moussaKam commited on
Commit
04487cb
1 Parent(s): 56c35dc
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 2160803840,
4
+ "init_mem_cpu_peaked_delta": 12996608,
5
+ "init_mem_gpu_alloc_delta": 17548800,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 14491648000,
8
+ "train_mem_cpu_peaked_delta": 174706688,
9
+ "train_mem_gpu_alloc_delta": 53029376,
10
+ "train_mem_gpu_peaked_delta": 669877760,
11
+ "train_runtime": 37325.4581,
12
+ "train_samples": 4500000,
13
+ "train_samples_per_second": 11.303
14
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 512,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 2,
23
+ "num_hidden_layers": 2,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "transformers_version": "4.6.0.dev0",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 30522
30
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5291f740d57b97ba5a32c53eca370276fe29044a905ded8de4c2022c5112b38b
3
+ size 17565609
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "google/bert_uncased_L-2_H-128_A-2", "do_basic_tokenize": true, "never_split": null}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 2160803840,
4
+ "init_mem_cpu_peaked_delta": 12996608,
5
+ "init_mem_gpu_alloc_delta": 17548800,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 14491648000,
8
+ "train_mem_cpu_peaked_delta": 174706688,
9
+ "train_mem_gpu_alloc_delta": 53029376,
10
+ "train_mem_gpu_peaked_delta": 669877760,
11
+ "train_runtime": 37325.4581,
12
+ "train_samples": 4500000,
13
+ "train_samples_per_second": 11.303
14
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8afc4d4e0c149b35266e25c644cf727fb6395869117b8429211b96653173c8
3
+ size 2543
vocab.txt ADDED
The diff for this file is too large to render. See raw diff