Hugging Face's logo

gchhablani
/
fnet-large-finetuned-qqp

Text Classification
Transformers
PyTorch
TensorBoard
English
fnet
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
gchhablani commited on
Commit
01d3c02
•
1 Parent(s): 56381a2

Add checkpoints

Browse files
Files changed (44) hide show
  1. README.md +82 -0
  2. all_results.json +16 -0
  3. checkpoint-181924/config.json +36 -0
  4. checkpoint-181924/optimizer.pt +3 -0
  5. checkpoint-181924/pytorch_model.bin +3 -0
  6. checkpoint-181924/rng_state.pth +3 -0
  7. checkpoint-181924/scheduler.pt +3 -0
  8. checkpoint-181924/special_tokens_map.json +1 -0
  9. checkpoint-181924/tokenizer.json +0 -0
  10. checkpoint-181924/tokenizer_config.json +1 -0
  11. checkpoint-181924/trainer_state.json +50 -0
  12. checkpoint-181924/training_args.bin +3 -0
  13. checkpoint-272886/config.json +36 -0
  14. checkpoint-272886/optimizer.pt +3 -0
  15. checkpoint-272886/pytorch_model.bin +3 -0
  16. checkpoint-272886/rng_state.pth +3 -0
  17. checkpoint-272886/scheduler.pt +3 -0
  18. checkpoint-272886/special_tokens_map.json +1 -0
  19. checkpoint-272886/tokenizer.json +0 -0
  20. checkpoint-272886/tokenizer_config.json +1 -0
  21. checkpoint-272886/trainer_state.json +67 -0
  22. checkpoint-272886/training_args.bin +3 -0
  23. checkpoint-90962/config.json +36 -0
  24. checkpoint-90962/optimizer.pt +3 -0
  25. checkpoint-90962/pytorch_model.bin +3 -0
  26. checkpoint-90962/rng_state.pth +3 -0
  27. checkpoint-90962/scheduler.pt +3 -0
  28. checkpoint-90962/special_tokens_map.json +1 -0
  29. checkpoint-90962/tokenizer.json +0 -0
  30. checkpoint-90962/tokenizer_config.json +1 -0
  31. checkpoint-90962/trainer_state.json +33 -0
  32. checkpoint-90962/training_args.bin +3 -0
  33. config.json +36 -0
  34. eval_results.json +11 -0
  35. pytorch_model.bin +3 -0
  36. runs/Oct07_18-47-52_patrick-general-gpu/1633632529.3936458/events.out.tfevents.1633632529.patrick-general-gpu.7674.1 +3 -0
  37. runs/Oct07_18-47-52_patrick-general-gpu/events.out.tfevents.1633632529.patrick-general-gpu.7674.0 +3 -0
  38. runs/Oct07_18-47-52_patrick-general-gpu/events.out.tfevents.1633713835.patrick-general-gpu.7674.2 +3 -0
  39. special_tokens_map.json +1 -0
  40. tokenizer.json +0 -0
  41. tokenizer_config.json +1 -0
  42. train_results.json +8 -0
  43. trainer_state.json +76 -0
  44. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ model-index:
13
+ - name: fnet-large-finetuned-qqp
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: GLUE QQP
20
+ type: glue
21
+ args: qqp
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8943111550828593
26
+ - name: F1
27
+ type: f1
28
+ value: 0.8556565212985171
29
+ ---
30
+
31
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
+ should probably proofread and complete it, then remove this comment. -->
33
+
34
+ # fnet-large-finetuned-qqp
35
+
36
+ This model is a fine-tuned version of [google/fnet-large](https://huggingface.co/google/fnet-large) on the GLUE QQP dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.5515
39
+ - Accuracy: 0.8943
40
+ - F1: 0.8557
41
+ - Combined Score: 0.8750
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 2e-05
61
+ - train_batch_size: 4
62
+ - eval_batch_size: 8
63
+ - seed: 42
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: linear
66
+ - num_epochs: 3.0
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
71
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:--------------:|
72
+ | 0.4574 | 1.0 | 90962 | 0.4946 | 0.8694 | 0.8297 | 0.8496 |
73
+ | 0.3387 | 2.0 | 181924 | 0.4745 | 0.8874 | 0.8437 | 0.8655 |
74
+ | 0.2029 | 3.0 | 272886 | 0.5515 | 0.8943 | 0.8557 | 0.8750 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.11.0.dev0
80
+ - Pytorch 1.9.0
81
+ - Datasets 1.12.1
82
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8943111550828593,
4
+ "eval_combined_score": 0.8749838381906883,
5
+ "eval_f1": 0.8556565212985171,
6
+ "eval_loss": 0.5514675378799438,
7
+ "eval_runtime": 880.1227,
8
+ "eval_samples": 40430,
9
+ "eval_samples_per_second": 45.937,
10
+ "eval_steps_per_second": 5.742,
11
+ "train_loss": 0.33302516177772035,
12
+ "train_runtime": 80424.3343,
13
+ "train_samples": 363846,
14
+ "train_samples_per_second": 13.572,
15
+ "train_steps_per_second": 3.393
16
+ }
checkpoint-181924/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "actual_seq_length": 512,
4
+ "architectures": [
5
+ "FNetForSequenceClassification"
6
+ ],
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "finetuning_task": "qqp",
10
+ "hidden_act": "gelu_new",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "not_duplicate",
15
+ "1": "duplicate"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "duplicate": 1,
21
+ "not_duplicate": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "fnet",
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 3,
28
+ "torch_dtype": "float32",
29
+ "tpu_short_seq_length": 512,
30
+ "transformers_version": "4.11.0.dev0",
31
+ "type_vocab_size": 4,
32
+ "use_fft": true,
33
+ "use_latest": false,
34
+ "use_tpu_fourier_optimizations": false,
35
+ "vocab_size": 32000
36
+ }
checkpoint-181924/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:356eac65cad9d8f53e26c8f72cc0748eeb75e20d6a6cbd3f5a69fc6c74b84e10
3
+ size 1895697365
checkpoint-181924/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62fc2f96dd91c48b89926560a5100682ac9599da6ae0a775a3affaa6625e6c9
3
+ size 947877033
checkpoint-181924/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88870878240675cd1765ef9c08970d1c905a2445b60d9436c655cb0f370e5e6
3
+ size 14503
checkpoint-181924/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86181bb01c20f7a468946469c97d839677b71c857e93d81e3a335c84c2976968
3
+ size 623
checkpoint-181924/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-181924/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-181924/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": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
checkpoint-181924/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 181924,
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": 0.4574,
14
+ "step": 90962
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.869403907989117,
19
+ "eval_combined_score": 0.8495626351091097,
20
+ "eval_f1": 0.8297213622291022,
21
+ "eval_loss": 0.4945518374443054,
22
+ "eval_runtime": 876.4633,
23
+ "eval_samples_per_second": 46.129,
24
+ "eval_steps_per_second": 5.766,
25
+ "step": 90962
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 0.3387,
31
+ "step": 181924
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.8873608706406134,
36
+ "eval_combined_score": 0.8655189633993949,
37
+ "eval_f1": 0.8436770561581766,
38
+ "eval_loss": 0.47449207305908203,
39
+ "eval_runtime": 876.5998,
40
+ "eval_samples_per_second": 46.121,
41
+ "eval_steps_per_second": 5.765,
42
+ "step": 181924
43
+ }
44
+ ],
45
+ "max_steps": 272886,
46
+ "num_train_epochs": 3,
47
+ "total_flos": 4.55255830552191e+17,
48
+ "trial_name": null,
49
+ "trial_params": null
50
+ }
checkpoint-181924/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3453e7fb209e2d4f6345b8ff751fcc363e00c0536c39f3fbc8f5d8792d7ac6
3
+ size 2735
checkpoint-272886/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "actual_seq_length": 512,
4
+ "architectures": [
5
+ "FNetForSequenceClassification"
6
+ ],
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "finetuning_task": "qqp",
10
+ "hidden_act": "gelu_new",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "not_duplicate",
15
+ "1": "duplicate"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "duplicate": 1,
21
+ "not_duplicate": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "fnet",
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 3,
28
+ "torch_dtype": "float32",
29
+ "tpu_short_seq_length": 512,
30
+ "transformers_version": "4.11.0.dev0",
31
+ "type_vocab_size": 4,
32
+ "use_fft": true,
33
+ "use_latest": false,
34
+ "use_tpu_fourier_optimizations": false,
35
+ "vocab_size": 32000
36
+ }
checkpoint-272886/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651b0b02538fe4aebd54414c0ab010758cb638908e876dffbceb2d7b076a09f4
3
+ size 1895697365
checkpoint-272886/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df739a99f45c64cd26fed95a3472559fc85affd2d94b2819157cb40ffbeb90d7
3
+ size 947877033
checkpoint-272886/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4f5422ead01a5f6b04bab6f520e24955a185100ba36cf2798e425491fe0eb5a
3
+ size 14503
checkpoint-272886/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65901e571bc51bc6bdc6fe5fbb1bd0b3f76e35188d6e68147199d1bc05c163b1
3
+ size 623
checkpoint-272886/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-272886/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-272886/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": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
checkpoint-272886/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 272886,
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": 0.4574,
14
+ "step": 90962
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.869403907989117,
19
+ "eval_combined_score": 0.8495626351091097,
20
+ "eval_f1": 0.8297213622291022,
21
+ "eval_loss": 0.4945518374443054,
22
+ "eval_runtime": 876.4633,
23
+ "eval_samples_per_second": 46.129,
24
+ "eval_steps_per_second": 5.766,
25
+ "step": 90962
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 0.3387,
31
+ "step": 181924
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.8873608706406134,
36
+ "eval_combined_score": 0.8655189633993949,
37
+ "eval_f1": 0.8436770561581766,
38
+ "eval_loss": 0.47449207305908203,
39
+ "eval_runtime": 876.5998,
40
+ "eval_samples_per_second": 46.121,
41
+ "eval_steps_per_second": 5.765,
42
+ "step": 181924
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 0.0,
47
+ "loss": 0.2029,
48
+ "step": 272886
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8943111550828593,
53
+ "eval_combined_score": 0.8749838381906883,
54
+ "eval_f1": 0.8556565212985171,
55
+ "eval_loss": 0.5514675378799438,
56
+ "eval_runtime": 879.9699,
57
+ "eval_samples_per_second": 45.945,
58
+ "eval_steps_per_second": 5.743,
59
+ "step": 272886
60
+ }
61
+ ],
62
+ "max_steps": 272886,
63
+ "num_train_epochs": 3,
64
+ "total_flos": 6.828837458282865e+17,
65
+ "trial_name": null,
66
+ "trial_params": null
67
+ }
checkpoint-272886/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3453e7fb209e2d4f6345b8ff751fcc363e00c0536c39f3fbc8f5d8792d7ac6
3
+ size 2735
checkpoint-90962/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "actual_seq_length": 512,
4
+ "architectures": [
5
+ "FNetForSequenceClassification"
6
+ ],
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "finetuning_task": "qqp",
10
+ "hidden_act": "gelu_new",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "not_duplicate",
15
+ "1": "duplicate"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "duplicate": 1,
21
+ "not_duplicate": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "fnet",
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 3,
28
+ "torch_dtype": "float32",
29
+ "tpu_short_seq_length": 512,
30
+ "transformers_version": "4.11.0.dev0",
31
+ "type_vocab_size": 4,
32
+ "use_fft": true,
33
+ "use_latest": false,
34
+ "use_tpu_fourier_optimizations": false,
35
+ "vocab_size": 32000
36
+ }
checkpoint-90962/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb08a81a65b959d9bcd7b1e45ee22ae88a769c6e0d5623cae80d280c7006370
3
+ size 1895697365
checkpoint-90962/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f03b27e600a88e9819c26f8d8f06b976fde14306eb9e3eb7bb04b44fcb9f8d9
3
+ size 947877033
checkpoint-90962/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa1252da6a44aa0df7ab15528038774e20d39ab4daf4f77507741c577bbe05c
3
+ size 14503
checkpoint-90962/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d423117ef475f193d50a0e5947239f6abc81c66955fdd7e6217345c82e83d62
3
+ size 623
checkpoint-90962/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-90962/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-90962/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": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
checkpoint-90962/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 90962,
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": 0.4574,
14
+ "step": 90962
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.869403907989117,
19
+ "eval_combined_score": 0.8495626351091097,
20
+ "eval_f1": 0.8297213622291022,
21
+ "eval_loss": 0.4945518374443054,
22
+ "eval_runtime": 876.4633,
23
+ "eval_samples_per_second": 46.129,
24
+ "eval_steps_per_second": 5.766,
25
+ "step": 90962
26
+ }
27
+ ],
28
+ "max_steps": 272886,
29
+ "num_train_epochs": 3,
30
+ "total_flos": 2.276279152760955e+17,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-90962/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3453e7fb209e2d4f6345b8ff751fcc363e00c0536c39f3fbc8f5d8792d7ac6
3
+ size 2735
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "actual_seq_length": 512,
4
+ "architectures": [
5
+ "FNetForSequenceClassification"
6
+ ],
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "finetuning_task": "qqp",
10
+ "hidden_act": "gelu_new",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "not_duplicate",
15
+ "1": "duplicate"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "duplicate": 1,
21
+ "not_duplicate": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "fnet",
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 3,
28
+ "torch_dtype": "float32",
29
+ "tpu_short_seq_length": 512,
30
+ "transformers_version": "4.11.0.dev0",
31
+ "type_vocab_size": 4,
32
+ "use_fft": true,
33
+ "use_latest": false,
34
+ "use_tpu_fourier_optimizations": false,
35
+ "vocab_size": 32000
36
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8943111550828593,
4
+ "eval_combined_score": 0.8749838381906883,
5
+ "eval_f1": 0.8556565212985171,
6
+ "eval_loss": 0.5514675378799438,
7
+ "eval_runtime": 880.1227,
8
+ "eval_samples": 40430,
9
+ "eval_samples_per_second": 45.937,
10
+ "eval_steps_per_second": 5.742
11
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df739a99f45c64cd26fed95a3472559fc85affd2d94b2819157cb40ffbeb90d7
3
+ size 947877033
runs/Oct07_18-47-52_patrick-general-gpu/1633632529.3936458/events.out.tfevents.1633632529.patrick-general-gpu.7674.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119c3bae6f8512946c75750ad0ec62eb8df4f52a8491a4641c6ba86c83492e17
3
+ size 4346
runs/Oct07_18-47-52_patrick-general-gpu/events.out.tfevents.1633632529.patrick-general-gpu.7674.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a181d6dd1674fa7201bfdab42820754cadc59c17be0dd961a5e8f817ab0450c
3
+ size 5391
runs/Oct07_18-47-52_patrick-general-gpu/events.out.tfevents.1633713835.patrick-general-gpu.7674.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf0355b6c94f793bd370635267e8e830c2686310b9c6bb78ec0adb95203c737a
3
+ size 475
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": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.33302516177772035,
4
+ "train_runtime": 80424.3343,
5
+ "train_samples": 363846,
6
+ "train_samples_per_second": 13.572,
7
+ "train_steps_per_second": 3.393
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 272886,
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": 0.4574,
14
+ "step": 90962
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.869403907989117,
19
+ "eval_combined_score": 0.8495626351091097,
20
+ "eval_f1": 0.8297213622291022,
21
+ "eval_loss": 0.4945518374443054,
22
+ "eval_runtime": 876.4633,
23
+ "eval_samples_per_second": 46.129,
24
+ "eval_steps_per_second": 5.766,
25
+ "step": 90962
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 0.3387,
31
+ "step": 181924
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.8873608706406134,
36
+ "eval_combined_score": 0.8655189633993949,
37
+ "eval_f1": 0.8436770561581766,
38
+ "eval_loss": 0.47449207305908203,
39
+ "eval_runtime": 876.5998,
40
+ "eval_samples_per_second": 46.121,
41
+ "eval_steps_per_second": 5.765,
42
+ "step": 181924
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 0.0,
47
+ "loss": 0.2029,
48
+ "step": 272886
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8943111550828593,
53
+ "eval_combined_score": 0.8749838381906883,
54
+ "eval_f1": 0.8556565212985171,
55
+ "eval_loss": 0.5514675378799438,
56
+ "eval_runtime": 879.9699,
57
+ "eval_samples_per_second": 45.945,
58
+ "eval_steps_per_second": 5.743,
59
+ "step": 272886
60
+ },
61
+ {
62
+ "epoch": 3.0,
63
+ "step": 272886,
64
+ "total_flos": 6.828837458282865e+17,
65
+ "train_loss": 0.33302516177772035,
66
+ "train_runtime": 80424.3343,
67
+ "train_samples_per_second": 13.572,
68
+ "train_steps_per_second": 3.393
69
+ }
70
+ ],
71
+ "max_steps": 272886,
72
+ "num_train_epochs": 3,
73
+ "total_flos": 6.828837458282865e+17,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3453e7fb209e2d4f6345b8ff751fcc363e00c0536c39f3fbc8f5d8792d7ac6
3
+ size 2735