Hugging Face's logo

docampo99
/
roberta-base-finetuned-rte

Text Classification
Transformers
TensorBoard
Safetensors
roberta
text-embeddings-inference
Model card Files
xet
Metrics Community
docampo99 commited on
Commit
7fe3ffc
·
verified ·
1 Parent(s): 818c5ad

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. model.safetensors +1 -1
  2. run-6/checkpoint-126/config.json +28 -0
  3. run-6/checkpoint-126/merges.txt +0 -0
  4. run-6/checkpoint-126/model.safetensors +3 -0
  5. run-6/checkpoint-126/optimizer.pt +3 -0
  6. run-6/checkpoint-126/rng_state.pth +3 -0
  7. run-6/checkpoint-126/scheduler.pt +3 -0
  8. run-6/checkpoint-126/special_tokens_map.json +15 -0
  9. run-6/checkpoint-126/tokenizer.json +0 -0
  10. run-6/checkpoint-126/tokenizer_config.json +57 -0
  11. run-6/checkpoint-126/trainer_state.json +44 -0
  12. run-6/checkpoint-126/training_args.bin +3 -0
  13. run-6/checkpoint-126/vocab.json +0 -0
  14. run-7/checkpoint-16/config.json +28 -0
  15. run-7/checkpoint-16/merges.txt +0 -0
  16. run-7/checkpoint-16/model.safetensors +3 -0
  17. run-7/checkpoint-16/optimizer.pt +3 -0
  18. run-7/checkpoint-16/rng_state.pth +3 -0
  19. run-7/checkpoint-16/scheduler.pt +3 -0
  20. run-7/checkpoint-16/special_tokens_map.json +15 -0
  21. run-7/checkpoint-16/tokenizer.json +0 -0
  22. run-7/checkpoint-16/tokenizer_config.json +57 -0
  23. run-7/checkpoint-16/trainer_state.json +35 -0
  24. run-7/checkpoint-16/training_args.bin +3 -0
  25. run-7/checkpoint-16/vocab.json +0 -0
  26. runs/Mar09_12-48-04_a0f3909bd2ac/events.out.tfevents.1709990027.a0f3909bd2ac.40155.9 +3 -0
  27. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dc0a6d72d65473b7c3baccbf6daf1d166f3222b61d32462ec1b40b13cd3442a
3
  size 498612824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650754b08769b0a1cd4c33311a5b040cd5faa2e4d12a2dbc29020fc3927bb2ad
3
  size 498612824
run-6/checkpoint-126/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
run-6/checkpoint-126/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-126/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e47a4785714cc6b76eede60684fdf1f4010dd607535c1bb14138b8cb15b55f2
3
+ size 498612824
run-6/checkpoint-126/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb5771710d7063ed5feabcdcb6faa656a94692a2e093b6cf18b8230dd28ea761
3
+ size 997345530
run-6/checkpoint-126/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c2750f8ec671ea8a2a02de5563a216c2d19953ed53873c317ddd0413f866e63
3
+ size 14244
run-6/checkpoint-126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6ac7155176086844de32708e46ae2b3edb196019f382b2fc7ccc5fef513cbc
3
+ size 1064
run-6/checkpoint-126/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
run-6/checkpoint-126/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-126/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
run-6/checkpoint-126/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5270758122743683,
3
+ "best_model_checkpoint": "roberta-base-finetuned-rte/run-6/checkpoint-63",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 126,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.5270758122743683,
14
+ "eval_loss": 0.692136824131012,
15
+ "eval_runtime": 2.8392,
16
+ "eval_samples_per_second": 97.564,
17
+ "eval_steps_per_second": 6.34,
18
+ "step": 63
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.5270758122743683,
23
+ "eval_loss": 0.6920813918113708,
24
+ "eval_runtime": 5.8327,
25
+ "eval_samples_per_second": 47.491,
26
+ "eval_steps_per_second": 3.086,
27
+ "step": 126
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 126,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 4,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.012941554128117e-06,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 4,
42
+ "seed": 12
43
+ }
44
+ }
run-6/checkpoint-126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f9f2c16c8d8724c7ec08227c986fe9d1e15d9407c6de5be35e9de88fa9ea94
3
+ size 4920
run-6/checkpoint-126/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-16/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
run-7/checkpoint-16/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-16/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650754b08769b0a1cd4c33311a5b040cd5faa2e4d12a2dbc29020fc3927bb2ad
3
+ size 498612824
run-7/checkpoint-16/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7222ec75967ea96db0bee34757a16abe18f7fb8da3046c144dfebf4d1f442d
3
+ size 997345530
run-7/checkpoint-16/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52a5483b6267fb61455245246035e99258c3af5f42808caa71fb8979afc1b5a3
3
+ size 14244
run-7/checkpoint-16/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d778eb9a079ba4bbc50f3d35bf995f44ad35005a2ae71f682205b0a4ec709f3b
3
+ size 1064
run-7/checkpoint-16/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
run-7/checkpoint-16/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-16/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
run-7/checkpoint-16/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5306859205776173,
3
+ "best_model_checkpoint": "roberta-base-finetuned-rte/run-7/checkpoint-16",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 16,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.5306859205776173,
14
+ "eval_loss": 0.691372275352478,
15
+ "eval_runtime": 5.2976,
16
+ "eval_samples_per_second": 52.288,
17
+ "eval_steps_per_second": 3.398,
18
+ "step": 16
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 80,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.7748968704173344e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 5
34
+ }
35
+ }
run-7/checkpoint-16/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa733664c0a41f15223138133c5c814c03e69769d17e724863ed784ac0184750
3
+ size 4920
run-7/checkpoint-16/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar09_12-48-04_a0f3909bd2ac/events.out.tfevents.1709990027.a0f3909bd2ac.40155.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c211ec753a48c9d0c61ae789fd539427ab7d798f3bfa710f251c003bb8fa2bf4
3
+ size 5259
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38f9f2c16c8d8724c7ec08227c986fe9d1e15d9407c6de5be35e9de88fa9ea94
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa733664c0a41f15223138133c5c814c03e69769d17e724863ed784ac0184750
3
  size 4920