haibotamiu commited on
Commit
d7785c4
1 Parent(s): 5e0a508

Model save

Browse files
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 4.621011098225911,
4
- "train_runtime": 40.2608,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 223.543,
7
- "train_steps_per_second": 0.894
8
  }
 
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 4.621011098225911,
4
+ "train_runtime": 40.2946,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 223.355,
7
+ "train_steps_per_second": 0.893
8
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:487e31429614afd7e284f2fbbfa60f8641f08267f6cb8303e68bafbbe12cd651
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abc41cf6e45166d7704c9e792670b81f9584e8f4f477af4235a86aa107312ece
3
  size 5652
config.json CHANGED
@@ -2,7 +2,7 @@
2
  "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
- "QuantizedDistilBertForQuestionAnswering"
6
  ],
7
  "attention_dropout": 0.1,
8
  "dim": 768,
 
2
  "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
  ],
7
  "attention_dropout": 0.1,
8
  "dim": 768,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3ef050729f0931a1ab4b251d4ccc9bd10abefc57d7de8209769201e2e17232c
3
- size 265832945
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f49d0d4ef9d2b6a142d56f5151687051e5e54606390c6de709e339848665c4
3
+ size 265493026
raw_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1f0839ac6d21be64cac0d009add03e24b92d8146d213fbb1f1473a3a4c3ea9e
3
- size 265864653
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace5d339b09a1b5d89214c499f75ccb2fefdcce154e576b06cc71a1361c8eb03
3
+ size 435382250
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 384,
6
- "strategy": "OnlySecond",
7
- "stride": 128
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 384
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 0,
16
- "pad_type_id": 0,
17
- "pad_token": "[PAD]"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 4.621011098225911,
4
- "train_runtime": 40.2608,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 223.543,
7
- "train_steps_per_second": 0.894
8
  }
 
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 4.621011098225911,
4
+ "train_runtime": 40.2946,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 223.355,
7
+ "train_steps_per_second": 0.893
8
  }
trainer_state.json CHANGED
@@ -13,9 +13,9 @@
13
  "step": 36,
14
  "total_flos": 881908425216000.0,
15
  "train_loss": 4.621011098225911,
16
- "train_runtime": 40.2608,
17
- "train_samples_per_second": 223.543,
18
- "train_steps_per_second": 0.894
19
  }
20
  ],
21
  "logging_steps": 500,
 
13
  "step": 36,
14
  "total_flos": 881908425216000.0,
15
  "train_loss": 4.621011098225911,
16
+ "train_runtime": 40.2946,
17
+ "train_samples_per_second": 223.355,
18
+ "train_steps_per_second": 0.893
19
  }
20
  ],
21
  "logging_steps": 500,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:907d06d261539b8a1e3605fab8d7d4bf5f2b4926be120fd5f849138fc9cb68e7
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232a44bf482ca5a92e56f6d7c781e94d5a384f3b15bcb46eef3b2e0869dcddd9
3
  size 4664