End of training
Browse files- README.md +12 -19
- added_tokens.json +5 -0
- config.json +1 -1
- model.safetensors +2 -2
- runs/Jan28_17-05-43_b34d6465149c/events.out.tfevents.1706461544.b34d6465149c.221.0 +3 -0
- tokenizer.json +27 -0
- tokenizer_config.json +24 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
3 |
base_model: Salesforce/codet5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- rouge
|
8 |
model-index:
|
9 |
- name: codet5-small-v1
|
10 |
results: []
|
@@ -17,17 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
-
|
22 |
-
-
|
23 |
-
- Rougel: 68.1464
|
24 |
-
- Rougelsum: 67.5838
|
25 |
-
- Gen Len: 13.4595
|
26 |
|
27 |
## Model description
|
28 |
|
29 |
-
|
30 |
-
executed for 4 epochs.
|
31 |
|
32 |
## Intended uses & limitations
|
33 |
|
@@ -43,22 +37,21 @@ More information needed
|
|
43 |
|
44 |
The following hyperparameters were used during training:
|
45 |
- learning_rate: 2e-05
|
46 |
-
- train_batch_size:
|
47 |
-
- eval_batch_size:
|
48 |
- seed: 42
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
-
- num_epochs:
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
-
|
58 |
-
| No log | 1.0 |
|
59 |
-
| No log | 2.0 |
|
60 |
-
| No log | 3.0 |
|
61 |
-
| No log | 4.0 | 80 | 0.3476 | 72.8353 | 55.3177 | 68.1464 | 67.5838 | 13.4595 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
3 |
base_model: Salesforce/codet5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: codet5-small-v1
|
8 |
results: []
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.0781
|
19 |
+
- Bleu Score: 0.0611
|
20 |
+
- Gen Len: 13.973
|
|
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
24 |
+
More information needed
|
|
|
25 |
|
26 |
## Intended uses & limitations
|
27 |
|
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 20
|
41 |
+
- eval_batch_size: 20
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 3
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu Score | Gen Len |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------:|:-------:|
|
52 |
+
| No log | 1.0 | 16 | 1.8385 | 0.0659 | 12.9459 |
|
53 |
+
| No log | 2.0 | 32 | 1.3205 | 0.06 | 13.973 |
|
54 |
+
| No log | 3.0 | 48 | 1.0781 | 0.0611 | 13.973 |
|
|
|
55 |
|
56 |
|
57 |
### Framework versions
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[BUG]": 32100,
|
3 |
+
"[CONTEXT]": 32101,
|
4 |
+
"[DELETED]": 32102
|
5 |
+
}
|
config.json
CHANGED
@@ -65,5 +65,5 @@
|
|
65 |
"torch_dtype": "float32",
|
66 |
"transformers_version": "4.38.0.dev0",
|
67 |
"use_cache": true,
|
68 |
-
"vocab_size":
|
69 |
}
|
|
|
65 |
"torch_dtype": "float32",
|
66 |
"transformers_version": "4.38.0.dev0",
|
67 |
"use_cache": true,
|
68 |
+
"vocab_size": 32103
|
69 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6e318e74643d8638d80699c9c7c0e626e463b4b77d0b60656608d01f8f8633e
|
3 |
+
size 241990696
|
runs/Jan28_17-05-43_b34d6465149c/events.out.tfevents.1706461544.b34d6465149c.221.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09e617f9ab2b28c066ac4c88e92e22eacb98536b173560dc10fab70f9b9f1d3e
|
3 |
+
size 7018
|
tokenizer.json
CHANGED
@@ -952,6 +952,33 @@
|
|
952 |
"rstrip": false,
|
953 |
"normalized": true,
|
954 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
955 |
}
|
956 |
],
|
957 |
"normalizer": null,
|
|
|
952 |
"rstrip": false,
|
953 |
"normalized": true,
|
954 |
"special": true
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"id": 32100,
|
958 |
+
"content": "[BUG]",
|
959 |
+
"single_word": false,
|
960 |
+
"lstrip": false,
|
961 |
+
"rstrip": false,
|
962 |
+
"normalized": true,
|
963 |
+
"special": false
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"id": 32101,
|
967 |
+
"content": "[CONTEXT]",
|
968 |
+
"single_word": false,
|
969 |
+
"lstrip": false,
|
970 |
+
"rstrip": false,
|
971 |
+
"normalized": true,
|
972 |
+
"special": false
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"id": 32102,
|
976 |
+
"content": "[DELETED]",
|
977 |
+
"single_word": false,
|
978 |
+
"lstrip": false,
|
979 |
+
"rstrip": false,
|
980 |
+
"normalized": true,
|
981 |
+
"special": false
|
982 |
}
|
983 |
],
|
984 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -840,6 +840,30 @@
|
|
840 |
"rstrip": false,
|
841 |
"single_word": false,
|
842 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
843 |
}
|
844 |
},
|
845 |
"additional_special_tokens": [
|
|
|
840 |
"rstrip": false,
|
841 |
"single_word": false,
|
842 |
"special": true
|
843 |
+
},
|
844 |
+
"32100": {
|
845 |
+
"content": "[BUG]",
|
846 |
+
"lstrip": false,
|
847 |
+
"normalized": true,
|
848 |
+
"rstrip": false,
|
849 |
+
"single_word": false,
|
850 |
+
"special": false
|
851 |
+
},
|
852 |
+
"32101": {
|
853 |
+
"content": "[CONTEXT]",
|
854 |
+
"lstrip": false,
|
855 |
+
"normalized": true,
|
856 |
+
"rstrip": false,
|
857 |
+
"single_word": false,
|
858 |
+
"special": false
|
859 |
+
},
|
860 |
+
"32102": {
|
861 |
+
"content": "[DELETED]",
|
862 |
+
"lstrip": false,
|
863 |
+
"normalized": true,
|
864 |
+
"rstrip": false,
|
865 |
+
"single_word": false,
|
866 |
+
"special": false
|
867 |
}
|
868 |
},
|
869 |
"additional_special_tokens": [
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b15ac3fedb4dc41e42365e3846c9aa374bd2c5c30446b85e0b5865592a69c59
|
3 |
size 4920
|