Hugging Face's logo

Motahar
/
clickbait-identification-content-transformer-finetuning

TensorBoard
Model card Files
xet
 Metrics Community
MotaharMahtabAnkon commited on
Commit
5e45c68
·
1 Parent(s): 02b20f6

fcsebuetnlp/banglabert-new

Browse files
Files changed (7) hide show
  1. csebuetnlp/banglabert/checkpoint-8000/optimizer.pt +3 -0
  2. csebuetnlp/banglabert/checkpoint-8000/pytorch_model.bin +3 -0
  3. csebuetnlp/banglabert/checkpoint-8000/rng_state.pth +3 -0
  4. csebuetnlp/banglabert/checkpoint-8000/scheduler.pt +3 -0
  5. csebuetnlp/banglabert/runs2/Jan14_13-43-45_4ac0fd88951a/1642167963.155689/events.out.tfevents.1642167963.4ac0fd88951a.2300.17 +3 -0
  6. csebuetnlp/banglabert/runs2/Jan14_13-43-45_4ac0fd88951a/events.out.tfevents.1642167963.4ac0fd88951a.2300.16 +3 -0
  7. csebuetnlp/banglabert/trainer_state.json +181 -0
csebuetnlp/banglabert/checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8792961eca66fa8a7c4737a4729c26d0571a50454572700fee429c4ab7df6e44
3
+ size 880341733
csebuetnlp/banglabert/checkpoint-8000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47bc3afb33671f5faf7de692d66c6ae19549cfb4369a8222f82449471467663
3
+ size 440196977
csebuetnlp/banglabert/checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f666cb80b0a3ba24cd6a58768a539f6f1559d121adb3752b78526a3d4eb34b
3
+ size 14503
csebuetnlp/banglabert/checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45803f109d11da67ac8663f411272883599d138daeffce48a734439256fded2c
3
+ size 623
csebuetnlp/banglabert/runs2/Jan14_13-43-45_4ac0fd88951a/1642167963.155689/events.out.tfevents.1642167963.4ac0fd88951a.2300.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab225fb619e8b9ed30643885a396aa30b2864739c32cfd954878601e4502a8af
3
+ size 4924
csebuetnlp/banglabert/runs2/Jan14_13-43-45_4ac0fd88951a/events.out.tfevents.1642167963.4ac0fd88951a.2300.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350237b7870d4ca868a8f144b665b1bc927a0fc8de8910b288fdb736c7d81f91
3
+ size 5928
csebuetnlp/banglabert/trainer_state.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7209533267130088,
3
+ "best_model_checkpoint": "./clickbait_identification/neuralspace-reverie/indic-transformers-bn-xlmroberta/checkpoint-8000",
4
+ "epoch": 3.635161929940516,
5
+ "global_step": 11000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.33,
12
+ "eval_accuracy": 0.7013372956909361,
13
+ "eval_f1": 0.32094594594594594,
14
+ "eval_loss": 0.5926413536071777,
15
+ "eval_precision": 0.7480314960629921,
16
+ "eval_recall": 0.20430107526881722,
17
+ "eval_runtime": 25.7194,
18
+ "eval_samples_per_second": 52.334,
19
+ "eval_steps_per_second": 13.103,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.66,
24
+ "eval_accuracy": 0.7332838038632986,
25
+ "eval_f1": 0.4665676077265974,
26
+ "eval_loss": 0.514832079410553,
27
+ "eval_precision": 0.7548076923076923,
28
+ "eval_recall": 0.33763440860215055,
29
+ "eval_runtime": 25.719,
30
+ "eval_samples_per_second": 52.335,
31
+ "eval_steps_per_second": 13.103,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.99,
36
+ "eval_accuracy": 0.7540861812778603,
37
+ "eval_f1": 0.6814244465832531,
38
+ "eval_loss": 0.49710002541542053,
39
+ "eval_precision": 0.6167247386759582,
40
+ "eval_recall": 0.7612903225806451,
41
+ "eval_runtime": 25.7279,
42
+ "eval_samples_per_second": 52.317,
43
+ "eval_steps_per_second": 13.099,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "learning_rate": 1.9e-05,
49
+ "loss": 0.58,
50
+ "step": 3026
51
+ },
52
+ {
53
+ "epoch": 1.32,
54
+ "eval_accuracy": 0.7674591381872214,
55
+ "eval_f1": 0.6916256157635469,
56
+ "eval_loss": 0.628989577293396,
57
+ "eval_precision": 0.6381818181818182,
58
+ "eval_recall": 0.7548387096774194,
59
+ "eval_runtime": 25.7155,
60
+ "eval_samples_per_second": 52.342,
61
+ "eval_steps_per_second": 13.105,
62
+ "step": 4000
63
+ },
64
+ {
65
+ "epoch": 1.65,
66
+ "eval_accuracy": 0.7867756315007429,
67
+ "eval_f1": 0.6849615806805708,
68
+ "eval_loss": 0.6614874005317688,
69
+ "eval_precision": 0.6995515695067265,
70
+ "eval_recall": 0.6709677419354839,
71
+ "eval_runtime": 26.0668,
72
+ "eval_samples_per_second": 51.636,
73
+ "eval_steps_per_second": 12.928,
74
+ "step": 5000
75
+ },
76
+ {
77
+ "epoch": 1.98,
78
+ "eval_accuracy": 0.7838038632986627,
79
+ "eval_f1": 0.7063572149344096,
80
+ "eval_loss": 0.6481547951698303,
81
+ "eval_precision": 0.6653992395437263,
82
+ "eval_recall": 0.7526881720430108,
83
+ "eval_runtime": 25.9916,
84
+ "eval_samples_per_second": 51.786,
85
+ "eval_steps_per_second": 12.966,
86
+ "step": 6000
87
+ },
88
+ {
89
+ "epoch": 2.0,
90
+ "learning_rate": 1.8e-05,
91
+ "loss": 0.4892,
92
+ "step": 6052
93
+ },
94
+ {
95
+ "epoch": 2.31,
96
+ "eval_accuracy": 0.7800891530460624,
97
+ "eval_f1": 0.6613272311212814,
98
+ "eval_loss": 0.7997592687606812,
99
+ "eval_precision": 0.706601466992665,
100
+ "eval_recall": 0.621505376344086,
101
+ "eval_runtime": 14.3538,
102
+ "eval_samples_per_second": 93.773,
103
+ "eval_steps_per_second": 23.478,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 2.64,
108
+ "eval_accuracy": 0.7912332838038633,
109
+ "eval_f1": 0.7209533267130088,
110
+ "eval_loss": 0.7411750555038452,
111
+ "eval_precision": 0.6697416974169742,
112
+ "eval_recall": 0.7806451612903226,
113
+ "eval_runtime": 14.126,
114
+ "eval_samples_per_second": 95.285,
115
+ "eval_steps_per_second": 23.857,
116
+ "step": 8000
117
+ },
118
+ {
119
+ "epoch": 2.97,
120
+ "eval_accuracy": 0.7912332838038633,
121
+ "eval_f1": 0.6839145106861643,
122
+ "eval_loss": 0.730811595916748,
123
+ "eval_precision": 0.7169811320754716,
124
+ "eval_recall": 0.6537634408602151,
125
+ "eval_runtime": 14.1172,
126
+ "eval_samples_per_second": 95.345,
127
+ "eval_steps_per_second": 23.872,
128
+ "step": 9000
129
+ },
130
+ {
131
+ "epoch": 3.0,
132
+ "learning_rate": 1.7e-05,
133
+ "loss": 0.5359,
134
+ "step": 9078
135
+ },
136
+ {
137
+ "epoch": 3.3,
138
+ "eval_accuracy": 0.7897473997028231,
139
+ "eval_f1": 0.7049009384775808,
140
+ "eval_loss": 0.8810334801673889,
141
+ "eval_precision": 0.6842105263157895,
142
+ "eval_recall": 0.7268817204301076,
143
+ "eval_runtime": 14.149,
144
+ "eval_samples_per_second": 95.13,
145
+ "eval_steps_per_second": 23.818,
146
+ "step": 10000
147
+ },
148
+ {
149
+ "epoch": 3.64,
150
+ "eval_accuracy": 0.787518573551263,
151
+ "eval_f1": 0.7008368200836819,
152
+ "eval_loss": 0.755975067615509,
153
+ "eval_precision": 0.6822810590631364,
154
+ "eval_recall": 0.7204301075268817,
155
+ "eval_runtime": 14.1239,
156
+ "eval_samples_per_second": 95.3,
157
+ "eval_steps_per_second": 23.86,
158
+ "step": 11000
159
+ },
160
+ {
161
+ "epoch": 3.64,
162
+ "learning_rate": 1.6364838070059484e-05,
163
+ "loss": 0.5023,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 3.64,
168
+ "step": 11000,
169
+ "total_flos": 0.0,
170
+ "train_loss": 0.23749410299821333,
171
+ "train_runtime": 750.0737,
172
+ "train_samples_per_second": 322.688,
173
+ "train_steps_per_second": 80.685
174
+ }
175
+ ],
176
+ "max_steps": 60520,
177
+ "num_train_epochs": 20,
178
+ "total_flos": 0.0,
179
+ "trial_name": null,
180
+ "trial_params": null
181
+ }