gchhablani commited on
Commit
8ee18ba
1 Parent(s): 3dd7f57

Training in progress, epoch 3

Browse files
checkpoint-1080/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "stsb",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
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": 12,
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-1080/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e735253a514cc2c0f79aaf4e3edf13c3056ad22d55145e0843ca7dc777472009
3
+ size 662956117
checkpoint-1080/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4eebdaf76581e9d2b1591ea760fbfe79f6f5829477e3d183d2c6bff5e8839a
3
+ size 331494633
checkpoint-1080/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c41e9f52a3754df91fa341960dc35e16bc94805466ea42f583bd94d97e82a53
3
+ size 14503
checkpoint-1080/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527295045d2586065b1903e97996e4dbfc999e3944d447aefd0d55843d2c92d2
3
+ size 623
checkpoint-1080/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-1080/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1080/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-1080/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": 1080,
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": 1.5473,
14
+ "step": 360
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_combined_score": 0.8120419393156919,
19
+ "eval_loss": 0.7750807404518127,
20
+ "eval_pearson": 0.8115414805311705,
21
+ "eval_runtime": 10.8984,
22
+ "eval_samples_per_second": 137.634,
23
+ "eval_spearmanr": 0.8125423981002132,
24
+ "eval_steps_per_second": 17.25,
25
+ "step": 360
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 0.6954,
31
+ "step": 720
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_combined_score": 0.8145095741908042,
36
+ "eval_loss": 0.8717353343963623,
37
+ "eval_pearson": 0.8159860577723805,
38
+ "eval_runtime": 10.909,
39
+ "eval_samples_per_second": 137.502,
40
+ "eval_spearmanr": 0.8130330906092277,
41
+ "eval_steps_per_second": 17.234,
42
+ "step": 720
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 0.0,
47
+ "loss": 0.4828,
48
+ "step": 1080
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_combined_score": 0.8237743551253471,
53
+ "eval_loss": 0.789396345615387,
54
+ "eval_pearson": 0.825608960477892,
55
+ "eval_runtime": 10.9264,
56
+ "eval_samples_per_second": 137.282,
57
+ "eval_spearmanr": 0.8219397497728022,
58
+ "eval_steps_per_second": 17.206,
59
+ "step": 1080
60
+ }
61
+ ],
62
+ "max_steps": 1080,
63
+ "num_train_epochs": 3,
64
+ "total_flos": 3067148834731008.0,
65
+ "trial_name": null,
66
+ "trial_params": null
67
+ }
checkpoint-1080/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5c6eb180bb5162515a2b4e6e16c49ba285a05c5fb2d9ca9fa6f6e3fa827889
3
+ size 2799
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:575ac348a486eb875c9b5018bcf08e8961e9d2f8525d87facacf5f120da6568d
3
  size 331494633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4eebdaf76581e9d2b1591ea760fbfe79f6f5829477e3d183d2c6bff5e8839a
3
  size 331494633
runs/Sep19_15-39-26_patrick-general-gpu/events.out.tfevents.1632065982.patrick-general-gpu.509410.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:856395f3745ee8c6860fb98dbf3e3dcdf5162fd0597db224e9309fd024fd019b
3
- size 4306
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f491d2df56edb97594ba0071576f5b4ae2cbb6f900c10b4e13a2f78adaa57c
3
+ size 4896