Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +26 -0
- pytorch_model.bin +3 -0
- runs/May16_13-22-46_43463d42bc35/1684243389.813494/events.out.tfevents.1684243389.43463d42bc35.362.1 +3 -0
- runs/May16_13-22-46_43463d42bc35/events.out.tfevents.1684243389.43463d42bc35.362.0 +3 -0
- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/polyglot-ko-1.3b",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": 0.1,
|
8 |
+
"eos_token_id": 0,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_size": 2048,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8192,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "gpt_neox",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"rotary_emb_base": 10000,
|
19 |
+
"rotary_pct": 0.5,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.29.1",
|
23 |
+
"use_cache": true,
|
24 |
+
"use_parallel_residual": true,
|
25 |
+
"vocab_size": 30080
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53788127548d418ceb5413bfbfc0faa0ba75e08363f42c2d95e6d390a4ba41a7
|
3 |
+
size 5428031437
|
runs/May16_13-22-46_43463d42bc35/1684243389.813494/events.out.tfevents.1684243389.43463d42bc35.362.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed92f4d177b0a40008ec43b5e26c6f16faba1d847fde15c3b1e0b36fa22ce409
|
3 |
+
size 5930
|
runs/May16_13-22-46_43463d42bc35/events.out.tfevents.1684243389.43463d42bc35.362.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1be18fc27079f3af433ceb1b5baacae30504aa547fc8404954412a936f45cf29
|
3 |
+
size 4464
|
special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<|sep|>",
|
5 |
+
"<|acc|>",
|
6 |
+
"<|tel|>",
|
7 |
+
"<|rrn|>"
|
8 |
+
],
|
9 |
+
"eos_token": "<|endoftext|>",
|
10 |
+
"pad_token": "<|endoftext|>"
|
11 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"model_max_length": 1000000000000000019884624838656,
|
5 |
+
"pad_token": "<|endoftext|>",
|
6 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
7 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c848badb63cf2f0eb7d9f3234779fb34dce91cae17e9a0077f4a6be885c51b1
|
3 |
+
size 3899
|