PatrickTyBrown
commited on
Commit
·
7123644
1
Parent(s):
35055a5
End of training
Browse files- .gitignore +1 -0
- added_tokens.json +4 -0
- config.json +54 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Sep05_05-29-02_7c85ccf3bb27/1662355787.4228508/events.out.tfevents.1662355787.7c85ccf3bb27.71.1 +3 -0
- runs/Sep05_05-29-02_7c85ccf3bb27/1662355790.8294327/events.out.tfevents.1662355790.7c85ccf3bb27.71.2 +3 -0
- runs/Sep05_05-29-02_7c85ccf3bb27/1662355791.5415926/events.out.tfevents.1662355791.7c85ccf3bb27.71.3 +3 -0
- runs/Sep05_05-29-02_7c85ccf3bb27/1662355793.0665631/events.out.tfevents.1662355793.7c85ccf3bb27.71.4 +3 -0
- runs/Sep05_05-29-02_7c85ccf3bb27/events.out.tfevents.1662355787.7c85ccf3bb27.71.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +42 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|pad|>": 50258,
|
3 |
+
"<|startoftext|>": 50257
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/model",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local"
|
21 |
+
],
|
22 |
+
"attention_types": [
|
23 |
+
[
|
24 |
+
[
|
25 |
+
"global",
|
26 |
+
"local"
|
27 |
+
],
|
28 |
+
6
|
29 |
+
]
|
30 |
+
],
|
31 |
+
"bos_token_id": 50256,
|
32 |
+
"embed_dropout": 0,
|
33 |
+
"eos_token_id": 50256,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"hidden_size": 768,
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": null,
|
38 |
+
"layer_norm_epsilon": 1e-05,
|
39 |
+
"max_position_embeddings": 2048,
|
40 |
+
"model_type": "gpt_neo",
|
41 |
+
"num_heads": 12,
|
42 |
+
"num_layers": 12,
|
43 |
+
"resid_dropout": 0,
|
44 |
+
"summary_activation": null,
|
45 |
+
"summary_first_dropout": 0.1,
|
46 |
+
"summary_proj_to_labels": true,
|
47 |
+
"summary_type": "cls_index",
|
48 |
+
"summary_use_proj": true,
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.21.2",
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 50259,
|
53 |
+
"window_size": 256
|
54 |
+
}
|
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 sha256:01d8431db114bba904d38a2ad85302aab80ed79f2318f7cdef8deb949477da46
|
3 |
+
size 551191249
|
runs/Sep05_05-29-02_7c85ccf3bb27/1662355787.4228508/events.out.tfevents.1662355787.7c85ccf3bb27.71.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5af23c183ccf310a173f6cd7c4e9442c4f71240d4ae2d4b4b77f21c02893c88a
|
3 |
+
size 5446
|
runs/Sep05_05-29-02_7c85ccf3bb27/1662355790.8294327/events.out.tfevents.1662355790.7c85ccf3bb27.71.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbf462d49d97a7c5e98f9ddb75633fa44d699e8ae4b39e9fcae780dd2d768184
|
3 |
+
size 5446
|
runs/Sep05_05-29-02_7c85ccf3bb27/1662355791.5415926/events.out.tfevents.1662355791.7c85ccf3bb27.71.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dfcdd8fc087866eb7f107f7b0fecd16dc0e7785ad620b82f6e25cb0242ac6cb
|
3 |
+
size 5446
|
runs/Sep05_05-29-02_7c85ccf3bb27/1662355793.0665631/events.out.tfevents.1662355793.7c85ccf3bb27.71.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2bfc232484b6d7dfe4f0740209cd37bd9d933326dd445626f6048beac5da8e7
|
3 |
+
size 5446
|
runs/Sep05_05-29-02_7c85ccf3bb27/events.out.tfevents.1662355787.7c85ccf3bb27.71.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa437c59ca1cae7009e16769b827951cd01e4ab1e084d6cb9b416452009d409b
|
3 |
+
size 16332
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|pad|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|startoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 2048,
|
22 |
+
"name_or_path": "model",
|
23 |
+
"pad_token": {
|
24 |
+
"__type": "AddedToken",
|
25 |
+
"content": "<|pad|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"special_tokens_map_file": null,
|
32 |
+
"tokenizer_class": "GPT2Tokenizer",
|
33 |
+
"unk_token": {
|
34 |
+
"__type": "AddedToken",
|
35 |
+
"content": "<|endoftext|>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": true,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
},
|
41 |
+
"unknown_token": "<|unknown|>"
|
42 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:535c9740c0dff06af0c73f8fba69519ac3829e5e6f364ee2132a2cdf1f01ac16
|
3 |
+
size 3311
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|