Hugging Face's logo

uvegesistvan
/
wildmann_german_proposal_1

TensorBoard
Safetensors
English
xlm-roberta
emotion-classification
text-analysis
Model card Files Metrics Community
uvegesistvan commited on
Commit
fc089f1
·
verified ·
1 Parent(s): 5893381

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-4410/config.json +51 -0
  2. checkpoint-4410/model.safetensors +3 -0
  3. checkpoint-4410/optimizer.pt +3 -0
  4. checkpoint-4410/rng_state.pth +3 -0
  5. checkpoint-4410/scheduler.pt +3 -0
  6. checkpoint-4410/trainer_state.json +80 -0
  7. checkpoint-4410/training_args.bin +3 -0
  8. config.json +51 -0
  9. events.out.tfevents.1734268801.5dc78d0c0094.597.10 +3 -0
  10. events.out.tfevents.1734292683.26dae68edbc1.519.0 +3 -0
  11. events.out.tfevents.1734293482.15565a6fdb0d.517.0 +3 -0
  12. events.out.tfevents.1734299316.15565a6fdb0d.14799.0 +3 -0
  13. model.safetensors +3 -0
  14. training_args.bin +3 -0
checkpoint-4410/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
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": 1024,
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
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "problem_type": "single_label_classification",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.47.0",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
checkpoint-4410/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bff3c3206e752f2a4247168df34eee1719863889ad6b645d17c3acc45d58cf0
3
+ size 2239647372
checkpoint-4410/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19433272c864b8281d437bf5c08d94b352fabbaf65c4995225a40bfb693bad5b
3
+ size 4479530129
checkpoint-4410/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e435b40d5be1c7c112f86239ff8b4ba9d10355241a4327cdb848ce0835fb13
3
+ size 14244
checkpoint-4410/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9513b58ff967203466b7afdb6d49ebbbe6f8fef74f5ee039176002fb6b70289c
3
+ size 1064
checkpoint-4410/trainer_state.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.2541574239730835,
3
+ "best_model_checkpoint": "model/checkpoint-4410",
4
+ "epoch": 2.0,
5
+ "eval_steps": 100,
6
+ "global_step": 4410,
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": 44.31188201904297,
14
+ "learning_rate": 8.333333333333334e-06,
15
+ "loss": 1.584,
16
+ "step": 2205
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5222222222222223,
21
+ "eval_f1": 0.515083636023541,
22
+ "eval_loss": 1.2932672500610352,
23
+ "eval_precision": 0.5406457440910268,
24
+ "eval_recall": 0.5222222222222223,
25
+ "eval_runtime": 58.9593,
26
+ "eval_samples_per_second": 74.797,
27
+ "eval_steps_per_second": 4.681,
28
+ "step": 2205
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 21.185283660888672,
33
+ "learning_rate": 6.666666666666667e-06,
34
+ "loss": 1.2405,
35
+ "step": 4410
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.5344671201814059,
40
+ "eval_f1": 0.5194090089676107,
41
+ "eval_loss": 1.2541574239730835,
42
+ "eval_precision": 0.537798009379494,
43
+ "eval_recall": 0.5344671201814059,
44
+ "eval_runtime": 58.8691,
45
+ "eval_samples_per_second": 74.912,
46
+ "eval_steps_per_second": 4.688,
47
+ "step": 4410
48
+ }
49
+ ],
50
+ "logging_steps": 100,
51
+ "max_steps": 13230,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 6,
54
+ "save_steps": 100,
55
+ "stateful_callbacks": {
56
+ "EarlyStoppingCallback": {
57
+ "args": {
58
+ "early_stopping_patience": 2,
59
+ "early_stopping_threshold": 0.0
60
+ },
61
+ "attributes": {
62
+ "early_stopping_patience_counter": 0
63
+ }
64
+ },
65
+ "TrainerControl": {
66
+ "args": {
67
+ "should_epoch_stop": false,
68
+ "should_evaluate": false,
69
+ "should_log": false,
70
+ "should_save": true,
71
+ "should_training_stop": false
72
+ },
73
+ "attributes": {}
74
+ }
75
+ },
76
+ "total_flos": 3.287931612585984e+16,
77
+ "train_batch_size": 16,
78
+ "trial_name": null,
79
+ "trial_params": null
80
+ }
checkpoint-4410/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
3
+ size 5240
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
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": 1024,
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
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "problem_type": "single_label_classification",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.47.0",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
events.out.tfevents.1734268801.5dc78d0c0094.597.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc1315c7e1f2183cb5b32925df2e7b72f36542226b646d07a45f3c2ae0533f0
3
+ size 8513
events.out.tfevents.1734292683.26dae68edbc1.519.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153851a01c1db2c0602694cc5524d930f1f95c7a7c3a8cd4d23bbb7b09b9dc0a
3
+ size 5395
events.out.tfevents.1734293482.15565a6fdb0d.517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5315719c053e1861da202c80e15d78116f848d40ccf4a2f40dcb34688c8375dc
3
+ size 7444
events.out.tfevents.1734299316.15565a6fdb0d.14799.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30436099c0ccf2daef57aa51b47cca5db54f956c27940eddb55b1a3664918dc
3
+ size 8481
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bff3c3206e752f2a4247168df34eee1719863889ad6b645d17c3acc45d58cf0
3
+ size 2239647372
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
3
+ size 5240