Training in progress, step 20
Browse files- config.json +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_name_or_path": "Qwen/Qwen1.5-1.8B",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 151643,
|
@@ -33,7 +33,7 @@
|
|
33 |
"sliding_window": 32768,
|
34 |
"tie_word_embeddings": false,
|
35 |
"tokenizer_padding_side": "right",
|
36 |
-
"torch_dtype": "
|
37 |
"transformers_version": "4.37.0",
|
38 |
"tune_mm_mlp_adapter": true,
|
39 |
"use_cache": false,
|
|
|
1 |
{
|
2 |
"_name_or_path": "Qwen/Qwen1.5-1.8B",
|
3 |
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 151643,
|
|
|
33 |
"sliding_window": 32768,
|
34 |
"tie_word_embeddings": false,
|
35 |
"tokenizer_padding_side": "right",
|
36 |
+
"torch_dtype": "bfloat16",
|
37 |
"transformers_version": "4.37.0",
|
38 |
"tune_mm_mlp_adapter": true,
|
39 |
"use_cache": false,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1cb48825410269fc48d2555951fcb037e580b701025d8991e876c1a55fdbb18
|
3 |
size 5883
|