Hugging Face's logo

Ayoola
/
clyde

Transformers
PyTorch
bart
text2text-generation
Model card Files
xet
 Community
1
Ayoola commited on
Commit
7d9a15b
·
1 Parent(s): 1cf1d86

add model

Browse files
Files changed (10) hide show
  1. merges.txt +0 -0
  2. optimizer.pt +3 -0
  3. rng_state.pth +3 -0
  4. scaler.pt +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +15 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +16 -0
  9. trainer_state.json +108 -0
  10. training_args.bin +3 -0
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:baeca4286e88c2b3daca8c94e107ee72e78b74b7d356b6dc09a8bd673049e701
3
+ size 3250621339
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04795425663d225ecbb1127a681a9f25acf06d074e1461aadd820be3ce50b2f4
3
+ size 14503
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f358f2aa27e75a3fdd47c517f622e60591d8c47ccfe8b21d6ca2c5b013d3e8d
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:740968ba0ba7c4205d76586a4c987b6d066f04979c9119d4b974232e7c58e327
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 1024,
9
+ "name_or_path": "facebook/bart-large-xsum",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "BartTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
trainer_state.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9872386641325006,
5
+ "global_step": 5500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.27,
12
+ "learning_rate": 1.8203874705775847e-05,
13
+ "loss": 1.5351,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.54,
18
+ "learning_rate": 1.639326453014666e-05,
19
+ "loss": 1.418,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.81,
24
+ "learning_rate": 1.4586275574868732e-05,
25
+ "loss": 1.3833,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.0,
30
+ "eval_gen_len": 25.9756,
31
+ "eval_loss": 1.4744428396224976,
32
+ "eval_rouge1": 53.2728,
33
+ "eval_rouge2": 28.5907,
34
+ "eval_rougeL": 43.9891,
35
+ "eval_rougeLsum": 48.6797,
36
+ "eval_runtime": 208.0144,
37
+ "eval_samples_per_second": 3.932,
38
+ "eval_steps_per_second": 0.986,
39
+ "step": 1841
40
+ },
41
+ {
42
+ "epoch": 1.09,
43
+ "learning_rate": 1.2775665399239545e-05,
44
+ "loss": 1.2657,
45
+ "step": 2000
46
+ },
47
+ {
48
+ "epoch": 1.36,
49
+ "learning_rate": 1.0965055223610357e-05,
50
+ "loss": 1.0604,
51
+ "step": 2500
52
+ },
53
+ {
54
+ "epoch": 1.63,
55
+ "learning_rate": 9.15444504798117e-06,
56
+ "loss": 1.0653,
57
+ "step": 3000
58
+ },
59
+ {
60
+ "epoch": 1.9,
61
+ "learning_rate": 7.343834872351984e-06,
62
+ "loss": 1.0762,
63
+ "step": 3500
64
+ },
65
+ {
66
+ "epoch": 2.0,
67
+ "eval_gen_len": 30.9328,
68
+ "eval_loss": 1.4248533248901367,
69
+ "eval_rouge1": 54.4293,
70
+ "eval_rouge2": 29.3125,
71
+ "eval_rougeL": 44.6626,
72
+ "eval_rougeLsum": 50.0031,
73
+ "eval_runtime": 237.2771,
74
+ "eval_samples_per_second": 3.447,
75
+ "eval_steps_per_second": 0.864,
76
+ "step": 3682
77
+ },
78
+ {
79
+ "epoch": 2.17,
80
+ "learning_rate": 5.5332246967227965e-06,
81
+ "loss": 0.9395,
82
+ "step": 4000
83
+ },
84
+ {
85
+ "epoch": 2.44,
86
+ "learning_rate": 3.7262357414448676e-06,
87
+ "loss": 0.8509,
88
+ "step": 4500
89
+ },
90
+ {
91
+ "epoch": 2.72,
92
+ "learning_rate": 1.91562556581568e-06,
93
+ "loss": 0.8581,
94
+ "step": 5000
95
+ },
96
+ {
97
+ "epoch": 2.99,
98
+ "learning_rate": 1.0501539018649285e-07,
99
+ "loss": 0.8555,
100
+ "step": 5500
101
+ }
102
+ ],
103
+ "max_steps": 5523,
104
+ "num_train_epochs": 3,
105
+ "total_flos": 2.597261321227469e+16,
106
+ "trial_name": null,
107
+ "trial_params": null
108
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9374432267fffa1483b65a8302bb41cc090c8c62b5c13d32558e4678b0e21593
3
+ size 3503