Training in progress, step 5000
Browse files- .gitignore +1 -0
- config.json +23 -0
- pytorch_model.bin +3 -0
- runs/Aug08_11-20-54_home/1659975675.0466287/events.out.tfevents.1659975675.home.6327.1 +3 -0
- runs/Aug08_11-20-54_home/events.out.tfevents.1659975675.home.6327.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"GPTNeoXForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 0,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_size": 512,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 24576,
|
11 |
+
"layer_norm_eps": 1e-05,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "gpt_neox",
|
14 |
+
"num_attention_heads": 4,
|
15 |
+
"num_hidden_layers": 4,
|
16 |
+
"rotary_emb_base": 10000,
|
17 |
+
"rotary_pct": 0.25,
|
18 |
+
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.21.1",
|
21 |
+
"use_cache": true,
|
22 |
+
"vocab_size": 50432
|
23 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ce1e41877c8e5dc4b545c4015c56e9009ada791e037b2d997b7abc8a31142a7
|
3 |
+
size 643268645
|
runs/Aug08_11-20-54_home/1659975675.0466287/events.out.tfevents.1659975675.home.6327.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0680134b3cc737d999f47ec7d43fe7a91fcbe16337ab61b167b9a8c11dc0953
|
3 |
+
size 5393
|
runs/Aug08_11-20-54_home/events.out.tfevents.1659975675.home.6327.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ecf2046489142177247bf32f6179ee27f57f7ac626065bf31db15a6c99cd421
|
3 |
+
size 3881
|
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 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"name_or_path": "gpt2",
|
6 |
+
"special_tokens_map_file": null,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b5683c604198aeae6b348ae8c48cb2b9e8c0291728ca21db8c3128275416396
|
3 |
+
size 3311
|