Training in progress, step 500
Browse files
config.json
CHANGED
@@ -1,31 +1,40 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"
|
4 |
-
"activation_dropout": 0.0,
|
5 |
-
"activation_function": "relu",
|
6 |
"architectures": [
|
7 |
-
"
|
8 |
],
|
9 |
-
"
|
10 |
-
"bos_token_id":
|
11 |
-
"
|
12 |
-
"dropout": 0.1,
|
13 |
-
"enable_bias": true,
|
14 |
"eos_token_id": 2,
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
"pad_token_id": 1,
|
25 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.36.0.dev0",
|
28 |
-
"use_cache":
|
29 |
-
"vocab_size":
|
30 |
-
"word_embed_proj_dim": 512
|
31 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "domsebalj/GPcroaT",
|
3 |
+
"activation_function": "gelu_new",
|
|
|
|
|
4 |
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
|
|
|
|
10 |
"eos_token_id": 2,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
"pad_token_id": 1,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.36.0.dev0",
|
38 |
+
"use_cache": false,
|
39 |
+
"vocab_size": 50257
|
|
|
40 |
}
|
model.safetensors
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:c84256dfbb1f379817a0f1c25db6aacbd94e2d0f41dd20934e996ad3e6dc2c92
|
3 |
+
size 497774208
|
runs/Apr25_01-16-05_DESKTOP-0IP9EM7/events.out.tfevents.1714000586.DESKTOP-0IP9EM7.8980.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e392737c82932614aa13da7d1df6249e0924ac4017a5c1bda50995f4ab66ae37
|
3 |
+
size 9112
|
runs/Apr25_01-16-05_DESKTOP-0IP9EM7/events.out.tfevents.1714000979.DESKTOP-0IP9EM7.8980.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8bf3a5fab5492b1336d2d282ffecb0d11e0366baca53d0cbc63d687afa85bca
|
3 |
+
size 4757
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71790111b2ff34e6c22447616b8c197b3fc68e4800fe4796e0d27b1f3e90c024
|
3 |
size 4664
|