Commit
•
ed69064
1
Parent(s):
901c131
Model save
Browse files- README.md +6 -6
- adapter_model.safetensors +1 -1
- all_results.json +7 -7
- eval_results.json +4 -4
- runs/Dec14_13-56-05_s4311/events.out.tfevents.1702562244.s4311.817937.0 +3 -0
- runs/Dec14_13-56-05_s4311/events.out.tfevents.1702566386.s4311.817937.1 +3 -0
- train_results.json +3 -3
- trainer_state.json +43 -43
- training_args.bin +1 -1
README.md
CHANGED
@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
-
| 1.7095 | 0.09 | 1 | 1.
|
53 |
| 1.7095 | 1.07 | 2 | 1.6854 |
|
54 |
| 1.7095 | 2.06 | 3 | 1.6635 |
|
55 |
-
| 1.7095 | 3.04 | 4 | 1.
|
56 |
-
| 1.6715 | 4.02 | 5 | 1.
|
57 |
| 1.6715 | 5.1 | 7 | 1.5584 |
|
58 |
-
| 1.6715 | 6.08 | 8 | 1.
|
59 |
-
| 1.6715 | 7.06 | 9 | 1.
|
60 |
-
| 1.5588 | 8.05 | 10 | 1.
|
61 |
| 1.5588 | 9.03 | 11 | 1.4756 |
|
62 |
|
63 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 1.7095 | 0.09 | 1 | 1.7015 |
|
53 |
| 1.7095 | 1.07 | 2 | 1.6854 |
|
54 |
| 1.7095 | 2.06 | 3 | 1.6635 |
|
55 |
+
| 1.7095 | 3.04 | 4 | 1.6377 |
|
56 |
+
| 1.6715 | 4.02 | 5 | 1.6106 |
|
57 |
| 1.6715 | 5.1 | 7 | 1.5584 |
|
58 |
+
| 1.6715 | 6.08 | 8 | 1.5344 |
|
59 |
+
| 1.6715 | 7.06 | 9 | 1.5132 |
|
60 |
+
| 1.5588 | 8.05 | 10 | 1.4933 |
|
61 |
| 1.5588 | 9.03 | 11 | 1.4756 |
|
62 |
|
63 |
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218138576
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:666cc01e681b40ccae20914c7fad0fdcd73f72ed3f8d6b3d3d5f94c4575a253e
|
3 |
size 218138576
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 9.03,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 6.
|
5 |
"eval_samples": 294,
|
6 |
-
"eval_samples_per_second": 46.
|
7 |
-
"eval_steps_per_second": 5.
|
8 |
-
"train_loss": 1.
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 5895,
|
11 |
-
"train_samples_per_second": 14.
|
12 |
"train_steps_per_second": 0.027
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 9.03,
|
3 |
+
"eval_loss": 1.4756207466125488,
|
4 |
+
"eval_runtime": 6.3444,
|
5 |
"eval_samples": 294,
|
6 |
+
"eval_samples_per_second": 46.34,
|
7 |
+
"eval_steps_per_second": 5.832,
|
8 |
+
"train_loss": 1.7142409628087825,
|
9 |
+
"train_runtime": 4135.8024,
|
10 |
"train_samples": 5895,
|
11 |
+
"train_samples_per_second": 14.254,
|
12 |
"train_steps_per_second": 0.027
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 9.03,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 6.
|
5 |
"eval_samples": 294,
|
6 |
-
"eval_samples_per_second": 46.
|
7 |
-
"eval_steps_per_second": 5.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 9.03,
|
3 |
+
"eval_loss": 1.4756207466125488,
|
4 |
+
"eval_runtime": 6.3444,
|
5 |
"eval_samples": 294,
|
6 |
+
"eval_samples_per_second": 46.34,
|
7 |
+
"eval_steps_per_second": 5.832
|
8 |
}
|
runs/Dec14_13-56-05_s4311/events.out.tfevents.1702562244.s4311.817937.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e13bceaa2d273b3b12db226f49a3c79e6f99213d1bbb2e09a5be1614520450aa
|
3 |
+
size 7724
|
runs/Dec14_13-56-05_s4311/events.out.tfevents.1702566386.s4311.817937.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6655036fa20dec055f217bb8032aa555a529d2f754efb3e8a781fcff26d559ac
|
3 |
+
size 354
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 9.03,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 5895,
|
6 |
-
"train_samples_per_second": 14.
|
7 |
"train_steps_per_second": 0.027
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 9.03,
|
3 |
+
"train_loss": 1.7142409628087825,
|
4 |
+
"train_runtime": 4135.8024,
|
5 |
"train_samples": 5895,
|
6 |
+
"train_samples_per_second": 14.254,
|
7 |
"train_steps_per_second": 0.027
|
8 |
}
|
trainer_state.json
CHANGED
@@ -16,34 +16,34 @@
|
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.09,
|
19 |
-
"eval_loss": 1.
|
20 |
-
"eval_runtime": 6.
|
21 |
-
"eval_samples_per_second": 46.
|
22 |
-
"eval_steps_per_second": 5.
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.07,
|
27 |
-
"eval_loss": 1.
|
28 |
-
"eval_runtime": 6.
|
29 |
-
"eval_samples_per_second": 46.
|
30 |
-
"eval_steps_per_second": 5.
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 2.06,
|
35 |
-
"eval_loss": 1.
|
36 |
-
"eval_runtime": 6.
|
37 |
-
"eval_samples_per_second": 46.
|
38 |
-
"eval_steps_per_second": 5.
|
39 |
"step": 3
|
40 |
},
|
41 |
{
|
42 |
"epoch": 3.04,
|
43 |
-
"eval_loss": 1.
|
44 |
-
"eval_runtime": 6.
|
45 |
-
"eval_samples_per_second": 46.
|
46 |
-
"eval_steps_per_second": 5.
|
47 |
"step": 4
|
48 |
},
|
49 |
{
|
@@ -54,34 +54,34 @@
|
|
54 |
},
|
55 |
{
|
56 |
"epoch": 4.02,
|
57 |
-
"eval_loss": 1.
|
58 |
-
"eval_runtime": 6.
|
59 |
-
"eval_samples_per_second": 46.
|
60 |
-
"eval_steps_per_second": 5.
|
61 |
"step": 5
|
62 |
},
|
63 |
{
|
64 |
"epoch": 5.1,
|
65 |
-
"eval_loss": 1.
|
66 |
-
"eval_runtime": 6.
|
67 |
-
"eval_samples_per_second": 46.
|
68 |
-
"eval_steps_per_second": 5.
|
69 |
"step": 7
|
70 |
},
|
71 |
{
|
72 |
"epoch": 6.08,
|
73 |
-
"eval_loss": 1.
|
74 |
-
"eval_runtime": 6.
|
75 |
-
"eval_samples_per_second": 46.
|
76 |
-
"eval_steps_per_second": 5.
|
77 |
"step": 8
|
78 |
},
|
79 |
{
|
80 |
"epoch": 7.06,
|
81 |
-
"eval_loss": 1.
|
82 |
-
"eval_runtime": 6.
|
83 |
-
"eval_samples_per_second": 46.
|
84 |
-
"eval_steps_per_second": 5.
|
85 |
"step": 9
|
86 |
},
|
87 |
{
|
@@ -92,27 +92,27 @@
|
|
92 |
},
|
93 |
{
|
94 |
"epoch": 8.05,
|
95 |
-
"eval_loss": 1.
|
96 |
-
"eval_runtime": 6.
|
97 |
-
"eval_samples_per_second": 46.
|
98 |
-
"eval_steps_per_second": 5.
|
99 |
"step": 10
|
100 |
},
|
101 |
{
|
102 |
"epoch": 9.03,
|
103 |
-
"eval_loss": 1.
|
104 |
-
"eval_runtime": 6.
|
105 |
-
"eval_samples_per_second": 46.
|
106 |
-
"eval_steps_per_second": 5.
|
107 |
"step": 11
|
108 |
},
|
109 |
{
|
110 |
"epoch": 9.03,
|
111 |
"step": 11,
|
112 |
"total_flos": 5.3091621472200294e+17,
|
113 |
-
"train_loss": 1.
|
114 |
-
"train_runtime":
|
115 |
-
"train_samples_per_second": 14.
|
116 |
"train_steps_per_second": 0.027
|
117 |
}
|
118 |
],
|
|
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.09,
|
19 |
+
"eval_loss": 1.701454997062683,
|
20 |
+
"eval_runtime": 6.3744,
|
21 |
+
"eval_samples_per_second": 46.122,
|
22 |
+
"eval_steps_per_second": 5.804,
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.07,
|
27 |
+
"eval_loss": 1.6854428052902222,
|
28 |
+
"eval_runtime": 6.363,
|
29 |
+
"eval_samples_per_second": 46.204,
|
30 |
+
"eval_steps_per_second": 5.815,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 2.06,
|
35 |
+
"eval_loss": 1.6634844541549683,
|
36 |
+
"eval_runtime": 6.3663,
|
37 |
+
"eval_samples_per_second": 46.181,
|
38 |
+
"eval_steps_per_second": 5.812,
|
39 |
"step": 3
|
40 |
},
|
41 |
{
|
42 |
"epoch": 3.04,
|
43 |
+
"eval_loss": 1.6377184391021729,
|
44 |
+
"eval_runtime": 6.3346,
|
45 |
+
"eval_samples_per_second": 46.412,
|
46 |
+
"eval_steps_per_second": 5.841,
|
47 |
"step": 4
|
48 |
},
|
49 |
{
|
|
|
54 |
},
|
55 |
{
|
56 |
"epoch": 4.02,
|
57 |
+
"eval_loss": 1.6106265783309937,
|
58 |
+
"eval_runtime": 6.3433,
|
59 |
+
"eval_samples_per_second": 46.348,
|
60 |
+
"eval_steps_per_second": 5.833,
|
61 |
"step": 5
|
62 |
},
|
63 |
{
|
64 |
"epoch": 5.1,
|
65 |
+
"eval_loss": 1.5584189891815186,
|
66 |
+
"eval_runtime": 6.3627,
|
67 |
+
"eval_samples_per_second": 46.206,
|
68 |
+
"eval_steps_per_second": 5.815,
|
69 |
"step": 7
|
70 |
},
|
71 |
{
|
72 |
"epoch": 6.08,
|
73 |
+
"eval_loss": 1.5343831777572632,
|
74 |
+
"eval_runtime": 6.3403,
|
75 |
+
"eval_samples_per_second": 46.37,
|
76 |
+
"eval_steps_per_second": 5.836,
|
77 |
"step": 8
|
78 |
},
|
79 |
{
|
80 |
"epoch": 7.06,
|
81 |
+
"eval_loss": 1.5131820440292358,
|
82 |
+
"eval_runtime": 6.3297,
|
83 |
+
"eval_samples_per_second": 46.448,
|
84 |
+
"eval_steps_per_second": 5.845,
|
85 |
"step": 9
|
86 |
},
|
87 |
{
|
|
|
92 |
},
|
93 |
{
|
94 |
"epoch": 8.05,
|
95 |
+
"eval_loss": 1.4932821989059448,
|
96 |
+
"eval_runtime": 6.3196,
|
97 |
+
"eval_samples_per_second": 46.522,
|
98 |
+
"eval_steps_per_second": 5.855,
|
99 |
"step": 10
|
100 |
},
|
101 |
{
|
102 |
"epoch": 9.03,
|
103 |
+
"eval_loss": 1.4755805730819702,
|
104 |
+
"eval_runtime": 6.3502,
|
105 |
+
"eval_samples_per_second": 46.298,
|
106 |
+
"eval_steps_per_second": 5.827,
|
107 |
"step": 11
|
108 |
},
|
109 |
{
|
110 |
"epoch": 9.03,
|
111 |
"step": 11,
|
112 |
"total_flos": 5.3091621472200294e+17,
|
113 |
+
"train_loss": 1.7142409628087825,
|
114 |
+
"train_runtime": 4135.8024,
|
115 |
+
"train_samples_per_second": 14.254,
|
116 |
"train_steps_per_second": 0.027
|
117 |
}
|
118 |
],
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82f9cbd5ae020148e5023e8a94238eb6d948e2533fd584833fd423ac94f00345
|
3 |
size 4664
|