ZhangYunchenY
commited on
Commit
•
1290f12
1
Parent(s):
70fc684
[Model] bart-base-cola
Browse files- config.json +74 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +181 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForSequenceClassification"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"finetuning_task": "cola",
|
28 |
+
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
+
"id2label": {
|
31 |
+
"0": "unacceptable",
|
32 |
+
"1": "acceptable"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"acceptable": 1,
|
38 |
+
"unacceptable": 0
|
39 |
+
},
|
40 |
+
"max_position_embeddings": 1024,
|
41 |
+
"model_type": "bart",
|
42 |
+
"no_repeat_ngram_size": 3,
|
43 |
+
"normalize_before": false,
|
44 |
+
"normalize_embedding": true,
|
45 |
+
"num_beams": 4,
|
46 |
+
"num_hidden_layers": 6,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"problem_type": "single_label_classification",
|
49 |
+
"scale_embedding": false,
|
50 |
+
"task_specific_params": {
|
51 |
+
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
+
"length_penalty": 2.0,
|
59 |
+
"max_length": 142,
|
60 |
+
"min_length": 56,
|
61 |
+
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.16.2",
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 50265
|
74 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:847dd3b004891e595d7791c01019d2983f77384d50c9f6abc227c64e74bb98bf
|
3 |
+
size 1120266491
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a85bb0f3b54c44af4b79a488efde4248a095de99fbe08d638d992b9af06f627b
|
3 |
+
size 560154805
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7715ad3397c0c55c7b0871bf46cea42f26454b4139462854c332a4f6619eba6
|
3 |
+
size 14659
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7e0189f63e54dfab03937ea72158839b1c69101258a3d6704f3be974933751e
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "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 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base", "tokenizer_class": "BartTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.208955223880597,
|
5 |
+
"global_step": 2200,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.75,
|
12 |
+
"learning_rate": 3.92749244712991e-05,
|
13 |
+
"loss": 0.5968,
|
14 |
+
"step": 200
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.75,
|
18 |
+
"eval_loss": 0.5482025742530823,
|
19 |
+
"eval_matthews_correlation": 0.4044551659076911,
|
20 |
+
"eval_runtime": 7.0014,
|
21 |
+
"eval_samples_per_second": 148.97,
|
22 |
+
"eval_steps_per_second": 4.713,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.49,
|
27 |
+
"learning_rate": 3.8066465256797584e-05,
|
28 |
+
"loss": 0.4748,
|
29 |
+
"step": 400
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.49,
|
33 |
+
"eval_loss": 0.7374169826507568,
|
34 |
+
"eval_matthews_correlation": 0.295093127326412,
|
35 |
+
"eval_runtime": 4.195,
|
36 |
+
"eval_samples_per_second": 248.628,
|
37 |
+
"eval_steps_per_second": 7.866,
|
38 |
+
"step": 400
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.24,
|
42 |
+
"learning_rate": 3.685800604229608e-05,
|
43 |
+
"loss": 0.4165,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.24,
|
48 |
+
"eval_loss": 0.7154484391212463,
|
49 |
+
"eval_matthews_correlation": 0.4656950548188858,
|
50 |
+
"eval_runtime": 4.0204,
|
51 |
+
"eval_samples_per_second": 259.424,
|
52 |
+
"eval_steps_per_second": 8.208,
|
53 |
+
"step": 600
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 2.99,
|
57 |
+
"learning_rate": 3.564954682779456e-05,
|
58 |
+
"loss": 0.3461,
|
59 |
+
"step": 800
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 2.99,
|
63 |
+
"eval_loss": 0.5880667567253113,
|
64 |
+
"eval_matthews_correlation": 0.4966579188966687,
|
65 |
+
"eval_runtime": 4.1325,
|
66 |
+
"eval_samples_per_second": 252.389,
|
67 |
+
"eval_steps_per_second": 7.985,
|
68 |
+
"step": 800
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 3.73,
|
72 |
+
"learning_rate": 3.4441087613293056e-05,
|
73 |
+
"loss": 0.2666,
|
74 |
+
"step": 1000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 3.73,
|
78 |
+
"eval_loss": 0.6024960875511169,
|
79 |
+
"eval_matthews_correlation": 0.5243351914860497,
|
80 |
+
"eval_runtime": 4.2714,
|
81 |
+
"eval_samples_per_second": 244.185,
|
82 |
+
"eval_steps_per_second": 7.726,
|
83 |
+
"step": 1000
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 4.48,
|
87 |
+
"learning_rate": 3.323262839879154e-05,
|
88 |
+
"loss": 0.233,
|
89 |
+
"step": 1200
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 4.48,
|
93 |
+
"eval_loss": 0.7757831811904907,
|
94 |
+
"eval_matthews_correlation": 0.5180330680945964,
|
95 |
+
"eval_runtime": 5.4027,
|
96 |
+
"eval_samples_per_second": 193.052,
|
97 |
+
"eval_steps_per_second": 6.108,
|
98 |
+
"step": 1200
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 5.22,
|
102 |
+
"learning_rate": 3.2024169184290035e-05,
|
103 |
+
"loss": 0.2067,
|
104 |
+
"step": 1400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 5.22,
|
108 |
+
"eval_loss": 0.8261585831642151,
|
109 |
+
"eval_matthews_correlation": 0.4812305179480984,
|
110 |
+
"eval_runtime": 4.5778,
|
111 |
+
"eval_samples_per_second": 227.84,
|
112 |
+
"eval_steps_per_second": 7.209,
|
113 |
+
"step": 1400
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 5.97,
|
117 |
+
"learning_rate": 3.081570996978852e-05,
|
118 |
+
"loss": 0.174,
|
119 |
+
"step": 1600
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 5.97,
|
123 |
+
"eval_loss": 1.0030035972595215,
|
124 |
+
"eval_matthews_correlation": 0.4690871215881841,
|
125 |
+
"eval_runtime": 4.1699,
|
126 |
+
"eval_samples_per_second": 250.124,
|
127 |
+
"eval_steps_per_second": 7.914,
|
128 |
+
"step": 1600
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 6.72,
|
132 |
+
"learning_rate": 2.9607250755287014e-05,
|
133 |
+
"loss": 0.1504,
|
134 |
+
"step": 1800
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 6.72,
|
138 |
+
"eval_loss": 1.007808804512024,
|
139 |
+
"eval_matthews_correlation": 0.505928717066083,
|
140 |
+
"eval_runtime": 5.5718,
|
141 |
+
"eval_samples_per_second": 187.193,
|
142 |
+
"eval_steps_per_second": 5.923,
|
143 |
+
"step": 1800
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 7.46,
|
147 |
+
"learning_rate": 2.83987915407855e-05,
|
148 |
+
"loss": 0.1261,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 7.46,
|
153 |
+
"eval_loss": 1.0862607955932617,
|
154 |
+
"eval_matthews_correlation": 0.4929950873963667,
|
155 |
+
"eval_runtime": 4.1938,
|
156 |
+
"eval_samples_per_second": 248.698,
|
157 |
+
"eval_steps_per_second": 7.869,
|
158 |
+
"step": 2000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 8.21,
|
162 |
+
"learning_rate": 2.719033232628399e-05,
|
163 |
+
"loss": 0.1141,
|
164 |
+
"step": 2200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 8.21,
|
168 |
+
"eval_loss": 0.9651995301246643,
|
169 |
+
"eval_matthews_correlation": 0.5632084517291658,
|
170 |
+
"eval_runtime": 4.2997,
|
171 |
+
"eval_samples_per_second": 242.575,
|
172 |
+
"eval_steps_per_second": 7.675,
|
173 |
+
"step": 2200
|
174 |
+
}
|
175 |
+
],
|
176 |
+
"max_steps": 6700,
|
177 |
+
"num_train_epochs": 25,
|
178 |
+
"total_flos": 5382361281024000.0,
|
179 |
+
"trial_name": null,
|
180 |
+
"trial_params": null
|
181 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a21a436b6e8570df92e245a5b6f68672b3b1e04d27eed2a48a376a683ef2c570
|
3 |
+
size 2991
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|