debatelab-admin commited on
Commit
fe9104c
1 Parent(s): 7530210

upload model

Browse files
Files changed (4) hide show
  1. config.json +35 -0
  2. log_history.json +65 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "resid_pdrop": 0.1,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "vocab_size": 50257
35
+ }
log_history.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "loss": 1.7883309326171875,
4
+ "learning_rate": 4.4444444444444447e-05,
5
+ "epoch": 0.2222222222222222,
6
+ "total_flos": 4360067088384000,
7
+ "step": 500
8
+ },
9
+ {
10
+ "loss": 1.5973499755859375,
11
+ "learning_rate": 3.888888888888889e-05,
12
+ "epoch": 0.4444444444444444,
13
+ "total_flos": 8720134176768000,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "loss": 1.551248291015625,
18
+ "learning_rate": 3.3333333333333335e-05,
19
+ "epoch": 0.6666666666666666,
20
+ "total_flos": 13080201265152000,
21
+ "step": 1500
22
+ },
23
+ {
24
+ "loss": 1.51922998046875,
25
+ "learning_rate": 2.777777777777778e-05,
26
+ "epoch": 0.8888888888888888,
27
+ "total_flos": 17440268353536000,
28
+ "step": 2000
29
+ },
30
+ {
31
+ "loss": 1.4523193359375,
32
+ "learning_rate": 2.2222222222222223e-05,
33
+ "epoch": 1.1111111111111112,
34
+ "total_flos": 21800335441920000,
35
+ "step": 2500
36
+ },
37
+ {
38
+ "loss": 1.389939453125,
39
+ "learning_rate": 1.6666666666666667e-05,
40
+ "epoch": 1.3333333333333333,
41
+ "total_flos": 26160402530304000,
42
+ "step": 3000
43
+ },
44
+ {
45
+ "loss": 1.3925107421875,
46
+ "learning_rate": 1.1111111111111112e-05,
47
+ "epoch": 1.5555555555555556,
48
+ "total_flos": 30520469618688000,
49
+ "step": 3500
50
+ },
51
+ {
52
+ "loss": 1.36883984375,
53
+ "learning_rate": 5.555555555555556e-06,
54
+ "epoch": 1.7777777777777777,
55
+ "total_flos": 34880536707072000,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "loss": 1.3849873046875,
60
+ "learning_rate": 0.0,
61
+ "epoch": 2.0,
62
+ "total_flos": 39240603795456000,
63
+ "step": 4500
64
+ }
65
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abdd983e3d1a03c1215dd8ea582e73c5e6ae2466c428aae6b4147302133ee7b
3
+ size 1444589475
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfd4fe86d4f1de186454af395601d618d412be0cb6fd8575f9dc984371aee95
3
+ size 1839