Hugging Face's logo

gchhablani
/
fnet-base-finetuned-sst2

Text Classification
Transformers
PyTorch
TensorBoard
Rust
English
fnet
Generated from Trainer
fnet-bert-base-comparison
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
gchhablani commited on
Commit
82b9ede
•
1 Parent(s): 4e09239

Training in progress, epoch 1

Browse files
Files changed (18) hide show
  1. checkpoint-4210/config.json +33 -0
  2. checkpoint-4210/optimizer.pt +3 -0
  3. checkpoint-4210/pytorch_model.bin +3 -0
  4. checkpoint-4210/rng_state.pth +3 -0
  5. checkpoint-4210/scheduler.pt +3 -0
  6. checkpoint-4210/special_tokens_map.json +1 -0
  7. checkpoint-4210/tokenizer.json +0 -0
  8. checkpoint-4210/tokenizer_config.json +1 -0
  9. checkpoint-4210/trainer_state.json +31 -0
  10. checkpoint-4210/training_args.bin +3 -0
  11. config.json +33 -0
  12. pytorch_model.bin +3 -0
  13. runs/Sep19_08-31-53_patrick-general-gpu/1632040336.3470843/events.out.tfevents.1632040336.patrick-general-gpu.480409.1 +3 -0
  14. runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632040336.patrick-general-gpu.480409.0 +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-4210/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": "sst2",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "negative": 0,
20
+ "positive": 1
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-4210/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e0855d4578655a440467eee090cf33607f9a5a6ef88b6c0484d1b874a39cdd6
3
+ size 662962261
checkpoint-4210/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059641ac73283a9c0aaf62b3130ead411b9a4912cd5a172887570e9878a681d9
3
+ size 331497705
checkpoint-4210/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdfae54c3c96a5a1e4b6fee34ce013f7cb48d3df09559d0402f40560143f88b
3
+ size 14503
checkpoint-4210/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a351076d6c1a326efd23439dd26f13a3c00d4ed4099108ea5950c0f3d5cb02bf
3
+ size 623
checkpoint-4210/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-4210/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4210/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-4210/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": 4210,
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": 0.2956,
14
+ "step": 4210
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8818807339449541,
19
+ "eval_loss": 0.3128007650375366,
20
+ "eval_runtime": 6.3233,
21
+ "eval_samples_per_second": 137.902,
22
+ "eval_steps_per_second": 17.238,
23
+ "step": 4210
24
+ }
25
+ ],
26
+ "max_steps": 12630,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 1.1977280160135168e+16,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-4210/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a45e8f8a6be9a994d34ead5bf4a34c6c366dd946a5f7bcf5b8811be8ffa4f9c
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": "sst2",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "negative": 0,
20
+ "positive": 1
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 sha256:059641ac73283a9c0aaf62b3130ead411b9a4912cd5a172887570e9878a681d9
3
+ size 331497705
runs/Sep19_08-31-53_patrick-general-gpu/1632040336.3470843/events.out.tfevents.1632040336.patrick-general-gpu.480409.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48bd3857bcf0d4d1e46aea0bc1ffcef533beff61e1a40867649a75379dd093f2
3
+ size 4351
runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632040336.patrick-general-gpu.480409.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f27f2af251d77d30e5412ebaf64f6d8b7ce3073f766dfd9d017c1e3d83a5b42
3
+ size 3648
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 sha256:8a45e8f8a6be9a994d34ead5bf4a34c6c366dd946a5f7bcf5b8811be8ffa4f9c
3
+ size 2799