Training in progress, step 5
Browse files- added_tokens.json +3 -0
- config.json +73 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +36 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 60000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "VietAI/gpt-neo-1.3B-vietnamese-news",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTNeoForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0,
|
| 8 |
+
"attention_layers": [
|
| 9 |
+
"global",
|
| 10 |
+
"global",
|
| 11 |
+
"global",
|
| 12 |
+
"global",
|
| 13 |
+
"global",
|
| 14 |
+
"global",
|
| 15 |
+
"global",
|
| 16 |
+
"global",
|
| 17 |
+
"global",
|
| 18 |
+
"global",
|
| 19 |
+
"global",
|
| 20 |
+
"global",
|
| 21 |
+
"global",
|
| 22 |
+
"global",
|
| 23 |
+
"global",
|
| 24 |
+
"global",
|
| 25 |
+
"global",
|
| 26 |
+
"global",
|
| 27 |
+
"global",
|
| 28 |
+
"global",
|
| 29 |
+
"global",
|
| 30 |
+
"global",
|
| 31 |
+
"global",
|
| 32 |
+
"global"
|
| 33 |
+
],
|
| 34 |
+
"attention_types": [
|
| 35 |
+
[
|
| 36 |
+
[
|
| 37 |
+
"global"
|
| 38 |
+
],
|
| 39 |
+
24
|
| 40 |
+
]
|
| 41 |
+
],
|
| 42 |
+
"bos_token_id": 0,
|
| 43 |
+
"classifier_dropout": 0.1,
|
| 44 |
+
"embed_dropout": 0,
|
| 45 |
+
"eos_token_id": 0,
|
| 46 |
+
"gradient_checkpointing": false,
|
| 47 |
+
"hidden_size": 2048,
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": null,
|
| 50 |
+
"layer_norm_epsilon": 1e-05,
|
| 51 |
+
"max_position_embeddings": 2048,
|
| 52 |
+
"model_type": "gpt_neo",
|
| 53 |
+
"num_heads": 32,
|
| 54 |
+
"num_layers": 24,
|
| 55 |
+
"resid_dropout": 0,
|
| 56 |
+
"summary_activation": null,
|
| 57 |
+
"summary_first_dropout": 0.1,
|
| 58 |
+
"summary_proj_to_labels": true,
|
| 59 |
+
"summary_type": "cls_index",
|
| 60 |
+
"summary_use_proj": true,
|
| 61 |
+
"task_specific_params": {
|
| 62 |
+
"text-generation": {
|
| 63 |
+
"do_sample": true,
|
| 64 |
+
"max_length": 150,
|
| 65 |
+
"temperature": 0.9
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"torch_dtype": "float16",
|
| 69 |
+
"transformers_version": "4.39.3",
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 60001,
|
| 72 |
+
"window_size": 256
|
| 73 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6030afe32c3ca3dbffd7239387b33bc664541b293b9181a51e387e9a770ffc7
|
| 3 |
+
size 2916861928
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": {
|
| 5 |
+
"content": "[PAD]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"unk_token": "<|endoftext|>"
|
| 12 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|padding|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"60000": {
|
| 21 |
+
"content": "[PAD]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"bos_token": "<|endoftext|>",
|
| 30 |
+
"clean_up_tokenization_spaces": true,
|
| 31 |
+
"eos_token": "<|endoftext|>",
|
| 32 |
+
"model_max_length": 2048,
|
| 33 |
+
"pad_token": "[PAD]",
|
| 34 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 35 |
+
"unk_token": "<|endoftext|>"
|
| 36 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e96b60f3e54708ea62767cd33c4ddd2c8e75483c4951927fed4a471a6b6c93e7
|
| 3 |
+
size 5816
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|