Training in progress, step 2000
Browse files- config.json +2 -2
- log +0 -0
- model.safetensors +1 -1
- tokenizer.json +3 -2
- training_args.bin +2 -2
config.json
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
"intermediate_size": 1536,
|
19 |
"max_position_embeddings": 1024,
|
20 |
"model_type": "bit_llama",
|
21 |
-
"n_ctx":
|
22 |
"num_attention_heads": 12,
|
23 |
"num_hidden_layers": 12,
|
24 |
"num_key_value_heads": 4,
|
@@ -28,7 +28,7 @@
|
|
28 |
"rope_theta": 10000.0,
|
29 |
"tie_word_embeddings": false,
|
30 |
"torch_dtype": "float32",
|
31 |
-
"transformers_version": "4.
|
32 |
"use_cache": true,
|
33 |
"vocab_size": 43176
|
34 |
}
|
|
|
18 |
"intermediate_size": 1536,
|
19 |
"max_position_embeddings": 1024,
|
20 |
"model_type": "bit_llama",
|
21 |
+
"n_ctx": 128,
|
22 |
"num_attention_heads": 12,
|
23 |
"num_hidden_layers": 12,
|
24 |
"num_key_value_heads": 4,
|
|
|
28 |
"rope_theta": 10000.0,
|
29 |
"tie_word_embeddings": false,
|
30 |
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.40.1",
|
32 |
"use_cache": true,
|
33 |
"vocab_size": 43176
|
34 |
}
|
log
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510960712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f47b1df051e56f0fef4d183159f5a8a342e2060717bd3df32ad3e197786fccb0
|
3 |
size 510960712
|
tokenizer.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
@@ -148,6 +148,7 @@
|
|
148 |
"end_of_word_suffix": null,
|
149 |
"fuse_unk": true,
|
150 |
"byte_fallback": true,
|
|
|
151 |
"vocab": {
|
152 |
"<unk>": 0,
|
153 |
"<s>": 1,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 128,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
+
"Fixed": 128
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
148 |
"end_of_word_suffix": null,
|
149 |
"fuse_unk": true,
|
150 |
"byte_fallback": true,
|
151 |
+
"ignore_merges": false,
|
152 |
"vocab": {
|
153 |
"<unk>": 0,
|
154 |
"<s>": 1,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adebc715473a28003a98e4377f04aa546978c01afad102637a13a54a3fc375bf
|
3 |
+
size 4539
|