Training in progress, step 40
Browse files- .gitignore +1 -0
- config.json +80 -0
- last-checkpoint/config.json +80 -0
- last-checkpoint/generation_config.json +15 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +110 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +116 -0
- last-checkpoint/trainer_state.json +75 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +110 -0
- tokenizer.json +0 -0
- tokenizer_config.json +116 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "zedfum/arman-longformer-8k",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"PegasusForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dilation": [
|
11 |
+
1,
|
12 |
+
1,
|
13 |
+
1,
|
14 |
+
1,
|
15 |
+
1,
|
16 |
+
1,
|
17 |
+
1,
|
18 |
+
1,
|
19 |
+
1,
|
20 |
+
1,
|
21 |
+
1,
|
22 |
+
1
|
23 |
+
],
|
24 |
+
"attention_dropout": 0.1,
|
25 |
+
"attention_probs_dropout_prob": 0.1,
|
26 |
+
"attention_window": [
|
27 |
+
512,
|
28 |
+
512,
|
29 |
+
512,
|
30 |
+
512,
|
31 |
+
512,
|
32 |
+
512,
|
33 |
+
512,
|
34 |
+
512,
|
35 |
+
512,
|
36 |
+
512,
|
37 |
+
512,
|
38 |
+
512
|
39 |
+
],
|
40 |
+
"bos_token_id": 0,
|
41 |
+
"classif_dropout": 0.0,
|
42 |
+
"classifier_dropout": 0.0,
|
43 |
+
"d_model": 768,
|
44 |
+
"decoder_attention_heads": 12,
|
45 |
+
"decoder_ffn_dim": 3072,
|
46 |
+
"decoder_layerdrop": 0.0,
|
47 |
+
"decoder_layers": 12,
|
48 |
+
"decoder_start_token_id": 0,
|
49 |
+
"dropout": 0.1,
|
50 |
+
"early_stopping": true,
|
51 |
+
"encoder_attention_heads": 12,
|
52 |
+
"encoder_ffn_dim": 3072,
|
53 |
+
"encoder_layerdrop": 0.0,
|
54 |
+
"encoder_layers": 12,
|
55 |
+
"eos_token_id": 1,
|
56 |
+
"extra_pos_embeddings": 1,
|
57 |
+
"force_bos_token_to_be_generated": false,
|
58 |
+
"forced_eos_token_id": 1,
|
59 |
+
"init_std": 0.02,
|
60 |
+
"is_encoder_decoder": true,
|
61 |
+
"length_penalty": 2.0,
|
62 |
+
"max_decoder_position_embeddings": 512,
|
63 |
+
"max_encoder_position_embeddings": 8192,
|
64 |
+
"max_length": 512,
|
65 |
+
"max_position_embeddings": 8192,
|
66 |
+
"min_length": 100,
|
67 |
+
"model_type": "pegasus",
|
68 |
+
"no_repeat_ngram_size": 3,
|
69 |
+
"normalize_before": true,
|
70 |
+
"normalize_embedding": false,
|
71 |
+
"num_beams": 2,
|
72 |
+
"num_hidden_layers": 12,
|
73 |
+
"pad_token_id": 0,
|
74 |
+
"scale_embedding": true,
|
75 |
+
"static_position_embeddings": true,
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.30.2",
|
78 |
+
"use_cache": false,
|
79 |
+
"vocab_size": 96103
|
80 |
+
}
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "zedfum/arman-longformer-8k",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"PegasusForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dilation": [
|
11 |
+
1,
|
12 |
+
1,
|
13 |
+
1,
|
14 |
+
1,
|
15 |
+
1,
|
16 |
+
1,
|
17 |
+
1,
|
18 |
+
1,
|
19 |
+
1,
|
20 |
+
1,
|
21 |
+
1,
|
22 |
+
1
|
23 |
+
],
|
24 |
+
"attention_dropout": 0.1,
|
25 |
+
"attention_probs_dropout_prob": 0.1,
|
26 |
+
"attention_window": [
|
27 |
+
512,
|
28 |
+
512,
|
29 |
+
512,
|
30 |
+
512,
|
31 |
+
512,
|
32 |
+
512,
|
33 |
+
512,
|
34 |
+
512,
|
35 |
+
512,
|
36 |
+
512,
|
37 |
+
512,
|
38 |
+
512
|
39 |
+
],
|
40 |
+
"bos_token_id": 0,
|
41 |
+
"classif_dropout": 0.0,
|
42 |
+
"classifier_dropout": 0.0,
|
43 |
+
"d_model": 768,
|
44 |
+
"decoder_attention_heads": 12,
|
45 |
+
"decoder_ffn_dim": 3072,
|
46 |
+
"decoder_layerdrop": 0.0,
|
47 |
+
"decoder_layers": 12,
|
48 |
+
"decoder_start_token_id": 0,
|
49 |
+
"dropout": 0.1,
|
50 |
+
"early_stopping": true,
|
51 |
+
"encoder_attention_heads": 12,
|
52 |
+
"encoder_ffn_dim": 3072,
|
53 |
+
"encoder_layerdrop": 0.0,
|
54 |
+
"encoder_layers": 12,
|
55 |
+
"eos_token_id": 1,
|
56 |
+
"extra_pos_embeddings": 1,
|
57 |
+
"force_bos_token_to_be_generated": false,
|
58 |
+
"forced_eos_token_id": 1,
|
59 |
+
"init_std": 0.02,
|
60 |
+
"is_encoder_decoder": true,
|
61 |
+
"length_penalty": 2.0,
|
62 |
+
"max_decoder_position_embeddings": 512,
|
63 |
+
"max_encoder_position_embeddings": 8192,
|
64 |
+
"max_length": 512,
|
65 |
+
"max_position_embeddings": 8192,
|
66 |
+
"min_length": 100,
|
67 |
+
"model_type": "pegasus",
|
68 |
+
"no_repeat_ngram_size": 3,
|
69 |
+
"normalize_before": true,
|
70 |
+
"normalize_embedding": false,
|
71 |
+
"num_beams": 2,
|
72 |
+
"num_hidden_layers": 12,
|
73 |
+
"pad_token_id": 0,
|
74 |
+
"scale_embedding": true,
|
75 |
+
"static_position_embeddings": true,
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.30.2",
|
78 |
+
"use_cache": false,
|
79 |
+
"vocab_size": 96103
|
80 |
+
}
|
last-checkpoint/generation_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"forced_eos_token_id": 1,
|
7 |
+
"length_penalty": 2.0,
|
8 |
+
"max_length": 512,
|
9 |
+
"min_length": 100,
|
10 |
+
"no_repeat_ngram_size": 3,
|
11 |
+
"num_beams": 2,
|
12 |
+
"pad_token_id": 0,
|
13 |
+
"transformers_version": "4.30.2",
|
14 |
+
"use_cache": false
|
15 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f74d5f1a45d708b38e5462a32098619a77d216416ff27973af946caa6c7fbf36
|
3 |
+
size 3544920
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7ebbce591f251737d83478299d728e89bf21826c0f2b1592542f198360b0762
|
3 |
+
size 1140034381
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d74287cececdc4f6ced3ef29c8a8d27ff10637de332defa7d4dbb07c0865050
|
3 |
+
size 14511
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7345e2891e6c7505609bb455ba0e660aaff504ba8618e8322a39b4afd34a7832
|
3 |
+
size 627
|
last-checkpoint/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 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
107 |
+
"eos_token": "</s>",
|
108 |
+
"mask_token": "<mask_2>",
|
109 |
+
"mask_token_sent": "<mask_1>",
|
110 |
+
"model_max_length": 8192,
|
111 |
+
"offset": 103,
|
112 |
+
"pad_token": "<pad>",
|
113 |
+
"sp_model_kwargs": {},
|
114 |
+
"tokenizer_class": "PegasusTokenizer",
|
115 |
+
"unk_token": "<unk>"
|
116 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.32323232323232326,
|
5 |
+
"global_step": 40,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 4.9457994579945803e-05,
|
13 |
+
"loss": 4.3763,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.08,
|
18 |
+
"learning_rate": 4.878048780487805e-05,
|
19 |
+
"loss": 3.8394,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.12,
|
24 |
+
"learning_rate": 4.81029810298103e-05,
|
25 |
+
"loss": 3.639,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.16,
|
30 |
+
"learning_rate": 4.7425474254742554e-05,
|
31 |
+
"loss": 3.7962,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.2,
|
36 |
+
"learning_rate": 4.6747967479674795e-05,
|
37 |
+
"loss": 3.5152,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.24,
|
42 |
+
"learning_rate": 4.607046070460705e-05,
|
43 |
+
"loss": 3.5752,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.28,
|
48 |
+
"learning_rate": 4.53929539295393e-05,
|
49 |
+
"loss": 3.4463,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.32,
|
54 |
+
"learning_rate": 4.4715447154471546e-05,
|
55 |
+
"loss": 3.5218,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.32,
|
60 |
+
"eval_loss": 3.2419066429138184,
|
61 |
+
"eval_rouge2_fmeasure": 0.0,
|
62 |
+
"eval_rouge2_precision": 0.0,
|
63 |
+
"eval_rouge2_recall": 0.0,
|
64 |
+
"eval_runtime": 180.4791,
|
65 |
+
"eval_samples_per_second": 0.15,
|
66 |
+
"eval_steps_per_second": 0.078,
|
67 |
+
"step": 40
|
68 |
+
}
|
69 |
+
],
|
70 |
+
"max_steps": 369,
|
71 |
+
"num_train_epochs": 3,
|
72 |
+
"total_flos": 1560901173903360.0,
|
73 |
+
"trial_name": null,
|
74 |
+
"trial_params": null
|
75 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15f8f2ce7bcf861b6b5b78baf6158001d2b18da91cb88a0ef26f2379e4013039
|
3 |
+
size 4091
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7ebbce591f251737d83478299d728e89bf21826c0f2b1592542f198360b0762
|
3 |
+
size 1140034381
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
107 |
+
"eos_token": "</s>",
|
108 |
+
"mask_token": "<mask_2>",
|
109 |
+
"mask_token_sent": "<mask_1>",
|
110 |
+
"model_max_length": 8192,
|
111 |
+
"offset": 103,
|
112 |
+
"pad_token": "<pad>",
|
113 |
+
"sp_model_kwargs": {},
|
114 |
+
"tokenizer_class": "PegasusTokenizer",
|
115 |
+
"unk_token": "<unk>"
|
116 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15f8f2ce7bcf861b6b5b78baf6158001d2b18da91cb88a0ef26f2379e4013039
|
3 |
+
size 4091
|