gchhablani commited on
Commit
534a85a
1 Parent(s): 29f06d6

Training in progress, epoch 1

Browse files
checkpoint-360/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-360/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fbc0146bbbb3d9ac76a7df12498bb7f31a3fa37b0311aed81d72ff81682003
3
+ size 662956117
checkpoint-360/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9134d4468217d5caaa5242a6d33308f0bc4293df1161fa8d12ab51c3e4236973
3
+ size 331494633
checkpoint-360/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0311af968d54fce86db6b35ada8f69d5d2e9536c1f0ea21da1c148206211eb95
3
+ size 14503
checkpoint-360/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81034762933d2fc94a82edefefef5e312c2472682c4520f6e2d66896c744af3f
3
+ size 623
checkpoint-360/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-360/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-360/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-360/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 360,
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
+ "max_steps": 1080,
29
+ "num_train_epochs": 3,
30
+ "total_flos": 1022382944910336.0,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-360/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5c6eb180bb5162515a2b4e6e16c49ba285a05c5fb2d9ca9fa6f6e3fa827889
3
+ size 2799
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9134d4468217d5caaa5242a6d33308f0bc4293df1161fa8d12ab51c3e4236973
3
+ size 331494633
runs/Sep19_15-39-26_patrick-general-gpu/1632065982.6694088/events.out.tfevents.1632065982.patrick-general-gpu.509410.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10ceee3ed6de4a7b631d277efcdb1f9aad5bfe722eb13ae167a9e2a52c66edf
3
+ size 4351
runs/Sep19_15-39-26_patrick-general-gpu/events.out.tfevents.1632065982.patrick-general-gpu.509410.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc5147a83707a5de1370f103987de5aa22cb7e19997e52eb0c16f25b5b7a698
3
+ size 3716
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}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
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"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5c6eb180bb5162515a2b4e6e16c49ba285a05c5fb2d9ca9fa6f6e3fa827889
3
+ size 2799