checkpoint 40000
Browse files- config.json +60 -0
- generation_config.json +7 -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 +112 -0
- trainer_state.json +496 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-t5/t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 3072,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 12,
|
21 |
+
"num_heads": 12,
|
22 |
+
"num_layers": 12,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.26.0",
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 32128
|
60 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.26.0"
|
7 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c036163dfe921efbc92cf06adf7195a48812d562d04801114a94f52518a54d6
|
3 |
+
size 1783379133
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42d114772235b8166019ce39876256320a418e49c059d6ad9234900f385e5f81
|
3 |
+
size 891700799
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb1a3d9fd8c903108cc7d2faf1d5871096e97c6d3cadca373f3a5d5107e1f34
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db2f7d36d8edbbbf4278e13a19d972d0af8f15673cca269b72682bd5aa73a55b
|
3 |
+
size 623
|
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 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"extra_ids": 100,
|
106 |
+
"model_max_length": 1000000000000000019884624838656,
|
107 |
+
"name_or_path": "google-t5/t5-base",
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"special_tokens_map_file": null,
|
110 |
+
"tokenizer_class": "T5Tokenizer",
|
111 |
+
"unk_token": "<unk>"
|
112 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.34569480334286873,
|
5 |
+
"global_step": 40000,
|
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": 4.9956788149582146e-05,
|
13 |
+
"loss": 2.3181,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 4.991357629916428e-05,
|
19 |
+
"loss": 2.2625,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 4.9870364448746425e-05,
|
25 |
+
"loss": 2.1859,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 4.982715259832857e-05,
|
31 |
+
"loss": 2.1855,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.02,
|
36 |
+
"learning_rate": 4.9783940747910704e-05,
|
37 |
+
"loss": 2.1539,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.03,
|
42 |
+
"learning_rate": 4.974072889749285e-05,
|
43 |
+
"loss": 2.1454,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.03,
|
48 |
+
"learning_rate": 4.969751704707499e-05,
|
49 |
+
"loss": 2.1311,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.03,
|
54 |
+
"learning_rate": 4.9654305196657134e-05,
|
55 |
+
"loss": 2.1232,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.04,
|
60 |
+
"learning_rate": 4.961109334623927e-05,
|
61 |
+
"loss": 2.0882,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.04,
|
66 |
+
"learning_rate": 4.956788149582141e-05,
|
67 |
+
"loss": 2.1255,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.05,
|
72 |
+
"learning_rate": 4.9524669645403556e-05,
|
73 |
+
"loss": 2.1109,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.05,
|
78 |
+
"learning_rate": 4.94814577949857e-05,
|
79 |
+
"loss": 2.0932,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.06,
|
84 |
+
"learning_rate": 4.943824594456784e-05,
|
85 |
+
"loss": 2.0806,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.06,
|
90 |
+
"learning_rate": 4.9395034094149986e-05,
|
91 |
+
"loss": 2.108,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.06,
|
96 |
+
"learning_rate": 4.935182224373212e-05,
|
97 |
+
"loss": 2.1137,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.07,
|
102 |
+
"learning_rate": 4.9308610393314265e-05,
|
103 |
+
"loss": 2.0663,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.07,
|
108 |
+
"learning_rate": 4.926539854289641e-05,
|
109 |
+
"loss": 2.0729,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.08,
|
114 |
+
"learning_rate": 4.922218669247855e-05,
|
115 |
+
"loss": 2.0571,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.08,
|
120 |
+
"learning_rate": 4.917897484206069e-05,
|
121 |
+
"loss": 2.1231,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.09,
|
126 |
+
"learning_rate": 4.913576299164283e-05,
|
127 |
+
"loss": 2.0631,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.09,
|
132 |
+
"learning_rate": 4.9092551141224974e-05,
|
133 |
+
"loss": 2.0889,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.1,
|
138 |
+
"learning_rate": 4.904933929080711e-05,
|
139 |
+
"loss": 2.0952,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.1,
|
144 |
+
"learning_rate": 4.9006127440389254e-05,
|
145 |
+
"loss": 2.0885,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.1,
|
150 |
+
"learning_rate": 4.89629155899714e-05,
|
151 |
+
"loss": 2.0642,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.11,
|
156 |
+
"learning_rate": 4.891970373955353e-05,
|
157 |
+
"loss": 2.0385,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.11,
|
162 |
+
"learning_rate": 4.8876491889135676e-05,
|
163 |
+
"loss": 2.0664,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.12,
|
168 |
+
"learning_rate": 4.883328003871782e-05,
|
169 |
+
"loss": 2.0678,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.12,
|
174 |
+
"learning_rate": 4.879006818829996e-05,
|
175 |
+
"loss": 2.0487,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.13,
|
180 |
+
"learning_rate": 4.87468563378821e-05,
|
181 |
+
"loss": 2.0119,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.13,
|
186 |
+
"learning_rate": 4.870364448746424e-05,
|
187 |
+
"loss": 2.0541,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.13,
|
192 |
+
"learning_rate": 4.8660432637046385e-05,
|
193 |
+
"loss": 2.0105,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.14,
|
198 |
+
"learning_rate": 4.861722078662853e-05,
|
199 |
+
"loss": 2.0374,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.14,
|
204 |
+
"learning_rate": 4.857400893621067e-05,
|
205 |
+
"loss": 2.0205,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.15,
|
210 |
+
"learning_rate": 4.8530797085792814e-05,
|
211 |
+
"loss": 2.0243,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.15,
|
216 |
+
"learning_rate": 4.848758523537495e-05,
|
217 |
+
"loss": 2.0473,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.16,
|
222 |
+
"learning_rate": 4.8444373384957094e-05,
|
223 |
+
"loss": 2.0331,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.16,
|
228 |
+
"learning_rate": 4.840116153453924e-05,
|
229 |
+
"loss": 2.0622,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.16,
|
234 |
+
"learning_rate": 4.835794968412137e-05,
|
235 |
+
"loss": 2.0277,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.17,
|
240 |
+
"learning_rate": 4.8314737833703516e-05,
|
241 |
+
"loss": 2.0355,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.17,
|
246 |
+
"learning_rate": 4.827152598328566e-05,
|
247 |
+
"loss": 2.0415,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.18,
|
252 |
+
"learning_rate": 4.82283141328678e-05,
|
253 |
+
"loss": 2.0355,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.18,
|
258 |
+
"learning_rate": 4.818510228244994e-05,
|
259 |
+
"loss": 1.9982,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.19,
|
264 |
+
"learning_rate": 4.814189043203208e-05,
|
265 |
+
"loss": 2.0237,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.19,
|
270 |
+
"learning_rate": 4.8098678581614225e-05,
|
271 |
+
"loss": 2.0248,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.19,
|
276 |
+
"learning_rate": 4.805546673119636e-05,
|
277 |
+
"loss": 2.0038,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.2,
|
282 |
+
"learning_rate": 4.8012254880778505e-05,
|
283 |
+
"loss": 2.0252,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.2,
|
288 |
+
"learning_rate": 4.796904303036065e-05,
|
289 |
+
"loss": 1.9888,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.21,
|
294 |
+
"learning_rate": 4.7925831179942784e-05,
|
295 |
+
"loss": 2.0121,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.21,
|
300 |
+
"learning_rate": 4.788261932952493e-05,
|
301 |
+
"loss": 1.9794,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.22,
|
306 |
+
"learning_rate": 4.783940747910707e-05,
|
307 |
+
"loss": 1.9893,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.22,
|
312 |
+
"learning_rate": 4.7796195628689213e-05,
|
313 |
+
"loss": 1.9933,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.22,
|
318 |
+
"learning_rate": 4.7752983778271357e-05,
|
319 |
+
"loss": 1.9897,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.23,
|
324 |
+
"learning_rate": 4.77097719278535e-05,
|
325 |
+
"loss": 2.0199,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.23,
|
330 |
+
"learning_rate": 4.766656007743564e-05,
|
331 |
+
"loss": 2.0092,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.24,
|
336 |
+
"learning_rate": 4.762334822701778e-05,
|
337 |
+
"loss": 1.9775,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.24,
|
342 |
+
"learning_rate": 4.758013637659992e-05,
|
343 |
+
"loss": 1.9796,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.25,
|
348 |
+
"learning_rate": 4.7536924526182065e-05,
|
349 |
+
"loss": 1.9855,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.25,
|
354 |
+
"learning_rate": 4.74937126757642e-05,
|
355 |
+
"loss": 2.0539,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.25,
|
360 |
+
"learning_rate": 4.7450500825346345e-05,
|
361 |
+
"loss": 2.0053,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.26,
|
366 |
+
"learning_rate": 4.740728897492849e-05,
|
367 |
+
"loss": 1.9682,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.26,
|
372 |
+
"learning_rate": 4.736407712451063e-05,
|
373 |
+
"loss": 2.0241,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.27,
|
378 |
+
"learning_rate": 4.732086527409277e-05,
|
379 |
+
"loss": 1.9906,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.27,
|
384 |
+
"learning_rate": 4.727765342367491e-05,
|
385 |
+
"loss": 1.999,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.28,
|
390 |
+
"learning_rate": 4.7234441573257054e-05,
|
391 |
+
"loss": 2.0129,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.28,
|
396 |
+
"learning_rate": 4.719122972283919e-05,
|
397 |
+
"loss": 2.0016,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.29,
|
402 |
+
"learning_rate": 4.714801787242133e-05,
|
403 |
+
"loss": 1.9669,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.29,
|
408 |
+
"learning_rate": 4.7104806022003476e-05,
|
409 |
+
"loss": 2.0073,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.29,
|
414 |
+
"learning_rate": 4.706159417158561e-05,
|
415 |
+
"loss": 1.9432,
|
416 |
+
"step": 34000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.3,
|
420 |
+
"learning_rate": 4.7018382321167756e-05,
|
421 |
+
"loss": 1.9661,
|
422 |
+
"step": 34500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.3,
|
426 |
+
"learning_rate": 4.69751704707499e-05,
|
427 |
+
"loss": 1.9904,
|
428 |
+
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.31,
|
432 |
+
"learning_rate": 4.693195862033204e-05,
|
433 |
+
"loss": 1.9749,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.31,
|
438 |
+
"learning_rate": 4.6888746769914185e-05,
|
439 |
+
"loss": 1.9963,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.32,
|
444 |
+
"learning_rate": 4.684553491949633e-05,
|
445 |
+
"loss": 1.9604,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.32,
|
450 |
+
"learning_rate": 4.680232306907847e-05,
|
451 |
+
"loss": 2.0006,
|
452 |
+
"step": 37000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.32,
|
456 |
+
"learning_rate": 4.675911121866061e-05,
|
457 |
+
"loss": 1.9637,
|
458 |
+
"step": 37500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.33,
|
462 |
+
"learning_rate": 4.671589936824275e-05,
|
463 |
+
"loss": 1.9799,
|
464 |
+
"step": 38000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.33,
|
468 |
+
"learning_rate": 4.6672687517824894e-05,
|
469 |
+
"loss": 1.9626,
|
470 |
+
"step": 38500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.34,
|
474 |
+
"learning_rate": 4.662947566740703e-05,
|
475 |
+
"loss": 1.9352,
|
476 |
+
"step": 39000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.34,
|
480 |
+
"learning_rate": 4.6586263816989173e-05,
|
481 |
+
"loss": 1.9919,
|
482 |
+
"step": 39500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.35,
|
486 |
+
"learning_rate": 4.6543051966571317e-05,
|
487 |
+
"loss": 1.9473,
|
488 |
+
"step": 40000
|
489 |
+
}
|
490 |
+
],
|
491 |
+
"max_steps": 578545,
|
492 |
+
"num_train_epochs": 5,
|
493 |
+
"total_flos": 5.842369833311232e+16,
|
494 |
+
"trial_name": null,
|
495 |
+
"trial_params": null
|
496 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb006876bc1eed6dfae25e2b01434f2f2f3632515a09507a8629ebf710003c06
|
3 |
+
size 3631
|