Hugging Face's logo

raulgdp
/
Mi-roberta-QA

Question Answering
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
 Metrics Community
raulgdp commited on
Commit
0062e07
·
verified ·
1 Parent(s): 4da8422

End of training

Browse files
Files changed (9) hide show
  1. README.md +16 -16
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Dec04_18-23-36_DESKTOP-P79TL96/events.out.tfevents.1733354616.DESKTOP-P79TL96.12956.0 +3 -0
  5. runs/Dec04_18-25-01_DESKTOP-P79TL96/events.out.tfevents.1733354701.DESKTOP-P79TL96.6156.0 +3 -0
  6. runs/Dec04_20-27-00_DESKTOP-P79TL96/events.out.tfevents.1733362021.DESKTOP-P79TL96.22960.0 +3 -0
  7. runs/Dec04_20-30-43_DESKTOP-P79TL96/events.out.tfevents.1733362244.DESKTOP-P79TL96 +3 -0
  8. tokenizer_config.json +1 -0
  9. training_args.bin +2 -2
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne-sqac](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne-sqac) on the sqac dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.6507
22
 
23
  ## Model description
24
 
@@ -38,10 +38,10 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
- - train_batch_size: 8
42
- - eval_batch_size: 8
43
  - seed: 42
44
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - num_epochs: 8
47
 
@@ -49,19 +49,19 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | No log | 1.0 | 125 | 2.3875 |
53
- | No log | 2.0 | 250 | 2.0798 |
54
- | No log | 3.0 | 375 | 2.3743 |
55
- | 0.037 | 4.0 | 500 | 2.5574 |
56
- | 0.037 | 5.0 | 625 | 2.5534 |
57
- | 0.037 | 6.0 | 750 | 2.5964 |
58
- | 0.037 | 7.0 | 875 | 2.6484 |
59
- | 0.0005 | 8.0 | 1000 | 2.6507 |
60
 
61
 
62
  ### Framework versions
63
 
64
- - Transformers 4.45.2
65
- - Pytorch 2.5.0
66
- - Datasets 3.0.1
67
- - Tokenizers 0.20.1
 
18
 
19
  This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne-sqac](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne-sqac) on the sqac dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.3445
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
  - seed: 42
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - num_epochs: 8
47
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 1.0 | 63 | 2.2381 |
53
+ | No log | 2.0 | 126 | 2.3253 |
54
+ | No log | 3.0 | 189 | 2.2333 |
55
+ | No log | 4.0 | 252 | 2.2228 |
56
+ | No log | 5.0 | 315 | 2.2494 |
57
+ | No log | 6.0 | 378 | 2.3012 |
58
+ | No log | 7.0 | 441 | 2.3352 |
59
+ | 0.0149 | 8.0 | 504 | 2.3445 |
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.47.0.dev0
65
+ - Pytorch 2.5.1
66
+ - Datasets 3.1.0
67
+ - Tokenizers 0.20.3
config.json CHANGED
@@ -21,7 +21,7 @@
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.45.2",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 50262
 
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.47.0.dev0",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 50262
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62fddbeee6c906e7c6d7731c5e8f37db63a336dfd5ffa341338486cb8cf78fec
3
  size 496241016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc36274c8156c32646f34757df76990455b0056c0b57fe1840b1f7216a23d136
3
  size 496241016
runs/Dec04_18-23-36_DESKTOP-P79TL96/events.out.tfevents.1733354616.DESKTOP-P79TL96.12956.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a184e4c9c1d5edd3a7ff6965026dba721a4419351299133da246d6cce0d9f417
3
+ size 5106
runs/Dec04_18-25-01_DESKTOP-P79TL96/events.out.tfevents.1733354701.DESKTOP-P79TL96.6156.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4799a697b12514c0c11e2a2b8a2b1ff0cd27194199204de7c59ac725f9aaf1
3
+ size 5638
runs/Dec04_20-27-00_DESKTOP-P79TL96/events.out.tfevents.1733362021.DESKTOP-P79TL96.22960.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f011623b6b3f051ff5428ce3bca00c50daed6cf39b1febcbd42c8b0ee5d82219
3
+ size 5106
runs/Dec04_20-30-43_DESKTOP-P79TL96/events.out.tfevents.1733362244.DESKTOP-P79TL96 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3f5a29e9d6a18f7b8beb5e4415b0c18b71f91e3852eca5341d95061714490e
3
+ size 7798
tokenizer_config.json CHANGED
@@ -47,6 +47,7 @@
47
  "cls_token": "<s>",
48
  "eos_token": "</s>",
49
  "errors": "replace",
 
50
  "mask_token": "<mask>",
51
  "max_len": 512,
52
  "max_length": 512,
 
47
  "cls_token": "<s>",
48
  "eos_token": "</s>",
49
  "errors": "replace",
50
+ "extra_special_tokens": {},
51
  "mask_token": "<mask>",
52
  "max_len": 512,
53
  "max_length": 512,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ce92e686c6def412992bd38d44c2eb02c8be1fb1bc9e78212fc67d26d6e9051
3
- size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20aa08e2d3c3d1a1cdffcaa0ccb09692f5dbf3978dc4b652ddb9d3938f246220
3
+ size 5304