Gaetano-Rossiello commited on
Commit
a28277d
1 Parent(s): ef0fcbc

GenRL LC-QuAD 1.0 model upload

Browse files
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_gen_len": 16.492,
4
+ "eval_loss": 1.3707971572875977,
5
+ "eval_rouge1": 87.4745,
6
+ "eval_rouge2": 75.8987,
7
+ "eval_rougeL": 80.4706,
8
+ "eval_rougeLsum": 80.5497,
9
+ "eval_runtime": 98.5514,
10
+ "eval_samples": 994,
11
+ "eval_samples_per_second": 10.086,
12
+ "train_runtime": 5930.4108,
13
+ "train_samples": 3995,
14
+ "train_samples_per_second": 1.685
15
+ }
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
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": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "num_beams": 4,
46
+ "num_hidden_layers": 12,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": false,
49
+ "task_specific_params": {
50
+ "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
55
+ },
56
+ "summarization_cnn": {
57
+ "length_penalty": 2.0,
58
+ "max_length": 142,
59
+ "min_length": 56,
60
+ "num_beams": 4
61
+ },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
+ }
68
+ },
69
+ "transformers_version": "4.5.0.dev0",
70
+ "use_cache": true,
71
+ "vocab_size": 50265
72
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_gen_len": 16.492,
4
+ "eval_loss": 1.3707971572875977,
5
+ "eval_rouge1": 87.4745,
6
+ "eval_rouge2": 75.8987,
7
+ "eval_rougeL": 80.4706,
8
+ "eval_rougeLsum": 80.5497,
9
+ "eval_runtime": 98.5514,
10
+ "eval_samples": 994,
11
+ "eval_samples_per_second": 10.086
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206e09096f5a4eced41a90863d782a0e821b365ee7421951e37d83e0139ab97c
3
+ size 1625569391
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_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>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large"}
train_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_runtime": 5930.4108,
4
+ "train_samples": 3995,
5
+ "train_samples_per_second": 1.685
6
+ }
trainer_state.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 9990,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.5,
12
+ "learning_rate": 4.74974974974975e-05,
13
+ "loss": 0.6173,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 4.4994994994994996e-05,
19
+ "loss": 0.4542,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.5,
24
+ "learning_rate": 4.24924924924925e-05,
25
+ "loss": 0.2895,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 3.998998998998999e-05,
31
+ "loss": 0.2248,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 2.5,
36
+ "learning_rate": 3.7487487487487486e-05,
37
+ "loss": 0.1654,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3.498498498498499e-05,
43
+ "loss": 0.1603,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 3.5,
48
+ "learning_rate": 3.2482482482482486e-05,
49
+ "loss": 0.1201,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 2.9979979979979983e-05,
55
+ "loss": 0.1236,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 4.5,
60
+ "learning_rate": 2.7477477477477483e-05,
61
+ "loss": 0.094,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 5.01,
66
+ "learning_rate": 2.4974974974974976e-05,
67
+ "loss": 0.0905,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 5.51,
72
+ "learning_rate": 2.2472472472472473e-05,
73
+ "loss": 0.081,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 6.01,
78
+ "learning_rate": 1.996996996996997e-05,
79
+ "loss": 0.0672,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 6.51,
84
+ "learning_rate": 1.746746746746747e-05,
85
+ "loss": 0.0576,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 7.01,
90
+ "learning_rate": 1.4964964964964966e-05,
91
+ "loss": 0.0536,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 7.51,
96
+ "learning_rate": 1.2462462462462463e-05,
97
+ "loss": 0.0356,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 8.01,
102
+ "learning_rate": 9.959959959959962e-06,
103
+ "loss": 0.0344,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 8.51,
108
+ "learning_rate": 7.457457457457457e-06,
109
+ "loss": 0.0231,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 9.01,
114
+ "learning_rate": 4.954954954954955e-06,
115
+ "loss": 0.0246,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 9.51,
120
+ "learning_rate": 2.4524524524524525e-06,
121
+ "loss": 0.0143,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 10.0,
126
+ "step": 9990,
127
+ "total_flos": 3.1793177520881664e+16,
128
+ "train_runtime": 5930.4108,
129
+ "train_samples_per_second": 1.685
130
+ }
131
+ ],
132
+ "max_steps": 9990,
133
+ "num_train_epochs": 10,
134
+ "total_flos": 3.1793177520881664e+16,
135
+ "trial_name": null,
136
+ "trial_params": null
137
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a08effb2c5948cab2e534c1eb92c0fd912087e196d9478afb40d4c85820d11
3
+ size 2415
vocab.json ADDED
The diff for this file is too large to render. See raw diff