Hugging Face's logo

gchhablani
/
fnet-large-finetuned-stsb

Text Classification
Transformers
PyTorch
TensorBoard
English
fnet
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
gchhablani commited on
Commit
5ec8f5c
•
1 Parent(s): ab9a75b

Add checkpoints

Browse files
Files changed (44) hide show
  1. README.md +78 -0
  2. all_results.json +16 -0
  3. checkpoint-1438/config.json +31 -0
  4. checkpoint-1438/optimizer.pt +3 -0
  5. checkpoint-1438/pytorch_model.bin +3 -0
  6. checkpoint-1438/rng_state.pth +3 -0
  7. checkpoint-1438/scheduler.pt +3 -0
  8. checkpoint-1438/special_tokens_map.json +1 -0
  9. checkpoint-1438/tokenizer.json +0 -0
  10. checkpoint-1438/tokenizer_config.json +1 -0
  11. checkpoint-1438/trainer_state.json +33 -0
  12. checkpoint-1438/training_args.bin +3 -0
  13. checkpoint-2876/config.json +31 -0
  14. checkpoint-2876/optimizer.pt +3 -0
  15. checkpoint-2876/pytorch_model.bin +3 -0
  16. checkpoint-2876/rng_state.pth +3 -0
  17. checkpoint-2876/scheduler.pt +3 -0
  18. checkpoint-2876/special_tokens_map.json +1 -0
  19. checkpoint-2876/tokenizer.json +0 -0
  20. checkpoint-2876/tokenizer_config.json +1 -0
  21. checkpoint-2876/trainer_state.json +50 -0
  22. checkpoint-2876/training_args.bin +3 -0
  23. checkpoint-4314/config.json +31 -0
  24. checkpoint-4314/optimizer.pt +3 -0
  25. checkpoint-4314/pytorch_model.bin +3 -0
  26. checkpoint-4314/rng_state.pth +3 -0
  27. checkpoint-4314/scheduler.pt +3 -0
  28. checkpoint-4314/special_tokens_map.json +1 -0
  29. checkpoint-4314/tokenizer.json +0 -0
  30. checkpoint-4314/tokenizer_config.json +1 -0
  31. checkpoint-4314/trainer_state.json +67 -0
  32. checkpoint-4314/training_args.bin +3 -0
  33. config.json +31 -0
  34. eval_results.json +11 -0
  35. pytorch_model.bin +3 -0
  36. runs/Sep24_18-20-37_patrick-general-gpu/1632507649.2059364/events.out.tfevents.1632507649.patrick-general-gpu.1107165.1 +3 -0
  37. runs/Sep24_18-20-37_patrick-general-gpu/events.out.tfevents.1632507649.patrick-general-gpu.1107165.0 +3 -0
  38. runs/Sep24_18-20-37_patrick-general-gpu/events.out.tfevents.1632509035.patrick-general-gpu.1107165.2 +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 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - spearmanr
11
+ model-index:
12
+ - name: fnet-large-finetuned-stsb
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: GLUE STSB
19
+ type: glue
20
+ args: stsb
21
+ metrics:
22
+ - name: Spearmanr
23
+ type: spearmanr
24
+ value: 0.8532669137129205
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # fnet-large-finetuned-stsb
31
+
32
+ This model is a fine-tuned version of [google/fnet-large](https://huggingface.co/google/fnet-large) on the GLUE STSB dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.6250
35
+ - Pearson: 0.8554
36
+ - Spearmanr: 0.8533
37
+ - Combined Score: 0.8543
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 2e-05
57
+ - train_batch_size: 4
58
+ - eval_batch_size: 8
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 3.0
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
67
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
68
+ | 1.0727 | 1.0 | 1438 | 0.7718 | 0.8187 | 0.8240 | 0.8214 |
69
+ | 0.4619 | 2.0 | 2876 | 0.7704 | 0.8472 | 0.8500 | 0.8486 |
70
+ | 0.2401 | 3.0 | 4314 | 0.6250 | 0.8554 | 0.8533 | 0.8543 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.11.0.dev0
76
+ - Pytorch 1.9.0
77
+ - Datasets 1.12.1
78
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_combined_score": 0.8543492000039965,
4
+ "eval_loss": 0.625028669834137,
5
+ "eval_pearson": 0.8554314862950724,
6
+ "eval_runtime": 32.7479,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 45.804,
9
+ "eval_spearmanr": 0.8532669137129205,
10
+ "eval_steps_per_second": 5.741,
11
+ "train_loss": 0.5915702214990438,
12
+ "train_runtime": 1352.1371,
13
+ "train_samples": 5749,
14
+ "train_samples_per_second": 12.755,
15
+ "train_steps_per_second": 3.191
16
+ }
checkpoint-1438/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "stsb",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "fnet",
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 3,
25
+ "torch_dtype": "float32",
26
+ "tpu_short_seq_length": 512,
27
+ "transformers_version": "4.11.0.dev0",
28
+ "type_vocab_size": 4,
29
+ "use_tpu_fourier_optimizations": false,
30
+ "vocab_size": 32000
31
+ }
checkpoint-1438/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a17c3fc7d93aa0ffce781a7e1356cfc640d8f30bb53643700dfea2614b8d9f91
3
+ size 1895688789
checkpoint-1438/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3028c92bd412e01da676bb811453b596c016746a9ec287648c8caac4d3046aa0
3
+ size 947872937
checkpoint-1438/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8381521d20c6732d143465da0c03debb51e75d3069a76d162927c1321648deea
3
+ size 14503
checkpoint-1438/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de648507a643c5cadb8a9fef6b709da7404fa161138afa69ddb2134bd0236c57
3
+ size 623
checkpoint-1438/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-1438/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1438/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-1438/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": 1438,
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": 1.0727,
14
+ "step": 1438
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_combined_score": 0.8213591113451347,
19
+ "eval_loss": 0.7718442678451538,
20
+ "eval_pearson": 0.818709053341712,
21
+ "eval_runtime": 32.7792,
22
+ "eval_samples_per_second": 45.761,
23
+ "eval_spearmanr": 0.8240091693485575,
24
+ "eval_steps_per_second": 5.735,
25
+ "step": 1438
26
+ }
27
+ ],
28
+ "max_steps": 4314,
29
+ "num_train_epochs": 3,
30
+ "total_flos": 3596648852585472.0,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-1438/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c887545f46b2401f9ca1984e8435a6b2cbaad512b73b402c41a85807f586e79
3
+ size 2735
checkpoint-2876/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "stsb",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "fnet",
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 3,
25
+ "torch_dtype": "float32",
26
+ "tpu_short_seq_length": 512,
27
+ "transformers_version": "4.11.0.dev0",
28
+ "type_vocab_size": 4,
29
+ "use_tpu_fourier_optimizations": false,
30
+ "vocab_size": 32000
31
+ }
checkpoint-2876/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f543368b2fef0ab280c17a990dcefa838dfd40a9850da42e5471a8de536aad
3
+ size 1895688789
checkpoint-2876/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de5381b30198de5e47041ff0aba8fdd4b6ab35e8417fbe847d8e97f8f6483a77
3
+ size 947872937
checkpoint-2876/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ccbeb3065092bd911e80126e4c66de03b109e371c9aacb1d80ec7b5dae0f3b
3
+ size 14503
checkpoint-2876/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6bf02f832915ae45a688359d3c748bf6988ac25d02572aade0b20aac24cc9df
3
+ size 623
checkpoint-2876/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-2876/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2876/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-2876/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": 2876,
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": 1.0727,
14
+ "step": 1438
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_combined_score": 0.8213591113451347,
19
+ "eval_loss": 0.7718442678451538,
20
+ "eval_pearson": 0.818709053341712,
21
+ "eval_runtime": 32.7792,
22
+ "eval_samples_per_second": 45.761,
23
+ "eval_spearmanr": 0.8240091693485575,
24
+ "eval_steps_per_second": 5.735,
25
+ "step": 1438
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 0.4619,
31
+ "step": 2876
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_combined_score": 0.8486223143978786,
36
+ "eval_loss": 0.7704320549964905,
37
+ "eval_pearson": 0.847231018036828,
38
+ "eval_runtime": 32.6549,
39
+ "eval_samples_per_second": 45.935,
40
+ "eval_spearmanr": 0.8500136107589293,
41
+ "eval_steps_per_second": 5.757,
42
+ "step": 2876
43
+ }
44
+ ],
45
+ "max_steps": 4314,
46
+ "num_train_epochs": 3,
47
+ "total_flos": 7193297705170944.0,
48
+ "trial_name": null,
49
+ "trial_params": null
50
+ }
checkpoint-2876/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c887545f46b2401f9ca1984e8435a6b2cbaad512b73b402c41a85807f586e79
3
+ size 2735
checkpoint-4314/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "stsb",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "fnet",
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 3,
25
+ "torch_dtype": "float32",
26
+ "tpu_short_seq_length": 512,
27
+ "transformers_version": "4.11.0.dev0",
28
+ "type_vocab_size": 4,
29
+ "use_tpu_fourier_optimizations": false,
30
+ "vocab_size": 32000
31
+ }
checkpoint-4314/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c722740f34d05e04371b9307cefc477a0f09c3e8aaf1eb9998397d628966a0af
3
+ size 1895688789
checkpoint-4314/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5198505b96a0cd3cf792df678f2f11533e7641df09e7543dabf3d1c0bf85ceb
3
+ size 947872937
checkpoint-4314/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5c196dde8a84b13c86282b36617bd0291fe5564eef5d831a7304d2602ab4c68
3
+ size 14503
checkpoint-4314/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64dbe7884195d95dce4c935057f8800babdea0a35c2585f6a379160b3100892b
3
+ size 623
checkpoint-4314/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-4314/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4314/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-4314/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": 4314,
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": 1.0727,
14
+ "step": 1438
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_combined_score": 0.8213591113451347,
19
+ "eval_loss": 0.7718442678451538,
20
+ "eval_pearson": 0.818709053341712,
21
+ "eval_runtime": 32.7792,
22
+ "eval_samples_per_second": 45.761,
23
+ "eval_spearmanr": 0.8240091693485575,
24
+ "eval_steps_per_second": 5.735,
25
+ "step": 1438
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 0.4619,
31
+ "step": 2876
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_combined_score": 0.8486223143978786,
36
+ "eval_loss": 0.7704320549964905,
37
+ "eval_pearson": 0.847231018036828,
38
+ "eval_runtime": 32.6549,
39
+ "eval_samples_per_second": 45.935,
40
+ "eval_spearmanr": 0.8500136107589293,
41
+ "eval_steps_per_second": 5.757,
42
+ "step": 2876
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 0.0,
47
+ "loss": 0.2401,
48
+ "step": 4314
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_combined_score": 0.8543492000039965,
53
+ "eval_loss": 0.625028669834137,
54
+ "eval_pearson": 0.8554314862950724,
55
+ "eval_runtime": 32.627,
56
+ "eval_samples_per_second": 45.974,
57
+ "eval_spearmanr": 0.8532669137129205,
58
+ "eval_steps_per_second": 5.762,
59
+ "step": 4314
60
+ }
61
+ ],
62
+ "max_steps": 4314,
63
+ "num_train_epochs": 3,
64
+ "total_flos": 1.0789946557756416e+16,
65
+ "trial_name": null,
66
+ "trial_params": null
67
+ }
checkpoint-4314/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c887545f46b2401f9ca1984e8435a6b2cbaad512b73b402c41a85807f586e79
3
+ size 2735
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "stsb",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "fnet",
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 3,
25
+ "torch_dtype": "float32",
26
+ "tpu_short_seq_length": 512,
27
+ "transformers_version": "4.11.0.dev0",
28
+ "type_vocab_size": 4,
29
+ "use_tpu_fourier_optimizations": false,
30
+ "vocab_size": 32000
31
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_combined_score": 0.8543492000039965,
4
+ "eval_loss": 0.625028669834137,
5
+ "eval_pearson": 0.8554314862950724,
6
+ "eval_runtime": 32.7479,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 45.804,
9
+ "eval_spearmanr": 0.8532669137129205,
10
+ "eval_steps_per_second": 5.741
11
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5198505b96a0cd3cf792df678f2f11533e7641df09e7543dabf3d1c0bf85ceb
3
+ size 947872937
runs/Sep24_18-20-37_patrick-general-gpu/1632507649.2059364/events.out.tfevents.1632507649.patrick-general-gpu.1107165.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8bbda3d5255625b5eabb2252ec559cdee1aa75af3a6cac5986da4a259e4a24d
3
+ size 4349
runs/Sep24_18-20-37_patrick-general-gpu/events.out.tfevents.1632507649.patrick-general-gpu.1107165.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc73cb903dcedbd392585526c538ce7bb6b5830cd0f59d7f8bacc275b8589b33
3
+ size 5250
runs/Sep24_18-20-37_patrick-general-gpu/events.out.tfevents.1632509035.patrick-general-gpu.1107165.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccf15b70367b9e177334446acf085142e206850d09a5b607d362e6922a30bcd
3
+ size 473
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": 0.5915702214990438,
4
+ "train_runtime": 1352.1371,
5
+ "train_samples": 5749,
6
+ "train_samples_per_second": 12.755,
7
+ "train_steps_per_second": 3.191
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": 4314,
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": 1.0727,
14
+ "step": 1438
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_combined_score": 0.8213591113451347,
19
+ "eval_loss": 0.7718442678451538,
20
+ "eval_pearson": 0.818709053341712,
21
+ "eval_runtime": 32.7792,
22
+ "eval_samples_per_second": 45.761,
23
+ "eval_spearmanr": 0.8240091693485575,
24
+ "eval_steps_per_second": 5.735,
25
+ "step": 1438
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 0.4619,
31
+ "step": 2876
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_combined_score": 0.8486223143978786,
36
+ "eval_loss": 0.7704320549964905,
37
+ "eval_pearson": 0.847231018036828,
38
+ "eval_runtime": 32.6549,
39
+ "eval_samples_per_second": 45.935,
40
+ "eval_spearmanr": 0.8500136107589293,
41
+ "eval_steps_per_second": 5.757,
42
+ "step": 2876
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 0.0,
47
+ "loss": 0.2401,
48
+ "step": 4314
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_combined_score": 0.8543492000039965,
53
+ "eval_loss": 0.625028669834137,
54
+ "eval_pearson": 0.8554314862950724,
55
+ "eval_runtime": 32.627,
56
+ "eval_samples_per_second": 45.974,
57
+ "eval_spearmanr": 0.8532669137129205,
58
+ "eval_steps_per_second": 5.762,
59
+ "step": 4314
60
+ },
61
+ {
62
+ "epoch": 3.0,
63
+ "step": 4314,
64
+ "total_flos": 1.0789946557756416e+16,
65
+ "train_loss": 0.5915702214990438,
66
+ "train_runtime": 1352.1371,
67
+ "train_samples_per_second": 12.755,
68
+ "train_steps_per_second": 3.191
69
+ }
70
+ ],
71
+ "max_steps": 4314,
72
+ "num_train_epochs": 3,
73
+ "total_flos": 1.0789946557756416e+16,
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 sha256:3c887545f46b2401f9ca1984e8435a6b2cbaad512b73b402c41a85807f586e79
3
+ size 2735