Hugging Face's logo

oneryalcin
/
static-embedding-chess

Sentence Similarity
sentence-transformers
Safetensors
English
static-embedding
chess
retrieval
exploratory
Model card Files
xet
 Community
oneryalcin commited on
Commit
b32a9d1
·
verified ·
1 Parent(s): 9b00e17

Training in progress, step 300

Browse files
Files changed (3) hide show
  1. README.md +26 -16
  2. eval/Information-Retrieval_evaluation_chess-ir_results.csv +1 -0
  3. model.safetensors +1 -1
README.md CHANGED
@@ -67,28 +67,28 @@ model-index:
67
  value: 0.025
68
  name: Cosine Accuracy@1
69
  - type: cosine_accuracy@10
70
- value: 0.14
71
  name: Cosine Accuracy@10
72
  - type: cosine_precision@1
73
  value: 0.025
74
  name: Cosine Precision@1
75
  - type: cosine_precision@10
76
- value: 0.017
77
  name: Cosine Precision@10
78
  - type: cosine_recall@1
79
  value: 0.008333333333333333
80
  name: Cosine Recall@1
81
  - type: cosine_recall@10
82
- value: 0.056666666666666664
83
  name: Cosine Recall@10
84
  - type: cosine_ndcg@10
85
- value: 0.037406426241984
86
  name: Cosine Ndcg@10
87
  - type: cosine_mrr@10
88
- value: 0.049240079365079355
89
  name: Cosine Mrr@10
90
  - type: cosine_map@100
91
- value: 0.02874627448743367
92
  name: Cosine Map@100
93
  ---
94
 
@@ -155,7 +155,7 @@ print(query_embeddings.shape, document_embeddings.shape)
155
  # Get the similarity scores for the embeddings
156
  similarities = model.similarity(query_embeddings, document_embeddings)
157
  print(similarities)
158
- # tensor([[ 0.9411, -0.1930, 0.3964]])
159
  ```
160
  <!--
161
  ### Direct Usage (Transformers)
@@ -193,14 +193,14 @@ You can finetune this model on your own dataset.
193
  | Metric | Value |
194
  |:--------------------|:-----------|
195
  | cosine_accuracy@1 | 0.025 |
196
- | cosine_accuracy@10 | 0.14 |
197
  | cosine_precision@1 | 0.025 |
198
- | cosine_precision@10 | 0.017 |
199
  | cosine_recall@1 | 0.0083 |
200
- | cosine_recall@10 | 0.0567 |
201
- | **cosine_ndcg@10** | **0.0374** |
202
- | cosine_mrr@10 | 0.0492 |
203
- | cosine_map@100 | 0.0287 |
204
 
205
  <!--
206
  ## Bias, Risks and Limitations
@@ -425,12 +425,22 @@ You can finetune this model on your own dataset.
425
  | 0.0843 | 240 | 1.3213 | - |
426
  | 0.0860 | 245 | 1.3127 | - |
427
  | 0.0878 | 250 | 1.2801 | 0.0374 |
 
 
 
 
 
 
 
 
 
 
428
 
429
 
430
  ### Training Time
431
- - **Training**: 21.2 seconds
432
- - **Evaluation**: 0.2 seconds
433
- - **Total**: 21.5 seconds
434
 
435
  ### Framework Versions
436
  - Python: 3.12.10
 
67
  value: 0.025
68
  name: Cosine Accuracy@1
69
  - type: cosine_accuracy@10
70
+ value: 0.125
71
  name: Cosine Accuracy@10
72
  - type: cosine_precision@1
73
  value: 0.025
74
  name: Cosine Precision@1
75
  - type: cosine_precision@10
76
+ value: 0.016
77
  name: Cosine Precision@10
78
  - type: cosine_recall@1
79
  value: 0.008333333333333333
80
  name: Cosine Recall@1
81
  - type: cosine_recall@10
82
+ value: 0.05333333333333333
83
  name: Cosine Recall@10
84
  - type: cosine_ndcg@10
85
+ value: 0.03923902062478621
86
  name: Cosine Ndcg@10
87
  - type: cosine_mrr@10
88
+ value: 0.053103174603174604
89
  name: Cosine Mrr@10
90
  - type: cosine_map@100
91
+ value: 0.03190843674305716
92
  name: Cosine Map@100
93
  ---
94
 
 
155
  # Get the similarity scores for the embeddings
156
  similarities = model.similarity(query_embeddings, document_embeddings)
157
  print(similarities)
158
+ # tensor([[ 0.9505, -0.1987, 0.4045]])
159
  ```
160
  <!--
161
  ### Direct Usage (Transformers)
 
193
  | Metric | Value |
194
  |:--------------------|:-----------|
195
  | cosine_accuracy@1 | 0.025 |
196
+ | cosine_accuracy@10 | 0.125 |
197
  | cosine_precision@1 | 0.025 |
198
+ | cosine_precision@10 | 0.016 |
199
  | cosine_recall@1 | 0.0083 |
200
+ | cosine_recall@10 | 0.0533 |
201
+ | **cosine_ndcg@10** | **0.0392** |
202
+ | cosine_mrr@10 | 0.0531 |
203
+ | cosine_map@100 | 0.0319 |
204
 
205
  <!--
206
  ## Bias, Risks and Limitations
 
425
  | 0.0843 | 240 | 1.3213 | - |
426
  | 0.0860 | 245 | 1.3127 | - |
427
  | 0.0878 | 250 | 1.2801 | 0.0374 |
428
+ | 0.0895 | 255 | 1.2940 | - |
429
+ | 0.0913 | 260 | 1.3423 | - |
430
+ | 0.0930 | 265 | 1.2860 | - |
431
+ | 0.0948 | 270 | 1.3022 | - |
432
+ | 0.0966 | 275 | 1.3040 | - |
433
+ | 0.0983 | 280 | 1.2921 | - |
434
+ | 0.1001 | 285 | 1.2940 | - |
435
+ | 0.1018 | 290 | 1.3064 | - |
436
+ | 0.1036 | 295 | 1.3042 | - |
437
+ | 0.1053 | 300 | 1.3058 | 0.0392 |
438
 
439
 
440
  ### Training Time
441
+ - **Training**: 25.3 seconds
442
+ - **Evaluation**: 0.3 seconds
443
+ - **Total**: 25.5 seconds
444
 
445
  ### Framework Versions
446
  - Python: 3.12.10
eval/Information-Retrieval_evaluation_chess-ir_results.csv CHANGED
@@ -4,3 +4,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@10,cosine-Precision@1,cosine-Recal
4
  0.05266853932584269,150,0.02,0.12,0.02,0.006666666666666666,0.0155,0.051666666666666666,0.04391468253968253,0.034539315152376744,0.02851338765635309
5
  0.0702247191011236,200,0.03,0.16,0.03,0.009999999999999998,0.02,0.06666666666666667,0.05857142857142858,0.045080933582823335,0.033163497941181515
6
  0.0877808988764045,250,0.025,0.14,0.025,0.008333333333333333,0.017,0.056666666666666664,0.049240079365079355,0.037406426241984,0.02874627448743367
 
 
4
  0.05266853932584269,150,0.02,0.12,0.02,0.006666666666666666,0.0155,0.051666666666666666,0.04391468253968253,0.034539315152376744,0.02851338765635309
5
  0.0702247191011236,200,0.03,0.16,0.03,0.009999999999999998,0.02,0.06666666666666667,0.05857142857142858,0.045080933582823335,0.033163497941181515
6
  0.0877808988764045,250,0.025,0.14,0.025,0.008333333333333333,0.017,0.056666666666666664,0.049240079365079355,0.037406426241984,0.02874627448743367
7
+ 0.10533707865168539,300,0.025,0.125,0.025,0.008333333333333333,0.016,0.05333333333333333,0.053103174603174604,0.03923902062478621,0.03190843674305716
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6414613fb87664a043eac994032609e6a48c5affbe464c8bb279f06170c4aeb2
3
  size 4343904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9765f24fcf2a3c67e7e6402e8f6453489a27ae2b99d12929d135e4886f7605e
3
  size 4343904