netapy commited on
Commit
6595278
1 Parent(s): bbe946c

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: solon-large-06-BIG
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # solon-large-06-BIG
13
+
14
+ This model was trained from scratch on an unknown dataset.
15
+
16
+ ## Model description
17
+
18
+ More information needed
19
+
20
+ ## Intended uses & limitations
21
+
22
+ More information needed
23
+
24
+ ## Training and evaluation data
25
+
26
+ More information needed
27
+
28
+ ## Training procedure
29
+
30
+ ### Training hyperparameters
31
+
32
+ The following hyperparameters were used during training:
33
+ - learning_rate: 1e-06
34
+ - train_batch_size: 32
35
+ - eval_batch_size: 8
36
+ - seed: 42
37
+ - distributed_type: multi-GPU
38
+ - num_devices: 4
39
+ - total_train_batch_size: 128
40
+ - total_eval_batch_size: 32
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 20.0
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.35.2
53
+ - Pytorch 2.1.1+cu121
54
+ - Datasets 2.3.2
55
+ - Tokenizers 0.15.0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "solon-large-06-BIG/checkpoint-6000",
3
  "architectures": [
4
  "XLMRobertaModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "solon-large-06-BIG",
3
  "architectures": [
4
  "XLMRobertaModel"
5
  ],
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.35.2",
5
+ "pytorch": "2.1.1+cu121"
6
+ }
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebecd3087208e74c7922e0efbc734f910e366b06634a005df4fe40dab3d3a4c8
3
  size 2239607176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08b024ee2b4cf4e2364ba1c4f9ea763764d6ea7081e303b836dc19bd5a3a8b1
3
  size 2239607176
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
runs/Dec09_10-01-38_ordalie-8x-a100/events.out.tfevents.1702116183.ordalie-8x-a100.19338.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cea7262b5033052bffb5cf143752328eeca21fbe977580fc218cc6629ab5f449
3
- size 99692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc0838a43d400c2e752b1129f2122e3468a21ba5a04d049d069187621f3e8d6e
3
+ size 147303
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6710678b12670bc442b99edc952c4d996ae309a7020c1fa0096dd245c2faf790
3
+ size 17082821