Training in progress, epoch 1
Browse files- config.json +68 -0
- logs/events.out.tfevents.1712131310.9eaa26613b79.646.0 +3 -0
- logs/events.out.tfevents.1712131506.9eaa26613b79.646.1 +3 -0
- logs/events.out.tfevents.1712131779.9eaa26613b79.646.2 +3 -0
- logs/events.out.tfevents.1712132028.9eaa26613b79.646.3 +3 -0
- logs/events.out.tfevents.1712132041.9eaa26613b79.646.4 +3 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +66 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ibaucells/RoBERTa-ca-CaWikiTC",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"finetuning_task": "mnli",
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "LABEL_0",
|
| 17 |
+
"1": "LABEL_1",
|
| 18 |
+
"2": "LABEL_2",
|
| 19 |
+
"3": "LABEL_3",
|
| 20 |
+
"4": "LABEL_4",
|
| 21 |
+
"5": "LABEL_5",
|
| 22 |
+
"6": "LABEL_6",
|
| 23 |
+
"7": "LABEL_7",
|
| 24 |
+
"8": "LABEL_8",
|
| 25 |
+
"9": "LABEL_9",
|
| 26 |
+
"10": "LABEL_10",
|
| 27 |
+
"11": "LABEL_11",
|
| 28 |
+
"12": "LABEL_12",
|
| 29 |
+
"13": "LABEL_13",
|
| 30 |
+
"14": "LABEL_14",
|
| 31 |
+
"15": "LABEL_15",
|
| 32 |
+
"16": "LABEL_16"
|
| 33 |
+
},
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_10": 10,
|
| 40 |
+
"LABEL_11": 11,
|
| 41 |
+
"LABEL_12": 12,
|
| 42 |
+
"LABEL_13": 13,
|
| 43 |
+
"LABEL_14": 14,
|
| 44 |
+
"LABEL_15": 15,
|
| 45 |
+
"LABEL_16": 16,
|
| 46 |
+
"LABEL_2": 2,
|
| 47 |
+
"LABEL_3": 3,
|
| 48 |
+
"LABEL_4": 4,
|
| 49 |
+
"LABEL_5": 5,
|
| 50 |
+
"LABEL_6": 6,
|
| 51 |
+
"LABEL_7": 7,
|
| 52 |
+
"LABEL_8": 8,
|
| 53 |
+
"LABEL_9": 9
|
| 54 |
+
},
|
| 55 |
+
"layer_norm_eps": 1e-05,
|
| 56 |
+
"max_position_embeddings": 514,
|
| 57 |
+
"model_type": "roberta",
|
| 58 |
+
"num_attention_heads": 12,
|
| 59 |
+
"num_hidden_layers": 12,
|
| 60 |
+
"pad_token_id": 1,
|
| 61 |
+
"position_embedding_type": "absolute",
|
| 62 |
+
"problem_type": "single_label_classification",
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.38.2",
|
| 65 |
+
"type_vocab_size": 1,
|
| 66 |
+
"use_cache": true,
|
| 67 |
+
"vocab_size": 50262
|
| 68 |
+
}
|
logs/events.out.tfevents.1712131310.9eaa26613b79.646.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e58e4c0f864eae47ca47c685a6351efab62827007a481c106b689ed882238f1c
|
| 3 |
+
size 5432
|
logs/events.out.tfevents.1712131506.9eaa26613b79.646.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b76380a53f274b0059c7618084fd2849b6631e265a4c2eb57ab4bd207620ce9
|
| 3 |
+
size 5432
|
logs/events.out.tfevents.1712131779.9eaa26613b79.646.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e04ea0197d20537d2216d8d7f51c9d725e29faa4423593c165db823afd29eae
|
| 3 |
+
size 6141
|
logs/events.out.tfevents.1712132028.9eaa26613b79.646.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fc3b9fed3982370967247907ebfbf07a27a946c849362faf9b8136761d66903
|
| 3 |
+
size 5428
|
logs/events.out.tfevents.1712132041.9eaa26613b79.646.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d782f900242051ae007d1282e6c2b2dcd20849fd35dbdd98901b67d9b6a1e53
|
| 3 |
+
size 8604
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:491631cb89aaf0ae98234a95e6fa93a7239e55b6bdac9a022f9e17bf77219d44
|
| 3 |
+
size 498649748
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"device": 0,
|
| 49 |
+
"eos_token": "</s>",
|
| 50 |
+
"errors": "replace",
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"max_len": 512,
|
| 53 |
+
"max_length": 512,
|
| 54 |
+
"model_max_length": 512,
|
| 55 |
+
"pad_to_multiple_of": null,
|
| 56 |
+
"pad_token": "<pad>",
|
| 57 |
+
"pad_token_type_id": 0,
|
| 58 |
+
"padding_side": "right",
|
| 59 |
+
"sep_token": "</s>",
|
| 60 |
+
"stride": 0,
|
| 61 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 62 |
+
"trim_offsets": true,
|
| 63 |
+
"truncation_side": "right",
|
| 64 |
+
"truncation_strategy": "longest_first",
|
| 65 |
+
"unk_token": "<unk>"
|
| 66 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:891e0456aec04c0151168e6b4ffccc10ba7e0470d1eff3a6c7a2d2c623d5b23b
|
| 3 |
+
size 4920
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|