Hugging Face's logo

gchhablani
/
fnet-base-finetuned-wnli

Text Classification
Transformers
PyTorch
TensorBoard
English
fnet
generated_from_trainer
fnet-bert-base-comparison
Eval Results
Inference Endpoints
Model card Files Metrics Community
gchhablani commited on
Commit
655b5ea
•
1 Parent(s): c3fedc1

Training in progress, epoch 1

Browse files
Files changed (18) hide show
  1. checkpoint-40/config.json +33 -0
  2. checkpoint-40/optimizer.pt +3 -0
  3. checkpoint-40/pytorch_model.bin +3 -0
  4. checkpoint-40/rng_state.pth +3 -0
  5. checkpoint-40/scheduler.pt +3 -0
  6. checkpoint-40/special_tokens_map.json +1 -0
  7. checkpoint-40/tokenizer.json +0 -0
  8. checkpoint-40/tokenizer_config.json +1 -0
  9. checkpoint-40/trainer_state.json +31 -0
  10. checkpoint-40/training_args.bin +3 -0
  11. config.json +33 -0
  12. pytorch_model.bin +3 -0
  13. runs/Sep16_18-42-03_patrick-general-gpu/1631817737.9312546/events.out.tfevents.1631817737.patrick-general-gpu.194163.1 +3 -0
  14. runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817737.patrick-general-gpu.194163.0 +3 -0
  15. special_tokens_map.json +1 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +1 -0
  18. training_args.bin +3 -0
checkpoint-40/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-base",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "wnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_entailment",
14
+ "1": "entailment"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "entailment": 1,
20
+ "not_entailment": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65177a6906cb6ed4a20c8dccdb6d4c175bfaf7db8c510fa95b581f8ca3d65075
3
+ size 662962197
checkpoint-40/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626ed3907402fd980be0cc276f022708d4128336ce7bbacd26826eaf5ad4444a
3
+ size 331497705
checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a73a39bc9e1cbf286b0c1de0d77ecab0345d463d17b585b43fb8e8fef3266d
3
+ size 14503
checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d01036d88d16c94acd7bc38524efe4572f3ae954e82ead144225291310226a7
3
+ size 623
checkpoint-40/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
checkpoint-40/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-40/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "google/fnet-base", "model_max_length": 512, "tokenizer_class": "FNetTokenizer"}
checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 40,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.6000000000000003e-05,
13
+ "loss": 0.7052,
14
+ "step": 40
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5633802816901409,
19
+ "eval_loss": 0.6902039051055908,
20
+ "eval_runtime": 0.5271,
21
+ "eval_samples_per_second": 134.707,
22
+ "eval_steps_per_second": 17.076,
23
+ "step": 40
24
+ }
25
+ ],
26
+ "max_steps": 200,
27
+ "num_train_epochs": 5,
28
+ "total_flos": 112927777720320.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0018d0bd5493d2abb91a78e7fe6494461f7f4d10944b54be5c94d6f6c54f5859
3
+ size 2799
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-base",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "wnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_entailment",
14
+ "1": "entailment"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "entailment": 1,
20
+ "not_entailment": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626ed3907402fd980be0cc276f022708d4128336ce7bbacd26826eaf5ad4444a
3
+ size 331497705
runs/Sep16_18-42-03_patrick-general-gpu/1631817737.9312546/events.out.tfevents.1631817737.patrick-general-gpu.194163.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61655b6a8c2eafa5b626423b6647d574b2e5da1a495e5ff344595de99dc62e75
3
+ size 4351
runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817737.patrick-general-gpu.194163.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e67b981c3c5ff96cef1ccb162a2f05ad1aa5111c255953faebaab3533315db
3
+ size 3655
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "google/fnet-base", "model_max_length": 512, "tokenizer_class": "FNetTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0018d0bd5493d2abb91a78e7fe6494461f7f4d10944b54be5c94d6f6c54f5859
3
+ size 2799