Harish Tayyar Madabushi commited on
Commit
b9616c4
1 Parent(s): 05b3430

added model

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlnet-base-cased",
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:ad36347408aa680a463a9e4a94765f25aa2c3f5852e385a715dca1abfa121767
3
+ size 938605498
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9c5a68f2b884f98f36dcbb00f1182dbe87431e2e13a554c9ea0b5419ae2e5b
3
+ size 469320121
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d779661500d8538e01dbb4ff04f953019ee782563f47a80d6bd8c1188a341b7
3
+ size 14647
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477942c74c3089ba96f7d3d1f346e421a58618837e875bf62691456abb3463a4
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": "xlnet-base-cased", "tokenizer_class": "XLNetTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8225606853879106,
3
+ "best_model_checkpoint": "output-no-git/EN-OUTPUT/xlnet-base-cased/FalseTrue-0/1/checkpoint-312",
4
+ "epoch": 3.0,
5
+ "global_step": 312,
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": 0.7875536680221558,
13
+ "eval_f1": 0.7775119963347881,
14
+ "eval_f1_binary": 0.8247787610619469,
15
+ "eval_f1_weighted": 0.7878579405454538,
16
+ "eval_loss": 0.5327664017677307,
17
+ "eval_runtime": 1.8369,
18
+ "eval_samples_per_second": 253.685,
19
+ "eval_steps_per_second": 32.119,
20
+ "step": 104
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.7982832789421082,
25
+ "eval_f1": 0.7889492753623188,
26
+ "eval_f1_binary": 0.8333333333333334,
27
+ "eval_f1_weighted": 0.7986642408409529,
28
+ "eval_loss": 1.0078827142715454,
29
+ "eval_runtime": 1.83,
30
+ "eval_samples_per_second": 254.641,
31
+ "eval_steps_per_second": 32.24,
32
+ "step": 208
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.8283261656761169,
37
+ "eval_f1": 0.8225606853879106,
38
+ "eval_f1_binary": 0.8545454545454546,
39
+ "eval_f1_weighted": 0.8295616434438536,
40
+ "eval_loss": 0.77229905128479,
41
+ "eval_runtime": 1.8293,
42
+ "eval_samples_per_second": 254.742,
43
+ "eval_steps_per_second": 32.253,
44
+ "step": 312
45
+ }
46
+ ],
47
+ "max_steps": 936,
48
+ "num_train_epochs": 9,
49
+ "total_flos": 710847517552128.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735ad523505f78488984ea19e3855292231736542e50b657df894edc95b016fc
3
+ size 2735