Training in progress, step 500
Browse files
config.json
CHANGED
@@ -1,32 +1,46 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "LABEL_0"
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
16 |
-
"intermediate_size": 3072,
|
17 |
"label2id": {
|
18 |
"LABEL_0": 0
|
19 |
},
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"torch_dtype": "float32",
|
28 |
"transformers_version": "4.45.1",
|
29 |
-
"type_vocab_size": 2,
|
30 |
"use_cache": true,
|
31 |
-
"vocab_size":
|
32 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert/distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
|
|
|
|
12 |
"id2label": {
|
13 |
"0": "LABEL_0"
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
|
|
16 |
"label2id": {
|
17 |
"LABEL_0": 0
|
18 |
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
"torch_dtype": "float32",
|
43 |
"transformers_version": "4.45.1",
|
|
|
44 |
"use_cache": true,
|
45 |
+
"vocab_size": 50257
|
46 |
}
|
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 sha256:444ce32243fa0377e0d1e906d193b4d4ef97438a591ef13679d9c1ecb89cc1a0
|
3 |
+
size 327657928
|
runs/Oct10_22-07-07_sirius/events.out.tfevents.1728619628.sirius.2238978.3
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:ec562d760f010eba1c6ff6097809889df750c727ff5289a43adcb88b29f988dc
|
3 |
+
size 6411
|
runs/Oct19_20-35-39_sirius/events.out.tfevents.1729391741.sirius.2479049.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd34ca80b563e1c8902b3d764f01a3db43ae1a3874d301f11bbb68b4a59bfdde
|
3 |
+
size 5768
|
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 sha256:5b964f79a8b026e8b7e3280224e29f91dac7732f3e6c8de3112efdd198c2ec5e
|
3 |
size 5240
|