uvegesistvan
commited on
Commit
•
6e2bb01
1
Parent(s):
a189df9
Upload folder using huggingface_hub
Browse files- Hun_Eng_RoBERTa_large_Plain_predictions_ENG.xlsx +0 -0
- Hun_Eng_RoBERTa_large_Plain_predictions_HUN.xlsx +0 -0
- XLM-RoBERTa_base_Plain_predictions.xlsx +0 -0
- XLM-RoBERTa_large_Plain_predictions.xlsx +0 -0
- checkpoint-4452/config.json +29 -0
- checkpoint-4452/model.safetensors +3 -0
- checkpoint-4452/optimizer.pt +3 -0
- checkpoint-4452/rng_state.pth +3 -0
- checkpoint-4452/scheduler.pt +3 -0
- checkpoint-4452/trainer_state.json +118 -0
- checkpoint-4452/training_args.bin +3 -0
- config.json +29 -0
- events.out.tfevents.1728743175.1edb6b62aae0.1000.0 +3 -0
- model.safetensors +3 -0
- test_dataset_roberta_large_ENG.xlsx +0 -0
- test_dataset_roberta_large_HUN.xlsx +0 -0
- training_args.bin +3 -0
Hun_Eng_RoBERTa_large_Plain_predictions_ENG.xlsx
ADDED
Binary file (119 kB). View file
|
|
Hun_Eng_RoBERTa_large_Plain_predictions_HUN.xlsx
ADDED
Binary file (243 kB). View file
|
|
XLM-RoBERTa_base_Plain_predictions.xlsx
ADDED
Binary file (135 kB). View file
|
|
XLM-RoBERTa_large_Plain_predictions.xlsx
ADDED
Binary file (135 kB). View file
|
|
checkpoint-4452/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
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": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"problem_type": "multi_label_classification",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.45.2",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 250002
|
29 |
+
}
|
checkpoint-4452/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88741b0f87b730216fef92fffd20f0aa842b2dab67cb3cb4f8cf5e4451cc1d08
|
3 |
+
size 1112205008
|
checkpoint-4452/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fca9d2319bf61c46ca77cfebad79a8e400618752dbbda6075da8193ae86a68ab
|
3 |
+
size 2224529658
|
checkpoint-4452/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c9d8bd3a74e25c778856e7a78b9e9ec0618323b8f309673645f4c9d390f9711
|
3 |
+
size 14244
|
checkpoint-4452/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af3d832d51f43cd5d3835fdf31f0538a2455743a8985ef0eaf0c7f51e0f690f3
|
3 |
+
size 1064
|
checkpoint-4452/trainer_state.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6224449276924133,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/XLM-RoBERTa/checkpoint-4452",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 4452,
|
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": 8.267438888549805,
|
14 |
+
"learning_rate": 4.5e-06,
|
15 |
+
"loss": 0.6879,
|
16 |
+
"step": 1113
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.6130337078651685,
|
21 |
+
"eval_f1": 0.674233825198638,
|
22 |
+
"eval_loss": 0.6553897857666016,
|
23 |
+
"eval_precision": 0.5920265780730897,
|
24 |
+
"eval_recall": 0.7829525483304042,
|
25 |
+
"eval_runtime": 16.6298,
|
26 |
+
"eval_samples_per_second": 133.796,
|
27 |
+
"eval_steps_per_second": 8.419,
|
28 |
+
"step": 1113
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"grad_norm": 11.426044464111328,
|
33 |
+
"learning_rate": 4.000000000000001e-06,
|
34 |
+
"loss": 0.6446,
|
35 |
+
"step": 2226
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.6449438202247191,
|
40 |
+
"eval_f1": 0.6786004882017901,
|
41 |
+
"eval_loss": 0.6413919925689697,
|
42 |
+
"eval_precision": 0.6318181818181818,
|
43 |
+
"eval_recall": 0.7328646748681898,
|
44 |
+
"eval_runtime": 16.2984,
|
45 |
+
"eval_samples_per_second": 136.517,
|
46 |
+
"eval_steps_per_second": 8.59,
|
47 |
+
"step": 2226
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.0,
|
51 |
+
"grad_norm": 34.342185974121094,
|
52 |
+
"learning_rate": 3.5e-06,
|
53 |
+
"loss": 0.62,
|
54 |
+
"step": 3339
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.6494382022471911,
|
59 |
+
"eval_f1": 0.6758104738154613,
|
60 |
+
"eval_loss": 0.6359991431236267,
|
61 |
+
"eval_precision": 0.6411671924290221,
|
62 |
+
"eval_recall": 0.7144112478031635,
|
63 |
+
"eval_runtime": 16.3309,
|
64 |
+
"eval_samples_per_second": 136.245,
|
65 |
+
"eval_steps_per_second": 8.573,
|
66 |
+
"step": 3339
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 4.0,
|
70 |
+
"grad_norm": 15.571684837341309,
|
71 |
+
"learning_rate": 3e-06,
|
72 |
+
"loss": 0.5939,
|
73 |
+
"step": 4452
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 4.0,
|
77 |
+
"eval_accuracy": 0.6548314606741573,
|
78 |
+
"eval_f1": 0.7009345794392523,
|
79 |
+
"eval_loss": 0.6224449276924133,
|
80 |
+
"eval_precision": 0.6293706293706294,
|
81 |
+
"eval_recall": 0.7908611599297012,
|
82 |
+
"eval_runtime": 16.3616,
|
83 |
+
"eval_samples_per_second": 135.99,
|
84 |
+
"eval_steps_per_second": 8.557,
|
85 |
+
"step": 4452
|
86 |
+
}
|
87 |
+
],
|
88 |
+
"logging_steps": 100,
|
89 |
+
"max_steps": 11130,
|
90 |
+
"num_input_tokens_seen": 0,
|
91 |
+
"num_train_epochs": 10,
|
92 |
+
"save_steps": 100,
|
93 |
+
"stateful_callbacks": {
|
94 |
+
"EarlyStoppingCallback": {
|
95 |
+
"args": {
|
96 |
+
"early_stopping_patience": 2,
|
97 |
+
"early_stopping_threshold": 0.0
|
98 |
+
},
|
99 |
+
"attributes": {
|
100 |
+
"early_stopping_patience_counter": 0
|
101 |
+
}
|
102 |
+
},
|
103 |
+
"TrainerControl": {
|
104 |
+
"args": {
|
105 |
+
"should_epoch_stop": false,
|
106 |
+
"should_evaluate": false,
|
107 |
+
"should_log": false,
|
108 |
+
"should_save": true,
|
109 |
+
"should_training_stop": false
|
110 |
+
},
|
111 |
+
"attributes": {}
|
112 |
+
}
|
113 |
+
},
|
114 |
+
"total_flos": 1.872929736474624e+16,
|
115 |
+
"train_batch_size": 16,
|
116 |
+
"trial_name": null,
|
117 |
+
"trial_params": null
|
118 |
+
}
|
checkpoint-4452/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dff238aadf09bba908ff3dfad1141ff451e76dde0b91b1ef88bb5f1889cd5372
|
3 |
+
size 5176
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
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": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"problem_type": "multi_label_classification",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.45.2",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 250002
|
29 |
+
}
|
events.out.tfevents.1728743175.1edb6b62aae0.1000.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78f261297030e07ec31596e3f7ab7e5d5b941003a22057e0fc3bbdbc5395142c
|
3 |
+
size 9441
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88741b0f87b730216fef92fffd20f0aa842b2dab67cb3cb4f8cf5e4451cc1d08
|
3 |
+
size 1112205008
|
test_dataset_roberta_large_ENG.xlsx
ADDED
Binary file (130 kB). View file
|
|
test_dataset_roberta_large_HUN.xlsx
ADDED
Binary file (117 kB). View file
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dff238aadf09bba908ff3dfad1141ff451e76dde0b91b1ef88bb5f1889cd5372
|
3 |
+
size 5176
|