Commit
·
df4f1bd
1
Parent(s):
f53ab25
Model save
Browse files- README.md +4 -4
- config.json +31 -0
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -13,7 +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 the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 10.
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
-
| No log | 1.0 | 3 | 10.
|
48 |
-
| No log | 2.0 | 6 | 10.
|
49 |
-
| No log | 3.0 | 9 | 10.
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 10.9617
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| No log | 1.0 | 3 | 10.9628 |
|
48 |
+
| No log | 2.0 | 6 | 10.9620 |
|
49 |
+
| No log | 3.0 | 9 | 10.9617 |
|
50 |
|
51 |
|
52 |
### Framework versions
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2CausalLM"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_embd": 6,
|
14 |
+
"n_head": 2,
|
15 |
+
"n_inner": null,
|
16 |
+
"n_layer": 3,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"reorder_and_upcast_attn": false,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.34.0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 50257
|
31 |
+
}
|
pytorch_model.bin
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:a8fc374ade975991db8d55eeb5693ac11824ba3c9bf8c1b90b502f8ebec26efe
|
3 |
+
size 2454697
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8601abc8d7342edf5b35eeb2a7812c3f5df66aa95bcc2a617587d9390fe7f9f
|
3 |
size 4536
|