spacemanidol commited on
Commit
f26eda9
1 Parent(s): 3c14596

Upload 12 files

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - xsum
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: small-3-6-t
10
+ results:
11
+ - task:
12
+ name: Summarization
13
+ type: summarization
14
+ dataset:
15
+ name: xsum
16
+ type: xsum
17
+ config: default
18
+ split: validation
19
+ args: default
20
+ metrics:
21
+ - name: Rouge1
22
+ type: rouge
23
+ value: 31.7432
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # small-3-6-t
30
+
31
+ This model is a fine-tuned version of [models/small-3-6](https://huggingface.co/models/small-3-6) on the xsum dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 2.1322
34
+ - Rouge1: 31.7432
35
+ - Rouge2: 10.077
36
+ - Rougel: 24.8565
37
+ - Rougelsum: 24.8444
38
+ - Gen Len: 28.8587
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 0.0001
58
+ - train_batch_size: 32
59
+ - eval_batch_size: 16
60
+ - seed: 42
61
+ - gradient_accumulation_steps: 2
62
+ - total_train_batch_size: 64
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: constant
65
+ - num_epochs: 3.0
66
+
67
+ ### Training results
68
+
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.27.0.dev0
74
+ - Pytorch 1.12.1+cu113
75
+ - Datasets 2.10.0
76
+ - Tokenizers 0.13.2
all_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_gen_len": 28.858656307936787,
4
+ "eval_loss": 2.132248878479004,
5
+ "eval_rouge1": 31.7432,
6
+ "eval_rouge2": 10.077,
7
+ "eval_rougeL": 24.8565,
8
+ "eval_rougeLsum": 24.8444,
9
+ "eval_runtime": 553.66,
10
+ "eval_samples": 11327,
11
+ "eval_samples_per_second": 20.458,
12
+ "eval_steps_per_second": 1.279,
13
+ "train_loss": 2.37733912099011,
14
+ "train_runtime": 8397.5704,
15
+ "train_samples": 204017,
16
+ "train_samples_per_second": 72.884,
17
+ "train_steps_per_second": 1.139
18
+ }
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/small-3-6",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 4,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.27.0.dev0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
eval_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_gen_len": 28.858656307936787,
4
+ "eval_loss": 2.132248878479004,
5
+ "eval_rouge1": 31.7432,
6
+ "eval_rouge2": 10.077,
7
+ "eval_rougeL": 24.8565,
8
+ "eval_rougeLsum": 24.8444,
9
+ "eval_runtime": 553.66,
10
+ "eval_samples": 11327,
11
+ "eval_samples_per_second": 20.458,
12
+ "eval_steps_per_second": 1.279
13
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.27.0.dev0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:682d6e315377557db86cd39f41c08b2f2a3761cecb5e3b5441b3f7afa4bae9ea
3
+ size 270131021
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "extra_ids": 100,
106
+ "model_max_length": 512,
107
+ "pad_token": "<pad>",
108
+ "sp_model_kwargs": {},
109
+ "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.37733912099011,
4
+ "train_runtime": 8397.5704,
5
+ "train_samples": 204017,
6
+ "train_samples_per_second": 72.884,
7
+ "train_steps_per_second": 1.139
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 9564,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 0.0001,
13
+ "loss": 2.5455,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.31,
18
+ "learning_rate": 0.0001,
19
+ "loss": 2.4773,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.47,
24
+ "learning_rate": 0.0001,
25
+ "loss": 2.4581,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.63,
30
+ "learning_rate": 0.0001,
31
+ "loss": 2.4289,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.78,
36
+ "learning_rate": 0.0001,
37
+ "loss": 2.4264,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.94,
42
+ "learning_rate": 0.0001,
43
+ "loss": 2.4111,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.1,
48
+ "learning_rate": 0.0001,
49
+ "loss": 2.3918,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.25,
54
+ "learning_rate": 0.0001,
55
+ "loss": 2.373,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.41,
60
+ "learning_rate": 0.0001,
61
+ "loss": 2.3684,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.57,
66
+ "learning_rate": 0.0001,
67
+ "loss": 2.364,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.73,
72
+ "learning_rate": 0.0001,
73
+ "loss": 2.3606,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.88,
78
+ "learning_rate": 0.0001,
79
+ "loss": 2.3512,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.04,
84
+ "learning_rate": 0.0001,
85
+ "loss": 2.3383,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.2,
90
+ "learning_rate": 0.0001,
91
+ "loss": 2.3184,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.35,
96
+ "learning_rate": 0.0001,
97
+ "loss": 2.3238,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.51,
102
+ "learning_rate": 0.0001,
103
+ "loss": 2.3079,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.67,
108
+ "learning_rate": 0.0001,
109
+ "loss": 2.3105,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 2.82,
114
+ "learning_rate": 0.0001,
115
+ "loss": 2.3148,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 2.98,
120
+ "learning_rate": 0.0001,
121
+ "loss": 2.3072,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 3.0,
126
+ "step": 9564,
127
+ "total_flos": 1.916909651434537e+17,
128
+ "train_loss": 2.37733912099011,
129
+ "train_runtime": 8397.5704,
130
+ "train_samples_per_second": 72.884,
131
+ "train_steps_per_second": 1.139
132
+ }
133
+ ],
134
+ "max_steps": 9564,
135
+ "num_train_epochs": 3,
136
+ "total_flos": 1.916909651434537e+17,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b06acb0c42c995c39614ca9c1505acc13befd60ef91232c34d33675a0e2843b
3
+ size 3631