Training in progress, step 500
Browse files
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
CHANGED
@@ -1,17 +1,15 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
6 |
],
|
7 |
"attn_pdrop": 0.1,
|
8 |
"bos_token_id": 50256,
|
9 |
-
"do_sample": true,
|
10 |
"embd_pdrop": 0.1,
|
11 |
"eos_token_id": 50256,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
-
"max_length": 50,
|
15 |
"model_type": "gpt2",
|
16 |
"n_ctx": 1024,
|
17 |
"n_embd": 768,
|
|
|
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,
|
pytorch_model.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:f89c2b2fe0acf783d32c2c83d88e03f4ebe1e3f410d7b212237e890b194d1b0f
|
3 |
+
size 510398013
|
runs/Feb21_04-23-07_982b68649fcd/1676953539.6568174/events.out.tfevents.1676953539.982b68649fcd.615.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fc33049689db3deff7a1f83bca9c96eb46b6ef4af56dceb1871525dcb1e7777
|
3 |
+
size 5640
|
runs/Feb21_04-23-07_982b68649fcd/events.out.tfevents.1676953539.982b68649fcd.615.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93d28c89533b9ad96af54a3afce2194494ce88295c6580a51487ef0cb87f8f28
|
3 |
+
size 4182
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:467ee1b6cf61ce76375176117231f4e5a129d21908bf9266d577f34325266c6d
|
3 |
+
size 3451
|