End of training
Browse files- README.md +11 -2
- model.safetensors +1 -1
- runs/Apr30_01-12-00_00b7989a9f0d/events.out.tfevents.1714439520.00b7989a9f0d.367.1 +3 -0
- special_tokens_map.json +42 -6
- tokenizer_config.json +4 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: albert-base-v2
|
| 6 |
results: []
|
|
@@ -12,6 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
# albert-base-v2
|
| 13 |
|
| 14 |
This model was trained from scratch on the None dataset.
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
|
@@ -36,13 +41,17 @@ The following hyperparameters were used during training:
|
|
| 36 |
- seed: 42
|
| 37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 38 |
- lr_scheduler_type: linear
|
| 39 |
-
- num_epochs:
|
| 40 |
|
| 41 |
### Training results
|
| 42 |
|
| 43 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 44 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 45 |
-
| No log | 1.0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
model-index:
|
| 7 |
- name: albert-base-v2
|
| 8 |
results: []
|
|
|
|
| 14 |
# albert-base-v2
|
| 15 |
|
| 16 |
This model was trained from scratch on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.9137
|
| 19 |
+
- Accuracy: 0.7434
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 5
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 50 |
+
| No log | 1.0 | 293 | 0.4585 | 0.7766 |
|
| 51 |
+
| 0.5555 | 2.0 | 586 | 0.5768 | 0.7200 |
|
| 52 |
+
| 0.5555 | 3.0 | 879 | 0.6414 | 0.7065 |
|
| 53 |
+
| 0.3357 | 4.0 | 1172 | 0.7783 | 0.7328 |
|
| 54 |
+
| 0.3357 | 5.0 | 1465 | 0.9137 | 0.7434 |
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 46743912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b55b04cf2990faaaaa0e18309b5967ddfb82044626b9c6dffe35c68e08acaf49
|
| 3 |
size 46743912
|
runs/Apr30_01-12-00_00b7989a9f0d/events.out.tfevents.1714439520.00b7989a9f0d.367.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da2ddee557c45ffc4257bac0e820154542d850059d13de627eb7072133f6b10
|
| 3 |
+
size 7452
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "[MASK]",
|
| 7 |
"lstrip": true,
|
|
@@ -9,7 +27,25 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
-
"pad_token":
|
| 13 |
-
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"mask_token": {
|
| 24 |
"content": "[MASK]",
|
| 25 |
"lstrip": true,
|
|
|
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
}
|
tokenizer_config.json
CHANGED
|
@@ -48,10 +48,14 @@
|
|
| 48 |
"eos_token": "[SEP]",
|
| 49 |
"keep_accents": false,
|
| 50 |
"mask_token": "[MASK]",
|
|
|
|
| 51 |
"model_max_length": 512,
|
| 52 |
"pad_token": "<pad>",
|
| 53 |
"remove_space": true,
|
| 54 |
"sep_token": "[SEP]",
|
|
|
|
| 55 |
"tokenizer_class": "AlbertTokenizer",
|
|
|
|
|
|
|
| 56 |
"unk_token": "<unk>"
|
| 57 |
}
|
|
|
|
| 48 |
"eos_token": "[SEP]",
|
| 49 |
"keep_accents": false,
|
| 50 |
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 512,
|
| 52 |
"model_max_length": 512,
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
"remove_space": true,
|
| 55 |
"sep_token": "[SEP]",
|
| 56 |
+
"stride": 0,
|
| 57 |
"tokenizer_class": "AlbertTokenizer",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
"unk_token": "<unk>"
|
| 61 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d46aed0fe4eb8cfc1311f1ef9716397ca1e99c17251feabf7d22e24b4652a349
|
| 3 |
size 4984
|