jialicheng commited on
Commit
d2382c6
1 Parent(s): 74584e3

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: albert/albert-base-v2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: imdb_42
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # imdb_42
15
+
16
+ This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.2715
19
+ - eval_accuracy: 0.8925
20
+ - eval_runtime: 44.3585
21
+ - eval_samples_per_second: 563.589
22
+ - eval_steps_per_second: 2.209
23
+ - step: 0
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 256
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 10
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.39.3
53
+ - Pytorch 2.2.2+cu118
54
+ - Datasets 2.18.0
55
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.89252,
4
+ "eval_loss": 0.27154749631881714,
5
+ "eval_runtime": 44.3585,
6
+ "eval_samples": 25000,
7
+ "eval_samples_per_second": 563.589,
8
+ "eval_steps_per_second": 2.209,
9
+ "train_loss": 0.17865913017936375,
10
+ "train_runtime": 809.0649,
11
+ "train_samples": 25000,
12
+ "train_samples_per_second": 308.999,
13
+ "train_steps_per_second": 9.665
14
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert/albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
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
+ "finetuning_task": "text-classification",
13
+ "gap_size": 0,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_dropout_prob": 0,
16
+ "hidden_size": 768,
17
+ "id2label": {
18
+ "0": "0",
19
+ "1": "1"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "inner_group_num": 1,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "0": 0,
26
+ "1": 1
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_position_embeddings": 512,
30
+ "model_type": "albert",
31
+ "net_structure_type": 0,
32
+ "num_attention_heads": 12,
33
+ "num_hidden_groups": 1,
34
+ "num_hidden_layers": 12,
35
+ "num_memory_blocks": 0,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.28.0",
41
+ "type_vocab_size": 2,
42
+ "vocab_size": 30000
43
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_accuracy": 0.84076,
3
+ "eval_loss": 0.3598438799381256,
4
+ "eval_runtime": 47.5688,
5
+ "eval_samples": 25000,
6
+ "eval_samples_per_second": 525.554,
7
+ "eval_steps_per_second": 2.06
8
+ }
pred_logit_eval.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6021f8f7ab84bd43c0be2a382ed39e21f2b4fdcc2bfb2416e667f25ce4862757
3
+ size 200128
pred_logit_test.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6021f8f7ab84bd43c0be2a382ed39e21f2b4fdcc2bfb2416e667f25ce4862757
3
+ size 200128
pred_logit_train.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988e034eca9cbad6949247ece24d157a98ad9984c2aaa81387a3bb8232a098dd
3
+ size 200128
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d9a12ee5162981368fc98cef77071a44e16ed19b3b58efbf0636b403d60cd5
3
+ size 46753425
runs/Apr21_19-06-37_clu/events.out.tfevents.1713726476.clu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3695dfd634f3c66cc7e4af307d1c0936a2640d72935d1c4eef75a787fafd85b0
3
+ size 814
runs/Mar18_17-10-35_clu/1710781866.5679219/events.out.tfevents.1710781866.clu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f0a5e4653e9b5b0e9f9114ff296052fbf2e0857aed44389bd99c048bec951e9
3
+ size 5639
runs/Mar18_17-10-35_clu/events.out.tfevents.1710781866.clu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff745329f3196826b4248078cdb7606c7076c381b5b5a53d3fc2836c93139a0
3
+ size 9051
runs/Mar18_17-10-35_clu/events.out.tfevents.1710782695.clu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ada75ba0e6715f0367d77b06e10471ffd06883d8c142ca1ed8b9d2d2314f7a
3
+ size 363
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_accuracy": 0.84076,
3
+ "eval_loss": 0.3598438799381256,
4
+ "eval_runtime": 44.4368,
5
+ "eval_samples": 25000,
6
+ "eval_samples_per_second": 562.597,
7
+ "eval_steps_per_second": 2.205
8
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "[SEP]",
7
+ "keep_accents": false,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "tokenizer_class": "AlbertTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_accuracy": 0.89252,
3
+ "eval_loss": 0.27154749631881714,
4
+ "eval_runtime": 44.3585,
5
+ "eval_samples": 25000,
6
+ "eval_samples_per_second": 563.589,
7
+ "eval_steps_per_second": 2.209
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.84072,
3
+ "best_model_checkpoint": "checkpoint/albert-base-v2/imdb_42/checkpoint-1564",
4
+ "epoch": 10.0,
5
+ "global_step": 7820,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.8094,
13
+ "eval_loss": 0.39343979954719543,
14
+ "eval_runtime": 19.8571,
15
+ "eval_samples_per_second": 1258.993,
16
+ "eval_steps_per_second": 4.935,
17
+ "step": 782
18
+ },
19
+ {
20
+ "epoch": 1.28,
21
+ "learning_rate": 4.360613810741688e-05,
22
+ "loss": 0.5098,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "eval_accuracy": 0.84072,
28
+ "eval_loss": 0.3598405718803406,
29
+ "eval_runtime": 19.9131,
30
+ "eval_samples_per_second": 1255.458,
31
+ "eval_steps_per_second": 4.921,
32
+ "step": 1564
33
+ },
34
+ {
35
+ "epoch": 2.56,
36
+ "learning_rate": 3.721227621483376e-05,
37
+ "loss": 0.3335,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "eval_accuracy": 0.83936,
43
+ "eval_loss": 0.4151993691921234,
44
+ "eval_runtime": 19.8841,
45
+ "eval_samples_per_second": 1257.285,
46
+ "eval_steps_per_second": 4.929,
47
+ "step": 2346
48
+ },
49
+ {
50
+ "epoch": 3.84,
51
+ "learning_rate": 3.081841432225064e-05,
52
+ "loss": 0.2248,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "eval_accuracy": 0.82468,
58
+ "eval_loss": 0.44072645902633667,
59
+ "eval_runtime": 19.8311,
60
+ "eval_samples_per_second": 1260.645,
61
+ "eval_steps_per_second": 4.942,
62
+ "step": 3128
63
+ },
64
+ {
65
+ "epoch": 5.0,
66
+ "eval_accuracy": 0.82064,
67
+ "eval_loss": 0.6104266047477722,
68
+ "eval_runtime": 19.826,
69
+ "eval_samples_per_second": 1260.968,
70
+ "eval_steps_per_second": 4.943,
71
+ "step": 3910
72
+ },
73
+ {
74
+ "epoch": 5.12,
75
+ "learning_rate": 2.442455242966752e-05,
76
+ "loss": 0.1481,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 6.0,
81
+ "eval_accuracy": 0.78312,
82
+ "eval_loss": 0.9157971143722534,
83
+ "eval_runtime": 19.8594,
84
+ "eval_samples_per_second": 1258.849,
85
+ "eval_steps_per_second": 4.935,
86
+ "step": 4692
87
+ },
88
+ {
89
+ "epoch": 6.39,
90
+ "learning_rate": 1.80306905370844e-05,
91
+ "loss": 0.0904,
92
+ "step": 5000
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "eval_accuracy": 0.81568,
97
+ "eval_loss": 0.8991187214851379,
98
+ "eval_runtime": 19.845,
99
+ "eval_samples_per_second": 1259.764,
100
+ "eval_steps_per_second": 4.938,
101
+ "step": 5474
102
+ },
103
+ {
104
+ "epoch": 7.67,
105
+ "learning_rate": 1.163682864450128e-05,
106
+ "loss": 0.0532,
107
+ "step": 6000
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_accuracy": 0.82364,
112
+ "eval_loss": 1.0848387479782104,
113
+ "eval_runtime": 19.903,
114
+ "eval_samples_per_second": 1256.093,
115
+ "eval_steps_per_second": 4.924,
116
+ "step": 6256
117
+ },
118
+ {
119
+ "epoch": 8.95,
120
+ "learning_rate": 5.242966751918159e-06,
121
+ "loss": 0.026,
122
+ "step": 7000
123
+ },
124
+ {
125
+ "epoch": 9.0,
126
+ "eval_accuracy": 0.8226,
127
+ "eval_loss": 1.1122615337371826,
128
+ "eval_runtime": 19.8109,
129
+ "eval_samples_per_second": 1261.933,
130
+ "eval_steps_per_second": 4.947,
131
+ "step": 7038
132
+ },
133
+ {
134
+ "epoch": 10.0,
135
+ "eval_accuracy": 0.81924,
136
+ "eval_loss": 1.2039557695388794,
137
+ "eval_runtime": 19.8508,
138
+ "eval_samples_per_second": 1259.396,
139
+ "eval_steps_per_second": 4.937,
140
+ "step": 7820
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "step": 7820,
145
+ "total_flos": 1493631360000000.0,
146
+ "train_loss": 0.17865913017936375,
147
+ "train_runtime": 809.0649,
148
+ "train_samples_per_second": 308.999,
149
+ "train_steps_per_second": 9.665
150
+ }
151
+ ],
152
+ "max_steps": 7820,
153
+ "num_train_epochs": 10,
154
+ "total_flos": 1493631360000000.0,
155
+ "trial_name": null,
156
+ "trial_params": null
157
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2eddc05289366c5a87139ea57137ff681dec15447838a56b273b059e273576d
3
+ size 3631