Aunsiels commited on
Commit
86b1bed
1 Parent(s): cbd5c9b

Upload 10 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"<SEP>": 28998, "<BOS>": 28996, "<PAD>": 28999, "<EOS>": 28997}
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-cased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "transformers_version": "4.5.1",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 29000
30
+ }
eval_results_mlm.txt ADDED
@@ -0,0 +1 @@
 
1
+ perplexity = 11.000638008243978
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1af4f0f3524fa8ffd0f6083132bed8a0309bba8f0e4104cfdc66e47101a6ca5
3
+ size 1334625496
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<BOS>", "eos_token": "<EOS>", "unk_token": "[UNK]", "sep_token": "<SEP>", "pad_token": "<PAD>", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-cased"}
train_results.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch = 5.0
2
+ init_mem_cpu_alloc_delta = 1159303168
3
+ init_mem_cpu_peaked_delta = 916664320
4
+ init_mem_gpu_alloc_delta = 1335215616
5
+ init_mem_gpu_peaked_delta = 0
6
+ train_mem_cpu_alloc_delta = 29356032
7
+ train_mem_cpu_peaked_delta = 0
8
+ train_mem_gpu_alloc_delta = 4003456000
9
+ train_mem_gpu_peaked_delta = 19106743296
10
+ train_runtime = 393.5719
11
+ train_samples_per_second = 0.978
trainer_state.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 385,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 5.0,
12
+ "step": 385,
13
+ "total_flos": 3141206509117440.0,
14
+ "train_runtime": 393.5719,
15
+ "train_samples_per_second": 0.978
16
+ }
17
+ ],
18
+ "max_steps": 385,
19
+ "num_train_epochs": 5,
20
+ "total_flos": 3141206509117440.0,
21
+ "trial_name": null,
22
+ "trial_params": null
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d6747927314afef61a048408044c8503515955e00c6d9c7bf4bd12f66916167
3
+ size 2351
vocab.txt ADDED
The diff for this file is too large to render. See raw diff