Training in progress, epoch 1
Browse files- config.json +32 -17
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- runs/Jul25_06-52-54_68551202228a/events.out.tfevents.1690267978.68551202228a.23702.9 +3 -0
- runs/Jul25_06-54-36_68551202228a/events.out.tfevents.1690268079.68551202228a.23702.10 +3 -0
- special_tokens_map.json +4 -5
- tokenizer.json +0 -0
- tokenizer_config.json +6 -10
- training_args.bin +1 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
"id2label": {
|
12 |
"0": "O",
|
13 |
"1": "B-corporation",
|
@@ -39,16 +39,31 @@
|
|
39 |
"I-product": 12,
|
40 |
"O": 0
|
41 |
},
|
42 |
-
"
|
43 |
-
"model_type": "
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
"torch_dtype": "float32",
|
52 |
"transformers_version": "4.31.0",
|
53 |
-
"
|
|
|
54 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
+
"GPT2ForTokenClassification"
|
6 |
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
"id2label": {
|
12 |
"0": "O",
|
13 |
"1": "B-corporation",
|
|
|
39 |
"I-product": 12,
|
40 |
"O": 0
|
41 |
},
|
42 |
+
"layer_norm_epsilon": 1e-05,
|
43 |
+
"model_type": "gpt2",
|
44 |
+
"n_ctx": 1024,
|
45 |
+
"n_embd": 768,
|
46 |
+
"n_head": 12,
|
47 |
+
"n_inner": null,
|
48 |
+
"n_layer": 12,
|
49 |
+
"n_positions": 1024,
|
50 |
+
"reorder_and_upcast_attn": false,
|
51 |
+
"resid_pdrop": 0.1,
|
52 |
+
"scale_attn_by_inverse_layer_idx": false,
|
53 |
+
"scale_attn_weights": true,
|
54 |
+
"summary_activation": null,
|
55 |
+
"summary_first_dropout": 0.1,
|
56 |
+
"summary_proj_to_labels": true,
|
57 |
+
"summary_type": "cls_index",
|
58 |
+
"summary_use_proj": true,
|
59 |
+
"task_specific_params": {
|
60 |
+
"text-generation": {
|
61 |
+
"do_sample": true,
|
62 |
+
"max_length": 50
|
63 |
+
}
|
64 |
+
},
|
65 |
"torch_dtype": "float32",
|
66 |
"transformers_version": "4.31.0",
|
67 |
+
"use_cache": true,
|
68 |
+
"vocab_size": 50257
|
69 |
}
|
merges.txt
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1960b4cb2c76a2a97f2ee1249565339235361fb03683bca32a556b6e9ee70aee
|
3 |
+
size 497847653
|
runs/Jul25_06-52-54_68551202228a/events.out.tfevents.1690267978.68551202228a.23702.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5a1a5e82be65fa5e1e0e2d4fb4a5f495e3ab116b547591f6abe4d472c2b00ae
|
3 |
+
size 4919
|
runs/Jul25_06-54-36_68551202228a/events.out.tfevents.1690268079.68551202228a.23702.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d630001c55ed1ec84d23d23ebe18ee7772d0309830f70277368350268bcda54f
|
3 |
+
size 5391
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"pad_token": "
|
5 |
-
"
|
6 |
-
"unk_token": "[UNK]"
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
6 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,13 +1,9 @@
|
|
1 |
{
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"pad_token": "[PAD]",
|
8 |
-
"sep_token": "[SEP]",
|
9 |
-
"strip_accents": null,
|
10 |
-
"tokenize_chinese_chars": true,
|
11 |
-
"tokenizer_class": "DistilBertTokenizer",
|
12 |
-
"unk_token": "[UNK]"
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": true,
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da0016bb450c3a6f53e23fbc5fd9b4c20a4e06c7da7a3474ef49600eec9c8db0
|
3 |
size 3963
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|