xinhe commited on
Commit
686aebc
1 Parent(s): 933899d

upload fp32 model

Browse files
README.md CHANGED
@@ -1,3 +1,77 @@
1
  ---
 
 
2
  license: mit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
  license: mit
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ model-index:
13
+ - name: xlnet-base-cased-mrpc
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: GLUE MRPC
20
+ type: glue
21
+ args: mrpc
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8455882352941176
26
+ - name: F1
27
+ type: f1
28
+ value: 0.8896672504378283
29
  ---
30
+
31
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
+ should probably proofread and complete it, then remove this comment. -->
33
+
34
+ # xlnet-base-cased-mrpc
35
+
36
+ This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the GLUE MRPC dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.7156
39
+ - Accuracy: 0.8456
40
+ - F1: 0.8897
41
+ - Combined Score: 0.8676
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 2e-05
61
+ - train_batch_size: 16
62
+ - eval_batch_size: 8
63
+ - seed: 42
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: linear
66
+ - num_epochs: 5.0
67
+
68
+ ### Training results
69
+
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.18.0
75
+ - Pytorch 1.10.0+cu102
76
+ - Datasets 2.1.0
77
+ - Tokenizers 0.11.6
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8455882352941176,
4
+ "eval_combined_score": 0.867627742865973,
5
+ "eval_f1": 0.8896672504378283,
6
+ "eval_loss": 0.7156228423118591,
7
+ "eval_runtime": 28.4059,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 14.363,
10
+ "eval_steps_per_second": 1.795,
11
+ "train_loss": 0.2684407242484715,
12
+ "train_runtime": 5649.8451,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 3.246,
15
+ "train_steps_per_second": 0.204
16
+ }
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "mrpc",
18
+ "id2label": {
19
+ "0": "not_equivalent",
20
+ "1": "equivalent"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "equivalent": 1,
25
+ "not_equivalent": 0
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "mem_len": null,
29
+ "model_type": "xlnet",
30
+ "n_head": 12,
31
+ "n_layer": 12,
32
+ "pad_token_id": 5,
33
+ "problem_type": "single_label_classification",
34
+ "reuse_len": null,
35
+ "same_length": false,
36
+ "start_n_top": 5,
37
+ "summary_activation": "tanh",
38
+ "summary_last_dropout": 0.1,
39
+ "summary_type": "last",
40
+ "summary_use_proj": true,
41
+ "task_specific_params": {
42
+ "text-generation": {
43
+ "do_sample": true,
44
+ "max_length": 250
45
+ }
46
+ },
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.18.0",
49
+ "untie_r": true,
50
+ "use_mems_eval": true,
51
+ "use_mems_train": false,
52
+ "vocab_size": 32000
53
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8455882352941176,
4
+ "eval_combined_score": 0.867627742865973,
5
+ "eval_f1": 0.8896672504378283,
6
+ "eval_loss": 0.7156228423118591,
7
+ "eval_runtime": 28.4059,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 14.363,
10
+ "eval_steps_per_second": 1.795
11
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647ba3eec5026c3900f003c4a3b58fa45e4a9b39a2233f2ba4e0e7210a267cee
3
+ size 469306973
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"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.2684407242484715,
4
+ "train_runtime": 5649.8451,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 3.246,
7
+ "train_steps_per_second": 0.204
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 1150,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.17,
12
+ "learning_rate": 1.1304347826086957e-05,
13
+ "loss": 0.4261,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 4.35,
18
+ "learning_rate": 2.6086956521739132e-06,
19
+ "loss": 0.1647,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 5.0,
24
+ "step": 1150,
25
+ "total_flos": 2612352163491840.0,
26
+ "train_loss": 0.2684407242484715,
27
+ "train_runtime": 5649.8451,
28
+ "train_samples_per_second": 3.246,
29
+ "train_steps_per_second": 0.204
30
+ }
31
+ ],
32
+ "max_steps": 1150,
33
+ "num_train_epochs": 5,
34
+ "total_flos": 2612352163491840.0,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62e5a671aa2a65b27140fbb487c094a58ebe69c2d6d73c0f07e2938b7dd7c1e
3
+ size 3055