Hugging Face's logo

ringorsolya
/
wildman_german_balanced

TensorBoard
Safetensors
Model card Files Metrics Community
ringorsolya commited on
Commit
0399b21
•
1 Parent(s): d44b3c9

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-13230/config.json +51 -0
  2. checkpoint-13230/model.safetensors +3 -0
  3. checkpoint-13230/optimizer.pt +3 -0
  4. checkpoint-13230/rng_state.pth +3 -0
  5. checkpoint-13230/scheduler.pt +3 -0
  6. checkpoint-13230/trainer_state.json +99 -0
  7. checkpoint-13230/training_args.bin +3 -0
  8. events.out.tfevents.1732629299.237f633d3b75.10785.0 +3 -0
  9. events.out.tfevents.1732629498.237f633d3b75.10785.1 +3 -0
  10. events.out.tfevents.1732630471.237f633d3b75.10785.2 +3 -0
  11. events.out.tfevents.1732637550.237f633d3b75.10785.3 +3 -0
  12. events.out.tfevents.1732638176.237f633d3b75.10785.4 +3 -0
  13. events.out.tfevents.1732638466.237f633d3b75.10785.5 +3 -0
  14. events.out.tfevents.1732790113.fac4cbce8395.18098.0 +3 -0
checkpoint-13230/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": "multi_label_classification",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.46.3",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
checkpoint-13230/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a18d7672c859d8668687d3bbb8a75a39597d598f3e0a6c5e577962cf2595098
3
+ size 2239647372
checkpoint-13230/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e56c12116f50b1af5a6cc0544c81f4c621a1355d4c188b2cce0a2b7a17cb5a3
3
+ size 4479530129
checkpoint-13230/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a23e671e6f20c563b79fc7ee0ef08606cddf2d8abc0074c825ede81637bebfec
3
+ size 14244
checkpoint-13230/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7304d6a95175f33702ee403f739d613fa3ccc5f3b466253bd6bf1bf6d7ecd429
3
+ size 1064
checkpoint-13230/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3349315822124481,
3
+ "best_model_checkpoint": "model/checkpoint-13230",
4
+ "epoch": 3.0,
5
+ "eval_steps": 100,
6
+ "global_step": 13230,
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": 0.9415076375007629,
14
+ "learning_rate": 4.5e-05,
15
+ "loss": 0.3384,
16
+ "step": 4410
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.17596371882086168,
21
+ "eval_f1": 0.05266017963940943,
22
+ "eval_loss": 0.33717620372772217,
23
+ "eval_precision": 0.030963230341267273,
24
+ "eval_recall": 0.17596371882086168,
25
+ "eval_runtime": 129.9657,
26
+ "eval_samples_per_second": 33.932,
27
+ "eval_steps_per_second": 4.247,
28
+ "step": 4410
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 1.411308765411377,
33
+ "learning_rate": 4e-05,
34
+ "loss": 0.3376,
35
+ "step": 8820
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.17596371882086168,
40
+ "eval_f1": 0.05266017963940943,
41
+ "eval_loss": 0.33663079142570496,
42
+ "eval_precision": 0.030963230341267273,
43
+ "eval_recall": 0.17596371882086168,
44
+ "eval_runtime": 129.7235,
45
+ "eval_samples_per_second": 33.995,
46
+ "eval_steps_per_second": 4.255,
47
+ "step": 8820
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 0.9971898198127747,
52
+ "learning_rate": 3.5e-05,
53
+ "loss": 0.3363,
54
+ "step": 13230
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.17596371882086168,
59
+ "eval_f1": 0.05266017963940943,
60
+ "eval_loss": 0.3349315822124481,
61
+ "eval_precision": 0.030963230341267273,
62
+ "eval_recall": 0.17596371882086168,
63
+ "eval_runtime": 129.7239,
64
+ "eval_samples_per_second": 33.995,
65
+ "eval_steps_per_second": 4.255,
66
+ "step": 13230
67
+ }
68
+ ],
69
+ "logging_steps": 100,
70
+ "max_steps": 44100,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 10,
73
+ "save_steps": 100,
74
+ "stateful_callbacks": {
75
+ "EarlyStoppingCallback": {
76
+ "args": {
77
+ "early_stopping_patience": 2,
78
+ "early_stopping_threshold": 0.0
79
+ },
80
+ "attributes": {
81
+ "early_stopping_patience_counter": 0
82
+ }
83
+ },
84
+ "TrainerControl": {
85
+ "args": {
86
+ "should_epoch_stop": false,
87
+ "should_evaluate": false,
88
+ "should_log": false,
89
+ "should_save": true,
90
+ "should_training_stop": false
91
+ },
92
+ "attributes": {}
93
+ }
94
+ },
95
+ "total_flos": 9.863794837757952e+16,
96
+ "train_batch_size": 8,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
checkpoint-13230/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309c9a2ffc926bc067f4565ef7482d32ea0fd74d99f370ce4e742bb7a759ec2a
3
+ size 5176
events.out.tfevents.1732629299.237f633d3b75.10785.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b518fdfec9575978f4921a86a25bec02b8299b75d0b219ea67ffee0da156b7
3
+ size 5433
events.out.tfevents.1732629498.237f633d3b75.10785.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7abec825184bfc590d8a2ef95b958d39a30e0702100942fd06c486ff6b75b5
3
+ size 5433
events.out.tfevents.1732630471.237f633d3b75.10785.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035e78060654766d77ae6229225d55198acafd65b426de743e7a6c7a6e7c2e90
3
+ size 5606
events.out.tfevents.1732637550.237f633d3b75.10785.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229f102f587308e8dd05df8cf29a3b018759f9149a4dec0eb0b45f61e769489a
3
+ size 5395
events.out.tfevents.1732638176.237f633d3b75.10785.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21fa6cd55274947890decaac72442459c87ff9d23e641a7cfa17704a6d47ca97
3
+ size 5395
events.out.tfevents.1732638466.237f633d3b75.10785.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e27dba5296ceca7b8051df602059534fd77c8bd1d3415ecc9fcb2c336bc4d5e
3
+ size 9918
events.out.tfevents.1732790113.fac4cbce8395.18098.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3481ddcb1fadbb73714c9862a5c2b92448ee8df58a091ec86edfac7fe41c21c2
3
+ size 9196