Edward Gow-Smith commited on
Commit
f2dba93
1 Parent(s): 67be74b

added model

Browse files

config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "results/xlnet-base-cased-FalseTrue0-1",
3
+ "architectures": [
4
+ "XLNetForSequenceClassification"
5
+ ],
6
+ "attn_type": "bi",
7
+ "bi_data": false,
8
+ "bos_token_id": 1,
9
+ "clamp_len": -1,
10
+ "d_head": 64,
11
+ "d_inner": 3072,
12
+ "d_model": 768,
13
+ "dropout": 0.1,
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
+ "initializer_range": 0.02,
18
+ "layer_norm_eps": 1e-12,
19
+ "mem_len": null,
20
+ "model_type": "xlnet",
21
+ "n_head": 12,
22
+ "n_layer": 12,
23
+ "pad_token_id": 5,
24
+ "reuse_len": null,
25
+ "same_length": false,
26
+ "start_n_top": 5,
27
+ "summary_activation": "tanh",
28
+ "summary_last_dropout": 0.1,
29
+ "summary_type": "last",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 250
35
+ }
36
+ },
37
+ "transformers_version": "4.6.0.dev0",
38
+ "untie_r": true,
39
+ "use_mems_eval": true,
40
+ "use_mems_train": false,
41
+ "vocab_size": 32000
42
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4682ac012ec703c13c395cdf2d903fa675cb4248c0f796058ae9ae869f850290
3
+ size 938609441
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ce3a3f9a24b74a093e7f0141c3a97221e3b6f3604ef5a8938e3e3bf2c19a4c
3
+ size 469322193
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1825773cc31372f9e7539e27c6acf17ff906d240466d81932ff305dd2ad4661
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<eop>", "<eod>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<eop>", "<eod>"], "special_tokens_map_file": null, "name_or_path": "results/xlnet-base-cased-FalseTrue0-1"}
trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.0,
5
+ "global_step": 21,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.8004291653633118,
13
+ "eval_f1": 0.8318264014466547,
14
+ "eval_loss": 0.6778749227523804,
15
+ "eval_runtime": 10.0381,
16
+ "eval_samples_per_second": 46.423,
17
+ "step": 3
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.8025751113891602,
22
+ "eval_f1": 0.8486842105263158,
23
+ "eval_loss": 0.46581605076789856,
24
+ "eval_runtime": 10.1348,
25
+ "eval_samples_per_second": 45.98,
26
+ "step": 6
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_accuracy": 0.8133047223091125,
31
+ "eval_f1": 0.8580750407830342,
32
+ "eval_loss": 0.42553967237472534,
33
+ "eval_runtime": 10.1921,
34
+ "eval_samples_per_second": 45.722,
35
+ "step": 9
36
+ },
37
+ {
38
+ "epoch": 4.0,
39
+ "eval_accuracy": 0.8412017226219177,
40
+ "eval_f1": 0.8774834437086093,
41
+ "eval_loss": 0.38268426060676575,
42
+ "eval_runtime": 10.2307,
43
+ "eval_samples_per_second": 45.549,
44
+ "step": 12
45
+ },
46
+ {
47
+ "epoch": 5.0,
48
+ "eval_accuracy": 0.8798283338546753,
49
+ "eval_f1": 0.903114186851211,
50
+ "eval_loss": 0.3336368203163147,
51
+ "eval_runtime": 10.2564,
52
+ "eval_samples_per_second": 45.435,
53
+ "step": 15
54
+ },
55
+ {
56
+ "epoch": 6.0,
57
+ "eval_accuracy": 0.8927038908004761,
58
+ "eval_f1": 0.9131944444444444,
59
+ "eval_loss": 0.3360987901687622,
60
+ "eval_runtime": 10.2682,
61
+ "eval_samples_per_second": 45.383,
62
+ "step": 18
63
+ },
64
+ {
65
+ "epoch": 7.0,
66
+ "eval_accuracy": 0.9034335017204285,
67
+ "eval_f1": 0.9222797927461139,
68
+ "eval_loss": 0.3484722375869751,
69
+ "eval_runtime": 10.234,
70
+ "eval_samples_per_second": 45.535,
71
+ "step": 21
72
+ }
73
+ ],
74
+ "max_steps": 27,
75
+ "num_train_epochs": 9,
76
+ "total_flos": 7838216096256.0,
77
+ "trial_name": null,
78
+ "trial_params": null
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8929fa397b0dcda9ce8e2da1b2738c6467b4c882c7b679572a5117fedaec6d1a
3
+ size 2415