Training in progress, step 500
Browse files- added_tokens.json +24 -24
- config.json +46 -60
- pytorch_model.bin +2 -2
- runs/Mar15_07-26-14_ef61eddbf762/1678865590.8356483/events.out.tfevents.1678865590.ef61eddbf762.130.1 +3 -0
- runs/Mar15_07-26-14_ef61eddbf762/events.out.tfevents.1678865590.ef61eddbf762.130.0 +3 -0
- special_tokens_map.json +0 -10
- tokenizer.json +0 -0
- tokenizer_config.json +106 -10
- training_args.bin +1 -1
added_tokens.json
CHANGED
|
@@ -1,26 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
":ARG0":
|
| 3 |
-
":ARG1":
|
| 4 |
-
":ARG2":
|
| 5 |
-
":ARG3":
|
| 6 |
-
":ARG4":
|
| 7 |
-
":ARG5":
|
| 8 |
-
":ARGM-CAU":
|
| 9 |
-
":ARGM-DIR":
|
| 10 |
-
":ARGM-EXT":
|
| 11 |
-
":ARGM-LOC":
|
| 12 |
-
":ARGM-MNR":
|
| 13 |
-
":ARGM-NEG":
|
| 14 |
-
":ARGM-PRP":
|
| 15 |
-
":ARGM-TMP":
|
| 16 |
-
":graph1":
|
| 17 |
-
":graph10":
|
| 18 |
-
":graph2":
|
| 19 |
-
":graph3":
|
| 20 |
-
":graph4":
|
| 21 |
-
":graph5":
|
| 22 |
-
":graph6":
|
| 23 |
-
":graph7":
|
| 24 |
-
":graph8":
|
| 25 |
-
":graph9":
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
":ARG0": 32100,
|
| 3 |
+
":ARG1": 32101,
|
| 4 |
+
":ARG2": 32102,
|
| 5 |
+
":ARG3": 32103,
|
| 6 |
+
":ARG4": 32104,
|
| 7 |
+
":ARG5": 32105,
|
| 8 |
+
":ARGM-CAU": 32110,
|
| 9 |
+
":ARGM-DIR": 32111,
|
| 10 |
+
":ARGM-EXT": 32112,
|
| 11 |
+
":ARGM-LOC": 32106,
|
| 12 |
+
":ARGM-MNR": 32108,
|
| 13 |
+
":ARGM-NEG": 32113,
|
| 14 |
+
":ARGM-PRP": 32109,
|
| 15 |
+
":ARGM-TMP": 32107,
|
| 16 |
+
":graph1": 32114,
|
| 17 |
+
":graph10": 32123,
|
| 18 |
+
":graph2": 32115,
|
| 19 |
+
":graph3": 32116,
|
| 20 |
+
":graph4": 32117,
|
| 21 |
+
":graph5": 32118,
|
| 22 |
+
":graph6": 32119,
|
| 23 |
+
":graph7": 32120,
|
| 24 |
+
":graph8": 32121,
|
| 25 |
+
":graph9": 32122
|
| 26 |
}
|
config.json
CHANGED
|
@@ -1,74 +1,60 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"activation_dropout": 0.1,
|
| 4 |
-
"activation_function": "gelu",
|
| 5 |
-
"add_bias_logits": false,
|
| 6 |
-
"add_final_layer_norm": false,
|
| 7 |
"architectures": [
|
| 8 |
-
"
|
| 9 |
],
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"decoder_start_token_id": 2,
|
| 20 |
-
"dropout": 0.1,
|
| 21 |
-
"early_stopping": true,
|
| 22 |
-
"encoder_attention_heads": 16,
|
| 23 |
-
"encoder_ffn_dim": 4096,
|
| 24 |
-
"encoder_layerdrop": 0.0,
|
| 25 |
-
"encoder_layers": 12,
|
| 26 |
-
"eos_token_id": 2,
|
| 27 |
-
"forced_bos_token_id": 0,
|
| 28 |
-
"forced_eos_token_id": 2,
|
| 29 |
-
"gradient_checkpointing": false,
|
| 30 |
-
"id2label": {
|
| 31 |
-
"0": "LABEL_0",
|
| 32 |
-
"1": "LABEL_1",
|
| 33 |
-
"2": "LABEL_2"
|
| 34 |
-
},
|
| 35 |
-
"init_std": 0.02,
|
| 36 |
"is_encoder_decoder": true,
|
| 37 |
-
"
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"pad_token_id": 1,
|
| 49 |
-
"scale_embedding": false,
|
| 50 |
"task_specific_params": {
|
| 51 |
"summarization": {
|
| 52 |
-
"
|
| 53 |
-
"max_length": 128,
|
| 54 |
-
"min_length": 12,
|
| 55 |
-
"num_beams": 4
|
| 56 |
-
},
|
| 57 |
-
"summarization_cnn": {
|
| 58 |
"length_penalty": 2.0,
|
| 59 |
-
"max_length":
|
| 60 |
-
"min_length":
|
| 61 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
},
|
| 63 |
-
"
|
| 64 |
-
"
|
| 65 |
-
"max_length":
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
}
|
| 69 |
},
|
| 70 |
"torch_dtype": "float32",
|
| 71 |
"transformers_version": "4.26.1",
|
| 72 |
"use_cache": true,
|
| 73 |
-
"vocab_size":
|
| 74 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "t5-small",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 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": 6,
|
| 21 |
+
"num_heads": 8,
|
| 22 |
+
"num_layers": 6,
|
| 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": "4.26.1",
|
| 58 |
"use_cache": true,
|
| 59 |
+
"vocab_size": 32124
|
| 60 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f75cd7599b8b193c1a91f8df58c09e6029f0faf0427a6f6a08aa3b6544a7db18
|
| 3 |
+
size 242063449
|
runs/Mar15_07-26-14_ef61eddbf762/1678865590.8356483/events.out.tfevents.1678865590.ef61eddbf762.130.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18f6d7cf8e870dce8d13e931b639bcc40aa85fb37bcf73d74b7d5d14c5368798
|
| 3 |
+
size 5882
|
runs/Mar15_07-26-14_ef61eddbf762/events.out.tfevents.1678865590.ef61eddbf762.130.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3feb74cf80d78c52e437e38c0bdc0aa9c3fc993dabb9148cb0c3f0d73e8dd39c
|
| 3 |
+
size 5706
|
special_tokens_map.json
CHANGED
|
@@ -25,17 +25,7 @@
|
|
| 25 |
":graph9",
|
| 26 |
":graph10"
|
| 27 |
],
|
| 28 |
-
"bos_token": "<s>",
|
| 29 |
-
"cls_token": "<s>",
|
| 30 |
"eos_token": "</s>",
|
| 31 |
-
"mask_token": {
|
| 32 |
-
"content": "<mask>",
|
| 33 |
-
"lstrip": true,
|
| 34 |
-
"normalized": false,
|
| 35 |
-
"rstrip": false,
|
| 36 |
-
"single_word": false
|
| 37 |
-
},
|
| 38 |
"pad_token": "<pad>",
|
| 39 |
-
"sep_token": "</s>",
|
| 40 |
"unk_token": "<unk>"
|
| 41 |
}
|
|
|
|
| 25 |
":graph9",
|
| 26 |
":graph10"
|
| 27 |
],
|
|
|
|
|
|
|
| 28 |
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"pad_token": "<pad>",
|
|
|
|
| 30 |
"unk_token": "<unk>"
|
| 31 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,16 +1,112 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"eos_token": "</s>",
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"name_or_path": "facebook/bart-large",
|
| 10 |
"pad_token": "<pad>",
|
| 11 |
-
"sep_token": "</s>",
|
| 12 |
"special_tokens_map_file": null,
|
| 13 |
-
"tokenizer_class": "
|
| 14 |
-
"trim_offsets": true,
|
| 15 |
"unk_token": "<unk>"
|
| 16 |
}
|
|
|
|
| 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": 512,
|
| 107 |
+
"name_or_path": "t5-small",
|
|
|
|
| 108 |
"pad_token": "<pad>",
|
|
|
|
| 109 |
"special_tokens_map_file": null,
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
|
|
|
| 111 |
"unk_token": "<unk>"
|
| 112 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a30bd09f4afc5c21d55974f45dcdf6d0bc7c83e942122064a692247db45e17d0
|
| 3 |
size 3579
|