Upload folder using huggingface_hub
Browse files- README.md +26 -0
- added_tokens.json +3 -0
- checkpoint-1506/config.json +44 -0
- checkpoint-1506/model.safetensors +3 -0
- checkpoint-1506/optimizer.pt +3 -0
- checkpoint-1506/rng_state.pth +3 -0
- checkpoint-1506/scheduler.pt +3 -0
- checkpoint-1506/trainer_state.json +475 -0
- checkpoint-1506/training_args.bin +3 -0
- config.json +44 -0
- model.safetensors +3 -0
- runs/Jul27_13-05-12_r-assaflehr-autotrain-11-oca54c7t-69274-el26c/events.out.tfevents.1722085513.r-assaflehr-autotrain-11-oca54c7t-69274-el26c.81.0 +2 -2
- runs/Jul27_13-05-12_r-assaflehr-autotrain-11-oca54c7t-69274-el26c/events.out.tfevents.1722086681.r-assaflehr-autotrain-11-oca54c7t-69274-el26c.81.1 +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- training_params.json +30 -0
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: microsoft/deberta-v3-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: 0.32059717178344727
|
17 |
+
|
18 |
+
f1: 0.9162629757785468
|
19 |
+
|
20 |
+
precision: 0.9168975069252078
|
21 |
+
|
22 |
+
recall: 0.9156293222683264
|
23 |
+
|
24 |
+
auc: 0.963556761725483
|
25 |
+
|
26 |
+
accuracy: 0.9163208852005532
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
checkpoint-1506/config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"DebertaV2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "0",
|
13 |
+
"1": "1"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"0": 0,
|
19 |
+
"1": 1
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-07,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"max_relative_positions": -1,
|
24 |
+
"model_type": "deberta-v2",
|
25 |
+
"norm_rel_ebd": "layer_norm",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"pooler_dropout": 0,
|
30 |
+
"pooler_hidden_act": "gelu",
|
31 |
+
"pooler_hidden_size": 768,
|
32 |
+
"pos_att_type": [
|
33 |
+
"p2c",
|
34 |
+
"c2p"
|
35 |
+
],
|
36 |
+
"position_biased_input": false,
|
37 |
+
"position_buckets": 256,
|
38 |
+
"relative_attention": true,
|
39 |
+
"share_att_key": true,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.43.1",
|
42 |
+
"type_vocab_size": 0,
|
43 |
+
"vocab_size": 128100
|
44 |
+
}
|
checkpoint-1506/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:518b11a5117e064fdcc6f8c23aace5c04b12afdfa3d85dce4ef525171e206a67
|
3 |
+
size 737719272
|
checkpoint-1506/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f72f89fe0b8d797d84f07d5061f43b7e663df322d06eb8010c4b0529910ae8d
|
3 |
+
size 1475558394
|
checkpoint-1506/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a96b791bd03096e0c852d4e4885cced6e19cb5ba7c01d3cf9738ab18e3961606
|
3 |
+
size 14244
|
checkpoint-1506/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2ffb5d07bf7ae203d3bfe157543b1d099428c0774dc6f4d9462cb029b7639d0
|
3 |
+
size 1064
|
checkpoint-1506/trainer_state.json
ADDED
@@ -0,0 +1,475 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.32059717178344727,
|
3 |
+
"best_model_checkpoint": "autotrain-z9wst-apic1/checkpoint-1506",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1506,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.016600265604249667,
|
13 |
+
"grad_norm": 0.7011755108833313,
|
14 |
+
"learning_rate": 8.27814569536424e-06,
|
15 |
+
"loss": 0.6938,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.033200531208499334,
|
20 |
+
"grad_norm": 1.692274808883667,
|
21 |
+
"learning_rate": 1.655629139072848e-05,
|
22 |
+
"loss": 0.6645,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.049800796812749,
|
27 |
+
"grad_norm": 2.9643406867980957,
|
28 |
+
"learning_rate": 2.4834437086092715e-05,
|
29 |
+
"loss": 0.4689,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.06640106241699867,
|
34 |
+
"grad_norm": 6.690465927124023,
|
35 |
+
"learning_rate": 3.2450331125827816e-05,
|
36 |
+
"loss": 0.411,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.08300132802124834,
|
41 |
+
"grad_norm": 4.3464460372924805,
|
42 |
+
"learning_rate": 4.0728476821192055e-05,
|
43 |
+
"loss": 0.3856,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.099601593625498,
|
48 |
+
"grad_norm": 4.394780158996582,
|
49 |
+
"learning_rate": 4.900662251655629e-05,
|
50 |
+
"loss": 0.3458,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.11620185922974767,
|
55 |
+
"grad_norm": 4.849474906921387,
|
56 |
+
"learning_rate": 4.9967485104175286e-05,
|
57 |
+
"loss": 0.3469,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.13280212483399734,
|
62 |
+
"grad_norm": 3.016519069671631,
|
63 |
+
"learning_rate": 4.9851715045824994e-05,
|
64 |
+
"loss": 0.3273,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.14940239043824702,
|
69 |
+
"grad_norm": 7.323078632354736,
|
70 |
+
"learning_rate": 4.965247392483274e-05,
|
71 |
+
"loss": 0.326,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.16600265604249667,
|
76 |
+
"grad_norm": 1.702303171157837,
|
77 |
+
"learning_rate": 4.937043094523778e-05,
|
78 |
+
"loss": 0.3507,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.18260292164674635,
|
83 |
+
"grad_norm": 3.314708709716797,
|
84 |
+
"learning_rate": 4.900653342303719e-05,
|
85 |
+
"loss": 0.3253,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.199203187250996,
|
90 |
+
"grad_norm": 3.7664265632629395,
|
91 |
+
"learning_rate": 4.8562003604374334e-05,
|
92 |
+
"loss": 0.3223,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.2158034528552457,
|
97 |
+
"grad_norm": 2.8503146171569824,
|
98 |
+
"learning_rate": 4.8038334560301714e-05,
|
99 |
+
"loss": 0.3276,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.23240371845949534,
|
104 |
+
"grad_norm": 3.164609909057617,
|
105 |
+
"learning_rate": 4.7437285171906644e-05,
|
106 |
+
"loss": 0.2694,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.24900398406374502,
|
111 |
+
"grad_norm": 5.1076531410217285,
|
112 |
+
"learning_rate": 4.676087422264358e-05,
|
113 |
+
"loss": 0.2641,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.2656042496679947,
|
118 |
+
"grad_norm": 3.561342477798462,
|
119 |
+
"learning_rate": 4.60113736177156e-05,
|
120 |
+
"loss": 0.3179,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.2822045152722444,
|
125 |
+
"grad_norm": 5.70325231552124,
|
126 |
+
"learning_rate": 4.519130075327941e-05,
|
127 |
+
"loss": 0.2602,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.29880478087649404,
|
132 |
+
"grad_norm": 3.692572593688965,
|
133 |
+
"learning_rate": 4.43034100611041e-05,
|
134 |
+
"loss": 0.2565,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.3154050464807437,
|
139 |
+
"grad_norm": 3.2501657009124756,
|
140 |
+
"learning_rate": 4.3350683757082966e-05,
|
141 |
+
"loss": 0.2269,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.33200531208499334,
|
146 |
+
"grad_norm": 4.347064971923828,
|
147 |
+
"learning_rate": 4.233632182467218e-05,
|
148 |
+
"loss": 0.2527,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.34860557768924305,
|
153 |
+
"grad_norm": 3.8920302391052246,
|
154 |
+
"learning_rate": 4.126373126689931e-05,
|
155 |
+
"loss": 0.2233,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.3652058432934927,
|
160 |
+
"grad_norm": 2.748621940612793,
|
161 |
+
"learning_rate": 4.013651466304197e-05,
|
162 |
+
"loss": 0.2574,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.38180610889774236,
|
167 |
+
"grad_norm": 1.6398485898971558,
|
168 |
+
"learning_rate": 3.8958458068411756e-05,
|
169 |
+
"loss": 0.2627,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.398406374501992,
|
174 |
+
"grad_norm": 3.143782377243042,
|
175 |
+
"learning_rate": 3.773351829788543e-05,
|
176 |
+
"loss": 0.2377,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.4150066401062417,
|
181 |
+
"grad_norm": 2.3850388526916504,
|
182 |
+
"learning_rate": 3.646580963589486e-05,
|
183 |
+
"loss": 0.2221,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.4316069057104914,
|
188 |
+
"grad_norm": 3.32765531539917,
|
189 |
+
"learning_rate": 3.5159590017513796e-05,
|
190 |
+
"loss": 0.2248,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.448207171314741,
|
195 |
+
"grad_norm": 3.9372353553771973,
|
196 |
+
"learning_rate": 3.381924672705598e-05,
|
197 |
+
"loss": 0.2127,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.4648074369189907,
|
202 |
+
"grad_norm": 1.9122364521026611,
|
203 |
+
"learning_rate": 3.2449281662219556e-05,
|
204 |
+
"loss": 0.2034,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.4814077025232404,
|
209 |
+
"grad_norm": 2.339261054992676,
|
210 |
+
"learning_rate": 3.105429621327208e-05,
|
211 |
+
"loss": 0.2036,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.49800796812749004,
|
216 |
+
"grad_norm": 2.478360652923584,
|
217 |
+
"learning_rate": 2.9638975808063486e-05,
|
218 |
+
"loss": 0.2134,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.5146082337317397,
|
223 |
+
"grad_norm": 3.1056790351867676,
|
224 |
+
"learning_rate": 2.8208074174776444e-05,
|
225 |
+
"loss": 0.2316,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.5312084993359893,
|
230 |
+
"grad_norm": 1.999221920967102,
|
231 |
+
"learning_rate": 2.676639737527213e-05,
|
232 |
+
"loss": 0.2325,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.547808764940239,
|
237 |
+
"grad_norm": 1.5150188207626343,
|
238 |
+
"learning_rate": 2.5318787662659414e-05,
|
239 |
+
"loss": 0.1733,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.5644090305444888,
|
244 |
+
"grad_norm": 5.388316631317139,
|
245 |
+
"learning_rate": 2.3870107217306106e-05,
|
246 |
+
"loss": 0.193,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.5810092961487384,
|
251 |
+
"grad_norm": 2.7311172485351562,
|
252 |
+
"learning_rate": 2.242522181591934e-05,
|
253 |
+
"loss": 0.1616,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.5976095617529881,
|
258 |
+
"grad_norm": 1.276823878288269,
|
259 |
+
"learning_rate": 2.0988984488546643e-05,
|
260 |
+
"loss": 0.1526,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.6142098273572377,
|
265 |
+
"grad_norm": 1.8383485078811646,
|
266 |
+
"learning_rate": 1.956621921838998e-05,
|
267 |
+
"loss": 0.1881,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.6308100929614874,
|
272 |
+
"grad_norm": 4.960041522979736,
|
273 |
+
"learning_rate": 1.8161704739181486e-05,
|
274 |
+
"loss": 0.1749,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.647410358565737,
|
279 |
+
"grad_norm": 1.369192361831665,
|
280 |
+
"learning_rate": 1.6780158484541295e-05,
|
281 |
+
"loss": 0.1222,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.6640106241699867,
|
286 |
+
"grad_norm": 4.590680122375488,
|
287 |
+
"learning_rate": 1.54262207432282e-05,
|
288 |
+
"loss": 0.1664,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.6806108897742363,
|
293 |
+
"grad_norm": 1.1486464738845825,
|
294 |
+
"learning_rate": 1.4104439073501647e-05,
|
295 |
+
"loss": 0.1389,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.6972111553784861,
|
300 |
+
"grad_norm": 1.1831196546554565,
|
301 |
+
"learning_rate": 1.2819253028943757e-05,
|
302 |
+
"loss": 0.1941,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.7138114209827358,
|
307 |
+
"grad_norm": 1.529694676399231,
|
308 |
+
"learning_rate": 1.1574979247043486e-05,
|
309 |
+
"loss": 0.1479,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.7304116865869854,
|
314 |
+
"grad_norm": 5.450222492218018,
|
315 |
+
"learning_rate": 1.0375796950627137e-05,
|
316 |
+
"loss": 0.1561,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.7470119521912351,
|
321 |
+
"grad_norm": 1.9736617803573608,
|
322 |
+
"learning_rate": 9.225733910832388e-06,
|
323 |
+
"loss": 0.1598,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.7636122177954847,
|
328 |
+
"grad_norm": 4.179745197296143,
|
329 |
+
"learning_rate": 8.128652918772865e-06,
|
330 |
+
"loss": 0.1353,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.7802124833997344,
|
335 |
+
"grad_norm": 5.7941083908081055,
|
336 |
+
"learning_rate": 7.088238811331752e-06,
|
337 |
+
"loss": 0.1358,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.796812749003984,
|
342 |
+
"grad_norm": 2.463935136795044,
|
343 |
+
"learning_rate": 6.1079860946618685e-06,
|
344 |
+
"loss": 0.1337,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.8134130146082338,
|
349 |
+
"grad_norm": 1.1269705295562744,
|
350 |
+
"learning_rate": 5.19118720696184e-06,
|
351 |
+
"loss": 0.1538,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.8300132802124834,
|
356 |
+
"grad_norm": 5.329429626464844,
|
357 |
+
"learning_rate": 4.340921459950962e-06,
|
358 |
+
"loss": 0.1323,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.8466135458167331,
|
363 |
+
"grad_norm": 6.623585224151611,
|
364 |
+
"learning_rate": 3.56004469618578e-06,
|
365 |
+
"loss": 0.1455,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.8632138114209827,
|
370 |
+
"grad_norm": 1.3128626346588135,
|
371 |
+
"learning_rate": 2.851179696956993e-06,
|
372 |
+
"loss": 0.1367,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.8798140770252324,
|
377 |
+
"grad_norm": 4.968562126159668,
|
378 |
+
"learning_rate": 2.216707372984292e-06,
|
379 |
+
"loss": 0.0909,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.896414342629482,
|
384 |
+
"grad_norm": 1.0073035955429077,
|
385 |
+
"learning_rate": 1.6587587674975424e-06,
|
386 |
+
"loss": 0.1443,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.9130146082337317,
|
391 |
+
"grad_norm": 4.145277500152588,
|
392 |
+
"learning_rate": 1.1792078985640525e-06,
|
393 |
+
"loss": 0.138,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.9296148738379814,
|
398 |
+
"grad_norm": 1.9500765800476074,
|
399 |
+
"learning_rate": 7.796654647029e-07,
|
400 |
+
"loss": 0.1265,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.9462151394422311,
|
405 |
+
"grad_norm": 1.5362143516540527,
|
406 |
+
"learning_rate": 4.614734349276256e-07,
|
407 |
+
"loss": 0.1555,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.9628154050464808,
|
412 |
+
"grad_norm": 2.4286270141601562,
|
413 |
+
"learning_rate": 2.2570054138813246e-07,
|
414 |
+
"loss": 0.1389,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.9794156706507304,
|
419 |
+
"grad_norm": 2.250825881958008,
|
420 |
+
"learning_rate": 7.313868975087345e-08,
|
421 |
+
"loss": 0.1173,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.9960159362549801,
|
426 |
+
"grad_norm": 0.48711511492729187,
|
427 |
+
"learning_rate": 4.3002993740770546e-09,
|
428 |
+
"loss": 0.1262,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.0,
|
433 |
+
"eval_accuracy": 0.9163208852005532,
|
434 |
+
"eval_auc": 0.963556761725483,
|
435 |
+
"eval_f1": 0.9162629757785468,
|
436 |
+
"eval_loss": 0.32059717178344727,
|
437 |
+
"eval_precision": 0.9168975069252078,
|
438 |
+
"eval_recall": 0.9156293222683264,
|
439 |
+
"eval_runtime": 39.0094,
|
440 |
+
"eval_samples_per_second": 148.272,
|
441 |
+
"eval_steps_per_second": 2.333,
|
442 |
+
"step": 1506
|
443 |
+
}
|
444 |
+
],
|
445 |
+
"logging_steps": 25,
|
446 |
+
"max_steps": 1506,
|
447 |
+
"num_input_tokens_seen": 0,
|
448 |
+
"num_train_epochs": 1,
|
449 |
+
"save_steps": 500,
|
450 |
+
"stateful_callbacks": {
|
451 |
+
"EarlyStoppingCallback": {
|
452 |
+
"args": {
|
453 |
+
"early_stopping_patience": 5,
|
454 |
+
"early_stopping_threshold": 0.01
|
455 |
+
},
|
456 |
+
"attributes": {
|
457 |
+
"early_stopping_patience_counter": 0
|
458 |
+
}
|
459 |
+
},
|
460 |
+
"TrainerControl": {
|
461 |
+
"args": {
|
462 |
+
"should_epoch_stop": false,
|
463 |
+
"should_evaluate": false,
|
464 |
+
"should_log": false,
|
465 |
+
"should_save": true,
|
466 |
+
"should_training_stop": true
|
467 |
+
},
|
468 |
+
"attributes": {}
|
469 |
+
}
|
470 |
+
},
|
471 |
+
"total_flos": 6340037689147392.0,
|
472 |
+
"train_batch_size": 32,
|
473 |
+
"trial_name": null,
|
474 |
+
"trial_params": null
|
475 |
+
}
|
checkpoint-1506/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:420fbbf1db34ea4a83e10fa4f705a919aee64d5989d87bed3809536874237be4
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"DebertaV2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "0",
|
13 |
+
"1": "1"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"0": 0,
|
19 |
+
"1": 1
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-07,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"max_relative_positions": -1,
|
24 |
+
"model_type": "deberta-v2",
|
25 |
+
"norm_rel_ebd": "layer_norm",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"pooler_dropout": 0,
|
30 |
+
"pooler_hidden_act": "gelu",
|
31 |
+
"pooler_hidden_size": 768,
|
32 |
+
"pos_att_type": [
|
33 |
+
"p2c",
|
34 |
+
"c2p"
|
35 |
+
],
|
36 |
+
"position_biased_input": false,
|
37 |
+
"position_buckets": 256,
|
38 |
+
"relative_attention": true,
|
39 |
+
"share_att_key": true,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.43.1",
|
42 |
+
"type_vocab_size": 0,
|
43 |
+
"vocab_size": 128100
|
44 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:518b11a5117e064fdcc6f8c23aace5c04b12afdfa3d85dce4ef525171e206a67
|
3 |
+
size 737719272
|
runs/Jul27_13-05-12_r-assaflehr-autotrain-11-oca54c7t-69274-el26c/events.out.tfevents.1722085513.r-assaflehr-autotrain-11-oca54c7t-69274-el26c.81.0
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 sha256:8583adc23094d215ed96526c0fae333cc25bf79b62571b6d9f0025809caaaa72
|
3 |
+
size 18714
|
runs/Jul27_13-05-12_r-assaflehr-autotrain-11-oca54c7t-69274-el26c/events.out.tfevents.1722086681.r-assaflehr-autotrain-11-oca54c7t-69274-el26c.81.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0b59aa0674dfa107f275869184efa8372c81d67e956513a4e78b09060e8289e
|
3 |
+
size 607
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": {
|
9 |
+
"content": "[UNK]",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
}
|
15 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
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": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128000": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "[CLS]",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"eos_token": "[SEP]",
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"split_by_punct": false,
|
55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
56 |
+
"unk_token": "[UNK]",
|
57 |
+
"vocab_type": "spm"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:420fbbf1db34ea4a83e10fa4f705a919aee64d5989d87bed3809536874237be4
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-z9wst-apic1/autotrain-data",
|
3 |
+
"model": "microsoft/deberta-v3-base",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 1,
|
6 |
+
"max_seq_length": 256,
|
7 |
+
"batch_size": 32,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "cosine",
|
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-z9wst-apic1",
|
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": "assaflehr",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|