Mikhail Biriuchinskii commited on
Commit
f032d29
1 Parent(s): 523a1f4

sarcasm_BARThez

Browse files
README.md CHANGED
@@ -1,5 +1,57 @@
1
  ---
2
- language:
3
- - fr
4
- - en
5
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: moussaKam/barthez-orangesum-abstract
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: sarcasm_BARThez
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # sarcasm_BARThez
15
+
16
+ This model is a fine-tuned version of [moussaKam/barthez-orangesum-abstract](https://huggingface.co/moussaKam/barthez-orangesum-abstract) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 7.9423
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 1
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 11 | 7.9423 |
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.38.1
55
+ - Pytorch 2.1.0+cu121
56
+ - Datasets 2.17.1
57
+ - Tokenizers 0.15.2
config.json CHANGED
@@ -1,4 +1,4 @@
1
- MBartConfig {
2
  "_name_or_path": "moussaKam/barthez-orangesum-abstract",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
@@ -39,10 +39,12 @@ MBartConfig {
39
  "LABEL_1": 1,
40
  "LABEL_2": 2
41
  },
 
42
  "max_position_embeddings": 1024,
43
  "model_type": "mbart",
44
  "normalize_before": true,
45
  "normalize_embedding": true,
 
46
  "num_hidden_layers": 6,
47
  "pad_token_id": 1,
48
  "scale_embedding": false,
@@ -58,6 +60,7 @@ MBartConfig {
58
  }
59
  },
60
  "tokenizer_class": "BarthezTokenizer",
 
61
  "transformers_version": "4.38.1",
62
  "use_cache": true,
63
  "vocab_size": 50002
 
1
+ {
2
  "_name_or_path": "moussaKam/barthez-orangesum-abstract",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
 
39
  "LABEL_1": 1,
40
  "LABEL_2": 2
41
  },
42
+ "max_new_tokens": 30,
43
  "max_position_embeddings": 1024,
44
  "model_type": "mbart",
45
  "normalize_before": true,
46
  "normalize_embedding": true,
47
+ "num_beams": 2,
48
  "num_hidden_layers": 6,
49
  "pad_token_id": 1,
50
  "scale_embedding": false,
 
60
  }
61
  },
62
  "tokenizer_class": "BarthezTokenizer",
63
+ "torch_dtype": "float32",
64
  "transformers_version": "4.38.1",
65
  "use_cache": true,
66
  "vocab_size": 50002
generation_config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
2
- "do_sample": true,
 
3
  "eos_token_id": 2,
 
4
  "max_new_tokens": 30,
5
  "num_beams": 2,
 
6
  "transformers_version": "4.38.1"
7
  }
 
1
  {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
  "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
  "max_new_tokens": 30,
7
  "num_beams": 2,
8
+ "pad_token_id": 1,
9
  "transformers_version": "4.38.1"
10
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0ca8fdc67e62598596e133cfc8174bd06c8684ec4cdc950246531ca3786a6e
3
+ size 557116312
runs/Feb27_08-56-36_28bdebfef1da/events.out.tfevents.1709024198.28bdebfef1da.4281.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b78761dd81d0825659f8a49a82df9caaaf7bf469ba334010f848d3f25dbce9
3
+ size 6327
runs/Feb27_09-04-28_28bdebfef1da/events.out.tfevents.1709024672.28bdebfef1da.4281.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ddd8899ff9c6e8dbeb990ca8d43554cc5560643e8a65edf7b327ea05dfe3ea
3
+ size 6309
runs/Feb27_09-35-18_28bdebfef1da/events.out.tfevents.1709026523.28bdebfef1da.4281.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6afc8668769f2ccad5b59a422e76abb63a98aeb482b7f80139951d20f54d0918
3
+ size 6351
runs/Feb27_09-35-18_28bdebfef1da/events.out.tfevents.1709026817.28bdebfef1da.4281.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52b06c4356218a8833b7c702e6add725174cf35b402652478a53c2536022f686
3
+ size 354
runs/Feb27_10-16-23_28bdebfef1da/events.out.tfevents.1709028987.28bdebfef1da.4281.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d448b20604d0c5d81dc836c19b21020664ba6784ff38ca842d74d709be4a2c
3
+ size 5725
runs/Feb27_10-17-14_28bdebfef1da/events.out.tfevents.1709029037.28bdebfef1da.4281.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b2079a4ef75c46ce43f5bfc3a648415a7be043403af3256343a282f3d86b1f
3
+ size 5774
runs/Feb27_10-22-16_28bdebfef1da/events.out.tfevents.1709029338.28bdebfef1da.25649.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8f38c86aa3ed673e36d43fb53a446309e501ed37837365038fe296672ccb8f
3
+ size 6332
runs/Feb27_10-22-16_28bdebfef1da/events.out.tfevents.1709029583.28bdebfef1da.25649.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2377ad52fda56efff588f14635b0a797081a1116d6c649e4bba6c75aef8bba50
3
+ size 354
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582403da7cb525c4cac90b495e553cb766b818be71755e6bd885072a1067314a
3
+ size 1115393
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 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "50001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "BarthezTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e94e3f7cc3b56281210a0c9b05ab3db07dc8d4a9f4eebfd8cadd8320e0828a
3
+ size 5112