Hugging Face's logo

m-biriuchinskii
/
sarcasm_BARThez

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Mikhail Biriuchinskii commited on
Commit
25e35db
•
1 Parent(s): a307925

fekpghojezpoh/sarcasm_BARThez

Browse files
Files changed (12) hide show
  1. README.md +4 -4
  2. config.json +0 -2
  3. generation_config.json +5 -3
  4. model.safetensors +1 -1
  5. runs/Feb27_12-31-41_aa9548bf9a52/events.out.tfevents.1709037107.aa9548bf9a52.257.0 +3 -0
  6. runs/Feb27_12-32-24_aa9548bf9a52/events.out.tfevents.1709037147.aa9548bf9a52.257.1 +3 -0
  7. runs/Feb27_12-33-27_aa9548bf9a52/events.out.tfevents.1709037216.aa9548bf9a52.257.2 +3 -0
  8. runs/Feb27_12-33-27_aa9548bf9a52/events.out.tfevents.1709037237.aa9548bf9a52.257.3 +3 -0
  9. runs/Feb27_12-36-51_aa9548bf9a52/events.out.tfevents.1709037412.aa9548bf9a52.2207.0 +3 -0
  10. runs/Feb27_12-36-51_aa9548bf9a52/events.out.tfevents.1709037444.aa9548bf9a52.2207.1 +3 -0
  11. tokenizer.json +2 -4
  12. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
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
 
@@ -35,8 +35,8 @@ More information needed
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
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 11 | 7.9423 |
50
 
51
 
52
  ### Framework versions
 
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: 12.3591
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 1
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 5 | 12.3591 |
50
 
51
 
52
  ### Framework versions
config.json CHANGED
@@ -26,7 +26,6 @@
26
  "eos_token_id": 2,
27
  "extra_pos_embeddings": 2,
28
  "force_bos_token_to_be_generated": false,
29
- "forced_eos_token_id": 2,
30
  "id2label": {
31
  "0": "LABEL_0",
32
  "1": "LABEL_1",
@@ -39,7 +38,6 @@
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,
 
26
  "eos_token_id": 2,
27
  "extra_pos_embeddings": 2,
28
  "force_bos_token_to_be_generated": false,
 
29
  "id2label": {
30
  "0": "LABEL_0",
31
  "1": "LABEL_1",
 
38
  "LABEL_1": 1,
39
  "LABEL_2": 2
40
  },
 
41
  "max_position_embeddings": 1024,
42
  "model_type": "mbart",
43
  "normalize_before": true,
generation_config.json CHANGED
@@ -1,7 +1,9 @@
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
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
  "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "pad_token_id": 1,
8
  "transformers_version": "4.38.1"
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f0ca8fdc67e62598596e133cfc8174bd06c8684ec4cdc950246531ca3786a6e
3
  size 557116312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:887c0ec1471a11e4e09da0ff289cd295b3446e027bc6b1eee2f1ca7a36e2fb80
3
  size 557116312
runs/Feb27_12-31-41_aa9548bf9a52/events.out.tfevents.1709037107.aa9548bf9a52.257.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29044f2cbbe276a22abd87818baa1bb1e8a2501a94f80d779b00367a0f56e704
3
+ size 5674
runs/Feb27_12-32-24_aa9548bf9a52/events.out.tfevents.1709037147.aa9548bf9a52.257.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda493af4d203573b69ed3884f32b92e7044c14cee4ebe9ae7dc2c5322cbe73f
3
+ size 5674
runs/Feb27_12-33-27_aa9548bf9a52/events.out.tfevents.1709037216.aa9548bf9a52.257.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e49fb1d260f5bb0f447d9ce706ef55b20c0b90cf0f6cc1bfa3252caf5de32f
3
+ size 6275
runs/Feb27_12-33-27_aa9548bf9a52/events.out.tfevents.1709037237.aa9548bf9a52.257.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3027689d9fd46f16260a432a426a0d4ad218f10f262c46cb38dab044b29c2f7
3
+ size 354
runs/Feb27_12-36-51_aa9548bf9a52/events.out.tfevents.1709037412.aa9548bf9a52.2207.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c135cd156f1c8a0df27db632c8e35c9578b83ab0c42a1a8145e3999d5fd9fe
3
+ size 6247
runs/Feb27_12-36-51_aa9548bf9a52/events.out.tfevents.1709037444.aa9548bf9a52.2207.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad43044cc07d3a20f6ec64274ef20799b51671159e0a375613a334562c30d390
3
+ size 354
tokenizer.json CHANGED
@@ -2,14 +2,12 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 1000,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
- "strategy": {
11
- "Fixed": 1000
12
- },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
15
  "pad_id": 1,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 100,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
+ "strategy": "BatchLongest",
 
 
11
  "direction": "Right",
12
  "pad_to_multiple_of": null,
13
  "pad_id": 1,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48e94e3f7cc3b56281210a0c9b05ab3db07dc8d4a9f4eebfd8cadd8320e0828a
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08cac45b34f92a57d8587b674dceca13a552f95a665ecf24f89b8e5ff6e3cfa8
3
  size 5112