ltuzova commited on
Commit
b8596b8
·
1 Parent(s): 07560d0

citation_intent_classification_roberta

Browse files
last-checkpoint/config.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "_name_or_path": "roberta-base",
3
- "architectures": [
4
- "RobertaForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": 0.1,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
13
- "id2label": {
14
- "0": "Background",
15
- "1": "CompareOrContrast",
16
- "2": "Uses",
17
- "3": "Motivation",
18
- "4": "Future",
19
- "5": "Extends"
20
- },
21
- "initializer_range": 0.02,
22
- "intermediate_size": 3072,
23
- "label2id": {
24
- "Background": 0,
25
- "CompareOrContrast": 1,
26
- "Extends": 5,
27
- "Future": 4,
28
- "Motivation": 3,
29
- "Uses": 2
30
- },
31
- "layer_norm_eps": 1e-05,
32
- "max_position_embeddings": 514,
33
- "model_type": "roberta",
34
- "num_attention_heads": 12,
35
- "num_hidden_layers": 12,
36
- "num_of_labels": 6,
37
- "pad_token_id": 1,
38
- "position_embedding_type": "absolute",
39
- "problem_type": "single_label_classification",
40
- "torch_dtype": "float32",
41
- "transformers_version": "4.30.2",
42
- "type_vocab_size": 1,
43
- "use_cache": true,
44
- "vocab_size": 50265
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a64ed1826ce6bd044bd7afe85a8b4c78cd608ca3f7b77f1c2cf3cddf498f28cb
3
- size 997319621
 
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0227a1ed78395be68d1dc9455b3765af1ed82b2c2a57129e3c0c585461fca76
3
- size 498674357
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01e7f2bd676c936e7a6fdf9cde6071c5938c578820d54a54ab03298d96dc82c2
3
- size 14575
 
 
 
 
last-checkpoint/special_tokens_map.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "bos_token": "<s>",
4
- "clean_up_tokenization_spaces": true,
5
- "cls_token": "<s>",
6
- "eos_token": "</s>",
7
- "errors": "replace",
8
- "mask_token": "<mask>",
9
- "model_max_length": 512,
10
- "pad_token": "<pad>",
11
- "sep_token": "</s>",
12
- "tokenizer_class": "RobertaTokenizer",
13
- "trim_offsets": true,
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "best_metric": 0.30706436420722133,
3
- "best_model_checkpoint": "citation_intent_classification_roberta/checkpoint-105",
4
- "epoch": 0.995260663507109,
5
- "global_step": 105,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.95,
12
- "learning_rate": 1.9250253292806485e-05,
13
- "loss": 1.3931,
14
- "step": 100
15
- },
16
- {
17
- "epoch": 1.0,
18
- "eval_accuracy": 0.6842105263157895,
19
- "eval_f1_macro": 0.30706436420722133,
20
- "eval_loss": 1.0457483530044556,
21
- "eval_runtime": 0.3443,
22
- "eval_samples_per_second": 331.11,
23
- "eval_steps_per_second": 23.236,
24
- "step": 105
25
- }
26
- ],
27
- "max_steps": 1050,
28
- "num_train_epochs": 10,
29
- "total_flos": 88083700250400.0,
30
- "trial_name": null,
31
- "trial_params": null
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd89d8b68f6298238df90c756d07336ff7d1f52ab6d9e6c4f4d07884d79975a1
3
- size 4027
 
 
 
 
last-checkpoint/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0227a1ed78395be68d1dc9455b3765af1ed82b2c2a57129e3c0c585461fca76
3
  size 498674357
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1fa0c1572bb7bb1ff84ef8998dbda144cea4be127468da62bad20d0dcf83a0
3
  size 498674357
runs/Apr20_23-44-07_jupyter/events.out.tfevents.1713656651.jupyter.2695507.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4598ca3596bc2a028b73dea60883f42611cb3030a9b2f03b363a4365cba3654d
3
- size 4875
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc30c878a25445d36390f1842b85f8e1c55440bf54908878ccf7e4a31b88a660
3
+ size 10017
last-checkpoint/scheduler.pt → runs/Apr20_23-44-07_jupyter/events.out.tfevents.1713656908.jupyter.2695507.3 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6aae226b0a385b18c8012f4d652e8fbdd18f15a3fe78c710dfd63cccbeb8c1b
3
- size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb5c2eb58098ddaaa99f38047bdd0cdcdf3e7c8ce8738a0be45cdf8afabc476
3
+ size 415