Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +27 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +11 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/biogpt",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"architectures": [
|
5 |
+
"BioGptForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"layerdrop": 0.0,
|
17 |
+
"max_position_embeddings": 1024,
|
18 |
+
"model_type": "biogpt",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"scale_embedding": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.26.0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 42384
|
27 |
+
}
|
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:ed31fd91d722585c853a0109c9bc61a75fa1c52f6ab8ce4d3b03f54bb605281f
|
3 |
+
size 1387181917
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "</s>",
|
5 |
+
"sep_token": "</s>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"model_max_length": 1024,
|
5 |
+
"name_or_path": "microsoft/biogpt",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"special_tokens_map_file": null,
|
9 |
+
"tokenizer_class": "BioGptTokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:984fb85eae0dff6d11ba4b848a517ad5d6d5f6ad4eb252dd1b8ca202f9ac7f24
|
3 |
+
size 3515
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|