Hugging Face's logo

uvegesistvan
/
wildmann_german_proposal_0

TensorBoard
Safetensors
multilingual
xlm-roberta
classification
emotions
Model card Files
xet
 Metrics Community
uvegesistvan commited on
Commit
386d1f6
·
verified ·
1 Parent(s): 0f061b3

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. checkpoint-12022/config.json +51 -0
  2. checkpoint-12022/model.safetensors +3 -0
  3. checkpoint-12022/optimizer.pt +3 -0
  4. checkpoint-12022/rng_state.pth +3 -0
  5. checkpoint-12022/scheduler.pt +3 -0
  6. checkpoint-12022/trainer_state.json +80 -0
  7. checkpoint-12022/training_args.bin +3 -0
  8. config.json +51 -0
  9. events.out.tfevents.1734268801.5dc78d0c0094.597.10 +3 -0
  10. model.safetensors +3 -0
  11. training_args.bin +3 -0
checkpoint-12022/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-12022/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11ac6c9e4d04a4389befd6e49c4922acf670b3aa318a534ec6eccc352ddb905
3
+ size 2239647372
checkpoint-12022/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:643b40e90d53a14a2de571a8c4b343f4ed90018f13dee13036ba3f1f0e211950
3
+ size 4479530129
checkpoint-12022/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9444c9a9ccbfb0a14f5f2e825c6f7635ea8d81e1415b30e254f5f35f266ac37b
3
+ size 14244
checkpoint-12022/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e187affbb1191783817bb2d38d92e09fee187d8e5ad29b11aebdb889c68530
3
+ size 1064
checkpoint-12022/trainer_state.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9693565368652344,
3
+ "best_model_checkpoint": "model/checkpoint-12022",
4
+ "epoch": 2.0,
5
+ "eval_steps": 100,
6
+ "global_step": 12022,
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": 14.125932693481445,
14
+ "learning_rate": 8.000000000000001e-06,
15
+ "loss": 1.0593,
16
+ "step": 6011
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6449010148061887,
21
+ "eval_f1": 0.6090798045608603,
22
+ "eval_loss": 0.9724791646003723,
23
+ "eval_precision": 0.6399609014205598,
24
+ "eval_recall": 0.6449010148061887,
25
+ "eval_runtime": 128.4211,
26
+ "eval_samples_per_second": 93.614,
27
+ "eval_steps_per_second": 5.856,
28
+ "step": 6011
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 10.282686233520508,
33
+ "learning_rate": 6e-06,
34
+ "loss": 0.9302,
35
+ "step": 12022
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6383297288304774,
40
+ "eval_f1": 0.605702835886063,
41
+ "eval_loss": 0.9693565368652344,
42
+ "eval_precision": 0.6297167704652535,
43
+ "eval_recall": 0.6383297288304774,
44
+ "eval_runtime": 128.6794,
45
+ "eval_samples_per_second": 93.426,
46
+ "eval_steps_per_second": 5.844,
47
+ "step": 12022
48
+ }
49
+ ],
50
+ "logging_steps": 100,
51
+ "max_steps": 30055,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 5,
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": 8.962875481214054e+16,
77
+ "train_batch_size": 16,
78
+ "trial_name": null,
79
+ "trial_params": null
80
+ }
checkpoint-12022/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c3abe8bc5fca362e1e10dd1bcb05eb54f12bac5fd23402f7502c9d72f499b5
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
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11ac6c9e4d04a4389befd6e49c4922acf670b3aa318a534ec6eccc352ddb905
3
+ size 2239647372
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c3abe8bc5fca362e1e10dd1bcb05eb54f12bac5fd23402f7502c9d72f499b5
3
+ size 5240