feat: add weights and states from 1120 step
Browse files- added_tokens.json +109 -0
- config.json +32 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +12 -0
- tokenizer_config.json +41 -0
- trainer_state.json +688 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<LM>": 50357,
|
3 |
+
"<SC1>": 50358,
|
4 |
+
"<SC2>": 50359,
|
5 |
+
"<SC3>": 50360,
|
6 |
+
"<SC4>": 50361,
|
7 |
+
"<SC5>": 50362,
|
8 |
+
"<SC6>": 50363,
|
9 |
+
"<extra_id_0>": 50257,
|
10 |
+
"<extra_id_10>": 50267,
|
11 |
+
"<extra_id_11>": 50268,
|
12 |
+
"<extra_id_12>": 50269,
|
13 |
+
"<extra_id_13>": 50270,
|
14 |
+
"<extra_id_14>": 50271,
|
15 |
+
"<extra_id_15>": 50272,
|
16 |
+
"<extra_id_16>": 50273,
|
17 |
+
"<extra_id_17>": 50274,
|
18 |
+
"<extra_id_18>": 50275,
|
19 |
+
"<extra_id_19>": 50276,
|
20 |
+
"<extra_id_1>": 50258,
|
21 |
+
"<extra_id_20>": 50277,
|
22 |
+
"<extra_id_21>": 50278,
|
23 |
+
"<extra_id_22>": 50279,
|
24 |
+
"<extra_id_23>": 50280,
|
25 |
+
"<extra_id_24>": 50281,
|
26 |
+
"<extra_id_25>": 50282,
|
27 |
+
"<extra_id_26>": 50283,
|
28 |
+
"<extra_id_27>": 50284,
|
29 |
+
"<extra_id_28>": 50285,
|
30 |
+
"<extra_id_29>": 50286,
|
31 |
+
"<extra_id_2>": 50259,
|
32 |
+
"<extra_id_30>": 50287,
|
33 |
+
"<extra_id_31>": 50288,
|
34 |
+
"<extra_id_32>": 50289,
|
35 |
+
"<extra_id_33>": 50290,
|
36 |
+
"<extra_id_34>": 50291,
|
37 |
+
"<extra_id_35>": 50292,
|
38 |
+
"<extra_id_36>": 50293,
|
39 |
+
"<extra_id_37>": 50294,
|
40 |
+
"<extra_id_38>": 50295,
|
41 |
+
"<extra_id_39>": 50296,
|
42 |
+
"<extra_id_3>": 50260,
|
43 |
+
"<extra_id_40>": 50297,
|
44 |
+
"<extra_id_41>": 50298,
|
45 |
+
"<extra_id_42>": 50299,
|
46 |
+
"<extra_id_43>": 50300,
|
47 |
+
"<extra_id_44>": 50301,
|
48 |
+
"<extra_id_45>": 50302,
|
49 |
+
"<extra_id_46>": 50303,
|
50 |
+
"<extra_id_47>": 50304,
|
51 |
+
"<extra_id_48>": 50305,
|
52 |
+
"<extra_id_49>": 50306,
|
53 |
+
"<extra_id_4>": 50261,
|
54 |
+
"<extra_id_50>": 50307,
|
55 |
+
"<extra_id_51>": 50308,
|
56 |
+
"<extra_id_52>": 50309,
|
57 |
+
"<extra_id_53>": 50310,
|
58 |
+
"<extra_id_54>": 50311,
|
59 |
+
"<extra_id_55>": 50312,
|
60 |
+
"<extra_id_56>": 50313,
|
61 |
+
"<extra_id_57>": 50314,
|
62 |
+
"<extra_id_58>": 50315,
|
63 |
+
"<extra_id_59>": 50316,
|
64 |
+
"<extra_id_5>": 50262,
|
65 |
+
"<extra_id_60>": 50317,
|
66 |
+
"<extra_id_61>": 50318,
|
67 |
+
"<extra_id_62>": 50319,
|
68 |
+
"<extra_id_63>": 50320,
|
69 |
+
"<extra_id_64>": 50321,
|
70 |
+
"<extra_id_65>": 50322,
|
71 |
+
"<extra_id_66>": 50323,
|
72 |
+
"<extra_id_67>": 50324,
|
73 |
+
"<extra_id_68>": 50325,
|
74 |
+
"<extra_id_69>": 50326,
|
75 |
+
"<extra_id_6>": 50263,
|
76 |
+
"<extra_id_70>": 50327,
|
77 |
+
"<extra_id_71>": 50328,
|
78 |
+
"<extra_id_72>": 50329,
|
79 |
+
"<extra_id_73>": 50330,
|
80 |
+
"<extra_id_74>": 50331,
|
81 |
+
"<extra_id_75>": 50332,
|
82 |
+
"<extra_id_76>": 50333,
|
83 |
+
"<extra_id_77>": 50334,
|
84 |
+
"<extra_id_78>": 50335,
|
85 |
+
"<extra_id_79>": 50336,
|
86 |
+
"<extra_id_7>": 50264,
|
87 |
+
"<extra_id_80>": 50337,
|
88 |
+
"<extra_id_81>": 50338,
|
89 |
+
"<extra_id_82>": 50339,
|
90 |
+
"<extra_id_83>": 50340,
|
91 |
+
"<extra_id_84>": 50341,
|
92 |
+
"<extra_id_85>": 50342,
|
93 |
+
"<extra_id_86>": 50343,
|
94 |
+
"<extra_id_87>": 50344,
|
95 |
+
"<extra_id_88>": 50345,
|
96 |
+
"<extra_id_89>": 50346,
|
97 |
+
"<extra_id_8>": 50265,
|
98 |
+
"<extra_id_90>": 50347,
|
99 |
+
"<extra_id_91>": 50348,
|
100 |
+
"<extra_id_92>": 50349,
|
101 |
+
"<extra_id_93>": 50350,
|
102 |
+
"<extra_id_94>": 50351,
|
103 |
+
"<extra_id_95>": 50352,
|
104 |
+
"<extra_id_96>": 50353,
|
105 |
+
"<extra_id_97>": 50354,
|
106 |
+
"<extra_id_98>": 50355,
|
107 |
+
"<extra_id_99>": 50356,
|
108 |
+
"<extra_id_9>": 50266
|
109 |
+
}
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/kaggle/input/fred-t5-large-instruct",
|
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": 2,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"gradient_checkpointing": false,
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
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": "4.30.2",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 50364
|
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": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.30.2"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99c56ade3ce8ce7f4cd660c9f56cfd465189c0f3e6cea93876304e1f0a19b386
|
3 |
+
size 5922605
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17e20280f7ac97d48e5623917bbbbf3a30fba6331dd764e6dbcb38e5e5f4373f
|
3 |
+
size 3282182981
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b9e29cdc3030e4b9c9f1d5b3772b55f7698772a789cb32861fca81f87bb6ae0
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c111d4fd09f2ba45d9ce9a3f9e472c9d29e15e5ddc9015049a18f079a487648d
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
}
|
12 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": {
|
24 |
+
"__type": "AddedToken",
|
25 |
+
"content": "<pad>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"tokenizer_class": "GPT2Tokenizer",
|
32 |
+
"tokenizer_file": null,
|
33 |
+
"unk_token": {
|
34 |
+
"__type": "AddedToken",
|
35 |
+
"content": "<|endoftext|>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": true,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
}
|
41 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,688 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.01949769498511016,
|
5 |
+
"global_step": 1120,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 2e-05,
|
13 |
+
"loss": 4.1497,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.0,
|
18 |
+
"learning_rate": 4e-05,
|
19 |
+
"loss": 3.7626,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.0,
|
24 |
+
"learning_rate": 6e-05,
|
25 |
+
"loss": 3.3202,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.0,
|
30 |
+
"learning_rate": 8e-05,
|
31 |
+
"loss": 3.1832,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.0,
|
36 |
+
"learning_rate": 0.0001,
|
37 |
+
"loss": 3.0717,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0,
|
42 |
+
"learning_rate": 0.00012,
|
43 |
+
"loss": 2.9981,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0,
|
48 |
+
"learning_rate": 0.00014000000000000001,
|
49 |
+
"loss": 2.9461,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.0,
|
54 |
+
"learning_rate": 0.00016,
|
55 |
+
"loss": 2.9218,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.0,
|
60 |
+
"learning_rate": 0.00017999999999999998,
|
61 |
+
"loss": 2.9574,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.0,
|
66 |
+
"learning_rate": 0.0002,
|
67 |
+
"loss": 2.9917,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.0,
|
72 |
+
"learning_rate": 0.00022,
|
73 |
+
"loss": 2.9242,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.0,
|
78 |
+
"learning_rate": 0.00024,
|
79 |
+
"loss": 2.9225,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.0,
|
84 |
+
"learning_rate": 0.00026000000000000003,
|
85 |
+
"loss": 2.9253,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.0,
|
90 |
+
"learning_rate": 0.00028000000000000003,
|
91 |
+
"loss": 2.8171,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.0,
|
96 |
+
"learning_rate": 0.0003,
|
97 |
+
"loss": 2.9023,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.0,
|
102 |
+
"learning_rate": 0.00032,
|
103 |
+
"loss": 2.809,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.0,
|
108 |
+
"learning_rate": 0.00034,
|
109 |
+
"loss": 2.9079,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.0,
|
114 |
+
"learning_rate": 0.00035999999999999997,
|
115 |
+
"loss": 2.7811,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.0,
|
120 |
+
"learning_rate": 0.00038,
|
121 |
+
"loss": 2.8214,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.0,
|
126 |
+
"learning_rate": 0.0004,
|
127 |
+
"loss": 2.821,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0,
|
132 |
+
"learning_rate": 0.00042,
|
133 |
+
"loss": 2.7647,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.0,
|
138 |
+
"learning_rate": 0.00044,
|
139 |
+
"loss": 2.776,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.0,
|
144 |
+
"learning_rate": 0.00046,
|
145 |
+
"loss": 2.8615,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.0,
|
150 |
+
"learning_rate": 0.00048,
|
151 |
+
"loss": 2.7913,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.0,
|
156 |
+
"learning_rate": 0.0005,
|
157 |
+
"loss": 2.7515,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.0,
|
162 |
+
"learning_rate": 0.0005200000000000001,
|
163 |
+
"loss": 2.7199,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.0,
|
168 |
+
"learning_rate": 0.00054,
|
169 |
+
"loss": 2.7464,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.0,
|
174 |
+
"learning_rate": 0.0005600000000000001,
|
175 |
+
"loss": 2.7036,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.0,
|
180 |
+
"learning_rate": 0.00058,
|
181 |
+
"loss": 2.8226,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.0,
|
186 |
+
"learning_rate": 0.0006,
|
187 |
+
"loss": 2.6855,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.0,
|
192 |
+
"learning_rate": 0.00062,
|
193 |
+
"loss": 2.7442,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.0,
|
198 |
+
"learning_rate": 0.00064,
|
199 |
+
"loss": 2.7517,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.0,
|
204 |
+
"learning_rate": 0.00066,
|
205 |
+
"loss": 2.6921,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.0,
|
210 |
+
"learning_rate": 0.00068,
|
211 |
+
"loss": 2.7034,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.0,
|
216 |
+
"learning_rate": 0.0007,
|
217 |
+
"loss": 2.7489,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.0,
|
222 |
+
"learning_rate": 0.0007199999999999999,
|
223 |
+
"loss": 2.6452,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.0,
|
228 |
+
"learning_rate": 0.00074,
|
229 |
+
"loss": 2.7452,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.0,
|
234 |
+
"learning_rate": 0.00076,
|
235 |
+
"loss": 2.6834,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.0,
|
240 |
+
"learning_rate": 0.0007800000000000001,
|
241 |
+
"loss": 2.6984,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.0,
|
246 |
+
"learning_rate": 0.0008,
|
247 |
+
"loss": 2.6716,
|
248 |
+
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.0,
|
252 |
+
"learning_rate": 0.00082,
|
253 |
+
"loss": 2.7164,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.0,
|
258 |
+
"learning_rate": 0.00084,
|
259 |
+
"loss": 2.634,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.0,
|
264 |
+
"learning_rate": 0.00086,
|
265 |
+
"loss": 2.6932,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.0,
|
270 |
+
"learning_rate": 0.00088,
|
271 |
+
"loss": 2.623,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.0,
|
276 |
+
"learning_rate": 0.0009000000000000001,
|
277 |
+
"loss": 2.6827,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.0,
|
282 |
+
"learning_rate": 0.00092,
|
283 |
+
"loss": 2.6558,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.0,
|
288 |
+
"learning_rate": 0.00094,
|
289 |
+
"loss": 2.7282,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.0,
|
294 |
+
"learning_rate": 0.00096,
|
295 |
+
"loss": 2.7123,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.0,
|
300 |
+
"learning_rate": 0.00098,
|
301 |
+
"loss": 2.5858,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.0,
|
306 |
+
"learning_rate": 0.001,
|
307 |
+
"loss": 2.7641,
|
308 |
+
"step": 500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.0,
|
312 |
+
"learning_rate": 0.00102,
|
313 |
+
"loss": 2.6606,
|
314 |
+
"step": 510
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.0,
|
318 |
+
"learning_rate": 0.0010400000000000001,
|
319 |
+
"loss": 2.7237,
|
320 |
+
"step": 520
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.0,
|
324 |
+
"learning_rate": 0.0010600000000000002,
|
325 |
+
"loss": 2.66,
|
326 |
+
"step": 530
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.0,
|
330 |
+
"learning_rate": 0.00108,
|
331 |
+
"loss": 2.6041,
|
332 |
+
"step": 540
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.0,
|
336 |
+
"learning_rate": 0.0011,
|
337 |
+
"loss": 2.608,
|
338 |
+
"step": 550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.0,
|
342 |
+
"learning_rate": 0.0011200000000000001,
|
343 |
+
"loss": 2.63,
|
344 |
+
"step": 560
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.0,
|
348 |
+
"learning_rate": 0.00114,
|
349 |
+
"loss": 2.6255,
|
350 |
+
"step": 570
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.0,
|
354 |
+
"learning_rate": 0.00116,
|
355 |
+
"loss": 2.6602,
|
356 |
+
"step": 580
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.0,
|
360 |
+
"learning_rate": 0.00118,
|
361 |
+
"loss": 2.6522,
|
362 |
+
"step": 590
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.0,
|
366 |
+
"learning_rate": 0.0012,
|
367 |
+
"loss": 2.7137,
|
368 |
+
"step": 600
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.0,
|
372 |
+
"learning_rate": 0.00122,
|
373 |
+
"loss": 2.6914,
|
374 |
+
"step": 610
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.0,
|
378 |
+
"learning_rate": 0.00124,
|
379 |
+
"loss": 2.6888,
|
380 |
+
"step": 620
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.0,
|
384 |
+
"learning_rate": 0.00126,
|
385 |
+
"loss": 2.6398,
|
386 |
+
"step": 630
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.0,
|
390 |
+
"learning_rate": 0.00128,
|
391 |
+
"loss": 2.6058,
|
392 |
+
"step": 640
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.0,
|
396 |
+
"learning_rate": 0.0013000000000000002,
|
397 |
+
"loss": 2.7215,
|
398 |
+
"step": 650
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.0,
|
402 |
+
"learning_rate": 0.00132,
|
403 |
+
"loss": 2.5945,
|
404 |
+
"step": 660
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.0,
|
408 |
+
"learning_rate": 0.00134,
|
409 |
+
"loss": 2.6325,
|
410 |
+
"step": 670
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.0,
|
414 |
+
"learning_rate": 0.00136,
|
415 |
+
"loss": 2.6191,
|
416 |
+
"step": 680
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.01,
|
420 |
+
"learning_rate": 0.00138,
|
421 |
+
"loss": 2.5328,
|
422 |
+
"step": 690
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.01,
|
426 |
+
"learning_rate": 0.0014,
|
427 |
+
"loss": 2.562,
|
428 |
+
"step": 700
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.01,
|
432 |
+
"learning_rate": 0.00142,
|
433 |
+
"loss": 2.5454,
|
434 |
+
"step": 710
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.01,
|
438 |
+
"learning_rate": 0.0014399999999999999,
|
439 |
+
"loss": 2.5328,
|
440 |
+
"step": 720
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.01,
|
444 |
+
"learning_rate": 0.00146,
|
445 |
+
"loss": 2.5141,
|
446 |
+
"step": 730
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.01,
|
450 |
+
"learning_rate": 0.00148,
|
451 |
+
"loss": 2.5019,
|
452 |
+
"step": 740
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.01,
|
456 |
+
"learning_rate": 0.0015,
|
457 |
+
"loss": 2.4906,
|
458 |
+
"step": 750
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.01,
|
462 |
+
"learning_rate": 0.00152,
|
463 |
+
"loss": 2.5153,
|
464 |
+
"step": 760
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.01,
|
468 |
+
"learning_rate": 0.0015400000000000001,
|
469 |
+
"loss": 2.4857,
|
470 |
+
"step": 770
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.01,
|
474 |
+
"learning_rate": 0.0015600000000000002,
|
475 |
+
"loss": 2.5265,
|
476 |
+
"step": 780
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.01,
|
480 |
+
"learning_rate": 0.00158,
|
481 |
+
"loss": 2.4994,
|
482 |
+
"step": 790
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.01,
|
486 |
+
"learning_rate": 0.0016,
|
487 |
+
"loss": 2.4538,
|
488 |
+
"step": 800
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.01,
|
492 |
+
"learning_rate": 0.0016200000000000001,
|
493 |
+
"loss": 2.5823,
|
494 |
+
"step": 810
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.01,
|
498 |
+
"learning_rate": 0.00164,
|
499 |
+
"loss": 2.4527,
|
500 |
+
"step": 820
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.01,
|
504 |
+
"learning_rate": 0.00166,
|
505 |
+
"loss": 2.4914,
|
506 |
+
"step": 830
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.01,
|
510 |
+
"learning_rate": 0.00168,
|
511 |
+
"loss": 2.4307,
|
512 |
+
"step": 840
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.01,
|
516 |
+
"learning_rate": 0.0017,
|
517 |
+
"loss": 2.4795,
|
518 |
+
"step": 850
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.01,
|
522 |
+
"learning_rate": 0.00172,
|
523 |
+
"loss": 2.4245,
|
524 |
+
"step": 860
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.02,
|
528 |
+
"learning_rate": 0.00174,
|
529 |
+
"loss": 2.4751,
|
530 |
+
"step": 870
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.02,
|
534 |
+
"learning_rate": 0.00176,
|
535 |
+
"loss": 2.4705,
|
536 |
+
"step": 880
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.02,
|
540 |
+
"learning_rate": 0.0017800000000000001,
|
541 |
+
"loss": 2.4574,
|
542 |
+
"step": 890
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.02,
|
546 |
+
"learning_rate": 0.0018000000000000002,
|
547 |
+
"loss": 2.4271,
|
548 |
+
"step": 900
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.02,
|
552 |
+
"learning_rate": 0.00182,
|
553 |
+
"loss": 2.4609,
|
554 |
+
"step": 910
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.02,
|
558 |
+
"learning_rate": 0.00184,
|
559 |
+
"loss": 2.4255,
|
560 |
+
"step": 920
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.02,
|
564 |
+
"learning_rate": 0.00186,
|
565 |
+
"loss": 2.4151,
|
566 |
+
"step": 930
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.02,
|
570 |
+
"learning_rate": 0.00188,
|
571 |
+
"loss": 2.4331,
|
572 |
+
"step": 940
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.02,
|
576 |
+
"learning_rate": 0.0019,
|
577 |
+
"loss": 2.4576,
|
578 |
+
"step": 950
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.02,
|
582 |
+
"learning_rate": 0.00192,
|
583 |
+
"loss": 2.4156,
|
584 |
+
"step": 960
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.02,
|
588 |
+
"learning_rate": 0.0019399999999999999,
|
589 |
+
"loss": 2.417,
|
590 |
+
"step": 970
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.02,
|
594 |
+
"learning_rate": 0.00196,
|
595 |
+
"loss": 2.444,
|
596 |
+
"step": 980
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.02,
|
600 |
+
"learning_rate": 0.00198,
|
601 |
+
"loss": 2.5019,
|
602 |
+
"step": 990
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.02,
|
606 |
+
"learning_rate": 0.002,
|
607 |
+
"loss": 2.4522,
|
608 |
+
"step": 1000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.02,
|
612 |
+
"learning_rate": 0.00202,
|
613 |
+
"loss": 2.4106,
|
614 |
+
"step": 1010
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.02,
|
618 |
+
"learning_rate": 0.00204,
|
619 |
+
"loss": 2.4295,
|
620 |
+
"step": 1020
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.02,
|
624 |
+
"learning_rate": 0.00206,
|
625 |
+
"loss": 2.4683,
|
626 |
+
"step": 1030
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.02,
|
630 |
+
"learning_rate": 0.0020800000000000003,
|
631 |
+
"loss": 2.4315,
|
632 |
+
"step": 1040
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.02,
|
636 |
+
"learning_rate": 0.0021000000000000003,
|
637 |
+
"loss": 2.41,
|
638 |
+
"step": 1050
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.02,
|
642 |
+
"learning_rate": 0.0021200000000000004,
|
643 |
+
"loss": 2.4551,
|
644 |
+
"step": 1060
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.02,
|
648 |
+
"learning_rate": 0.00214,
|
649 |
+
"loss": 2.4642,
|
650 |
+
"step": 1070
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.02,
|
654 |
+
"learning_rate": 0.00216,
|
655 |
+
"loss": 2.4526,
|
656 |
+
"step": 1080
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.02,
|
660 |
+
"learning_rate": 0.00218,
|
661 |
+
"loss": 2.3934,
|
662 |
+
"step": 1090
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.02,
|
666 |
+
"learning_rate": 0.0022,
|
667 |
+
"loss": 2.3918,
|
668 |
+
"step": 1100
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.02,
|
672 |
+
"learning_rate": 0.00222,
|
673 |
+
"loss": 2.4356,
|
674 |
+
"step": 1110
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.02,
|
678 |
+
"learning_rate": 0.0022400000000000002,
|
679 |
+
"loss": 2.4506,
|
680 |
+
"step": 1120
|
681 |
+
}
|
682 |
+
],
|
683 |
+
"max_steps": 172326,
|
684 |
+
"num_train_epochs": 3,
|
685 |
+
"total_flos": 5.5330613854470144e+17,
|
686 |
+
"trial_name": null,
|
687 |
+
"trial_params": null
|
688 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:958eaa6a0110d49c3a54d902ba1dc985dc8e8f3b8eb2c03dc0e099f08d75886a
|
3 |
+
size 4091
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|