End of training
Browse files
README.md
CHANGED
@@ -40,112 +40,44 @@ The following hyperparameters were used during training:
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
| No log | 1.0 | 42 | 0.0129 |
|
50 |
-
| No log | 2.0 | 84 | 0.
|
51 |
| No log | 3.0 | 126 | 0.0007 |
|
52 |
| No log | 4.0 | 168 | 0.0005 |
|
53 |
| No log | 5.0 | 210 | 0.0003 |
|
54 |
| No log | 6.0 | 252 | 0.0003 |
|
55 |
| No log | 7.0 | 294 | 0.0002 |
|
56 |
| No log | 8.0 | 336 | 0.0002 |
|
57 |
-
| No log | 9.0 | 378 | 0.
|
58 |
-
| No log | 10.0 | 420 | 0.
|
59 |
| No log | 11.0 | 462 | 0.0001 |
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.0 | 24.0 | 1008 | 0.
|
73 |
-
| 0.0 | 25.0 | 1050 | 0.
|
74 |
-
| 0.0 | 26.0 | 1092 | 0.
|
75 |
-
| 0.0 | 27.0 | 1134 | 0.
|
76 |
-
| 0.0 | 28.0 | 1176 | 0.
|
77 |
-
| 0.0 | 29.0 | 1218 | 0.
|
78 |
-
| 0.0 | 30.0 | 1260 | 0.
|
79 |
-
| 0.0 | 31.0 | 1302 | 0.
|
80 |
| 0.0 | 32.0 | 1344 | 0.0000 |
|
81 |
-
| 0.0 | 33.0 | 1386 | 0.0000 |
|
82 |
-
| 0.0 | 34.0 | 1428 | 0.0000 |
|
83 |
-
| 0.0 | 35.0 | 1470 | 0.0000 |
|
84 |
-
| 0.0 | 36.0 | 1512 | 0.0000 |
|
85 |
-
| 0.0 | 37.0 | 1554 | 0.0000 |
|
86 |
-
| 0.0 | 38.0 | 1596 | 0.0000 |
|
87 |
-
| 0.0 | 39.0 | 1638 | 0.0000 |
|
88 |
-
| 0.0 | 40.0 | 1680 | 0.0000 |
|
89 |
-
| 0.0 | 41.0 | 1722 | 0.0000 |
|
90 |
-
| 0.0 | 42.0 | 1764 | 0.0000 |
|
91 |
-
| 0.0 | 43.0 | 1806 | 0.0000 |
|
92 |
-
| 0.0 | 44.0 | 1848 | 0.0000 |
|
93 |
-
| 0.0 | 45.0 | 1890 | 0.0000 |
|
94 |
-
| 0.0 | 46.0 | 1932 | 0.0000 |
|
95 |
-
| 0.0 | 47.0 | 1974 | 0.0000 |
|
96 |
-
| 0.0 | 48.0 | 2016 | 0.0000 |
|
97 |
-
| 0.0 | 49.0 | 2058 | 0.0000 |
|
98 |
-
| 0.0 | 50.0 | 2100 | 0.0000 |
|
99 |
-
| 0.0 | 51.0 | 2142 | 0.0000 |
|
100 |
-
| 0.0 | 52.0 | 2184 | 0.0000 |
|
101 |
-
| 0.0 | 53.0 | 2226 | 0.0000 |
|
102 |
-
| 0.0 | 54.0 | 2268 | 0.0000 |
|
103 |
-
| 0.0 | 55.0 | 2310 | 0.0000 |
|
104 |
-
| 0.0 | 56.0 | 2352 | 0.0000 |
|
105 |
-
| 0.0 | 57.0 | 2394 | 0.0000 |
|
106 |
-
| 0.0 | 58.0 | 2436 | 0.0000 |
|
107 |
-
| 0.0 | 59.0 | 2478 | 0.0000 |
|
108 |
-
| 0.0 | 60.0 | 2520 | 0.0000 |
|
109 |
-
| 0.0 | 61.0 | 2562 | 0.0000 |
|
110 |
-
| 0.0 | 62.0 | 2604 | 0.0000 |
|
111 |
-
| 0.0 | 63.0 | 2646 | 0.0000 |
|
112 |
-
| 0.0 | 64.0 | 2688 | 0.0000 |
|
113 |
-
| 0.0 | 65.0 | 2730 | 0.0000 |
|
114 |
-
| 0.0 | 66.0 | 2772 | 0.0000 |
|
115 |
-
| 0.0 | 67.0 | 2814 | 0.0000 |
|
116 |
-
| 0.0 | 68.0 | 2856 | 0.0000 |
|
117 |
-
| 0.0 | 69.0 | 2898 | 0.0000 |
|
118 |
-
| 0.0 | 70.0 | 2940 | 0.0000 |
|
119 |
-
| 0.0 | 71.0 | 2982 | 0.0000 |
|
120 |
-
| 0.0 | 72.0 | 3024 | 0.0000 |
|
121 |
-
| 0.0 | 73.0 | 3066 | 0.0000 |
|
122 |
-
| 0.0 | 74.0 | 3108 | 0.0000 |
|
123 |
-
| 0.0 | 75.0 | 3150 | 0.0000 |
|
124 |
-
| 0.0 | 76.0 | 3192 | 0.0000 |
|
125 |
-
| 0.0 | 77.0 | 3234 | 0.0000 |
|
126 |
-
| 0.0 | 78.0 | 3276 | 0.0000 |
|
127 |
-
| 0.0 | 79.0 | 3318 | 0.0000 |
|
128 |
-
| 0.0 | 80.0 | 3360 | 0.0000 |
|
129 |
-
| 0.0 | 81.0 | 3402 | 0.0000 |
|
130 |
-
| 0.0 | 82.0 | 3444 | 0.0000 |
|
131 |
-
| 0.0 | 83.0 | 3486 | 0.0000 |
|
132 |
-
| 0.0 | 84.0 | 3528 | 0.0000 |
|
133 |
-
| 0.0 | 85.0 | 3570 | 0.0000 |
|
134 |
-
| 0.0 | 86.0 | 3612 | 0.0000 |
|
135 |
-
| 0.0 | 87.0 | 3654 | 0.0000 |
|
136 |
-
| 0.0 | 88.0 | 3696 | 0.0000 |
|
137 |
-
| 0.0 | 89.0 | 3738 | 0.0000 |
|
138 |
-
| 0.0 | 90.0 | 3780 | 0.0000 |
|
139 |
-
| 0.0 | 91.0 | 3822 | 0.0000 |
|
140 |
-
| 0.0 | 92.0 | 3864 | 0.0000 |
|
141 |
-
| 0.0 | 93.0 | 3906 | 0.0000 |
|
142 |
-
| 0.0 | 94.0 | 3948 | 0.0000 |
|
143 |
-
| 0.0 | 95.0 | 3990 | 0.0000 |
|
144 |
-
| 0.0 | 96.0 | 4032 | 0.0000 |
|
145 |
-
| 0.0 | 97.0 | 4074 | 0.0000 |
|
146 |
-
| 0.0 | 98.0 | 4116 | 0.0000 |
|
147 |
-
| 0.0 | 99.0 | 4158 | 0.0000 |
|
148 |
-
| 0.0 | 100.0 | 4200 | 0.0000 |
|
149 |
|
150 |
|
151 |
### Framework versions
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 32
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
| No log | 1.0 | 42 | 0.0129 |
|
50 |
+
| No log | 2.0 | 84 | 0.0014 |
|
51 |
| No log | 3.0 | 126 | 0.0007 |
|
52 |
| No log | 4.0 | 168 | 0.0005 |
|
53 |
| No log | 5.0 | 210 | 0.0003 |
|
54 |
| No log | 6.0 | 252 | 0.0003 |
|
55 |
| No log | 7.0 | 294 | 0.0002 |
|
56 |
| No log | 8.0 | 336 | 0.0002 |
|
57 |
+
| No log | 9.0 | 378 | 0.0001 |
|
58 |
+
| No log | 10.0 | 420 | 0.0001 |
|
59 |
| No log | 11.0 | 462 | 0.0001 |
|
60 |
+
| 0.0161 | 12.0 | 504 | 0.0001 |
|
61 |
+
| 0.0161 | 13.0 | 546 | 0.0001 |
|
62 |
+
| 0.0161 | 14.0 | 588 | 0.0001 |
|
63 |
+
| 0.0161 | 15.0 | 630 | 0.0001 |
|
64 |
+
| 0.0161 | 16.0 | 672 | 0.0001 |
|
65 |
+
| 0.0161 | 17.0 | 714 | 0.0001 |
|
66 |
+
| 0.0161 | 18.0 | 756 | 0.0001 |
|
67 |
+
| 0.0161 | 19.0 | 798 | 0.0000 |
|
68 |
+
| 0.0161 | 20.0 | 840 | 0.0000 |
|
69 |
+
| 0.0161 | 21.0 | 882 | 0.0000 |
|
70 |
+
| 0.0161 | 22.0 | 924 | 0.0000 |
|
71 |
+
| 0.0161 | 23.0 | 966 | 0.0000 |
|
72 |
+
| 0.0 | 24.0 | 1008 | 0.0000 |
|
73 |
+
| 0.0 | 25.0 | 1050 | 0.0000 |
|
74 |
+
| 0.0 | 26.0 | 1092 | 0.0000 |
|
75 |
+
| 0.0 | 27.0 | 1134 | 0.0000 |
|
76 |
+
| 0.0 | 28.0 | 1176 | 0.0000 |
|
77 |
+
| 0.0 | 29.0 | 1218 | 0.0000 |
|
78 |
+
| 0.0 | 30.0 | 1260 | 0.0000 |
|
79 |
+
| 0.0 | 31.0 | 1302 | 0.0000 |
|
80 |
| 0.0 | 32.0 | 1344 | 0.0000 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
|
82 |
|
83 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3555504
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:481b649a7c35e013243c07a42f6fc614a934057148a010733ebfa8c12c31fad9
|
3 |
size 3555504
|
logs/events.out.tfevents.1717282943.llms-a100.324432.0
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 sha256:3270044c0306304edde66c827dec35d48ca031227fa7176f5b320c5e023f67a9
|
3 |
+
size 14363
|
logs/events.out.tfevents.1717285975.llms-a100.324432.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bf21050ec4e233d9876082ecd0f86989c6a7ab81943f8aa2402ed7154c25d19
|
3 |
+
size 359
|