Hugging Face's logo

gchhablani
/
fnet-large-finetuned-mnli

Text Classification
Transformers
PyTorch
TensorBoard
fnet
Inference Endpoints
Model card Files Metrics Community
gchhablani commited on
Commit
f7c7766
·
1 Parent(s): 211d414

Add checkpoints

Browse files
Files changed (43) hide show
  1. all_results.json +14 -0
  2. checkpoint-196352/config.json +35 -0
  3. checkpoint-196352/optimizer.pt +3 -0
  4. checkpoint-196352/pytorch_model.bin +3 -0
  5. checkpoint-196352/rng_state.pth +3 -0
  6. checkpoint-196352/scheduler.pt +3 -0
  7. checkpoint-196352/special_tokens_map.json +1 -0
  8. checkpoint-196352/tokenizer.json +0 -0
  9. checkpoint-196352/tokenizer_config.json +1 -0
  10. checkpoint-196352/trainer_state.json +46 -0
  11. checkpoint-196352/training_args.bin +3 -0
  12. checkpoint-294528/config.json +35 -0
  13. checkpoint-294528/optimizer.pt +3 -0
  14. checkpoint-294528/pytorch_model.bin +3 -0
  15. checkpoint-294528/rng_state.pth +3 -0
  16. checkpoint-294528/scheduler.pt +3 -0
  17. checkpoint-294528/special_tokens_map.json +1 -0
  18. checkpoint-294528/tokenizer.json +0 -0
  19. checkpoint-294528/tokenizer_config.json +1 -0
  20. checkpoint-294528/trainer_state.json +61 -0
  21. checkpoint-294528/training_args.bin +3 -0
  22. checkpoint-98176/config.json +35 -0
  23. checkpoint-98176/optimizer.pt +3 -0
  24. checkpoint-98176/pytorch_model.bin +3 -0
  25. checkpoint-98176/rng_state.pth +3 -0
  26. checkpoint-98176/scheduler.pt +3 -0
  27. checkpoint-98176/special_tokens_map.json +1 -0
  28. checkpoint-98176/tokenizer.json +0 -0
  29. checkpoint-98176/tokenizer_config.json +1 -0
  30. checkpoint-98176/trainer_state.json +31 -0
  31. checkpoint-98176/training_args.bin +3 -0
  32. config.json +35 -0
  33. eval_results.json +9 -0
  34. pytorch_model.bin +3 -0
  35. runs/Sep23_08-45-32_patrick-general-gpu/1632386803.5092177/events.out.tfevents.1632386803.patrick-general-gpu.978016.1 +3 -0
  36. runs/Sep23_08-45-32_patrick-general-gpu/events.out.tfevents.1632386803.patrick-general-gpu.978016.0 +3 -0
  37. runs/Sep23_08-45-32_patrick-general-gpu/events.out.tfevents.1632472740.patrick-general-gpu.978016.2 +3 -0
  38. special_tokens_map.json +1 -0
  39. tokenizer.json +0 -0
  40. tokenizer_config.json +1 -0
  41. train_results.json +8 -0
  42. trainer_state.json +70 -0
  43. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.7956672091131001,
4
+ "eval_loss": 0.9942970871925354,
5
+ "eval_runtime": 214.2499,
6
+ "eval_samples": 9832,
7
+ "eval_samples_per_second": 45.89,
8
+ "eval_steps_per_second": 5.736,
9
+ "train_loss": 0.5576832624996605,
10
+ "train_runtime": 85721.6525,
11
+ "train_samples": 392702,
12
+ "train_samples_per_second": 13.743,
13
+ "train_steps_per_second": 3.436
14
+ }
checkpoint-196352/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "neutral",
15
+ "2": "contradiction"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
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": 24,
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-196352/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe675864c65bd141a317da01998bbadea6b4cf12cef879444047875d75997356
3
+ size 1895705557
checkpoint-196352/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add264b071a683ff6b1d12c77ebe7bf7be6305843c185450eea683c7ce4d2bf8
3
+ size 947881129
checkpoint-196352/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440cd491eb10f141552b44cfb1527062c4c455b4ecd6aa3dbebcfc86fbc20cb3
3
+ size 14503
checkpoint-196352/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c6084f8bba6f63c4c3ce7bcc1468553c600a7aea047d2359565e41e4d148b5
3
+ size 623
checkpoint-196352/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-196352/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-196352/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-196352/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": 196352,
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": 0.7012,
14
+ "step": 98176
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7716760061130922,
19
+ "eval_loss": 0.6348065137863159,
20
+ "eval_runtime": 215.1813,
21
+ "eval_samples_per_second": 45.613,
22
+ "eval_steps_per_second": 5.702,
23
+ "step": 98176
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.5672,
29
+ "step": 196352
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.7882832399388691,
34
+ "eval_loss": 0.849821925163269,
35
+ "eval_runtime": 214.1745,
36
+ "eval_samples_per_second": 45.827,
37
+ "eval_steps_per_second": 5.729,
38
+ "step": 196352
39
+ }
40
+ ],
41
+ "max_steps": 294528,
42
+ "num_train_epochs": 3,
43
+ "total_flos": 4.913638599567237e+17,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-196352/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8709b7dc45e490729e0cf6d4d9c770ba40f06424b922c8c8109c4753cc4c61
3
+ size 2735
checkpoint-294528/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "neutral",
15
+ "2": "contradiction"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
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": 24,
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-294528/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53292996a64316c6206b23b2ac2c385f02db856c69c7f561638f4b5722e6962
3
+ size 1895705557
checkpoint-294528/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ab0eab036eaecb0bef2ac5e36105d418cffb4453128def3a2207de6f06694f
3
+ size 947881129
checkpoint-294528/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fede22a355a943a2fa8b27a7f0728acd03a4a87c8d2a66d22e95a29a9560a64
3
+ size 14503
checkpoint-294528/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925cf22a8ec1642736c08a275a1c329b031b1e8fb5c0408b3ec02430c2d3bde9
3
+ size 623
checkpoint-294528/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-294528/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-294528/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-294528/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 294528,
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": 0.7012,
14
+ "step": 98176
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7716760061130922,
19
+ "eval_loss": 0.6348065137863159,
20
+ "eval_runtime": 215.1813,
21
+ "eval_samples_per_second": 45.613,
22
+ "eval_steps_per_second": 5.702,
23
+ "step": 98176
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.5672,
29
+ "step": 196352
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.7882832399388691,
34
+ "eval_loss": 0.849821925163269,
35
+ "eval_runtime": 214.1745,
36
+ "eval_samples_per_second": 45.827,
37
+ "eval_steps_per_second": 5.729,
38
+ "step": 196352
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.4047,
44
+ "step": 294528
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.7896077432501274,
49
+ "eval_loss": 1.0135771036148071,
50
+ "eval_runtime": 214.0372,
51
+ "eval_samples_per_second": 45.857,
52
+ "eval_steps_per_second": 5.733,
53
+ "step": 294528
54
+ }
55
+ ],
56
+ "max_steps": 294528,
57
+ "num_train_epochs": 3,
58
+ "total_flos": 7.370457899350856e+17,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-294528/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8709b7dc45e490729e0cf6d4d9c770ba40f06424b922c8c8109c4753cc4c61
3
+ size 2735
checkpoint-98176/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "neutral",
15
+ "2": "contradiction"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
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": 24,
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-98176/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d21ded37348bfded42899e47e05f95d8a49a93b10f59d7fc01e88ae2f20d82
3
+ size 1895705557
checkpoint-98176/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921b0c85cd8d7420f2922330543b40aa2684b3e4e86830becc76479f5ae93b58
3
+ size 947881129
checkpoint-98176/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7804317abb8fa47a79a8bd7591f9da27af83aa1e7baf31f61be46a02be1b59c
3
+ size 14503
checkpoint-98176/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a256ab82c250b1fa51a2d56a25cbec0981416a5e5d65628713cdfae707cc87
3
+ size 623
checkpoint-98176/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-98176/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-98176/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-98176/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": 98176,
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": 0.7012,
14
+ "step": 98176
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7716760061130922,
19
+ "eval_loss": 0.6348065137863159,
20
+ "eval_runtime": 215.1813,
21
+ "eval_samples_per_second": 45.613,
22
+ "eval_steps_per_second": 5.702,
23
+ "step": 98176
24
+ }
25
+ ],
26
+ "max_steps": 294528,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 2.4568192997836186e+17,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-98176/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8709b7dc45e490729e0cf6d4d9c770ba40f06424b922c8c8109c4753cc4c61
3
+ size 2735
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "neutral",
15
+ "2": "contradiction"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
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": 24,
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
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.7956672091131001,
4
+ "eval_loss": 0.9942970871925354,
5
+ "eval_runtime": 214.2499,
6
+ "eval_samples": 9832,
7
+ "eval_samples_per_second": 45.89,
8
+ "eval_steps_per_second": 5.736
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ab0eab036eaecb0bef2ac5e36105d418cffb4453128def3a2207de6f06694f
3
+ size 947881129
runs/Sep23_08-45-32_patrick-general-gpu/1632386803.5092177/events.out.tfevents.1632386803.patrick-general-gpu.978016.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97a00e4513b52fe2360a38354b6599c94b7a03c5e7e8d0843285d770f85907c4
3
+ size 4349
runs/Sep23_08-45-32_patrick-general-gpu/events.out.tfevents.1632386803.patrick-general-gpu.978016.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45eb9e487c3426f8c16b8562f9f03c926d8433d72ee53f3d130754fff74c0396
3
+ size 5047
runs/Sep23_08-45-32_patrick-general-gpu/events.out.tfevents.1632472740.patrick-general-gpu.978016.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716b03023590cff8e208e9615098ce7d40a0e09c3fb4b9451ebf6025836a97a3
3
+ size 698
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": 0.5576832624996605,
4
+ "train_runtime": 85721.6525,
5
+ "train_samples": 392702,
6
+ "train_samples_per_second": 13.743,
7
+ "train_steps_per_second": 3.436
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 294528,
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": 0.7012,
14
+ "step": 98176
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7716760061130922,
19
+ "eval_loss": 0.6348065137863159,
20
+ "eval_runtime": 215.1813,
21
+ "eval_samples_per_second": 45.613,
22
+ "eval_steps_per_second": 5.702,
23
+ "step": 98176
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.5672,
29
+ "step": 196352
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.7882832399388691,
34
+ "eval_loss": 0.849821925163269,
35
+ "eval_runtime": 214.1745,
36
+ "eval_samples_per_second": 45.827,
37
+ "eval_steps_per_second": 5.729,
38
+ "step": 196352
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.4047,
44
+ "step": 294528
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.7896077432501274,
49
+ "eval_loss": 1.0135771036148071,
50
+ "eval_runtime": 214.0372,
51
+ "eval_samples_per_second": 45.857,
52
+ "eval_steps_per_second": 5.733,
53
+ "step": 294528
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "step": 294528,
58
+ "total_flos": 7.370457899350856e+17,
59
+ "train_loss": 0.5576832624996605,
60
+ "train_runtime": 85721.6525,
61
+ "train_samples_per_second": 13.743,
62
+ "train_steps_per_second": 3.436
63
+ }
64
+ ],
65
+ "max_steps": 294528,
66
+ "num_train_epochs": 3,
67
+ "total_flos": 7.370457899350856e+17,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8709b7dc45e490729e0cf6d4d9c770ba40f06424b922c8c8109c4753cc4c61
3
+ size 2735