xinhe commited on
Commit
f2f8409
1 Parent(s): 8b406b7

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: roberta-base-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: 0.8774509803921569
26
+ - name: F1
27
+ type: f1
28
+ value: 0.9137931034482758
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
+ # roberta-base-mrpc
35
+
36
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the GLUE MRPC dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.5565
39
+ - Accuracy: 0.8775
40
+ - F1: 0.9138
41
+ - Combined Score: 0.8956
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": 0.8774509803921569,
4
+ "eval_combined_score": 0.8956220419202163,
5
+ "eval_f1": 0.9137931034482758,
6
+ "eval_loss": 0.5565009117126465,
7
+ "eval_runtime": 10.3375,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 39.468,
10
+ "eval_steps_per_second": 4.933,
11
+ "train_loss": 0.2803073907935101,
12
+ "train_runtime": 6011.5008,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 3.051,
15
+ "train_steps_per_second": 0.191
16
+ }
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "mrpc",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "not_equivalent",
16
+ "1": "equivalent"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "equivalent": 1,
22
+ "not_equivalent": 0
23
+ },
24
+ "layer_norm_eps": 1e-05,
25
+ "max_position_embeddings": 514,
26
+ "model_type": "roberta",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.18.0",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 50265
37
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8774509803921569,
4
+ "eval_combined_score": 0.8956220419202163,
5
+ "eval_f1": 0.9137931034482758,
6
+ "eval_loss": 0.5565009117126465,
7
+ "eval_runtime": 10.3375,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 39.468,
10
+ "eval_steps_per_second": 4.933
11
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7938b88f6f408a2414fdc41230f990c06ac16e1025575f14c629d5246bcaab7
3
+ size 498657517
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.2803073907935101,
4
+ "train_runtime": 6011.5008,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 3.051,
7
+ "train_steps_per_second": 0.191
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": 0.4267,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 4.35,
18
+ "learning_rate": 2.6086956521739132e-06,
19
+ "loss": 0.1886,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 5.0,
24
+ "step": 1150,
25
+ "total_flos": 2412728377651200.0,
26
+ "train_loss": 0.2803073907935101,
27
+ "train_runtime": 6011.5008,
28
+ "train_samples_per_second": 3.051,
29
+ "train_steps_per_second": 0.191
30
+ }
31
+ ],
32
+ "max_steps": 1150,
33
+ "num_train_epochs": 5,
34
+ "total_flos": 2412728377651200.0,
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 sha256:5d97d89295ed50c09704af46bdabf4d6482fd899dbc66951d064f4d225c8f688
3
+ size 3055
vocab.json ADDED
The diff for this file is too large to render. See raw diff