skarsa commited on
Commit
6701467
·
verified ·
1 Parent(s): 80d8934

Training in progress, step 24

Browse files
Files changed (26) hide show
  1. README.md +53 -0
  2. config.json +28 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. runs/Jan15_19-27-19_439725d22e93/events.out.tfevents.1736969240.439725d22e93.31.36 +3 -0
  6. runs/Jan15_19-28-05_439725d22e93/events.out.tfevents.1736969286.439725d22e93.31.37 +3 -0
  7. runs/Jan15_19-28-34_439725d22e93/events.out.tfevents.1736969315.439725d22e93.31.38 +3 -0
  8. runs/Jan15_19-29-19_439725d22e93/events.out.tfevents.1736969360.439725d22e93.31.39 +3 -0
  9. runs/Jan15_19-30-04_439725d22e93/events.out.tfevents.1736969405.439725d22e93.31.40 +3 -0
  10. runs/Jan15_19-30-33_439725d22e93/events.out.tfevents.1736969434.439725d22e93.31.41 +3 -0
  11. runs/Jan15_19-31-23_439725d22e93/events.out.tfevents.1736969484.439725d22e93.31.42 +3 -0
  12. runs/Jan15_19-32-07_439725d22e93/events.out.tfevents.1736969528.439725d22e93.31.43 +3 -0
  13. runs/Jan15_19-32-55_439725d22e93/events.out.tfevents.1736969576.439725d22e93.31.44 +3 -0
  14. runs/Jan15_19-33-39_439725d22e93/events.out.tfevents.1736969622.439725d22e93.31.45 +3 -0
  15. runs/Jan15_19-34-23_439725d22e93/events.out.tfevents.1736969664.439725d22e93.31.46 +3 -0
  16. runs/Jan15_19-35-08_439725d22e93/events.out.tfevents.1736969709.439725d22e93.31.47 +3 -0
  17. runs/Jan15_19-35-59_439725d22e93/events.out.tfevents.1736969760.439725d22e93.31.48 +3 -0
  18. runs/Jan15_19-36-46_439725d22e93/events.out.tfevents.1736969807.439725d22e93.31.49 +3 -0
  19. runs/Jan15_19-37-33_439725d22e93/events.out.tfevents.1736969854.439725d22e93.31.50 +3 -0
  20. runs/Jan15_19-38-19_439725d22e93/events.out.tfevents.1736969900.439725d22e93.31.51 +3 -0
  21. runs/Jan15_19-39-02_439725d22e93/events.out.tfevents.1736969943.439725d22e93.31.52 +3 -0
  22. special_tokens_map.json +15 -0
  23. tokenizer.json +0 -0
  24. tokenizer_config.json +58 -0
  25. training_args.bin +3 -0
  26. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: roberta-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: babe_topic_subsamples_model_alpha_0_1_idx_1
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # babe_topic_subsamples_model_alpha_0_1_idx_1
16
+
17
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 64
38
+ - eval_batch_size: 64
39
+ - seed: 42
40
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.47.0
51
+ - Pytorch 2.5.1+cu121
52
+ - Datasets 3.2.0
53
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.47.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86d47599ece9e36a8d2dbed89a0b1622f830f003f33f4f684ee95c8ab905461
3
+ size 498612824
runs/Jan15_19-27-19_439725d22e93/events.out.tfevents.1736969240.439725d22e93.31.36 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b876f4850c68738b5385b8107f45fc7f6adb2b48e11e3ee3482afee999b66da
3
+ size 5559
runs/Jan15_19-28-05_439725d22e93/events.out.tfevents.1736969286.439725d22e93.31.37 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d232e73f303f2f85971d743c8b0c40ecb928076fc303079caf9cfdaacf2f9a7
3
+ size 5559
runs/Jan15_19-28-34_439725d22e93/events.out.tfevents.1736969315.439725d22e93.31.38 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39379fbc991c74f396ff10abdf130f0830b1d2fa6b2be4d16554926f5a0a7b3d
3
+ size 5559
runs/Jan15_19-29-19_439725d22e93/events.out.tfevents.1736969360.439725d22e93.31.39 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf28f18f0ad22a43c0d3902a7865b7a5eae19fa85c815e81ef4ba35ea24538c2
3
+ size 5559
runs/Jan15_19-30-04_439725d22e93/events.out.tfevents.1736969405.439725d22e93.31.40 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ce23bf0d503f17236e6a2a0549bac862239d346dcc8c44f730d7785c5db643
3
+ size 5559
runs/Jan15_19-30-33_439725d22e93/events.out.tfevents.1736969434.439725d22e93.31.41 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:003853571ef87a7f66679af0ef9af75cfd5b453bbac86cd7a94754f8fc0f6fd0
3
+ size 5559
runs/Jan15_19-31-23_439725d22e93/events.out.tfevents.1736969484.439725d22e93.31.42 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34092c829374a764c5e7491bb138922443faec74d05d3f22a46d38dff8ed6ad3
3
+ size 5557
runs/Jan15_19-32-07_439725d22e93/events.out.tfevents.1736969528.439725d22e93.31.43 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:570ba3e7a84cb915d3b579abaa507df93730274b66740eacebbede6474333113
3
+ size 5557
runs/Jan15_19-32-55_439725d22e93/events.out.tfevents.1736969576.439725d22e93.31.44 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa68aac94199844677554d21ccbf484f618780baf77de66aee3a44ae54f6918a
3
+ size 5557
runs/Jan15_19-33-39_439725d22e93/events.out.tfevents.1736969622.439725d22e93.31.45 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e2ad0b256587fed301851d49f71076e00f323e1932256c4b711f7149bc31d40
3
+ size 5557
runs/Jan15_19-34-23_439725d22e93/events.out.tfevents.1736969664.439725d22e93.31.46 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c05b38da0ee0f8ebd682ba23044c917d225d012915c5604475dc421a77d8a33
3
+ size 5557
runs/Jan15_19-35-08_439725d22e93/events.out.tfevents.1736969709.439725d22e93.31.47 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79022fe8a66e24d05c8ba628cdc3a2195fe8cb5a7d96874d216ffc80d664edca
3
+ size 5557
runs/Jan15_19-35-59_439725d22e93/events.out.tfevents.1736969760.439725d22e93.31.48 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a0a5948ecf551def11a2db04d29e45331801d6fdfdc5db23036164996a561d
3
+ size 5557
runs/Jan15_19-36-46_439725d22e93/events.out.tfevents.1736969807.439725d22e93.31.49 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a0b35fec6253531fd9b86bdaa37c138717b22f3f5918897a8ce351a2638cf2
3
+ size 5557
runs/Jan15_19-37-33_439725d22e93/events.out.tfevents.1736969854.439725d22e93.31.50 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f5f572d122db8304aefdb3f8ee6cb50fdac3911f435ae25c1b613703ae44de
3
+ size 5557
runs/Jan15_19-38-19_439725d22e93/events.out.tfevents.1736969900.439725d22e93.31.51 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78314a2cbcac22a2bfffe84bd87e1518318132fa7a5c41e0155729c14bf704c0
3
+ size 5555
runs/Jan15_19-39-02_439725d22e93/events.out.tfevents.1736969943.439725d22e93.31.52 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f85a69fb71ab1d35651a4397dc8c787d86751489a4c3906b5e7e55b085b94e9
3
+ size 5555
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade37c0e99ad18df5a4b97d4c5018c5de63969e3a12def766e8806907d4b5f81
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff