srcocotero commited on
Commit
81006e8
1 Parent(s): 9d2871c

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
@@ -8,14 +8,14 @@
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
  "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
  "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "torch_dtype": "float32",
 
1
  {
2
+ "_name_or_path": "bert-large-uncased",
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
 
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
  "position_embedding_type": "absolute",
21
  "torch_dtype": "float32",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:849a59f71e71db8f80bced81e7e1b2420aaadc750d756b68f2b886d061f98847
3
- size 435643185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b22a8e9ba9515e56628d1abbf7ad18e5e0e7f718ccde7ff7d8d891459e8a626f
3
+ size 1336512689
runs/Aug11_08-18-32_1be7fe59a580/1660206317.0508385/events.out.tfevents.1660206317.1be7fe59a580.402.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78d4e01b201d73cca4487ebb4af50ab09c9617e1f2ea55d4c012865811ffac7
3
+ size 5450
runs/Aug11_08-18-32_1be7fe59a580/events.out.tfevents.1660206317.1be7fe59a580.402.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e611a1a92cf0d121bf383ba7dd51db2333aaffa154fb35d6a6d311e2c7fe021d
3
+ size 3691
runs/Aug11_08-26-39_1be7fe59a580/1660206482.9024284/events.out.tfevents.1660206482.1be7fe59a580.532.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5be3df94b0e852a6483a74259389231a1108610979a1b837352d6542a40e02
3
+ size 5450
runs/Aug11_08-26-39_1be7fe59a580/events.out.tfevents.1660206482.1be7fe59a580.532.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6cf9418c729edde01721a8e6a2049fd4f92720799836af486ccb72e3b0aa4f
3
+ size 3847
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 512,
6
  "strategy": "OnlySecond",
7
  "stride": 128
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 512
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 256,
6
  "strategy": "OnlySecond",
7
  "stride": 128
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 256
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "do_lower_case": true,
4
  "mask_token": "[MASK]",
5
  "model_max_length": 512,
6
- "name_or_path": "bert-base-uncased",
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "special_tokens_map_file": null,
 
3
  "do_lower_case": true,
4
  "mask_token": "[MASK]",
5
  "model_max_length": 512,
6
+ "name_or_path": "bert-large-uncased",
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "special_tokens_map_file": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91b7488f97da025180e210796811ecec5ddd5c9b83ad319282b873324fa7ae54
3
  size 3375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f2d1af2b461509c59568493fa72effe9106b7a86dde014eea50f6167118b23
3
  size 3375