Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +26 -0
- checkpoint-300/config.json +38 -0
- checkpoint-300/model.safetensors +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/trainer_state.json +501 -0
- checkpoint-300/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/Nov03_16-28-56_r-bgonzalezbustamante-autotrain-cpu-basic-05k7pl17-01b73-wh5dr/events.out.tfevents.1730651339.r-bgonzalezbustamante-autotrain-cpu-basic-05k7pl17-01b73-wh5dr.108.0 +2 -2
- runs/Nov03_16-28-56_r-bgonzalezbustamante-autotrain-cpu-basic-05k7pl17-01b73-wh5dr/events.out.tfevents.1730654082.r-bgonzalezbustamante-autotrain-cpu-basic-05k7pl17-01b73-wh5dr.108.1 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: FacebookAI/xlm-roberta-base
|
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: 0.6090161800384521
|
17 |
+
|
18 |
+
f1: 0.7886178861788617
|
19 |
+
|
20 |
+
precision: 0.6879432624113475
|
21 |
+
|
22 |
+
recall: 0.9238095238095239
|
23 |
+
|
24 |
+
auc: 0.8025062656641604
|
25 |
+
|
26 |
+
accuracy: 0.74
|
checkpoint-300/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/xlm-roberta-base",
|
3 |
+
"_num_labels": 2,
|
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 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "NONTOXIC",
|
16 |
+
"1": "TOXIC"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"NONTOXIC": 0,
|
22 |
+
"TOXIC": 1
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-05,
|
25 |
+
"max_position_embeddings": 514,
|
26 |
+
"model_type": "xlm-roberta",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"output_past": true,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.45.0",
|
35 |
+
"type_vocab_size": 1,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 250002
|
38 |
+
}
|
checkpoint-300/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1d8a85af8ed5607450fd4d069979e9ff02ad642953d2d32171a34e1c8dd2083
|
3 |
+
size 1112205008
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8efe4d3c05dd7c420ff79f96d0c3a2dfdeb4a110f5eaa76fc4eb104dc98d3f71
|
3 |
+
size 2224524026
|
checkpoint-300/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ddf4eb02e917a839b50449a330c1d491ecea7d29591dae65c7c50e726939c49
|
3 |
+
size 13990
|
checkpoint-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cabdd96162ecddbb53d954d7eb1984d5ac789bd18a1ad68743eeb1f283f45df1
|
3 |
+
size 1064
|
checkpoint-300/trainer_state.json
ADDED
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6090161800384521,
|
3 |
+
"best_model_checkpoint": "autotrain-k2nef-2mp1e/checkpoint-300",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05,
|
13 |
+
"grad_norm": 2.0926642417907715,
|
14 |
+
"learning_rate": 8.333333333333334e-06,
|
15 |
+
"loss": 0.7016,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.1,
|
20 |
+
"grad_norm": 4.052657127380371,
|
21 |
+
"learning_rate": 1.6666666666666667e-05,
|
22 |
+
"loss": 0.7067,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.15,
|
27 |
+
"grad_norm": 5.750674724578857,
|
28 |
+
"learning_rate": 2.5e-05,
|
29 |
+
"loss": 0.6934,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2,
|
34 |
+
"grad_norm": 3.0751872062683105,
|
35 |
+
"learning_rate": 3.3333333333333335e-05,
|
36 |
+
"loss": 0.7022,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.25,
|
41 |
+
"grad_norm": 7.624610900878906,
|
42 |
+
"learning_rate": 4.166666666666667e-05,
|
43 |
+
"loss": 0.6635,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3,
|
48 |
+
"grad_norm": 6.501454830169678,
|
49 |
+
"learning_rate": 5e-05,
|
50 |
+
"loss": 0.7008,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.35,
|
55 |
+
"grad_norm": 1.1909492015838623,
|
56 |
+
"learning_rate": 4.9074074074074075e-05,
|
57 |
+
"loss": 0.7069,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4,
|
62 |
+
"grad_norm": 4.995346546173096,
|
63 |
+
"learning_rate": 4.814814814814815e-05,
|
64 |
+
"loss": 0.6667,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.45,
|
69 |
+
"grad_norm": 4.344069004058838,
|
70 |
+
"learning_rate": 4.722222222222222e-05,
|
71 |
+
"loss": 0.6798,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5,
|
76 |
+
"grad_norm": 2.269436836242676,
|
77 |
+
"learning_rate": 4.62962962962963e-05,
|
78 |
+
"loss": 0.7114,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.55,
|
83 |
+
"grad_norm": 3.151176929473877,
|
84 |
+
"learning_rate": 4.5370370370370374e-05,
|
85 |
+
"loss": 0.6304,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.6,
|
90 |
+
"grad_norm": 2.426318407058716,
|
91 |
+
"learning_rate": 4.4444444444444447e-05,
|
92 |
+
"loss": 0.7266,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.65,
|
97 |
+
"grad_norm": 2.212985038757324,
|
98 |
+
"learning_rate": 4.351851851851852e-05,
|
99 |
+
"loss": 0.7392,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.7,
|
104 |
+
"grad_norm": 1.5283116102218628,
|
105 |
+
"learning_rate": 4.259259259259259e-05,
|
106 |
+
"loss": 0.7266,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.75,
|
111 |
+
"grad_norm": 2.971235752105713,
|
112 |
+
"learning_rate": 4.166666666666667e-05,
|
113 |
+
"loss": 0.6728,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.8,
|
118 |
+
"grad_norm": 3.4530913829803467,
|
119 |
+
"learning_rate": 4.074074074074074e-05,
|
120 |
+
"loss": 0.7161,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.85,
|
125 |
+
"grad_norm": 4.985769271850586,
|
126 |
+
"learning_rate": 3.981481481481482e-05,
|
127 |
+
"loss": 0.6379,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.9,
|
132 |
+
"grad_norm": 1.9118386507034302,
|
133 |
+
"learning_rate": 3.888888888888889e-05,
|
134 |
+
"loss": 0.6737,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.95,
|
139 |
+
"grad_norm": 3.0985093116760254,
|
140 |
+
"learning_rate": 3.7962962962962964e-05,
|
141 |
+
"loss": 0.6806,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.0,
|
146 |
+
"grad_norm": 8.572888374328613,
|
147 |
+
"learning_rate": 3.7037037037037037e-05,
|
148 |
+
"loss": 0.8093,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.0,
|
153 |
+
"eval_accuracy": 0.525,
|
154 |
+
"eval_auc": 0.6939348370927318,
|
155 |
+
"eval_f1": 0.6885245901639344,
|
156 |
+
"eval_loss": 0.6925095319747925,
|
157 |
+
"eval_precision": 0.525,
|
158 |
+
"eval_recall": 1.0,
|
159 |
+
"eval_runtime": 35.807,
|
160 |
+
"eval_samples_per_second": 5.585,
|
161 |
+
"eval_steps_per_second": 0.363,
|
162 |
+
"step": 100
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.05,
|
166 |
+
"grad_norm": 1.2586256265640259,
|
167 |
+
"learning_rate": 3.611111111111111e-05,
|
168 |
+
"loss": 0.716,
|
169 |
+
"step": 105
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.1,
|
173 |
+
"grad_norm": 1.7259572744369507,
|
174 |
+
"learning_rate": 3.518518518518519e-05,
|
175 |
+
"loss": 0.6773,
|
176 |
+
"step": 110
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.15,
|
180 |
+
"grad_norm": 1.5281599760055542,
|
181 |
+
"learning_rate": 3.425925925925926e-05,
|
182 |
+
"loss": 0.7073,
|
183 |
+
"step": 115
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 1.2,
|
187 |
+
"grad_norm": 2.143573760986328,
|
188 |
+
"learning_rate": 3.3333333333333335e-05,
|
189 |
+
"loss": 0.6748,
|
190 |
+
"step": 120
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 1.25,
|
194 |
+
"grad_norm": 2.464813709259033,
|
195 |
+
"learning_rate": 3.240740740740741e-05,
|
196 |
+
"loss": 0.7014,
|
197 |
+
"step": 125
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.3,
|
201 |
+
"grad_norm": 3.4055287837982178,
|
202 |
+
"learning_rate": 3.148148148148148e-05,
|
203 |
+
"loss": 0.6871,
|
204 |
+
"step": 130
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.35,
|
208 |
+
"grad_norm": 2.0612735748291016,
|
209 |
+
"learning_rate": 3.055555555555556e-05,
|
210 |
+
"loss": 0.6959,
|
211 |
+
"step": 135
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 1.4,
|
215 |
+
"grad_norm": 4.995764255523682,
|
216 |
+
"learning_rate": 2.962962962962963e-05,
|
217 |
+
"loss": 0.6947,
|
218 |
+
"step": 140
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.45,
|
222 |
+
"grad_norm": 5.578982830047607,
|
223 |
+
"learning_rate": 2.8703703703703706e-05,
|
224 |
+
"loss": 0.6397,
|
225 |
+
"step": 145
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.5,
|
229 |
+
"grad_norm": 13.800985336303711,
|
230 |
+
"learning_rate": 2.777777777777778e-05,
|
231 |
+
"loss": 0.7913,
|
232 |
+
"step": 150
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.55,
|
236 |
+
"grad_norm": 6.1693806648254395,
|
237 |
+
"learning_rate": 2.6851851851851855e-05,
|
238 |
+
"loss": 0.7603,
|
239 |
+
"step": 155
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.6,
|
243 |
+
"grad_norm": 2.4309499263763428,
|
244 |
+
"learning_rate": 2.5925925925925925e-05,
|
245 |
+
"loss": 0.6809,
|
246 |
+
"step": 160
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.65,
|
250 |
+
"grad_norm": 3.3699936866760254,
|
251 |
+
"learning_rate": 2.5e-05,
|
252 |
+
"loss": 0.702,
|
253 |
+
"step": 165
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 1.7,
|
257 |
+
"grad_norm": 7.083240032196045,
|
258 |
+
"learning_rate": 2.4074074074074074e-05,
|
259 |
+
"loss": 0.7349,
|
260 |
+
"step": 170
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.75,
|
264 |
+
"grad_norm": 3.991142988204956,
|
265 |
+
"learning_rate": 2.314814814814815e-05,
|
266 |
+
"loss": 0.6858,
|
267 |
+
"step": 175
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.8,
|
271 |
+
"grad_norm": 2.0945520401000977,
|
272 |
+
"learning_rate": 2.2222222222222223e-05,
|
273 |
+
"loss": 0.7108,
|
274 |
+
"step": 180
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.85,
|
278 |
+
"grad_norm": 4.659959316253662,
|
279 |
+
"learning_rate": 2.1296296296296296e-05,
|
280 |
+
"loss": 0.6984,
|
281 |
+
"step": 185
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.9,
|
285 |
+
"grad_norm": 5.092476844787598,
|
286 |
+
"learning_rate": 2.037037037037037e-05,
|
287 |
+
"loss": 0.7022,
|
288 |
+
"step": 190
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 1.95,
|
292 |
+
"grad_norm": 3.881072521209717,
|
293 |
+
"learning_rate": 1.9444444444444445e-05,
|
294 |
+
"loss": 0.6897,
|
295 |
+
"step": 195
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 2.0,
|
299 |
+
"grad_norm": 2.4203667640686035,
|
300 |
+
"learning_rate": 1.8518518518518518e-05,
|
301 |
+
"loss": 0.7064,
|
302 |
+
"step": 200
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.0,
|
306 |
+
"eval_accuracy": 0.53,
|
307 |
+
"eval_auc": 0.7506766917293233,
|
308 |
+
"eval_f1": 0.6907894736842105,
|
309 |
+
"eval_loss": 0.6854195594787598,
|
310 |
+
"eval_precision": 0.5276381909547738,
|
311 |
+
"eval_recall": 1.0,
|
312 |
+
"eval_runtime": 35.8907,
|
313 |
+
"eval_samples_per_second": 5.572,
|
314 |
+
"eval_steps_per_second": 0.362,
|
315 |
+
"step": 200
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 2.05,
|
319 |
+
"grad_norm": 4.770285606384277,
|
320 |
+
"learning_rate": 1.7592592592592595e-05,
|
321 |
+
"loss": 0.688,
|
322 |
+
"step": 205
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 2.1,
|
326 |
+
"grad_norm": 2.5155324935913086,
|
327 |
+
"learning_rate": 1.6666666666666667e-05,
|
328 |
+
"loss": 0.6474,
|
329 |
+
"step": 210
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 2.15,
|
333 |
+
"grad_norm": 2.7012557983398438,
|
334 |
+
"learning_rate": 1.574074074074074e-05,
|
335 |
+
"loss": 0.7223,
|
336 |
+
"step": 215
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 2.2,
|
340 |
+
"grad_norm": 4.726611614227295,
|
341 |
+
"learning_rate": 1.4814814814814815e-05,
|
342 |
+
"loss": 0.6941,
|
343 |
+
"step": 220
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 2.25,
|
347 |
+
"grad_norm": 1.7803250551223755,
|
348 |
+
"learning_rate": 1.388888888888889e-05,
|
349 |
+
"loss": 0.6845,
|
350 |
+
"step": 225
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.3,
|
354 |
+
"grad_norm": 11.724671363830566,
|
355 |
+
"learning_rate": 1.2962962962962962e-05,
|
356 |
+
"loss": 0.6677,
|
357 |
+
"step": 230
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 2.35,
|
361 |
+
"grad_norm": 5.12057638168335,
|
362 |
+
"learning_rate": 1.2037037037037037e-05,
|
363 |
+
"loss": 0.6699,
|
364 |
+
"step": 235
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 2.4,
|
368 |
+
"grad_norm": 4.75656270980835,
|
369 |
+
"learning_rate": 1.1111111111111112e-05,
|
370 |
+
"loss": 0.7428,
|
371 |
+
"step": 240
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 2.45,
|
375 |
+
"grad_norm": 7.563472747802734,
|
376 |
+
"learning_rate": 1.0185185185185185e-05,
|
377 |
+
"loss": 0.6592,
|
378 |
+
"step": 245
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 2.5,
|
382 |
+
"grad_norm": 1.8900893926620483,
|
383 |
+
"learning_rate": 9.259259259259259e-06,
|
384 |
+
"loss": 0.6835,
|
385 |
+
"step": 250
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 2.55,
|
389 |
+
"grad_norm": 6.5432024002075195,
|
390 |
+
"learning_rate": 8.333333333333334e-06,
|
391 |
+
"loss": 0.6682,
|
392 |
+
"step": 255
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.6,
|
396 |
+
"grad_norm": 3.4254777431488037,
|
397 |
+
"learning_rate": 7.4074074074074075e-06,
|
398 |
+
"loss": 0.7187,
|
399 |
+
"step": 260
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 2.65,
|
403 |
+
"grad_norm": 5.301848411560059,
|
404 |
+
"learning_rate": 6.481481481481481e-06,
|
405 |
+
"loss": 0.6392,
|
406 |
+
"step": 265
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 2.7,
|
410 |
+
"grad_norm": 2.3317384719848633,
|
411 |
+
"learning_rate": 5.555555555555556e-06,
|
412 |
+
"loss": 0.6316,
|
413 |
+
"step": 270
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 2.75,
|
417 |
+
"grad_norm": 4.123948574066162,
|
418 |
+
"learning_rate": 4.6296296296296296e-06,
|
419 |
+
"loss": 0.6764,
|
420 |
+
"step": 275
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 2.8,
|
424 |
+
"grad_norm": 6.580291748046875,
|
425 |
+
"learning_rate": 3.7037037037037037e-06,
|
426 |
+
"loss": 0.6914,
|
427 |
+
"step": 280
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 2.85,
|
431 |
+
"grad_norm": 6.623916149139404,
|
432 |
+
"learning_rate": 2.777777777777778e-06,
|
433 |
+
"loss": 0.5946,
|
434 |
+
"step": 285
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.9,
|
438 |
+
"grad_norm": 13.349700927734375,
|
439 |
+
"learning_rate": 1.8518518518518519e-06,
|
440 |
+
"loss": 0.6564,
|
441 |
+
"step": 290
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 2.95,
|
445 |
+
"grad_norm": 29.791109085083008,
|
446 |
+
"learning_rate": 9.259259259259259e-07,
|
447 |
+
"loss": 0.613,
|
448 |
+
"step": 295
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 3.0,
|
452 |
+
"grad_norm": 3.5324182510375977,
|
453 |
+
"learning_rate": 0.0,
|
454 |
+
"loss": 0.5895,
|
455 |
+
"step": 300
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 3.0,
|
459 |
+
"eval_accuracy": 0.74,
|
460 |
+
"eval_auc": 0.8025062656641604,
|
461 |
+
"eval_f1": 0.7886178861788617,
|
462 |
+
"eval_loss": 0.6090161800384521,
|
463 |
+
"eval_precision": 0.6879432624113475,
|
464 |
+
"eval_recall": 0.9238095238095239,
|
465 |
+
"eval_runtime": 40.0605,
|
466 |
+
"eval_samples_per_second": 4.992,
|
467 |
+
"eval_steps_per_second": 0.325,
|
468 |
+
"step": 300
|
469 |
+
}
|
470 |
+
],
|
471 |
+
"logging_steps": 5,
|
472 |
+
"max_steps": 300,
|
473 |
+
"num_input_tokens_seen": 0,
|
474 |
+
"num_train_epochs": 3,
|
475 |
+
"save_steps": 500,
|
476 |
+
"stateful_callbacks": {
|
477 |
+
"EarlyStoppingCallback": {
|
478 |
+
"args": {
|
479 |
+
"early_stopping_patience": 5,
|
480 |
+
"early_stopping_threshold": 0.01
|
481 |
+
},
|
482 |
+
"attributes": {
|
483 |
+
"early_stopping_patience_counter": 0
|
484 |
+
}
|
485 |
+
},
|
486 |
+
"TrainerControl": {
|
487 |
+
"args": {
|
488 |
+
"should_epoch_stop": false,
|
489 |
+
"should_evaluate": false,
|
490 |
+
"should_log": false,
|
491 |
+
"should_save": true,
|
492 |
+
"should_training_stop": true
|
493 |
+
},
|
494 |
+
"attributes": {}
|
495 |
+
}
|
496 |
+
},
|
497 |
+
"total_flos": 157866633216000.0,
|
498 |
+
"train_batch_size": 8,
|
499 |
+
"trial_name": null,
|
500 |
+
"trial_params": null
|
501 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb8ba97e85c548fccb145838b54bf018b26f9757bc98d1b873003e64a7993366
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/xlm-roberta-base",
|
3 |
+
"_num_labels": 2,
|
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 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "NONTOXIC",
|
16 |
+
"1": "TOXIC"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"NONTOXIC": 0,
|
22 |
+
"TOXIC": 1
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-05,
|
25 |
+
"max_position_embeddings": 514,
|
26 |
+
"model_type": "xlm-roberta",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"output_past": true,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.45.0",
|
35 |
+
"type_vocab_size": 1,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 250002
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1d8a85af8ed5607450fd4d069979e9ff02ad642953d2d32171a34e1c8dd2083
|
3 |
+
size 1112205008
|
runs/Nov03_16-28-56_r-bgonzalezbustamante-autotrain-cpu-basic-05k7pl17-01b73-wh5dr/events.out.tfevents.1730651339.r-bgonzalezbustamante-autotrain-cpu-basic-05k7pl17-01b73-wh5dr.108.0
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 sha256:324f8ec6ee90c1fd14977a855945025fc9133232d59f44a2528183edbd7407b0
|
3 |
+
size 19633
|
runs/Nov03_16-28-56_r-bgonzalezbustamante-autotrain-cpu-basic-05k7pl17-01b73-wh5dr/events.out.tfevents.1730654082.r-bgonzalezbustamante-autotrain-cpu-basic-05k7pl17-01b73-wh5dr.108.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3de21afc1c616a7033663f2b60aaa4531eeabc7cf945866fc1fc04551e8871d
|
3 |
+
size 607
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
|
3 |
+
size 17082999
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb8ba97e85c548fccb145838b54bf018b26f9757bc98d1b873003e64a7993366
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-k2nef-2mp1e/autotrain-data",
|
3 |
+
"model": "FacebookAI/xlm-roberta-base",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
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": "autotrain-k2nef-2mp1e",
|
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": "bgonzalezbustamante",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|