Hugging Face's logo

Heejindo
/
ArTS_large_f4

PyTorch
t5
Model card Files
xet
Community
Heejindo commited on
Commit
095a129
·
verified ·
1 Parent(s): ad73759

Upload model checkpoint

Browse files
Files changed (13) hide show
  1. config.json +60 -0
  2. generation_config.json +7 -0
  3. optimizer.pt +3 -0
  4. over_range.csv +92 -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
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:be17769fbe9096ab933159bee6e378265e6ef1d7b27368e3867a3c2a0801fa39
3
+ size 5901652619
over_range.csv ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ,overall,content,word choice,organization,sentence fluency,conventions,prompt adherence,language,narrativity,style,voice
2
+ 0,"Empty DataFrame
3
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
4
+ Index: []","Empty DataFrame
5
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
6
+ Index: []","Empty DataFrame
7
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
8
+ Index: []","Empty DataFrame
9
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
10
+ Index: []","Empty DataFrame
11
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
12
+ Index: []","Empty DataFrame
13
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
14
+ Index: []",,,,,
15
+ 1,"Empty DataFrame
16
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
17
+ Index: []","Empty DataFrame
18
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions]
19
+ Index: []"," overall content word choice organization sentence fluency conventions
20
+ 110 3.0 1.0 -1.0 -1.0 -1.0 -1.0"," overall content word choice organization sentence fluency conventions
21
+ 110 3.0 1.0 -1.0 -1.0 -1.0 -1.0"," overall content word choice organization sentence fluency conventions
22
+ 110 3.0 1.0 -1.0 -1.0 -1.0 -1.0"," overall content word choice organization sentence fluency conventions
23
+ 110 3.0 1.0 -1.0 -1.0 -1.0 -1.0",,,,,
24
+ 2,"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, prompt adherence, language, narrativity]
32
+ Index: []","Empty DataFrame
33
+ Columns: [overall, content, prompt adherence, language, narrativity]
34
+ Index: []",,
35
+ 3," overall content prompt adherence language narrativity
36
+ 106 4.0 3.0 3.0 3.0 3.0","Empty DataFrame
37
+ Columns: [overall, content, prompt adherence, language, narrativity]
38
+ Index: []",,,,,"Empty DataFrame
39
+ Columns: [overall, content, prompt adherence, language, narrativity]
40
+ Index: []","Empty DataFrame
41
+ Columns: [overall, content, prompt adherence, language, narrativity]
42
+ Index: []","Empty DataFrame
43
+ Columns: [overall, content, prompt adherence, language, narrativity]
44
+ Index: []",,
45
+ 4,"Empty DataFrame
46
+ Columns: [overall, content, prompt adherence, language, narrativity]
47
+ Index: []","Empty DataFrame
48
+ Columns: [overall, content, prompt adherence, language, narrativity]
49
+ Index: []",,,,,"Empty DataFrame
50
+ Columns: [overall, content, prompt adherence, language, narrativity]
51
+ Index: []","Empty DataFrame
52
+ Columns: [overall, content, prompt adherence, language, narrativity]
53
+ Index: []","Empty DataFrame
54
+ Columns: [overall, content, prompt adherence, language, narrativity]
55
+ Index: []",,
56
+ 5,"Empty DataFrame
57
+ Columns: [overall, content, prompt adherence, language, narrativity]
58
+ Index: []","Empty DataFrame
59
+ Columns: [overall, content, prompt adherence, language, narrativity]
60
+ Index: []",,,,,"Empty DataFrame
61
+ Columns: [overall, content, prompt adherence, language, narrativity]
62
+ Index: []","Empty DataFrame
63
+ Columns: [overall, content, prompt adherence, language, narrativity]
64
+ Index: []","Empty DataFrame
65
+ Columns: [overall, content, prompt adherence, language, narrativity]
66
+ Index: []",,
67
+ 6,"Empty DataFrame
68
+ Columns: [overall, content, organization, conventions, style]
69
+ Index: []","Empty DataFrame
70
+ Columns: [overall, content, organization, conventions, style]
71
+ Index: []",,"Empty DataFrame
72
+ Columns: [overall, content, organization, conventions, style]
73
+ Index: []",,"Empty DataFrame
74
+ Columns: [overall, content, organization, conventions, style]
75
+ Index: []",,,,"Empty DataFrame
76
+ Columns: [overall, content, organization, conventions, style]
77
+ Index: []",
78
+ 7,"Empty DataFrame
79
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
80
+ Index: []","Empty DataFrame
81
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
82
+ Index: []","Empty DataFrame
83
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
84
+ Index: []","Empty DataFrame
85
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
86
+ Index: []","Empty DataFrame
87
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
88
+ Index: []","Empty DataFrame
89
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
90
+ Index: []",,,,,"Empty DataFrame
91
+ Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
92
+ Index: []"
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0499bc876a169699f3b81bf0081165eb7c036c635953709a0691991823d8ff48
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
+ 0,0.797298956871881,0.7137625253295161,0.6834065704122201,0.6812122065822175,0.6578848678042377,0.6527434829321621,,,,,
3
+ 1,0.7268455061680047,0.7195755249491985,0.7449736148549266,0.7330831618448129,0.7318928120366812,0.7484251968503937,,,,,
4
+ 2,0.6610687022900763,0.7624512279091118,,,,,0.7698584659299518,0.7456965702640593,0.7889908256880733,,
5
+ 3,0.7790818054278942,0.7846417609158532,,,,,0.7786320228804111,0.6913864895557315,0.766142437028513,,
6
+ 4,0.7965532224272851,0.73952134645631,,,,,0.7223202570019456,0.6932361819897559,0.6822437384972393,,
7
+ 5,0.8410404624277457,0.8210061094501495,,,,,0.783171715954948,0.6818136422650554,0.7057192573187755,,
8
+ 6,0.7971992259582541,0.7729707627092524,,0.7176870071559791,,0.7060756878580148,,,,0.7096727441375112,
9
+ 7,0.7132691728859082,0.6028537455410226,0.6115437471369676,0.6409309198374584,0.6724770642201835,0.6210070384407147,,,,,0.6038338658146964
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f834e5861ff0691f9884d50027b5275493690d599f1ec9292651db47e1b6734
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca62df99abc3cbb49ed9f2419a3e714d659a10cf139cc3fd9d6b987e6cd7997
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": 0.025097770616412163,
3
+ "best_model_checkpoint": "./results_pnum/results_cvrev_pnum_f4_large_b4e15_5000/checkpoint-10000",
4
+ "epoch": 10.26694045174538,
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": 4.914946777561009e-05,
13
+ "loss": 0.5832,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.51,
18
+ "learning_rate": 4.829380155388986e-05,
19
+ "loss": 0.0339,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.77,
24
+ "learning_rate": 4.743813533216963e-05,
25
+ "loss": 0.0314,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.03,
30
+ "learning_rate": 4.65824691104494e-05,
31
+ "loss": 0.0301,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.28,
36
+ "learning_rate": 4.572680288872916e-05,
37
+ "loss": 0.0292,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.54,
42
+ "learning_rate": 4.487113666700893e-05,
43
+ "loss": 0.029,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.8,
48
+ "learning_rate": 4.40154704452887e-05,
49
+ "loss": 0.0278,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 2.05,
54
+ "learning_rate": 4.3159804223568475e-05,
55
+ "loss": 0.0273,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 2.31,
60
+ "learning_rate": 4.2304138001848244e-05,
61
+ "loss": 0.0261,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 2.57,
66
+ "learning_rate": 4.144847178012801e-05,
67
+ "loss": 0.0266,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.57,
72
+ "eval_loss": 0.025240449234843254,
73
+ "eval_runtime": 181.3134,
74
+ "eval_samples_per_second": 14.307,
75
+ "eval_steps_per_second": 3.579,
76
+ "step": 5000
77
+ },
78
+ {
79
+ "epoch": 2.82,
80
+ "learning_rate": 4.0592805558407774e-05,
81
+ "loss": 0.026,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 3.08,
86
+ "learning_rate": 3.973713933668754e-05,
87
+ "loss": 0.0265,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 3.34,
92
+ "learning_rate": 3.888147311496732e-05,
93
+ "loss": 0.0248,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 3.59,
98
+ "learning_rate": 3.8025806893247086e-05,
99
+ "loss": 0.0247,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 3.85,
104
+ "learning_rate": 3.7170140671526854e-05,
105
+ "loss": 0.0245,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 4.11,
110
+ "learning_rate": 3.631447444980662e-05,
111
+ "loss": 0.0241,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 4.36,
116
+ "learning_rate": 3.5458808228086384e-05,
117
+ "loss": 0.0226,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 4.62,
122
+ "learning_rate": 3.460314200636616e-05,
123
+ "loss": 0.0232,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 4.88,
128
+ "learning_rate": 3.374747578464593e-05,
129
+ "loss": 0.0232,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 5.13,
134
+ "learning_rate": 3.2891809562925697e-05,
135
+ "loss": 0.0215,
136
+ "step": 10000
137
+ },
138
+ {
139
+ "epoch": 5.13,
140
+ "eval_loss": 0.025097770616412163,
141
+ "eval_runtime": 120.6593,
142
+ "eval_samples_per_second": 21.499,
143
+ "eval_steps_per_second": 5.379,
144
+ "step": 10000
145
+ },
146
+ {
147
+ "epoch": 5.39,
148
+ "learning_rate": 3.2036143341205465e-05,
149
+ "loss": 0.0211,
150
+ "step": 10500
151
+ },
152
+ {
153
+ "epoch": 5.65,
154
+ "learning_rate": 3.1180477119485233e-05,
155
+ "loss": 0.0211,
156
+ "step": 11000
157
+ },
158
+ {
159
+ "epoch": 5.9,
160
+ "learning_rate": 3.0324810897765e-05,
161
+ "loss": 0.0216,
162
+ "step": 11500
163
+ },
164
+ {
165
+ "epoch": 6.16,
166
+ "learning_rate": 2.946914467604477e-05,
167
+ "loss": 0.0201,
168
+ "step": 12000
169
+ },
170
+ {
171
+ "epoch": 6.42,
172
+ "learning_rate": 2.861347845432454e-05,
173
+ "loss": 0.0197,
174
+ "step": 12500
175
+ },
176
+ {
177
+ "epoch": 6.67,
178
+ "learning_rate": 2.7757812232604307e-05,
179
+ "loss": 0.0196,
180
+ "step": 13000
181
+ },
182
+ {
183
+ "epoch": 6.93,
184
+ "learning_rate": 2.690214601088408e-05,
185
+ "loss": 0.0186,
186
+ "step": 13500
187
+ },
188
+ {
189
+ "epoch": 7.19,
190
+ "learning_rate": 2.6046479789163847e-05,
191
+ "loss": 0.0179,
192
+ "step": 14000
193
+ },
194
+ {
195
+ "epoch": 7.44,
196
+ "learning_rate": 2.5190813567443612e-05,
197
+ "loss": 0.0178,
198
+ "step": 14500
199
+ },
200
+ {
201
+ "epoch": 7.7,
202
+ "learning_rate": 2.433514734572338e-05,
203
+ "loss": 0.0178,
204
+ "step": 15000
205
+ },
206
+ {
207
+ "epoch": 7.7,
208
+ "eval_loss": 0.02974303811788559,
209
+ "eval_runtime": 120.9977,
210
+ "eval_samples_per_second": 21.438,
211
+ "eval_steps_per_second": 5.364,
212
+ "step": 15000
213
+ },
214
+ {
215
+ "epoch": 7.96,
216
+ "learning_rate": 2.347948112400315e-05,
217
+ "loss": 0.0174,
218
+ "step": 15500
219
+ },
220
+ {
221
+ "epoch": 8.21,
222
+ "learning_rate": 2.2623814902282918e-05,
223
+ "loss": 0.0159,
224
+ "step": 16000
225
+ },
226
+ {
227
+ "epoch": 8.47,
228
+ "learning_rate": 2.1768148680562686e-05,
229
+ "loss": 0.016,
230
+ "step": 16500
231
+ },
232
+ {
233
+ "epoch": 8.73,
234
+ "learning_rate": 2.0912482458842455e-05,
235
+ "loss": 0.0158,
236
+ "step": 17000
237
+ },
238
+ {
239
+ "epoch": 8.98,
240
+ "learning_rate": 2.0056816237122226e-05,
241
+ "loss": 0.0163,
242
+ "step": 17500
243
+ },
244
+ {
245
+ "epoch": 9.24,
246
+ "learning_rate": 1.920115001540199e-05,
247
+ "loss": 0.014,
248
+ "step": 18000
249
+ },
250
+ {
251
+ "epoch": 9.5,
252
+ "learning_rate": 1.834548379368176e-05,
253
+ "loss": 0.0143,
254
+ "step": 18500
255
+ },
256
+ {
257
+ "epoch": 9.75,
258
+ "learning_rate": 1.748981757196153e-05,
259
+ "loss": 0.0149,
260
+ "step": 19000
261
+ },
262
+ {
263
+ "epoch": 10.01,
264
+ "learning_rate": 1.6634151350241297e-05,
265
+ "loss": 0.0142,
266
+ "step": 19500
267
+ },
268
+ {
269
+ "epoch": 10.27,
270
+ "learning_rate": 1.577848512852107e-05,
271
+ "loss": 0.0128,
272
+ "step": 20000
273
+ },
274
+ {
275
+ "epoch": 10.27,
276
+ "eval_loss": 0.03699657693505287,
277
+ "eval_runtime": 120.8215,
278
+ "eval_samples_per_second": 21.47,
279
+ "eval_steps_per_second": 5.372,
280
+ "step": 20000
281
+ }
282
+ ],
283
+ "max_steps": 29220,
284
+ "num_train_epochs": 15,
285
+ "total_flos": 1.7313883226112e+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:feb2f7a530b7e4051cf7b8645c71bd7d775f151e51b0fefffdee0be55ef1d05a
3
+ size 4091