Hugging Face's logo

Heejindo
/
ArTS_large_f0

PyTorch
t5
Model card Files
xet
Community
Heejindo commited on
Commit
90d1440
·
verified ·
1 Parent(s): a470e68

Upload model checkpoint

Browse files
Files changed (14) hide show
  1. config.json +60 -0
  2. generation_config.json +7 -0
  3. optimizer.pt +3 -0
  4. over_range.csv +96 -0
  5. pytorch_model.bin +3 -0
  6. qwk_results.csv +9 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. special_tokens_map.json +107 -0
  10. spiece.model +3 -0
  11. tokenizer_config.json +113 -0
  12. trainer_state.json +288 -0
  13. training_args.bin +3 -0
  14. val_qwk_results.csv +9 -0
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-large",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 4096,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
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
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.31.0",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
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": "4.31.0"
7
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bab8d8461021b7c3423564827156d4e93db754ca5d5f91bff854d69faab5ef2
3
+ size 5901652619
over_range.csv ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ,1,2,3,4,5,6,7,8
2
+ overall,"Empty DataFrame
3
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
4
+ Index: []"," overall content word choice organization sentence fluency conventions
5
+ 66 0.0 1.0 1.0 1.0 1.0 1.0","Empty DataFrame
6
+ Columns: [overall, content, prompt adherence, language, narrativity]
7
+ Index: []","Empty DataFrame
8
+ Columns: [overall, content, prompt adherence, language, narrativity]
9
+ Index: []","Empty DataFrame
10
+ Columns: [overall, content, prompt adherence, language, narrativity]
11
+ Index: []","Empty DataFrame
12
+ Columns: [overall, content, prompt adherence, language, narrativity]
13
+ Index: []","Empty DataFrame
14
+ Columns: [overall, content, organization, conventions, style]
15
+ Index: []","Empty DataFrame
16
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
17
+ Index: []"
18
+ content,"Empty DataFrame
19
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
20
+ Index: []","Empty DataFrame
21
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
22
+ Index: []","Empty DataFrame
23
+ Columns: [overall, content, prompt adherence, language, narrativity]
24
+ Index: []","Empty DataFrame
25
+ Columns: [overall, content, prompt adherence, language, narrativity]
26
+ Index: []","Empty DataFrame
27
+ Columns: [overall, content, prompt adherence, language, narrativity]
28
+ Index: []","Empty DataFrame
29
+ Columns: [overall, content, prompt adherence, language, narrativity]
30
+ Index: []","Empty DataFrame
31
+ Columns: [overall, content, organization, conventions, style]
32
+ Index: []","Empty DataFrame
33
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
34
+ Index: []"
35
+ word choice,"Empty DataFrame
36
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
37
+ Index: []","Empty DataFrame
38
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
39
+ Index: []",,,,,,"Empty DataFrame
40
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
41
+ Index: []"
42
+ organization,"Empty DataFrame
43
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
44
+ Index: []","Empty DataFrame
45
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
46
+ Index: []",,,,,"Empty DataFrame
47
+ Columns: [overall, content, organization, conventions, style]
48
+ Index: []","Empty DataFrame
49
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
50
+ Index: []"
51
+ sentence fluency,"Empty DataFrame
52
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
53
+ Index: []","Empty DataFrame
54
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
55
+ Index: []",,,,,,"Empty DataFrame
56
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
57
+ Index: []"
58
+ conventions,"Empty DataFrame
59
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
60
+ Index: []","Empty DataFrame
61
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
62
+ Index: []",,,,,"Empty DataFrame
63
+ Columns: [overall, content, organization, conventions, style]
64
+ Index: []","Empty DataFrame
65
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
66
+ Index: []"
67
+ prompt adherence,,," overall content prompt adherence language narrativity
68
+ 115 1.0 1.0 -1.0 -1.0 -1.0","Empty DataFrame
69
+ Columns: [overall, content, prompt adherence, language, narrativity]
70
+ Index: []","Empty DataFrame
71
+ Columns: [overall, content, prompt adherence, language, narrativity]
72
+ Index: []","Empty DataFrame
73
+ Columns: [overall, content, prompt adherence, language, narrativity]
74
+ Index: []",,
75
+ language,,," overall content prompt adherence language narrativity
76
+ 115 1.0 1.0 -1.0 -1.0 -1.0","Empty DataFrame
77
+ Columns: [overall, content, prompt adherence, language, narrativity]
78
+ Index: []","Empty DataFrame
79
+ Columns: [overall, content, prompt adherence, language, narrativity]
80
+ Index: []","Empty DataFrame
81
+ Columns: [overall, content, prompt adherence, language, narrativity]
82
+ Index: []",,
83
+ narrativity,,," overall content prompt adherence language narrativity
84
+ 115 1.0 1.0 -1.0 -1.0 -1.0","Empty DataFrame
85
+ Columns: [overall, content, prompt adherence, language, narrativity]
86
+ Index: []","Empty DataFrame
87
+ Columns: [overall, content, prompt adherence, language, narrativity]
88
+ Index: []","Empty DataFrame
89
+ Columns: [overall, content, prompt adherence, language, narrativity]
90
+ Index: []",,
91
+ style,,,,,,,"Empty DataFrame
92
+ Columns: [overall, content, organization, conventions, style]
93
+ Index: []",
94
+ voice,,,,,,,,"Empty DataFrame
95
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
96
+ Index: []"
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93d96763857dc803824f12bc849ae85cf9a0863d97b137838cfc618ce7621b91
3
+ size 2950848513
qwk_results.csv ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ,overall,content,word choice,organization,sentence fluency,conventions,prompt adherence,language,narrativity,style,voice
2
+ 0,0.762017528453995,0.7040814222500815,0.698338786810974,0.6920348892935877,0.7158248410296282,0.699753237031081,,,,,
3
+ 1,0.6796959826275788,0.7023872121148387,0.7534737785746302,0.7050877982890589,0.7195001348557044,0.7239225484072455,,,,,
4
+ 2,0.6773031757018337,0.7510453924523186,,,,,0.7725945474066567,0.7566628528241679,0.7637861902518294,,
5
+ 3,0.8170103092783505,0.8133928814786838,,,,,0.805538562420782,0.7494757641745302,0.7942617583525887,,
6
+ 4,0.8249060264338547,0.755121046398884,,,,,0.7558764069210424,0.7255721359602518,0.6839199638713007,,
7
+ 5,0.8432080357843522,0.8403504326105057,,,,,0.8098342841619125,0.7096071630233121,0.7209302325581395,,
8
+ 6,0.7873428244630581,0.7449238090104796,,0.6997189622420568,,0.6795415292824619,,,,0.7347815383570597,
9
+ 7,0.7096219685140885,0.606111078063966,0.6113417774741157,0.6158375036797175,0.6257197696737046,0.6862908258789266,,,,,0.6345346009285873
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8a021fe5e9c45df1c7239cdac4fda916f78b93d8fc4801c3f4818ddf6d8a2f
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5d548c4baf38fd8f3941ccf1c8825ee3ed0f8924f7ade462b4519d2ac25ba9
3
+ size 627
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
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "legacy": true,
108
+ "model_max_length": 512,
109
+ "pad_token": "<pad>",
110
+ "sp_model_kwargs": {},
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
trainer_state.json ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.024844545871019363,
3
+ "best_model_checkpoint": "./results_pnum/results_cvrev_pnum_f0_large_b4e15_5000/checkpoint-10000",
4
+ "epoch": 10.277492291880781,
5
+ "global_step": 20000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.26,
12
+ "learning_rate": 4.91485935519238e-05,
13
+ "loss": 0.5437,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.51,
18
+ "learning_rate": 4.829204782951314e-05,
19
+ "loss": 0.0334,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.77,
24
+ "learning_rate": 4.743550210710248e-05,
25
+ "loss": 0.0315,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.03,
30
+ "learning_rate": 4.657895638469182e-05,
31
+ "loss": 0.0313,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.28,
36
+ "learning_rate": 4.572241066228116e-05,
37
+ "loss": 0.0295,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.54,
42
+ "learning_rate": 4.48658649398705e-05,
43
+ "loss": 0.0284,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.8,
48
+ "learning_rate": 4.400931921745983e-05,
49
+ "loss": 0.0283,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 2.06,
54
+ "learning_rate": 4.315277349504917e-05,
55
+ "loss": 0.0268,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 2.31,
60
+ "learning_rate": 4.229622777263851e-05,
61
+ "loss": 0.0267,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 2.57,
66
+ "learning_rate": 4.143968205022784e-05,
67
+ "loss": 0.0263,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.57,
72
+ "eval_loss": 0.02492157183587551,
73
+ "eval_runtime": 103.3756,
74
+ "eval_samples_per_second": 25.083,
75
+ "eval_steps_per_second": 6.278,
76
+ "step": 5000
77
+ },
78
+ {
79
+ "epoch": 2.83,
80
+ "learning_rate": 4.058313632781718e-05,
81
+ "loss": 0.0262,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 3.08,
86
+ "learning_rate": 3.972659060540652e-05,
87
+ "loss": 0.0252,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 3.34,
92
+ "learning_rate": 3.887004488299585e-05,
93
+ "loss": 0.0247,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 3.6,
98
+ "learning_rate": 3.801349916058519e-05,
99
+ "loss": 0.0251,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 3.85,
104
+ "learning_rate": 3.715695343817453e-05,
105
+ "loss": 0.0244,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 4.11,
110
+ "learning_rate": 3.630040771576387e-05,
111
+ "loss": 0.0239,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 4.37,
116
+ "learning_rate": 3.544386199335321e-05,
117
+ "loss": 0.0233,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 4.62,
122
+ "learning_rate": 3.458731627094255e-05,
123
+ "loss": 0.0229,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 4.88,
128
+ "learning_rate": 3.373077054853188e-05,
129
+ "loss": 0.0232,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 5.14,
134
+ "learning_rate": 3.287422482612122e-05,
135
+ "loss": 0.0226,
136
+ "step": 10000
137
+ },
138
+ {
139
+ "epoch": 5.14,
140
+ "eval_loss": 0.024844545871019363,
141
+ "eval_runtime": 103.4165,
142
+ "eval_samples_per_second": 25.073,
143
+ "eval_steps_per_second": 6.276,
144
+ "step": 10000
145
+ },
146
+ {
147
+ "epoch": 5.4,
148
+ "learning_rate": 3.201767910371056e-05,
149
+ "loss": 0.0216,
150
+ "step": 10500
151
+ },
152
+ {
153
+ "epoch": 5.65,
154
+ "learning_rate": 3.11611333812999e-05,
155
+ "loss": 0.0219,
156
+ "step": 11000
157
+ },
158
+ {
159
+ "epoch": 5.91,
160
+ "learning_rate": 3.0304587658889232e-05,
161
+ "loss": 0.0213,
162
+ "step": 11500
163
+ },
164
+ {
165
+ "epoch": 6.17,
166
+ "learning_rate": 2.944804193647857e-05,
167
+ "loss": 0.0203,
168
+ "step": 12000
169
+ },
170
+ {
171
+ "epoch": 6.42,
172
+ "learning_rate": 2.8591496214067907e-05,
173
+ "loss": 0.0204,
174
+ "step": 12500
175
+ },
176
+ {
177
+ "epoch": 6.68,
178
+ "learning_rate": 2.7734950491657246e-05,
179
+ "loss": 0.0205,
180
+ "step": 13000
181
+ },
182
+ {
183
+ "epoch": 6.94,
184
+ "learning_rate": 2.6878404769246586e-05,
185
+ "loss": 0.02,
186
+ "step": 13500
187
+ },
188
+ {
189
+ "epoch": 7.19,
190
+ "learning_rate": 2.602185904683592e-05,
191
+ "loss": 0.0186,
192
+ "step": 14000
193
+ },
194
+ {
195
+ "epoch": 7.45,
196
+ "learning_rate": 2.516531332442526e-05,
197
+ "loss": 0.0181,
198
+ "step": 14500
199
+ },
200
+ {
201
+ "epoch": 7.71,
202
+ "learning_rate": 2.4308767602014596e-05,
203
+ "loss": 0.0181,
204
+ "step": 15000
205
+ },
206
+ {
207
+ "epoch": 7.71,
208
+ "eval_loss": 0.026644999161362648,
209
+ "eval_runtime": 103.372,
210
+ "eval_samples_per_second": 25.084,
211
+ "eval_steps_per_second": 6.278,
212
+ "step": 15000
213
+ },
214
+ {
215
+ "epoch": 7.97,
216
+ "learning_rate": 2.3452221879603932e-05,
217
+ "loss": 0.0187,
218
+ "step": 15500
219
+ },
220
+ {
221
+ "epoch": 8.22,
222
+ "learning_rate": 2.259567615719327e-05,
223
+ "loss": 0.0169,
224
+ "step": 16000
225
+ },
226
+ {
227
+ "epoch": 8.48,
228
+ "learning_rate": 2.173913043478261e-05,
229
+ "loss": 0.0168,
230
+ "step": 16500
231
+ },
232
+ {
233
+ "epoch": 8.74,
234
+ "learning_rate": 2.0882584712371946e-05,
235
+ "loss": 0.0164,
236
+ "step": 17000
237
+ },
238
+ {
239
+ "epoch": 8.99,
240
+ "learning_rate": 2.0026038989961285e-05,
241
+ "loss": 0.0167,
242
+ "step": 17500
243
+ },
244
+ {
245
+ "epoch": 9.25,
246
+ "learning_rate": 1.9169493267550624e-05,
247
+ "loss": 0.0152,
248
+ "step": 18000
249
+ },
250
+ {
251
+ "epoch": 9.51,
252
+ "learning_rate": 1.831294754513996e-05,
253
+ "loss": 0.0154,
254
+ "step": 18500
255
+ },
256
+ {
257
+ "epoch": 9.76,
258
+ "learning_rate": 1.74564018227293e-05,
259
+ "loss": 0.0148,
260
+ "step": 19000
261
+ },
262
+ {
263
+ "epoch": 10.02,
264
+ "learning_rate": 1.6599856100318635e-05,
265
+ "loss": 0.0147,
266
+ "step": 19500
267
+ },
268
+ {
269
+ "epoch": 10.28,
270
+ "learning_rate": 1.5743310377907974e-05,
271
+ "loss": 0.0137,
272
+ "step": 20000
273
+ },
274
+ {
275
+ "epoch": 10.28,
276
+ "eval_loss": 0.03126714006066322,
277
+ "eval_runtime": 103.3509,
278
+ "eval_samples_per_second": 25.089,
279
+ "eval_steps_per_second": 6.28,
280
+ "step": 20000
281
+ }
282
+ ],
283
+ "max_steps": 29190,
284
+ "num_train_epochs": 15,
285
+ "total_flos": 1.7320378368e+17,
286
+ "trial_name": null,
287
+ "trial_params": null
288
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e924ca6e12c90de7f603e37fe24b83222e25c0bc35fa892c8a2161efe2e4d8cc
3
+ size 4091
val_qwk_results.csv ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ,overall,content,word choice,organization,sentence fluency,conventions,prompt adherence,language,narrativity,style,voice
2
+ 0,0.7836810264693781,0.7022522253420156,0.7030532461937542,0.6967191689981316,0.6966368732010302,0.6869279068008172,,,,,
3
+ 1,0.7079704310912683,0.7293372364268398,0.757475708121165,0.7452884066247858,0.745412344962646,0.7448888359063003,,,,,
4
+ 2,0.7028068244358832,0.7643312803675506,,,,,0.7849160428055459,0.7329693049886019,0.7861501210653753,,
5
+ 3,0.78999696487533,0.8052805280528053,,,,,0.791821075525768,0.6494248495467357,0.7784994934747631,,
6
+ 4,0.7998927721134798,0.7336792747733667,,,,,0.7185071657121347,0.679982647730059,0.69577336963568,,
7
+ 5,0.842924659438421,0.8401939933612927,,,,,0.7959622703954989,0.6855731739017417,0.6884383666443532,,
8
+ 6,0.7973402054340766,0.7847865444016662,,0.7240669997061417,,0.6835860601223729,,,,0.6896930782072686,
9
+ 7,0.7002956288093369,0.5549738219895288,0.6302359171882523,0.6160373686259246,0.6967457384670402,0.6179516685845798,,,,,0.5729218516674963