tzartrooper
commited on
Commit
•
b162eab
1
Parent(s):
bd7a7d4
Training in progress, step 500
Browse files- config.json +46 -0
- model.safetensors +3 -0
- runs/Mar16_14-09-40_beff20e9b121/events.out.tfevents.1710598181.beff20e9b121.823.0 +3 -0
- runs/Mar16_14-11-58_beff20e9b121/events.out.tfevents.1710598318.beff20e9b121.823.1 +3 -0
- runs/Mar16_14-13-36_beff20e9b121/events.out.tfevents.1710598417.beff20e9b121.823.2 +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "4.38.2",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50257
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2927df402581b05cc0293fd9527c7cbf0a47fa91bcfe73c0d95c1ef9c06d76d3
|
3 |
+
size 327657928
|
runs/Mar16_14-09-40_beff20e9b121/events.out.tfevents.1710598181.beff20e9b121.823.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82be4cb35c9e65b7388882c179d5ca251d2626ce549250cb699ab75c34609646
|
3 |
+
size 4993
|
runs/Mar16_14-11-58_beff20e9b121/events.out.tfevents.1710598318.beff20e9b121.823.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79b008e36c40ae181b3f854dab0673d4f7a35b82116dbf694ae0e1d3681a1a19
|
3 |
+
size 4993
|
runs/Mar16_14-13-36_beff20e9b121/events.out.tfevents.1710598417.beff20e9b121.823.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cae82a68e837a1841eacedf84c4f47d3ce0e0d4411e4d69827b7527cb00ffca
|
3 |
+
size 5204
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a09044870fb2f5147cacc5deddc4e427eebe3f4b0d14e5243d24a0527feb0d57
|
3 |
+
size 4920
|