Upload folder using huggingface_hub
Browse files- config.json +61 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +111 -0
- trainer_state.json +817 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 3072,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "relu",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "relu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": false,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_heads": 12,
|
23 |
+
"num_layers": 12,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"task_specific_params": {
|
29 |
+
"summarization": {
|
30 |
+
"early_stopping": true,
|
31 |
+
"length_penalty": 2.0,
|
32 |
+
"max_length": 200,
|
33 |
+
"min_length": 30,
|
34 |
+
"no_repeat_ngram_size": 3,
|
35 |
+
"num_beams": 4,
|
36 |
+
"prefix": "summarize: "
|
37 |
+
},
|
38 |
+
"translation_en_to_de": {
|
39 |
+
"early_stopping": true,
|
40 |
+
"max_length": 300,
|
41 |
+
"num_beams": 4,
|
42 |
+
"prefix": "translate English to German: "
|
43 |
+
},
|
44 |
+
"translation_en_to_fr": {
|
45 |
+
"early_stopping": true,
|
46 |
+
"max_length": 300,
|
47 |
+
"num_beams": 4,
|
48 |
+
"prefix": "translate English to French: "
|
49 |
+
},
|
50 |
+
"translation_en_to_ro": {
|
51 |
+
"early_stopping": true,
|
52 |
+
"max_length": 300,
|
53 |
+
"num_beams": 4,
|
54 |
+
"prefix": "translate English to Romanian: "
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.33.0",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32128
|
61 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.33.0"
|
6 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8e1ce5355f19eac921bb673f19ef29abdc0a50136eda968f1210aed53006558
|
3 |
+
size 1783444357
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84eca485ee0eed5f75acac0b8b383263b71a1e7f6ef914834db575666fcd6cbe
|
3 |
+
size 891702929
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7fbc4bb9c97bf9a4572b02e2d033d671f6b59c00aedb0671d681959fedf05b7
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcfe6fb965574a3f0e9fac2d6e2a551508df896c5b8f466cf65d656fc354c54e
|
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.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": 512,
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"tokenizer_class": "T5Tokenizer",
|
110 |
+
"unk_token": "<unk>"
|
111 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,817 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.983079526226735,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 59000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.08,
|
13 |
+
"learning_rate": 1.9830795262267346e-05,
|
14 |
+
"loss": 2.6117,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.17,
|
19 |
+
"learning_rate": 1.9661590524534688e-05,
|
20 |
+
"loss": 1.7548,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.25,
|
25 |
+
"learning_rate": 1.9492385786802032e-05,
|
26 |
+
"loss": 1.4794,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.34,
|
31 |
+
"learning_rate": 1.9323181049069374e-05,
|
32 |
+
"loss": 1.3088,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.42,
|
37 |
+
"learning_rate": 1.915397631133672e-05,
|
38 |
+
"loss": 1.1959,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.51,
|
43 |
+
"learning_rate": 1.8984771573604063e-05,
|
44 |
+
"loss": 1.1127,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.59,
|
49 |
+
"learning_rate": 1.8815566835871405e-05,
|
50 |
+
"loss": 1.0536,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.68,
|
55 |
+
"learning_rate": 1.864636209813875e-05,
|
56 |
+
"loss": 0.9879,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.76,
|
61 |
+
"learning_rate": 1.8477157360406094e-05,
|
62 |
+
"loss": 0.9587,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.85,
|
67 |
+
"learning_rate": 1.830795262267344e-05,
|
68 |
+
"loss": 0.9123,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.93,
|
73 |
+
"learning_rate": 1.813874788494078e-05,
|
74 |
+
"loss": 0.8893,
|
75 |
+
"step": 5500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 1.0,
|
79 |
+
"eval_bleu": 4.0777,
|
80 |
+
"eval_gen_len": 18.1211,
|
81 |
+
"eval_loss": 2.386338472366333,
|
82 |
+
"eval_runtime": 52.6636,
|
83 |
+
"eval_samples_per_second": 39.211,
|
84 |
+
"eval_steps_per_second": 1.234,
|
85 |
+
"step": 5910
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 1.02,
|
89 |
+
"learning_rate": 1.7969543147208125e-05,
|
90 |
+
"loss": 0.8853,
|
91 |
+
"step": 6000
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 1.1,
|
95 |
+
"learning_rate": 1.7800338409475466e-05,
|
96 |
+
"loss": 0.8313,
|
97 |
+
"step": 6500
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 1.18,
|
101 |
+
"learning_rate": 1.763113367174281e-05,
|
102 |
+
"loss": 0.8256,
|
103 |
+
"step": 7000
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 1.27,
|
107 |
+
"learning_rate": 1.7461928934010152e-05,
|
108 |
+
"loss": 0.8104,
|
109 |
+
"step": 7500
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 1.35,
|
113 |
+
"learning_rate": 1.7292724196277497e-05,
|
114 |
+
"loss": 0.8096,
|
115 |
+
"step": 8000
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.44,
|
119 |
+
"learning_rate": 1.7123519458544842e-05,
|
120 |
+
"loss": 0.7792,
|
121 |
+
"step": 8500
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.52,
|
125 |
+
"learning_rate": 1.6954314720812183e-05,
|
126 |
+
"loss": 0.7643,
|
127 |
+
"step": 9000
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 1.61,
|
131 |
+
"learning_rate": 1.6785109983079528e-05,
|
132 |
+
"loss": 0.7603,
|
133 |
+
"step": 9500
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 1.69,
|
137 |
+
"learning_rate": 1.661590524534687e-05,
|
138 |
+
"loss": 0.7385,
|
139 |
+
"step": 10000
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 1.78,
|
143 |
+
"learning_rate": 1.6446700507614214e-05,
|
144 |
+
"loss": 0.7424,
|
145 |
+
"step": 10500
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 1.86,
|
149 |
+
"learning_rate": 1.627749576988156e-05,
|
150 |
+
"loss": 0.7244,
|
151 |
+
"step": 11000
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 1.95,
|
155 |
+
"learning_rate": 1.61082910321489e-05,
|
156 |
+
"loss": 0.7182,
|
157 |
+
"step": 11500
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 2.0,
|
161 |
+
"eval_bleu": 4.0885,
|
162 |
+
"eval_gen_len": 18.231,
|
163 |
+
"eval_loss": 2.2319083213806152,
|
164 |
+
"eval_runtime": 49.7931,
|
165 |
+
"eval_samples_per_second": 41.472,
|
166 |
+
"eval_steps_per_second": 1.305,
|
167 |
+
"step": 11820
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 2.03,
|
171 |
+
"learning_rate": 1.5939086294416245e-05,
|
172 |
+
"loss": 0.7002,
|
173 |
+
"step": 12000
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 2.12,
|
177 |
+
"learning_rate": 1.576988155668359e-05,
|
178 |
+
"loss": 0.6985,
|
179 |
+
"step": 12500
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 2.2,
|
183 |
+
"learning_rate": 1.5600676818950934e-05,
|
184 |
+
"loss": 0.6908,
|
185 |
+
"step": 13000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 2.28,
|
189 |
+
"learning_rate": 1.5431472081218276e-05,
|
190 |
+
"loss": 0.6684,
|
191 |
+
"step": 13500
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.37,
|
195 |
+
"learning_rate": 1.526226734348562e-05,
|
196 |
+
"loss": 0.6749,
|
197 |
+
"step": 14000
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 2.45,
|
201 |
+
"learning_rate": 1.5093062605752962e-05,
|
202 |
+
"loss": 0.6763,
|
203 |
+
"step": 14500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 2.54,
|
207 |
+
"learning_rate": 1.4923857868020306e-05,
|
208 |
+
"loss": 0.6526,
|
209 |
+
"step": 15000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 2.62,
|
213 |
+
"learning_rate": 1.4754653130287648e-05,
|
214 |
+
"loss": 0.6536,
|
215 |
+
"step": 15500
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 2.71,
|
219 |
+
"learning_rate": 1.4585448392554992e-05,
|
220 |
+
"loss": 0.6345,
|
221 |
+
"step": 16000
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.79,
|
225 |
+
"learning_rate": 1.4416243654822337e-05,
|
226 |
+
"loss": 0.6522,
|
227 |
+
"step": 16500
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 2.88,
|
231 |
+
"learning_rate": 1.424703891708968e-05,
|
232 |
+
"loss": 0.6379,
|
233 |
+
"step": 17000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.96,
|
237 |
+
"learning_rate": 1.4077834179357023e-05,
|
238 |
+
"loss": 0.6277,
|
239 |
+
"step": 17500
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 3.0,
|
243 |
+
"eval_bleu": 4.2683,
|
244 |
+
"eval_gen_len": 18.2155,
|
245 |
+
"eval_loss": 2.1325912475585938,
|
246 |
+
"eval_runtime": 49.4798,
|
247 |
+
"eval_samples_per_second": 41.734,
|
248 |
+
"eval_steps_per_second": 1.314,
|
249 |
+
"step": 17730
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 3.05,
|
253 |
+
"learning_rate": 1.3908629441624366e-05,
|
254 |
+
"loss": 0.6309,
|
255 |
+
"step": 18000
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 3.13,
|
259 |
+
"learning_rate": 1.3739424703891711e-05,
|
260 |
+
"loss": 0.6427,
|
261 |
+
"step": 18500
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 3.21,
|
265 |
+
"learning_rate": 1.3570219966159052e-05,
|
266 |
+
"loss": 0.614,
|
267 |
+
"step": 19000
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 3.3,
|
271 |
+
"learning_rate": 1.3401015228426397e-05,
|
272 |
+
"loss": 0.6126,
|
273 |
+
"step": 19500
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 3.38,
|
277 |
+
"learning_rate": 1.323181049069374e-05,
|
278 |
+
"loss": 0.6118,
|
279 |
+
"step": 20000
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 3.47,
|
283 |
+
"learning_rate": 1.3062605752961083e-05,
|
284 |
+
"loss": 0.5909,
|
285 |
+
"step": 20500
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 3.55,
|
289 |
+
"learning_rate": 1.2893401015228428e-05,
|
290 |
+
"loss": 0.5972,
|
291 |
+
"step": 21000
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 3.64,
|
295 |
+
"learning_rate": 1.2724196277495771e-05,
|
296 |
+
"loss": 0.6019,
|
297 |
+
"step": 21500
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 3.72,
|
301 |
+
"learning_rate": 1.2554991539763116e-05,
|
302 |
+
"loss": 0.5879,
|
303 |
+
"step": 22000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 3.81,
|
307 |
+
"learning_rate": 1.2385786802030457e-05,
|
308 |
+
"loss": 0.5931,
|
309 |
+
"step": 22500
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 3.89,
|
313 |
+
"learning_rate": 1.2216582064297802e-05,
|
314 |
+
"loss": 0.5979,
|
315 |
+
"step": 23000
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 3.98,
|
319 |
+
"learning_rate": 1.2047377326565143e-05,
|
320 |
+
"loss": 0.5981,
|
321 |
+
"step": 23500
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 4.0,
|
325 |
+
"eval_bleu": 4.3741,
|
326 |
+
"eval_gen_len": 18.3075,
|
327 |
+
"eval_loss": 2.0639102458953857,
|
328 |
+
"eval_runtime": 49.7175,
|
329 |
+
"eval_samples_per_second": 41.535,
|
330 |
+
"eval_steps_per_second": 1.307,
|
331 |
+
"step": 23640
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 4.06,
|
335 |
+
"learning_rate": 1.1878172588832488e-05,
|
336 |
+
"loss": 0.5758,
|
337 |
+
"step": 24000
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 4.15,
|
341 |
+
"learning_rate": 1.1708967851099833e-05,
|
342 |
+
"loss": 0.5724,
|
343 |
+
"step": 24500
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 4.23,
|
347 |
+
"learning_rate": 1.1539763113367176e-05,
|
348 |
+
"loss": 0.5708,
|
349 |
+
"step": 25000
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 4.31,
|
353 |
+
"learning_rate": 1.1370558375634519e-05,
|
354 |
+
"loss": 0.5764,
|
355 |
+
"step": 25500
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 4.4,
|
359 |
+
"learning_rate": 1.1201353637901862e-05,
|
360 |
+
"loss": 0.5743,
|
361 |
+
"step": 26000
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 4.48,
|
365 |
+
"learning_rate": 1.1032148900169206e-05,
|
366 |
+
"loss": 0.5715,
|
367 |
+
"step": 26500
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 4.57,
|
371 |
+
"learning_rate": 1.0862944162436548e-05,
|
372 |
+
"loss": 0.5688,
|
373 |
+
"step": 27000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 4.65,
|
377 |
+
"learning_rate": 1.0693739424703892e-05,
|
378 |
+
"loss": 0.5776,
|
379 |
+
"step": 27500
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 4.74,
|
383 |
+
"learning_rate": 1.0524534686971236e-05,
|
384 |
+
"loss": 0.5712,
|
385 |
+
"step": 28000
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 4.82,
|
389 |
+
"learning_rate": 1.035532994923858e-05,
|
390 |
+
"loss": 0.5544,
|
391 |
+
"step": 28500
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 4.91,
|
395 |
+
"learning_rate": 1.0186125211505923e-05,
|
396 |
+
"loss": 0.5657,
|
397 |
+
"step": 29000
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 4.99,
|
401 |
+
"learning_rate": 1.0016920473773266e-05,
|
402 |
+
"loss": 0.5585,
|
403 |
+
"step": 29500
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 5.0,
|
407 |
+
"eval_bleu": 4.5943,
|
408 |
+
"eval_gen_len": 18.309,
|
409 |
+
"eval_loss": 2.012233018875122,
|
410 |
+
"eval_runtime": 49.6368,
|
411 |
+
"eval_samples_per_second": 41.602,
|
412 |
+
"eval_steps_per_second": 1.31,
|
413 |
+
"step": 29550
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 5.08,
|
417 |
+
"learning_rate": 9.84771573604061e-06,
|
418 |
+
"loss": 0.5618,
|
419 |
+
"step": 30000
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 5.16,
|
423 |
+
"learning_rate": 9.678510998307954e-06,
|
424 |
+
"loss": 0.5427,
|
425 |
+
"step": 30500
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 5.25,
|
429 |
+
"learning_rate": 9.509306260575297e-06,
|
430 |
+
"loss": 0.5469,
|
431 |
+
"step": 31000
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 5.33,
|
435 |
+
"learning_rate": 9.34010152284264e-06,
|
436 |
+
"loss": 0.5387,
|
437 |
+
"step": 31500
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 5.41,
|
441 |
+
"learning_rate": 9.170896785109983e-06,
|
442 |
+
"loss": 0.5454,
|
443 |
+
"step": 32000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 5.5,
|
447 |
+
"learning_rate": 9.001692047377328e-06,
|
448 |
+
"loss": 0.5474,
|
449 |
+
"step": 32500
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 5.58,
|
453 |
+
"learning_rate": 8.832487309644671e-06,
|
454 |
+
"loss": 0.5566,
|
455 |
+
"step": 33000
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 5.67,
|
459 |
+
"learning_rate": 8.663282571912014e-06,
|
460 |
+
"loss": 0.5339,
|
461 |
+
"step": 33500
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 5.75,
|
465 |
+
"learning_rate": 8.494077834179357e-06,
|
466 |
+
"loss": 0.5437,
|
467 |
+
"step": 34000
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 5.84,
|
471 |
+
"learning_rate": 8.324873096446702e-06,
|
472 |
+
"loss": 0.5408,
|
473 |
+
"step": 34500
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 5.92,
|
477 |
+
"learning_rate": 8.155668358714045e-06,
|
478 |
+
"loss": 0.537,
|
479 |
+
"step": 35000
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 6.0,
|
483 |
+
"eval_bleu": 4.6946,
|
484 |
+
"eval_gen_len": 18.3172,
|
485 |
+
"eval_loss": 1.9772592782974243,
|
486 |
+
"eval_runtime": 49.5084,
|
487 |
+
"eval_samples_per_second": 41.71,
|
488 |
+
"eval_steps_per_second": 1.313,
|
489 |
+
"step": 35460
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 6.01,
|
493 |
+
"learning_rate": 7.986463620981388e-06,
|
494 |
+
"loss": 0.5411,
|
495 |
+
"step": 35500
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 6.09,
|
499 |
+
"learning_rate": 7.817258883248731e-06,
|
500 |
+
"loss": 0.5292,
|
501 |
+
"step": 36000
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 6.18,
|
505 |
+
"learning_rate": 7.648054145516076e-06,
|
506 |
+
"loss": 0.5436,
|
507 |
+
"step": 36500
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 6.26,
|
511 |
+
"learning_rate": 7.478849407783419e-06,
|
512 |
+
"loss": 0.5317,
|
513 |
+
"step": 37000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 6.35,
|
517 |
+
"learning_rate": 7.309644670050762e-06,
|
518 |
+
"loss": 0.516,
|
519 |
+
"step": 37500
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 6.43,
|
523 |
+
"learning_rate": 7.140439932318105e-06,
|
524 |
+
"loss": 0.522,
|
525 |
+
"step": 38000
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 6.51,
|
529 |
+
"learning_rate": 6.9712351945854495e-06,
|
530 |
+
"loss": 0.528,
|
531 |
+
"step": 38500
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 6.6,
|
535 |
+
"learning_rate": 6.8020304568527926e-06,
|
536 |
+
"loss": 0.53,
|
537 |
+
"step": 39000
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 6.68,
|
541 |
+
"learning_rate": 6.6328257191201364e-06,
|
542 |
+
"loss": 0.5282,
|
543 |
+
"step": 39500
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 6.77,
|
547 |
+
"learning_rate": 6.4636209813874795e-06,
|
548 |
+
"loss": 0.5386,
|
549 |
+
"step": 40000
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 6.85,
|
553 |
+
"learning_rate": 6.2944162436548225e-06,
|
554 |
+
"loss": 0.5243,
|
555 |
+
"step": 40500
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 6.94,
|
559 |
+
"learning_rate": 6.125211505922166e-06,
|
560 |
+
"loss": 0.513,
|
561 |
+
"step": 41000
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 7.0,
|
565 |
+
"eval_bleu": 4.9177,
|
566 |
+
"eval_gen_len": 18.2939,
|
567 |
+
"eval_loss": 1.94707190990448,
|
568 |
+
"eval_runtime": 49.7911,
|
569 |
+
"eval_samples_per_second": 41.473,
|
570 |
+
"eval_steps_per_second": 1.305,
|
571 |
+
"step": 41370
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 7.02,
|
575 |
+
"learning_rate": 5.9560067681895094e-06,
|
576 |
+
"loss": 0.5096,
|
577 |
+
"step": 41500
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 7.11,
|
581 |
+
"learning_rate": 5.7868020304568525e-06,
|
582 |
+
"loss": 0.5175,
|
583 |
+
"step": 42000
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 7.19,
|
587 |
+
"learning_rate": 5.617597292724196e-06,
|
588 |
+
"loss": 0.5205,
|
589 |
+
"step": 42500
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 7.28,
|
593 |
+
"learning_rate": 5.44839255499154e-06,
|
594 |
+
"loss": 0.5079,
|
595 |
+
"step": 43000
|
596 |
+
},
|
597 |
+
{
|
598 |
+
"epoch": 7.36,
|
599 |
+
"learning_rate": 5.279187817258884e-06,
|
600 |
+
"loss": 0.5067,
|
601 |
+
"step": 43500
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 7.45,
|
605 |
+
"learning_rate": 5.109983079526227e-06,
|
606 |
+
"loss": 0.5174,
|
607 |
+
"step": 44000
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 7.53,
|
611 |
+
"learning_rate": 4.94077834179357e-06,
|
612 |
+
"loss": 0.5153,
|
613 |
+
"step": 44500
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 7.61,
|
617 |
+
"learning_rate": 4.771573604060914e-06,
|
618 |
+
"loss": 0.5227,
|
619 |
+
"step": 45000
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 7.7,
|
623 |
+
"learning_rate": 4.602368866328257e-06,
|
624 |
+
"loss": 0.5146,
|
625 |
+
"step": 45500
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 7.78,
|
629 |
+
"learning_rate": 4.433164128595601e-06,
|
630 |
+
"loss": 0.5065,
|
631 |
+
"step": 46000
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 7.87,
|
635 |
+
"learning_rate": 4.263959390862945e-06,
|
636 |
+
"loss": 0.5143,
|
637 |
+
"step": 46500
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 7.95,
|
641 |
+
"learning_rate": 4.094754653130288e-06,
|
642 |
+
"loss": 0.5234,
|
643 |
+
"step": 47000
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 8.0,
|
647 |
+
"eval_bleu": 5.0134,
|
648 |
+
"eval_gen_len": 18.2939,
|
649 |
+
"eval_loss": 1.928272008895874,
|
650 |
+
"eval_runtime": 49.7105,
|
651 |
+
"eval_samples_per_second": 41.54,
|
652 |
+
"eval_steps_per_second": 1.308,
|
653 |
+
"step": 47280
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 8.04,
|
657 |
+
"learning_rate": 3.925549915397631e-06,
|
658 |
+
"loss": 0.5043,
|
659 |
+
"step": 47500
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 8.12,
|
663 |
+
"learning_rate": 3.756345177664975e-06,
|
664 |
+
"loss": 0.5272,
|
665 |
+
"step": 48000
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 8.21,
|
669 |
+
"learning_rate": 3.5871404399323183e-06,
|
670 |
+
"loss": 0.5068,
|
671 |
+
"step": 48500
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 8.29,
|
675 |
+
"learning_rate": 3.417935702199662e-06,
|
676 |
+
"loss": 0.5071,
|
677 |
+
"step": 49000
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 8.38,
|
681 |
+
"learning_rate": 3.2487309644670053e-06,
|
682 |
+
"loss": 0.5061,
|
683 |
+
"step": 49500
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 8.46,
|
687 |
+
"learning_rate": 3.079526226734349e-06,
|
688 |
+
"loss": 0.4997,
|
689 |
+
"step": 50000
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 8.54,
|
693 |
+
"learning_rate": 2.910321489001692e-06,
|
694 |
+
"loss": 0.4953,
|
695 |
+
"step": 50500
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 8.63,
|
699 |
+
"learning_rate": 2.7411167512690357e-06,
|
700 |
+
"loss": 0.5072,
|
701 |
+
"step": 51000
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 8.71,
|
705 |
+
"learning_rate": 2.571912013536379e-06,
|
706 |
+
"loss": 0.512,
|
707 |
+
"step": 51500
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 8.8,
|
711 |
+
"learning_rate": 2.4027072758037226e-06,
|
712 |
+
"loss": 0.5043,
|
713 |
+
"step": 52000
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 8.88,
|
717 |
+
"learning_rate": 2.233502538071066e-06,
|
718 |
+
"loss": 0.499,
|
719 |
+
"step": 52500
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 8.97,
|
723 |
+
"learning_rate": 2.0642978003384095e-06,
|
724 |
+
"loss": 0.5133,
|
725 |
+
"step": 53000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 9.0,
|
729 |
+
"eval_bleu": 5.0308,
|
730 |
+
"eval_gen_len": 18.3027,
|
731 |
+
"eval_loss": 1.91579270362854,
|
732 |
+
"eval_runtime": 49.6621,
|
733 |
+
"eval_samples_per_second": 41.581,
|
734 |
+
"eval_steps_per_second": 1.309,
|
735 |
+
"step": 53190
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 9.05,
|
739 |
+
"learning_rate": 1.8950930626057532e-06,
|
740 |
+
"loss": 0.5146,
|
741 |
+
"step": 53500
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 9.14,
|
745 |
+
"learning_rate": 1.7258883248730964e-06,
|
746 |
+
"loss": 0.4968,
|
747 |
+
"step": 54000
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 9.22,
|
751 |
+
"learning_rate": 1.55668358714044e-06,
|
752 |
+
"loss": 0.4806,
|
753 |
+
"step": 54500
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 9.31,
|
757 |
+
"learning_rate": 1.3874788494077834e-06,
|
758 |
+
"loss": 0.4979,
|
759 |
+
"step": 55000
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 9.39,
|
763 |
+
"learning_rate": 1.218274111675127e-06,
|
764 |
+
"loss": 0.4971,
|
765 |
+
"step": 55500
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 9.48,
|
769 |
+
"learning_rate": 1.0490693739424705e-06,
|
770 |
+
"loss": 0.5013,
|
771 |
+
"step": 56000
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 9.56,
|
775 |
+
"learning_rate": 8.79864636209814e-07,
|
776 |
+
"loss": 0.5119,
|
777 |
+
"step": 56500
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 9.64,
|
781 |
+
"learning_rate": 7.106598984771574e-07,
|
782 |
+
"loss": 0.5076,
|
783 |
+
"step": 57000
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 9.73,
|
787 |
+
"learning_rate": 5.414551607445009e-07,
|
788 |
+
"loss": 0.508,
|
789 |
+
"step": 57500
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 9.81,
|
793 |
+
"learning_rate": 3.7225042301184434e-07,
|
794 |
+
"loss": 0.4978,
|
795 |
+
"step": 58000
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 9.9,
|
799 |
+
"learning_rate": 2.0304568527918783e-07,
|
800 |
+
"loss": 0.5046,
|
801 |
+
"step": 58500
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 9.98,
|
805 |
+
"learning_rate": 3.3840947546531305e-08,
|
806 |
+
"loss": 0.5074,
|
807 |
+
"step": 59000
|
808 |
+
}
|
809 |
+
],
|
810 |
+
"logging_steps": 500,
|
811 |
+
"max_steps": 59100,
|
812 |
+
"num_train_epochs": 10,
|
813 |
+
"save_steps": 500,
|
814 |
+
"total_flos": 7.765950061873152e+16,
|
815 |
+
"trial_name": null,
|
816 |
+
"trial_params": null
|
817 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16d07b9ade7c6d14d31d7737e39fd36e905074f0ac5caa1bf9e4131e9414bd33
|
3 |
+
size 4219
|