Harish Tayyar Madabushi commited on
Commit
e9d9916
1 Parent(s): e67f3f4

added model

Browse files

config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output-no-git/EN-OUTPUT/xlnet-base-cased/ForZeroFew/",
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
+ "problem_type": "single_label_classification",
25
+ "reuse_len": null,
26
+ "same_length": false,
27
+ "start_n_top": 5,
28
+ "summary_activation": "tanh",
29
+ "summary_last_dropout": 0.1,
30
+ "summary_type": "last",
31
+ "summary_use_proj": true,
32
+ "task_specific_params": {
33
+ "text-generation": {
34
+ "do_sample": true,
35
+ "max_length": 250
36
+ }
37
+ },
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.10.0.dev0",
40
+ "untie_r": true,
41
+ "use_mems_eval": true,
42
+ "use_mems_train": false,
43
+ "vocab_size": 32000
44
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3219a473e3b96b63070fc7f0a9d8a44d5348402abda9203e1ef16ad60f5a6e
3
+ size 938605244
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f4c8b5d8703e7d12cce21f6c676cba042057aa9b36632ebd41870be9a43214
3
+ size 469320127
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0655a8f37cde43be460274ecae711d7e8c58d41c02a1f4a477e989fb245bc0a
3
+ size 14583
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4368ad420157f7355673704fa0c7355bbd997a50e22ca62121062e961a3b08f8
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": "output-no-git/EN-OUTPUT/xlnet-base-cased/ForZeroFew/", "tokenizer_class": "XLNetTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7817807192807192,
3
+ "best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/TrueFalse-0/train_from_dev_and_test.csv/0/checkpoint-72",
4
+ "epoch": 8.0,
5
+ "global_step": 72,
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": 0.7317596673965454,
13
+ "eval_f1": 0.6922337227303228,
14
+ "eval_f1_binary": 0.8025276461295419,
15
+ "eval_f1_weighted": 0.7163753111138428,
16
+ "eval_loss": 0.5622926354408264,
17
+ "eval_runtime": 1.8244,
18
+ "eval_samples_per_second": 255.432,
19
+ "eval_steps_per_second": 32.34,
20
+ "step": 9
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.7103004455566406,
25
+ "eval_f1": 0.6222324972527637,
26
+ "eval_f1_binary": 0.804630969609262,
27
+ "eval_f1_weighted": 0.6621566263951731,
28
+ "eval_loss": 0.5607165694236755,
29
+ "eval_runtime": 1.8304,
30
+ "eval_samples_per_second": 254.587,
31
+ "eval_steps_per_second": 32.233,
32
+ "step": 18
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.7618025541305542,
37
+ "eval_f1": 0.7149061647421942,
38
+ "eval_f1_binary": 0.8305343511450382,
39
+ "eval_f1_weighted": 0.740215338590027,
40
+ "eval_loss": 0.5542925000190735,
41
+ "eval_runtime": 1.821,
42
+ "eval_samples_per_second": 255.897,
43
+ "eval_steps_per_second": 32.399,
44
+ "step": 27
45
+ },
46
+ {
47
+ "epoch": 4.0,
48
+ "eval_accuracy": 0.7618025541305542,
49
+ "eval_f1": 0.7346772332076633,
50
+ "eval_f1_binary": 0.8195121951219512,
51
+ "eval_f1_weighted": 0.7532462592060696,
52
+ "eval_loss": 0.5325024724006653,
53
+ "eval_runtime": 1.8314,
54
+ "eval_samples_per_second": 254.445,
55
+ "eval_steps_per_second": 32.215,
56
+ "step": 36
57
+ },
58
+ {
59
+ "epoch": 5.0,
60
+ "eval_accuracy": 0.770386278629303,
61
+ "eval_f1": 0.7204214256477541,
62
+ "eval_f1_binary": 0.8386123680241327,
63
+ "eval_f1_weighted": 0.7462915460820687,
64
+ "eval_loss": 0.6570885181427002,
65
+ "eval_runtime": 1.8193,
66
+ "eval_samples_per_second": 256.143,
67
+ "eval_steps_per_second": 32.43,
68
+ "step": 45
69
+ },
70
+ {
71
+ "epoch": 6.0,
72
+ "eval_accuracy": 0.7918455004692078,
73
+ "eval_f1": 0.759455072772264,
74
+ "eval_f1_binary": 0.847723704866562,
75
+ "eval_f1_weighted": 0.7787756746469816,
76
+ "eval_loss": 0.619213342666626,
77
+ "eval_runtime": 1.8279,
78
+ "eval_samples_per_second": 254.931,
79
+ "eval_steps_per_second": 32.277,
80
+ "step": 54
81
+ },
82
+ {
83
+ "epoch": 7.0,
84
+ "eval_accuracy": 0.8004291653633118,
85
+ "eval_f1": 0.7741342019543973,
86
+ "eval_f1_binary": 0.8511999999999998,
87
+ "eval_f1_weighted": 0.7910026813549369,
88
+ "eval_loss": 0.6259479522705078,
89
+ "eval_runtime": 1.8288,
90
+ "eval_samples_per_second": 254.808,
91
+ "eval_steps_per_second": 32.261,
92
+ "step": 63
93
+ },
94
+ {
95
+ "epoch": 8.0,
96
+ "eval_accuracy": 0.8068669438362122,
97
+ "eval_f1": 0.7817807192807192,
98
+ "eval_f1_binary": 0.8557692307692308,
99
+ "eval_f1_weighted": 0.7979756295206938,
100
+ "eval_loss": 0.6622598767280579,
101
+ "eval_runtime": 1.8334,
102
+ "eval_samples_per_second": 254.179,
103
+ "eval_steps_per_second": 32.182,
104
+ "step": 72
105
+ }
106
+ ],
107
+ "max_steps": 81,
108
+ "num_train_epochs": 9,
109
+ "total_flos": 160672477667328.0,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fdea2904f61695073d9fb39277bb65b922a1b6e161c17eccfcf9223a9f95b0
3
+ size 2799