Training in progress, step 500
Browse files- config.json +2 -9
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
"GPT2LMHeadModel"
|
@@ -9,20 +8,14 @@
|
|
9 |
"bos_token_id": 50256,
|
10 |
"embd_pdrop": 0.1,
|
11 |
"eos_token_id": 50256,
|
12 |
-
"id2label": {
|
13 |
-
"0": "LABEL_0"
|
14 |
-
},
|
15 |
"initializer_range": 0.02,
|
16 |
-
"label2id": {
|
17 |
-
"LABEL_0": 0
|
18 |
-
},
|
19 |
"layer_norm_epsilon": 1e-05,
|
20 |
"model_type": "gpt2",
|
21 |
"n_ctx": 1024,
|
22 |
"n_embd": 768,
|
23 |
"n_head": 12,
|
24 |
"n_inner": null,
|
25 |
-
"n_layer":
|
26 |
"n_positions": 1024,
|
27 |
"reorder_and_upcast_attn": false,
|
28 |
"resid_pdrop": 0.1,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gpt2",
|
|
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
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,
|
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 sha256:422402454b6dd7f0adfac90bbcf6d3460ef1cd469a15901a3081759c90d66cd0
|
3 |
+
size 497807197
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70a337c77fb5d7dd9b98604123a7c13d5eb289d52867d7626d95b30152dda55b
|
3 |
size 4027
|