carrie
commited on
Commit
•
b315137
1
Parent(s):
36d072a
add model files
Browse files- config.json +57 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +511 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 24,
|
19 |
+
"num_heads": 16,
|
20 |
+
"num_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"task_specific_params": {
|
25 |
+
"summarization": {
|
26 |
+
"early_stopping": true,
|
27 |
+
"length_penalty": 2.0,
|
28 |
+
"max_length": 200,
|
29 |
+
"min_length": 30,
|
30 |
+
"no_repeat_ngram_size": 3,
|
31 |
+
"num_beams": 4,
|
32 |
+
"prefix": "summarize: "
|
33 |
+
},
|
34 |
+
"translation_en_to_de": {
|
35 |
+
"early_stopping": true,
|
36 |
+
"max_length": 300,
|
37 |
+
"num_beams": 4,
|
38 |
+
"prefix": "translate English to German: "
|
39 |
+
},
|
40 |
+
"translation_en_to_fr": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"max_length": 300,
|
43 |
+
"num_beams": 4,
|
44 |
+
"prefix": "translate English to French: "
|
45 |
+
},
|
46 |
+
"translation_en_to_ro": {
|
47 |
+
"early_stopping": true,
|
48 |
+
"max_length": 300,
|
49 |
+
"num_beams": 4,
|
50 |
+
"prefix": "translate English to Romanian: "
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.11.3",
|
55 |
+
"use_cache": true,
|
56 |
+
"vocab_size": 32100
|
57 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c20aa45fecd1a64f4230b2d340ae2815f05dbc54de2472af4286e8ecc5733bb3
|
3 |
+
size 2950790023
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-large", "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,511 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6115376353591917,
|
3 |
+
"best_model_checkpoint": "/data2/fxu/lfqa_discourse/t5_large_finetuning_eli5_only_888/checkpoint-504",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"global_step": 540,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_Answer": 0.0,
|
13 |
+
"eval_Answer(Summary)": 0.44135188866799197,
|
14 |
+
"eval_Answer-Example": 0.0,
|
15 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
16 |
+
"eval_AuxiliaryInformation": 0.0,
|
17 |
+
"eval_Miscellaneous": 0.0,
|
18 |
+
"eval_accuracy": 0.26811594202898553,
|
19 |
+
"eval_loss": 0.27198654413223267,
|
20 |
+
"eval_macro_f1": 0.07355864811133199,
|
21 |
+
"eval_runtime": 13.2965,
|
22 |
+
"eval_samples_per_second": 4.663,
|
23 |
+
"eval_steps_per_second": 0.301,
|
24 |
+
"step": 18
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_Answer": 0.4731707317073171,
|
29 |
+
"eval_Answer(Summary)": 0.4433497536945813,
|
30 |
+
"eval_Answer-Example": 0.0,
|
31 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
32 |
+
"eval_AuxiliaryInformation": 0.0,
|
33 |
+
"eval_Miscellaneous": 0.6,
|
34 |
+
"eval_accuracy": 0.4082125603864734,
|
35 |
+
"eval_loss": 0.18863672018051147,
|
36 |
+
"eval_macro_f1": 0.2527534142336497,
|
37 |
+
"eval_runtime": 10.164,
|
38 |
+
"eval_samples_per_second": 6.1,
|
39 |
+
"eval_steps_per_second": 0.394,
|
40 |
+
"step": 36
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.0,
|
44 |
+
"eval_Answer": 0.375,
|
45 |
+
"eval_Answer(Summary)": 0.49720670391061456,
|
46 |
+
"eval_Answer-Example": 0.15384615384615388,
|
47 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
48 |
+
"eval_AuxiliaryInformation": 0.0,
|
49 |
+
"eval_Miscellaneous": 0.6923076923076923,
|
50 |
+
"eval_accuracy": 0.4082125603864734,
|
51 |
+
"eval_loss": 0.17385143041610718,
|
52 |
+
"eval_macro_f1": 0.28639342501074344,
|
53 |
+
"eval_runtime": 12.0287,
|
54 |
+
"eval_samples_per_second": 5.154,
|
55 |
+
"eval_steps_per_second": 0.333,
|
56 |
+
"step": 54
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_Answer": 0.4250871080139373,
|
61 |
+
"eval_Answer(Summary)": 0.4433962264150943,
|
62 |
+
"eval_Answer-Example": 0.5189189189189188,
|
63 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
64 |
+
"eval_AuxiliaryInformation": 0.0,
|
65 |
+
"eval_Miscellaneous": 0.6842105263157895,
|
66 |
+
"eval_accuracy": 0.4396135265700483,
|
67 |
+
"eval_loss": 0.1758367419242859,
|
68 |
+
"eval_macro_f1": 0.3452687966106233,
|
69 |
+
"eval_runtime": 11.2352,
|
70 |
+
"eval_samples_per_second": 5.518,
|
71 |
+
"eval_steps_per_second": 0.356,
|
72 |
+
"step": 72
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 5.0,
|
76 |
+
"eval_Answer": 0.43205574912891986,
|
77 |
+
"eval_Answer(Summary)": 0.4,
|
78 |
+
"eval_Answer-Example": 0.5072463768115941,
|
79 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
80 |
+
"eval_AuxiliaryInformation": 0.2797202797202797,
|
81 |
+
"eval_Miscellaneous": 0.765432098765432,
|
82 |
+
"eval_accuracy": 0.4420289855072464,
|
83 |
+
"eval_loss": 0.1732899248600006,
|
84 |
+
"eval_macro_f1": 0.3974090840710376,
|
85 |
+
"eval_runtime": 11.2192,
|
86 |
+
"eval_samples_per_second": 5.526,
|
87 |
+
"eval_steps_per_second": 0.357,
|
88 |
+
"step": 90
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.0,
|
92 |
+
"eval_Answer": 0.475609756097561,
|
93 |
+
"eval_Answer(Summary)": 0.4120603015075377,
|
94 |
+
"eval_Answer-Example": 0.5222929936305732,
|
95 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
96 |
+
"eval_AuxiliaryInformation": 0.02985074626865672,
|
97 |
+
"eval_Miscellaneous": 0.7123287671232877,
|
98 |
+
"eval_accuracy": 0.45169082125603865,
|
99 |
+
"eval_loss": 0.16830046474933624,
|
100 |
+
"eval_macro_f1": 0.3586904274379361,
|
101 |
+
"eval_runtime": 11.055,
|
102 |
+
"eval_samples_per_second": 5.608,
|
103 |
+
"eval_steps_per_second": 0.362,
|
104 |
+
"step": 108
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_Answer": 0.4397163120567376,
|
109 |
+
"eval_Answer(Summary)": 0.5263157894736842,
|
110 |
+
"eval_Answer-Example": 0.6206896551724138,
|
111 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
112 |
+
"eval_AuxiliaryInformation": 0.25999999999999995,
|
113 |
+
"eval_Miscellaneous": 0.6732673267326732,
|
114 |
+
"eval_accuracy": 0.49516908212560384,
|
115 |
+
"eval_loss": 0.15517334640026093,
|
116 |
+
"eval_macro_f1": 0.41999818057258476,
|
117 |
+
"eval_runtime": 11.346,
|
118 |
+
"eval_samples_per_second": 5.464,
|
119 |
+
"eval_steps_per_second": 0.353,
|
120 |
+
"step": 126
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 8.0,
|
124 |
+
"eval_Answer": 0.4920127795527157,
|
125 |
+
"eval_Answer(Summary)": 0.5025641025641026,
|
126 |
+
"eval_Answer-Example": 0.6495726495726496,
|
127 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
128 |
+
"eval_AuxiliaryInformation": 0.32786885245901637,
|
129 |
+
"eval_Miscellaneous": 0.7272727272727273,
|
130 |
+
"eval_accuracy": 0.5120772946859904,
|
131 |
+
"eval_loss": 0.1799505650997162,
|
132 |
+
"eval_macro_f1": 0.44988185190353525,
|
133 |
+
"eval_runtime": 10.9313,
|
134 |
+
"eval_samples_per_second": 5.672,
|
135 |
+
"eval_steps_per_second": 0.366,
|
136 |
+
"step": 144
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 9.0,
|
140 |
+
"eval_Answer": 0.5092024539877301,
|
141 |
+
"eval_Answer(Summary)": 0.5235602094240838,
|
142 |
+
"eval_Answer-Example": 0.5636363636363636,
|
143 |
+
"eval_Answer-Organizationalsentence": 0.2857142857142857,
|
144 |
+
"eval_AuxiliaryInformation": 0.22033898305084745,
|
145 |
+
"eval_Miscellaneous": 0.736842105263158,
|
146 |
+
"eval_accuracy": 0.4975845410628019,
|
147 |
+
"eval_loss": 0.18231035768985748,
|
148 |
+
"eval_macro_f1": 0.47321573351274476,
|
149 |
+
"eval_runtime": 10.9336,
|
150 |
+
"eval_samples_per_second": 5.671,
|
151 |
+
"eval_steps_per_second": 0.366,
|
152 |
+
"step": 162
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 10.0,
|
156 |
+
"eval_Answer": 0.42704626334519574,
|
157 |
+
"eval_Answer(Summary)": 0.6071428571428571,
|
158 |
+
"eval_Answer-Example": 0.5161290322580646,
|
159 |
+
"eval_Answer-Organizationalsentence": 0.4,
|
160 |
+
"eval_AuxiliaryInformation": 0.33333333333333337,
|
161 |
+
"eval_Miscellaneous": 0.765432098765432,
|
162 |
+
"eval_accuracy": 0.5024154589371981,
|
163 |
+
"eval_loss": 0.20293939113616943,
|
164 |
+
"eval_macro_f1": 0.5081805974741471,
|
165 |
+
"eval_runtime": 11.8591,
|
166 |
+
"eval_samples_per_second": 5.228,
|
167 |
+
"eval_steps_per_second": 0.337,
|
168 |
+
"step": 180
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 11.0,
|
172 |
+
"eval_Answer": 0.46583850931677023,
|
173 |
+
"eval_Answer(Summary)": 0.5294117647058824,
|
174 |
+
"eval_Answer-Example": 0.6153846153846154,
|
175 |
+
"eval_Answer-Organizationalsentence": 0.4,
|
176 |
+
"eval_AuxiliaryInformation": 0.28571428571428575,
|
177 |
+
"eval_Miscellaneous": 0.7297297297297297,
|
178 |
+
"eval_accuracy": 0.4975845410628019,
|
179 |
+
"eval_loss": 0.20877273380756378,
|
180 |
+
"eval_macro_f1": 0.5043464841418805,
|
181 |
+
"eval_runtime": 10.9599,
|
182 |
+
"eval_samples_per_second": 5.657,
|
183 |
+
"eval_steps_per_second": 0.365,
|
184 |
+
"step": 198
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 12.0,
|
188 |
+
"eval_Answer": 0.42909090909090913,
|
189 |
+
"eval_Answer(Summary)": 0.5714285714285714,
|
190 |
+
"eval_Answer-Example": 0.6611570247933884,
|
191 |
+
"eval_Answer-Organizationalsentence": 0.0,
|
192 |
+
"eval_AuxiliaryInformation": 0.3364485981308411,
|
193 |
+
"eval_Miscellaneous": 0.736842105263158,
|
194 |
+
"eval_accuracy": 0.5193236714975845,
|
195 |
+
"eval_loss": 0.22424167394638062,
|
196 |
+
"eval_macro_f1": 0.45582786811781134,
|
197 |
+
"eval_runtime": 11.5376,
|
198 |
+
"eval_samples_per_second": 5.374,
|
199 |
+
"eval_steps_per_second": 0.347,
|
200 |
+
"step": 216
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 13.0,
|
204 |
+
"eval_Answer": 0.4677966101694915,
|
205 |
+
"eval_Answer(Summary)": 0.5739910313901346,
|
206 |
+
"eval_Answer-Example": 0.6721311475409836,
|
207 |
+
"eval_Answer-Organizationalsentence": 0.4,
|
208 |
+
"eval_AuxiliaryInformation": 0.31067961165048547,
|
209 |
+
"eval_Miscellaneous": 0.7749999999999999,
|
210 |
+
"eval_accuracy": 0.5362318840579711,
|
211 |
+
"eval_loss": 0.23804587125778198,
|
212 |
+
"eval_macro_f1": 0.5332664001251824,
|
213 |
+
"eval_runtime": 10.943,
|
214 |
+
"eval_samples_per_second": 5.666,
|
215 |
+
"eval_steps_per_second": 0.366,
|
216 |
+
"step": 234
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 14.0,
|
220 |
+
"eval_Answer": 0.4834437086092715,
|
221 |
+
"eval_Answer(Summary)": 0.5517241379310346,
|
222 |
+
"eval_Answer-Example": 0.6666666666666667,
|
223 |
+
"eval_Answer-Organizationalsentence": 0.5,
|
224 |
+
"eval_AuxiliaryInformation": 0.3709677419354839,
|
225 |
+
"eval_Miscellaneous": 0.75,
|
226 |
+
"eval_accuracy": 0.5314009661835749,
|
227 |
+
"eval_loss": 0.2845667898654938,
|
228 |
+
"eval_macro_f1": 0.5538003758570761,
|
229 |
+
"eval_runtime": 11.0141,
|
230 |
+
"eval_samples_per_second": 5.629,
|
231 |
+
"eval_steps_per_second": 0.363,
|
232 |
+
"step": 252
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 15.0,
|
236 |
+
"eval_Answer": 0.5100671140939598,
|
237 |
+
"eval_Answer(Summary)": 0.5714285714285714,
|
238 |
+
"eval_Answer-Example": 0.6464646464646465,
|
239 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
240 |
+
"eval_AuxiliaryInformation": 0.4153846153846154,
|
241 |
+
"eval_Miscellaneous": 0.7126436781609196,
|
242 |
+
"eval_accuracy": 0.5483091787439613,
|
243 |
+
"eval_loss": 0.2950053811073303,
|
244 |
+
"eval_macro_f1": 0.5871092153665631,
|
245 |
+
"eval_runtime": 11.553,
|
246 |
+
"eval_samples_per_second": 5.367,
|
247 |
+
"eval_steps_per_second": 0.346,
|
248 |
+
"step": 270
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 16.0,
|
252 |
+
"eval_Answer": 0.45637583892617456,
|
253 |
+
"eval_Answer(Summary)": 0.5945945945945946,
|
254 |
+
"eval_Answer-Example": 0.607843137254902,
|
255 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
256 |
+
"eval_AuxiliaryInformation": 0.38333333333333336,
|
257 |
+
"eval_Miscellaneous": 0.7848101265822784,
|
258 |
+
"eval_accuracy": 0.5314009661835749,
|
259 |
+
"eval_loss": 0.28483256697654724,
|
260 |
+
"eval_macro_f1": 0.5822706162263249,
|
261 |
+
"eval_runtime": 10.9374,
|
262 |
+
"eval_samples_per_second": 5.669,
|
263 |
+
"eval_steps_per_second": 0.366,
|
264 |
+
"step": 288
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 17.0,
|
268 |
+
"eval_Answer": 0.4557823129251701,
|
269 |
+
"eval_Answer(Summary)": 0.5952380952380952,
|
270 |
+
"eval_Answer-Example": 0.6923076923076923,
|
271 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
272 |
+
"eval_AuxiliaryInformation": 0.3125,
|
273 |
+
"eval_Miscellaneous": 0.7848101265822784,
|
274 |
+
"eval_accuracy": 0.5434782608695652,
|
275 |
+
"eval_loss": 0.29017218947410583,
|
276 |
+
"eval_macro_f1": 0.5845508156199838,
|
277 |
+
"eval_runtime": 11.3062,
|
278 |
+
"eval_samples_per_second": 5.484,
|
279 |
+
"eval_steps_per_second": 0.354,
|
280 |
+
"step": 306
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 18.0,
|
284 |
+
"eval_Answer": 0.4621212121212122,
|
285 |
+
"eval_Answer(Summary)": 0.5844748858447489,
|
286 |
+
"eval_Answer-Example": 0.6611570247933884,
|
287 |
+
"eval_Answer-Organizationalsentence": 0.33333333333333337,
|
288 |
+
"eval_AuxiliaryInformation": 0.43283582089552236,
|
289 |
+
"eval_Miscellaneous": 0.7380952380952381,
|
290 |
+
"eval_accuracy": 0.5458937198067633,
|
291 |
+
"eval_loss": 0.3154158294200897,
|
292 |
+
"eval_macro_f1": 0.5353362525139073,
|
293 |
+
"eval_runtime": 11.5419,
|
294 |
+
"eval_samples_per_second": 5.372,
|
295 |
+
"eval_steps_per_second": 0.347,
|
296 |
+
"step": 324
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 19.0,
|
300 |
+
"eval_Answer": 0.46905537459283386,
|
301 |
+
"eval_Answer(Summary)": 0.5526315789473685,
|
302 |
+
"eval_Answer-Example": 0.6315789473684211,
|
303 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
304 |
+
"eval_AuxiliaryInformation": 0.38775510204081637,
|
305 |
+
"eval_Miscellaneous": 0.7692307692307693,
|
306 |
+
"eval_accuracy": 0.533816425120773,
|
307 |
+
"eval_loss": 0.3426768183708191,
|
308 |
+
"eval_macro_f1": 0.5794864064744794,
|
309 |
+
"eval_runtime": 11.3895,
|
310 |
+
"eval_samples_per_second": 5.444,
|
311 |
+
"eval_steps_per_second": 0.351,
|
312 |
+
"step": 342
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 20.0,
|
316 |
+
"eval_Answer": 0.5089820359281436,
|
317 |
+
"eval_Answer(Summary)": 0.5700934579439253,
|
318 |
+
"eval_Answer-Example": 0.45161290322580644,
|
319 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
320 |
+
"eval_AuxiliaryInformation": 0.3921568627450981,
|
321 |
+
"eval_Miscellaneous": 0.765432098765432,
|
322 |
+
"eval_accuracy": 0.5289855072463768,
|
323 |
+
"eval_loss": 0.3493908941745758,
|
324 |
+
"eval_macro_f1": 0.5591573375458453,
|
325 |
+
"eval_runtime": 11.3644,
|
326 |
+
"eval_samples_per_second": 5.456,
|
327 |
+
"eval_steps_per_second": 0.352,
|
328 |
+
"step": 360
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 21.0,
|
332 |
+
"eval_Answer": 0.4316546762589928,
|
333 |
+
"eval_Answer(Summary)": 0.5701754385964912,
|
334 |
+
"eval_Answer-Example": 0.6666666666666667,
|
335 |
+
"eval_Answer-Organizationalsentence": 0.5,
|
336 |
+
"eval_AuxiliaryInformation": 0.4,
|
337 |
+
"eval_Miscellaneous": 0.7749999999999999,
|
338 |
+
"eval_accuracy": 0.5265700483091788,
|
339 |
+
"eval_loss": 0.34431466460227966,
|
340 |
+
"eval_macro_f1": 0.5572494635870251,
|
341 |
+
"eval_runtime": 11.6127,
|
342 |
+
"eval_samples_per_second": 5.339,
|
343 |
+
"eval_steps_per_second": 0.344,
|
344 |
+
"step": 378
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 22.0,
|
348 |
+
"eval_Answer": 0.4968944099378882,
|
349 |
+
"eval_Answer(Summary)": 0.5909090909090909,
|
350 |
+
"eval_Answer-Example": 0.4597701149425288,
|
351 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
352 |
+
"eval_AuxiliaryInformation": 0.4000000000000001,
|
353 |
+
"eval_Miscellaneous": 0.7749999999999999,
|
354 |
+
"eval_accuracy": 0.5314009661835749,
|
355 |
+
"eval_loss": 0.3664790987968445,
|
356 |
+
"eval_macro_f1": 0.5648733804093624,
|
357 |
+
"eval_runtime": 11.1595,
|
358 |
+
"eval_samples_per_second": 5.556,
|
359 |
+
"eval_steps_per_second": 0.358,
|
360 |
+
"step": 396
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 23.0,
|
364 |
+
"eval_Answer": 0.48965517241379314,
|
365 |
+
"eval_Answer(Summary)": 0.6079295154185023,
|
366 |
+
"eval_Answer-Example": 0.6666666666666667,
|
367 |
+
"eval_Answer-Organizationalsentence": 0.5,
|
368 |
+
"eval_AuxiliaryInformation": 0.416,
|
369 |
+
"eval_Miscellaneous": 0.7749999999999999,
|
370 |
+
"eval_accuracy": 0.5603864734299517,
|
371 |
+
"eval_loss": 0.36973538994789124,
|
372 |
+
"eval_macro_f1": 0.575875225749827,
|
373 |
+
"eval_runtime": 11.3197,
|
374 |
+
"eval_samples_per_second": 5.477,
|
375 |
+
"eval_steps_per_second": 0.353,
|
376 |
+
"step": 414
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 24.0,
|
380 |
+
"eval_Answer": 0.4774193548387097,
|
381 |
+
"eval_Answer(Summary)": 0.5833333333333334,
|
382 |
+
"eval_Answer-Example": 0.5217391304347826,
|
383 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
384 |
+
"eval_AuxiliaryInformation": 0.40944881889763785,
|
385 |
+
"eval_Miscellaneous": 0.759493670886076,
|
386 |
+
"eval_accuracy": 0.5265700483091788,
|
387 |
+
"eval_loss": 0.3806516230106354,
|
388 |
+
"eval_macro_f1": 0.5696834958428677,
|
389 |
+
"eval_runtime": 11.2648,
|
390 |
+
"eval_samples_per_second": 5.504,
|
391 |
+
"eval_steps_per_second": 0.355,
|
392 |
+
"step": 432
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 25.0,
|
396 |
+
"eval_Answer": 0.4871794871794871,
|
397 |
+
"eval_Answer(Summary)": 0.588785046728972,
|
398 |
+
"eval_Answer-Example": 0.5833333333333334,
|
399 |
+
"eval_Answer-Organizationalsentence": 0.5,
|
400 |
+
"eval_AuxiliaryInformation": 0.3934426229508197,
|
401 |
+
"eval_Miscellaneous": 0.759493670886076,
|
402 |
+
"eval_accuracy": 0.5362318840579711,
|
403 |
+
"eval_loss": 0.39177072048187256,
|
404 |
+
"eval_macro_f1": 0.552039026846448,
|
405 |
+
"eval_runtime": 11.3644,
|
406 |
+
"eval_samples_per_second": 5.456,
|
407 |
+
"eval_steps_per_second": 0.352,
|
408 |
+
"step": 450
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 26.0,
|
412 |
+
"eval_Answer": 0.5116279069767442,
|
413 |
+
"eval_Answer(Summary)": 0.5915492957746479,
|
414 |
+
"eval_Answer-Example": 0.7102803738317757,
|
415 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
416 |
+
"eval_AuxiliaryInformation": 0.4032258064516129,
|
417 |
+
"eval_Miscellaneous": 0.759493670886076,
|
418 |
+
"eval_accuracy": 0.5652173913043478,
|
419 |
+
"eval_loss": 0.3835026025772095,
|
420 |
+
"eval_macro_f1": 0.6071406200979206,
|
421 |
+
"eval_runtime": 11.3582,
|
422 |
+
"eval_samples_per_second": 5.459,
|
423 |
+
"eval_steps_per_second": 0.352,
|
424 |
+
"step": 468
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 27.0,
|
428 |
+
"eval_Answer": 0.5100671140939598,
|
429 |
+
"eval_Answer(Summary)": 0.609090909090909,
|
430 |
+
"eval_Answer-Example": 0.69811320754717,
|
431 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
432 |
+
"eval_AuxiliaryInformation": 0.4132231404958678,
|
433 |
+
"eval_Miscellaneous": 0.759493670886076,
|
434 |
+
"eval_accuracy": 0.5700483091787439,
|
435 |
+
"eval_loss": 0.3833402693271637,
|
436 |
+
"eval_macro_f1": 0.6094424514634416,
|
437 |
+
"eval_runtime": 11.4693,
|
438 |
+
"eval_samples_per_second": 5.406,
|
439 |
+
"eval_steps_per_second": 0.349,
|
440 |
+
"step": 486
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 27.78,
|
444 |
+
"learning_rate": 7.4074074074074075e-06,
|
445 |
+
"loss": 0.0945,
|
446 |
+
"step": 500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 28.0,
|
450 |
+
"eval_Answer": 0.5167785234899329,
|
451 |
+
"eval_Answer(Summary)": 0.5972850678733032,
|
452 |
+
"eval_Answer-Example": 0.7222222222222223,
|
453 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
454 |
+
"eval_AuxiliaryInformation": 0.4067796610169492,
|
455 |
+
"eval_Miscellaneous": 0.759493670886076,
|
456 |
+
"eval_accuracy": 0.572463768115942,
|
457 |
+
"eval_loss": 0.39141198992729187,
|
458 |
+
"eval_macro_f1": 0.6115376353591917,
|
459 |
+
"eval_runtime": 11.4624,
|
460 |
+
"eval_samples_per_second": 5.409,
|
461 |
+
"eval_steps_per_second": 0.349,
|
462 |
+
"step": 504
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 29.0,
|
466 |
+
"eval_Answer": 0.5214521452145214,
|
467 |
+
"eval_Answer(Summary)": 0.599078341013825,
|
468 |
+
"eval_Answer-Example": 0.7102803738317757,
|
469 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
470 |
+
"eval_AuxiliaryInformation": 0.4067796610169492,
|
471 |
+
"eval_Miscellaneous": 0.759493670886076,
|
472 |
+
"eval_accuracy": 0.572463768115942,
|
473 |
+
"eval_loss": 0.3956356346607208,
|
474 |
+
"eval_macro_f1": 0.610625143104969,
|
475 |
+
"eval_runtime": 11.2747,
|
476 |
+
"eval_samples_per_second": 5.499,
|
477 |
+
"eval_steps_per_second": 0.355,
|
478 |
+
"step": 522
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 30.0,
|
482 |
+
"eval_Answer": 0.5197368421052633,
|
483 |
+
"eval_Answer(Summary)": 0.5925925925925926,
|
484 |
+
"eval_Answer-Example": 0.7102803738317757,
|
485 |
+
"eval_Answer-Organizationalsentence": 0.6666666666666666,
|
486 |
+
"eval_AuxiliaryInformation": 0.4067796610169492,
|
487 |
+
"eval_Miscellaneous": 0.759493670886076,
|
488 |
+
"eval_accuracy": 0.5700483091787439,
|
489 |
+
"eval_loss": 0.39962947368621826,
|
490 |
+
"eval_macro_f1": 0.6092583011832206,
|
491 |
+
"eval_runtime": 11.3436,
|
492 |
+
"eval_samples_per_second": 5.466,
|
493 |
+
"eval_steps_per_second": 0.353,
|
494 |
+
"step": 540
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 30.0,
|
498 |
+
"step": 540,
|
499 |
+
"total_flos": 1.5886402423296e+16,
|
500 |
+
"train_loss": 0.08773032142608254,
|
501 |
+
"train_runtime": 1826.4445,
|
502 |
+
"train_samples_per_second": 4.714,
|
503 |
+
"train_steps_per_second": 0.296
|
504 |
+
}
|
505 |
+
],
|
506 |
+
"max_steps": 540,
|
507 |
+
"num_train_epochs": 30,
|
508 |
+
"total_flos": 1.5886402423296e+16,
|
509 |
+
"trial_name": null,
|
510 |
+
"trial_params": null
|
511 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7df648d0055b2c07133e57699f4fff7e73e5efd0053a82e29c47d6ab72a66349
|
3 |
+
size 3055
|