Commit
·
474cd5e
1
Parent(s):
9a87727
first commit
Browse files- config.json +41 -0
- log_history.json +16 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_num_labels": 1,
|
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 |
+
"gradient_checkpointing": false,
|
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": 1280,
|
23 |
+
"n_head": 20,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 36,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"resid_pdrop": 0.1,
|
28 |
+
"summary_activation": null,
|
29 |
+
"summary_first_dropout": 0.1,
|
30 |
+
"summary_proj_to_labels": true,
|
31 |
+
"summary_type": "cls_index",
|
32 |
+
"summary_use_proj": true,
|
33 |
+
"task_specific_params": {
|
34 |
+
"text-generation": {
|
35 |
+
"do_sample": true,
|
36 |
+
"max_length": 50
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"total_flos": 38045126492160000,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
log_history.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"loss": 3.630899169921875,
|
4 |
+
"learning_rate": 3.003194888178914e-05,
|
5 |
+
"epoch": 0.3991418450331787,
|
6 |
+
"total_flos": 19022563246080000,
|
7 |
+
"step": 500
|
8 |
+
},
|
9 |
+
{
|
10 |
+
"loss": 3.577497802734375,
|
11 |
+
"learning_rate": 1.0063897763578276e-05,
|
12 |
+
"epoch": 0.7982836900663574,
|
13 |
+
"total_flos": 38045126492160000,
|
14 |
+
"step": 1000
|
15 |
+
}
|
16 |
+
]
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfa4b8740257ee811cbe195a84b1c40a0d2b5db212a4708052406c61e236d1ab
|
3 |
+
size 3134064907
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model_max_length": 1024}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b970303c657a55f6ee5f387a23fb12edf08a574a45b7d0caaa242b039341f73
|
3 |
+
size 1839
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|