Hugging Face's logo

paride92
/
IdeoBert-IT-classifier-v2

TensorBoard
Safetensors
eurobert
custom_code
Model card Files
xet
 Metrics Community
paride92 commited on
Commit
0a2fc22
·
verified ·
1 Parent(s): 14d58d2

Upload folder using huggingface_hub

Browse files
Files changed (31) hide show
  1. .gitattributes +1 -0
  2. checkpoint-216/config.json +58 -0
  3. checkpoint-216/model.safetensors +3 -0
  4. checkpoint-216/optimizer.pt +3 -0
  5. checkpoint-216/rng_state.pth +3 -0
  6. checkpoint-216/scaler.pt +3 -0
  7. checkpoint-216/scheduler.pt +3 -0
  8. checkpoint-216/trainer_state.json +84 -0
  9. checkpoint-216/training_args.bin +3 -0
  10. checkpoint-432/config.json +58 -0
  11. checkpoint-432/model.safetensors +3 -0
  12. checkpoint-432/optimizer.pt +3 -0
  13. checkpoint-432/rng_state.pth +3 -0
  14. checkpoint-432/scaler.pt +3 -0
  15. checkpoint-432/scheduler.pt +3 -0
  16. checkpoint-432/trainer_state.json +125 -0
  17. checkpoint-432/training_args.bin +3 -0
  18. config.json +58 -0
  19. label_mapping.json +10 -0
  20. logs/events.out.tfevents.1786704328.9a9a7a5d0773.2818.3 +3 -0
  21. logs/events.out.tfevents.1786705361.9a9a7a5d0773.2818.4 +3 -0
  22. model.safetensors +3 -0
  23. test_pred_labels.npy +3 -0
  24. test_pred_probs.npy +3 -0
  25. test_predictions.csv +0 -0
  26. test_true_labels.npy +3 -0
  27. tokenizer.json +3 -0
  28. tokenizer_config.json +20 -0
  29. trainer_state.json +147 -0
  30. training_args.bin +3 -0
  31. training_args.json +38 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-216/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EuroBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_eurobert.EuroBertConfig",
9
+ "AutoModel": "modeling_eurobert.EuroBertModel",
10
+ "AutoModelForMaskedLM": "modeling_eurobert.EuroBertForMaskedLM",
11
+ "AutoModelForPreTraining": "modeling_eurobert.EuroBertPreTrainedModel",
12
+ "AutoModelForQuestionAnswering": "modeling_eurobert.EuroBertForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "modeling_eurobert.EuroBertForSequenceClassification",
14
+ "AutoModelForTokenClassification": "modeling_eurobert.EuroBertForTokenClassification"
15
+ },
16
+ "bos_token": "<|begin_of_text|>",
17
+ "bos_token_id": 128000,
18
+ "classifier_pooling": "late",
19
+ "dtype": "float32",
20
+ "eos_token": "<|end_of_text|>",
21
+ "eos_token_id": 128001,
22
+ "head_dim": 64,
23
+ "hidden_act": "silu",
24
+ "hidden_dropout": 0.0,
25
+ "hidden_size": 1152,
26
+ "id2label": {
27
+ "0": "0",
28
+ "1": "1"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "is_decoder": false,
33
+ "label2id": {
34
+ "0": 0,
35
+ "1": 1
36
+ },
37
+ "mask_token": "<|mask|>",
38
+ "mask_token_id": 128002,
39
+ "max_position_embeddings": 8192,
40
+ "mlp_bias": false,
41
+ "model_type": "eurobert",
42
+ "num_attention_heads": 18,
43
+ "num_hidden_layers": 26,
44
+ "num_key_value_heads": 6,
45
+ "pad_token": "<|end_of_text|>",
46
+ "pad_token_id": 128001,
47
+ "pretraining_tp": 1,
48
+ "problem_type": "single_label_classification",
49
+ "rms_norm_eps": 1e-05,
50
+ "rope_parameters": {
51
+ "rope_theta": 250000,
52
+ "rope_type": "default"
53
+ },
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "5.13.1",
56
+ "use_cache": false,
57
+ "vocab_size": 128256
58
+ }
checkpoint-216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f8049f9ecd762a8a9a64c82c1674badd229311c74d3fae4132bf4be3b2999ce
3
+ size 2436848304
checkpoint-216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7c6725b1a6510b9e1802013310b6947b94f98182dd8d52b6852ffc531a47a7
3
+ size 4873851039
checkpoint-216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
checkpoint-216/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7d9d994d7b3ebf4276d197f9e784ff4414d64bc0e210602f15dc531db14876
3
+ size 1383
checkpoint-216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14c26ac71be79f13413302ebbd59b05648c2b6d3459588c99f0f73a9aa1a809
3
+ size 1465
checkpoint-216/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 216,
3
+ "best_metric": 0.8380090497737557,
4
+ "best_model_checkpoint": "ft_outputs/notebook_model_clf/checkpoint-216",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 216,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.23148148148148148,
14
+ "grad_norm": 34.480255126953125,
15
+ "learning_rate": 9.845758354755784e-06,
16
+ "loss": 0.49710899353027344,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.46296296296296297,
21
+ "grad_norm": 14.985294342041016,
22
+ "learning_rate": 8.560411311053985e-06,
23
+ "loss": 0.4200091552734375,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.6944444444444444,
28
+ "grad_norm": 11.86069393157959,
29
+ "learning_rate": 7.275064267352185e-06,
30
+ "loss": 0.3548846435546875,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.9259259259259259,
35
+ "grad_norm": 14.185436248779297,
36
+ "learning_rate": 5.9897172236503865e-06,
37
+ "loss": 0.3545515060424805,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.8443478260869566,
43
+ "eval_f1": 0.8380090497737557,
44
+ "eval_loss": 0.3412903845310211,
45
+ "eval_precision": 0.9090314136125655,
46
+ "eval_recall": 0.7772803581421377,
47
+ "eval_roc_auc": 0.9340782513920103,
48
+ "eval_runtime": 19.7364,
49
+ "eval_samples_per_second": 174.804,
50
+ "eval_steps_per_second": 2.736,
51
+ "step": 216
52
+ }
53
+ ],
54
+ "logging_steps": 50,
55
+ "max_steps": 432,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 2,
58
+ "save_steps": 500,
59
+ "stateful_callbacks": {
60
+ "EarlyStoppingCallback": {
61
+ "args": {
62
+ "early_stopping_patience": 3,
63
+ "early_stopping_threshold": 0.0
64
+ },
65
+ "attributes": {
66
+ "early_stopping_patience_counter": 0
67
+ }
68
+ },
69
+ "TrainerControl": {
70
+ "args": {
71
+ "should_epoch_stop": false,
72
+ "should_evaluate": false,
73
+ "should_log": false,
74
+ "should_save": true,
75
+ "should_training_stop": false
76
+ },
77
+ "attributes": {}
78
+ }
79
+ },
80
+ "total_flos": 4889260068132864.0,
81
+ "train_batch_size": 64,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
checkpoint-216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592b45e05a9a269ad5b812dc6f5406445dd8e02a5966389686957724c15cdd41
3
+ size 5265
checkpoint-432/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EuroBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_eurobert.EuroBertConfig",
9
+ "AutoModel": "modeling_eurobert.EuroBertModel",
10
+ "AutoModelForMaskedLM": "modeling_eurobert.EuroBertForMaskedLM",
11
+ "AutoModelForPreTraining": "modeling_eurobert.EuroBertPreTrainedModel",
12
+ "AutoModelForQuestionAnswering": "modeling_eurobert.EuroBertForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "modeling_eurobert.EuroBertForSequenceClassification",
14
+ "AutoModelForTokenClassification": "modeling_eurobert.EuroBertForTokenClassification"
15
+ },
16
+ "bos_token": "<|begin_of_text|>",
17
+ "bos_token_id": 128000,
18
+ "classifier_pooling": "late",
19
+ "dtype": "float32",
20
+ "eos_token": "<|end_of_text|>",
21
+ "eos_token_id": 128001,
22
+ "head_dim": 64,
23
+ "hidden_act": "silu",
24
+ "hidden_dropout": 0.0,
25
+ "hidden_size": 1152,
26
+ "id2label": {
27
+ "0": "0",
28
+ "1": "1"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "is_decoder": false,
33
+ "label2id": {
34
+ "0": 0,
35
+ "1": 1
36
+ },
37
+ "mask_token": "<|mask|>",
38
+ "mask_token_id": 128002,
39
+ "max_position_embeddings": 8192,
40
+ "mlp_bias": false,
41
+ "model_type": "eurobert",
42
+ "num_attention_heads": 18,
43
+ "num_hidden_layers": 26,
44
+ "num_key_value_heads": 6,
45
+ "pad_token": "<|end_of_text|>",
46
+ "pad_token_id": 128001,
47
+ "pretraining_tp": 1,
48
+ "problem_type": "single_label_classification",
49
+ "rms_norm_eps": 1e-05,
50
+ "rope_parameters": {
51
+ "rope_theta": 250000,
52
+ "rope_type": "default"
53
+ },
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "5.13.1",
56
+ "use_cache": false,
57
+ "vocab_size": 128256
58
+ }
checkpoint-432/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29edf1cbe4faf365d3568e77a5c77eceb96921e9ccb03130a9141c0fa0dfd6d
3
+ size 2436848304
checkpoint-432/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e65be2b0f6d875f2dd6f4e70a17ecbcb2e8bc8b466aed1c1939b407fbb456a
3
+ size 4873851039
checkpoint-432/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
3
+ size 14645
checkpoint-432/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda266edb09567bd020093316026cf4b63ebd8f392947738547abc05cfdd48d7
3
+ size 1383
checkpoint-432/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae178711c6c4aa5ecdd3a6d14418ff388c7d907bb832269df1a505bccf6d822c
3
+ size 1465
checkpoint-432/trainer_state.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 432,
3
+ "best_metric": 0.8670062252405206,
4
+ "best_model_checkpoint": "ft_outputs/notebook_model_clf/checkpoint-432",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 432,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.23148148148148148,
14
+ "grad_norm": 34.480255126953125,
15
+ "learning_rate": 9.845758354755784e-06,
16
+ "loss": 0.49710899353027344,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.46296296296296297,
21
+ "grad_norm": 14.985294342041016,
22
+ "learning_rate": 8.560411311053985e-06,
23
+ "loss": 0.4200091552734375,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.6944444444444444,
28
+ "grad_norm": 11.86069393157959,
29
+ "learning_rate": 7.275064267352185e-06,
30
+ "loss": 0.3548846435546875,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.9259259259259259,
35
+ "grad_norm": 14.185436248779297,
36
+ "learning_rate": 5.9897172236503865e-06,
37
+ "loss": 0.3545515060424805,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.8443478260869566,
43
+ "eval_f1": 0.8380090497737557,
44
+ "eval_loss": 0.3412903845310211,
45
+ "eval_precision": 0.9090314136125655,
46
+ "eval_recall": 0.7772803581421377,
47
+ "eval_roc_auc": 0.9340782513920103,
48
+ "eval_runtime": 19.7364,
49
+ "eval_samples_per_second": 174.804,
50
+ "eval_steps_per_second": 2.736,
51
+ "step": 216
52
+ },
53
+ {
54
+ "epoch": 1.1574074074074074,
55
+ "grad_norm": 33.73603057861328,
56
+ "learning_rate": 4.704370179948586e-06,
57
+ "loss": 0.25113576889038086,
58
+ "step": 250
59
+ },
60
+ {
61
+ "epoch": 1.3888888888888888,
62
+ "grad_norm": 71.73030853271484,
63
+ "learning_rate": 3.4190231362467867e-06,
64
+ "loss": 0.17481367111206056,
65
+ "step": 300
66
+ },
67
+ {
68
+ "epoch": 1.6203703703703702,
69
+ "grad_norm": 35.59589767456055,
70
+ "learning_rate": 2.1336760925449874e-06,
71
+ "loss": 0.1653757858276367,
72
+ "step": 350
73
+ },
74
+ {
75
+ "epoch": 1.8518518518518519,
76
+ "grad_norm": 16.84499740600586,
77
+ "learning_rate": 8.483290488431877e-07,
78
+ "loss": 0.15949118614196778,
79
+ "step": 400
80
+ },
81
+ {
82
+ "epoch": 2.0,
83
+ "eval_accuracy": 0.863768115942029,
84
+ "eval_f1": 0.8670062252405206,
85
+ "eval_loss": 0.33692029118537903,
86
+ "eval_precision": 0.8769318832283916,
87
+ "eval_recall": 0.8573027420257414,
88
+ "eval_roc_auc": 0.9436943704801936,
89
+ "eval_runtime": 19.6866,
90
+ "eval_samples_per_second": 175.246,
91
+ "eval_steps_per_second": 2.743,
92
+ "step": 432
93
+ }
94
+ ],
95
+ "logging_steps": 50,
96
+ "max_steps": 432,
97
+ "num_input_tokens_seen": 0,
98
+ "num_train_epochs": 2,
99
+ "save_steps": 500,
100
+ "stateful_callbacks": {
101
+ "EarlyStoppingCallback": {
102
+ "args": {
103
+ "early_stopping_patience": 3,
104
+ "early_stopping_threshold": 0.0
105
+ },
106
+ "attributes": {
107
+ "early_stopping_patience_counter": 0
108
+ }
109
+ },
110
+ "TrainerControl": {
111
+ "args": {
112
+ "should_epoch_stop": false,
113
+ "should_evaluate": false,
114
+ "should_log": false,
115
+ "should_save": true,
116
+ "should_training_stop": true
117
+ },
118
+ "attributes": {}
119
+ }
120
+ },
121
+ "total_flos": 9778520136265728.0,
122
+ "train_batch_size": 64,
123
+ "trial_name": null,
124
+ "trial_params": null
125
+ }
checkpoint-432/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592b45e05a9a269ad5b812dc6f5406445dd8e02a5966389686957724c15cdd41
3
+ size 5265
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EuroBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_eurobert.EuroBertConfig",
9
+ "AutoModel": "modeling_eurobert.EuroBertModel",
10
+ "AutoModelForMaskedLM": "modeling_eurobert.EuroBertForMaskedLM",
11
+ "AutoModelForPreTraining": "modeling_eurobert.EuroBertPreTrainedModel",
12
+ "AutoModelForQuestionAnswering": "modeling_eurobert.EuroBertForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "modeling_eurobert.EuroBertForSequenceClassification",
14
+ "AutoModelForTokenClassification": "modeling_eurobert.EuroBertForTokenClassification"
15
+ },
16
+ "bos_token": "<|begin_of_text|>",
17
+ "bos_token_id": 128000,
18
+ "classifier_pooling": "late",
19
+ "dtype": "float32",
20
+ "eos_token": "<|end_of_text|>",
21
+ "eos_token_id": 128001,
22
+ "head_dim": 64,
23
+ "hidden_act": "silu",
24
+ "hidden_dropout": 0.0,
25
+ "hidden_size": 1152,
26
+ "id2label": {
27
+ "0": "0",
28
+ "1": "1"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "is_decoder": false,
33
+ "label2id": {
34
+ "0": 0,
35
+ "1": 1
36
+ },
37
+ "mask_token": "<|mask|>",
38
+ "mask_token_id": 128002,
39
+ "max_position_embeddings": 8192,
40
+ "mlp_bias": false,
41
+ "model_type": "eurobert",
42
+ "num_attention_heads": 18,
43
+ "num_hidden_layers": 26,
44
+ "num_key_value_heads": 6,
45
+ "pad_token": "<|end_of_text|>",
46
+ "pad_token_id": 128001,
47
+ "pretraining_tp": 1,
48
+ "problem_type": "single_label_classification",
49
+ "rms_norm_eps": 1e-05,
50
+ "rope_parameters": {
51
+ "rope_theta": 250000,
52
+ "rope_type": "default"
53
+ },
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "5.13.1",
56
+ "use_cache": false,
57
+ "vocab_size": 128256
58
+ }
label_mapping.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "label2id": {
3
+ "0": 0,
4
+ "1": 1
5
+ },
6
+ "id2label": {
7
+ "0": "0",
8
+ "1": "1"
9
+ }
10
+ }
logs/events.out.tfevents.1786704328.9a9a7a5d0773.2818.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2e7098e9f7459ffe6c9ba52b942163b478a50283c67d1444aba935e681e018
3
+ size 8433
logs/events.out.tfevents.1786705361.9a9a7a5d0773.2818.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c328728545224ec9563f5ab68b58e98216376550087b6706c97aab73e67a76
3
+ size 611
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29edf1cbe4faf365d3568e77a5c77eceb96921e9ccb03130a9141c0fa0dfd6d
3
+ size 2436848304
test_pred_labels.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d867e9f682f6806e9cbe5de9347e27872e8cbc21a89393db417de63151eadba9
3
+ size 27728
test_pred_probs.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939a84e22a0e8e6bbc40f6ef8c51164d2a8bd10c82b8a325d6d793330456ed4a
3
+ size 13928
test_predictions.csv ADDED
The diff for this file is too large to render. See raw diff
 
test_true_labels.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4fdd9556ac2ea46801f400db2a03f08a076be5bd992a98857cb880bdfa118a5
3
+ size 27728
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed633ef6508ce915f55a544a510744359811213fa14117c20cbaff4aefc08e4a
3
+ size 17210345
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin_of_text|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|end_of_text|>",
6
+ "is_local": false,
7
+ "local_files_only": false,
8
+ "mask_token": "<|mask|>",
9
+ "max_length": null,
10
+ "model_input_names": [
11
+ "input_ids",
12
+ "attention_mask"
13
+ ],
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_to_multiple_of": null,
16
+ "pad_token": "<|pad|>",
17
+ "pad_token_type_id": 0,
18
+ "padding_side": "right",
19
+ "tokenizer_class": "TokenizersBackend"
20
+ }
trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 432,
3
+ "best_metric": 0.8670062252405206,
4
+ "best_model_checkpoint": "ft_outputs/notebook_model_clf/checkpoint-432",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 432,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.23148148148148148,
14
+ "grad_norm": 34.480255126953125,
15
+ "learning_rate": 9.845758354755784e-06,
16
+ "loss": 0.49710899353027344,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.46296296296296297,
21
+ "grad_norm": 14.985294342041016,
22
+ "learning_rate": 8.560411311053985e-06,
23
+ "loss": 0.4200091552734375,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.6944444444444444,
28
+ "grad_norm": 11.86069393157959,
29
+ "learning_rate": 7.275064267352185e-06,
30
+ "loss": 0.3548846435546875,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.9259259259259259,
35
+ "grad_norm": 14.185436248779297,
36
+ "learning_rate": 5.9897172236503865e-06,
37
+ "loss": 0.3545515060424805,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.8443478260869566,
43
+ "eval_f1": 0.8380090497737557,
44
+ "eval_loss": 0.3412903845310211,
45
+ "eval_precision": 0.9090314136125655,
46
+ "eval_recall": 0.7772803581421377,
47
+ "eval_roc_auc": 0.9340782513920103,
48
+ "eval_runtime": 19.7364,
49
+ "eval_samples_per_second": 174.804,
50
+ "eval_steps_per_second": 2.736,
51
+ "step": 216
52
+ },
53
+ {
54
+ "epoch": 1.1574074074074074,
55
+ "grad_norm": 33.73603057861328,
56
+ "learning_rate": 4.704370179948586e-06,
57
+ "loss": 0.25113576889038086,
58
+ "step": 250
59
+ },
60
+ {
61
+ "epoch": 1.3888888888888888,
62
+ "grad_norm": 71.73030853271484,
63
+ "learning_rate": 3.4190231362467867e-06,
64
+ "loss": 0.17481367111206056,
65
+ "step": 300
66
+ },
67
+ {
68
+ "epoch": 1.6203703703703702,
69
+ "grad_norm": 35.59589767456055,
70
+ "learning_rate": 2.1336760925449874e-06,
71
+ "loss": 0.1653757858276367,
72
+ "step": 350
73
+ },
74
+ {
75
+ "epoch": 1.8518518518518519,
76
+ "grad_norm": 16.84499740600586,
77
+ "learning_rate": 8.483290488431877e-07,
78
+ "loss": 0.15949118614196778,
79
+ "step": 400
80
+ },
81
+ {
82
+ "epoch": 2.0,
83
+ "eval_accuracy": 0.863768115942029,
84
+ "eval_f1": 0.8670062252405206,
85
+ "eval_loss": 0.33692029118537903,
86
+ "eval_precision": 0.8769318832283916,
87
+ "eval_recall": 0.8573027420257414,
88
+ "eval_roc_auc": 0.9436943704801936,
89
+ "eval_runtime": 19.6866,
90
+ "eval_samples_per_second": 175.246,
91
+ "eval_steps_per_second": 2.743,
92
+ "step": 432
93
+ },
94
+ {
95
+ "epoch": 2.0,
96
+ "step": 432,
97
+ "total_flos": 9778520136265728.0,
98
+ "train_loss": 0.28536773942134996,
99
+ "train_runtime": 974.0574,
100
+ "train_samples_per_second": 28.327,
101
+ "train_steps_per_second": 0.444
102
+ },
103
+ {
104
+ "epoch": 2.0,
105
+ "eval_accuracy": 0.863768115942029,
106
+ "eval_f1": 0.8670062252405206,
107
+ "eval_loss": 0.33692029118537903,
108
+ "eval_precision": 0.8769318832283916,
109
+ "eval_recall": 0.8573027420257414,
110
+ "eval_roc_auc": 0.9436943704801936,
111
+ "eval_runtime": 19.3494,
112
+ "eval_samples_per_second": 178.3,
113
+ "eval_steps_per_second": 2.791,
114
+ "step": 432
115
+ }
116
+ ],
117
+ "logging_steps": 50,
118
+ "max_steps": 432,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 2,
121
+ "save_steps": 500,
122
+ "stateful_callbacks": {
123
+ "EarlyStoppingCallback": {
124
+ "args": {
125
+ "early_stopping_patience": 3,
126
+ "early_stopping_threshold": 0.0
127
+ },
128
+ "attributes": {
129
+ "early_stopping_patience_counter": 0
130
+ }
131
+ },
132
+ "TrainerControl": {
133
+ "args": {
134
+ "should_epoch_stop": false,
135
+ "should_evaluate": false,
136
+ "should_log": false,
137
+ "should_save": true,
138
+ "should_training_stop": true
139
+ },
140
+ "attributes": {}
141
+ }
142
+ },
143
+ "total_flos": 9778520136265728.0,
144
+ "train_batch_size": 64,
145
+ "trial_name": null,
146
+ "trial_params": null
147
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592b45e05a9a269ad5b812dc6f5406445dd8e02a5966389686957724c15cdd41
3
+ size 5265
training_args.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "EuroBERT/EuroBERT-610m",
3
+ "train_file": "train_set_binary.csv",
4
+ "test_file": "test_set_binary.csv",
5
+ "text_column": "sentence",
6
+ "target_column": "ideological",
7
+ "label2id": {
8
+ "0": 0,
9
+ "1": 1
10
+ },
11
+ "id2label": {
12
+ "0": "0",
13
+ "1": "1"
14
+ },
15
+ "seed": 42,
16
+ "max_seq_length": 128,
17
+ "num_train_epochs": 2,
18
+ "per_device_train_batch_size": 64,
19
+ "per_device_eval_batch_size": 64,
20
+ "gradient_accumulation_steps": 1,
21
+ "learning_rate": 1e-05,
22
+ "weight_decay": 0.02,
23
+ "warmup_ratio": 0.1,
24
+ "warmup_steps": 43,
25
+ "logging_steps": 50,
26
+ "metric_for_best_model": "f1",
27
+ "early_stopping_patience": 3,
28
+ "max_grad_norm": 1.0,
29
+ "use_class_weights": true,
30
+ "class_weights": [
31
+ 1.0379174947738647,
32
+ 0.9647552371025085
33
+ ],
34
+ "classification_threshold": 0.5,
35
+ "gradient_checkpointing": true,
36
+ "dataloader_pin_memory": false,
37
+ "auto_empty_cache": true
38
+ }