Hugging Face's logo

sms1097
/
retrieval_model

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
text-embeddings-inference
Model card Files
xet
 Metrics Community
sms1097 commited on
Commit
4d2afd5
·
verified ·
1 Parent(s): 575cb1d

Training in progress, epoch 3

Browse files
Files changed (13) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-13356/config.json +25 -0
  3. run-0/checkpoint-13356/model.safetensors +3 -0
  4. run-0/checkpoint-13356/optimizer.pt +3 -0
  5. run-0/checkpoint-13356/rng_state.pth +3 -0
  6. run-0/checkpoint-13356/scheduler.pt +3 -0
  7. run-0/checkpoint-13356/special_tokens_map.json +7 -0
  8. run-0/checkpoint-13356/tokenizer.json +0 -0
  9. run-0/checkpoint-13356/tokenizer_config.json +55 -0
  10. run-0/checkpoint-13356/trainer_state.json +207 -0
  11. run-0/checkpoint-13356/training_args.bin +3 -0
  12. run-0/checkpoint-13356/vocab.txt +0 -0
  13. runs/Feb05_22-24-00_760f8e25befd/events.out.tfevents.1707171842.760f8e25befd.956.0 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25e2cf606b083f1c3f9ca6ef1dc8d64d999d160a70822da9f82e1c4f2df28db1
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455e1b3d30c65b601cb9015a0fc8be70c0f51850c8ccb7f28ea47e432cdc4b7b
3
  size 267832560
run-0/checkpoint-13356/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
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
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.35.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-13356/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455e1b3d30c65b601cb9015a0fc8be70c0f51850c8ccb7f28ea47e432cdc4b7b
3
+ size 267832560
run-0/checkpoint-13356/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6885eda864a10f5d617b47afb1a035d17daba7dc8aa77ebfaf0719144363f8cc
3
+ size 535727290
run-0/checkpoint-13356/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f78a14ee5781d823a45fdd7de2f82e433307246bd7f42212ec40fe098b1cb9ee
3
+ size 14308
run-0/checkpoint-13356/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fefc8b6a0ef675bbdef5440cd1f838bb0c3f71bd6d2cf77c65536376cbbf0d
3
+ size 1064
run-0/checkpoint-13356/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
+ }
run-0/checkpoint-13356/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-13356/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-13356/trainer_state.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8416517055655296,
3
+ "best_model_checkpoint": "retrieval_model/run-0/checkpoint-13356",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 13356,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11,
13
+ "learning_rate": 1.8075065847895588e-06,
14
+ "loss": 0.4825,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.22,
19
+ "learning_rate": 1.73720841332139e-06,
20
+ "loss": 0.3777,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.34,
25
+ "learning_rate": 1.666910241853221e-06,
26
+ "loss": 0.3516,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.45,
31
+ "learning_rate": 1.5966120703850521e-06,
32
+ "loss": 0.3194,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.56,
37
+ "learning_rate": 1.5263138989168832e-06,
38
+ "loss": 0.3394,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.67,
43
+ "learning_rate": 1.4560157274487143e-06,
44
+ "loss": 0.3201,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.79,
49
+ "learning_rate": 1.3857175559805454e-06,
50
+ "loss": 0.3128,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.9,
55
+ "learning_rate": 1.3154193845123765e-06,
56
+ "loss": 0.3316,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.0,
61
+ "eval_f1": 0.8266480641785839,
62
+ "eval_loss": 0.306449294090271,
63
+ "eval_runtime": 15.3165,
64
+ "eval_samples_per_second": 258.283,
65
+ "eval_steps_per_second": 8.096,
66
+ "step": 4452
67
+ },
68
+ {
69
+ "epoch": 1.01,
70
+ "learning_rate": 1.2451212130442076e-06,
71
+ "loss": 0.3137,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 1.12,
76
+ "learning_rate": 1.1748230415760387e-06,
77
+ "loss": 0.304,
78
+ "step": 5000
79
+ },
80
+ {
81
+ "epoch": 1.24,
82
+ "learning_rate": 1.1045248701078698e-06,
83
+ "loss": 0.2966,
84
+ "step": 5500
85
+ },
86
+ {
87
+ "epoch": 1.35,
88
+ "learning_rate": 1.034226698639701e-06,
89
+ "loss": 0.2903,
90
+ "step": 6000
91
+ },
92
+ {
93
+ "epoch": 1.46,
94
+ "learning_rate": 9.639285271715318e-07,
95
+ "loss": 0.287,
96
+ "step": 6500
97
+ },
98
+ {
99
+ "epoch": 1.57,
100
+ "learning_rate": 8.936303557033631e-07,
101
+ "loss": 0.2896,
102
+ "step": 7000
103
+ },
104
+ {
105
+ "epoch": 1.68,
106
+ "learning_rate": 8.233321842351941e-07,
107
+ "loss": 0.2882,
108
+ "step": 7500
109
+ },
110
+ {
111
+ "epoch": 1.8,
112
+ "learning_rate": 7.530340127670252e-07,
113
+ "loss": 0.2879,
114
+ "step": 8000
115
+ },
116
+ {
117
+ "epoch": 1.91,
118
+ "learning_rate": 6.827358412988563e-07,
119
+ "loss": 0.2851,
120
+ "step": 8500
121
+ },
122
+ {
123
+ "epoch": 2.0,
124
+ "eval_f1": 0.8342602892102335,
125
+ "eval_loss": 0.2832660973072052,
126
+ "eval_runtime": 14.8465,
127
+ "eval_samples_per_second": 266.459,
128
+ "eval_steps_per_second": 8.352,
129
+ "step": 8904
130
+ },
131
+ {
132
+ "epoch": 2.02,
133
+ "learning_rate": 6.124376698306876e-07,
134
+ "loss": 0.2749,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 2.13,
139
+ "learning_rate": 5.421394983625185e-07,
140
+ "loss": 0.2714,
141
+ "step": 9500
142
+ },
143
+ {
144
+ "epoch": 2.25,
145
+ "learning_rate": 4.7184132689434965e-07,
146
+ "loss": 0.2688,
147
+ "step": 10000
148
+ },
149
+ {
150
+ "epoch": 2.36,
151
+ "learning_rate": 4.015431554261808e-07,
152
+ "loss": 0.283,
153
+ "step": 10500
154
+ },
155
+ {
156
+ "epoch": 2.47,
157
+ "learning_rate": 3.3124498395801186e-07,
158
+ "loss": 0.2765,
159
+ "step": 11000
160
+ },
161
+ {
162
+ "epoch": 2.58,
163
+ "learning_rate": 2.6094681248984296e-07,
164
+ "loss": 0.2749,
165
+ "step": 11500
166
+ },
167
+ {
168
+ "epoch": 2.7,
169
+ "learning_rate": 1.9064864102167406e-07,
170
+ "loss": 0.261,
171
+ "step": 12000
172
+ },
173
+ {
174
+ "epoch": 2.81,
175
+ "learning_rate": 1.2035046955350516e-07,
176
+ "loss": 0.2774,
177
+ "step": 12500
178
+ },
179
+ {
180
+ "epoch": 2.92,
181
+ "learning_rate": 5.005229808533626e-08,
182
+ "loss": 0.2827,
183
+ "step": 13000
184
+ },
185
+ {
186
+ "epoch": 3.0,
187
+ "eval_f1": 0.8416517055655296,
188
+ "eval_loss": 0.27812373638153076,
189
+ "eval_runtime": 14.8558,
190
+ "eval_samples_per_second": 266.293,
191
+ "eval_steps_per_second": 8.347,
192
+ "step": 13356
193
+ }
194
+ ],
195
+ "logging_steps": 500,
196
+ "max_steps": 13356,
197
+ "num_train_epochs": 3,
198
+ "save_steps": 500,
199
+ "total_flos": 1.5367472803502412e+16,
200
+ "trial_name": null,
201
+ "trial_params": {
202
+ "learning_rate": 1.8778047562577277e-06,
203
+ "num_train_epochs": 3,
204
+ "per_device_train_batch_size": 16,
205
+ "seed": 37
206
+ }
207
+ }
run-0/checkpoint-13356/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5521eb92746940d9565af4306b63f1239e8192971887da1871b30da6a3051d
3
+ size 4600
run-0/checkpoint-13356/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb05_22-24-00_760f8e25befd/events.out.tfevents.1707171842.760f8e25befd.956.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aae16c69fd9d256683ff3e9cd7d681d556f4a05ae95e7c4858a925c36783aa2c
3
- size 7407
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2765d7e5a9ab8fb4db1710993b6dadf013eb2945f1cda8a6d026c24e1ae0173b
3
+ size 9491