Commit
•
315c4f4
1
Parent(s):
7d70729
ArpitaAeries/mistral-instruct-generation
Browse files- README.md +11 -11
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- runs/May21_11-59-13_vm/events.out.tfevents.1716297485.vm.56490.0 +3 -0
- tokenizer.json +2 -16
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:------:|:----:|:---------------:|
|
53 |
-
| 2.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
56 |
-
| 1.6579 | 0.5556 | 20 | 1.
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
-
| 1.
|
62 |
-
| 1.
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.1218
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:------:|:----:|:---------------:|
|
53 |
+
| 2.0253 | 0.1389 | 5 | 2.0089 |
|
54 |
+
| 1.94 | 0.2778 | 10 | 1.9158 |
|
55 |
+
| 1.8034 | 0.4167 | 15 | 1.7803 |
|
56 |
+
| 1.6579 | 0.5556 | 20 | 1.6171 |
|
57 |
+
| 1.5197 | 0.6944 | 25 | 1.4960 |
|
58 |
+
| 1.4063 | 0.8333 | 30 | 1.3825 |
|
59 |
+
| 1.3019 | 0.9722 | 35 | 1.2824 |
|
60 |
+
| 1.2145 | 1.1111 | 40 | 1.2010 |
|
61 |
+
| 1.1549 | 1.25 | 45 | 1.1446 |
|
62 |
+
| 1.1269 | 1.3889 | 50 | 1.1218 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,14 +20,14 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"gate_proj",
|
24 |
-
"o_proj",
|
25 |
"up_proj",
|
26 |
"lm_head",
|
27 |
-
"k_proj",
|
28 |
-
"v_proj",
|
29 |
"down_proj",
|
30 |
-
"
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"v_proj",
|
26 |
"gate_proj",
|
|
|
27 |
"up_proj",
|
28 |
"lm_head",
|
|
|
|
|
29 |
"down_proj",
|
30 |
+
"o_proj"
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 751667752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a771b83c1c5bd08ea119cc6427e6c8135a5f966aafd8be28febf86ae437448dd
|
3 |
size 751667752
|
runs/May21_11-59-13_vm/events.out.tfevents.1716297485.vm.56490.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:833d36636a9d928d62b085ac52e24f1d7ebcc6cf081fd12aa7bfc968e7a1cf7a
|
3 |
+
size 18789
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 512,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 512
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 2,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "</s>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b51b3fc93d654563abb6136b1926b7f2268f48b6215bae60a38ce5bb32ced7d
|
3 |
size 5112
|