gchhablani commited on
Commit
f42909f
1 Parent(s): a370d21

Training in progress, epoch 5

Browse files
checkpoint-200/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": "wnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_entailment",
14
+ "1": "entailment"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "entailment": 1,
20
+ "not_entailment": 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-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f3707cf356216bf94f8045998ee0ff364c01be603134bdb1e28699b23f0156
3
+ size 662962197
checkpoint-200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c825b4c933a950d7d3f60ee6674d84bec214f9c3db0266f400941dccadf9409a
3
+ size 331497705
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:958c9e2a682eede97b84ae0076803f0bb839eb5ed5a43542930dccb2e9fc49c3
3
+ size 14503
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2d9de141c4d7c893f366f03bc36eb1e21b38067602ae80b7cfc2d4d1ad8d24
3
+ size 623
checkpoint-200/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-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/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-200/trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 200,
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": 1.6000000000000003e-05,
13
+ "loss": 0.7052,
14
+ "step": 40
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5633802816901409,
19
+ "eval_loss": 0.6902039051055908,
20
+ "eval_runtime": 0.5271,
21
+ "eval_samples_per_second": 134.707,
22
+ "eval_steps_per_second": 17.076,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 1.2e-05,
28
+ "loss": 0.6957,
29
+ "step": 80
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.43661971830985913,
34
+ "eval_loss": 0.7012577056884766,
35
+ "eval_runtime": 0.5221,
36
+ "eval_samples_per_second": 135.995,
37
+ "eval_steps_per_second": 17.239,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 8.000000000000001e-06,
43
+ "loss": 0.6898,
44
+ "step": 120
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.5352112676056338,
49
+ "eval_loss": 0.6898324489593506,
50
+ "eval_runtime": 0.5232,
51
+ "eval_samples_per_second": 135.691,
52
+ "eval_steps_per_second": 17.2,
53
+ "step": 120
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 4.000000000000001e-06,
58
+ "loss": 0.6958,
59
+ "step": 160
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.5633802816901409,
64
+ "eval_loss": 0.6874184608459473,
65
+ "eval_runtime": 0.5224,
66
+ "eval_samples_per_second": 135.906,
67
+ "eval_steps_per_second": 17.228,
68
+ "step": 160
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 0.0,
73
+ "loss": 0.6982,
74
+ "step": 200
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_accuracy": 0.5492957746478874,
79
+ "eval_loss": 0.6887156963348389,
80
+ "eval_runtime": 0.523,
81
+ "eval_samples_per_second": 135.751,
82
+ "eval_steps_per_second": 17.208,
83
+ "step": 200
84
+ }
85
+ ],
86
+ "max_steps": 200,
87
+ "num_train_epochs": 5,
88
+ "total_flos": 564638888601600.0,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0018d0bd5493d2abb91a78e7fe6494461f7f4d10944b54be5c94d6f6c54f5859
3
+ size 2799
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe832b99d1cedb1f93201b4d006be4b4ab822195e72e15f8fa2db8483e6361a
3
  size 331497705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c825b4c933a950d7d3f60ee6674d84bec214f9c3db0266f400941dccadf9409a
3
  size 331497705
runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817737.patrick-general-gpu.194163.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45e7b48829e156ea65cddff0a729cc931e4b80a7143ac333269412b1c3e1f149
3
- size 5077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7c06557997450138a2e9f842f00f90c573d0f7e2cf8143b69d72cf762e34740
3
+ size 5557