Hugging Face's logo

joey234
/
roberta-base-mnli-negnli

Text Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
Thinh Truong commited on
Commit
447dfe2
·
1 Parent(s): 73ff1ab

update model files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +56 -0
  2. all_results.json +14 -0
  3. config.json +38 -0
  4. eval_results.json +9 -0
  5. merges.txt +0 -0
  6. pytorch_model.bin +3 -0
  7. roberta2-base-mnli-negnli/README.md +56 -0
  8. roberta2-base-mnli-negnli/all_results.json +14 -0
  9. roberta2-base-mnli-negnli/checkpoint-500/config.json +38 -0
  10. roberta2-base-mnli-negnli/checkpoint-500/merges.txt +0 -0
  11. roberta2-base-mnli-negnli/checkpoint-500/optimizer.pt +3 -0
  12. roberta2-base-mnli-negnli/checkpoint-500/pytorch_model.bin +3 -0
  13. roberta2-base-mnli-negnli/checkpoint-500/rng_state.pth +3 -0
  14. roberta2-base-mnli-negnli/checkpoint-500/scheduler.pt +3 -0
  15. roberta2-base-mnli-negnli/checkpoint-500/special_tokens_map.json +15 -0
  16. roberta2-base-mnli-negnli/checkpoint-500/tokenizer.json +0 -0
  17. roberta2-base-mnli-negnli/checkpoint-500/tokenizer_config.json +16 -0
  18. roberta2-base-mnli-negnli/checkpoint-500/trainer_state.json +22 -0
  19. roberta2-base-mnli-negnli/checkpoint-500/training_args.bin +3 -0
  20. roberta2-base-mnli-negnli/checkpoint-500/vocab.json +0 -0
  21. roberta2-base-mnli-negnli/config.json +38 -0
  22. roberta2-base-mnli-negnli/eval_results.json +9 -0
  23. roberta2-base-mnli-negnli/merges.txt +0 -0
  24. roberta2-base-mnli-negnli/pytorch_model.bin +3 -0
  25. roberta2-base-mnli-negnli/runs/Jul07_23-50-30_doe/1657201850.622683/events.out.tfevents.1657201850.doe.63764.1 +3 -0
  26. roberta2-base-mnli-negnli/runs/Jul07_23-50-30_doe/events.out.tfevents.1657201850.doe.63764.0 +3 -0
  27. roberta2-base-mnli-negnli/runs/Jul07_23-50-30_doe/events.out.tfevents.1657201943.doe.63764.2 +3 -0
  28. roberta2-base-mnli-negnli/runs/Jul07_23-54-02_doe/1657202061.6067924/events.out.tfevents.1657202061.doe.2632.1 +3 -0
  29. roberta2-base-mnli-negnli/runs/Jul07_23-54-02_doe/events.out.tfevents.1657202061.doe.2632.0 +3 -0
  30. roberta2-base-mnli-negnli/runs/Jul07_23-54-02_doe/events.out.tfevents.1657202129.doe.2632.2 +3 -0
  31. roberta2-base-mnli-negnli/runs/Jul08_00-57-12_doe/1657205852.4321375/events.out.tfevents.1657205852.doe.4547.1 +3 -0
  32. roberta2-base-mnli-negnli/runs/Jul08_00-57-12_doe/events.out.tfevents.1657205852.doe.4547.0 +3 -0
  33. roberta2-base-mnli-negnli/runs/Jul08_00-57-12_doe/events.out.tfevents.1657206008.doe.4547.2 +3 -0
  34. roberta2-base-mnli-negnli/runs/Jul08_01-08-17_doe/1657206517.7561595/events.out.tfevents.1657206517.doe.16385.1 +3 -0
  35. roberta2-base-mnli-negnli/runs/Jul08_01-08-17_doe/events.out.tfevents.1657206517.doe.16385.0 +3 -0
  36. roberta2-base-mnli-negnli/runs/Jul08_01-08-17_doe/events.out.tfevents.1657206612.doe.16385.2 +3 -0
  37. roberta2-base-mnli-negnli/runs/Jul08_01-12-22_doe/1657206761.9519951/events.out.tfevents.1657206761.doe.20937.1 +3 -0
  38. roberta2-base-mnli-negnli/runs/Jul08_01-12-22_doe/events.out.tfevents.1657206761.doe.20937.0 +3 -0
  39. roberta2-base-mnli-negnli/runs/Jul08_01-12-22_doe/events.out.tfevents.1657206857.doe.20937.2 +3 -0
  40. roberta2-base-mnli-negnli/runs/Jul08_01-15-21_doe/1657206941.3139427/events.out.tfevents.1657206941.doe.25921.1 +3 -0
  41. roberta2-base-mnli-negnli/runs/Jul08_01-15-21_doe/events.out.tfevents.1657206941.doe.25921.0 +3 -0
  42. roberta2-base-mnli-negnli/runs/Jul08_01-15-21_doe/events.out.tfevents.1657207104.doe.25921.2 +3 -0
  43. roberta2-base-mnli-negnli/runs/Jul08_01-22-31_doe/1657207371.2546418/events.out.tfevents.1657207371.doe.33741.1 +3 -0
  44. roberta2-base-mnli-negnli/runs/Jul08_01-22-31_doe/events.out.tfevents.1657207371.doe.33741.0 +3 -0
  45. roberta2-base-mnli-negnli/runs/Jul08_01-22-31_doe/events.out.tfevents.1657207536.doe.33741.2 +3 -0
  46. roberta2-base-mnli-negnli/special_tokens_map.json +15 -0
  47. roberta2-base-mnli-negnli/tokenizer.json +0 -0
  48. roberta2-base-mnli-negnli/tokenizer_config.json +16 -0
  49. roberta2-base-mnli-negnli/train_results.json +8 -0
  50. roberta2-base-mnli-negnli/trainer_state.json +31 -0
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: roberta2-base-mnli-negnli
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # roberta2-base-mnli-negnli
16
+
17
+ This model is a fine-tuned version of [sileod/roberta-base-mnli](https://huggingface.co/sileod/roberta-base-mnli) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8397
20
+ - Accuracy: 0.8400
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 5.0
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.21.0.dev0
54
+ - Pytorch 1.8.0
55
+ - Datasets 1.18.3
56
+ - Tokenizers 0.12.1
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8399999737739563,
4
+ "eval_loss": 0.8397448658943176,
5
+ "eval_runtime": 1.7729,
6
+ "eval_samples": 300,
7
+ "eval_samples_per_second": 169.214,
8
+ "eval_steps_per_second": 21.434,
9
+ "train_loss": 0.444431884765625,
10
+ "train_runtime": 158.4081,
11
+ "train_samples": 1200,
12
+ "train_samples_per_second": 37.877,
13
+ "train_steps_per_second": 4.735
14
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sileod/roberta-base-mnli",
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
+ "id2label": {
14
+ "0": "CONTRADICTION",
15
+ "1": "ENTAILMENT",
16
+ "2": "NEUTRAL"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "CONTRADICTION": 0,
22
+ "ENTAILMENT": 1,
23
+ "NEUTRAL": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.21.0.dev0",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8399999737739563,
4
+ "eval_loss": 0.8397448658943176,
5
+ "eval_runtime": 1.7729,
6
+ "eval_samples": 300,
7
+ "eval_samples_per_second": 169.214,
8
+ "eval_steps_per_second": 21.434
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28c6566a80bf80b26a2e5cc10639cbdb067568ff4892835ccb87fe6371ac35b
3
+ size 498668617
roberta2-base-mnli-negnli/README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: roberta2-base-mnli-negnli
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # roberta2-base-mnli-negnli
16
+
17
+ This model is a fine-tuned version of [sileod/roberta-base-mnli](https://huggingface.co/sileod/roberta-base-mnli) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8397
20
+ - Accuracy: 0.8400
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 5.0
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.21.0.dev0
54
+ - Pytorch 1.8.0
55
+ - Datasets 1.18.3
56
+ - Tokenizers 0.12.1
roberta2-base-mnli-negnli/all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8399999737739563,
4
+ "eval_loss": 0.8397448658943176,
5
+ "eval_runtime": 1.7729,
6
+ "eval_samples": 300,
7
+ "eval_samples_per_second": 169.214,
8
+ "eval_steps_per_second": 21.434,
9
+ "train_loss": 0.444431884765625,
10
+ "train_runtime": 158.4081,
11
+ "train_samples": 1200,
12
+ "train_samples_per_second": 37.877,
13
+ "train_steps_per_second": 4.735
14
+ }
roberta2-base-mnli-negnli/checkpoint-500/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sileod/roberta-base-mnli",
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
+ "id2label": {
14
+ "0": "CONTRADICTION",
15
+ "1": "ENTAILMENT",
16
+ "2": "NEUTRAL"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "CONTRADICTION": 0,
22
+ "ENTAILMENT": 1,
23
+ "NEUTRAL": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.21.0.dev0",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
roberta2-base-mnli-negnli/checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
roberta2-base-mnli-negnli/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9551da3c73121e547aa394625b20438e8a11b4245def5cae7805c1bc86e83c
3
+ size 997309649
roberta2-base-mnli-negnli/checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17766a4377f17b6610496612f147935767e3bc8738819ade326f26428061adb3
3
+ size 498668617
roberta2-base-mnli-negnli/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b52f8bf55ed105f0f2d1c981187dc836c4a58af053360add9d9a3266f9fd3b1
3
+ size 14657
roberta2-base-mnli-negnli/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519f1a7aac1e26b93c5dc8fd29b1ba14a602229a9976e9a4f11ec0084c0506e1
3
+ size 623
roberta2-base-mnli-negnli/checkpoint-500/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
+ }
roberta2-base-mnli-negnli/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
roberta2-base-mnli-negnli/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
roberta2-base-mnli-negnli/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.3333333333333335,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.33,
12
+ "learning_rate": 6.666666666666667e-06,
13
+ "loss": 0.5834,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 750,
18
+ "num_train_epochs": 5,
19
+ "total_flos": 263113417728000.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
roberta2-base-mnli-negnli/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d8ac10c632bedfc183e887aabf3ba8bb835486176969bfa525240f0f4f51ac7
3
+ size 3311
roberta2-base-mnli-negnli/checkpoint-500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
roberta2-base-mnli-negnli/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sileod/roberta-base-mnli",
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
+ "id2label": {
14
+ "0": "CONTRADICTION",
15
+ "1": "ENTAILMENT",
16
+ "2": "NEUTRAL"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "CONTRADICTION": 0,
22
+ "ENTAILMENT": 1,
23
+ "NEUTRAL": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.21.0.dev0",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
roberta2-base-mnli-negnli/eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8399999737739563,
4
+ "eval_loss": 0.8397448658943176,
5
+ "eval_runtime": 1.7729,
6
+ "eval_samples": 300,
7
+ "eval_samples_per_second": 169.214,
8
+ "eval_steps_per_second": 21.434
9
+ }
roberta2-base-mnli-negnli/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
roberta2-base-mnli-negnli/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28c6566a80bf80b26a2e5cc10639cbdb067568ff4892835ccb87fe6371ac35b
3
+ size 498668617
roberta2-base-mnli-negnli/runs/Jul07_23-50-30_doe/1657201850.622683/events.out.tfevents.1657201850.doe.63764.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eefc6dd2cc4695bd0f63bffbbd0533708dcb84d82c5ca338c92e366c5d64846
3
+ size 5365
roberta2-base-mnli-negnli/runs/Jul07_23-50-30_doe/events.out.tfevents.1657201850.doe.63764.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee2e90b2d788565553ebd5878c2b5606cb503e2714bbcfe49a35dffcc7e5762
3
+ size 4215
roberta2-base-mnli-negnli/runs/Jul07_23-50-30_doe/events.out.tfevents.1657201943.doe.63764.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee715a065059002451302c27b446ca8dfbc200031d44ea4ed32123de54ab7def
3
+ size 363
roberta2-base-mnli-negnli/runs/Jul07_23-54-02_doe/1657202061.6067924/events.out.tfevents.1657202061.doe.2632.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b96e4de1cc2f0c22feafe25fbde21e41266a99ee6ea55d71ac849a31c99124a
3
+ size 5365
roberta2-base-mnli-negnli/runs/Jul07_23-54-02_doe/events.out.tfevents.1657202061.doe.2632.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55fb8b1e827be004241cdeeaa1afab3479f43c26f94bfd65ab9692aebcdbd76c
3
+ size 4215
roberta2-base-mnli-negnli/runs/Jul07_23-54-02_doe/events.out.tfevents.1657202129.doe.2632.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d26a7d40ef50f6c4521a21ff0912102037aea093d50638826be6914494d79b
3
+ size 363
roberta2-base-mnli-negnli/runs/Jul08_00-57-12_doe/1657205852.4321375/events.out.tfevents.1657205852.doe.4547.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdea2c00555620bc8d641c32aaea93537577589515f8368c1e48d024dc9101b8
3
+ size 5365
roberta2-base-mnli-negnli/runs/Jul08_00-57-12_doe/events.out.tfevents.1657205852.doe.4547.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129c745c8128bc9abc69b7d043df76197bdf3f5230e3ef1a61dd519a255acaf4
3
+ size 4445
roberta2-base-mnli-negnli/runs/Jul08_00-57-12_doe/events.out.tfevents.1657206008.doe.4547.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41814716da87e078ad112b437f2d16a1e4f205ed0123fc6710265a37ce042d37
3
+ size 363
roberta2-base-mnli-negnli/runs/Jul08_01-08-17_doe/1657206517.7561595/events.out.tfevents.1657206517.doe.16385.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f986d4bb16a3aeddb300cf944f37db69f563e84c7e08b83238d71c7ae6a31271
3
+ size 5365
roberta2-base-mnli-negnli/runs/Jul08_01-08-17_doe/events.out.tfevents.1657206517.doe.16385.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ebd2278c753d388b8c5ffcdaf0a98fbff43cd241ef963546610c42ddd22e45
3
+ size 4215
roberta2-base-mnli-negnli/runs/Jul08_01-08-17_doe/events.out.tfevents.1657206612.doe.16385.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b1a60159001ce313ad8ecc1a27c52e24a82f18fb32cad5e979b12d3d1155600
3
+ size 363
roberta2-base-mnli-negnli/runs/Jul08_01-12-22_doe/1657206761.9519951/events.out.tfevents.1657206761.doe.20937.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73b0655c7c22c157f08feb5fd5b079430c6974f976c602e863d2acc35961f01
3
+ size 5365
roberta2-base-mnli-negnli/runs/Jul08_01-12-22_doe/events.out.tfevents.1657206761.doe.20937.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9750c7e2b2837d2176aba17d8c5f47cf47dc06e73b72a5162d9e6e0208c3c3e7
3
+ size 4249
roberta2-base-mnli-negnli/runs/Jul08_01-12-22_doe/events.out.tfevents.1657206857.doe.20937.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c970e9141055c4f2a314c219a9a8403acd07c5e6d2bc723518a3f1bdfffa343
3
+ size 363
roberta2-base-mnli-negnli/runs/Jul08_01-15-21_doe/1657206941.3139427/events.out.tfevents.1657206941.doe.25921.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e4bc0171d172a263aecf4a88587c394f2e4b13abcd4724fcf2cae98bd8dc1b7
3
+ size 5365
roberta2-base-mnli-negnli/runs/Jul08_01-15-21_doe/events.out.tfevents.1657206941.doe.25921.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2343c15b57f947fe9ddbd3ea1db5f66a111013901d5cacadeddb72c3b82ced6
3
+ size 4406
roberta2-base-mnli-negnli/runs/Jul08_01-15-21_doe/events.out.tfevents.1657207104.doe.25921.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b4f4109f27eb713949884555036a225f29554c68fd6690d580ca4f7bc19fce
3
+ size 363
roberta2-base-mnli-negnli/runs/Jul08_01-22-31_doe/1657207371.2546418/events.out.tfevents.1657207371.doe.33741.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1285fb859702ce1e7ad8ab9c725d482ebd2ac1c769c61fbfb3aa54a17efe84b9
3
+ size 5365
roberta2-base-mnli-negnli/runs/Jul08_01-22-31_doe/events.out.tfevents.1657207371.doe.33741.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c06ceed443ee396d79106660494c31cdfe84bd675323f59efe192bd3e2915ee5
3
+ size 4445
roberta2-base-mnli-negnli/runs/Jul08_01-22-31_doe/events.out.tfevents.1657207536.doe.33741.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328a9c6f9adab7a18c86e781f03655c14449695e2135aeb02b3af07aaca7418e
3
+ size 363
roberta2-base-mnli-negnli/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
+ }
roberta2-base-mnli-negnli/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
roberta2-base-mnli-negnli/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
roberta2-base-mnli-negnli/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.444431884765625,
4
+ "train_runtime": 158.4081,
5
+ "train_samples": 1200,
6
+ "train_samples_per_second": 37.877,
7
+ "train_steps_per_second": 4.735
8
+ }
roberta2-base-mnli-negnli/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 750,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.33,
12
+ "learning_rate": 6.666666666666667e-06,
13
+ "loss": 0.5834,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 5.0,
18
+ "step": 750,
19
+ "total_flos": 394670126592000.0,
20
+ "train_loss": 0.444431884765625,
21
+ "train_runtime": 158.4081,
22
+ "train_samples_per_second": 37.877,
23
+ "train_steps_per_second": 4.735
24
+ }
25
+ ],
26
+ "max_steps": 750,
27
+ "num_train_epochs": 5,
28
+ "total_flos": 394670126592000.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }