tmnam20 commited on
Commit
addca46
1 Parent(s): 91ac9f6

Training in progress, step 50000, checkpoint

Browse files
checkpoint-50000/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
checkpoint-50000/bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "demdecuong/vihealthbert-base-word",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "word-level",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "layer_norm_eps": 1e-05,
18
+ "max_position_embeddings": 258,
19
+ "model_type": "roberta",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "output_hidden_states": true,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "tokenizer_class": "PhobertTokenizer",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.40.2",
28
+ "type_vocab_size": 1,
29
+ "use_cache": true,
30
+ "vocab_size": 64001
31
+ }
checkpoint-50000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:013f5cc6da610214e1d8eba9d4279385005c5b734c6cc0c65a30576bc09d3324
3
+ size 540279452
checkpoint-50000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47d67e60faaa01cb8c0c29bddf4efd82f897ff8665dc3e3260a5474d275b98b
3
+ size 1080630853
checkpoint-50000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893344f94951d042bb3987ff13e80c267476e6fcde15243e4f646165f4b5908f
3
+ size 14575
checkpoint-50000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33a2fdb9a65951191a707093372fdb5992932c160db4998c0949d3981a49de5
3
+ size 627
checkpoint-50000/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
checkpoint-50000/tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "PhobertTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
checkpoint-50000/trainer_state.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6852411542306852,
3
+ "best_model_checkpoint": "output/pretraining/vihealthbert-w_unsup-SynPD/lr3e-5_wr0.1_wd0.0/checkpoint-50000",
4
+ "epoch": 8.61623298293986,
5
+ "eval_steps": 5000,
6
+ "global_step": 50000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00017232465965879716,
13
+ "grad_norm": 41.827266693115234,
14
+ "learning_rate": 5.169739789763915e-09,
15
+ "loss": 13.7242,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.8616232982939859,
20
+ "grad_norm": 5.6151957511901855,
21
+ "learning_rate": 2.584869894881958e-05,
22
+ "loss": 7.0234,
23
+ "step": 5000
24
+ },
25
+ {
26
+ "epoch": 0.8616232982939859,
27
+ "eval_accuracy": 0.5576033171446898,
28
+ "eval_loss": 2.590928077697754,
29
+ "eval_runtime": 37.589,
30
+ "eval_samples_per_second": 260.023,
31
+ "eval_steps_per_second": 16.255,
32
+ "step": 5000
33
+ },
34
+ {
35
+ "epoch": 1.7232465965879717,
36
+ "grad_norm": 4.410743713378906,
37
+ "learning_rate": 2.758917801137343e-05,
38
+ "loss": 5.2736,
39
+ "step": 10000
40
+ },
41
+ {
42
+ "epoch": 1.7232465965879717,
43
+ "eval_accuracy": 0.596153624823046,
44
+ "eval_loss": 2.188957452774048,
45
+ "eval_runtime": 37.6297,
46
+ "eval_samples_per_second": 259.741,
47
+ "eval_steps_per_second": 16.237,
48
+ "step": 10000
49
+ },
50
+ {
51
+ "epoch": 2.5848698948819577,
52
+ "grad_norm": 4.754213809967041,
53
+ "learning_rate": 2.4717100350393475e-05,
54
+ "loss": 4.9126,
55
+ "step": 15000
56
+ },
57
+ {
58
+ "epoch": 2.5848698948819577,
59
+ "eval_accuracy": 0.6381037526075694,
60
+ "eval_loss": 1.909491777420044,
61
+ "eval_runtime": 36.8556,
62
+ "eval_samples_per_second": 265.197,
63
+ "eval_steps_per_second": 16.578,
64
+ "step": 15000
65
+ },
66
+ {
67
+ "epoch": 3.4464931931759435,
68
+ "grad_norm": 4.2047200202941895,
69
+ "learning_rate": 2.184502268941352e-05,
70
+ "loss": 4.791,
71
+ "step": 20000
72
+ },
73
+ {
74
+ "epoch": 3.4464931931759435,
75
+ "eval_accuracy": 0.6468589272593681,
76
+ "eval_loss": 1.8286069631576538,
77
+ "eval_runtime": 35.9342,
78
+ "eval_samples_per_second": 271.997,
79
+ "eval_steps_per_second": 17.003,
80
+ "step": 20000
81
+ },
82
+ {
83
+ "epoch": 4.30811649146993,
84
+ "grad_norm": 4.629519462585449,
85
+ "learning_rate": 1.897294502843357e-05,
86
+ "loss": 4.6538,
87
+ "step": 25000
88
+ },
89
+ {
90
+ "epoch": 4.30811649146993,
91
+ "eval_accuracy": 0.6644416567883901,
92
+ "eval_loss": 1.714424967765808,
93
+ "eval_runtime": 35.6122,
94
+ "eval_samples_per_second": 274.456,
95
+ "eval_steps_per_second": 17.157,
96
+ "step": 25000
97
+ },
98
+ {
99
+ "epoch": 5.1697397897639155,
100
+ "grad_norm": 3.993448257446289,
101
+ "learning_rate": 1.6100867367453616e-05,
102
+ "loss": 4.5846,
103
+ "step": 30000
104
+ },
105
+ {
106
+ "epoch": 5.1697397897639155,
107
+ "eval_accuracy": 0.6703549228453575,
108
+ "eval_loss": 1.6779303550720215,
109
+ "eval_runtime": 36.1572,
110
+ "eval_samples_per_second": 270.32,
111
+ "eval_steps_per_second": 16.898,
112
+ "step": 30000
113
+ },
114
+ {
115
+ "epoch": 6.031363088057901,
116
+ "grad_norm": 4.6959357261657715,
117
+ "learning_rate": 1.3228789706473663e-05,
118
+ "loss": 4.5568,
119
+ "step": 35000
120
+ },
121
+ {
122
+ "epoch": 6.031363088057901,
123
+ "eval_accuracy": 0.6765665494261385,
124
+ "eval_loss": 1.6362268924713135,
125
+ "eval_runtime": 36.2906,
126
+ "eval_samples_per_second": 269.326,
127
+ "eval_steps_per_second": 16.836,
128
+ "step": 35000
129
+ },
130
+ {
131
+ "epoch": 6.892986386351887,
132
+ "grad_norm": 4.4082441329956055,
133
+ "learning_rate": 1.035671204549371e-05,
134
+ "loss": 4.5079,
135
+ "step": 40000
136
+ },
137
+ {
138
+ "epoch": 6.892986386351887,
139
+ "eval_accuracy": 0.681425908452811,
140
+ "eval_loss": 1.6008453369140625,
141
+ "eval_runtime": 36.1284,
142
+ "eval_samples_per_second": 270.535,
143
+ "eval_steps_per_second": 16.912,
144
+ "step": 40000
145
+ },
146
+ {
147
+ "epoch": 7.754609684645873,
148
+ "grad_norm": 5.832913398742676,
149
+ "learning_rate": 7.484634384513757e-06,
150
+ "loss": 4.469,
151
+ "step": 45000
152
+ },
153
+ {
154
+ "epoch": 7.754609684645873,
155
+ "eval_accuracy": 0.6805218690729352,
156
+ "eval_loss": 1.6063588857650757,
157
+ "eval_runtime": 36.0752,
158
+ "eval_samples_per_second": 270.934,
159
+ "eval_steps_per_second": 16.937,
160
+ "step": 45000
161
+ },
162
+ {
163
+ "epoch": 8.61623298293986,
164
+ "grad_norm": 3.991995096206665,
165
+ "learning_rate": 4.612556723533804e-06,
166
+ "loss": 4.4514,
167
+ "step": 50000
168
+ },
169
+ {
170
+ "epoch": 8.61623298293986,
171
+ "eval_accuracy": 0.6852411542306852,
172
+ "eval_loss": 1.5799689292907715,
173
+ "eval_runtime": 37.5803,
174
+ "eval_samples_per_second": 260.083,
175
+ "eval_steps_per_second": 16.259,
176
+ "step": 50000
177
+ }
178
+ ],
179
+ "logging_steps": 5000,
180
+ "max_steps": 58030,
181
+ "num_input_tokens_seen": 0,
182
+ "num_train_epochs": 10,
183
+ "save_steps": 5000,
184
+ "total_flos": 0.0,
185
+ "train_batch_size": 32,
186
+ "trial_name": null,
187
+ "trial_params": null
188
+ }
checkpoint-50000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2690ff9d34fa5fa3d550f183e187fe6edb89806dc8d5d196cb79437ad79b8f1
3
+ size 4859
checkpoint-50000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff