debatelab-admin
commited on
Commit
•
bca488f
1
Parent(s):
35f6dff
upload model
Browse files- config.json +33 -0
- log_history.json +65 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"gradient_checkpointing": false,
|
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 |
+
"resid_pdrop": 0.1,
|
21 |
+
"summary_activation": null,
|
22 |
+
"summary_first_dropout": 0.1,
|
23 |
+
"summary_proj_to_labels": true,
|
24 |
+
"summary_type": "cls_index",
|
25 |
+
"summary_use_proj": true,
|
26 |
+
"task_specific_params": {
|
27 |
+
"text-generation": {
|
28 |
+
"do_sample": true,
|
29 |
+
"max_length": 50
|
30 |
+
}
|
31 |
+
},
|
32 |
+
"vocab_size": 50257
|
33 |
+
}
|
log_history.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"loss": 2.096086181640625,
|
4 |
+
"learning_rate": 4.4444444444444447e-05,
|
5 |
+
"epoch": 0.2222222222222222,
|
6 |
+
"total_flos": 1529116360704000,
|
7 |
+
"step": 500
|
8 |
+
},
|
9 |
+
{
|
10 |
+
"loss": 1.851991455078125,
|
11 |
+
"learning_rate": 3.888888888888889e-05,
|
12 |
+
"epoch": 0.4444444444444444,
|
13 |
+
"total_flos": 3058232721408000,
|
14 |
+
"step": 1000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"loss": 1.8009189453125,
|
18 |
+
"learning_rate": 3.3333333333333335e-05,
|
19 |
+
"epoch": 0.6666666666666666,
|
20 |
+
"total_flos": 4587349082112000,
|
21 |
+
"step": 1500
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"loss": 1.770126953125,
|
25 |
+
"learning_rate": 2.777777777777778e-05,
|
26 |
+
"epoch": 0.8888888888888888,
|
27 |
+
"total_flos": 6116465442816000,
|
28 |
+
"step": 2000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"loss": 1.71751513671875,
|
32 |
+
"learning_rate": 2.2222222222222223e-05,
|
33 |
+
"epoch": 1.1111111111111112,
|
34 |
+
"total_flos": 7645581803520000,
|
35 |
+
"step": 2500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"loss": 1.6680078125,
|
39 |
+
"learning_rate": 1.6666666666666667e-05,
|
40 |
+
"epoch": 1.3333333333333333,
|
41 |
+
"total_flos": 9174698164224000,
|
42 |
+
"step": 3000
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"loss": 1.6722744140625,
|
46 |
+
"learning_rate": 1.1111111111111112e-05,
|
47 |
+
"epoch": 1.5555555555555556,
|
48 |
+
"total_flos": 10703814524928000,
|
49 |
+
"step": 3500
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"loss": 1.64707421875,
|
53 |
+
"learning_rate": 5.555555555555556e-06,
|
54 |
+
"epoch": 1.7777777777777777,
|
55 |
+
"total_flos": 12232930885632000,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"loss": 1.667453125,
|
60 |
+
"learning_rate": 0.0,
|
61 |
+
"epoch": 2.0,
|
62 |
+
"total_flos": 13762047246336000,
|
63 |
+
"step": 4500
|
64 |
+
}
|
65 |
+
]
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fab882c102a886c158d75de18e0da94758910a3824990d6f48dc6da5dad62c1
|
3 |
+
size 510408315
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d15a1dac50e52ee2caa4bd7846d36b52cc7afcb4742d5640a035f519c10e2823
|
3 |
+
size 1839
|