cnatale/Mistral-7B-Instruct-v0.1-Txt-2-Presto-SQL
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -53,12 +53,12 @@ The following hyperparameters were used during training:
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6143
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|
|
56 |
+
| 0.8588 | 1.33 | 20 | 0.7602 |
|
57 |
+
| 0.6494 | 2.67 | 40 | 0.6310 |
|
58 |
+
| 0.5549 | 4.0 | 60 | 0.5919 |
|
59 |
+
| 0.4855 | 5.33 | 80 | 0.6051 |
|
60 |
+
| 0.4283 | 6.67 | 100 | 0.6050 |
|
61 |
+
| 0.3904 | 8.0 | 120 | 0.6143 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109069176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1abbe85561b652b5746f919cb017f565519376439ecfe3740d496dfe8c3dd600
|
3 |
size 109069176
|
runs/Jan02_00-57-36_c16c6898537f/events.out.tfevents.1704157057.c16c6898537f.1158.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b6b6de26b6da2df5c2dbbad3640481fa529143612092a932311e966b30f6146
|
3 |
+
size 8617
|
special_tokens_map.json
CHANGED
@@ -13,6 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "</s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -33,7 +33,7 @@
|
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
-
"pad_token":
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31696b5a25f77c15b40627919ea506fa6982e8d8c8ad696eecdb750ddaf0ac09
|
3 |
size 4728
|