
+
7.65625,
|
| 360 |
+
7.71875,
|
| 361 |
+
7.65625,
|
| 362 |
+
7.71875,
|
| 363 |
+
7.71875,
|
| 364 |
+
7.6875,
|
| 365 |
+
7.6875,
|
| 366 |
+
7.71875,
|
| 367 |
+
7.65625,
|
| 368 |
+
7.65625,
|
| 369 |
+
7.625,
|
| 370 |
+
7.6875,
|
| 371 |
+
7.6875,
|
| 372 |
+
7.59375,
|
| 373 |
+
7.65625,
|
| 374 |
+
7.59375,
|
| 375 |
+
7.625,
|
| 376 |
+
7.625,
|
| 377 |
+
7.625,
|
| 378 |
+
7.59375,
|
| 379 |
+
7.59375,
|
| 380 |
+
7.59375,
|
| 381 |
+
7.65625,
|
| 382 |
+
7.59375,
|
| 383 |
+
7.53125,
|
| 384 |
+
7.5625,
|
| 385 |
+
7.53125,
|
| 386 |
+
7.5,
|
| 387 |
+
7.5625,
|
| 388 |
+
7.53125,
|
| 389 |
+
7.5,
|
| 390 |
+
7.5,
|
| 391 |
+
7.5,
|
| 392 |
+
7.59375,
|
| 393 |
+
7.46875,
|
| 394 |
+
7.53125,
|
| 395 |
+
7.46875,
|
| 396 |
+
7.53125,
|
| 397 |
+
7.5,
|
| 398 |
+
7.46875,
|
| 399 |
+
7.5,
|
| 400 |
+
7.46875,
|
| 401 |
+
7.5,
|
| 402 |
+
7.4375,
|
| 403 |
+
7.5,
|
| 404 |
+
7.5,
|
| 405 |
+
7.46875,
|
| 406 |
+
7.4375,
|
| 407 |
+
7.5,
|
| 408 |
+
7.375,
|
| 409 |
+
7.4375,
|
| 410 |
+
7.40625,
|
| 411 |
+
7.375,
|
| 412 |
+
7.375,
|
| 413 |
+
7.3125,
|
| 414 |
+
7.40625,
|
| 415 |
+
7.375,
|
| 416 |
+
7.3125,
|
| 417 |
+
7.34375,
|
| 418 |
+
7.34375,
|
| 419 |
+
7.375,
|
| 420 |
+
7.34375,
|
| 421 |
+
7.375,
|
| 422 |
+
7.40625,
|
| 423 |
+
7.28125,
|
| 424 |
+
7.375,
|
| 425 |
+
7.3125,
|
| 426 |
+
7.34375,
|
| 427 |
+
7.375,
|
| 428 |
+
7.3125,
|
| 429 |
+
7.25,
|
| 430 |
+
7.34375,
|
| 431 |
+
7.34375,
|
| 432 |
+
7.3125,
|
| 433 |
+
7.375,
|
| 434 |
+
7.28125,
|
| 435 |
+
7.34375,
|
| 436 |
+
7.25,
|
| 437 |
+
7.25,
|
| 438 |
+
7.3125,
|
| 439 |
+
7.3125,
|
| 440 |
+
7.34375,
|
| 441 |
+
7.34375,
|
| 442 |
+
7.3125,
|
| 443 |
+
7.28125,
|
| 444 |
+
7.3125,
|
| 445 |
+
7.25,
|
| 446 |
+
7.25,
|
| 447 |
+
7.375,
|
| 448 |
+
7.25,
|
| 449 |
+
7.34375,
|
| 450 |
+
7.1875,
|
| 451 |
+
7.1875,
|
| 452 |
+
7.21875,
|
| 453 |
+
7.21875,
|
| 454 |
+
7.21875,
|
| 455 |
+
7.21875,
|
| 456 |
+
7.1875,
|
| 457 |
+
7.21875,
|
| 458 |
+
7.1875,
|
| 459 |
+
7.1875,
|
| 460 |
+
7.3125,
|
| 461 |
+
7.25,
|
| 462 |
+
7.21875,
|
| 463 |
+
7.25,
|
| 464 |
+
7.15625,
|
| 465 |
+
7.25,
|
| 466 |
+
7.1875,
|
| 467 |
+
7.1875,
|
| 468 |
+
7.25,
|
| 469 |
+
7.21875,
|
| 470 |
+
7.1875,
|
| 471 |
+
7.1875,
|
| 472 |
+
7.1875,
|
| 473 |
+
7.21875,
|
| 474 |
+
7.1875,
|
| 475 |
+
7.1875,
|
| 476 |
+
7.125,
|
| 477 |
+
7.15625,
|
| 478 |
+
7.25,
|
| 479 |
+
7.1875,
|
| 480 |
+
7.15625,
|
| 481 |
+
7.1875,
|
| 482 |
+
7.15625,
|
| 483 |
+
7.1875,
|
| 484 |
+
7.0625,
|
| 485 |
+
7.125,
|
| 486 |
+
7.15625,
|
| 487 |
+
7.125,
|
| 488 |
+
7.125,
|
| 489 |
+
7.125,
|
| 490 |
+
7.09375,
|
| 491 |
+
7.15625,
|
| 492 |
+
7.125,
|
| 493 |
+
7.09375,
|
| 494 |
+
7.15625,
|
| 495 |
+
7.15625,
|
| 496 |
+
7.125,
|
| 497 |
+
7.125,
|
| 498 |
+
7.125,
|
| 499 |
+
7.09375,
|
| 500 |
+
7.125,
|
| 501 |
+
7.15625,
|
| 502 |
+
7.15625,
|
| 503 |
+
7.125,
|
| 504 |
+
7.125,
|
| 505 |
+
7.21875,
|
| 506 |
+
7.03125,
|
| 507 |
+
7.03125,
|
| 508 |
+
7.09375,
|
| 509 |
+
7.125,
|
| 510 |
+
7.125,
|
| 511 |
+
7.1875,
|
| 512 |
+
7.125,
|
| 513 |
+
7.03125,
|
| 514 |
+
7.09375,
|
| 515 |
+
7.03125,
|
| 516 |
+
7.09375,
|
| 517 |
+
7.0625,
|
| 518 |
+
7.09375,
|
| 519 |
+
7.03125,
|
| 520 |
+
7.0,
|
| 521 |
+
7.03125,
|
| 522 |
+
7.03125,
|
| 523 |
+
7.09375,
|
| 524 |
+
7.0625,
|
| 525 |
+
7.09375,
|
| 526 |
+
7.0,
|
| 527 |
+
7.0,
|
| 528 |
+
7.09375,
|
| 529 |
+
7.09375,
|
| 530 |
+
6.96875,
|
| 531 |
+
7.0625,
|
| 532 |
+
7.03125,
|
| 533 |
+
7.125,
|
| 534 |
+
7.0625,
|
| 535 |
+
7.09375,
|
| 536 |
+
7.0625,
|
| 537 |
+
7.0,
|
| 538 |
+
7.0,
|
| 539 |
+
7.03125,
|
| 540 |
+
7.0625,
|
| 541 |
+
6.96875
|
| 542 |
+
],
|
| 543 |
+
"accuracies": [
|
| 544 |
+
0.0,
|
| 545 |
+
0.04423302650274912,
|
| 546 |
+
0.04827222368768135,
|
| 547 |
+
0.05212991292068722,
|
| 548 |
+
0.044954881050041015,
|
| 549 |
+
0.04950160500084474,
|
| 550 |
+
0.04848041902673732,
|
| 551 |
+
0.053017360154312486,
|
| 552 |
+
0.046307523529072116,
|
| 553 |
+
0.05398880719850763,
|
| 554 |
+
0.07635887360838245,
|
| 555 |
+
0.08790523690773068,
|
| 556 |
+
0.09341814159292035,
|
| 557 |
+
0.083670145382156,
|
| 558 |
+
0.0899413945700275,
|
| 559 |
+
0.09564366691603844,
|
| 560 |
+
0.09995699453216195,
|
| 561 |
+
0.10162823073663822,
|
| 562 |
+
0.10413742772132711,
|
| 563 |
+
0.1001869835333856,
|
| 564 |
+
0.10753554775200046,
|
| 565 |
+
0.10891808439789308,
|
| 566 |
+
0.11429497568881686,
|
| 567 |
+
0.10425450364124185,
|
| 568 |
+
0.10341046800161578,
|
| 569 |
+
0.11589257503949447,
|
| 570 |
+
0.11176896256825208,
|
| 571 |
+
0.11698880976602238,
|
| 572 |
+
0.1125892915656334,
|
| 573 |
+
0.10911955879456371,
|
| 574 |
+
0.12144368680931107,
|
| 575 |
+
0.11017418600356989,
|
| 576 |
+
0.11480237969016906,
|
| 577 |
+
0.11978341257263603,
|
| 578 |
+
0.11681080440706078,
|
| 579 |
+
0.11649415079316469,
|
| 580 |
+
0.11555281453240637,
|
| 581 |
+
0.11003338162121308,
|
| 582 |
+
0.11689138360048608,
|
| 583 |
+
0.12174754931622897,
|
| 584 |
+
0.12477749066896354,
|
| 585 |
+
0.1201019432940427,
|
| 586 |
+
0.12122096416481849,
|
| 587 |
+
0.11860842396202607,
|
| 588 |
+
0.12766453115899826,
|
| 589 |
+
0.11962117841479693,
|
| 590 |
+
0.12314615287108632,
|
| 591 |
+
0.12122148729677938,
|
| 592 |
+
0.12069913829982278,
|
| 593 |
+
0.12193533104346796,
|
| 594 |
+
0.12389127324749642,
|
| 595 |
+
0.12640217262959028,
|
| 596 |
+
0.12956831003188618,
|
| 597 |
+
0.12451748742542987,
|
| 598 |
+
0.11773620096753512,
|
| 599 |
+
0.12327175554780992,
|
| 600 |
+
0.13320532821312853,
|
| 601 |
+
0.12767546042807368,
|
| 602 |
+
0.12988321773667674,
|
| 603 |
+
0.12672353353587287,
|
| 604 |
+
0.13206696716033484,
|
| 605 |
+
0.12795810164231217,
|
| 606 |
+
0.1381201695337821,
|
| 607 |
+
0.12992290683081337,
|
| 608 |
+
0.14040131424548227,
|
| 609 |
+
0.13993130644956112,
|
| 610 |
+
0.1397613673008707,
|
| 611 |
+
0.14226041293710467,
|
| 612 |
+
0.14079068342016549,
|
| 613 |
+
0.13980189104007204,
|
| 614 |
+
0.13823358512492737,
|
| 615 |
+
0.1407876618011567,
|
| 616 |
+
0.1402567760342368,
|
| 617 |
+
0.14064837905236907,
|
| 618 |
+
0.14689437218913334,
|
| 619 |
+
0.14099757410804095,
|
| 620 |
+
0.14469289555618456,
|
| 621 |
+
0.14470220970802472,
|
| 622 |
+
0.14906476650973408,
|
| 623 |
+
0.14987903463739896,
|
| 624 |
+
0.15018988844054118,
|
| 625 |
+
0.15366918357715903,
|
| 626 |
+
0.1468786808009423,
|
| 627 |
+
0.15481609054004183,
|
| 628 |
+
0.1521385692846423,
|
| 629 |
+
0.15592946871038377,
|
| 630 |
+
0.1564777803903127,
|
| 631 |
+
0.1566301336866193,
|
| 632 |
+
0.14522481128979323,
|
| 633 |
+
0.15749023560539246,
|
| 634 |
+
0.1539742820974082,
|
| 635 |
+
0.1550881665604419,
|
| 636 |
+
0.15072547881601858,
|
| 637 |
+
0.1575404457517819,
|
| 638 |
+
0.1554497415945648,
|
| 639 |
+
0.15989308061478646,
|
| 640 |
+
0.15661824303260802,
|
| 641 |
+
0.1563026153328095,
|
| 642 |
+
0.15625,
|
| 643 |
+
0.15798840346747803,
|
| 644 |
+
0.16426361566750336,
|
| 645 |
+
0.16115069587800493,
|
| 646 |
+
0.15960610666842906,
|
| 647 |
+
0.15820996722793537,
|
| 648 |
+
0.1622126269109581,
|
| 649 |
+
0.1621356845456772,
|
| 650 |
+
0.15993617282435252,
|
| 651 |
+
0.15809825673534073,
|
| 652 |
+
0.15992658305292137,
|
| 653 |
+
0.16723528695016449,
|
| 654 |
+
0.16247399281255911,
|
| 655 |
+
0.16403560830860534,
|
| 656 |
+
0.16861952060905253,
|
| 657 |
+
0.16138059701492538,
|
| 658 |
+
0.1690070523622293,
|
| 659 |
+
0.17176768285335584,
|
| 660 |
+
0.17175141242937852,
|
| 661 |
+
0.17319158510518617,
|
| 662 |
+
0.162311653633416,
|
| 663 |
+
0.16818897637795274,
|
| 664 |
+
0.17052296068941092,
|
| 665 |
+
0.16895452874126732,
|
| 666 |
+
0.16135312728157702,
|
| 667 |
+
0.16497908203480263,
|
| 668 |
+
0.17369889027357427,
|
| 669 |
+
0.17823473152069955,
|
| 670 |
+
0.17684088940225237,
|
| 671 |
+
0.1721441523118767,
|
| 672 |
+
0.17593335390311632,
|
| 673 |
+
0.1714674970805761,
|
| 674 |
+
0.16319444444444445,
|
| 675 |
+
0.1752780885934312,
|
| 676 |
+
0.1774151264910211,
|
| 677 |
+
0.1675549633577615,
|
| 678 |
+
0.17832665201086254,
|
| 679 |
+
0.17135161268043372,
|
| 680 |
+
0.18018568966475787,
|
| 681 |
+
0.1718141103937649,
|
| 682 |
+
0.17716872629389452,
|
| 683 |
+
0.17983464909554298,
|
| 684 |
+
0.17548830479864963,
|
| 685 |
+
0.1753569021506035,
|
| 686 |
+
0.1769342711617754,
|
| 687 |
+
0.1795614398014067,
|
| 688 |
+
0.17274399137548355,
|
| 689 |
+
0.17778324214667732,
|
| 690 |
+
0.1757472063305352,
|
| 691 |
+
0.18108540487324637,
|
| 692 |
+
0.17718785723358313,
|
| 693 |
+
0.18160060708656822,
|
| 694 |
+
0.1781688376753507,
|
| 695 |
+
0.1779335152567601,
|
| 696 |
+
0.1808099372583814,
|
| 697 |
+
0.17645324843768423,
|
| 698 |
+
0.1787539547335118,
|
| 699 |
+
0.18748072772124577,
|
| 700 |
+
0.18202976664420897,
|
| 701 |
+
0.1789703739679456,
|
| 702 |
+
0.18572278405710888,
|
| 703 |
+
0.1765648243506122,
|
| 704 |
+
0.18143991240076648,
|
| 705 |
+
0.1820546989022146,
|
| 706 |
+
0.18812062138288152,
|
| 707 |
+
0.1831071725283855,
|
| 708 |
+
0.18061035042933396,
|
| 709 |
+
0.18062250788549664,
|
| 710 |
+
0.17738528341743925,
|
| 711 |
+
0.17949581719162316,
|
| 712 |
+
0.18172097473127358,
|
| 713 |
+
0.17748557148807045,
|
| 714 |
+
0.18424678047319556,
|
| 715 |
+
0.1887334738455643,
|
| 716 |
+
0.1815368746776689,
|
| 717 |
+
0.1760951393813758,
|
| 718 |
+
0.18922133199799698,
|
| 719 |
+
0.1776448324278127,
|
| 720 |
+
0.1896094280249275,
|
| 721 |
+
0.19332184128200217,
|
| 722 |
+
0.18473488686254644,
|
| 723 |
+
0.18706615247700978,
|
| 724 |
+
0.18972089020041805,
|
| 725 |
+
0.18542973478595795,
|
| 726 |
+
0.19167449139280124,
|
| 727 |
+
0.19097265576226746,
|
| 728 |
+
0.18781275733198202,
|
| 729 |
+
0.1960016131820015,
|
| 730 |
+
0.185518341307815,
|
| 731 |
+
0.18537485857202407,
|
| 732 |
+
0.18766933590222168,
|
| 733 |
+
0.18968998693431524,
|
| 734 |
+
0.19535288992158,
|
| 735 |
+
0.1876954496138873,
|
| 736 |
+
0.19527523707984962,
|
| 737 |
+
0.19185649556203835,
|
| 738 |
+
0.18391405342624856,
|
| 739 |
+
0.19106635682933126,
|
| 740 |
+
0.19672669909294072,
|
| 741 |
+
0.19490586932447398,
|
| 742 |
+
0.19185478775346085,
|
| 743 |
+
0.19083046029153813,
|
| 744 |
+
0.18796148620710024,
|
| 745 |
+
0.1963360988919205,
|
| 746 |
+
0.1899639386345578,
|
| 747 |
+
0.1982010315762989,
|
| 748 |
+
0.18932487779098955,
|
| 749 |
+
0.19341587934980342,
|
| 750 |
+
0.19753702779164586,
|
| 751 |
+
0.19842900302114805,
|
| 752 |
+
0.19303702817491178,
|
| 753 |
+
0.1965719492056261,
|
| 754 |
+
0.19681215366415541,
|
| 755 |
+
0.1996670160942221,
|
| 756 |
+
0.20012128562765313,
|
| 757 |
+
0.19841318278913642,
|
| 758 |
+
0.19645053593393078,
|
| 759 |
+
0.20727468839884947,
|
| 760 |
+
0.2050131610433118,
|
| 761 |
+
0.19620965353864378,
|
| 762 |
+
0.20050987890376035,
|
| 763 |
+
0.201457406332624,
|
| 764 |
+
0.19989537316903047,
|
| 765 |
+
0.1965027700831025,
|
| 766 |
+
0.20240843576464715,
|
| 767 |
+
0.1964020891095493,
|
| 768 |
+
0.19782742594770145,
|
| 769 |
+
0.19955947136563876,
|
| 770 |
+
0.1991643454038997,
|
| 771 |
+
0.19850907779247326,
|
| 772 |
+
0.19737464522232734,
|
| 773 |
+
0.19536738181127777,
|
| 774 |
+
0.19968845485591036,
|
| 775 |
+
0.18690645773979106,
|
| 776 |
+
0.20488583353793272,
|
| 777 |
+
0.19926312557568315,
|
| 778 |
+
0.202051346589479,
|
| 779 |
+
0.1990265329138719,
|
| 780 |
+
0.1982712047541869,
|
| 781 |
+
0.19302726138860843,
|
| 782 |
+
0.20222195957924596,
|
| 783 |
+
0.20388872270415795,
|
| 784 |
+
0.19997665869171968,
|
| 785 |
+
0.20794248160422402,
|
| 786 |
+
0.2001875,
|
| 787 |
+
0.19940980724555785,
|
| 788 |
+
0.19916739702015776,
|
| 789 |
+
0.21011620877275475,
|
| 790 |
+
0.20827744778693236,
|
| 791 |
+
0.20298416565164434,
|
| 792 |
+
0.20731631959463634,
|
| 793 |
+
0.20344218887908208,
|
| 794 |
+
0.2077930213618994,
|
| 795 |
+
0.20241656402135022,
|
| 796 |
+
0.2116437934642132,
|
| 797 |
+
0.20662152857470736,
|
| 798 |
+
0.19898477157360406,
|
| 799 |
+
0.20519389775241645,
|
| 800 |
+
0.2095681376303541,
|
| 801 |
+
0.2089129631909393,
|
| 802 |
+
0.2049614366294463,
|
| 803 |
+
0.19996526370636253,
|
| 804 |
+
0.20843324171004152,
|
| 805 |
+
0.19918018590150685,
|
| 806 |
+
0.206639338754116,
|
| 807 |
+
0.21402843601895735,
|
| 808 |
+
0.21074124489543372,
|
| 809 |
+
0.21234243997034163,
|
| 810 |
+
0.2036560085432502,
|
| 811 |
+
0.20563956943802417
|
| 812 |
+
],
|
| 813 |
+
"grad_norms": [
|
| 814 |
+
0.46484375,
|
| 815 |
+
0.96875,
|
| 816 |
+
0.8125,
|
| 817 |
+
0.84765625,
|
| 818 |
+
0.7890625,
|
| 819 |
+
0.7734375,
|
| 820 |
+
0.69921875,
|
| 821 |
+
0.578125,
|
| 822 |
+
0.4140625,
|
| 823 |
+
0.279296875,
|
| 824 |
+
0.2333984375,
|
| 825 |
+
0.28125,
|
| 826 |
+
0.255859375,
|
| 827 |
+
0.236328125,
|
| 828 |
+
0.19921875,
|
| 829 |
+
0.255859375,
|
| 830 |
+
0.1669921875,
|
| 831 |
+
0.25,
|
| 832 |
+
0.1513671875,
|
| 833 |
+
0.1806640625,
|
| 834 |
+
0.2041015625,
|
| 835 |
+
0.130859375,
|
| 836 |
+
0.16015625,
|
| 837 |
+
0.166015625,
|
| 838 |
+
0.140625,
|
| 839 |
+
0.1640625,
|
| 840 |
+
0.125,
|
| 841 |
+
0.212890625,
|
| 842 |
+
0.203125,
|
| 843 |
+
0.1337890625,
|
| 844 |
+
0.2392578125,
|
| 845 |
+
0.1337890625,
|
| 846 |
+
0.1484375,
|
| 847 |
+
0.1728515625,
|
| 848 |
+
0.142578125,
|
| 849 |
+
0.14453125,
|
| 850 |
+
0.1083984375,
|
| 851 |
+
0.12060546875,
|
| 852 |
+
0.10888671875,
|
| 853 |
+
0.1328125,
|
| 854 |
+
0.1396484375,
|
| 855 |
+
0.1171875,
|
| 856 |
+
0.115234375,
|
| 857 |
+
0.1337890625,
|
| 858 |
+
0.134765625,
|
| 859 |
+
0.130859375,
|
| 860 |
+
0.12109375,
|
| 861 |
+
0.142578125,
|
| 862 |
+
0.146484375,
|
| 863 |
+
0.1318359375,
|
| 864 |
+
0.126953125,
|
| 865 |
+
0.1396484375,
|
| 866 |
+
0.1806640625,
|
| 867 |
+
0.1826171875,
|
| 868 |
+
0.1962890625,
|
| 869 |
+
0.1103515625,
|
| 870 |
+
0.1484375,
|
| 871 |
+
0.1435546875,
|
| 872 |
+
0.1357421875,
|
| 873 |
+
0.1357421875,
|
| 874 |
+
0.171875,
|
| 875 |
+
0.2197265625,
|
| 876 |
+
0.2109375,
|
| 877 |
+
0.171875,
|
| 878 |
+
0.1328125,
|
| 879 |
+
0.1552734375,
|
| 880 |
+
0.125,
|
| 881 |
+
0.224609375,
|
| 882 |
+
0.2255859375,
|
| 883 |
+
0.1884765625,
|
| 884 |
+
0.126953125,
|
| 885 |
+
0.154296875,
|
| 886 |
+
0.154296875,
|
| 887 |
+
0.166015625,
|
| 888 |
+
0.154296875,
|
| 889 |
+
0.1806640625,
|
| 890 |
+
0.140625,
|
| 891 |
+
0.1455078125,
|
| 892 |
+
0.1640625,
|
| 893 |
+
0.1279296875,
|
| 894 |
+
0.1298828125,
|
| 895 |
+
0.1357421875,
|
| 896 |
+
0.1298828125,
|
| 897 |
+
0.1484375,
|
| 898 |
+
0.11865234375,
|
| 899 |
+
0.1572265625,
|
| 900 |
+
0.1474609375,
|
| 901 |
+
0.24609375,
|
| 902 |
+
0.306640625,
|
| 903 |
+
0.19921875,
|
| 904 |
+
0.177734375,
|
| 905 |
+
0.189453125,
|
| 906 |
+
0.1748046875,
|
| 907 |
+
0.1708984375,
|
| 908 |
+
0.1337890625,
|
| 909 |
+
0.150390625,
|
| 910 |
+
0.126953125,
|
| 911 |
+
0.1552734375,
|
| 912 |
+
0.1474609375,
|
| 913 |
+
0.15234375,
|
| 914 |
+
0.1494140625,
|
| 915 |
+
0.1435546875,
|
| 916 |
+
0.16015625,
|
| 917 |
+
0.1728515625,
|
| 918 |
+
0.14453125,
|
| 919 |
+
0.1279296875,
|
| 920 |
+
0.12451171875,
|
| 921 |
+
0.154296875,
|
| 922 |
+
0.1357421875,
|
| 923 |
+
0.1513671875,
|
| 924 |
+
0.1240234375,
|
| 925 |
+
0.1484375,
|
| 926 |
+
0.126953125,
|
| 927 |
+
0.13671875,
|
| 928 |
+
0.138671875,
|
| 929 |
+
0.115234375,
|
| 930 |
+
0.1494140625,
|
| 931 |
+
0.125,
|
| 932 |
+
0.14453125,
|
| 933 |
+
0.1416015625,
|
| 934 |
+
0.1259765625,
|
| 935 |
+
0.205078125,
|
| 936 |
+
0.208984375,
|
| 937 |
+
0.1689453125,
|
| 938 |
+
0.1787109375,
|
| 939 |
+
0.150390625,
|
| 940 |
+
0.171875,
|
| 941 |
+
0.1826171875,
|
| 942 |
+
0.1806640625,
|
| 943 |
+
0.1552734375,
|
| 944 |
+
0.1435546875,
|
| 945 |
+
0.1787109375,
|
| 946 |
+
0.1376953125,
|
| 947 |
+
0.15234375,
|
| 948 |
+
0.1474609375,
|
| 949 |
+
0.1689453125,
|
| 950 |
+
0.15625,
|
| 951 |
+
0.1494140625,
|
| 952 |
+
0.16015625,
|
| 953 |
+
0.1318359375,
|
| 954 |
+
0.177734375,
|
| 955 |
+
0.1533203125,
|
| 956 |
+
0.1787109375,
|
| 957 |
+
0.1650390625,
|
| 958 |
+
0.17578125,
|
| 959 |
+
0.1953125,
|
| 960 |
+
0.1787109375,
|
| 961 |
+
0.1494140625,
|
| 962 |
+
0.12890625,
|
| 963 |
+
0.1552734375,
|
| 964 |
+
0.1396484375,
|
| 965 |
+
0.146484375,
|
| 966 |
+
0.1435546875,
|
| 967 |
+
0.154296875,
|
| 968 |
+
0.17578125,
|
| 969 |
+
0.130859375,
|
| 970 |
+
0.146484375,
|
| 971 |
+
0.1533203125,
|
| 972 |
+
0.181640625,
|
| 973 |
+
0.162109375,
|
| 974 |
+
0.1513671875,
|
| 975 |
+
0.20703125,
|
| 976 |
+
0.1357421875,
|
| 977 |
+
0.25,
|
| 978 |
+
0.1796875,
|
| 979 |
+
0.1884765625,
|
| 980 |
+
0.1728515625,
|
| 981 |
+
0.1845703125,
|
| 982 |
+
0.1640625,
|
| 983 |
+
0.185546875,
|
| 984 |
+
0.197265625,
|
| 985 |
+
0.203125,
|
| 986 |
+
0.177734375,
|
| 987 |
+
0.20703125,
|
| 988 |
+
0.1806640625,
|
| 989 |
+
0.21875,
|
| 990 |
+
0.1376953125,
|
| 991 |
+
0.205078125,
|
| 992 |
+
0.1748046875,
|
| 993 |
+
0.162109375,
|
| 994 |
+
0.177734375,
|
| 995 |
+
0.1552734375,
|
| 996 |
+
0.1650390625,
|
| 997 |
+
0.18359375,
|
| 998 |
+
0.166015625,
|
| 999 |
+
0.1533203125,
|
| 1000 |
+
0.1572265625,
|
| 1001 |
+
0.1552734375,
|
| 1002 |
+
0.1689453125,
|
| 1003 |
+
0.1533203125,
|
| 1004 |
+
0.16796875,
|
| 1005 |
+
0.1474609375,
|
| 1006 |
+
0.166015625,
|
| 1007 |
+
0.181640625,
|
| 1008 |
+
0.1669921875,
|
| 1009 |
+
0.16015625,
|
| 1010 |
+
0.1640625,
|
| 1011 |
+
0.154296875,
|
| 1012 |
+
0.15234375,
|
| 1013 |
+
0.1435546875,
|
| 1014 |
+
0.1484375,
|
| 1015 |
+
0.1796875,
|
| 1016 |
+
0.16015625,
|
| 1017 |
+
0.1455078125,
|
| 1018 |
+
0.166015625,
|
| 1019 |
+
0.2001953125,
|
| 1020 |
+
0.1748046875,
|
| 1021 |
+
0.1357421875,
|
| 1022 |
+
0.146484375,
|
| 1023 |
+
0.1650390625,
|
| 1024 |
+
0.1806640625,
|
| 1025 |
+
0.166015625,
|
| 1026 |
+
0.1806640625,
|
| 1027 |
+
0.17578125,
|
| 1028 |
+
0.17578125,
|
| 1029 |
+
0.2060546875,
|
| 1030 |
+
0.158203125,
|
| 1031 |
+
0.1953125,
|
| 1032 |
+
0.158203125,
|
| 1033 |
+
0.166015625,
|
| 1034 |
+
0.1669921875,
|
| 1035 |
+
0.171875,
|
| 1036 |
+
0.142578125,
|
| 1037 |
+
0.166015625,
|
| 1038 |
+
0.1494140625,
|
| 1039 |
+
0.1787109375,
|
| 1040 |
+
0.2099609375,
|
| 1041 |
+
0.2197265625,
|
| 1042 |
+
0.171875,
|
| 1043 |
+
0.1708984375,
|
| 1044 |
+
0.1650390625,
|
| 1045 |
+
0.17578125,
|
| 1046 |
+
0.17578125,
|
| 1047 |
+
0.169921875,
|
| 1048 |
+
0.1826171875,
|
| 1049 |
+
0.17578125,
|
| 1050 |
+
0.185546875,
|
| 1051 |
+
0.2451171875,
|
| 1052 |
+
0.201171875,
|
| 1053 |
+
0.1748046875,
|
| 1054 |
+
0.16796875,
|
| 1055 |
+
0.16796875,
|
| 1056 |
+
0.1826171875,
|
| 1057 |
+
0.162109375,
|
| 1058 |
+
0.158203125,
|
| 1059 |
+
0.185546875,
|
| 1060 |
+
0.1435546875,
|
| 1061 |
+
0.169921875,
|
| 1062 |
+
0.140625,
|
| 1063 |
+
0.142578125,
|
| 1064 |
+
0.1416015625,
|
| 1065 |
+
0.1455078125,
|
| 1066 |
+
0.1572265625,
|
| 1067 |
+
0.150390625,
|
| 1068 |
+
0.14453125,
|
| 1069 |
+
0.142578125,
|
| 1070 |
+
0.1494140625,
|
| 1071 |
+
0.1318359375,
|
| 1072 |
+
0.150390625,
|
| 1073 |
+
0.1318359375,
|
| 1074 |
+
0.1533203125,
|
| 1075 |
+
0.1513671875,
|
| 1076 |
+
0.16015625,
|
| 1077 |
+
0.16015625,
|
| 1078 |
+
0.142578125,
|
| 1079 |
+
0.16015625,
|
| 1080 |
+
0.1708984375,
|
| 1081 |
+
0.1474609375
|
| 1082 |
+
]
|
| 1083 |
+
},
|
| 1084 |
+
"eval": {
|
| 1085 |
+
"effective_batch_nums": [
|
| 1086 |
+
134,
|
| 1087 |
+
268
|
| 1088 |
+
],
|
| 1089 |
+
"losses": [
|
| 1090 |
+
7.514705882352941,
|
| 1091 |
+
7.224264705882353
|
| 1092 |
+
],
|
| 1093 |
+
"perplexities": [
|
| 1094 |
+
1834.8277417067065,
|
| 1095 |
+
1372.329178985474
|
| 1096 |
+
],
|
| 1097 |
+
"accuracies": [
|
| 1098 |
+
0.17672043251292333,
|
| 1099 |
+
0.20080300360920214
|
| 1100 |
+
]
|
| 1101 |
+
}
|
| 1102 |
+
}
|
control_789/epoch1/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:486ff26fd00e8f268b5f968b03c7f5590086244b1f616bd1c966b14825dcb125
|
| 3 |
+
size 29774819
|
control_789/epoch1/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82e97c7c504c445f15bf27902d5bf27443d217191333cb3972f164cc8971edcb
|
| 3 |
+
size 59595275
|
control_789/epoch1/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd4db8821455adef0fec8cff4845bd5e7b110d5b7d9dc915eca5d1cbce619b99
|
| 3 |
+
size 1465
|
control_789/epoch1/tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
control_789/epoch1/tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
control_789/epoch1/tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
control_789/epoch1/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"pad_token": "<|endoftext|>",
|
| 19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 20 |
+
"unk_token": "<|endoftext|>"
|
| 21 |
+
}
|
control_789/epoch1/tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|