Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-843/config.json +42 -0
- checkpoint-843/model.safetensors +3 -0
- checkpoint-843/optimizer.pt +3 -0
- checkpoint-843/rng_state.pth +3 -0
- checkpoint-843/scheduler.pt +3 -0
- checkpoint-843/trainer_state.json +270 -0
- checkpoint-843/training_args.bin +3 -0
- config.json +42 -0
- model.safetensors +3 -0
- runs/Apr15_00-15-00_r-aveo-tt3-hpvnh2hj-124f7-v0zy5/events.out.tfevents.1713140101.r-aveo-tt3-hpvnh2hj-124f7-v0zy5.107.0 +2 -2
- runs/Apr15_00-15-00_r-aveo-tt3-hpvnh2hj-124f7-v0zy5/events.out.tfevents.1713169784.r-aveo-tt3-hpvnh2hj-124f7-v0zy5.107.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
widget:
|
7 |
+
- text: "I love AutoTrain"
|
8 |
+
datasets:
|
9 |
+
- autotrain-wg8v5-kpkgo/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 1.3752745389938354
|
18 |
+
|
19 |
+
f1_macro: 0.12909967845659162
|
20 |
+
|
21 |
+
f1_micro: 0.47655786350148366
|
22 |
+
|
23 |
+
f1_weighted: 0.30761733472000913
|
24 |
+
|
25 |
+
precision_macro: 0.09531157270029673
|
26 |
+
|
27 |
+
precision_micro: 0.47655786350148366
|
28 |
+
|
29 |
+
precision_weighted: 0.22710739726509874
|
30 |
+
|
31 |
+
recall_macro: 0.2
|
32 |
+
|
33 |
+
recall_micro: 0.47655786350148366
|
34 |
+
|
35 |
+
recall_weighted: 0.47655786350148366
|
36 |
+
|
37 |
+
accuracy: 0.47655786350148366
|
checkpoint-843/config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "Happy",
|
15 |
+
"1": "Natural",
|
16 |
+
"2": "Sad",
|
17 |
+
"3": "Very Happy",
|
18 |
+
"4": "Very Sad"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"Happy": 0,
|
24 |
+
"Natural": 1,
|
25 |
+
"Sad": 2,
|
26 |
+
"Very Happy": 3,
|
27 |
+
"Very Sad": 4
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-12,
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "bert",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.39.3",
|
39 |
+
"type_vocab_size": 2,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 30522
|
42 |
+
}
|
checkpoint-843/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7243385d23010f643a2c85f5225997a2522b60877bf4ea06b0da3df94a4616f2
|
3 |
+
size 437967876
|
checkpoint-843/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d27c790daf901c72d580da5b98ab2d81afc9c93903fcdf3f4096d684797906da
|
3 |
+
size 876051194
|
checkpoint-843/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6748f7d5b837d994aea368fc2ae6527d8e85d067616599ed87762ea0307f064c
|
3 |
+
size 13990
|
checkpoint-843/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c6878f1980c691230187b05ee0d48a957642a50782484eb86f0e3f85a46a9e4
|
3 |
+
size 1064
|
checkpoint-843/trainer_state.json
ADDED
@@ -0,0 +1,270 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.3752745389938354,
|
3 |
+
"best_model_checkpoint": "autotrain-wg8v5-kpkgo/checkpoint-843",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 843,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"grad_norm": 6.179622650146484,
|
14 |
+
"learning_rate": 4.940711462450593e-06,
|
15 |
+
"loss": 1.7123,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.06,
|
20 |
+
"grad_norm": 6.649145603179932,
|
21 |
+
"learning_rate": 9.881422924901186e-06,
|
22 |
+
"loss": 1.5335,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.09,
|
27 |
+
"grad_norm": 4.227591037750244,
|
28 |
+
"learning_rate": 1.482213438735178e-05,
|
29 |
+
"loss": 1.4174,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.12,
|
34 |
+
"grad_norm": 5.757178783416748,
|
35 |
+
"learning_rate": 1.9762845849802372e-05,
|
36 |
+
"loss": 1.3798,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.15,
|
41 |
+
"grad_norm": 6.150519847869873,
|
42 |
+
"learning_rate": 2.4703557312252964e-05,
|
43 |
+
"loss": 1.3849,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.18,
|
48 |
+
"grad_norm": 8.02762508392334,
|
49 |
+
"learning_rate": 2.964426877470356e-05,
|
50 |
+
"loss": 1.4092,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.21,
|
55 |
+
"grad_norm": 5.58803653717041,
|
56 |
+
"learning_rate": 3.4584980237154155e-05,
|
57 |
+
"loss": 1.3856,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.24,
|
62 |
+
"grad_norm": 6.091395378112793,
|
63 |
+
"learning_rate": 3.9525691699604744e-05,
|
64 |
+
"loss": 1.3579,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.27,
|
69 |
+
"grad_norm": 5.184357166290283,
|
70 |
+
"learning_rate": 4.446640316205534e-05,
|
71 |
+
"loss": 1.4074,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.3,
|
76 |
+
"grad_norm": 5.105162620544434,
|
77 |
+
"learning_rate": 4.940711462450593e-05,
|
78 |
+
"loss": 1.3069,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.33,
|
83 |
+
"grad_norm": 7.753561019897461,
|
84 |
+
"learning_rate": 4.951669595782074e-05,
|
85 |
+
"loss": 1.4305,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.36,
|
90 |
+
"grad_norm": 8.277456283569336,
|
91 |
+
"learning_rate": 4.896748681898067e-05,
|
92 |
+
"loss": 1.3952,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.39,
|
97 |
+
"grad_norm": 6.107973575592041,
|
98 |
+
"learning_rate": 4.84182776801406e-05,
|
99 |
+
"loss": 1.34,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.42,
|
104 |
+
"grad_norm": 7.971636772155762,
|
105 |
+
"learning_rate": 4.786906854130053e-05,
|
106 |
+
"loss": 1.3664,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.44,
|
111 |
+
"grad_norm": 9.235652923583984,
|
112 |
+
"learning_rate": 4.7319859402460456e-05,
|
113 |
+
"loss": 1.3988,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.47,
|
118 |
+
"grad_norm": 2.7545487880706787,
|
119 |
+
"learning_rate": 4.677065026362039e-05,
|
120 |
+
"loss": 1.4104,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5,
|
125 |
+
"grad_norm": 5.908019542694092,
|
126 |
+
"learning_rate": 4.6221441124780316e-05,
|
127 |
+
"loss": 1.3817,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.53,
|
132 |
+
"grad_norm": 4.202744960784912,
|
133 |
+
"learning_rate": 4.567223198594025e-05,
|
134 |
+
"loss": 1.3859,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.56,
|
139 |
+
"grad_norm": 7.947572231292725,
|
140 |
+
"learning_rate": 4.5123022847100176e-05,
|
141 |
+
"loss": 1.3895,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.59,
|
146 |
+
"grad_norm": 3.720993757247925,
|
147 |
+
"learning_rate": 4.457381370826011e-05,
|
148 |
+
"loss": 1.3206,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.62,
|
153 |
+
"grad_norm": 4.2290263175964355,
|
154 |
+
"learning_rate": 4.4024604569420036e-05,
|
155 |
+
"loss": 1.4144,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.65,
|
160 |
+
"grad_norm": 5.278575420379639,
|
161 |
+
"learning_rate": 4.347539543057997e-05,
|
162 |
+
"loss": 1.3504,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.68,
|
167 |
+
"grad_norm": 4.833432674407959,
|
168 |
+
"learning_rate": 4.2926186291739896e-05,
|
169 |
+
"loss": 1.3349,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.71,
|
174 |
+
"grad_norm": 3.244654655456543,
|
175 |
+
"learning_rate": 4.237697715289983e-05,
|
176 |
+
"loss": 1.3701,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.74,
|
181 |
+
"grad_norm": 5.314866065979004,
|
182 |
+
"learning_rate": 4.1827768014059756e-05,
|
183 |
+
"loss": 1.395,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.77,
|
188 |
+
"grad_norm": 6.206879138946533,
|
189 |
+
"learning_rate": 4.127855887521968e-05,
|
190 |
+
"loss": 1.3853,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.8,
|
195 |
+
"grad_norm": 3.967287540435791,
|
196 |
+
"learning_rate": 4.072934973637961e-05,
|
197 |
+
"loss": 1.3525,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.83,
|
202 |
+
"grad_norm": 4.5076003074646,
|
203 |
+
"learning_rate": 4.018014059753954e-05,
|
204 |
+
"loss": 1.4722,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.86,
|
209 |
+
"grad_norm": 6.542933940887451,
|
210 |
+
"learning_rate": 3.9630931458699476e-05,
|
211 |
+
"loss": 1.5171,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.89,
|
216 |
+
"grad_norm": 3.0289199352264404,
|
217 |
+
"learning_rate": 3.90817223198594e-05,
|
218 |
+
"loss": 1.4568,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.92,
|
223 |
+
"grad_norm": 5.208413124084473,
|
224 |
+
"learning_rate": 3.8532513181019336e-05,
|
225 |
+
"loss": 1.4538,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.95,
|
230 |
+
"grad_norm": 4.89143180847168,
|
231 |
+
"learning_rate": 3.798330404217926e-05,
|
232 |
+
"loss": 1.2829,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.98,
|
237 |
+
"grad_norm": 11.690943717956543,
|
238 |
+
"learning_rate": 3.7434094903339196e-05,
|
239 |
+
"loss": 1.4691,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.0,
|
244 |
+
"eval_accuracy": 0.47655786350148366,
|
245 |
+
"eval_f1_macro": 0.12909967845659162,
|
246 |
+
"eval_f1_micro": 0.47655786350148366,
|
247 |
+
"eval_f1_weighted": 0.30761733472000913,
|
248 |
+
"eval_loss": 1.3752745389938354,
|
249 |
+
"eval_precision_macro": 0.09531157270029673,
|
250 |
+
"eval_precision_micro": 0.47655786350148366,
|
251 |
+
"eval_precision_weighted": 0.22710739726509874,
|
252 |
+
"eval_recall_macro": 0.2,
|
253 |
+
"eval_recall_micro": 0.47655786350148366,
|
254 |
+
"eval_recall_weighted": 0.47655786350148366,
|
255 |
+
"eval_runtime": 640.7518,
|
256 |
+
"eval_samples_per_second": 2.63,
|
257 |
+
"eval_steps_per_second": 0.165,
|
258 |
+
"step": 843
|
259 |
+
}
|
260 |
+
],
|
261 |
+
"logging_steps": 25,
|
262 |
+
"max_steps": 2529,
|
263 |
+
"num_input_tokens_seen": 0,
|
264 |
+
"num_train_epochs": 3,
|
265 |
+
"save_steps": 500,
|
266 |
+
"total_flos": 443156731444992.0,
|
267 |
+
"train_batch_size": 8,
|
268 |
+
"trial_name": null,
|
269 |
+
"trial_params": null
|
270 |
+
}
|
checkpoint-843/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4c1cf98887bab0a8af99b69a297aa08c35656257df7a1842414e7c3c6e28fa2
|
3 |
+
size 4984
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "Happy",
|
15 |
+
"1": "Natural",
|
16 |
+
"2": "Sad",
|
17 |
+
"3": "Very Happy",
|
18 |
+
"4": "Very Sad"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"Happy": 0,
|
24 |
+
"Natural": 1,
|
25 |
+
"Sad": 2,
|
26 |
+
"Very Happy": 3,
|
27 |
+
"Very Sad": 4
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-12,
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "bert",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.39.3",
|
39 |
+
"type_vocab_size": 2,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 30522
|
42 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7243385d23010f643a2c85f5225997a2522b60877bf4ea06b0da3df94a4616f2
|
3 |
+
size 437967876
|
runs/Apr15_00-15-00_r-aveo-tt3-hpvnh2hj-124f7-v0zy5/events.out.tfevents.1713140101.r-aveo-tt3-hpvnh2hj-124f7-v0zy5.107.0
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:b4779713f0f0ddf4bcf27c3e77abbf81478a26c211b195f0e2192d28ef3442b5
|
3 |
+
size 29021
|
runs/Apr15_00-15-00_r-aveo-tt3-hpvnh2hj-124f7-v0zy5/events.out.tfevents.1713169784.r-aveo-tt3-hpvnh2hj-124f7-v0zy5.107.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5da1f1a5c17dce4fb417a91a8bd64310afe8554da8c4fca95db2d89f49dcae99
|
3 |
+
size 921
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4c1cf98887bab0a8af99b69a297aa08c35656257df7a1842414e7c3c6e28fa2
|
3 |
+
size 4984
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-wg8v5-kpkgo/autotrain-data",
|
3 |
+
"model": "google-bert/bert-base-uncased",
|
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-wg8v5-kpkgo",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": null,
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"save_strategy": "epoch",
|
25 |
+
"push_to_hub": true,
|
26 |
+
"repo_id": "Aveo/autotrain-wg8v5-kpkgo",
|
27 |
+
"evaluation_strategy": "epoch",
|
28 |
+
"username": "Aveo",
|
29 |
+
"log": "tensorboard"
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|