Hugging Face's logo

gchhablani
/
fnet-base-finetuned-mnli

Text Classification
Transformers
PyTorch
TensorBoard
English
fnet
generated_from_trainer
fnet-bert-base-comparison
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
gchhablani commited on
Commit
916f4b5
•
1 Parent(s): e8cf618

Training in progress, epoch 1

Browse files
Files changed (18) hide show
  1. checkpoint-24544/config.json +35 -0
  2. checkpoint-24544/optimizer.pt +3 -0
  3. checkpoint-24544/pytorch_model.bin +3 -0
  4. checkpoint-24544/rng_state.pth +3 -0
  5. checkpoint-24544/scheduler.pt +3 -0
  6. checkpoint-24544/special_tokens_map.json +1 -0
  7. checkpoint-24544/tokenizer.json +0 -0
  8. checkpoint-24544/tokenizer_config.json +1 -0
  9. checkpoint-24544/trainer_state.json +31 -0
  10. checkpoint-24544/training_args.bin +3 -0
  11. config.json +35 -0
  12. pytorch_model.bin +3 -0
  13. runs/Sep17_07-10-01_patrick-general-gpu/1631862669.4718635/events.out.tfevents.1631862669.patrick-general-gpu.234538.1 +3 -0
  14. runs/Sep17_07-10-01_patrick-general-gpu/events.out.tfevents.1631862669.patrick-general-gpu.234538.0 +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-24544/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "neutral",
15
+ "2": "contradiction"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "contradiction": 2,
21
+ "entailment": 0,
22
+ "neutral": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "fnet",
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 3,
29
+ "torch_dtype": "float32",
30
+ "tpu_short_seq_length": 512,
31
+ "transformers_version": "4.11.0.dev0",
32
+ "type_vocab_size": 4,
33
+ "use_tpu_fourier_optimizations": false,
34
+ "vocab_size": 32000
35
+ }
checkpoint-24544/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3c9afc7c0df62b45ed620e44a565016f697d635cc5fd2d8580f90768120908
3
+ size 662968405
checkpoint-24544/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1f9c30e2a50c012f5aacd4b9eec926869ad425009003f6ff7d518d87f187c2
3
+ size 331500777
checkpoint-24544/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bdd5f17c94d913fc4d541fb76e5f50b2fffe848f5d4f53d6bb6f5032ca1d29
3
+ size 14503
checkpoint-24544/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2001c64ada8fbad63d9fef31c5b12c73ccec49a590e98a18f28b62f88e283e4
3
+ size 623
checkpoint-24544/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-24544/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-24544/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-24544/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": 24544,
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": 1.3333333333333333e-05,
13
+ "loss": 0.7143,
14
+ "step": 24544
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7503820682628629,
19
+ "eval_loss": 0.6168540120124817,
20
+ "eval_runtime": 71.4698,
21
+ "eval_samples_per_second": 137.331,
22
+ "eval_steps_per_second": 17.168,
23
+ "step": 24544
24
+ }
25
+ ],
26
+ "max_steps": 73632,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 6.98386665512448e+16,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-24544/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7074326752f68eaba5eb9d6552280139883b78c4355f1f89c5ffc904d6a668
3
+ size 2799
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "neutral",
15
+ "2": "contradiction"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "contradiction": 2,
21
+ "entailment": 0,
22
+ "neutral": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "fnet",
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 3,
29
+ "torch_dtype": "float32",
30
+ "tpu_short_seq_length": 512,
31
+ "transformers_version": "4.11.0.dev0",
32
+ "type_vocab_size": 4,
33
+ "use_tpu_fourier_optimizations": false,
34
+ "vocab_size": 32000
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1f9c30e2a50c012f5aacd4b9eec926869ad425009003f6ff7d518d87f187c2
3
+ size 331500777
runs/Sep17_07-10-01_patrick-general-gpu/1631862669.4718635/events.out.tfevents.1631862669.patrick-general-gpu.234538.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b776ab1fc240ac25c95ea8fb9d030a310e2ffecfa8460f05746f5fdd54b99aae
3
+ size 4351
runs/Sep17_07-10-01_patrick-general-gpu/events.out.tfevents.1631862669.patrick-general-gpu.234538.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9feceab7fe4d4ce8f9a2ad240b9e335b2f51a9e62d7802865d3d070eafeffc7
3
+ size 3709
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:ec7074326752f68eaba5eb9d6552280139883b78c4355f1f89c5ffc904d6a668
3
+ size 2799