anaryegen commited on
Commit
96f298f
1 Parent(s): 798aa8c

update model

Browse files
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.24564219588448766,
4
- "train_runtime": 262.0679,
5
  "train_samples": 8808,
6
- "train_samples_per_second": 100.829,
7
- "train_steps_per_second": 6.308
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.23321845325209195,
4
+ "train_runtime": 205.592,
5
  "train_samples": 8808,
6
+ "train_samples_per_second": 128.526,
7
+ "train_steps_per_second": 8.04
8
  }
config.json CHANGED
@@ -11,20 +11,20 @@
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
- "0": "LABEL_0",
15
- "1": "LABEL_1",
16
- "2": "LABEL_2",
17
- "3": "LABEL_3",
18
- "4": "LABEL_4"
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
- "LABEL_0": 0,
24
- "LABEL_1": 1,
25
- "LABEL_2": 2,
26
- "LABEL_3": 3,
27
- "LABEL_4": 4
28
  },
29
  "layer_norm_eps": 1e-12,
30
  "max_position_embeddings": 512,
@@ -39,7 +39,7 @@
39
  "pooler_type": "first_token_transform",
40
  "position_embedding_type": "absolute",
41
  "torch_dtype": "float32",
42
- "transformers_version": "4.36.2",
43
  "type_vocab_size": 2,
44
  "use_cache": true,
45
  "vocab_size": 119547
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
+ "0": "B-Claim",
15
+ "1": "B-Premise",
16
+ "2": "I-Claim",
17
+ "3": "I-Premise",
18
+ "4": "O"
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
+ "B-Claim": 0,
24
+ "B-Premise": 1,
25
+ "I-Claim": 2,
26
+ "I-Premise": 3,
27
+ "O": 4
28
  },
29
  "layer_norm_eps": 1e-12,
30
  "max_position_embeddings": 512,
 
39
  "pooler_type": "first_token_transform",
40
  "position_embedding_type": "absolute",
41
  "torch_dtype": "float32",
42
+ "transformers_version": "4.40.0.dev0",
43
  "type_vocab_size": 2,
44
  "use_cache": true,
45
  "vocab_size": 119547
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d88e185b8f01e5d7aff8d660772f93e7497df7ea384348229e5a140bbc692235
3
  size 709090132
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a11f26a1e60915fd8c58c74707dd728a37ce27f8b70d3f8814faf80ca5b5a46
3
  size 709090132
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 256,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
tokenizer_config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "[PAD]",
@@ -52,5 +51,6 @@
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
  "tokenizer_class": "BertTokenizer",
 
55
  "unk_token": "[UNK]"
56
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "[PAD]",
 
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
  "tokenizer_class": "BertTokenizer",
54
+ "truncation": true,
55
  "unk_token": "[UNK]"
56
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.24564219588448766,
4
- "train_runtime": 262.0679,
5
  "train_samples": 8808,
6
- "train_samples_per_second": 100.829,
7
- "train_steps_per_second": 6.308
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.23321845325209195,
4
+ "train_runtime": 205.592,
5
  "train_samples": 8808,
6
+ "train_samples_per_second": 128.526,
7
+ "train_steps_per_second": 8.04
8
  }
trainer_state.json CHANGED
@@ -10,30 +10,33 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.91,
 
13
  "learning_rate": 3.487598306110103e-05,
14
- "loss": 0.4056,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 1.81,
 
19
  "learning_rate": 1.975196612220206e-05,
20
- "loss": 0.2455,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 2.72,
 
25
  "learning_rate": 4.627949183303086e-06,
26
- "loss": 0.1298,
27
  "step": 1500
28
  },
29
  {
30
  "epoch": 3.0,
31
  "step": 1653,
32
- "total_flos": 1395101222261760.0,
33
- "train_loss": 0.24564219588448766,
34
- "train_runtime": 262.0679,
35
- "train_samples_per_second": 100.829,
36
- "train_steps_per_second": 6.308
37
  }
38
  ],
39
  "logging_steps": 500,
@@ -41,7 +44,7 @@
41
  "num_input_tokens_seen": 0,
42
  "num_train_epochs": 3,
43
  "save_steps": 500,
44
- "total_flos": 1395101222261760.0,
45
  "train_batch_size": 16,
46
  "trial_name": null,
47
  "trial_params": null
 
10
  "log_history": [
11
  {
12
  "epoch": 0.91,
13
+ "grad_norm": 4.16880989074707,
14
  "learning_rate": 3.487598306110103e-05,
15
+ "loss": 0.4004,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.81,
20
+ "grad_norm": 1.7097141742706299,
21
  "learning_rate": 1.975196612220206e-05,
22
+ "loss": 0.2175,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 2.72,
27
+ "grad_norm": 0.8170027136802673,
28
  "learning_rate": 4.627949183303086e-06,
29
+ "loss": 0.1255,
30
  "step": 1500
31
  },
32
  {
33
  "epoch": 3.0,
34
  "step": 1653,
35
+ "total_flos": 1394635774789920.0,
36
+ "train_loss": 0.23321845325209195,
37
+ "train_runtime": 205.592,
38
+ "train_samples_per_second": 128.526,
39
+ "train_steps_per_second": 8.04
40
  }
41
  ],
42
  "logging_steps": 500,
 
44
  "num_input_tokens_seen": 0,
45
  "num_train_epochs": 3,
46
  "save_steps": 500,
47
+ "total_flos": 1394635774789920.0,
48
  "train_batch_size": 16,
49
  "trial_name": null,
50
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de11250632abb8e8078d16652e77145ac8ead77ea6eca4e95f9eb9fc9d3743bf
3
- size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed24ac9afab1bea179b4701674fefdacd7f3cebd1c81dd62a5bc0fdf71863ccd
3
+ size 5048