Model save

README.md

@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: -398032279857701120.0000
-- Ndcg: 0.9570
-- Ndcg@25: 0.6865
-- Precision@25: 0.5943
+- Loss: -289695770057323328.0000
+- Ndcg: 0.9560
+- Ndcg@25: 0.6207
+- Precision@25: 0.2464
 
 ## Model description
 
@@ -51,15 +51,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss             | Epoch  | Step | Validation Loss          | Ndcg   | Ndcg@25 | Precision@25 |
-|:-------------------------:|:------:|:----:|:------------------------:|:------:|:-------:|:------------:|
-| -6942806799963652096.0000 | 1.0    | 44   | -380035817867927296.0000 | 0.9569 | 0.7741  | 0.4871       |
-| -194661386872160256.0000  | 1.9711 | 86   | -398032279857701120.0000 | 0.9570 | 0.6865  | 0.5943       |
+| Training Loss            | Epoch  | Step | Validation Loss          | Ndcg   | Ndcg@25 | Precision@25 |
+|:------------------------:|:------:|:----:|:------------------------:|:------:|:-------:|:------------:|
+| -824219259923909888.0000 | 1.0    | 44   | -120189777058411312.0000 | 0.9555 | 0.2126  | 0.0          |
+| -91157196780129488.0000  | 1.9711 | 86   | -289695770057323328.0000 | 0.9560 | 0.6207  | 0.2464       |
 
 
 ### Framework versions
 
 - Transformers 4.49.0
-- Pytorch 2.7.1+cu126
+- Pytorch 2.6.0
 - Datasets 3.6.0
 - Tokenizers 0.21.1

config.json

@@ -1,11 +1,13 @@
 {
+  "_attn_implementation_autoset": true,
   "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
   "architectures": [
-    "LTRModel"
+    "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "ground_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
@@ -15924,7 +15926,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
   "use_cache": true,
   "vocab_size": 32768

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fbcd969a528ea265d3e0a119126666d4f717cfde9636af938da134a6727a9af
+oid sha256:447ef3af00bc298553b96416a20b9b05d450c52588ee3a4e274faecc870a6815
 size 4323010659

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb3360639518e9a55108617cf345932de4c931395fe7e3d9217af81f42a449a
-size 5905
+oid sha256:f28aac9705c5796bc9414dbec1ffbbcacc5bed2ae18f36b3f5117eafd1bd7aa5
+size 5432