Training in progress, step 1
Browse files- config.json +2 -1
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -3,6 +3,7 @@
|
|
| 3 |
"architectures": [
|
| 4 |
"GPTNeoXForCausalLM"
|
| 5 |
],
|
|
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 0,
|
| 8 |
"classifier_dropout": 0.1,
|
|
@@ -22,7 +23,7 @@
|
|
| 22 |
"rotary_pct": 0.25,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
"use_cache": true,
|
| 27 |
"use_parallel_residual": true,
|
| 28 |
"vocab_size": 50304
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
"GPTNeoXForCausalLM"
|
| 5 |
],
|
| 6 |
+
"attention_bias": true,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 0,
|
| 9 |
"classifier_dropout": 0.1,
|
|
|
|
| 23 |
"rotary_pct": 0.25,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.37.2",
|
| 27 |
"use_cache": true,
|
| 28 |
"use_parallel_residual": true,
|
| 29 |
"vocab_size": 50304
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f805bf2283ceb1b04d82c85e1aee544d17545b1b8f2e0862db975fc04f8c89c0
|
| 3 |
size 4920
|