Hugging Face's logo

visegradmedia-emotion
/
Emotion_RoBERTa_german6_v7

Text Classification
Transformers
TensorBoard
Safetensors
German
xlm-roberta
emotion-classification
roberta
fine-tuned
german
Eval Results
Inference Endpoints
Model card Files Metrics Community
ringorsolya commited on
Commit
e80ddbf
•
1 Parent(s): 2f2f3e5

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-11636/config.json +45 -0
  2. checkpoint-11636/model.safetensors +3 -0
  3. checkpoint-11636/optimizer.pt +3 -0
  4. checkpoint-11636/rng_state.pth +3 -0
  5. checkpoint-11636/scheduler.pt +3 -0
  6. checkpoint-11636/trainer_state.json +118 -0
  7. checkpoint-11636/training_args.bin +3 -0
  8. config.json +45 -0
  9. events.out.tfevents.1721195436.3849cf64efaa.1701.0 +3 -0
  10. model.safetensors +3 -0
  11. moresBERT_train_german6_reduced_3520.xlsx +0 -0
  12. test_data.xlsx +0 -0
  13. test_data_original.xlsx +0 -0
  14. training_args.bin +3 -0
checkpoint-11636/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "xlm-roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_past": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "multi_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.42.4",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 250002
45
+ }
checkpoint-11636/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46818477dbbc7540ce52c6775ee7c7b1307a6930b025a04001f650a7ac0e94b
3
+ size 1112217312
checkpoint-11636/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d6be132599f77b08a23222ce61f44f358e8d4bdc30a6ddb09f48c26e65d0db
3
+ size 2224554234
checkpoint-11636/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5753c9c57b5ba512a320323bbacddbe4706b9614c657a6cae85eb014b47f8423
3
+ size 14244
checkpoint-11636/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe734f183c28726442e39763a4012097758103830e87ef8ac8f1a29b59f6dae
3
+ size 1064
checkpoint-11636/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1422930359840393,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/RoBERTa/checkpoint-11636",
4
+ "epoch": 4.0,
5
+ "eval_steps": 100,
6
+ "global_step": 11636,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 5.20160436630249,
14
+ "learning_rate": 4.5e-06,
15
+ "loss": 0.2335,
16
+ "step": 2909
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8119305483926422,
21
+ "eval_f1": 0.8125438936194447,
22
+ "eval_loss": 0.15657220780849457,
23
+ "eval_precision": 0.8148818865641057,
24
+ "eval_recall": 0.8119305483926422,
25
+ "eval_runtime": 99.4857,
26
+ "eval_samples_per_second": 58.471,
27
+ "eval_steps_per_second": 3.659,
28
+ "step": 2909
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 3.025620937347412,
33
+ "learning_rate": 4.000000000000001e-06,
34
+ "loss": 0.1564,
35
+ "step": 5818
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8196664947567475,
40
+ "eval_f1": 0.819601210384621,
41
+ "eval_loss": 0.14257530868053436,
42
+ "eval_precision": 0.8231443904443204,
43
+ "eval_recall": 0.8196664947567475,
44
+ "eval_runtime": 99.334,
45
+ "eval_samples_per_second": 58.56,
46
+ "eval_steps_per_second": 3.664,
47
+ "step": 5818
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 5.3682355880737305,
52
+ "learning_rate": 3.5e-06,
53
+ "loss": 0.1403,
54
+ "step": 8727
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8134777376654633,
59
+ "eval_f1": 0.8103113366034572,
60
+ "eval_loss": 0.14786231517791748,
61
+ "eval_precision": 0.8253242439784585,
62
+ "eval_recall": 0.8134777376654633,
63
+ "eval_runtime": 99.221,
64
+ "eval_samples_per_second": 58.627,
65
+ "eval_steps_per_second": 3.669,
66
+ "step": 8727
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 24.70423126220703,
71
+ "learning_rate": 3e-06,
72
+ "loss": 0.13,
73
+ "step": 11636
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8201822245143545,
78
+ "eval_f1": 0.8192565062099832,
79
+ "eval_loss": 0.1422930359840393,
80
+ "eval_precision": 0.8239091740579143,
81
+ "eval_recall": 0.8201822245143545,
82
+ "eval_runtime": 99.1112,
83
+ "eval_samples_per_second": 58.692,
84
+ "eval_steps_per_second": 3.673,
85
+ "step": 11636
86
+ }
87
+ ],
88
+ "logging_steps": 100,
89
+ "max_steps": 29090,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 10,
92
+ "save_steps": 100,
93
+ "stateful_callbacks": {
94
+ "EarlyStoppingCallback": {
95
+ "args": {
96
+ "early_stopping_patience": 2,
97
+ "early_stopping_threshold": 0.0
98
+ },
99
+ "attributes": {
100
+ "early_stopping_patience_counter": 0
101
+ }
102
+ },
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": false
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 4.897619828740915e+16,
115
+ "train_batch_size": 16,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-11636/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b0cf35159a87a40f7d00aac1283cee32991a88b237343acab3942b89e7e8ba8
3
+ size 5048
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "xlm-roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_past": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "multi_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.42.4",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 250002
45
+ }
events.out.tfevents.1721195436.3849cf64efaa.1701.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757b263e542cdc313dd2f75533ca5039fdfab32ee382bd8f0f4ecdcb67cec62f
3
+ size 9665
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46818477dbbc7540ce52c6775ee7c7b1307a6930b025a04001f650a7ac0e94b
3
+ size 1112217312
moresBERT_train_german6_reduced_3520.xlsx ADDED
Binary file (726 kB). View file
 
test_data.xlsx ADDED
Binary file (384 kB). View file
 
test_data_original.xlsx ADDED
Binary file (700 kB). View file
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b0cf35159a87a40f7d00aac1283cee32991a88b237343acab3942b89e7e8ba8
3
+ size 5048