Hugging Face's logo

nbtpj
/
bart-base-rmqa-fine-tune

Transformers
PyTorch
bart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
1
nbtpj commited on
Commit
68565c9
·
1 Parent(s): a2f1df5

Training in progress, step 2500

Browse files
Files changed (14) hide show
  1. .gitignore +1 -0
  2. config.json +75 -0
  3. last-checkpoint/config.json +75 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/trainer_state.json +166 -0
  9. last-checkpoint/training_args.bin +3 -0
  10. pytorch_model.bin +3 -0
  11. runs/Jan03_01-47-25_21bb7eba274c/1672710460.1306343/events.out.tfevents.1672710460.21bb7eba274c.23.1 +3 -0
  12. runs/Jan03_01-47-25_21bb7eba274c/1672710478.6635218/events.out.tfevents.1672710478.21bb7eba274c.23.2 +3 -0
  13. runs/Jan03_01-47-25_21bb7eba274c/events.out.tfevents.1672710460.21bb7eba274c.23.0 +3 -0
  14. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/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
+ "BartForConditionalGeneration"
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
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.20.1",
73
+ "use_cache": true,
74
+ "vocab_size": 50265
75
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/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
+ "BartForConditionalGeneration"
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
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.20.1",
73
+ "use_cache": true,
74
+ "vocab_size": 50265
75
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56910156101018ce8c0acada7c6d392f2df7f8fc4bd016a4cc901612310d7ba
3
+ size 1115513717
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445636c2c8221172a25226bb20ae02fbe55f18487903a9c9cda323dc22694e17
3
+ size 557969145
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0173c131ef4ad3f41c830b2d39455080c8f27dcb8b1317e619ce097ac90c49e4
3
+ size 15459
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56dda2424865fef018f240b5645371aea4b9aeaad407013e41a7c8be1115657
3
+ size 623
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.14013452914798205,
5
+ "global_step": 2500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.966367713004485e-05,
13
+ "loss": 1.0008,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 4.9352267065271554e-05,
19
+ "loss": 0.9438,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 4.904085700049826e-05,
25
+ "loss": 0.912,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 4.872944693572497e-05,
31
+ "loss": 0.8963,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 4.8418036870951675e-05,
37
+ "loss": 0.8806,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 4.8106626806178375e-05,
43
+ "loss": 0.8355,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 4.779521674140508e-05,
49
+ "loss": 0.8538,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 4.748380667663179e-05,
55
+ "loss": 0.8787,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.05,
60
+ "learning_rate": 4.7172396611858496e-05,
61
+ "loss": 0.8817,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.06,
66
+ "learning_rate": 4.6860986547085203e-05,
67
+ "loss": 0.8483,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.06,
72
+ "learning_rate": 4.654957648231191e-05,
73
+ "loss": 0.8328,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 0.07,
78
+ "learning_rate": 4.623816641753862e-05,
79
+ "loss": 0.9183,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 4.5926756352765324e-05,
85
+ "loss": 0.8237,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 0.08,
90
+ "learning_rate": 4.5615346287992025e-05,
91
+ "loss": 0.8074,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 0.08,
96
+ "learning_rate": 4.530393622321873e-05,
97
+ "loss": 0.881,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 0.09,
102
+ "learning_rate": 4.499252615844544e-05,
103
+ "loss": 0.85,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 0.1,
108
+ "learning_rate": 4.4681116093672146e-05,
109
+ "loss": 0.8827,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 0.1,
114
+ "learning_rate": 4.436970602889885e-05,
115
+ "loss": 0.9127,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 0.11,
120
+ "learning_rate": 4.405829596412556e-05,
121
+ "loss": 0.9172,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 0.11,
126
+ "learning_rate": 4.374688589935227e-05,
127
+ "loss": 0.8163,
128
+ "step": 2000
129
+ },
130
+ {
131
+ "epoch": 0.12,
132
+ "learning_rate": 4.3435475834578974e-05,
133
+ "loss": 0.8268,
134
+ "step": 2100
135
+ },
136
+ {
137
+ "epoch": 0.12,
138
+ "learning_rate": 4.312406576980568e-05,
139
+ "loss": 0.7457,
140
+ "step": 2200
141
+ },
142
+ {
143
+ "epoch": 0.13,
144
+ "learning_rate": 4.281265570503239e-05,
145
+ "loss": 0.8587,
146
+ "step": 2300
147
+ },
148
+ {
149
+ "epoch": 0.13,
150
+ "learning_rate": 4.2501245640259095e-05,
151
+ "loss": 0.8008,
152
+ "step": 2400
153
+ },
154
+ {
155
+ "epoch": 0.14,
156
+ "learning_rate": 4.21898355754858e-05,
157
+ "loss": 0.7494,
158
+ "step": 2500
159
+ }
160
+ ],
161
+ "max_steps": 32112,
162
+ "num_train_epochs": 2,
163
+ "total_flos": 1.162967019282432e+16,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ba5b3f42228ed1cc9f39879296610a57bbd6ad0d8088954907f54e07dac886
3
+ size 3439
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445636c2c8221172a25226bb20ae02fbe55f18487903a9c9cda323dc22694e17
3
+ size 557969145
runs/Jan03_01-47-25_21bb7eba274c/1672710460.1306343/events.out.tfevents.1672710460.21bb7eba274c.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e24e3d52bdf48b10f6d7bfdc588975a0a37010f7e288afa42684cff04a40ddd2
3
+ size 5591
runs/Jan03_01-47-25_21bb7eba274c/1672710478.6635218/events.out.tfevents.1672710478.21bb7eba274c.23.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d86e8c700095683981c397065a1d2515ce190b9c9f757eeae9e55e6d14beef9
3
+ size 5591
runs/Jan03_01-47-25_21bb7eba274c/events.out.tfevents.1672710460.21bb7eba274c.23.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa46f6e3a042f3a784499fb7ab21b8983bcd4e195edcab582314cb84f6d18eff
3
+ size 13564
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ba5b3f42228ed1cc9f39879296610a57bbd6ad0d8088954907f54e07dac886
3
+ size 3439