gchhablani commited on
Commit
05c581a
1 Parent(s): c2a5a6f

Training in progress, epoch 3

Browse files
checkpoint-1605/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": "cola",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "unacceptable",
14
+ "1": "acceptable"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "acceptable": 1,
20
+ "unacceptable": 0
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-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f61f465b3ee19b1ba73b7a4b0a12a73043501526edb4e49f905a8d855e44e2
3
+ size 662962261
checkpoint-1605/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2663d881bea73fc94c3a6fee90ae84e7a071a6ae9cd1b0bb7eace5ad5f5163a
3
+ size 331497705
checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3073cce146d32a4cbdc8f7f1fd5e284dabd15186d6e0df89890ec1c34375f613
3
+ size 14503
checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1acca92a8b10bd06cc866eafb8aeb9d4f85bcdb2d57143bebcfe2bc573e5d33a
3
+ size 623
checkpoint-1605/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-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1605/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-1605/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": 1605,
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": 0.5895,
14
+ "step": 535
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.6146270632743835,
19
+ "eval_matthews_correlation": 0.16988650877044353,
20
+ "eval_runtime": 7.5781,
21
+ "eval_samples_per_second": 137.634,
22
+ "eval_steps_per_second": 17.287,
23
+ "step": 535
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.4656,
29
+ "step": 1070
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_loss": 0.5666966438293457,
34
+ "eval_matthews_correlation": 0.30468062994701894,
35
+ "eval_runtime": 7.5686,
36
+ "eval_samples_per_second": 137.807,
37
+ "eval_steps_per_second": 17.308,
38
+ "step": 1070
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.3329,
44
+ "step": 1605
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_loss": 0.5929099917411804,
49
+ "eval_matthews_correlation": 0.35940659235571387,
50
+ "eval_runtime": 7.5654,
51
+ "eval_samples_per_second": 137.865,
52
+ "eval_steps_per_second": 17.316,
53
+ "step": 1605
54
+ }
55
+ ],
56
+ "max_steps": 1605,
57
+ "num_train_epochs": 3,
58
+ "total_flos": 4562104380880896.0,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-1605/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1065b6c21962e07acc7e5e66d233473b94f201230ab4baac099ee8ece74e5327
3
+ size 2799
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85a6d9d605e9095607d42698a9b93353f860d7ec7d068fcae5dafcb027c4c7fd
3
  size 331497705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2663d881bea73fc94c3a6fee90ae84e7a071a6ae9cd1b0bb7eace5ad5f5163a
3
  size 331497705
runs/Sep16_19-30-53_patrick-general-gpu/events.out.tfevents.1631820668.patrick-general-gpu.205020.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:195cf06a0cbb228ee1919e0e60eca2f51be36f37f9f68e2f17a6ef4846a712c1
3
- size 4164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6d5bd7febf0a97a957cd66f7bb445a5d9d432650464ed60ac68ba42ca591f3
3
+ size 4656