Model save
Browse files- README.md +9 -9
- config.json +4 -2
- eval_loss_plot.png +0 -0
- eval_ndcg@25_plot.png +0 -0
- model.safetensors +1 -1
- train_loss_plot.png +0 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: -
|
20 |
-
- Ndcg: 0.
|
21 |
-
- Ndcg@25: 0.
|
22 |
-
- Precision@25: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -51,15 +51,15 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss
|
55 |
-
|
56 |
-
| -
|
57 |
-
| -
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
- Transformers 4.49.0
|
63 |
-
- Pytorch 2.
|
64 |
- Datasets 3.6.0
|
65 |
- Tokenizers 0.21.1
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: -289695770057323328.0000
|
20 |
+
- Ndcg: 0.9560
|
21 |
+
- Ndcg@25: 0.6207
|
22 |
+
- Precision@25: 0.2464
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Ndcg | Ndcg@25 | Precision@25 |
|
55 |
+
|:------------------------:|:------:|:----:|:------------------------:|:------:|:-------:|:------------:|
|
56 |
+
| -824219259923909888.0000 | 1.0 | 44 | -120189777058411312.0000 | 0.9555 | 0.2126 | 0.0 |
|
57 |
+
| -91157196780129488.0000 | 1.9711 | 86 | -289695770057323328.0000 | 0.9560 | 0.6207 | 0.2464 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
- Transformers 4.49.0
|
63 |
+
- Pytorch 2.6.0
|
64 |
- Datasets 3.6.0
|
65 |
- Tokenizers 0.21.1
|
config.json
CHANGED
@@ -1,11 +1,13 @@
|
|
1 |
{
|
|
|
2 |
"_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
|
|
9 |
"head_dim": 128,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
@@ -15924,7 +15926,7 @@
|
|
15924 |
"rope_theta": 1000000.0,
|
15925 |
"sliding_window": null,
|
15926 |
"tie_word_embeddings": false,
|
15927 |
-
"torch_dtype": "
|
15928 |
"transformers_version": "4.49.0",
|
15929 |
"use_cache": true,
|
15930 |
"vocab_size": 32768
|
|
|
1 |
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
"_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
4 |
"architectures": [
|
5 |
+
"MistralForCausalLM"
|
6 |
],
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
"eos_token_id": 2,
|
10 |
+
"ground_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
11 |
"head_dim": 128,
|
12 |
"hidden_act": "silu",
|
13 |
"hidden_size": 4096,
|
|
|
15926 |
"rope_theta": 1000000.0,
|
15927 |
"sliding_window": null,
|
15928 |
"tie_word_embeddings": false,
|
15929 |
+
"torch_dtype": "bfloat16",
|
15930 |
"transformers_version": "4.49.0",
|
15931 |
"use_cache": true,
|
15932 |
"vocab_size": 32768
|
eval_loss_plot.png
CHANGED
![]() |
![]() |
eval_ndcg@25_plot.png
CHANGED
![]() |
![]() |
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4323010659
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:447ef3af00bc298553b96416a20b9b05d450c52588ee3a4e274faecc870a6815
|
3 |
size 4323010659
|
train_loss_plot.png
CHANGED
![]() |
![]() |
training_args.bin
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:f28aac9705c5796bc9414dbec1ffbbcacc5bed2ae18f36b3f5117eafd1bd7aa5
|
3 |
+
size 5432
|