Hugging Face's logo

deb101
/
mistral-7b-instruct-v0.3-mimic4-adapt-l2r

Transformers
Safetensors
ltr_model
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files
xet
Community
deb101 commited on
Commit
4e4441b
·
verified ·
1 Parent(s): 1e76e17

Model save

Browse files
Files changed (6) hide show
  1. README.md +8 -8
  2. config.json +3 -2
  3. eval_loss_plot.png +0 -0
  4. eval_ndcg@25_plot.png +0 -0
  5. train_loss_plot.png +0 -0
  6. training_args.bin +1 -1
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: -289695770057323328.0000
20
- - Ndcg: 0.9560
21
- - Ndcg@25: 0.6207
22
- - Precision@25: 0.2464
23
 
24
  ## Model description
25
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
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
 
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: -377379303853489216.0000
20
+ - Ndcg: 0.9566
21
+ - Ndcg@25: 0.5389
22
+ - Precision@25: 0.2423
23
 
24
  ## Model description
25
 
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Ndcg | Ndcg@25 | Precision@25 |
55
+ |:-------------------------:|:------:|:----:|:------------------------:|:------:|:-------:|:------------:|
56
+ | -6819856770917832704.0000 | 1.0 | 44 | -289695770057323328.0000 | 0.9560 | 0.6207 | 0.2464 |
57
+ | -160735776926492256.0000 | 1.9711 | 86 | -377379303853489216.0000 | 0.9566 | 0.5389 | 0.2423 |
58
 
59
 
60
  ### Framework versions
config.json CHANGED
@@ -1,7 +1,8 @@
1
  {
 
2
  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
3
  "architectures": [
4
- "LTRModel"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
@@ -15925,7 +15926,7 @@
15925
  "rope_theta": 1000000.0,
15926
  "sliding_window": null,
15927
  "tie_word_embeddings": false,
15928
- "torch_dtype": "float32",
15929
  "transformers_version": "4.49.0",
15930
  "use_cache": true,
15931
  "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,
 
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
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:f28aac9705c5796bc9414dbec1ffbbcacc5bed2ae18f36b3f5117eafd1bd7aa5
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8ecf06721ad87ab8121f2db0c7f9e06711bbd37d7a94b1f2e0165aeb84b036
3
  size 5432