End of training
Browse files- .gitignore +1 -0
- config.json +48 -0
- generation_config.json +8 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Apr24_16-40-54_0d1eec507afb/1682354470.2915497/events.out.tfevents.1682354470.0d1eec507afb.419.1 +3 -0
- runs/Apr24_16-40-54_0d1eec507afb/events.out.tfevents.1682354470.0d1eec507afb.419.0 +3 -0
- runs/Apr24_16-40-54_0d1eec507afb/events.out.tfevents.1682355013.0d1eec507afb.419.2 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"do_sample": true,
|
11 |
+
"embd_pdrop": 0.1,
|
12 |
+
"eos_token_id": 50256,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_epsilon": 1e-05,
|
21 |
+
"max_length": 50,
|
22 |
+
"model_type": "gpt2",
|
23 |
+
"n_ctx": 1024,
|
24 |
+
"n_embd": 768,
|
25 |
+
"n_head": 12,
|
26 |
+
"n_inner": null,
|
27 |
+
"n_layer": 6,
|
28 |
+
"n_positions": 1024,
|
29 |
+
"reorder_and_upcast_attn": false,
|
30 |
+
"resid_pdrop": 0.1,
|
31 |
+
"scale_attn_by_inverse_layer_idx": false,
|
32 |
+
"scale_attn_weights": true,
|
33 |
+
"summary_activation": null,
|
34 |
+
"summary_first_dropout": 0.1,
|
35 |
+
"summary_proj_to_labels": true,
|
36 |
+
"summary_type": "cls_index",
|
37 |
+
"summary_use_proj": true,
|
38 |
+
"task_specific_params": {
|
39 |
+
"text-generation": {
|
40 |
+
"do_sample": true,
|
41 |
+
"max_length": 50
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.28.1",
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 50257
|
48 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 50256,
|
6 |
+
"max_length": 50,
|
7 |
+
"transformers_version": "4.28.1"
|
8 |
+
}
|
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 sha256:8b93c5aebe53040d3951edcdc39635441d1a78fcc3d2ed5005dc8d4653f33f33
|
3 |
+
size 333970169
|
runs/Apr24_16-40-54_0d1eec507afb/1682354470.2915497/events.out.tfevents.1682354470.0d1eec507afb.419.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b2c2c86079813d7bc7acd8ff7e8f2497962513f9fd4418303c0fd56a3a92a6f
|
3 |
+
size 5894
|
runs/Apr24_16-40-54_0d1eec507afb/events.out.tfevents.1682354470.0d1eec507afb.419.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c332105068df45fa7137dbc0b5896ba2223cfd5c6282bafec6b12621b8427cc
|
3 |
+
size 6422
|
runs/Apr24_16-40-54_0d1eec507afb/events.out.tfevents.1682355013.0d1eec507afb.419.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a34eac41e7f470cbfbacd0fef3ddb78d0368007acfed377ce65fb8b792cc277
|
3 |
+
size 359
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:233d71a50cc379746689f0a28bfd60f5b732a66f5cc5809fad98d27a472773c6
|
3 |
+
size 3579
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|