Hugging Face's logo

ofirzaf
/
bert-large-uncased-squad

Question Answering
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
1
ofirzaf commited on
Commit
57953dd
•
1 Parent(s): 69182eb

initial commit

Browse files
Files changed (11) hide show
  1. all_results.json +17 -0
  2. config.json +24 -0
  3. eval_results.json +5 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +1 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +1 -0
  8. train_results.json +14 -0
  9. trainer_state.json +71 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_samples": 10784,
4
+ "exact_match": 84.12488174077578,
5
+ "f1": 91.04804757290493,
6
+ "init_mem_cpu_alloc_delta": 2174533632,
7
+ "init_mem_cpu_peaked_delta": 122687488,
8
+ "init_mem_gpu_alloc_delta": 1337192960,
9
+ "init_mem_gpu_peaked_delta": 0,
10
+ "train_mem_cpu_alloc_delta": 432713728,
11
+ "train_mem_cpu_peaked_delta": 246333440,
12
+ "train_mem_gpu_alloc_delta": 4046356480,
13
+ "train_mem_gpu_peaked_delta": 22872401920,
14
+ "train_runtime": 3222.535,
15
+ "train_samples": 88524,
16
+ "train_samples_per_second": 0.686
17
+ }
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
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": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.6.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
eval_results.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eval_samples": 10784,
3
+ "exact_match": 84.12488174077578,
4
+ "f1": 91.04804757290493
5
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d86be3cb439f2207665d3fe44265d733512aa2c94214788c082c4468a4ec1d
3
+ size 1336542929
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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "init_mem_cpu_alloc_delta": 2174533632,
4
+ "init_mem_cpu_peaked_delta": 122687488,
5
+ "init_mem_gpu_alloc_delta": 1337192960,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 432713728,
8
+ "train_mem_cpu_peaked_delta": 246333440,
9
+ "train_mem_gpu_alloc_delta": 4046356480,
10
+ "train_mem_gpu_peaked_delta": 22872401920,
11
+ "train_runtime": 3222.535,
12
+ "train_samples": 88524,
13
+ "train_samples_per_second": 0.686
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.999322340185227,
5
+ "global_step": 2212,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.45,
12
+ "learning_rate": 4.311557788944724e-05,
13
+ "loss": 1.8701,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.45,
18
+ "exact_match": 79.49858088930937,
19
+ "f1": 87.56398459706838,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 0.9,
24
+ "learning_rate": 3.057788944723618e-05,
25
+ "loss": 0.9835,
26
+ "step": 1000
27
+ },
28
+ {
29
+ "epoch": 0.9,
30
+ "exact_match": 82.90444654683066,
31
+ "f1": 89.73526941390388,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 1.36,
36
+ "learning_rate": 1.801507537688442e-05,
37
+ "loss": 0.7131,
38
+ "step": 1500
39
+ },
40
+ {
41
+ "epoch": 1.36,
42
+ "exact_match": 83.78429517502366,
43
+ "f1": 90.6613951393689,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 1.81,
48
+ "learning_rate": 5.452261306532663e-06,
49
+ "loss": 0.6276,
50
+ "step": 2000
51
+ },
52
+ {
53
+ "epoch": 1.81,
54
+ "exact_match": 84.1438032166509,
55
+ "f1": 90.984962516233,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 2.0,
60
+ "step": 2212,
61
+ "total_flos": 1.36249422804523e+17,
62
+ "train_runtime": 3222.535,
63
+ "train_samples_per_second": 0.686
64
+ }
65
+ ],
66
+ "max_steps": 2212,
67
+ "num_train_epochs": 2,
68
+ "total_flos": 1.36249422804523e+17,
69
+ "trial_name": null,
70
+ "trial_params": null
71
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c2368b5be8baec1801e72fbf6c930c51a9d88497ee3466d4a354a108bec68a
3
+ size 2479
vocab.txt ADDED
The diff for this file is too large to render. See raw diff