Commit
•
60f2985
1
Parent(s):
a45c063
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-1082/config.json +38 -0
- checkpoint-1082/model.safetensors +3 -0
- checkpoint-1082/optimizer.pt +3 -0
- checkpoint-1082/rng_state.pth +3 -0
- checkpoint-1082/scheduler.pt +3 -0
- checkpoint-1082/trainer_state.json +340 -0
- checkpoint-1082/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/Apr30_04-58-14_r-akhil-9640-actsa-train-78jy1l28-40c6f-n1jol/events.out.tfevents.1714453096.r-akhil-9640-actsa-train-78jy1l28-40c6f-n1jol.86.0 +2 -2
- runs/Apr30_04-58-14_r-akhil-9640-actsa-train-78jy1l28-40c6f-n1jol/events.out.tfevents.1714471420.r-akhil-9640-actsa-train-78jy1l28-40c6f-n1jol.86.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +244 -0
- training_args.bin +3 -0
- training_params.json +28 -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-byt8e-zygc3/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 1.0650867223739624
|
18 |
+
|
19 |
+
f1_macro: 0.2095479509928179
|
20 |
+
|
21 |
+
f1_micro: 0.4584103512014787
|
22 |
+
|
23 |
+
f1_weighted: 0.2881768494245037
|
24 |
+
|
25 |
+
precision_macro: 0.1528034504004929
|
26 |
+
|
27 |
+
precision_micro: 0.4584103512014787
|
28 |
+
|
29 |
+
precision_weighted: 0.21014005008866307
|
30 |
+
|
31 |
+
recall_macro: 0.3333333333333333
|
32 |
+
|
33 |
+
recall_micro: 0.4584103512014787
|
34 |
+
|
35 |
+
recall_weighted: 0.4584103512014787
|
36 |
+
|
37 |
+
accuracy: 0.4584103512014787
|
checkpoint-1082/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ai4bharat/IndicBERTv2-MLM-only",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"embedding_size": 768,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "-1",
|
15 |
+
"1": "0",
|
16 |
+
"2": "1"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"-1": 0,
|
22 |
+
"0": 1,
|
23 |
+
"1": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.40.1",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 250000
|
38 |
+
}
|
checkpoint-1082/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42d425e792106bb55a3f19ead9cdd8d06d972de42a0249756f8d1cbf72e24f62
|
3 |
+
size 1112198276
|
checkpoint-1082/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b77406c217ca1e30c0fe0bd13a39ad6147d1358f66a12c985bb83ed6ae0c798
|
3 |
+
size 2224511738
|
checkpoint-1082/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4986f3dac3baecec29f5c0462ee70fe166a3b52de3c7fa1e0b481c129f9f95e7
|
3 |
+
size 13990
|
checkpoint-1082/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65f918d733a96e2fd5bf6c66a3cee41062c3dc6c3fac84d62c5e968c1a5b3ea7
|
3 |
+
size 1064
|
checkpoint-1082/trainer_state.json
ADDED
@@ -0,0 +1,340 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0650867223739624,
|
3 |
+
"best_model_checkpoint": "autotrain-byt8e-zygc3/checkpoint-1082",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1082,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02310536044362292,
|
13 |
+
"grad_norm": 3.5127339363098145,
|
14 |
+
"learning_rate": 3.846153846153846e-05,
|
15 |
+
"loss": 1.0872,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04621072088724584,
|
20 |
+
"grad_norm": 6.642369270324707,
|
21 |
+
"learning_rate": 7.692307692307693e-05,
|
22 |
+
"loss": 1.1215,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06931608133086876,
|
27 |
+
"grad_norm": 6.217954158782959,
|
28 |
+
"learning_rate": 0.0001153846153846154,
|
29 |
+
"loss": 1.0733,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09242144177449169,
|
34 |
+
"grad_norm": 2.9232001304626465,
|
35 |
+
"learning_rate": 0.00015384615384615385,
|
36 |
+
"loss": 1.1347,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.11552680221811461,
|
41 |
+
"grad_norm": 3.7540340423583984,
|
42 |
+
"learning_rate": 0.00019230769230769233,
|
43 |
+
"loss": 1.3273,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.13863216266173753,
|
48 |
+
"grad_norm": 4.9391679763793945,
|
49 |
+
"learning_rate": 0.0002307692307692308,
|
50 |
+
"loss": 1.1507,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.16173752310536044,
|
55 |
+
"grad_norm": 1.5326274633407593,
|
56 |
+
"learning_rate": 0.0002692307692307692,
|
57 |
+
"loss": 1.1118,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.18484288354898337,
|
62 |
+
"grad_norm": 1.3186924457550049,
|
63 |
+
"learning_rate": 0.0003076923076923077,
|
64 |
+
"loss": 1.1426,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.20794824399260628,
|
69 |
+
"grad_norm": 3.582869052886963,
|
70 |
+
"learning_rate": 0.00034615384615384613,
|
71 |
+
"loss": 1.175,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.23105360443622922,
|
76 |
+
"grad_norm": 2.4438865184783936,
|
77 |
+
"learning_rate": 0.00038461538461538467,
|
78 |
+
"loss": 1.0483,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2541589648798521,
|
83 |
+
"grad_norm": 6.818902492523193,
|
84 |
+
"learning_rate": 0.0004230769230769231,
|
85 |
+
"loss": 1.0661,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.27726432532347506,
|
90 |
+
"grad_norm": 1.4846845865249634,
|
91 |
+
"learning_rate": 0.0004615384615384616,
|
92 |
+
"loss": 1.1412,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.300369685767098,
|
97 |
+
"grad_norm": 1.0014742612838745,
|
98 |
+
"learning_rate": 0.0005,
|
99 |
+
"loss": 1.0968,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3234750462107209,
|
104 |
+
"grad_norm": 0.8473600745201111,
|
105 |
+
"learning_rate": 0.0004957206436152003,
|
106 |
+
"loss": 1.1779,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.3465804066543438,
|
111 |
+
"grad_norm": 3.419077157974243,
|
112 |
+
"learning_rate": 0.0004914412872304005,
|
113 |
+
"loss": 1.1943,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.36968576709796674,
|
118 |
+
"grad_norm": 0.8151220083236694,
|
119 |
+
"learning_rate": 0.00048716193084560086,
|
120 |
+
"loss": 1.0639,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.3927911275415896,
|
125 |
+
"grad_norm": 1.3580329418182373,
|
126 |
+
"learning_rate": 0.0004828825744608011,
|
127 |
+
"loss": 1.2678,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.41589648798521256,
|
132 |
+
"grad_norm": 0.5541791319847107,
|
133 |
+
"learning_rate": 0.0004786032180760014,
|
134 |
+
"loss": 1.1612,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4390018484288355,
|
139 |
+
"grad_norm": 1.164920449256897,
|
140 |
+
"learning_rate": 0.0004743238616912017,
|
141 |
+
"loss": 1.1855,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.46210720887245843,
|
146 |
+
"grad_norm": 4.518599987030029,
|
147 |
+
"learning_rate": 0.0004700445053064019,
|
148 |
+
"loss": 1.1385,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.4852125693160813,
|
153 |
+
"grad_norm": 0.9030762910842896,
|
154 |
+
"learning_rate": 0.0004657651489216022,
|
155 |
+
"loss": 1.1228,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5083179297597042,
|
160 |
+
"grad_norm": 1.1489505767822266,
|
161 |
+
"learning_rate": 0.00046148579253680244,
|
162 |
+
"loss": 1.145,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5314232902033271,
|
167 |
+
"grad_norm": 0.9008183479309082,
|
168 |
+
"learning_rate": 0.00045720643615200274,
|
169 |
+
"loss": 1.1385,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5545286506469501,
|
174 |
+
"grad_norm": 0.9687894582748413,
|
175 |
+
"learning_rate": 0.00045292707976720304,
|
176 |
+
"loss": 1.1424,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.577634011090573,
|
181 |
+
"grad_norm": 0.43966954946517944,
|
182 |
+
"learning_rate": 0.0004486477233824033,
|
183 |
+
"loss": 1.1123,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.600739371534196,
|
188 |
+
"grad_norm": 0.9648946523666382,
|
189 |
+
"learning_rate": 0.0004443683669976036,
|
190 |
+
"loss": 0.9658,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6238447319778189,
|
195 |
+
"grad_norm": 1.1458590030670166,
|
196 |
+
"learning_rate": 0.00044008901061280383,
|
197 |
+
"loss": 1.1779,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.6469500924214417,
|
202 |
+
"grad_norm": 1.6918909549713135,
|
203 |
+
"learning_rate": 0.00043580965422800413,
|
204 |
+
"loss": 1.0564,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.6700554528650647,
|
209 |
+
"grad_norm": 0.38883867859840393,
|
210 |
+
"learning_rate": 0.00043153029784320443,
|
211 |
+
"loss": 1.1518,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.6931608133086876,
|
216 |
+
"grad_norm": 1.109215497970581,
|
217 |
+
"learning_rate": 0.0004272509414584047,
|
218 |
+
"loss": 1.0493,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7162661737523105,
|
223 |
+
"grad_norm": 4.412217140197754,
|
224 |
+
"learning_rate": 0.000422971585073605,
|
225 |
+
"loss": 1.0994,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.7393715341959335,
|
230 |
+
"grad_norm": 0.6967116594314575,
|
231 |
+
"learning_rate": 0.00041869222868880517,
|
232 |
+
"loss": 1.1258,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.7624768946395564,
|
237 |
+
"grad_norm": 1.0759273767471313,
|
238 |
+
"learning_rate": 0.00041441287230400547,
|
239 |
+
"loss": 1.0622,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.7855822550831792,
|
244 |
+
"grad_norm": 1.6998566389083862,
|
245 |
+
"learning_rate": 0.00041013351591920577,
|
246 |
+
"loss": 1.0942,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.8086876155268022,
|
251 |
+
"grad_norm": 1.0458375215530396,
|
252 |
+
"learning_rate": 0.000405854159534406,
|
253 |
+
"loss": 1.0698,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.8317929759704251,
|
258 |
+
"grad_norm": 1.579179048538208,
|
259 |
+
"learning_rate": 0.0004015748031496063,
|
260 |
+
"loss": 0.9733,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.8548983364140481,
|
265 |
+
"grad_norm": 1.5911906957626343,
|
266 |
+
"learning_rate": 0.00039729544676480656,
|
267 |
+
"loss": 1.1809,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.878003696857671,
|
272 |
+
"grad_norm": 0.30177101492881775,
|
273 |
+
"learning_rate": 0.00039301609038000686,
|
274 |
+
"loss": 1.0625,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.9011090573012939,
|
279 |
+
"grad_norm": 0.9385190606117249,
|
280 |
+
"learning_rate": 0.00038873673399520716,
|
281 |
+
"loss": 1.0929,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.9242144177449169,
|
286 |
+
"grad_norm": 1.7940095663070679,
|
287 |
+
"learning_rate": 0.0003844573776104074,
|
288 |
+
"loss": 1.1022,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.9473197781885397,
|
293 |
+
"grad_norm": 0.8840867280960083,
|
294 |
+
"learning_rate": 0.0003801780212256077,
|
295 |
+
"loss": 1.0802,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.9704251386321626,
|
300 |
+
"grad_norm": 0.9084434509277344,
|
301 |
+
"learning_rate": 0.00037589866484080795,
|
302 |
+
"loss": 1.1098,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.9935304990757856,
|
307 |
+
"grad_norm": 1.4320096969604492,
|
308 |
+
"learning_rate": 0.00037161930845600825,
|
309 |
+
"loss": 1.1118,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.0,
|
314 |
+
"eval_accuracy": 0.4584103512014787,
|
315 |
+
"eval_f1_macro": 0.2095479509928179,
|
316 |
+
"eval_f1_micro": 0.4584103512014787,
|
317 |
+
"eval_f1_weighted": 0.2881768494245037,
|
318 |
+
"eval_loss": 1.0650867223739624,
|
319 |
+
"eval_precision_macro": 0.1528034504004929,
|
320 |
+
"eval_precision_micro": 0.4584103512014787,
|
321 |
+
"eval_precision_weighted": 0.21014005008866307,
|
322 |
+
"eval_recall_macro": 0.3333333333333333,
|
323 |
+
"eval_recall_micro": 0.4584103512014787,
|
324 |
+
"eval_recall_weighted": 0.4584103512014787,
|
325 |
+
"eval_runtime": 190.8807,
|
326 |
+
"eval_samples_per_second": 5.668,
|
327 |
+
"eval_steps_per_second": 0.712,
|
328 |
+
"step": 1082
|
329 |
+
}
|
330 |
+
],
|
331 |
+
"logging_steps": 25,
|
332 |
+
"max_steps": 3246,
|
333 |
+
"num_input_tokens_seen": 0,
|
334 |
+
"num_train_epochs": 3,
|
335 |
+
"save_steps": 500,
|
336 |
+
"total_flos": 284688717981696.0,
|
337 |
+
"train_batch_size": 4,
|
338 |
+
"trial_name": null,
|
339 |
+
"trial_params": null
|
340 |
+
}
|
checkpoint-1082/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74dcd0666af3dd358c53b1fb3a82cd3d6eb357f28b66bb5900bf035abddba678
|
3 |
+
size 5048
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ai4bharat/IndicBERTv2-MLM-only",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"embedding_size": 768,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "-1",
|
15 |
+
"1": "0",
|
16 |
+
"2": "1"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"-1": 0,
|
22 |
+
"0": 1,
|
23 |
+
"1": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.40.1",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 250000
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42d425e792106bb55a3f19ead9cdd8d06d972de42a0249756f8d1cbf72e24f62
|
3 |
+
size 1112198276
|
runs/Apr30_04-58-14_r-akhil-9640-actsa-train-78jy1l28-40c6f-n1jol/events.out.tfevents.1714453096.r-akhil-9640-actsa-train-78jy1l28-40c6f-n1jol.86.0
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 sha256:877c3c1bdf14f9c12e574b18faeccb5095e5fc7d823f704024c462c10a41483f
|
3 |
+
size 34933
|
runs/Apr30_04-58-14_r-akhil-9640-actsa-train-78jy1l28-40c6f-n1jol/events.out.tfevents.1714471420.r-akhil-9640-actsa-train-78jy1l28-40c6f-n1jol.86.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d07f559fb46dc7c16b92fd577349800314aa5ab94d4b8ae5240668c223e600b1
|
3 |
+
size 921
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[UNK]",
|
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": "[PAD]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "<as>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "<bd>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<bn>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "<dg>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"9": {
|
76 |
+
"content": "<en>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"10": {
|
84 |
+
"content": "<gom>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"11": {
|
92 |
+
"content": "<gu>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"12": {
|
100 |
+
"content": "<hi>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"13": {
|
108 |
+
"content": "<kha>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"14": {
|
116 |
+
"content": "<kn>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"15": {
|
124 |
+
"content": "<ks>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"16": {
|
132 |
+
"content": "<mai>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"17": {
|
140 |
+
"content": "<ml>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"18": {
|
148 |
+
"content": "<mni>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"19": {
|
156 |
+
"content": "<mr>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"20": {
|
164 |
+
"content": "<ne>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"21": {
|
172 |
+
"content": "<or>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"22": {
|
180 |
+
"content": "<pa>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"23": {
|
188 |
+
"content": "<sa>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"24": {
|
196 |
+
"content": "<sd>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"25": {
|
204 |
+
"content": "<sat>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"26": {
|
212 |
+
"content": "<ta>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"27": {
|
220 |
+
"content": "<te>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"28": {
|
228 |
+
"content": "<ur>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
}
|
235 |
+
},
|
236 |
+
"clean_up_tokenization_spaces": true,
|
237 |
+
"cls_token": "[CLS]",
|
238 |
+
"mask_token": "[MASK]",
|
239 |
+
"model_max_length": 1000000000000000019884624838656,
|
240 |
+
"pad_token": "[PAD]",
|
241 |
+
"sep_token": "[SEP]",
|
242 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
243 |
+
"unk_token": "[UNK]"
|
244 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74dcd0666af3dd358c53b1fb3a82cd3d6eb357f28b66bb5900bf035abddba678
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-byt8e-zygc3/autotrain-data",
|
3 |
+
"model": "ai4bharat/IndicBERTv2-MLM-only",
|
4 |
+
"lr": 0.0005,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 4,
|
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-byt8e-zygc3",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": null,
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"evaluation_strategy": "epoch",
|
26 |
+
"username": "Akhil-9640",
|
27 |
+
"log": "tensorboard"
|
28 |
+
}
|