Hugging Face's logo

joey234
/
cuenb

Fill-Mask
Transformers
PyTorch
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Community
1
Thinh Truong commited on
Commit
77c9b30
·
1 Parent(s): be4043d

add model files

Browse files
Files changed (29) hide show
  1. randomcomb_mlm_ep5/README.md +57 -0
  2. randomcomb_mlm_ep5/all_results.json +14 -0
  3. randomcomb_mlm_ep5/checkpoint-200000/config.json +27 -0
  4. randomcomb_mlm_ep5/checkpoint-200000/merges.txt +0 -0
  5. randomcomb_mlm_ep5/checkpoint-200000/optimizer.pt +3 -0
  6. randomcomb_mlm_ep5/checkpoint-200000/pytorch_model.bin +3 -0
  7. randomcomb_mlm_ep5/checkpoint-200000/rng_state.pth +3 -0
  8. randomcomb_mlm_ep5/checkpoint-200000/scaler.pt +3 -0
  9. randomcomb_mlm_ep5/checkpoint-200000/scheduler.pt +3 -0
  10. randomcomb_mlm_ep5/checkpoint-200000/special_tokens_map.json +1 -0
  11. randomcomb_mlm_ep5/checkpoint-200000/tokenizer.json +0 -0
  12. randomcomb_mlm_ep5/checkpoint-200000/tokenizer_config.json +1 -0
  13. randomcomb_mlm_ep5/checkpoint-200000/trainer_state.json +30 -0
  14. randomcomb_mlm_ep5/checkpoint-200000/training_args.bin +3 -0
  15. randomcomb_mlm_ep5/checkpoint-200000/vocab.json +0 -0
  16. randomcomb_mlm_ep5/config.json +27 -0
  17. randomcomb_mlm_ep5/eval_results.json +9 -0
  18. randomcomb_mlm_ep5/merges.txt +0 -0
  19. randomcomb_mlm_ep5/pytorch_model.bin +3 -0
  20. randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/1639619972.0444322/events.out.tfevents.1639619972.slug.1802.1 +3 -0
  21. randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/events.out.tfevents.1639619972.slug.1802.0 +3 -0
  22. randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/events.out.tfevents.1639760604.slug.1802.2 +3 -0
  23. randomcomb_mlm_ep5/special_tokens_map.json +1 -0
  24. randomcomb_mlm_ep5/tokenizer.json +0 -0
  25. randomcomb_mlm_ep5/tokenizer_config.json +1 -0
  26. randomcomb_mlm_ep5/train_results.json +8 -0
  27. randomcomb_mlm_ep5/trainer_state.json +39 -0
  28. randomcomb_mlm_ep5/training_args.bin +3 -0
  29. randomcomb_mlm_ep5/vocab.json +0 -0
randomcomb_mlm_ep5/README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: randomcomb_mlm_ep5
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # randomcomb_mlm_ep5
14
+
15
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.5062
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 5.0
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:------:|:---------------:|
49
+ | 1.8998 | 2.57 | 200000 | 1.6606 |
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.13.0.dev0
55
+ - Pytorch 1.8.0
56
+ - Datasets 1.15.1
57
+ - Tokenizers 0.10.3
randomcomb_mlm_ep5/all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.5061932802200317,
4
+ "eval_runtime": 1068.1883,
5
+ "eval_samples": 138195,
6
+ "eval_samples_per_second": 129.373,
7
+ "eval_steps_per_second": 8.087,
8
+ "perplexity": 4.5095315557713995,
9
+ "train_loss": 1.7809591078664695,
10
+ "train_runtime": 139562.9056,
11
+ "train_samples": 1243753,
12
+ "train_samples_per_second": 44.559,
13
+ "train_steps_per_second": 2.785
14
+ }
randomcomb_mlm_ep5/checkpoint-200000/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
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
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.13.0.dev0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
randomcomb_mlm_ep5/checkpoint-200000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
randomcomb_mlm_ep5/checkpoint-200000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b336ebdd8510e2ec2847b6021cebe21dcfefee6f1d4b6c02e2a0fb1926bad3dd
3
+ size 997706595
randomcomb_mlm_ep5/checkpoint-200000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec69e9fd7bb3e50718768c181588be63926e9a88b7f5e1644e16f5c62cd76433
3
+ size 498880594
randomcomb_mlm_ep5/checkpoint-200000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf13c88685005b17fac38d90a62bc4f6e002321fb009598613a98a1189053740
3
+ size 15690
randomcomb_mlm_ep5/checkpoint-200000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ccc41a927f21310d033565b1364aba313733701696cabc6a441404047a6901
3
+ size 559
randomcomb_mlm_ep5/checkpoint-200000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1115ded262dd695c64e895fdc433cb710fca587cb71bd80f27825c4a51e0890
3
+ size 623
randomcomb_mlm_ep5/checkpoint-200000/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
randomcomb_mlm_ep5/checkpoint-200000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
randomcomb_mlm_ep5/checkpoint-200000/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
randomcomb_mlm_ep5/checkpoint-200000/trainer_state.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.5728436354280566,
5
+ "global_step": 200000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.57,
12
+ "learning_rate": 2.4280954524988745e-05,
13
+ "loss": 1.8998,
14
+ "step": 200000
15
+ },
16
+ {
17
+ "epoch": 2.57,
18
+ "eval_loss": 1.6605522632598877,
19
+ "eval_runtime": 1064.795,
20
+ "eval_samples_per_second": 129.786,
21
+ "eval_steps_per_second": 8.112,
22
+ "step": 200000
23
+ }
24
+ ],
25
+ "max_steps": 388675,
26
+ "num_train_epochs": 5,
27
+ "total_flos": 1.53636993828252e+17,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
randomcomb_mlm_ep5/checkpoint-200000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e400e663b7f67aadfb2815e255927a2d6e17765897a960c972b13851365792db
3
+ size 2799
randomcomb_mlm_ep5/checkpoint-200000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
randomcomb_mlm_ep5/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
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
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.13.0.dev0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
randomcomb_mlm_ep5/eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.5061932802200317,
4
+ "eval_runtime": 1068.1883,
5
+ "eval_samples": 138195,
6
+ "eval_samples_per_second": 129.373,
7
+ "eval_steps_per_second": 8.087,
8
+ "perplexity": 4.5095315557713995
9
+ }
randomcomb_mlm_ep5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
randomcomb_mlm_ep5/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5492a1f29ea154dd26217f60614c614cc1cdb3f5c1d4385a9b289d58c6a1a769
3
+ size 498880594
randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/1639619972.0444322/events.out.tfevents.1639619972.slug.1802.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7db48a3d09dd8bbbc85ba74c60a82388f70b2d58714d40fe8eddf4101cfa32
3
+ size 4514
randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/events.out.tfevents.1639619972.slug.1802.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a13ca19d2a19c215a7c885ebf08bbf8f060a4adf4929664cc28658157a348f1
3
+ size 3962
randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/events.out.tfevents.1639760604.slug.1802.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1defeeaf4819eaafe3c31c5b1c4a628254f8d39d8a130c7fb10df2d8d26de5be
3
+ size 316
randomcomb_mlm_ep5/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
randomcomb_mlm_ep5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
randomcomb_mlm_ep5/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
randomcomb_mlm_ep5/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 1.7809591078664695,
4
+ "train_runtime": 139562.9056,
5
+ "train_samples": 1243753,
6
+ "train_samples_per_second": 44.559,
7
+ "train_steps_per_second": 2.785
8
+ }
randomcomb_mlm_ep5/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 388675,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.57,
12
+ "learning_rate": 2.4280954524988745e-05,
13
+ "loss": 1.8998,
14
+ "step": 200000
15
+ },
16
+ {
17
+ "epoch": 2.57,
18
+ "eval_loss": 1.6605522632598877,
19
+ "eval_runtime": 1064.795,
20
+ "eval_samples_per_second": 129.786,
21
+ "eval_steps_per_second": 8.112,
22
+ "step": 200000
23
+ },
24
+ {
25
+ "epoch": 5.0,
26
+ "step": 388675,
27
+ "total_flos": 2.98603105152047e+17,
28
+ "train_loss": 1.7809591078664695,
29
+ "train_runtime": 139562.9056,
30
+ "train_samples_per_second": 44.559,
31
+ "train_steps_per_second": 2.785
32
+ }
33
+ ],
34
+ "max_steps": 388675,
35
+ "num_train_epochs": 5,
36
+ "total_flos": 2.98603105152047e+17,
37
+ "trial_name": null,
38
+ "trial_params": null
39
+ }
randomcomb_mlm_ep5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e400e663b7f67aadfb2815e255927a2d6e17765897a960c972b13851365792db
3
+ size 2799
randomcomb_mlm_ep5/vocab.json ADDED
The diff for this file is too large to render. See raw diff