traintogpb
commited on
Commit
•
544f6c6
1
Parent(s):
f494ae5
Initial commit
Browse files- config.json +32 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +111 -0
- trainer_state.json +371 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "paust/pko-t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2816,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1024,
|
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 |
+
"max_length": 200,
|
19 |
+
"model_type": "t5",
|
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 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.28.1",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 50358
|
32 |
+
}
|
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": "4.28.1"
|
7 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffc73d4ded92ac551a0237aae2ea4309e62784e68e5f6e4a92e9f366bf7a54e3
|
3 |
+
size 6564217929
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed44940f05505ed518ac76be8354b72eca15430bf989a1def5ab4366092b44bb
|
3 |
+
size 3282133829
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09d8cf44fe84ab7a9a0fe7fccd86502547835fd9aadc017c83994c2b591ff143
|
3 |
+
size 14575
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d989e7a97f4805b47dd44d07252870f9478885309572c78cf3925221cf1f7cf3
|
3 |
+
size 557
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aea62a1668200f0f4054007d559d86535bf4d0aa590af22c8e839af833c68572
|
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": "<pad>"
|
107 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"model_max_length": 1000000000000000019884624838656,
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"tokenizer_class": "T5Tokenizer",
|
110 |
+
"unk_token": "<pad>"
|
111 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,371 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2615379807814019,
|
3 |
+
"best_model_checkpoint": "/opt/ml/final/summary/training/../summary_models/checkpoint-5000",
|
4 |
+
"epoch": 2.3741690408357075,
|
5 |
+
"global_step": 5000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 9.333333333333334e-07,
|
13 |
+
"loss": 12.8401,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.09,
|
18 |
+
"learning_rate": 1.885714285714286e-06,
|
19 |
+
"loss": 11.0877,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.14,
|
24 |
+
"learning_rate": 2.838095238095238e-06,
|
25 |
+
"loss": 7.1907,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.19,
|
30 |
+
"learning_rate": 3.7904761904761907e-06,
|
31 |
+
"loss": 3.1573,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.24,
|
36 |
+
"learning_rate": 4.723809523809524e-06,
|
37 |
+
"loss": 1.707,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.28,
|
42 |
+
"learning_rate": 5.676190476190476e-06,
|
43 |
+
"loss": 0.9049,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.33,
|
48 |
+
"learning_rate": 6.628571428571428e-06,
|
49 |
+
"loss": 0.6742,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.38,
|
54 |
+
"learning_rate": 7.580952380952381e-06,
|
55 |
+
"loss": 0.6116,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.43,
|
60 |
+
"learning_rate": 8.533333333333335e-06,
|
61 |
+
"loss": 0.5597,
|
62 |
+
"step": 900
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.47,
|
66 |
+
"learning_rate": 9.485714285714287e-06,
|
67 |
+
"loss": 0.562,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.47,
|
72 |
+
"eval_loss": 0.5062821507453918,
|
73 |
+
"eval_rouge1": 0.24465619036536226,
|
74 |
+
"eval_rouge2": 0.05823001316422367,
|
75 |
+
"eval_rougeL": 0.2441932274023993,
|
76 |
+
"eval_runtime": 37.1079,
|
77 |
+
"eval_samples_per_second": 24.577,
|
78 |
+
"eval_steps_per_second": 6.144,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.52,
|
83 |
+
"learning_rate": 9.951476793248946e-06,
|
84 |
+
"loss": 0.5549,
|
85 |
+
"step": 1100
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 0.57,
|
89 |
+
"learning_rate": 9.845991561181436e-06,
|
90 |
+
"loss": 0.5342,
|
91 |
+
"step": 1200
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.62,
|
95 |
+
"learning_rate": 9.740506329113924e-06,
|
96 |
+
"loss": 0.5304,
|
97 |
+
"step": 1300
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.66,
|
101 |
+
"learning_rate": 9.635021097046414e-06,
|
102 |
+
"loss": 0.524,
|
103 |
+
"step": 1400
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 0.71,
|
107 |
+
"learning_rate": 9.529535864978904e-06,
|
108 |
+
"loss": 0.5235,
|
109 |
+
"step": 1500
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.76,
|
113 |
+
"learning_rate": 9.424050632911394e-06,
|
114 |
+
"loss": 0.5279,
|
115 |
+
"step": 1600
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.81,
|
119 |
+
"learning_rate": 9.318565400843884e-06,
|
120 |
+
"loss": 0.5304,
|
121 |
+
"step": 1700
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.85,
|
125 |
+
"learning_rate": 9.213080168776372e-06,
|
126 |
+
"loss": 0.5124,
|
127 |
+
"step": 1800
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 0.9,
|
131 |
+
"learning_rate": 9.107594936708862e-06,
|
132 |
+
"loss": 0.5014,
|
133 |
+
"step": 1900
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.95,
|
137 |
+
"learning_rate": 9.002109704641352e-06,
|
138 |
+
"loss": 0.4888,
|
139 |
+
"step": 2000
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 0.95,
|
143 |
+
"eval_loss": 0.47751283645629883,
|
144 |
+
"eval_rouge1": 0.25892549839485435,
|
145 |
+
"eval_rouge2": 0.06567851737773929,
|
146 |
+
"eval_rougeL": 0.2580640243425909,
|
147 |
+
"eval_runtime": 37.104,
|
148 |
+
"eval_samples_per_second": 24.58,
|
149 |
+
"eval_steps_per_second": 6.145,
|
150 |
+
"step": 2000
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 1.0,
|
154 |
+
"learning_rate": 8.897679324894515e-06,
|
155 |
+
"loss": 0.5153,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.04,
|
160 |
+
"learning_rate": 8.792194092827004e-06,
|
161 |
+
"loss": 0.4908,
|
162 |
+
"step": 2200
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.09,
|
166 |
+
"learning_rate": 8.686708860759494e-06,
|
167 |
+
"loss": 0.5025,
|
168 |
+
"step": 2300
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 1.14,
|
172 |
+
"learning_rate": 8.581223628691983e-06,
|
173 |
+
"loss": 0.4811,
|
174 |
+
"step": 2400
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.19,
|
178 |
+
"learning_rate": 8.475738396624473e-06,
|
179 |
+
"loss": 0.4832,
|
180 |
+
"step": 2500
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 1.23,
|
184 |
+
"learning_rate": 8.371308016877637e-06,
|
185 |
+
"loss": 0.483,
|
186 |
+
"step": 2600
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 1.28,
|
190 |
+
"learning_rate": 8.265822784810127e-06,
|
191 |
+
"loss": 0.5024,
|
192 |
+
"step": 2700
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 1.33,
|
196 |
+
"learning_rate": 8.160337552742617e-06,
|
197 |
+
"loss": 0.4867,
|
198 |
+
"step": 2800
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.38,
|
202 |
+
"learning_rate": 8.054852320675107e-06,
|
203 |
+
"loss": 0.4941,
|
204 |
+
"step": 2900
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.42,
|
208 |
+
"learning_rate": 7.949367088607595e-06,
|
209 |
+
"loss": 0.479,
|
210 |
+
"step": 3000
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 1.42,
|
214 |
+
"eval_loss": 0.46754053235054016,
|
215 |
+
"eval_rouge1": 0.25667075818488366,
|
216 |
+
"eval_rouge2": 0.06493933281502531,
|
217 |
+
"eval_rougeL": 0.25610002044309327,
|
218 |
+
"eval_runtime": 37.2336,
|
219 |
+
"eval_samples_per_second": 24.494,
|
220 |
+
"eval_steps_per_second": 6.123,
|
221 |
+
"step": 3000
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.47,
|
225 |
+
"learning_rate": 7.843881856540085e-06,
|
226 |
+
"loss": 0.486,
|
227 |
+
"step": 3100
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.52,
|
231 |
+
"learning_rate": 7.738396624472575e-06,
|
232 |
+
"loss": 0.482,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.57,
|
237 |
+
"learning_rate": 7.632911392405063e-06,
|
238 |
+
"loss": 0.4835,
|
239 |
+
"step": 3300
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.61,
|
243 |
+
"learning_rate": 7.528481012658229e-06,
|
244 |
+
"loss": 0.4751,
|
245 |
+
"step": 3400
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 1.66,
|
249 |
+
"learning_rate": 7.4229957805907185e-06,
|
250 |
+
"loss": 0.4689,
|
251 |
+
"step": 3500
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.71,
|
255 |
+
"learning_rate": 7.3175105485232076e-06,
|
256 |
+
"loss": 0.4885,
|
257 |
+
"step": 3600
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.76,
|
261 |
+
"learning_rate": 7.212025316455697e-06,
|
262 |
+
"loss": 0.4845,
|
263 |
+
"step": 3700
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.8,
|
267 |
+
"learning_rate": 7.106540084388186e-06,
|
268 |
+
"loss": 0.4868,
|
269 |
+
"step": 3800
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 1.85,
|
273 |
+
"learning_rate": 7.0010548523206756e-06,
|
274 |
+
"loss": 0.4837,
|
275 |
+
"step": 3900
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.9,
|
279 |
+
"learning_rate": 6.8955696202531655e-06,
|
280 |
+
"loss": 0.4883,
|
281 |
+
"step": 4000
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.9,
|
285 |
+
"eval_loss": 0.4646187722682953,
|
286 |
+
"eval_rouge1": 0.26037312163956894,
|
287 |
+
"eval_rouge2": 0.06617398820913363,
|
288 |
+
"eval_rougeL": 0.259785770394323,
|
289 |
+
"eval_runtime": 37.1142,
|
290 |
+
"eval_samples_per_second": 24.573,
|
291 |
+
"eval_steps_per_second": 6.143,
|
292 |
+
"step": 4000
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 1.95,
|
296 |
+
"learning_rate": 6.7900843881856545e-06,
|
297 |
+
"loss": 0.477,
|
298 |
+
"step": 4100
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 1.99,
|
302 |
+
"learning_rate": 6.684599156118144e-06,
|
303 |
+
"loss": 0.4758,
|
304 |
+
"step": 4200
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 2.04,
|
308 |
+
"learning_rate": 6.579113924050633e-06,
|
309 |
+
"loss": 0.4601,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 2.09,
|
314 |
+
"learning_rate": 6.4736286919831225e-06,
|
315 |
+
"loss": 0.4536,
|
316 |
+
"step": 4400
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 2.14,
|
320 |
+
"learning_rate": 6.368143459915612e-06,
|
321 |
+
"loss": 0.4747,
|
322 |
+
"step": 4500
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 2.18,
|
326 |
+
"learning_rate": 6.2626582278481014e-06,
|
327 |
+
"loss": 0.4501,
|
328 |
+
"step": 4600
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 2.23,
|
332 |
+
"learning_rate": 6.157172995780591e-06,
|
333 |
+
"loss": 0.4679,
|
334 |
+
"step": 4700
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 2.28,
|
338 |
+
"learning_rate": 6.051687763713081e-06,
|
339 |
+
"loss": 0.4581,
|
340 |
+
"step": 4800
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 2.33,
|
344 |
+
"learning_rate": 5.9462025316455694e-06,
|
345 |
+
"loss": 0.459,
|
346 |
+
"step": 4900
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 2.37,
|
350 |
+
"learning_rate": 5.840717299578059e-06,
|
351 |
+
"loss": 0.4514,
|
352 |
+
"step": 5000
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.37,
|
356 |
+
"eval_loss": 0.45936986804008484,
|
357 |
+
"eval_rouge1": 0.26192596998518053,
|
358 |
+
"eval_rouge2": 0.06934835885234081,
|
359 |
+
"eval_rougeL": 0.2615379807814019,
|
360 |
+
"eval_runtime": 37.1093,
|
361 |
+
"eval_samples_per_second": 24.576,
|
362 |
+
"eval_steps_per_second": 6.144,
|
363 |
+
"step": 5000
|
364 |
+
}
|
365 |
+
],
|
366 |
+
"max_steps": 10530,
|
367 |
+
"num_train_epochs": 5,
|
368 |
+
"total_flos": 4.723756721661542e+16,
|
369 |
+
"trial_name": null,
|
370 |
+
"trial_params": null
|
371 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af530b6804b5f28cbe5cf6c89cacb52dcd83532826153802481a477e11ddde6a
|
3 |
+
size 3707
|