gchhablani commited on
Commit
ffabd30
1 Parent(s): 6dfa339

Training in progress, epoch 4

Browse files
checkpoint-920/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": "mrpc",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_equivalent",
14
+ "1": "equivalent"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "equivalent": 1,
20
+ "not_equivalent": 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-920/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d75d6b7ce01c35e752bd84140bf0058408943c1831262aa6fdda811b7d32f6
3
+ size 662962261
checkpoint-920/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95898edd2606d404f0d472a07d985c7ec1f6a45d9d6efa4f50dae5ce365dac21
3
+ size 331497705
checkpoint-920/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6427e4861c08f2c4abec26f3956844dc2cb3c7366695cd4d380e858709ca3a
3
+ size 14503
checkpoint-920/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fadee31c0eb4f0928fb98267943debe14aaca6d7c279adf97c5bce0375a4f71e
3
+ size 623
checkpoint-920/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-920/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-920/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-920/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 920,
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": 0.544,
14
+ "step": 230
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7328431372549019,
19
+ "eval_combined_score": 0.7813981676914135,
20
+ "eval_f1": 0.8299531981279251,
21
+ "eval_loss": 0.5272471308708191,
22
+ "eval_runtime": 2.9626,
23
+ "eval_samples_per_second": 137.716,
24
+ "eval_steps_per_second": 17.215,
25
+ "step": 230
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 1.2e-05,
30
+ "loss": 0.4034,
31
+ "step": 460
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.7254901960784313,
36
+ "eval_combined_score": 0.7776387150604923,
37
+ "eval_f1": 0.8297872340425533,
38
+ "eval_loss": 0.6210632920265198,
39
+ "eval_runtime": 2.9625,
40
+ "eval_samples_per_second": 137.721,
41
+ "eval_steps_per_second": 17.215,
42
+ "step": 460
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 8.000000000000001e-06,
47
+ "loss": 0.2602,
48
+ "step": 690
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.7230392156862745,
53
+ "eval_combined_score": 0.7768119616662257,
54
+ "eval_f1": 0.830584707646177,
55
+ "eval_loss": 0.9109526872634888,
56
+ "eval_runtime": 2.9562,
57
+ "eval_samples_per_second": 138.014,
58
+ "eval_steps_per_second": 17.252,
59
+ "step": 690
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 0.1688,
65
+ "step": 920
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.7696078431372549,
70
+ "eval_combined_score": 0.8092412206039973,
71
+ "eval_f1": 0.8488745980707396,
72
+ "eval_loss": 0.8639819622039795,
73
+ "eval_runtime": 2.9721,
74
+ "eval_samples_per_second": 137.276,
75
+ "eval_steps_per_second": 17.16,
76
+ "step": 920
77
+ }
78
+ ],
79
+ "max_steps": 1150,
80
+ "num_train_epochs": 5,
81
+ "total_flos": 2609254101909504.0,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
checkpoint-920/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f60be56a92d65e72efa4b0a6aeb22bf463a1b2d3bd996251ddb8045bd4fad5f
3
+ size 2799
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2f4d4d9490f4b55b3077ada545046c09522ef4ee6fbd7cdb12fea3f0f63c6d2
3
  size 331497705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95898edd2606d404f0d472a07d985c7ec1f6a45d9d6efa4f50dae5ce365dac21
3
  size 331497705
runs/Sep16_17-30-11_patrick-general-gpu/events.out.tfevents.1631813426.patrick-general-gpu.181934.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d2bfeddac12b1c77bd79c9e7676fb38be15a9687ff8606290ff2af5eeb92806
3
- size 4936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fa0ac8bb09b418e64cba0f839a790ebbd9777daff871e316b22dc017f00676
3
+ size 5520