Hugging Face's logo

uvegesistvan
/
EGD_distilbert-base-multilingual-cased

Text Classification
Transformers
TensorBoard
Safetensors
English
Hungarian
German
distilbert
multilingual
fine-tuned
Model card Files Metrics Community
uvegesistvan commited on
Commit
c35a825
·
verified ·
1 Parent(s): 800d619

Upload folder using huggingface_hub

Browse files
Files changed (41) hide show
  1. checkpoint-5628/config.json +35 -0
  2. checkpoint-5628/model.safetensors +3 -0
  3. checkpoint-5628/optimizer.pt +3 -0
  4. checkpoint-5628/rng_state.pth +3 -0
  5. checkpoint-5628/scheduler.pt +3 -0
  6. checkpoint-5628/trainer_state.json +108 -0
  7. checkpoint-5628/training_args.bin +3 -0
  8. checkpoint-7504/config.json +35 -0
  9. checkpoint-7504/model.safetensors +3 -0
  10. checkpoint-7504/optimizer.pt +3 -0
  11. checkpoint-7504/rng_state.pth +3 -0
  12. checkpoint-7504/scheduler.pt +3 -0
  13. checkpoint-7504/trainer_state.json +130 -0
  14. checkpoint-7504/training_args.bin +3 -0
  15. checkpoint-9380/config.json +35 -0
  16. checkpoint-9380/model.safetensors +3 -0
  17. checkpoint-9380/optimizer.pt +3 -0
  18. checkpoint-9380/rng_state.pth +3 -0
  19. checkpoint-9380/scheduler.pt +3 -0
  20. checkpoint-9380/trainer_state.json +152 -0
  21. checkpoint-9380/training_args.bin +3 -0
  22. config.json +35 -0
  23. events.out.tfevents.1740349787.d7086afb14ac.759.3 +3 -0
  24. events.out.tfevents.1740350033.d7086afb14ac.759.4 +3 -0
  25. events.out.tfevents.1740350707.d7086afb14ac.759.5 +3 -0
  26. model.safetensors +3 -0
  27. runs/Feb22_13-02-01_c4da036077fd/events.out.tfevents.1740229322.c4da036077fd.6169.0 +3 -0
  28. runs/Feb22_13-05-37_c4da036077fd/events.out.tfevents.1740229538.c4da036077fd.6169.1 +3 -0
  29. runs/Feb22_13-06-15_c4da036077fd/events.out.tfevents.1740229576.c4da036077fd.6169.2 +3 -0
  30. runs/Feb22_13-07-10_c4da036077fd/events.out.tfevents.1740229631.c4da036077fd.6169.3 +3 -0
  31. runs/Feb22_13-08-22_c4da036077fd/events.out.tfevents.1740229703.c4da036077fd.6169.4 +3 -0
  32. runs/Feb22_13-10-35_c4da036077fd/events.out.tfevents.1740229837.c4da036077fd.6169.5 +3 -0
  33. runs/Feb22_13-11-22_c4da036077fd/events.out.tfevents.1740229884.c4da036077fd.6169.6 +3 -0
  34. runs/Feb22_13-12-47_c4da036077fd/events.out.tfevents.1740229969.c4da036077fd.6169.7 +3 -0
  35. runs/Feb22_13-16-26_c4da036077fd/events.out.tfevents.1740230187.c4da036077fd.6169.8 +3 -0
  36. runs/Feb22_13-30-31_c4da036077fd/events.out.tfevents.1740231033.c4da036077fd.9367.0 +3 -0
  37. runs/Feb22_13-34-19_c4da036077fd/events.out.tfevents.1740231261.c4da036077fd.9367.1 +3 -0
  38. runs/Feb22_13-35-13_c4da036077fd/events.out.tfevents.1740231315.c4da036077fd.9367.2 +3 -0
  39. runs/Feb22_13-40-16_c4da036077fd/events.out.tfevents.1740231618.c4da036077fd.9367.3 +3 -0
  40. runs/Feb22_13-40-16_c4da036077fd/events.out.tfevents.1740232282.c4da036077fd.9367.4 +3 -0
  41. training_args.bin +3 -0
checkpoint-5628/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.49.0",
34
+ "vocab_size": 119547
35
+ }
checkpoint-5628/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0963cd6fac43ba582b0e2aec7c473eba8ecb1bec1ade10985cb3181333c3ea49
3
+ size 541320452
checkpoint-5628/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a2e3f7c7acfbaa29be8fa176655032f13e4a2cc4c3410221eb39c83053e9f47
3
+ size 1082703034
checkpoint-5628/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d5b2ab33ba699de67499a86896add23c725c5b337505deccb47263b5728e71
3
+ size 14244
checkpoint-5628/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f8189f8adcf760ed2f809786703eec9f3cb051b1d3fce373553e9e709dcfc97
3
+ size 1064
checkpoint-5628/trainer_state.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5992706992706992,
3
+ "best_model_checkpoint": "model/checkpoint-3752",
4
+ "epoch": 3.0,
5
+ "eval_steps": 50,
6
+ "global_step": 5628,
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": 0.232726588845253,
14
+ "learning_rate": 9.084300622945162e-06,
15
+ "loss": 0.0817,
16
+ "step": 1876
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8464818763326226,
21
+ "eval_f1_macro": 0.4624149659863946,
22
+ "eval_f1_weighted": 0.8011493190026544,
23
+ "eval_loss": 0.06743289530277252,
24
+ "eval_precision_macro": 0.7010764171889492,
25
+ "eval_precision_weighted": 0.8229165574281427,
26
+ "eval_recall_macro": 0.44028979481565683,
27
+ "eval_recall_weighted": 0.8464818763326226,
28
+ "eval_runtime": 5.0821,
29
+ "eval_samples_per_second": 184.568,
30
+ "eval_steps_per_second": 46.24,
31
+ "step": 1876
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 0.18798664212226868,
36
+ "learning_rate": 6.593041210714562e-06,
37
+ "loss": 0.0588,
38
+ "step": 3752
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_accuracy": 0.8251599147121536,
43
+ "eval_f1_macro": 0.5992706992706992,
44
+ "eval_f1_weighted": 0.829400158611246,
45
+ "eval_loss": 0.06970743834972382,
46
+ "eval_precision_macro": 0.6140893452063056,
47
+ "eval_precision_weighted": 0.8365234937694226,
48
+ "eval_recall_macro": 0.5961441974373008,
49
+ "eval_recall_weighted": 0.8251599147121536,
50
+ "eval_runtime": 5.0788,
51
+ "eval_samples_per_second": 184.689,
52
+ "eval_steps_per_second": 46.271,
53
+ "step": 3752
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "grad_norm": 0.03722580894827843,
58
+ "learning_rate": 3.486973746877771e-06,
59
+ "loss": 0.0395,
60
+ "step": 5628
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.849680170575693,
65
+ "eval_f1_macro": 0.5773129404708353,
66
+ "eval_f1_weighted": 0.8345452465837384,
67
+ "eval_loss": 0.08055932819843292,
68
+ "eval_precision_macro": 0.6424363946177801,
69
+ "eval_precision_weighted": 0.8274003556291218,
70
+ "eval_recall_macro": 0.5397910877436739,
71
+ "eval_recall_weighted": 0.849680170575693,
72
+ "eval_runtime": 5.0482,
73
+ "eval_samples_per_second": 185.807,
74
+ "eval_steps_per_second": 46.551,
75
+ "step": 5628
76
+ }
77
+ ],
78
+ "logging_steps": 50,
79
+ "max_steps": 9380,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 5,
82
+ "save_steps": 50,
83
+ "stateful_callbacks": {
84
+ "EarlyStoppingCallback": {
85
+ "args": {
86
+ "early_stopping_patience": 2,
87
+ "early_stopping_threshold": 0.0
88
+ },
89
+ "attributes": {
90
+ "early_stopping_patience_counter": 1
91
+ }
92
+ },
93
+ "TrainerControl": {
94
+ "args": {
95
+ "should_epoch_stop": false,
96
+ "should_evaluate": false,
97
+ "should_log": false,
98
+ "should_save": true,
99
+ "should_training_stop": false
100
+ },
101
+ "attributes": {}
102
+ }
103
+ },
104
+ "total_flos": 1490682220803072.0,
105
+ "train_batch_size": 4,
106
+ "trial_name": null,
107
+ "trial_params": null
108
+ }
checkpoint-5628/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715c96820c45effa2b6e5bb29121868a8187d8c31c98bf6d56350dbbfcd41a1b
3
+ size 5240
checkpoint-7504/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.49.0",
34
+ "vocab_size": 119547
35
+ }
checkpoint-7504/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa0daa19a98b896474d8829711aba4f1fd1851b1c4255f4ef69dd5d3eb102c1
3
+ size 541320452
checkpoint-7504/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5321247d7246325e84a33fc274ccf1b4051888bcaafe2e00cbce2509ba659500
3
+ size 1082703034
checkpoint-7504/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1994c0acf7b2b0a8e2ec7ec0412f7e58dba29f484c5d6adbbf73047d792f9baa
3
+ size 14244
checkpoint-7504/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232e1e07cc83243f2cc6b60588afdfb89921234cd56328a8f6a1396fb5048933
3
+ size 1064
checkpoint-7504/trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6007231820008035,
3
+ "best_model_checkpoint": "model/checkpoint-7504",
4
+ "epoch": 4.0,
5
+ "eval_steps": 50,
6
+ "global_step": 7504,
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": 0.232726588845253,
14
+ "learning_rate": 9.084300622945162e-06,
15
+ "loss": 0.0817,
16
+ "step": 1876
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8464818763326226,
21
+ "eval_f1_macro": 0.4624149659863946,
22
+ "eval_f1_weighted": 0.8011493190026544,
23
+ "eval_loss": 0.06743289530277252,
24
+ "eval_precision_macro": 0.7010764171889492,
25
+ "eval_precision_weighted": 0.8229165574281427,
26
+ "eval_recall_macro": 0.44028979481565683,
27
+ "eval_recall_weighted": 0.8464818763326226,
28
+ "eval_runtime": 5.0821,
29
+ "eval_samples_per_second": 184.568,
30
+ "eval_steps_per_second": 46.24,
31
+ "step": 1876
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 0.18798664212226868,
36
+ "learning_rate": 6.593041210714562e-06,
37
+ "loss": 0.0588,
38
+ "step": 3752
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_accuracy": 0.8251599147121536,
43
+ "eval_f1_macro": 0.5992706992706992,
44
+ "eval_f1_weighted": 0.829400158611246,
45
+ "eval_loss": 0.06970743834972382,
46
+ "eval_precision_macro": 0.6140893452063056,
47
+ "eval_precision_weighted": 0.8365234937694226,
48
+ "eval_recall_macro": 0.5961441974373008,
49
+ "eval_recall_weighted": 0.8251599147121536,
50
+ "eval_runtime": 5.0788,
51
+ "eval_samples_per_second": 184.689,
52
+ "eval_steps_per_second": 46.271,
53
+ "step": 3752
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "grad_norm": 0.03722580894827843,
58
+ "learning_rate": 3.486973746877771e-06,
59
+ "loss": 0.0395,
60
+ "step": 5628
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.849680170575693,
65
+ "eval_f1_macro": 0.5773129404708353,
66
+ "eval_f1_weighted": 0.8345452465837384,
67
+ "eval_loss": 0.08055932819843292,
68
+ "eval_precision_macro": 0.6424363946177801,
69
+ "eval_precision_weighted": 0.8274003556291218,
70
+ "eval_recall_macro": 0.5397910877436739,
71
+ "eval_recall_weighted": 0.849680170575693,
72
+ "eval_runtime": 5.0482,
73
+ "eval_samples_per_second": 185.807,
74
+ "eval_steps_per_second": 46.551,
75
+ "step": 5628
76
+ },
77
+ {
78
+ "epoch": 4.0,
79
+ "grad_norm": 0.22263826429843903,
80
+ "learning_rate": 9.648338779170968e-07,
81
+ "loss": 0.0239,
82
+ "step": 7504
83
+ },
84
+ {
85
+ "epoch": 4.0,
86
+ "eval_accuracy": 0.8336886993603412,
87
+ "eval_f1_macro": 0.6007231820008035,
88
+ "eval_f1_weighted": 0.8327353646735044,
89
+ "eval_loss": 0.0956118032336235,
90
+ "eval_precision_macro": 0.6171054012879108,
91
+ "eval_precision_weighted": 0.8329684712250969,
92
+ "eval_recall_macro": 0.5898380302115934,
93
+ "eval_recall_weighted": 0.8336886993603412,
94
+ "eval_runtime": 5.0679,
95
+ "eval_samples_per_second": 185.087,
96
+ "eval_steps_per_second": 46.371,
97
+ "step": 7504
98
+ }
99
+ ],
100
+ "logging_steps": 50,
101
+ "max_steps": 9380,
102
+ "num_input_tokens_seen": 0,
103
+ "num_train_epochs": 5,
104
+ "save_steps": 50,
105
+ "stateful_callbacks": {
106
+ "EarlyStoppingCallback": {
107
+ "args": {
108
+ "early_stopping_patience": 2,
109
+ "early_stopping_threshold": 0.0
110
+ },
111
+ "attributes": {
112
+ "early_stopping_patience_counter": 0
113
+ }
114
+ },
115
+ "TrainerControl": {
116
+ "args": {
117
+ "should_epoch_stop": false,
118
+ "should_evaluate": false,
119
+ "should_log": false,
120
+ "should_save": true,
121
+ "should_training_stop": false
122
+ },
123
+ "attributes": {}
124
+ }
125
+ },
126
+ "total_flos": 1987576294404096.0,
127
+ "train_batch_size": 4,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }
checkpoint-7504/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715c96820c45effa2b6e5bb29121868a8187d8c31c98bf6d56350dbbfcd41a1b
3
+ size 5240
checkpoint-9380/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.49.0",
34
+ "vocab_size": 119547
35
+ }
checkpoint-9380/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a5ead72a2594f36b1057a7e9b143980d2aa440c42a278eac54996835532002
3
+ size 541320452
checkpoint-9380/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fddbb5e1314edd61875e1d554350b01b8ffcaa3549e28c1dea54020bd0ca03c
3
+ size 1082703034
checkpoint-9380/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfbff5bc84a8ebf0204467cc036c44a9325bd1e3df59fa8df328d90be66f86c
3
+ size 14244
checkpoint-9380/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbed8c49a5fc15cc0d6078ec60fa0ae98198507be7a37a106b7a52fb78ec09a6
3
+ size 1064
checkpoint-9380/trainer_state.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6007231820008035,
3
+ "best_model_checkpoint": "model/checkpoint-7504",
4
+ "epoch": 5.0,
5
+ "eval_steps": 50,
6
+ "global_step": 9380,
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": 0.232726588845253,
14
+ "learning_rate": 9.084300622945162e-06,
15
+ "loss": 0.0817,
16
+ "step": 1876
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8464818763326226,
21
+ "eval_f1_macro": 0.4624149659863946,
22
+ "eval_f1_weighted": 0.8011493190026544,
23
+ "eval_loss": 0.06743289530277252,
24
+ "eval_precision_macro": 0.7010764171889492,
25
+ "eval_precision_weighted": 0.8229165574281427,
26
+ "eval_recall_macro": 0.44028979481565683,
27
+ "eval_recall_weighted": 0.8464818763326226,
28
+ "eval_runtime": 5.0821,
29
+ "eval_samples_per_second": 184.568,
30
+ "eval_steps_per_second": 46.24,
31
+ "step": 1876
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 0.18798664212226868,
36
+ "learning_rate": 6.593041210714562e-06,
37
+ "loss": 0.0588,
38
+ "step": 3752
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_accuracy": 0.8251599147121536,
43
+ "eval_f1_macro": 0.5992706992706992,
44
+ "eval_f1_weighted": 0.829400158611246,
45
+ "eval_loss": 0.06970743834972382,
46
+ "eval_precision_macro": 0.6140893452063056,
47
+ "eval_precision_weighted": 0.8365234937694226,
48
+ "eval_recall_macro": 0.5961441974373008,
49
+ "eval_recall_weighted": 0.8251599147121536,
50
+ "eval_runtime": 5.0788,
51
+ "eval_samples_per_second": 184.689,
52
+ "eval_steps_per_second": 46.271,
53
+ "step": 3752
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "grad_norm": 0.03722580894827843,
58
+ "learning_rate": 3.486973746877771e-06,
59
+ "loss": 0.0395,
60
+ "step": 5628
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.849680170575693,
65
+ "eval_f1_macro": 0.5773129404708353,
66
+ "eval_f1_weighted": 0.8345452465837384,
67
+ "eval_loss": 0.08055932819843292,
68
+ "eval_precision_macro": 0.6424363946177801,
69
+ "eval_precision_weighted": 0.8274003556291218,
70
+ "eval_recall_macro": 0.5397910877436739,
71
+ "eval_recall_weighted": 0.849680170575693,
72
+ "eval_runtime": 5.0482,
73
+ "eval_samples_per_second": 185.807,
74
+ "eval_steps_per_second": 46.551,
75
+ "step": 5628
76
+ },
77
+ {
78
+ "epoch": 4.0,
79
+ "grad_norm": 0.22263826429843903,
80
+ "learning_rate": 9.648338779170968e-07,
81
+ "loss": 0.0239,
82
+ "step": 7504
83
+ },
84
+ {
85
+ "epoch": 4.0,
86
+ "eval_accuracy": 0.8336886993603412,
87
+ "eval_f1_macro": 0.6007231820008035,
88
+ "eval_f1_weighted": 0.8327353646735044,
89
+ "eval_loss": 0.0956118032336235,
90
+ "eval_precision_macro": 0.6171054012879108,
91
+ "eval_precision_weighted": 0.8329684712250969,
92
+ "eval_recall_macro": 0.5898380302115934,
93
+ "eval_recall_weighted": 0.8336886993603412,
94
+ "eval_runtime": 5.0679,
95
+ "eval_samples_per_second": 185.087,
96
+ "eval_steps_per_second": 46.371,
97
+ "step": 7504
98
+ },
99
+ {
100
+ "epoch": 5.0,
101
+ "grad_norm": 0.006782012525945902,
102
+ "learning_rate": 0.0,
103
+ "loss": 0.0168,
104
+ "step": 9380
105
+ },
106
+ {
107
+ "epoch": 5.0,
108
+ "eval_accuracy": 0.8390191897654584,
109
+ "eval_f1_macro": 0.5986856629739029,
110
+ "eval_f1_weighted": 0.8356391273708549,
111
+ "eval_loss": 0.09994609653949738,
112
+ "eval_precision_macro": 0.6148482050686072,
113
+ "eval_precision_weighted": 0.8329834413768394,
114
+ "eval_recall_macro": 0.5854920143713247,
115
+ "eval_recall_weighted": 0.8390191897654584,
116
+ "eval_runtime": 5.1031,
117
+ "eval_samples_per_second": 183.809,
118
+ "eval_steps_per_second": 46.05,
119
+ "step": 9380
120
+ }
121
+ ],
122
+ "logging_steps": 50,
123
+ "max_steps": 9380,
124
+ "num_input_tokens_seen": 0,
125
+ "num_train_epochs": 5,
126
+ "save_steps": 50,
127
+ "stateful_callbacks": {
128
+ "EarlyStoppingCallback": {
129
+ "args": {
130
+ "early_stopping_patience": 2,
131
+ "early_stopping_threshold": 0.0
132
+ },
133
+ "attributes": {
134
+ "early_stopping_patience_counter": 1
135
+ }
136
+ },
137
+ "TrainerControl": {
138
+ "args": {
139
+ "should_epoch_stop": false,
140
+ "should_evaluate": false,
141
+ "should_log": false,
142
+ "should_save": true,
143
+ "should_training_stop": true
144
+ },
145
+ "attributes": {}
146
+ }
147
+ },
148
+ "total_flos": 2484470368005120.0,
149
+ "train_batch_size": 4,
150
+ "trial_name": null,
151
+ "trial_params": null
152
+ }
checkpoint-9380/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715c96820c45effa2b6e5bb29121868a8187d8c31c98bf6d56350dbbfcd41a1b
3
+ size 5240
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.49.0",
34
+ "vocab_size": 119547
35
+ }
events.out.tfevents.1740349787.d7086afb14ac.759.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaaeb8b3efa39e2d2efd8a29fb90567e053185a5e770465c514fab7e86b7383b
3
+ size 5764
events.out.tfevents.1740350033.d7086afb14ac.759.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5b6397ad8a6d79d51d8368946d12081fe863c6c09563d541ffd354c9d95e56
3
+ size 5764
events.out.tfevents.1740350707.d7086afb14ac.759.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a6b2cc67220dd0fc0f96637bd3ac88b702149f5c517ea978aaaa8188046bb0
3
+ size 9820
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa0daa19a98b896474d8829711aba4f1fd1851b1c4255f4ef69dd5d3eb102c1
3
+ size 541320452
runs/Feb22_13-02-01_c4da036077fd/events.out.tfevents.1740229322.c4da036077fd.6169.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6e11dd354bca679e52c1fb04eb65d3c8a1bf5bf9089dcc63716b0bda6e43ef
3
+ size 5260
runs/Feb22_13-05-37_c4da036077fd/events.out.tfevents.1740229538.c4da036077fd.6169.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a9dd7ce9f2b2ff96880e633ca103ae353c14486fee1c9d3034b54602ce9fbf
3
+ size 5258
runs/Feb22_13-06-15_c4da036077fd/events.out.tfevents.1740229576.c4da036077fd.6169.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450eaf33ecdfa9b8ecb07dce4b18a558db3056de39888149297150c62814f04b
3
+ size 5261
runs/Feb22_13-07-10_c4da036077fd/events.out.tfevents.1740229631.c4da036077fd.6169.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58bcf68632f1f04dd9a9f72316889bc5078184c1e25efe7fc70623882e3c1086
3
+ size 5261
runs/Feb22_13-08-22_c4da036077fd/events.out.tfevents.1740229703.c4da036077fd.6169.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a93d9b038e1536a43909d796324c56074b2bc8a6b18b7d5318b12453933f1f89
3
+ size 5260
runs/Feb22_13-10-35_c4da036077fd/events.out.tfevents.1740229837.c4da036077fd.6169.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba102fc5e8886c888a39079779d0d8c6dc3e936d6cf05c6d6cb03baa0df0b9d5
3
+ size 5261
runs/Feb22_13-11-22_c4da036077fd/events.out.tfevents.1740229884.c4da036077fd.6169.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dee085d1b0493107185c7ac923233568b6990751842be14d4ade6c3455d7f0d
3
+ size 5259
runs/Feb22_13-12-47_c4da036077fd/events.out.tfevents.1740229969.c4da036077fd.6169.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b0cb488c66afa4bb81efbd2a2842a55b227416750240ef15327d1489b3327c
3
+ size 5689
runs/Feb22_13-16-26_c4da036077fd/events.out.tfevents.1740230187.c4da036077fd.6169.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68bf3056cc3b51ee82f7ad24a138d8e28e611852aed7034b0fcd34398af08ff
3
+ size 5259
runs/Feb22_13-30-31_c4da036077fd/events.out.tfevents.1740231033.c4da036077fd.9367.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1ad23f38788764778c6dc40b99d6543fff155aa1948d2419fb719eb7e24c79
3
+ size 5689
runs/Feb22_13-34-19_c4da036077fd/events.out.tfevents.1740231261.c4da036077fd.9367.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ac60542d39ed33a6e1567ec80aacf77ac2fb1e2f6b89cdd7f2d63a167a1454
3
+ size 5263
runs/Feb22_13-35-13_c4da036077fd/events.out.tfevents.1740231315.c4da036077fd.9367.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a8bf45edb3efc01beb4465d323a506f0685ff64b744cc78bfc5f9aa037fe00
3
+ size 6214
runs/Feb22_13-40-16_c4da036077fd/events.out.tfevents.1740231618.c4da036077fd.9367.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2c520c78ca0876056d46eaa91cd4361383e9c5d69312765ddf0c212d9b2302
3
+ size 9628
runs/Feb22_13-40-16_c4da036077fd/events.out.tfevents.1740232282.c4da036077fd.9367.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe811108afd5a92a7bac36f41385aa9063276fabaed4724f35e321071ba4253a
3
+ size 1037
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715c96820c45effa2b6e5bb29121868a8187d8c31c98bf6d56350dbbfcd41a1b
3
+ size 5240