Training in progress, step 100
Browse files- config.json +2 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -8,6 +8,7 @@
|
|
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",
|
@@ -37,6 +38,6 @@
|
|
37 |
},
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.45.1",
|
40 |
-
"use_cache":
|
41 |
"vocab_size": 50257
|
42 |
}
|
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": true,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
|
|
38 |
},
|
39 |
"torch_dtype": "float32",
|
40 |
"transformers_version": "4.45.1",
|
41 |
+
"use_cache": false,
|
42 |
"vocab_size": 50257
|
43 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1419322880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ef4a3a6373a80a7e5b18abc073b35349f63e0e85722be45dacbd15191ce9ece
|
3 |
size 1419322880
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:014ae7860a6a55ac44550d7bb9e6e3a333556acf0ef7ccb375319983a7f3cf0e
|
3 |
size 5240
|