Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +36 -0
- autotrain-data/dataset_dict.json +1 -0
- autotrain-data/train/data-00000-of-00001.arrow +3 -0
- autotrain-data/train/dataset_info.json +20 -0
- autotrain-data/train/state.json +16 -0
- autotrain-data/validation/data-00000-of-00001.arrow +3 -0
- autotrain-data/validation/dataset_info.json +20 -0
- autotrain-data/validation/state.json +16 -0
- checkpoint-24/config.json +41 -0
- checkpoint-24/model.safetensors +3 -0
- checkpoint-24/optimizer.pt +3 -0
- checkpoint-24/rng_state.pth +3 -0
- checkpoint-24/scheduler.pt +3 -0
- checkpoint-24/trainer_state.json +264 -0
- checkpoint-24/training_args.bin +3 -0
- config.json +41 -0
- model.safetensors +3 -0
- runs/Nov24_00-33-58_DESKTOP-PHPU4HD/events.out.tfevents.1732404840.DESKTOP-PHPU4HD.3204.0 +2 -2
- runs/Nov24_00-33-58_DESKTOP-PHPU4HD/events.out.tfevents.1732405835.DESKTOP-PHPU4HD.3204.1 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +61 -0
- training_args.bin +3 -0
- training_params.json +30 -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
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.946372926235199
|
17 |
+
|
18 |
+
f1_macro: 0.5230769230769231
|
19 |
+
|
20 |
+
f1_micro: 0.7391304347826086
|
21 |
+
|
22 |
+
f1_weighted: 0.7210702341137124
|
23 |
+
|
24 |
+
precision_macro: 0.5277777777777778
|
25 |
+
|
26 |
+
precision_micro: 0.7391304347826086
|
27 |
+
|
28 |
+
precision_weighted: 0.710144927536232
|
29 |
+
|
30 |
+
recall_macro: 0.5238095238095238
|
31 |
+
|
32 |
+
recall_micro: 0.7391304347826086
|
33 |
+
|
34 |
+
recall_weighted: 0.7391304347826086
|
35 |
+
|
36 |
+
accuracy: 0.7391304347826086
|
autotrain-data/dataset_dict.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"splits": ["train", "validation"]}
|
autotrain-data/train/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faba478211bafa2450a74a6896510b1fd2413f04364a6ff5c61a935b2aacc530
|
3 |
+
size 4968
|
autotrain-data/train/dataset_info.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"autotrain_text": {
|
6 |
+
"dtype": "string",
|
7 |
+
"_type": "Value"
|
8 |
+
},
|
9 |
+
"autotrain_label": {
|
10 |
+
"names": [
|
11 |
+
"0",
|
12 |
+
"1",
|
13 |
+
"2"
|
14 |
+
],
|
15 |
+
"_type": "ClassLabel"
|
16 |
+
}
|
17 |
+
},
|
18 |
+
"homepage": "",
|
19 |
+
"license": ""
|
20 |
+
}
|
autotrain-data/train/state.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "9b4cca20eb4faa4e",
|
8 |
+
"_format_columns": [
|
9 |
+
"autotrain_text",
|
10 |
+
"autotrain_label"
|
11 |
+
],
|
12 |
+
"_format_kwargs": {},
|
13 |
+
"_format_type": null,
|
14 |
+
"_output_all_columns": false,
|
15 |
+
"_split": null
|
16 |
+
}
|
autotrain-data/validation/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56d817b35396ed4ddbce23ad7e048c1e28edbb59b5cb74fd5efbcf3545929500
|
3 |
+
size 2016
|
autotrain-data/validation/dataset_info.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"autotrain_text": {
|
6 |
+
"dtype": "string",
|
7 |
+
"_type": "Value"
|
8 |
+
},
|
9 |
+
"autotrain_label": {
|
10 |
+
"names": [
|
11 |
+
"0",
|
12 |
+
"1",
|
13 |
+
"2"
|
14 |
+
],
|
15 |
+
"_type": "ClassLabel"
|
16 |
+
}
|
17 |
+
},
|
18 |
+
"homepage": "",
|
19 |
+
"license": ""
|
20 |
+
}
|
autotrain-data/validation/state.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "6bedf6a163b52e5f",
|
8 |
+
"_format_columns": [
|
9 |
+
"autotrain_text",
|
10 |
+
"autotrain_label"
|
11 |
+
],
|
12 |
+
"_format_kwargs": {},
|
13 |
+
"_format_type": null,
|
14 |
+
"_output_all_columns": false,
|
15 |
+
"_split": null
|
16 |
+
}
|
checkpoint-24/config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"XLMRobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "0",
|
17 |
+
"1": "1",
|
18 |
+
"2": "2"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"0": 0,
|
24 |
+
"1": 1,
|
25 |
+
"2": 2
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-05,
|
28 |
+
"max_position_embeddings": 514,
|
29 |
+
"model_type": "xlm-roberta",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"output_past": true,
|
33 |
+
"pad_token_id": 1,
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"problem_type": "single_label_classification",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.46.2",
|
38 |
+
"type_vocab_size": 1,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 250002
|
41 |
+
}
|
checkpoint-24/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05f5fe93423f2170a62ee644856c8c4f77c413bc8b152f40f3b63706294d6e58
|
3 |
+
size 1112208084
|
checkpoint-24/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3426c89a8770d0331873dc0f6226443d6866907429c3754f330cd87365ebeb06
|
3 |
+
size 2224530170
|
checkpoint-24/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9f949ebd38ae8393cd3eda0d6e6eb2354426cc686b2885735ccaeaea9352ebe
|
3 |
+
size 13990
|
checkpoint-24/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c16a55e06cfdab3977ba138cb50c04901f2c418a126fa98556f2de0b0f4689f3
|
3 |
+
size 1064
|
checkpoint-24/trainer_state.json
ADDED
@@ -0,0 +1,264 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.946372926235199,
|
3 |
+
"best_model_checkpoint": "finetune-tiktok-brat7\\checkpoint-24",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 24,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.125,
|
13 |
+
"grad_norm": 48.439212799072266,
|
14 |
+
"learning_rate": 3.3333333333333333e-06,
|
15 |
+
"loss": 1.298,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.25,
|
20 |
+
"grad_norm": 17.51978874206543,
|
21 |
+
"learning_rate": 6.666666666666667e-06,
|
22 |
+
"loss": 0.3288,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.375,
|
27 |
+
"grad_norm": 36.70003128051758,
|
28 |
+
"learning_rate": 1e-05,
|
29 |
+
"loss": 0.5146,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.5,
|
34 |
+
"grad_norm": 36.54575729370117,
|
35 |
+
"learning_rate": 9.523809523809525e-06,
|
36 |
+
"loss": 1.3186,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.625,
|
41 |
+
"grad_norm": 38.397705078125,
|
42 |
+
"learning_rate": 9.047619047619049e-06,
|
43 |
+
"loss": 1.0083,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.75,
|
48 |
+
"grad_norm": 52.007572174072266,
|
49 |
+
"learning_rate": 8.571428571428571e-06,
|
50 |
+
"loss": 0.9936,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.875,
|
55 |
+
"grad_norm": 57.42391586303711,
|
56 |
+
"learning_rate": 8.095238095238097e-06,
|
57 |
+
"loss": 1.1921,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.0,
|
62 |
+
"grad_norm": 39.129276275634766,
|
63 |
+
"learning_rate": 7.61904761904762e-06,
|
64 |
+
"loss": 1.2205,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.0,
|
69 |
+
"eval_accuracy": 0.6521739130434783,
|
70 |
+
"eval_f1_macro": 0.4761904761904762,
|
71 |
+
"eval_f1_micro": 0.6521739130434783,
|
72 |
+
"eval_f1_weighted": 0.6521739130434783,
|
73 |
+
"eval_loss": 1.1324578523635864,
|
74 |
+
"eval_precision_macro": 0.4761904761904762,
|
75 |
+
"eval_precision_micro": 0.6521739130434783,
|
76 |
+
"eval_precision_weighted": 0.6521739130434783,
|
77 |
+
"eval_recall_macro": 0.4761904761904762,
|
78 |
+
"eval_recall_micro": 0.6521739130434783,
|
79 |
+
"eval_recall_weighted": 0.6521739130434783,
|
80 |
+
"eval_runtime": 27.369,
|
81 |
+
"eval_samples_per_second": 0.84,
|
82 |
+
"eval_steps_per_second": 0.073,
|
83 |
+
"step": 8
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.125,
|
87 |
+
"grad_norm": 30.69573211669922,
|
88 |
+
"learning_rate": 7.1428571428571436e-06,
|
89 |
+
"loss": 0.8532,
|
90 |
+
"step": 9
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.25,
|
94 |
+
"grad_norm": 19.239377975463867,
|
95 |
+
"learning_rate": 6.666666666666667e-06,
|
96 |
+
"loss": 0.718,
|
97 |
+
"step": 10
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 1.375,
|
101 |
+
"grad_norm": 36.98495101928711,
|
102 |
+
"learning_rate": 6.1904761904761914e-06,
|
103 |
+
"loss": 0.7192,
|
104 |
+
"step": 11
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.5,
|
108 |
+
"grad_norm": 29.336002349853516,
|
109 |
+
"learning_rate": 5.7142857142857145e-06,
|
110 |
+
"loss": 1.0733,
|
111 |
+
"step": 12
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.625,
|
115 |
+
"grad_norm": 8.844223022460938,
|
116 |
+
"learning_rate": 5.2380952380952384e-06,
|
117 |
+
"loss": 0.2654,
|
118 |
+
"step": 13
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 1.75,
|
122 |
+
"grad_norm": 17.313766479492188,
|
123 |
+
"learning_rate": 4.761904761904762e-06,
|
124 |
+
"loss": 0.643,
|
125 |
+
"step": 14
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.875,
|
129 |
+
"grad_norm": 12.483030319213867,
|
130 |
+
"learning_rate": 4.2857142857142855e-06,
|
131 |
+
"loss": 0.3099,
|
132 |
+
"step": 15
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 2.0,
|
136 |
+
"grad_norm": 8.137201309204102,
|
137 |
+
"learning_rate": 3.80952380952381e-06,
|
138 |
+
"loss": 0.0809,
|
139 |
+
"step": 16
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 2.0,
|
143 |
+
"eval_accuracy": 0.6956521739130435,
|
144 |
+
"eval_f1_macro": 0.49096880131362886,
|
145 |
+
"eval_f1_micro": 0.6956521739130435,
|
146 |
+
"eval_f1_weighted": 0.6791604197901049,
|
147 |
+
"eval_loss": 0.9708660840988159,
|
148 |
+
"eval_precision_macro": 0.48253968253968255,
|
149 |
+
"eval_precision_micro": 0.6956521739130435,
|
150 |
+
"eval_precision_weighted": 0.6637681159420289,
|
151 |
+
"eval_recall_macro": 0.5,
|
152 |
+
"eval_recall_micro": 0.6956521739130435,
|
153 |
+
"eval_recall_weighted": 0.6956521739130435,
|
154 |
+
"eval_runtime": 27.3832,
|
155 |
+
"eval_samples_per_second": 0.84,
|
156 |
+
"eval_steps_per_second": 0.073,
|
157 |
+
"step": 16
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 2.125,
|
161 |
+
"grad_norm": 15.641371726989746,
|
162 |
+
"learning_rate": 3.3333333333333333e-06,
|
163 |
+
"loss": 0.4351,
|
164 |
+
"step": 17
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.25,
|
168 |
+
"grad_norm": 23.520936965942383,
|
169 |
+
"learning_rate": 2.8571428571428573e-06,
|
170 |
+
"loss": 0.4472,
|
171 |
+
"step": 18
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 2.375,
|
175 |
+
"grad_norm": 19.283954620361328,
|
176 |
+
"learning_rate": 2.380952380952381e-06,
|
177 |
+
"loss": 0.216,
|
178 |
+
"step": 19
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 2.5,
|
182 |
+
"grad_norm": 35.63965606689453,
|
183 |
+
"learning_rate": 1.904761904761905e-06,
|
184 |
+
"loss": 0.5644,
|
185 |
+
"step": 20
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 2.625,
|
189 |
+
"grad_norm": 14.39991283416748,
|
190 |
+
"learning_rate": 1.4285714285714286e-06,
|
191 |
+
"loss": 0.4427,
|
192 |
+
"step": 21
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 2.75,
|
196 |
+
"grad_norm": 22.22780418395996,
|
197 |
+
"learning_rate": 9.523809523809525e-07,
|
198 |
+
"loss": 0.4644,
|
199 |
+
"step": 22
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 2.875,
|
203 |
+
"grad_norm": 21.318103790283203,
|
204 |
+
"learning_rate": 4.7619047619047623e-07,
|
205 |
+
"loss": 0.5123,
|
206 |
+
"step": 23
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 3.0,
|
210 |
+
"grad_norm": 20.380773544311523,
|
211 |
+
"learning_rate": 0.0,
|
212 |
+
"loss": 0.8922,
|
213 |
+
"step": 24
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 3.0,
|
217 |
+
"eval_accuracy": 0.7391304347826086,
|
218 |
+
"eval_f1_macro": 0.5230769230769231,
|
219 |
+
"eval_f1_micro": 0.7391304347826086,
|
220 |
+
"eval_f1_weighted": 0.7210702341137124,
|
221 |
+
"eval_loss": 0.946372926235199,
|
222 |
+
"eval_precision_macro": 0.5277777777777778,
|
223 |
+
"eval_precision_micro": 0.7391304347826086,
|
224 |
+
"eval_precision_weighted": 0.710144927536232,
|
225 |
+
"eval_recall_macro": 0.5238095238095238,
|
226 |
+
"eval_recall_micro": 0.7391304347826086,
|
227 |
+
"eval_recall_weighted": 0.7391304347826086,
|
228 |
+
"eval_runtime": 27.6232,
|
229 |
+
"eval_samples_per_second": 0.833,
|
230 |
+
"eval_steps_per_second": 0.072,
|
231 |
+
"step": 24
|
232 |
+
}
|
233 |
+
],
|
234 |
+
"logging_steps": 1,
|
235 |
+
"max_steps": 24,
|
236 |
+
"num_input_tokens_seen": 0,
|
237 |
+
"num_train_epochs": 3,
|
238 |
+
"save_steps": 500,
|
239 |
+
"stateful_callbacks": {
|
240 |
+
"EarlyStoppingCallback": {
|
241 |
+
"args": {
|
242 |
+
"early_stopping_patience": 5,
|
243 |
+
"early_stopping_threshold": 0.01
|
244 |
+
},
|
245 |
+
"attributes": {
|
246 |
+
"early_stopping_patience_counter": 0
|
247 |
+
}
|
248 |
+
},
|
249 |
+
"TrainerControl": {
|
250 |
+
"args": {
|
251 |
+
"should_epoch_stop": false,
|
252 |
+
"should_evaluate": false,
|
253 |
+
"should_log": false,
|
254 |
+
"should_save": true,
|
255 |
+
"should_training_stop": true
|
256 |
+
},
|
257 |
+
"attributes": {}
|
258 |
+
}
|
259 |
+
},
|
260 |
+
"total_flos": 46571074937856.0,
|
261 |
+
"train_batch_size": 8,
|
262 |
+
"trial_name": null,
|
263 |
+
"trial_params": null
|
264 |
+
}
|
checkpoint-24/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9b050b0ef212bec5d00b2af8ebbfd6cf5b41ea3e5dfdad889542b5a12122389
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"XLMRobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "0",
|
17 |
+
"1": "1",
|
18 |
+
"2": "2"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"0": 0,
|
24 |
+
"1": 1,
|
25 |
+
"2": 2
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-05,
|
28 |
+
"max_position_embeddings": 514,
|
29 |
+
"model_type": "xlm-roberta",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"output_past": true,
|
33 |
+
"pad_token_id": 1,
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"problem_type": "single_label_classification",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.46.2",
|
38 |
+
"type_vocab_size": 1,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 250002
|
41 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05f5fe93423f2170a62ee644856c8c4f77c413bc8b152f40f3b63706294d6e58
|
3 |
+
size 1112208084
|
runs/Nov24_00-33-58_DESKTOP-PHPU4HD/events.out.tfevents.1732404840.DESKTOP-PHPU4HD.3204.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0321ddf4586f81259c92a728dc4d5a01e88daa1c1acd2d3b4b852387f568f0b5
|
3 |
+
size 13169
|
runs/Nov24_00-33-58_DESKTOP-PHPU4HD/events.out.tfevents.1732405835.DESKTOP-PHPU4HD.3204.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1a80e85a1b2913d74ce65df8406bff99c114b6f274ecfbddd7006ac813cd2cd
|
3 |
+
size 906
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
3 |
+
size 17082999
|
tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"max_length": 128,
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"pad_to_multiple_of": null,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"pad_token_type_id": 0,
|
54 |
+
"padding_side": "right",
|
55 |
+
"sep_token": "</s>",
|
56 |
+
"stride": 0,
|
57 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
58 |
+
"truncation_side": "right",
|
59 |
+
"truncation_strategy": "longest_first",
|
60 |
+
"unk_token": "<unk>"
|
61 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9b050b0ef212bec5d00b2af8ebbfd6cf5b41ea3e5dfdad889542b5a12122389
|
3 |
+
size 5304
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "finetune-tiktok-brat7/autotrain-data",
|
3 |
+
"model": "cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual",
|
4 |
+
"lr": 1e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 512,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "finetune-tiktok-brat7",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "Lyreck",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|