jin3213 commited on
Commit
d73ea91
·
verified ·
1 Parent(s): 129bce4

Upload 27 files

Browse files
finetuned_distilbert/checkpoint-296/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased-distilled-squad",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": true,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
+ "vocab_size": 28996
25
+ }
finetuned_distilbert/checkpoint-296/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8a9df62f54bd4b92b3fdb569ebdb2b6e6a3b94ae6cab7e360b1e291049f869
3
+ size 260782152
finetuned_distilbert/checkpoint-296/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc0edbc3aa5afe0dc6ba3a5a6e511fc60a9470d7ddea2976bc663e615d22e88d
3
+ size 521625611
finetuned_distilbert/checkpoint-296/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fea74348d064456dc86781e4e54bd1d504da2f98a52fe2589964204c7b29477
3
+ size 14645
finetuned_distilbert/checkpoint-296/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7959987c50bca324a6a5ff3fb0dd4e95ee53efcf0283c72dfddef23174d9820
3
+ size 1465
finetuned_distilbert/checkpoint-296/trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0008619087748229504,
3
+ "best_model_checkpoint": "/content/drive/My Drive/BonsAI/RAG/finetuned_distilbert/checkpoint-296",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 296,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.033783783783783786,
13
+ "grad_norm": 63.3484992980957,
14
+ "learning_rate": 2.696629213483146e-06,
15
+ "loss": 1.5891,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06756756756756757,
20
+ "grad_norm": 12.823508262634277,
21
+ "learning_rate": 6.067415730337078e-06,
22
+ "loss": 0.9926,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10135135135135136,
27
+ "grad_norm": 10.632203102111816,
28
+ "learning_rate": 9.438202247191012e-06,
29
+ "loss": 0.4432,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.13513513513513514,
34
+ "grad_norm": 1.4367406368255615,
35
+ "learning_rate": 1.2808988764044944e-05,
36
+ "loss": 0.1425,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.16891891891891891,
41
+ "grad_norm": 5.937399387359619,
42
+ "learning_rate": 1.6179775280898875e-05,
43
+ "loss": 0.0221,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.20270270270270271,
48
+ "grad_norm": 0.006844044663012028,
49
+ "learning_rate": 1.955056179775281e-05,
50
+ "loss": 0.0338,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.23648648648648649,
55
+ "grad_norm": 0.0062227933667600155,
56
+ "learning_rate": 2.292134831460674e-05,
57
+ "loss": 0.0188,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.2702702702702703,
62
+ "grad_norm": 0.9754657745361328,
63
+ "learning_rate": 2.595505617977528e-05,
64
+ "loss": 0.0298,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.30405405405405406,
69
+ "grad_norm": 0.004088506102561951,
70
+ "learning_rate": 2.932584269662921e-05,
71
+ "loss": 0.0006,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.33783783783783783,
76
+ "grad_norm": 0.0017175301909446716,
77
+ "learning_rate": 2.9992579868275392e-05,
78
+ "loss": 0.0011,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.3716216216216216,
83
+ "grad_norm": 2.027472734451294,
84
+ "learning_rate": 2.996244816439765e-05,
85
+ "loss": 0.001,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.40540540540540543,
90
+ "grad_norm": 0.12049974501132965,
91
+ "learning_rate": 2.990918767154285e-05,
92
+ "loss": 0.0137,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4391891891891892,
97
+ "grad_norm": 0.0021126759238541126,
98
+ "learning_rate": 2.983288071919922e-05,
99
+ "loss": 0.0016,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.47297297297297297,
104
+ "grad_norm": 0.008341561071574688,
105
+ "learning_rate": 2.9733645261820407e-05,
106
+ "loss": 0.0012,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5067567567567568,
111
+ "grad_norm": 0.001279486226849258,
112
+ "learning_rate": 2.9611634696492718e-05,
113
+ "loss": 0.0235,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5405405405405406,
118
+ "grad_norm": 0.0039567407220602036,
119
+ "learning_rate": 2.946703762581565e-05,
120
+ "loss": 0.0008,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5743243243243243,
125
+ "grad_norm": 0.0008406731067225337,
126
+ "learning_rate": 2.9300077566362e-05,
127
+ "loss": 0.0002,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6081081081081081,
132
+ "grad_norm": 0.0006949682137928903,
133
+ "learning_rate": 2.91110126031684e-05,
134
+ "loss": 0.0001,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6418918918918919,
139
+ "grad_norm": 0.0053464132361114025,
140
+ "learning_rate": 2.8900134990790303e-05,
141
+ "loss": 0.0001,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6756756756756757,
146
+ "grad_norm": 37.02953338623047,
147
+ "learning_rate": 2.8667770701538055e-05,
148
+ "loss": 0.0478,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7094594594594594,
153
+ "grad_norm": 1.9292826652526855,
154
+ "learning_rate": 2.8414278921592484e-05,
155
+ "loss": 0.0009,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.7432432432432432,
160
+ "grad_norm": 0.0011820381041616201,
161
+ "learning_rate": 2.8140051495778807e-05,
162
+ "loss": 0.0009,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.777027027027027,
167
+ "grad_norm": 0.0016253776848316193,
168
+ "learning_rate": 2.7845512321857174e-05,
169
+ "loss": 0.0471,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8108108108108109,
174
+ "grad_norm": 0.0026769598480314016,
175
+ "learning_rate": 2.7531116695266156e-05,
176
+ "loss": 0.0093,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.8445945945945946,
181
+ "grad_norm": 0.01816718466579914,
182
+ "learning_rate": 2.7197350605332033e-05,
183
+ "loss": 0.0019,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8783783783783784,
188
+ "grad_norm": 0.02628684975206852,
189
+ "learning_rate": 2.6844729984031765e-05,
190
+ "loss": 0.0144,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9121621621621622,
195
+ "grad_norm": 0.005144517868757248,
196
+ "learning_rate": 2.6473799908471016e-05,
197
+ "loss": 0.0004,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.9459459459459459,
202
+ "grad_norm": 0.0019285095622763038,
203
+ "learning_rate": 2.6085133758309887e-05,
204
+ "loss": 0.0003,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9797297297297297,
209
+ "grad_norm": 0.0016680621774867177,
210
+ "learning_rate": 2.5679332329438924e-05,
211
+ "loss": 0.0,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.0,
216
+ "eval_loss": 0.0008619087748229504,
217
+ "eval_runtime": 1.2802,
218
+ "eval_samples_per_second": 205.444,
219
+ "eval_steps_per_second": 51.556,
220
+ "step": 296
221
+ }
222
+ ],
223
+ "logging_steps": 10,
224
+ "max_steps": 888,
225
+ "num_input_tokens_seen": 0,
226
+ "num_train_epochs": 3,
227
+ "save_steps": 500,
228
+ "stateful_callbacks": {
229
+ "TrainerControl": {
230
+ "args": {
231
+ "should_epoch_stop": false,
232
+ "should_evaluate": false,
233
+ "should_log": false,
234
+ "should_save": true,
235
+ "should_training_stop": false
236
+ },
237
+ "attributes": {}
238
+ }
239
+ },
240
+ "total_flos": 231745936181760.0,
241
+ "train_batch_size": 4,
242
+ "trial_name": null,
243
+ "trial_params": null
244
+ }
finetuned_distilbert/checkpoint-296/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9988663bd319a438514dff5ffaf0334f9bcb456c0dcfeff35874f6030035c433
3
+ size 5649
finetuned_distilbert/checkpoint-592/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased-distilled-squad",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": true,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
+ "vocab_size": 28996
25
+ }
finetuned_distilbert/checkpoint-592/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a37041947570ce75dbdd0622e4feba2c2f716b3dd31c5acf8c77c6b42a561c
3
+ size 260782152
finetuned_distilbert/checkpoint-592/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f3b6037e0614df73850681b863603d587ca9ccc1689b28187c0e00e1656fc8
3
+ size 14645
finetuned_distilbert/checkpoint-592/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c35ec423c0634d869dd8ec1b9387f3973c45562d7d308287e7e995066436e53
3
+ size 1465
finetuned_distilbert/checkpoint-592/trainer_state.json ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.672690470717498e-06,
3
+ "best_model_checkpoint": "/content/drive/My Drive/BonsAI/RAG/finetuned_distilbert/checkpoint-592",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 592,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.033783783783783786,
13
+ "grad_norm": 63.3484992980957,
14
+ "learning_rate": 2.696629213483146e-06,
15
+ "loss": 1.5891,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06756756756756757,
20
+ "grad_norm": 12.823508262634277,
21
+ "learning_rate": 6.067415730337078e-06,
22
+ "loss": 0.9926,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10135135135135136,
27
+ "grad_norm": 10.632203102111816,
28
+ "learning_rate": 9.438202247191012e-06,
29
+ "loss": 0.4432,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.13513513513513514,
34
+ "grad_norm": 1.4367406368255615,
35
+ "learning_rate": 1.2808988764044944e-05,
36
+ "loss": 0.1425,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.16891891891891891,
41
+ "grad_norm": 5.937399387359619,
42
+ "learning_rate": 1.6179775280898875e-05,
43
+ "loss": 0.0221,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.20270270270270271,
48
+ "grad_norm": 0.006844044663012028,
49
+ "learning_rate": 1.955056179775281e-05,
50
+ "loss": 0.0338,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.23648648648648649,
55
+ "grad_norm": 0.0062227933667600155,
56
+ "learning_rate": 2.292134831460674e-05,
57
+ "loss": 0.0188,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.2702702702702703,
62
+ "grad_norm": 0.9754657745361328,
63
+ "learning_rate": 2.595505617977528e-05,
64
+ "loss": 0.0298,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.30405405405405406,
69
+ "grad_norm": 0.004088506102561951,
70
+ "learning_rate": 2.932584269662921e-05,
71
+ "loss": 0.0006,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.33783783783783783,
76
+ "grad_norm": 0.0017175301909446716,
77
+ "learning_rate": 2.9992579868275392e-05,
78
+ "loss": 0.0011,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.3716216216216216,
83
+ "grad_norm": 2.027472734451294,
84
+ "learning_rate": 2.996244816439765e-05,
85
+ "loss": 0.001,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.40540540540540543,
90
+ "grad_norm": 0.12049974501132965,
91
+ "learning_rate": 2.990918767154285e-05,
92
+ "loss": 0.0137,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4391891891891892,
97
+ "grad_norm": 0.0021126759238541126,
98
+ "learning_rate": 2.983288071919922e-05,
99
+ "loss": 0.0016,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.47297297297297297,
104
+ "grad_norm": 0.008341561071574688,
105
+ "learning_rate": 2.9733645261820407e-05,
106
+ "loss": 0.0012,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5067567567567568,
111
+ "grad_norm": 0.001279486226849258,
112
+ "learning_rate": 2.9611634696492718e-05,
113
+ "loss": 0.0235,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5405405405405406,
118
+ "grad_norm": 0.0039567407220602036,
119
+ "learning_rate": 2.946703762581565e-05,
120
+ "loss": 0.0008,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5743243243243243,
125
+ "grad_norm": 0.0008406731067225337,
126
+ "learning_rate": 2.9300077566362e-05,
127
+ "loss": 0.0002,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6081081081081081,
132
+ "grad_norm": 0.0006949682137928903,
133
+ "learning_rate": 2.91110126031684e-05,
134
+ "loss": 0.0001,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6418918918918919,
139
+ "grad_norm": 0.0053464132361114025,
140
+ "learning_rate": 2.8900134990790303e-05,
141
+ "loss": 0.0001,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6756756756756757,
146
+ "grad_norm": 37.02953338623047,
147
+ "learning_rate": 2.8667770701538055e-05,
148
+ "loss": 0.0478,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7094594594594594,
153
+ "grad_norm": 1.9292826652526855,
154
+ "learning_rate": 2.8414278921592484e-05,
155
+ "loss": 0.0009,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.7432432432432432,
160
+ "grad_norm": 0.0011820381041616201,
161
+ "learning_rate": 2.8140051495778807e-05,
162
+ "loss": 0.0009,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.777027027027027,
167
+ "grad_norm": 0.0016253776848316193,
168
+ "learning_rate": 2.7845512321857174e-05,
169
+ "loss": 0.0471,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8108108108108109,
174
+ "grad_norm": 0.0026769598480314016,
175
+ "learning_rate": 2.7531116695266156e-05,
176
+ "loss": 0.0093,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.8445945945945946,
181
+ "grad_norm": 0.01816718466579914,
182
+ "learning_rate": 2.7197350605332033e-05,
183
+ "loss": 0.0019,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8783783783783784,
188
+ "grad_norm": 0.02628684975206852,
189
+ "learning_rate": 2.6844729984031765e-05,
190
+ "loss": 0.0144,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9121621621621622,
195
+ "grad_norm": 0.005144517868757248,
196
+ "learning_rate": 2.6473799908471016e-05,
197
+ "loss": 0.0004,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.9459459459459459,
202
+ "grad_norm": 0.0019285095622763038,
203
+ "learning_rate": 2.6085133758309887e-05,
204
+ "loss": 0.0003,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9797297297297297,
209
+ "grad_norm": 0.0016680621774867177,
210
+ "learning_rate": 2.5679332329438924e-05,
211
+ "loss": 0.0,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.0,
216
+ "eval_loss": 0.0008619087748229504,
217
+ "eval_runtime": 1.2802,
218
+ "eval_samples_per_second": 205.444,
219
+ "eval_steps_per_second": 51.556,
220
+ "step": 296
221
+ },
222
+ {
223
+ "epoch": 1.0135135135135136,
224
+ "grad_norm": 0.0004233259242027998,
225
+ "learning_rate": 2.525702290527538e-05,
226
+ "loss": 0.0001,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.0472972972972974,
231
+ "grad_norm": 0.0012364143040031195,
232
+ "learning_rate": 2.4818858287115342e-05,
233
+ "loss": 0.0,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.0810810810810811,
238
+ "grad_norm": 0.0005589796346612275,
239
+ "learning_rate": 2.4365515785040646e-05,
240
+ "loss": 0.0007,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.114864864864865,
245
+ "grad_norm": 0.002292066579684615,
246
+ "learning_rate": 2.3897696170940328e-05,
247
+ "loss": 0.0001,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.1486486486486487,
252
+ "grad_norm": 0.00015610487025696784,
253
+ "learning_rate": 2.3416122595265107e-05,
254
+ "loss": 0.0001,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.1824324324324325,
259
+ "grad_norm": 0.0001659117260714993,
260
+ "learning_rate": 2.29215394691893e-05,
261
+ "loss": 0.0,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.2162162162162162,
266
+ "grad_norm": 0.0006985558429732919,
267
+ "learning_rate": 2.2414711313908155e-05,
268
+ "loss": 0.0001,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.25,
273
+ "grad_norm": 0.00019110628636553884,
274
+ "learning_rate": 2.1896421578849363e-05,
275
+ "loss": 0.0,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.2837837837837838,
280
+ "grad_norm": 0.00018775821081362665,
281
+ "learning_rate": 2.1367471430625464e-05,
282
+ "loss": 0.0,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.3175675675675675,
287
+ "grad_norm": 0.011069620959460735,
288
+ "learning_rate": 2.0828678514599244e-05,
289
+ "loss": 0.0029,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.3513513513513513,
294
+ "grad_norm": 0.0014019826194271445,
295
+ "learning_rate": 2.0280875690976484e-05,
296
+ "loss": 0.0,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.385135135135135,
301
+ "grad_norm": 0.0038798104505985975,
302
+ "learning_rate": 1.9724909747379727e-05,
303
+ "loss": 0.0,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.4189189189189189,
308
+ "grad_norm": 0.0006560618057847023,
309
+ "learning_rate": 1.9161640089893237e-05,
310
+ "loss": 0.0092,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.4527027027027026,
315
+ "grad_norm": 0.001959842164069414,
316
+ "learning_rate": 1.859193741460243e-05,
317
+ "loss": 0.0,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.4864864864864864,
322
+ "grad_norm": 0.0003938580339308828,
323
+ "learning_rate": 1.8016682361681422e-05,
324
+ "loss": 0.0,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.5202702702702702,
329
+ "grad_norm": 0.014895599335432053,
330
+ "learning_rate": 1.7436764154109012e-05,
331
+ "loss": 0.0,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.554054054054054,
336
+ "grad_norm": 0.020251600071787834,
337
+ "learning_rate": 1.6853079223117554e-05,
338
+ "loss": 0.0,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.5878378378378377,
343
+ "grad_norm": 0.00020745389338117093,
344
+ "learning_rate": 1.6266529822499306e-05,
345
+ "loss": 0.0001,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.6216216216216215,
350
+ "grad_norm": 0.0014518573880195618,
351
+ "learning_rate": 1.5678022633912405e-05,
352
+ "loss": 0.0,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.6554054054054053,
357
+ "grad_norm": 0.0029633333906531334,
358
+ "learning_rate": 1.508846736534227e-05,
359
+ "loss": 0.0,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.689189189189189,
364
+ "grad_norm": 0.005655954591929913,
365
+ "learning_rate": 1.4498775344884886e-05,
366
+ "loss": 0.0,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.722972972972973,
371
+ "grad_norm": 0.014498586766421795,
372
+ "learning_rate": 1.3909858112025813e-05,
373
+ "loss": 0.0,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.7567567567567568,
378
+ "grad_norm": 0.00017455824126955122,
379
+ "learning_rate": 1.3322626008592419e-05,
380
+ "loss": 0.0,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.7905405405405406,
385
+ "grad_norm": 0.0002139418647857383,
386
+ "learning_rate": 1.2737986771557401e-05,
387
+ "loss": 0.0,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.8243243243243243,
392
+ "grad_norm": 0.0010211545741185546,
393
+ "learning_rate": 1.2156844129868893e-05,
394
+ "loss": 0.007,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.8581081081081081,
399
+ "grad_norm": 0.00027997707366012037,
400
+ "learning_rate": 1.1580096407476113e-05,
401
+ "loss": 0.0,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.8918918918918919,
406
+ "grad_norm": 0.000816286716144532,
407
+ "learning_rate": 1.1008635134710045e-05,
408
+ "loss": 0.0,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.9256756756756757,
413
+ "grad_norm": 0.00012246037658769637,
414
+ "learning_rate": 1.0443343670165568e-05,
415
+ "loss": 0.0,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.9594594594594594,
420
+ "grad_norm": 0.0003848487394861877,
421
+ "learning_rate": 9.885095835215368e-06,
422
+ "loss": 0.0,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.9932432432432432,
427
+ "grad_norm": 0.002730418462306261,
428
+ "learning_rate": 9.334754563266447e-06,
429
+ "loss": 0.0,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 2.0,
434
+ "eval_loss": 2.672690470717498e-06,
435
+ "eval_runtime": 1.3117,
436
+ "eval_samples_per_second": 200.508,
437
+ "eval_steps_per_second": 50.318,
438
+ "step": 592
439
+ }
440
+ ],
441
+ "logging_steps": 10,
442
+ "max_steps": 888,
443
+ "num_input_tokens_seen": 0,
444
+ "num_train_epochs": 3,
445
+ "save_steps": 500,
446
+ "stateful_callbacks": {
447
+ "TrainerControl": {
448
+ "args": {
449
+ "should_epoch_stop": false,
450
+ "should_evaluate": false,
451
+ "should_log": false,
452
+ "should_save": true,
453
+ "should_training_stop": false
454
+ },
455
+ "attributes": {}
456
+ }
457
+ },
458
+ "total_flos": 463491872363520.0,
459
+ "train_batch_size": 4,
460
+ "trial_name": null,
461
+ "trial_params": null
462
+ }
finetuned_distilbert/checkpoint-592/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9988663bd319a438514dff5ffaf0334f9bcb456c0dcfeff35874f6030035c433
3
+ size 5649
finetuned_distilbert/checkpoint-888/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased-distilled-squad",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": true,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
+ "vocab_size": 28996
25
+ }
finetuned_distilbert/checkpoint-888/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1815c6277178bd2bd1b6672d90d44328ba0166680879ad203e18287018b641e
3
+ size 260782152
finetuned_distilbert/checkpoint-888/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eefcfd7bd840bf480153e604c33439bfa2e5e4f678f4a8c419a50f2c140840d
3
+ size 521625611
finetuned_distilbert/checkpoint-888/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f56d9ac2106efbb5eacd3b2cd2688d6b1b7e3129fdb61e2e170417d303ce7ad
3
+ size 14645
finetuned_distilbert/checkpoint-888/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48877d6f8b876923600fd7b4ed236faffe4ced54e13b5bc55a27052ebdd6a2e9
3
+ size 1465
finetuned_distilbert/checkpoint-888/trainer_state.json ADDED
@@ -0,0 +1,673 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.4147814201569417e-06,
3
+ "best_model_checkpoint": "/content/drive/My Drive/BonsAI/RAG/finetuned_distilbert/checkpoint-888",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 888,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.033783783783783786,
13
+ "grad_norm": 63.3484992980957,
14
+ "learning_rate": 2.696629213483146e-06,
15
+ "loss": 1.5891,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06756756756756757,
20
+ "grad_norm": 12.823508262634277,
21
+ "learning_rate": 6.067415730337078e-06,
22
+ "loss": 0.9926,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10135135135135136,
27
+ "grad_norm": 10.632203102111816,
28
+ "learning_rate": 9.438202247191012e-06,
29
+ "loss": 0.4432,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.13513513513513514,
34
+ "grad_norm": 1.4367406368255615,
35
+ "learning_rate": 1.2808988764044944e-05,
36
+ "loss": 0.1425,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.16891891891891891,
41
+ "grad_norm": 5.937399387359619,
42
+ "learning_rate": 1.6179775280898875e-05,
43
+ "loss": 0.0221,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.20270270270270271,
48
+ "grad_norm": 0.006844044663012028,
49
+ "learning_rate": 1.955056179775281e-05,
50
+ "loss": 0.0338,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.23648648648648649,
55
+ "grad_norm": 0.0062227933667600155,
56
+ "learning_rate": 2.292134831460674e-05,
57
+ "loss": 0.0188,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.2702702702702703,
62
+ "grad_norm": 0.9754657745361328,
63
+ "learning_rate": 2.595505617977528e-05,
64
+ "loss": 0.0298,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.30405405405405406,
69
+ "grad_norm": 0.004088506102561951,
70
+ "learning_rate": 2.932584269662921e-05,
71
+ "loss": 0.0006,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.33783783783783783,
76
+ "grad_norm": 0.0017175301909446716,
77
+ "learning_rate": 2.9992579868275392e-05,
78
+ "loss": 0.0011,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.3716216216216216,
83
+ "grad_norm": 2.027472734451294,
84
+ "learning_rate": 2.996244816439765e-05,
85
+ "loss": 0.001,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.40540540540540543,
90
+ "grad_norm": 0.12049974501132965,
91
+ "learning_rate": 2.990918767154285e-05,
92
+ "loss": 0.0137,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4391891891891892,
97
+ "grad_norm": 0.0021126759238541126,
98
+ "learning_rate": 2.983288071919922e-05,
99
+ "loss": 0.0016,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.47297297297297297,
104
+ "grad_norm": 0.008341561071574688,
105
+ "learning_rate": 2.9733645261820407e-05,
106
+ "loss": 0.0012,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5067567567567568,
111
+ "grad_norm": 0.001279486226849258,
112
+ "learning_rate": 2.9611634696492718e-05,
113
+ "loss": 0.0235,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5405405405405406,
118
+ "grad_norm": 0.0039567407220602036,
119
+ "learning_rate": 2.946703762581565e-05,
120
+ "loss": 0.0008,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5743243243243243,
125
+ "grad_norm": 0.0008406731067225337,
126
+ "learning_rate": 2.9300077566362e-05,
127
+ "loss": 0.0002,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6081081081081081,
132
+ "grad_norm": 0.0006949682137928903,
133
+ "learning_rate": 2.91110126031684e-05,
134
+ "loss": 0.0001,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6418918918918919,
139
+ "grad_norm": 0.0053464132361114025,
140
+ "learning_rate": 2.8900134990790303e-05,
141
+ "loss": 0.0001,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6756756756756757,
146
+ "grad_norm": 37.02953338623047,
147
+ "learning_rate": 2.8667770701538055e-05,
148
+ "loss": 0.0478,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7094594594594594,
153
+ "grad_norm": 1.9292826652526855,
154
+ "learning_rate": 2.8414278921592484e-05,
155
+ "loss": 0.0009,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.7432432432432432,
160
+ "grad_norm": 0.0011820381041616201,
161
+ "learning_rate": 2.8140051495778807e-05,
162
+ "loss": 0.0009,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.777027027027027,
167
+ "grad_norm": 0.0016253776848316193,
168
+ "learning_rate": 2.7845512321857174e-05,
169
+ "loss": 0.0471,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8108108108108109,
174
+ "grad_norm": 0.0026769598480314016,
175
+ "learning_rate": 2.7531116695266156e-05,
176
+ "loss": 0.0093,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.8445945945945946,
181
+ "grad_norm": 0.01816718466579914,
182
+ "learning_rate": 2.7197350605332033e-05,
183
+ "loss": 0.0019,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8783783783783784,
188
+ "grad_norm": 0.02628684975206852,
189
+ "learning_rate": 2.6844729984031765e-05,
190
+ "loss": 0.0144,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9121621621621622,
195
+ "grad_norm": 0.005144517868757248,
196
+ "learning_rate": 2.6473799908471016e-05,
197
+ "loss": 0.0004,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.9459459459459459,
202
+ "grad_norm": 0.0019285095622763038,
203
+ "learning_rate": 2.6085133758309887e-05,
204
+ "loss": 0.0003,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9797297297297297,
209
+ "grad_norm": 0.0016680621774867177,
210
+ "learning_rate": 2.5679332329438924e-05,
211
+ "loss": 0.0,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.0,
216
+ "eval_loss": 0.0008619087748229504,
217
+ "eval_runtime": 1.2802,
218
+ "eval_samples_per_second": 205.444,
219
+ "eval_steps_per_second": 51.556,
220
+ "step": 296
221
+ },
222
+ {
223
+ "epoch": 1.0135135135135136,
224
+ "grad_norm": 0.0004233259242027998,
225
+ "learning_rate": 2.525702290527538e-05,
226
+ "loss": 0.0001,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.0472972972972974,
231
+ "grad_norm": 0.0012364143040031195,
232
+ "learning_rate": 2.4818858287115342e-05,
233
+ "loss": 0.0,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.0810810810810811,
238
+ "grad_norm": 0.0005589796346612275,
239
+ "learning_rate": 2.4365515785040646e-05,
240
+ "loss": 0.0007,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.114864864864865,
245
+ "grad_norm": 0.002292066579684615,
246
+ "learning_rate": 2.3897696170940328e-05,
247
+ "loss": 0.0001,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.1486486486486487,
252
+ "grad_norm": 0.00015610487025696784,
253
+ "learning_rate": 2.3416122595265107e-05,
254
+ "loss": 0.0001,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.1824324324324325,
259
+ "grad_norm": 0.0001659117260714993,
260
+ "learning_rate": 2.29215394691893e-05,
261
+ "loss": 0.0,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.2162162162162162,
266
+ "grad_norm": 0.0006985558429732919,
267
+ "learning_rate": 2.2414711313908155e-05,
268
+ "loss": 0.0001,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.25,
273
+ "grad_norm": 0.00019110628636553884,
274
+ "learning_rate": 2.1896421578849363e-05,
275
+ "loss": 0.0,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.2837837837837838,
280
+ "grad_norm": 0.00018775821081362665,
281
+ "learning_rate": 2.1367471430625464e-05,
282
+ "loss": 0.0,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.3175675675675675,
287
+ "grad_norm": 0.011069620959460735,
288
+ "learning_rate": 2.0828678514599244e-05,
289
+ "loss": 0.0029,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.3513513513513513,
294
+ "grad_norm": 0.0014019826194271445,
295
+ "learning_rate": 2.0280875690976484e-05,
296
+ "loss": 0.0,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.385135135135135,
301
+ "grad_norm": 0.0038798104505985975,
302
+ "learning_rate": 1.9724909747379727e-05,
303
+ "loss": 0.0,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.4189189189189189,
308
+ "grad_norm": 0.0006560618057847023,
309
+ "learning_rate": 1.9161640089893237e-05,
310
+ "loss": 0.0092,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.4527027027027026,
315
+ "grad_norm": 0.001959842164069414,
316
+ "learning_rate": 1.859193741460243e-05,
317
+ "loss": 0.0,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.4864864864864864,
322
+ "grad_norm": 0.0003938580339308828,
323
+ "learning_rate": 1.8016682361681422e-05,
324
+ "loss": 0.0,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.5202702702702702,
329
+ "grad_norm": 0.014895599335432053,
330
+ "learning_rate": 1.7436764154109012e-05,
331
+ "loss": 0.0,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.554054054054054,
336
+ "grad_norm": 0.020251600071787834,
337
+ "learning_rate": 1.6853079223117554e-05,
338
+ "loss": 0.0,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.5878378378378377,
343
+ "grad_norm": 0.00020745389338117093,
344
+ "learning_rate": 1.6266529822499306e-05,
345
+ "loss": 0.0001,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.6216216216216215,
350
+ "grad_norm": 0.0014518573880195618,
351
+ "learning_rate": 1.5678022633912405e-05,
352
+ "loss": 0.0,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.6554054054054053,
357
+ "grad_norm": 0.0029633333906531334,
358
+ "learning_rate": 1.508846736534227e-05,
359
+ "loss": 0.0,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.689189189189189,
364
+ "grad_norm": 0.005655954591929913,
365
+ "learning_rate": 1.4498775344884886e-05,
366
+ "loss": 0.0,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.722972972972973,
371
+ "grad_norm": 0.014498586766421795,
372
+ "learning_rate": 1.3909858112025813e-05,
373
+ "loss": 0.0,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.7567567567567568,
378
+ "grad_norm": 0.00017455824126955122,
379
+ "learning_rate": 1.3322626008592419e-05,
380
+ "loss": 0.0,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.7905405405405406,
385
+ "grad_norm": 0.0002139418647857383,
386
+ "learning_rate": 1.2737986771557401e-05,
387
+ "loss": 0.0,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.8243243243243243,
392
+ "grad_norm": 0.0010211545741185546,
393
+ "learning_rate": 1.2156844129868893e-05,
394
+ "loss": 0.007,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.8581081081081081,
399
+ "grad_norm": 0.00027997707366012037,
400
+ "learning_rate": 1.1580096407476113e-05,
401
+ "loss": 0.0,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.8918918918918919,
406
+ "grad_norm": 0.000816286716144532,
407
+ "learning_rate": 1.1008635134710045e-05,
408
+ "loss": 0.0,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.9256756756756757,
413
+ "grad_norm": 0.00012246037658769637,
414
+ "learning_rate": 1.0443343670165568e-05,
415
+ "loss": 0.0,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.9594594594594594,
420
+ "grad_norm": 0.0003848487394861877,
421
+ "learning_rate": 9.885095835215368e-06,
422
+ "loss": 0.0,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.9932432432432432,
427
+ "grad_norm": 0.002730418462306261,
428
+ "learning_rate": 9.334754563266447e-06,
429
+ "loss": 0.0,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 2.0,
434
+ "eval_loss": 2.672690470717498e-06,
435
+ "eval_runtime": 1.3117,
436
+ "eval_samples_per_second": 200.508,
437
+ "eval_steps_per_second": 50.318,
438
+ "step": 592
439
+ },
440
+ {
441
+ "epoch": 2.027027027027027,
442
+ "grad_norm": 0.0005972671206109226,
443
+ "learning_rate": 8.793170565847057e-06,
444
+ "loss": 0.0,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.060810810810811,
449
+ "grad_norm": 0.003524207742884755,
450
+ "learning_rate": 8.26118101758611e-06,
451
+ "loss": 0.0008,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.0945945945945947,
456
+ "grad_norm": 0.0023349469993263483,
457
+ "learning_rate": 7.739608262117777e-06,
458
+ "loss": 0.0,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.1283783783783785,
463
+ "grad_norm": 0.00018075505795422941,
464
+ "learning_rate": 7.229258540911695e-06,
465
+ "loss": 0.0,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.1621621621621623,
470
+ "grad_norm": 0.0010670729679986835,
471
+ "learning_rate": 6.730920746993713e-06,
472
+ "loss": 0.0,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.195945945945946,
477
+ "grad_norm": 0.0004548372235149145,
478
+ "learning_rate": 6.2453652054836095e-06,
479
+ "loss": 0.0,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.22972972972973,
484
+ "grad_norm": 0.0005834044422954321,
485
+ "learning_rate": 5.773342482835027e-06,
486
+ "loss": 0.0,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.2635135135135136,
491
+ "grad_norm": 0.0003634082095231861,
492
+ "learning_rate": 5.315582226617964e-06,
493
+ "loss": 0.0,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.2972972972972974,
498
+ "grad_norm": 0.0003151243436150253,
499
+ "learning_rate": 4.872792037637571e-06,
500
+ "loss": 0.0,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.331081081081081,
505
+ "grad_norm": 0.00016155642515514046,
506
+ "learning_rate": 4.445656376132542e-06,
507
+ "loss": 0.0,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.364864864864865,
512
+ "grad_norm": 0.0002693350543268025,
513
+ "learning_rate": 4.034835503743947e-06,
514
+ "loss": 0.0,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.3986486486486487,
519
+ "grad_norm": 0.00017396688053850085,
520
+ "learning_rate": 3.6409644628900156e-06,
521
+ "loss": 0.0,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.4324324324324325,
526
+ "grad_norm": 0.00020753787248395383,
527
+ "learning_rate": 3.264652095124477e-06,
528
+ "loss": 0.0,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.4662162162162162,
533
+ "grad_norm": 0.004645159002393484,
534
+ "learning_rate": 2.9064800999959553e-06,
535
+ "loss": 0.0,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.5,
540
+ "grad_norm": 0.00012094193516531959,
541
+ "learning_rate": 2.567002135863145e-06,
542
+ "loss": 0.0,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.5337837837837838,
547
+ "grad_norm": 0.0003555043658707291,
548
+ "learning_rate": 2.2467429640557903e-06,
549
+ "loss": 0.0,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.5675675675675675,
554
+ "grad_norm": 0.0024685899261385202,
555
+ "learning_rate": 1.9461976377043095e-06,
556
+ "loss": 0.0,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.6013513513513513,
561
+ "grad_norm": 0.0003505544736981392,
562
+ "learning_rate": 1.6658307364921116e-06,
563
+ "loss": 0.0,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.635135135135135,
568
+ "grad_norm": 0.0009317690273746848,
569
+ "learning_rate": 1.4060756485133851e-06,
570
+ "loss": 0.0,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.668918918918919,
575
+ "grad_norm": 0.0001754916738718748,
576
+ "learning_rate": 1.1673339003465067e-06,
577
+ "loss": 0.0,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.7027027027027026,
582
+ "grad_norm": 0.0002394665643805638,
583
+ "learning_rate": 9.499745363786405e-07,
584
+ "loss": 0.0,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.7364864864864864,
589
+ "grad_norm": 0.00020074588246643543,
590
+ "learning_rate": 7.543335483409642e-07,
591
+ "loss": 0.0002,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.77027027027027,
596
+ "grad_norm": 0.008309523575007915,
597
+ "learning_rate": 5.807133559363159e-07,
598
+ "loss": 0.0,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.804054054054054,
603
+ "grad_norm": 0.0003275635826867074,
604
+ "learning_rate": 4.2938233936211824e-07,
605
+ "loss": 0.0,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.8378378378378377,
610
+ "grad_norm": 0.0005050458130426705,
611
+ "learning_rate": 3.005744244511988e-07,
612
+ "loss": 0.0,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.8716216216216215,
617
+ "grad_norm": 0.0005031975451856852,
618
+ "learning_rate": 1.9448872107179717e-07,
619
+ "loss": 0.0,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.9054054054054053,
624
+ "grad_norm": 0.04222193360328674,
625
+ "learning_rate": 1.1128921534570347e-07,
626
+ "loss": 0.0,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.939189189189189,
631
+ "grad_norm": 0.002297344384714961,
632
+ "learning_rate": 5.11045161602991e-08,
633
+ "loss": 0.0,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.972972972972973,
638
+ "grad_norm": 0.00021804046991746873,
639
+ "learning_rate": 1.402765636634551e-08,
640
+ "loss": 0.0,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 3.0,
645
+ "eval_loss": 2.4147814201569417e-06,
646
+ "eval_runtime": 1.3958,
647
+ "eval_samples_per_second": 188.419,
648
+ "eval_steps_per_second": 47.284,
649
+ "step": 888
650
+ }
651
+ ],
652
+ "logging_steps": 10,
653
+ "max_steps": 888,
654
+ "num_input_tokens_seen": 0,
655
+ "num_train_epochs": 3,
656
+ "save_steps": 500,
657
+ "stateful_callbacks": {
658
+ "TrainerControl": {
659
+ "args": {
660
+ "should_epoch_stop": false,
661
+ "should_evaluate": false,
662
+ "should_log": false,
663
+ "should_save": true,
664
+ "should_training_stop": true
665
+ },
666
+ "attributes": {}
667
+ }
668
+ },
669
+ "total_flos": 695237808545280.0,
670
+ "train_batch_size": 4,
671
+ "trial_name": null,
672
+ "trial_params": null
673
+ }
finetuned_distilbert/checkpoint-888/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9988663bd319a438514dff5ffaf0334f9bcb456c0dcfeff35874f6030035c433
3
+ size 5649
finetuned_distilbert/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased-distilled-squad",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": true,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
+ "vocab_size": 28996
25
+ }
finetuned_distilbert/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1815c6277178bd2bd1b6672d90d44328ba0166680879ad203e18287018b641e
3
+ size 260782152
finetuned_distilbert/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
+ }
finetuned_distilbert/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
finetuned_distilbert/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": false,
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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
finetuned_distilbert/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9988663bd319a438514dff5ffaf0334f9bcb456c0dcfeff35874f6030035c433
3
+ size 5649
finetuned_distilbert/vocab.txt ADDED
The diff for this file is too large to render. See raw diff