Hugging Face's logo

nbtpj
/
bart-base-mqa-fine-tune

Text2Text Generation
Transformers
PyTorch
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
nbtpj commited on
Commit
e1c32fa
•
1 Parent(s): 7cb94bb

Training in progress, step 2500

Browse files
Files changed (13) 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/Jan01_04-28-26_6ea5fb75c867/1672547319.336471/events.out.tfevents.1672547319.6ea5fb75c867.24.1 +3 -0
  12. runs/Jan01_04-28-26_6ea5fb75c867/events.out.tfevents.1672547319.6ea5fb75c867.24.0 +3 -0
  13. 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 sha256:9ec2c97bb156c6d257f8577705f2d4445aee082bdebd9da6f08cb492c9671da6
3
+ size 1115513717
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693dfa4e4e56bac990dac21b8fe757510daaf51de65de333584544574c1bdc24
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:cdb0fe4905a7633b14383ef952b93a78452b17a47d82a1f59d15c9573967fd13
3
+ size 15459
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d0af232cb02e9821619a36e3205ece6ae1dbe2e922db09496bf05b6937c641
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": 0.2872572676088705,
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": 4.968083748244606e-05,
13
+ "loss": 2.9096,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 4.936167496489212e-05,
19
+ "loss": 2.8631,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 4.904251244733819e-05,
25
+ "loss": 2.7364,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.05,
30
+ "learning_rate": 4.8723349929784253e-05,
31
+ "loss": 2.8226,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.06,
36
+ "learning_rate": 4.840418741223031e-05,
37
+ "loss": 2.7184,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.07,
42
+ "learning_rate": 4.808502489467637e-05,
43
+ "loss": 2.6843,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.08,
48
+ "learning_rate": 4.776586237712243e-05,
49
+ "loss": 2.7507,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.09,
54
+ "learning_rate": 4.744669985956849e-05,
55
+ "loss": 2.7261,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.1,
60
+ "learning_rate": 4.712753734201456e-05,
61
+ "loss": 2.7343,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.11,
66
+ "learning_rate": 4.6808374824460616e-05,
67
+ "loss": 2.7005,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.13,
72
+ "learning_rate": 4.6489212306906676e-05,
73
+ "loss": 2.6462,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 0.14,
78
+ "learning_rate": 4.617004978935274e-05,
79
+ "loss": 2.6276,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 0.15,
84
+ "learning_rate": 4.58508872717988e-05,
85
+ "loss": 2.6493,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 0.16,
90
+ "learning_rate": 4.553172475424487e-05,
91
+ "loss": 2.7024,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 0.17,
96
+ "learning_rate": 4.521256223669093e-05,
97
+ "loss": 2.6616,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 0.18,
102
+ "learning_rate": 4.4893399719136986e-05,
103
+ "loss": 2.7136,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 0.2,
108
+ "learning_rate": 4.4574237201583046e-05,
109
+ "loss": 2.6842,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 0.21,
114
+ "learning_rate": 4.4255074684029105e-05,
115
+ "loss": 2.5911,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 0.22,
120
+ "learning_rate": 4.393591216647517e-05,
121
+ "loss": 2.7281,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 0.23,
126
+ "learning_rate": 4.361674964892124e-05,
127
+ "loss": 2.6697,
128
+ "step": 2000
129
+ },
130
+ {
131
+ "epoch": 0.24,
132
+ "learning_rate": 4.32975871313673e-05,
133
+ "loss": 2.6282,
134
+ "step": 2100
135
+ },
136
+ {
137
+ "epoch": 0.25,
138
+ "learning_rate": 4.2978424613813356e-05,
139
+ "loss": 2.564,
140
+ "step": 2200
141
+ },
142
+ {
143
+ "epoch": 0.26,
144
+ "learning_rate": 4.2659262096259415e-05,
145
+ "loss": 2.4882,
146
+ "step": 2300
147
+ },
148
+ {
149
+ "epoch": 0.28,
150
+ "learning_rate": 4.2340099578705475e-05,
151
+ "loss": 2.6347,
152
+ "step": 2400
153
+ },
154
+ {
155
+ "epoch": 0.29,
156
+ "learning_rate": 4.202093706115154e-05,
157
+ "loss": 2.5994,
158
+ "step": 2500
159
+ }
160
+ ],
161
+ "max_steps": 15666,
162
+ "num_train_epochs": 2,
163
+ "total_flos": 9894917569904640.0,
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:fb5c03e02cabfaae5aac527cba1260f324dabff8089669a909b39dcb2a587966
3
+ size 3439
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693dfa4e4e56bac990dac21b8fe757510daaf51de65de333584544574c1bdc24
3
+ size 557969145
runs/Jan01_04-28-26_6ea5fb75c867/1672547319.336471/events.out.tfevents.1672547319.6ea5fb75c867.24.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a249c264b10e4e46772af5c41cc6f346530c36c0add7803e76df9c8de97606
3
+ size 5588
runs/Jan01_04-28-26_6ea5fb75c867/events.out.tfevents.1672547319.6ea5fb75c867.24.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6d1cd4831e53469a937a15316e8a11e633699d723260e7dab9000b8504aee42
3
+ size 8760
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb5c03e02cabfaae5aac527cba1260f324dabff8089669a909b39dcb2a587966
3
+ size 3439