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
34b2734
·
1 Parent(s): 82b9ede

Training in progress, epoch 2

Browse files
Files changed (12) hide show
  1. checkpoint-8420/config.json +33 -0
  2. checkpoint-8420/optimizer.pt +3 -0
  3. checkpoint-8420/pytorch_model.bin +3 -0
  4. checkpoint-8420/rng_state.pth +3 -0
  5. checkpoint-8420/scheduler.pt +3 -0
  6. checkpoint-8420/special_tokens_map.json +1 -0
  7. checkpoint-8420/tokenizer.json +0 -0
  8. checkpoint-8420/tokenizer_config.json +1 -0
  9. checkpoint-8420/trainer_state.json +46 -0
  10. checkpoint-8420/training_args.bin +3 -0
  11. pytorch_model.bin +1 -1
  12. runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632040336.patrick-general-gpu.480409.0 +2 -2
checkpoint-8420/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-8420/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b472440e6a5218b41fb6255e35b0abc1be651283c33bb7fd778749621211a9
3
+ size 662962261
checkpoint-8420/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1d430a37d7227f2ff689dfe9836ff507b99cf6e911a7b78439d25332b54598
3
+ size 331497705
checkpoint-8420/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f3b9bbc01b6a705e1b0142016fafcdbb595a8ae92e312b22a059a0dceba069
3
+ size 14503
checkpoint-8420/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225af2522a89939171f5e9b2ff307870c3f412dbff3b5422f6e3d50b51919c8d
3
+ size 623
checkpoint-8420/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-8420/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8420/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-8420/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 8420,
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
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.1746,
29
+ "step": 8420
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8979357798165137,
34
+ "eval_loss": 0.38503018021583557,
35
+ "eval_runtime": 6.3387,
36
+ "eval_samples_per_second": 137.568,
37
+ "eval_steps_per_second": 17.196,
38
+ "step": 8420
39
+ }
40
+ ],
41
+ "max_steps": 12630,
42
+ "num_train_epochs": 3,
43
+ "total_flos": 2.3954560320270336e+16,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-8420/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a45e8f8a6be9a994d34ead5bf4a34c6c366dd946a5f7bcf5b8811be8ffa4f9c
3
+ size 2799
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:059641ac73283a9c0aaf62b3130ead411b9a4912cd5a172887570e9878a681d9
3
  size 331497705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1d430a37d7227f2ff689dfe9836ff507b99cf6e911a7b78439d25332b54598
3
  size 331497705
runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632040336.patrick-general-gpu.480409.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f27f2af251d77d30e5412ebaf64f6d8b7ce3073f766dfd9d017c1e3d83a5b42
3
- size 3648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07bec62a368f913a44fd6366ace888d0066df49e7b96ea538acd30712c971b10
3
+ size 4128