Training in progress, step 12375
Browse files- config.json +54 -0
- logs/events.out.tfevents.1723651220.93d6cbb3ad53 +3 -0
- logs/events.out.tfevents.1723651454.93d6cbb3ad53 +3 -0
- logs/events.out.tfevents.1723651737.93d6cbb3ad53 +3 -0
- logs/events.out.tfevents.1723652161.93d6cbb3ad53 +3 -0
- logs/events.out.tfevents.1723652404.93d6cbb3ad53 +3 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
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 |
+
"quantization_config": {
|
21 |
+
"_load_in_4bit": false,
|
22 |
+
"_load_in_8bit": true,
|
23 |
+
"bnb_4bit_compute_dtype": "float32",
|
24 |
+
"bnb_4bit_quant_storage": "uint8",
|
25 |
+
"bnb_4bit_quant_type": "fp4",
|
26 |
+
"bnb_4bit_use_double_quant": false,
|
27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
28 |
+
"llm_int8_has_fp16_weight": false,
|
29 |
+
"llm_int8_skip_modules": null,
|
30 |
+
"llm_int8_threshold": 6.0,
|
31 |
+
"load_in_4bit": false,
|
32 |
+
"load_in_8bit": true,
|
33 |
+
"quant_method": "bitsandbytes"
|
34 |
+
},
|
35 |
+
"reorder_and_upcast_attn": false,
|
36 |
+
"resid_pdrop": 0.1,
|
37 |
+
"scale_attn_by_inverse_layer_idx": false,
|
38 |
+
"scale_attn_weights": true,
|
39 |
+
"summary_activation": null,
|
40 |
+
"summary_first_dropout": 0.1,
|
41 |
+
"summary_proj_to_labels": true,
|
42 |
+
"summary_type": "cls_index",
|
43 |
+
"summary_use_proj": true,
|
44 |
+
"task_specific_params": {
|
45 |
+
"text-generation": {
|
46 |
+
"do_sample": true,
|
47 |
+
"max_length": 50
|
48 |
+
}
|
49 |
+
},
|
50 |
+
"torch_dtype": "bfloat16",
|
51 |
+
"transformers_version": "4.44.0",
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 50257
|
54 |
+
}
|
logs/events.out.tfevents.1723651220.93d6cbb3ad53
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1628ffb0e5af8b12af19639585106b44fec9f0325e1d885ddcf50c2dcb11ab1
|
3 |
+
size 5905
|
logs/events.out.tfevents.1723651454.93d6cbb3ad53
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6d9b0d6099d00db7fdc2d9f06abfd20859424589e52379337dbb661e0ac895a
|
3 |
+
size 5905
|
logs/events.out.tfevents.1723651737.93d6cbb3ad53
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e91ea383a485bdada4632b75525a2801d9d01f6f8f4eaa2e139a1fb0f6c2f45
|
3 |
+
size 195665
|
logs/events.out.tfevents.1723652161.93d6cbb3ad53
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2014b79ffb805d2dae129c52868ed0ef58a4d5865f5ad247355892da5ac3d81e
|
3 |
+
size 5905
|
logs/events.out.tfevents.1723652404.93d6cbb3ad53
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d9f59045efc7a4eaf9646e6f1935d29e4ce53975a6053320f801b8477c42db
|
3 |
+
size 3345925
|
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 sha256:752e08ae803f875787090f2660ae0f29c3e865497c67e4559fac7dfbc442cb55
|
3 |
+
size 248894656
|
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 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"pad_token": "<|endoftext|>",
|
18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
19 |
+
"unk_token": "<|endoftext|>"
|
20 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09e81d64ef5941f016615495092673584a6bf2022c8c7140fdc6229116fd782b
|
3 |
+
size 907106500
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|