gchhablani commited on
Commit
4fc67ff
1 Parent(s): 103f55d

Training in progress, epoch 2

Browse files
checkpoint-45482/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": "qqp",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_duplicate",
14
+ "1": "duplicate"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "duplicate": 1,
20
+ "not_duplicate": 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-45482/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94901a940a52e57c599744674a4f66913af5f55e14a136923be75a160d26a304
3
+ size 662962261
checkpoint-45482/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772aa83e32ece12ce99581dfb8618e346ef27f0149cd377ab8136a328fb150fe
3
+ size 331497705
checkpoint-45482/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659ee3bb367b26afc9801556c00d53eb704a8a08cd524ae1993dd2a8bd78cb9d
3
+ size 14503
checkpoint-45482/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c119b06abaf66001cb16666fd1dc0c14f3702ac3158ea7bc99a4147e71286bda
3
+ size 623
checkpoint-45482/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-45482/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-45482/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-45482/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 45482,
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": 0.3484,
14
+ "step": 22741
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.867647786297304,
19
+ "eval_combined_score": 0.8486629929990515,
20
+ "eval_f1": 0.829678199700799,
21
+ "eval_loss": 0.3014103174209595,
22
+ "eval_runtime": 292.1565,
23
+ "eval_samples_per_second": 138.385,
24
+ "eval_steps_per_second": 17.299,
25
+ "step": 22741
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 0.2387,
31
+ "step": 45482
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.8800890427900074,
36
+ "eval_combined_score": 0.8615115077230022,
37
+ "eval_f1": 0.8429339726559969,
38
+ "eval_loss": 0.3011280596256256,
39
+ "eval_runtime": 292.4225,
40
+ "eval_samples_per_second": 138.259,
41
+ "eval_steps_per_second": 17.283,
42
+ "step": 45482
43
+ }
44
+ ],
45
+ "max_steps": 68223,
46
+ "num_train_epochs": 3,
47
+ "total_flos": 1.2941203216512614e+17,
48
+ "trial_name": null,
49
+ "trial_params": null
50
+ }
checkpoint-45482/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:676cd7dcad22f50371f3ace17b3013f3804e66830b0547378e7d1796db818952
3
+ size 2735
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f359ad91790330d688eb45ebaef7b9a0e2286a724688bb4964862abb3332768
3
  size 331497705
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772aa83e32ece12ce99581dfb8618e346ef27f0149cd377ab8136a328fb150fe
3
  size 331497705
runs/Sep18_18-21-44_patrick-general-gpu/events.out.tfevents.1631989416.patrick-general-gpu.389664.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:064300b4b997662a182f39c86ae2185f86b3e69f64d8026159819ee6f0b8c485
3
- size 3771
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b020aaa776642203335bcc9518fc4d604dee73e7b35c5547c3cac84156c59f
3
+ size 4366