Upload 12 files
Browse files- config.json +62 -0
- generation_config.json +16 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +110 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +118 -0
- trainer_state.json +318 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/pegasus-x-base",
|
| 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": 768,
|
| 16 |
+
"decoder_attention_heads": 12,
|
| 17 |
+
"decoder_ffn_dim": 3072,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 12,
|
| 20 |
+
"decoder_start_token_id": 0,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 12,
|
| 24 |
+
"encoder_ffn_dim": 3072,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 1,
|
| 28 |
+
"extra_pos_embeddings": 1,
|
| 29 |
+
"force_bos_token_to_be_generated": false,
|
| 30 |
+
"forced_eos_token_id": 1,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1",
|
| 34 |
+
"2": "LABEL_2"
|
| 35 |
+
},
|
| 36 |
+
"init_std": 0.02,
|
| 37 |
+
"is_encoder_decoder": true,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"LABEL_0": 0,
|
| 40 |
+
"LABEL_1": 1,
|
| 41 |
+
"LABEL_2": 2
|
| 42 |
+
},
|
| 43 |
+
"length_penalty": 2.0,
|
| 44 |
+
"max_length": 512,
|
| 45 |
+
"max_position_embeddings": 16384,
|
| 46 |
+
"min_length": 100,
|
| 47 |
+
"model_type": "pegasus_x",
|
| 48 |
+
"no_repeat_ngram_size": 3,
|
| 49 |
+
"normalize_before": true,
|
| 50 |
+
"normalize_embedding": false,
|
| 51 |
+
"num_beams": 2,
|
| 52 |
+
"num_global_tokens": 128,
|
| 53 |
+
"num_hidden_layers": 12,
|
| 54 |
+
"pad_token_id": 0,
|
| 55 |
+
"scale_embedding": true,
|
| 56 |
+
"stagger_local_blocks": true,
|
| 57 |
+
"static_position_embeddings": true,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.26.1",
|
| 60 |
+
"use_cache": false,
|
| 61 |
+
"vocab_size": 96103
|
| 62 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 0,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 1,
|
| 7 |
+
"forced_eos_token_id": 1,
|
| 8 |
+
"length_penalty": 2.0,
|
| 9 |
+
"max_length": 512,
|
| 10 |
+
"min_length": 100,
|
| 11 |
+
"no_repeat_ngram_size": 3,
|
| 12 |
+
"num_beams": 2,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"transformers_version": "4.26.1",
|
| 15 |
+
"use_cache": false
|
| 16 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc0721c949ea8c0652575a7a7965236d8430d208950c59b2512d24ef8e5a39e9
|
| 3 |
+
size 2178566661
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1ef6da9222f0db7ccec9a7714a6b0fa2b15788cf63bffde8e65de3af073cc50
|
| 3 |
+
size 1089301733
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1b9d7043ccd8afec2aa413640303022422f0689c0ef3679c13bc1ab6ad7b200
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37565a3fc8b8a3d73ae2398cca6bd61a01fe9813fd4bb04d4f2cd5b97983d762
|
| 3 |
+
size 627
|
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": "google/pegasus-x-base",
|
| 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 +1,318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.582800284292822,
|
| 5 |
+
"global_step": 8000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.24,
|
| 12 |
+
"learning_rate": 8.333333333333334e-06,
|
| 13 |
+
"loss": 5.2679,
|
| 14 |
+
"step": 250
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.47,
|
| 18 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 19 |
+
"loss": 4.0457,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.71,
|
| 24 |
+
"learning_rate": 2.5e-05,
|
| 25 |
+
"loss": 3.7746,
|
| 26 |
+
"step": 750
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.71,
|
| 30 |
+
"eval_loss": 3.4735970497131348,
|
| 31 |
+
"eval_rouge2_fmeasure": 0.0608,
|
| 32 |
+
"eval_rouge2_precision": 0.0752,
|
| 33 |
+
"eval_rouge2_recall": 0.0676,
|
| 34 |
+
"eval_runtime": 10444.2518,
|
| 35 |
+
"eval_samples_per_second": 0.09,
|
| 36 |
+
"eval_steps_per_second": 0.09,
|
| 37 |
+
"step": 750
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.95,
|
| 41 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 42 |
+
"loss": 3.6193,
|
| 43 |
+
"step": 1000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.18,
|
| 47 |
+
"learning_rate": 4.166666666666667e-05,
|
| 48 |
+
"loss": 3.5271,
|
| 49 |
+
"step": 1250
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.42,
|
| 53 |
+
"learning_rate": 5e-05,
|
| 54 |
+
"loss": 3.4793,
|
| 55 |
+
"step": 1500
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.42,
|
| 59 |
+
"eval_loss": 3.331468105316162,
|
| 60 |
+
"eval_rouge2_fmeasure": 0.0653,
|
| 61 |
+
"eval_rouge2_precision": 0.0796,
|
| 62 |
+
"eval_rouge2_recall": 0.0735,
|
| 63 |
+
"eval_runtime": 10901.7035,
|
| 64 |
+
"eval_samples_per_second": 0.086,
|
| 65 |
+
"eval_steps_per_second": 0.086,
|
| 66 |
+
"step": 1500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.66,
|
| 70 |
+
"learning_rate": 4.8529411764705885e-05,
|
| 71 |
+
"loss": 3.4251,
|
| 72 |
+
"step": 1750
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.9,
|
| 76 |
+
"learning_rate": 4.705882352941177e-05,
|
| 77 |
+
"loss": 3.4313,
|
| 78 |
+
"step": 2000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.13,
|
| 82 |
+
"learning_rate": 4.558823529411765e-05,
|
| 83 |
+
"loss": 3.3459,
|
| 84 |
+
"step": 2250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.13,
|
| 88 |
+
"eval_loss": 3.2606232166290283,
|
| 89 |
+
"eval_rouge2_fmeasure": 0.0685,
|
| 90 |
+
"eval_rouge2_precision": 0.0825,
|
| 91 |
+
"eval_rouge2_recall": 0.077,
|
| 92 |
+
"eval_runtime": 10929.9339,
|
| 93 |
+
"eval_samples_per_second": 0.086,
|
| 94 |
+
"eval_steps_per_second": 0.086,
|
| 95 |
+
"step": 2250
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.37,
|
| 99 |
+
"learning_rate": 4.411764705882353e-05,
|
| 100 |
+
"loss": 3.291,
|
| 101 |
+
"step": 2500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.61,
|
| 105 |
+
"learning_rate": 4.2647058823529415e-05,
|
| 106 |
+
"loss": 3.2803,
|
| 107 |
+
"step": 2750
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.84,
|
| 111 |
+
"learning_rate": 4.11764705882353e-05,
|
| 112 |
+
"loss": 3.2948,
|
| 113 |
+
"step": 3000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.84,
|
| 117 |
+
"eval_loss": 3.227094888687134,
|
| 118 |
+
"eval_rouge2_fmeasure": 0.0684,
|
| 119 |
+
"eval_rouge2_precision": 0.0815,
|
| 120 |
+
"eval_rouge2_recall": 0.078,
|
| 121 |
+
"eval_runtime": 11536.812,
|
| 122 |
+
"eval_samples_per_second": 0.081,
|
| 123 |
+
"eval_steps_per_second": 0.081,
|
| 124 |
+
"step": 3000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.08,
|
| 128 |
+
"learning_rate": 3.970588235294117e-05,
|
| 129 |
+
"loss": 3.2314,
|
| 130 |
+
"step": 3250
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 3.32,
|
| 134 |
+
"learning_rate": 3.8235294117647055e-05,
|
| 135 |
+
"loss": 3.2134,
|
| 136 |
+
"step": 3500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 3.55,
|
| 140 |
+
"learning_rate": 3.6764705882352945e-05,
|
| 141 |
+
"loss": 3.1879,
|
| 142 |
+
"step": 3750
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.55,
|
| 146 |
+
"eval_loss": 3.2067530155181885,
|
| 147 |
+
"eval_rouge2_fmeasure": 0.0704,
|
| 148 |
+
"eval_rouge2_precision": 0.083,
|
| 149 |
+
"eval_rouge2_recall": 0.0809,
|
| 150 |
+
"eval_runtime": 11358.1561,
|
| 151 |
+
"eval_samples_per_second": 0.083,
|
| 152 |
+
"eval_steps_per_second": 0.083,
|
| 153 |
+
"step": 3750
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 3.79,
|
| 157 |
+
"learning_rate": 3.529411764705883e-05,
|
| 158 |
+
"loss": 3.1617,
|
| 159 |
+
"step": 4000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.03,
|
| 163 |
+
"learning_rate": 3.382352941176471e-05,
|
| 164 |
+
"loss": 3.172,
|
| 165 |
+
"step": 4250
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.27,
|
| 169 |
+
"learning_rate": 3.235294117647059e-05,
|
| 170 |
+
"loss": 3.1038,
|
| 171 |
+
"step": 4500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.27,
|
| 175 |
+
"eval_loss": 3.1938178539276123,
|
| 176 |
+
"eval_rouge2_fmeasure": 0.0716,
|
| 177 |
+
"eval_rouge2_precision": 0.0858,
|
| 178 |
+
"eval_rouge2_recall": 0.0813,
|
| 179 |
+
"eval_runtime": 10958.7861,
|
| 180 |
+
"eval_samples_per_second": 0.086,
|
| 181 |
+
"eval_steps_per_second": 0.086,
|
| 182 |
+
"step": 4500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.5,
|
| 186 |
+
"learning_rate": 3.0882352941176475e-05,
|
| 187 |
+
"loss": 3.1153,
|
| 188 |
+
"step": 4750
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.74,
|
| 192 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 193 |
+
"loss": 3.1037,
|
| 194 |
+
"step": 5000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.98,
|
| 198 |
+
"learning_rate": 2.7941176470588236e-05,
|
| 199 |
+
"loss": 3.1155,
|
| 200 |
+
"step": 5250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.98,
|
| 204 |
+
"eval_loss": 3.187068462371826,
|
| 205 |
+
"eval_rouge2_fmeasure": 0.0725,
|
| 206 |
+
"eval_rouge2_precision": 0.0856,
|
| 207 |
+
"eval_rouge2_recall": 0.0839,
|
| 208 |
+
"eval_runtime": 11370.9481,
|
| 209 |
+
"eval_samples_per_second": 0.083,
|
| 210 |
+
"eval_steps_per_second": 0.083,
|
| 211 |
+
"step": 5250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 5.21,
|
| 215 |
+
"learning_rate": 2.647058823529412e-05,
|
| 216 |
+
"loss": 3.048,
|
| 217 |
+
"step": 5500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 5.45,
|
| 221 |
+
"learning_rate": 2.5e-05,
|
| 222 |
+
"loss": 3.0603,
|
| 223 |
+
"step": 5750
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.69,
|
| 227 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 228 |
+
"loss": 3.0534,
|
| 229 |
+
"step": 6000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 5.69,
|
| 233 |
+
"eval_loss": 3.181117057800293,
|
| 234 |
+
"eval_rouge2_fmeasure": 0.0735,
|
| 235 |
+
"eval_rouge2_precision": 0.0865,
|
| 236 |
+
"eval_rouge2_recall": 0.0848,
|
| 237 |
+
"eval_runtime": 11629.6122,
|
| 238 |
+
"eval_samples_per_second": 0.081,
|
| 239 |
+
"eval_steps_per_second": 0.081,
|
| 240 |
+
"step": 6000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.92,
|
| 244 |
+
"learning_rate": 2.2058823529411766e-05,
|
| 245 |
+
"loss": 3.0664,
|
| 246 |
+
"step": 6250
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 6.16,
|
| 250 |
+
"learning_rate": 2.058823529411765e-05,
|
| 251 |
+
"loss": 3.0255,
|
| 252 |
+
"step": 6500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 6.4,
|
| 256 |
+
"learning_rate": 1.9117647058823528e-05,
|
| 257 |
+
"loss": 3.0338,
|
| 258 |
+
"step": 6750
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 6.4,
|
| 262 |
+
"eval_loss": 3.1781060695648193,
|
| 263 |
+
"eval_rouge2_fmeasure": 0.0747,
|
| 264 |
+
"eval_rouge2_precision": 0.0879,
|
| 265 |
+
"eval_rouge2_recall": 0.0865,
|
| 266 |
+
"eval_runtime": 11275.9298,
|
| 267 |
+
"eval_samples_per_second": 0.083,
|
| 268 |
+
"eval_steps_per_second": 0.083,
|
| 269 |
+
"step": 6750
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 6.63,
|
| 273 |
+
"learning_rate": 1.7647058823529414e-05,
|
| 274 |
+
"loss": 2.9872,
|
| 275 |
+
"step": 7000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 6.87,
|
| 279 |
+
"learning_rate": 1.6176470588235296e-05,
|
| 280 |
+
"loss": 3.0128,
|
| 281 |
+
"step": 7250
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 7.11,
|
| 285 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 286 |
+
"loss": 3.0266,
|
| 287 |
+
"step": 7500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 7.11,
|
| 291 |
+
"eval_loss": 3.1731793880462646,
|
| 292 |
+
"eval_rouge2_fmeasure": 0.074,
|
| 293 |
+
"eval_rouge2_precision": 0.0886,
|
| 294 |
+
"eval_rouge2_recall": 0.0836,
|
| 295 |
+
"eval_runtime": 11197.1963,
|
| 296 |
+
"eval_samples_per_second": 0.084,
|
| 297 |
+
"eval_steps_per_second": 0.084,
|
| 298 |
+
"step": 7500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 7.35,
|
| 302 |
+
"learning_rate": 1.323529411764706e-05,
|
| 303 |
+
"loss": 2.9676,
|
| 304 |
+
"step": 7750
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 7.58,
|
| 308 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 309 |
+
"loss": 2.9834,
|
| 310 |
+
"step": 8000
|
| 311 |
+
}
|
| 312 |
+
],
|
| 313 |
+
"max_steps": 10000,
|
| 314 |
+
"num_train_epochs": 10,
|
| 315 |
+
"total_flos": 1.248414149407408e+18,
|
| 316 |
+
"trial_name": null,
|
| 317 |
+
"trial_params": null
|
| 318 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b1cbd06825f5f91c2f78f18190e09bad91e0918abcd1a637bcb25452f8f80e9
|
| 3 |
+
size 3707
|