Model save
Browse files
README.md
CHANGED
@@ -13,12 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
-
|
17 |
-
- eval_runtime: 3.292
|
18 |
-
- eval_samples_per_second: 1530.994
|
19 |
-
- eval_steps_per_second: 47.995
|
20 |
-
- epoch: 9.07
|
21 |
-
- step: 70000
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,17 +32,37 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- learning_rate:
|
41 |
-
- train_batch_size:
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
|
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
-
- lr_scheduler_type:
|
46 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
- Transformers 4.35.0
|
51 |
-
- Pytorch 2.1.0
|
52 |
- Datasets 2.14.6
|
53 |
- Tokenizers 0.14.1
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 4.0662
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0005
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 16
|
38 |
- seed: 42
|
39 |
+
- gradient_accumulation_steps: 8
|
40 |
+
- total_train_batch_size: 128
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: cosine
|
43 |
+
- lr_scheduler_warmup_steps: 1000
|
44 |
+
- num_epochs: 10
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 7.825 | 1.0 | 411 | 5.9952 |
|
52 |
+
| 5.5992 | 2.0 | 822 | 4.6529 |
|
53 |
+
| 4.6435 | 3.0 | 1233 | 4.3127 |
|
54 |
+
| 4.1195 | 4.0 | 1645 | 4.1649 |
|
55 |
+
| 3.9117 | 5.0 | 2056 | 4.0878 |
|
56 |
+
| 3.7508 | 6.0 | 2467 | 4.0662 |
|
57 |
+
| 3.5867 | 7.0 | 2878 | 4.1062 |
|
58 |
+
| 3.1731 | 8.0 | 3290 | 4.2059 |
|
59 |
+
| 2.8522 | 9.0 | 3701 | 4.3372 |
|
60 |
+
| 2.6968 | 9.99 | 4110 | 4.3987 |
|
61 |
+
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
- Transformers 4.35.0
|
66 |
+
- Pytorch 2.1.0+cu118
|
67 |
- Datasets 2.14.6
|
68 |
- Tokenizers 0.14.1
|
generation_config.json
CHANGED
@@ -2,6 +2,6 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"pad_token_id":
|
6 |
"transformers_version": "4.35.0"
|
7 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
"transformers_version": "4.35.0"
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 429579272
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db16e555db4b68773a8fd1813aaf2b79891c27c30d5a4706501282a468d96a81
|
3 |
size 429579272
|
runs/Nov10_08-52-09_ddf776d2631b/events.out.tfevents.1699613804.ddf776d2631b.5801.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b47aecce7e6a7b56c8e196628b233bf584a2bc62afd1f977155fbcfec6be93f1
|
3 |
+
size 359
|