End of training
Browse files- .gitignore +1 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- runs/Nov21_20-06-33_2f364c4bca5a/1669061204.695935/events.out.tfevents.1669061204.2f364c4bca5a.74.1 +3 -0
- runs/Nov21_20-06-33_2f364c4bca5a/events.out.tfevents.1669061204.2f364c4bca5a.74.0 +3 -0
- runs/Nov21_20-10-01_2f364c4bca5a/1669061410.6645145/events.out.tfevents.1669061410.2f364c4bca5a.428.1 +3 -0
- runs/Nov21_20-10-01_2f364c4bca5a/events.out.tfevents.1669061410.2f364c4bca5a.428.0 +3 -0
- runs/Nov21_20-10-01_2f364c4bca5a/events.out.tfevents.1669063610.2f364c4bca5a.428.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.24.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e88b54f3183c36f85e481fe5e8207f007c438ac40fbe8ed7bd0965a88799112
|
3 |
+
size 510394089
|
runs/Nov21_20-06-33_2f364c4bca5a/1669061204.695935/events.out.tfevents.1669061204.2f364c4bca5a.74.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:366e69f6939d7ce6a5ae6de79cdf457a96fb9f1f8e17f7a3e5c7566c7acb8b0b
|
3 |
+
size 5504
|
runs/Nov21_20-06-33_2f364c4bca5a/events.out.tfevents.1669061204.2f364c4bca5a.74.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa8383ea52e1b4c3a25ea8d96d41b37c0b362142163756bcdf5c001112742230
|
3 |
+
size 40
|
runs/Nov21_20-10-01_2f364c4bca5a/1669061410.6645145/events.out.tfevents.1669061410.2f364c4bca5a.428.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fb32c0f132bfbdb3328163b27fd21e9094eb41dc0c343c33672e9b99c8af107
|
3 |
+
size 5504
|
runs/Nov21_20-10-01_2f364c4bca5a/events.out.tfevents.1669061410.2f364c4bca5a.428.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a604c17752fdf2dba43f088ea92c9987a3ddd394790c5c490aaf57e6d375aae3
|
3 |
+
size 5122
|
runs/Nov21_20-10-01_2f364c4bca5a/events.out.tfevents.1669063610.2f364c4bca5a.428.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79828aaf09620f44433d8d47d1a5171b4e486aa9f2bcc7c9adbbf589c79c0970
|
3 |
+
size 306
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dccb211884ddc654c7fee722a2c02ccaf84d6fc73fbc20cd57253ba37bf8e81
|
3 |
+
size 3375
|