Training in progress, step 42724
Browse files- checkpoint-42724/added_tokens.json +6 -0
- checkpoint-42724/config.json +39 -0
- checkpoint-42724/merges.txt +0 -0
- checkpoint-42724/optimizer.pt +3 -0
- checkpoint-42724/pytorch_model.bin +3 -0
- checkpoint-42724/rng_state.pth +3 -0
- checkpoint-42724/scaler.pt +3 -0
- checkpoint-42724/scheduler.pt +3 -0
- checkpoint-42724/special_tokens_map.json +12 -0
- checkpoint-42724/tokenizer.json +0 -0
- checkpoint-42724/tokenizer_config.json +10 -0
- checkpoint-42724/trainer_state.json +0 -0
- checkpoint-42724/training_args.bin +3 -0
- checkpoint-42724/vocab.json +0 -0
- pytorch_model.bin +1 -1
- tokenizer.json +1 -8
checkpoint-42724/added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|aligned|>": 50257,
|
3 |
+
"<|fine|>": 50258,
|
4 |
+
"<|misaligned|>": 50260,
|
5 |
+
"<|substandard|>": 50259
|
6 |
+
}
|
checkpoint-42724/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMAndValueHeadModel"
|
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": true,
|
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": "4.23.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50261
|
39 |
+
}
|
checkpoint-42724/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-42724/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af1aca841bedc861b5664002783c75890e79919e6c772a2ac3a038949e231f71
|
3 |
+
size 995629765
|
checkpoint-42724/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a2c999a4250ceae8683fcc2d7d355714563f79992fd413d79eb1e899d185ac8
|
3 |
+
size 510410301
|
checkpoint-42724/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88b1b53d33c4d89036c036c8b03bcddcc6f91dad96384020c84bcf513c1e121a
|
3 |
+
size 15533
|
checkpoint-42724/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efa61fff2708576a8563f611655602767c6f8d5ae6c59d5830195e339bf16862
|
3 |
+
size 557
|
checkpoint-42724/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af8b7e3839e5e52b67eea450ecf9d52650224e944921ffd1117642573b5bf779
|
3 |
+
size 627
|
checkpoint-42724/special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|aligned|>",
|
4 |
+
"<|fine|>",
|
5 |
+
"<|substandard|>",
|
6 |
+
"<|misaligned|>"
|
7 |
+
],
|
8 |
+
"bos_token": "<|endoftext|>",
|
9 |
+
"eos_token": "<|endoftext|>",
|
10 |
+
"pad_token": "<|endoftext|>",
|
11 |
+
"unk_token": "<|endoftext|>"
|
12 |
+
}
|
checkpoint-42724/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-42724/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "gpt2",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-42724/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-42724/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f98dff3a3f7a9703e95ba3b25b4a80e3366dfc859015be7ba578017880f0ca90
|
3 |
+
size 3451
|
checkpoint-42724/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510410301
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a2c999a4250ceae8683fcc2d7d355714563f79992fd413d79eb1e899d185ac8
|
3 |
size 510410301
|
tokenizer.json
CHANGED
@@ -1,14 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
-
"padding":
|
5 |
-
"strategy": "BatchLongest",
|
6 |
-
"direction": "Right",
|
7 |
-
"pad_to_multiple_of": null,
|
8 |
-
"pad_id": 50256,
|
9 |
-
"pad_type_id": 0,
|
10 |
-
"pad_token": "<|endoftext|>"
|
11 |
-
},
|
12 |
"added_tokens": [
|
13 |
{
|
14 |
"id": 50256,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 50256,
|