pushing from VM
Browse files- config.json +64 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +110 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +118 -0
- trainer_state.json +496 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pszemraj/pegasus-x-large-booksum-WIP2",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"PegasusXForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"block_size": 512,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 1024,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 4096,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 16,
|
20 |
+
"decoder_start_token_id": 0,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 16,
|
27 |
+
"encoder_no_repeat_ngram_size": 4,
|
28 |
+
"eos_token_id": 1,
|
29 |
+
"extra_pos_embeddings": 1,
|
30 |
+
"force_bos_token_to_be_generated": false,
|
31 |
+
"forced_eos_token_id": 1,
|
32 |
+
"gradient_checkpointing": false,
|
33 |
+
"id2label": {
|
34 |
+
"0": "LABEL_0",
|
35 |
+
"1": "LABEL_1",
|
36 |
+
"2": "LABEL_2"
|
37 |
+
},
|
38 |
+
"init_std": 0.02,
|
39 |
+
"is_encoder_decoder": true,
|
40 |
+
"label2id": {
|
41 |
+
"LABEL_0": 0,
|
42 |
+
"LABEL_1": 1,
|
43 |
+
"LABEL_2": 2
|
44 |
+
},
|
45 |
+
"length_penalty": 0.8,
|
46 |
+
"max_length": 512,
|
47 |
+
"max_position_embeddings": 16384,
|
48 |
+
"min_length": 8,
|
49 |
+
"model_type": "pegasus_x",
|
50 |
+
"no_repeat_ngram_size": 3,
|
51 |
+
"normalize_before": true,
|
52 |
+
"normalize_embedding": false,
|
53 |
+
"num_beams": 2,
|
54 |
+
"num_global_tokens": 128,
|
55 |
+
"num_hidden_layers": 16,
|
56 |
+
"pad_token_id": 0,
|
57 |
+
"scale_embedding": true,
|
58 |
+
"stagger_local_blocks": true,
|
59 |
+
"static_position_embeddings": true,
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.22.0",
|
62 |
+
"use_cache": false,
|
63 |
+
"vocab_size": 96103
|
64 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:075aa2214ecc159f20c69228df00e7ee58a9e1b93337aa4f454a4cf9c5982441
|
3 |
+
size 2274842165
|
special_tokens_map.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<mask_1>",
|
4 |
+
"<unk_2>",
|
5 |
+
"<unk_3>",
|
6 |
+
"<unk_4>",
|
7 |
+
"<unk_5>",
|
8 |
+
"<unk_6>",
|
9 |
+
"<unk_7>",
|
10 |
+
"<unk_8>",
|
11 |
+
"<unk_9>",
|
12 |
+
"<unk_10>",
|
13 |
+
"<unk_11>",
|
14 |
+
"<unk_12>",
|
15 |
+
"<unk_13>",
|
16 |
+
"<unk_14>",
|
17 |
+
"<unk_15>",
|
18 |
+
"<unk_16>",
|
19 |
+
"<unk_17>",
|
20 |
+
"<unk_18>",
|
21 |
+
"<unk_19>",
|
22 |
+
"<unk_20>",
|
23 |
+
"<unk_21>",
|
24 |
+
"<unk_22>",
|
25 |
+
"<unk_23>",
|
26 |
+
"<unk_24>",
|
27 |
+
"<unk_25>",
|
28 |
+
"<unk_26>",
|
29 |
+
"<unk_27>",
|
30 |
+
"<unk_28>",
|
31 |
+
"<unk_29>",
|
32 |
+
"<unk_30>",
|
33 |
+
"<unk_31>",
|
34 |
+
"<unk_32>",
|
35 |
+
"<unk_33>",
|
36 |
+
"<unk_34>",
|
37 |
+
"<unk_35>",
|
38 |
+
"<unk_36>",
|
39 |
+
"<unk_37>",
|
40 |
+
"<unk_38>",
|
41 |
+
"<unk_39>",
|
42 |
+
"<unk_40>",
|
43 |
+
"<unk_41>",
|
44 |
+
"<unk_42>",
|
45 |
+
"<unk_43>",
|
46 |
+
"<unk_44>",
|
47 |
+
"<unk_45>",
|
48 |
+
"<unk_46>",
|
49 |
+
"<unk_47>",
|
50 |
+
"<unk_48>",
|
51 |
+
"<unk_49>",
|
52 |
+
"<unk_50>",
|
53 |
+
"<unk_51>",
|
54 |
+
"<unk_52>",
|
55 |
+
"<unk_53>",
|
56 |
+
"<unk_54>",
|
57 |
+
"<unk_55>",
|
58 |
+
"<unk_56>",
|
59 |
+
"<unk_57>",
|
60 |
+
"<unk_58>",
|
61 |
+
"<unk_59>",
|
62 |
+
"<unk_60>",
|
63 |
+
"<unk_61>",
|
64 |
+
"<unk_62>",
|
65 |
+
"<unk_63>",
|
66 |
+
"<unk_64>",
|
67 |
+
"<unk_65>",
|
68 |
+
"<unk_66>",
|
69 |
+
"<unk_67>",
|
70 |
+
"<unk_68>",
|
71 |
+
"<unk_69>",
|
72 |
+
"<unk_70>",
|
73 |
+
"<unk_71>",
|
74 |
+
"<unk_72>",
|
75 |
+
"<unk_73>",
|
76 |
+
"<unk_74>",
|
77 |
+
"<unk_75>",
|
78 |
+
"<unk_76>",
|
79 |
+
"<unk_77>",
|
80 |
+
"<unk_78>",
|
81 |
+
"<unk_79>",
|
82 |
+
"<unk_80>",
|
83 |
+
"<unk_81>",
|
84 |
+
"<unk_82>",
|
85 |
+
"<unk_83>",
|
86 |
+
"<unk_84>",
|
87 |
+
"<unk_85>",
|
88 |
+
"<unk_86>",
|
89 |
+
"<unk_87>",
|
90 |
+
"<unk_88>",
|
91 |
+
"<unk_89>",
|
92 |
+
"<unk_90>",
|
93 |
+
"<unk_91>",
|
94 |
+
"<unk_92>",
|
95 |
+
"<unk_93>",
|
96 |
+
"<unk_94>",
|
97 |
+
"<unk_95>",
|
98 |
+
"<unk_96>",
|
99 |
+
"<unk_97>",
|
100 |
+
"<unk_98>",
|
101 |
+
"<unk_99>",
|
102 |
+
"<unk_100>",
|
103 |
+
"<unk_101>",
|
104 |
+
"<unk_102>"
|
105 |
+
],
|
106 |
+
"eos_token": "</s>",
|
107 |
+
"mask_token": "<mask_2>",
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"unk_token": "<unk>"
|
110 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
|
3 |
+
size 1912529
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<mask_1>",
|
4 |
+
"<unk_2>",
|
5 |
+
"<unk_3>",
|
6 |
+
"<unk_4>",
|
7 |
+
"<unk_5>",
|
8 |
+
"<unk_6>",
|
9 |
+
"<unk_7>",
|
10 |
+
"<unk_8>",
|
11 |
+
"<unk_9>",
|
12 |
+
"<unk_10>",
|
13 |
+
"<unk_11>",
|
14 |
+
"<unk_12>",
|
15 |
+
"<unk_13>",
|
16 |
+
"<unk_14>",
|
17 |
+
"<unk_15>",
|
18 |
+
"<unk_16>",
|
19 |
+
"<unk_17>",
|
20 |
+
"<unk_18>",
|
21 |
+
"<unk_19>",
|
22 |
+
"<unk_20>",
|
23 |
+
"<unk_21>",
|
24 |
+
"<unk_22>",
|
25 |
+
"<unk_23>",
|
26 |
+
"<unk_24>",
|
27 |
+
"<unk_25>",
|
28 |
+
"<unk_26>",
|
29 |
+
"<unk_27>",
|
30 |
+
"<unk_28>",
|
31 |
+
"<unk_29>",
|
32 |
+
"<unk_30>",
|
33 |
+
"<unk_31>",
|
34 |
+
"<unk_32>",
|
35 |
+
"<unk_33>",
|
36 |
+
"<unk_34>",
|
37 |
+
"<unk_35>",
|
38 |
+
"<unk_36>",
|
39 |
+
"<unk_37>",
|
40 |
+
"<unk_38>",
|
41 |
+
"<unk_39>",
|
42 |
+
"<unk_40>",
|
43 |
+
"<unk_41>",
|
44 |
+
"<unk_42>",
|
45 |
+
"<unk_43>",
|
46 |
+
"<unk_44>",
|
47 |
+
"<unk_45>",
|
48 |
+
"<unk_46>",
|
49 |
+
"<unk_47>",
|
50 |
+
"<unk_48>",
|
51 |
+
"<unk_49>",
|
52 |
+
"<unk_50>",
|
53 |
+
"<unk_51>",
|
54 |
+
"<unk_52>",
|
55 |
+
"<unk_53>",
|
56 |
+
"<unk_54>",
|
57 |
+
"<unk_55>",
|
58 |
+
"<unk_56>",
|
59 |
+
"<unk_57>",
|
60 |
+
"<unk_58>",
|
61 |
+
"<unk_59>",
|
62 |
+
"<unk_60>",
|
63 |
+
"<unk_61>",
|
64 |
+
"<unk_62>",
|
65 |
+
"<unk_63>",
|
66 |
+
"<unk_64>",
|
67 |
+
"<unk_65>",
|
68 |
+
"<unk_66>",
|
69 |
+
"<unk_67>",
|
70 |
+
"<unk_68>",
|
71 |
+
"<unk_69>",
|
72 |
+
"<unk_70>",
|
73 |
+
"<unk_71>",
|
74 |
+
"<unk_72>",
|
75 |
+
"<unk_73>",
|
76 |
+
"<unk_74>",
|
77 |
+
"<unk_75>",
|
78 |
+
"<unk_76>",
|
79 |
+
"<unk_77>",
|
80 |
+
"<unk_78>",
|
81 |
+
"<unk_79>",
|
82 |
+
"<unk_80>",
|
83 |
+
"<unk_81>",
|
84 |
+
"<unk_82>",
|
85 |
+
"<unk_83>",
|
86 |
+
"<unk_84>",
|
87 |
+
"<unk_85>",
|
88 |
+
"<unk_86>",
|
89 |
+
"<unk_87>",
|
90 |
+
"<unk_88>",
|
91 |
+
"<unk_89>",
|
92 |
+
"<unk_90>",
|
93 |
+
"<unk_91>",
|
94 |
+
"<unk_92>",
|
95 |
+
"<unk_93>",
|
96 |
+
"<unk_94>",
|
97 |
+
"<unk_95>",
|
98 |
+
"<unk_96>",
|
99 |
+
"<unk_97>",
|
100 |
+
"<unk_98>",
|
101 |
+
"<unk_99>",
|
102 |
+
"<unk_100>",
|
103 |
+
"<unk_101>",
|
104 |
+
"<unk_102>"
|
105 |
+
],
|
106 |
+
"eos_token": "</s>",
|
107 |
+
"full_tokenizer_file": null,
|
108 |
+
"mask_token": "<mask_2>",
|
109 |
+
"mask_token_sent": "<mask_1>",
|
110 |
+
"model_max_length": 1024,
|
111 |
+
"name_or_path": "pszemraj/pegasus-x-large-booksum-WIP2",
|
112 |
+
"offset": 103,
|
113 |
+
"pad_token": "<pad>",
|
114 |
+
"sp_model_kwargs": {},
|
115 |
+
"special_tokens_map_file": null,
|
116 |
+
"tokenizer_class": "PegasusTokenizer",
|
117 |
+
"unk_token": "<unk>"
|
118 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9425981873111784,
|
5 |
+
"global_step": 160,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.02,
|
12 |
+
"learning_rate": 6e-05,
|
13 |
+
"loss": 2.2136,
|
14 |
+
"step": 2
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.05,
|
18 |
+
"learning_rate": 6e-05,
|
19 |
+
"loss": 2.1745,
|
20 |
+
"step": 4
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.07,
|
24 |
+
"learning_rate": 6e-05,
|
25 |
+
"loss": 2.2121,
|
26 |
+
"step": 6
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.1,
|
30 |
+
"learning_rate": 6e-05,
|
31 |
+
"loss": 2.1942,
|
32 |
+
"step": 8
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.12,
|
36 |
+
"learning_rate": 6e-05,
|
37 |
+
"loss": 2.213,
|
38 |
+
"step": 10
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.15,
|
42 |
+
"learning_rate": 6e-05,
|
43 |
+
"loss": 2.1835,
|
44 |
+
"step": 12
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.17,
|
48 |
+
"learning_rate": 6e-05,
|
49 |
+
"loss": 2.2074,
|
50 |
+
"step": 14
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.19,
|
54 |
+
"learning_rate": 6e-05,
|
55 |
+
"loss": 2.2165,
|
56 |
+
"step": 16
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.22,
|
60 |
+
"learning_rate": 6e-05,
|
61 |
+
"loss": 2.1942,
|
62 |
+
"step": 18
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.24,
|
66 |
+
"learning_rate": 6e-05,
|
67 |
+
"loss": 2.1919,
|
68 |
+
"step": 20
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.27,
|
72 |
+
"learning_rate": 6e-05,
|
73 |
+
"loss": 2.1598,
|
74 |
+
"step": 22
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.29,
|
78 |
+
"learning_rate": 6e-05,
|
79 |
+
"loss": 2.2082,
|
80 |
+
"step": 24
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.31,
|
84 |
+
"learning_rate": 6e-05,
|
85 |
+
"loss": 2.1798,
|
86 |
+
"step": 26
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.34,
|
90 |
+
"learning_rate": 6e-05,
|
91 |
+
"loss": 2.1878,
|
92 |
+
"step": 28
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.36,
|
96 |
+
"learning_rate": 6e-05,
|
97 |
+
"loss": 2.198,
|
98 |
+
"step": 30
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.39,
|
102 |
+
"learning_rate": 6e-05,
|
103 |
+
"loss": 2.1458,
|
104 |
+
"step": 32
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.41,
|
108 |
+
"learning_rate": 6e-05,
|
109 |
+
"loss": 2.1913,
|
110 |
+
"step": 34
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.44,
|
114 |
+
"learning_rate": 6e-05,
|
115 |
+
"loss": 2.1581,
|
116 |
+
"step": 36
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.46,
|
120 |
+
"learning_rate": 6e-05,
|
121 |
+
"loss": 2.1761,
|
122 |
+
"step": 38
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.48,
|
126 |
+
"learning_rate": 6e-05,
|
127 |
+
"loss": 2.1474,
|
128 |
+
"step": 40
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.51,
|
132 |
+
"learning_rate": 6e-05,
|
133 |
+
"loss": 2.1736,
|
134 |
+
"step": 42
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.53,
|
138 |
+
"learning_rate": 6e-05,
|
139 |
+
"loss": 2.1988,
|
140 |
+
"step": 44
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.56,
|
144 |
+
"learning_rate": 6e-05,
|
145 |
+
"loss": 2.1796,
|
146 |
+
"step": 46
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.58,
|
150 |
+
"learning_rate": 6e-05,
|
151 |
+
"loss": 2.2004,
|
152 |
+
"step": 48
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.6,
|
156 |
+
"learning_rate": 6e-05,
|
157 |
+
"loss": 2.2067,
|
158 |
+
"step": 50
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.63,
|
162 |
+
"learning_rate": 6e-05,
|
163 |
+
"loss": 2.1998,
|
164 |
+
"step": 52
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.65,
|
168 |
+
"learning_rate": 6e-05,
|
169 |
+
"loss": 2.2015,
|
170 |
+
"step": 54
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.68,
|
174 |
+
"learning_rate": 6e-05,
|
175 |
+
"loss": 2.2152,
|
176 |
+
"step": 56
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.7,
|
180 |
+
"learning_rate": 6e-05,
|
181 |
+
"loss": 2.1614,
|
182 |
+
"step": 58
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.73,
|
186 |
+
"learning_rate": 6e-05,
|
187 |
+
"loss": 2.1996,
|
188 |
+
"step": 60
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.75,
|
192 |
+
"learning_rate": 6e-05,
|
193 |
+
"loss": 2.1909,
|
194 |
+
"step": 62
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.77,
|
198 |
+
"learning_rate": 6e-05,
|
199 |
+
"loss": 2.208,
|
200 |
+
"step": 64
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.8,
|
204 |
+
"learning_rate": 6e-05,
|
205 |
+
"loss": 2.1879,
|
206 |
+
"step": 66
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.82,
|
210 |
+
"learning_rate": 6e-05,
|
211 |
+
"loss": 2.1759,
|
212 |
+
"step": 68
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.85,
|
216 |
+
"learning_rate": 6e-05,
|
217 |
+
"loss": 2.1351,
|
218 |
+
"step": 70
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.87,
|
222 |
+
"learning_rate": 6e-05,
|
223 |
+
"loss": 2.1713,
|
224 |
+
"step": 72
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.89,
|
228 |
+
"learning_rate": 6e-05,
|
229 |
+
"loss": 2.1473,
|
230 |
+
"step": 74
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.92,
|
234 |
+
"learning_rate": 6e-05,
|
235 |
+
"loss": 2.1646,
|
236 |
+
"step": 76
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.94,
|
240 |
+
"learning_rate": 6e-05,
|
241 |
+
"loss": 2.1772,
|
242 |
+
"step": 78
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.97,
|
246 |
+
"learning_rate": 6e-05,
|
247 |
+
"loss": 2.1615,
|
248 |
+
"step": 80
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.99,
|
252 |
+
"learning_rate": 6e-05,
|
253 |
+
"loss": 2.1634,
|
254 |
+
"step": 82
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.02,
|
258 |
+
"learning_rate": 6e-05,
|
259 |
+
"loss": 3.03,
|
260 |
+
"step": 84
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.05,
|
264 |
+
"learning_rate": 6e-05,
|
265 |
+
"loss": 2.1659,
|
266 |
+
"step": 86
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.07,
|
270 |
+
"learning_rate": 6e-05,
|
271 |
+
"loss": 2.147,
|
272 |
+
"step": 88
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.1,
|
276 |
+
"learning_rate": 6e-05,
|
277 |
+
"loss": 2.1871,
|
278 |
+
"step": 90
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.12,
|
282 |
+
"learning_rate": 6e-05,
|
283 |
+
"loss": 2.1916,
|
284 |
+
"step": 92
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.15,
|
288 |
+
"learning_rate": 6e-05,
|
289 |
+
"loss": 2.1893,
|
290 |
+
"step": 94
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.17,
|
294 |
+
"learning_rate": 6e-05,
|
295 |
+
"loss": 2.17,
|
296 |
+
"step": 96
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.19,
|
300 |
+
"learning_rate": 6e-05,
|
301 |
+
"loss": 2.1516,
|
302 |
+
"step": 98
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.22,
|
306 |
+
"learning_rate": 6e-05,
|
307 |
+
"loss": 2.1433,
|
308 |
+
"step": 100
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.24,
|
312 |
+
"learning_rate": 6e-05,
|
313 |
+
"loss": 2.1705,
|
314 |
+
"step": 102
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.27,
|
318 |
+
"learning_rate": 6e-05,
|
319 |
+
"loss": 2.2087,
|
320 |
+
"step": 104
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.29,
|
324 |
+
"learning_rate": 6e-05,
|
325 |
+
"loss": 2.2392,
|
326 |
+
"step": 106
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.31,
|
330 |
+
"learning_rate": 6e-05,
|
331 |
+
"loss": 2.221,
|
332 |
+
"step": 108
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.34,
|
336 |
+
"learning_rate": 6e-05,
|
337 |
+
"loss": 2.1764,
|
338 |
+
"step": 110
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.36,
|
342 |
+
"learning_rate": 6e-05,
|
343 |
+
"loss": 2.1441,
|
344 |
+
"step": 112
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.39,
|
348 |
+
"learning_rate": 6e-05,
|
349 |
+
"loss": 2.2088,
|
350 |
+
"step": 114
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.41,
|
354 |
+
"learning_rate": 6e-05,
|
355 |
+
"loss": 2.137,
|
356 |
+
"step": 116
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.44,
|
360 |
+
"learning_rate": 6e-05,
|
361 |
+
"loss": 2.143,
|
362 |
+
"step": 118
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.46,
|
366 |
+
"learning_rate": 6e-05,
|
367 |
+
"loss": 2.1853,
|
368 |
+
"step": 120
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.48,
|
372 |
+
"learning_rate": 6e-05,
|
373 |
+
"loss": 2.1816,
|
374 |
+
"step": 122
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.51,
|
378 |
+
"learning_rate": 6e-05,
|
379 |
+
"loss": 2.1805,
|
380 |
+
"step": 124
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.53,
|
384 |
+
"learning_rate": 6e-05,
|
385 |
+
"loss": 2.2074,
|
386 |
+
"step": 126
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 1.56,
|
390 |
+
"learning_rate": 6e-05,
|
391 |
+
"loss": 2.1545,
|
392 |
+
"step": 128
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.58,
|
396 |
+
"learning_rate": 6e-05,
|
397 |
+
"loss": 2.1655,
|
398 |
+
"step": 130
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.6,
|
402 |
+
"learning_rate": 6e-05,
|
403 |
+
"loss": 2.1827,
|
404 |
+
"step": 132
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.63,
|
408 |
+
"learning_rate": 6e-05,
|
409 |
+
"loss": 2.1936,
|
410 |
+
"step": 134
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.65,
|
414 |
+
"learning_rate": 6e-05,
|
415 |
+
"loss": 2.1696,
|
416 |
+
"step": 136
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.68,
|
420 |
+
"learning_rate": 6e-05,
|
421 |
+
"loss": 2.2112,
|
422 |
+
"step": 138
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.7,
|
426 |
+
"learning_rate": 6e-05,
|
427 |
+
"loss": 2.2027,
|
428 |
+
"step": 140
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.73,
|
432 |
+
"learning_rate": 6e-05,
|
433 |
+
"loss": 2.1224,
|
434 |
+
"step": 142
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.75,
|
438 |
+
"learning_rate": 6e-05,
|
439 |
+
"loss": 2.2016,
|
440 |
+
"step": 144
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.77,
|
444 |
+
"learning_rate": 6e-05,
|
445 |
+
"loss": 2.1465,
|
446 |
+
"step": 146
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.8,
|
450 |
+
"learning_rate": 6e-05,
|
451 |
+
"loss": 2.1658,
|
452 |
+
"step": 148
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.82,
|
456 |
+
"learning_rate": 6e-05,
|
457 |
+
"loss": 2.188,
|
458 |
+
"step": 150
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.85,
|
462 |
+
"learning_rate": 6e-05,
|
463 |
+
"loss": 2.1806,
|
464 |
+
"step": 152
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.87,
|
468 |
+
"learning_rate": 6e-05,
|
469 |
+
"loss": 2.221,
|
470 |
+
"step": 154
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.89,
|
474 |
+
"learning_rate": 6e-05,
|
475 |
+
"loss": 2.1824,
|
476 |
+
"step": 156
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.92,
|
480 |
+
"learning_rate": 6e-05,
|
481 |
+
"loss": 2.147,
|
482 |
+
"step": 158
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.94,
|
486 |
+
"learning_rate": 6e-05,
|
487 |
+
"loss": 2.1873,
|
488 |
+
"step": 160
|
489 |
+
}
|
490 |
+
],
|
491 |
+
"max_steps": 164,
|
492 |
+
"num_train_epochs": 2,
|
493 |
+
"total_flos": 7.131255647638651e+17,
|
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 sha256:572883ff89d51fc05ac257a4f1ab7d39c7ad3a3e17b49ea891eaa7dad8e87b9f
|
3 |
+
size 3567
|