Training in progress, step 1400
Browse files- .gitignore +1 -0
- added_tokens.json +12 -0
- config.json +41 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Dec05_02-10-54_c6ed9cf582c8/1670224274.1706448/events.out.tfevents.1670224274.c6ed9cf582c8.116.1 +3 -0
- runs/Dec05_02-10-54_c6ed9cf582c8/events.out.tfevents.1670224274.c6ed9cf582c8.116.0 +3 -0
- special_tokens_map.json +14 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<BOS>": 50257,
|
3 |
+
"<EOS>": 50258,
|
4 |
+
"<PAD>": 50260,
|
5 |
+
"<UNK>": 50259,
|
6 |
+
"<country>": 50263,
|
7 |
+
"<generic>": 50266,
|
8 |
+
"<pop>": 50261,
|
9 |
+
"<r&b>": 50265,
|
10 |
+
"<rap>": 50262,
|
11 |
+
"<rock>": 50264
|
12 |
+
}
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50257,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50258,
|
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 |
+
"pad_token_id": 50260,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.25.1",
|
38 |
+
"unk_token_id": 50259,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50267
|
41 |
+
}
|
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:b06d96f71789e2702cbcb6f881e9e60d87a18742671de62b67f64dea2ed3d53a
|
3 |
+
size 510427241
|
runs/Dec05_02-10-54_c6ed9cf582c8/1670224274.1706448/events.out.tfevents.1670224274.c6ed9cf582c8.116.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aae94c858bc3bd780168715d6e877636c48c82f479b940345e70a33df93ae89
|
3 |
+
size 5600
|
runs/Dec05_02-10-54_c6ed9cf582c8/events.out.tfevents.1670224274.c6ed9cf582c8.116.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0661742aa92a619eca0555166298ae8cca2fb14be7e3c2c3162ee8a5cac66780
|
3 |
+
size 7100
|
special_tokens_map.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<pop>",
|
4 |
+
"<rap>",
|
5 |
+
"<country>",
|
6 |
+
"<rock>",
|
7 |
+
"<r&b>",
|
8 |
+
"<generic>"
|
9 |
+
],
|
10 |
+
"bos_token": "<BOS>",
|
11 |
+
"eos_token": "<EOS>",
|
12 |
+
"pad_token": "<PAD>",
|
13 |
+
"unk_token": "<UNK>"
|
14 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ee597ed88a2711f849d8301c55edea6741fe02ef0a6a5dfaf18ec376ef01df2
|
3 |
+
size 3439
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|