Palak Goenka commited on
Commit
6257fbf
1 Parent(s): 3063cc3
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - squad
7
+ model-index:
8
+ - name: albert-base-v2_squad
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # albert-base-v2_squad
16
+
17
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 3e-05
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 32
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3.0
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.14.1
51
+ - Pytorch 1.9.0
52
+ - Datasets 1.16.1
53
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_exact_match": 82.69631031220435,
4
+ "eval_f1": 90.10806626207174,
5
+ "eval_samples": 10808,
6
+ "train_loss": 0.7218501507590394,
7
+ "train_runtime": 2515.671,
8
+ "train_samples": 88638,
9
+ "train_samples_per_second": 105.703,
10
+ "train_steps_per_second": 6.607
11
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.14.1",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
eval_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_exact_match": 82.69631031220435,
4
+ "eval_f1": 90.10806626207174,
5
+ "eval_samples": 10808
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a20c1af5591d161427cc88dfcf4acd283fd43a2ed968aaf57f4de67e257e86
3
+ size 44392343
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.7218501507590394,
4
+ "train_runtime": 2515.671,
5
+ "train_samples": 88638,
6
+ "train_samples_per_second": 105.703,
7
+ "train_steps_per_second": 6.607
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 16620,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 2.909747292418773e-05,
13
+ "loss": 1.4916,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 2.819494584837545e-05,
19
+ "loss": 1.143,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 2.729241877256318e-05,
25
+ "loss": 1.0765,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.36,
30
+ "learning_rate": 2.6389891696750903e-05,
31
+ "loss": 1.0025,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.45,
36
+ "learning_rate": 2.548736462093863e-05,
37
+ "loss": 1.0014,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.54,
42
+ "learning_rate": 2.4584837545126353e-05,
43
+ "loss": 0.9314,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.63,
48
+ "learning_rate": 2.368231046931408e-05,
49
+ "loss": 0.9617,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.72,
54
+ "learning_rate": 2.2779783393501805e-05,
55
+ "loss": 0.9426,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.81,
60
+ "learning_rate": 2.1877256317689534e-05,
61
+ "loss": 0.9326,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.9,
66
+ "learning_rate": 2.0974729241877255e-05,
67
+ "loss": 0.8923,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.99,
72
+ "learning_rate": 2.0072202166064983e-05,
73
+ "loss": 0.8866,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.08,
78
+ "learning_rate": 1.9169675090252708e-05,
79
+ "loss": 0.7289,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.17,
84
+ "learning_rate": 1.8267148014440436e-05,
85
+ "loss": 0.6916,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.26,
90
+ "learning_rate": 1.7364620938628157e-05,
91
+ "loss": 0.6857,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.35,
96
+ "learning_rate": 1.6462093862815885e-05,
97
+ "loss": 0.6954,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.44,
102
+ "learning_rate": 1.555956678700361e-05,
103
+ "loss": 0.6555,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.53,
108
+ "learning_rate": 1.4657039711191336e-05,
109
+ "loss": 0.6923,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.62,
114
+ "learning_rate": 1.3754512635379063e-05,
115
+ "loss": 0.6944,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.71,
120
+ "learning_rate": 1.2851985559566788e-05,
121
+ "loss": 0.6636,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.81,
126
+ "learning_rate": 1.1949458483754514e-05,
127
+ "loss": 0.6424,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.9,
132
+ "learning_rate": 1.1046931407942239e-05,
133
+ "loss": 0.6906,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.99,
138
+ "learning_rate": 1.0144404332129965e-05,
139
+ "loss": 0.6409,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.08,
144
+ "learning_rate": 9.24187725631769e-06,
145
+ "loss": 0.5255,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.17,
150
+ "learning_rate": 8.339350180505416e-06,
151
+ "loss": 0.4748,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.26,
156
+ "learning_rate": 7.436823104693141e-06,
157
+ "loss": 0.4609,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.35,
162
+ "learning_rate": 6.534296028880867e-06,
163
+ "loss": 0.473,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.44,
168
+ "learning_rate": 5.631768953068592e-06,
169
+ "loss": 0.4867,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.53,
174
+ "learning_rate": 4.729241877256318e-06,
175
+ "loss": 0.4564,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.62,
180
+ "learning_rate": 3.826714801444043e-06,
181
+ "loss": 0.45,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.71,
186
+ "learning_rate": 2.924187725631769e-06,
187
+ "loss": 0.4649,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.8,
192
+ "learning_rate": 2.0216606498194946e-06,
193
+ "loss": 0.4557,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.89,
198
+ "learning_rate": 1.1191335740072204e-06,
199
+ "loss": 0.4464,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 2.98,
204
+ "learning_rate": 2.1660649819494586e-07,
205
+ "loss": 0.4505,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 3.0,
210
+ "step": 16620,
211
+ "total_flos": 4404294320329728.0,
212
+ "train_loss": 0.7218501507590394,
213
+ "train_runtime": 2515.671,
214
+ "train_samples_per_second": 105.703,
215
+ "train_steps_per_second": 6.607
216
+ }
217
+ ],
218
+ "max_steps": 16620,
219
+ "num_train_epochs": 3,
220
+ "total_flos": 4404294320329728.0,
221
+ "trial_name": null,
222
+ "trial_params": null
223
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef346cec5f6880e87f7b5a24dc05cfda98fc929a96e2dd684a184c169d048b17
3
+ size 2927