Ubuntu commited on
Commit
573ea54
1 Parent(s): b7ce5e0

initial commit

Browse files
all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.4410819411277771,
4
+ "eval_matthews_correlation": 0.6730906275905355,
5
+ "eval_mem_cpu_alloc_delta": 4009984,
6
+ "eval_mem_cpu_peaked_delta": 0,
7
+ "eval_mem_gpu_alloc_delta": 0,
8
+ "eval_mem_gpu_peaked_delta": 34656256,
9
+ "eval_runtime": 7.315,
10
+ "eval_samples": 1043,
11
+ "eval_samples_per_second": 142.583,
12
+ "init_mem_cpu_alloc_delta": 3198349312,
13
+ "init_mem_cpu_peaked_delta": 319799296,
14
+ "init_mem_gpu_alloc_delta": 439072256,
15
+ "init_mem_gpu_peaked_delta": 0,
16
+ "train_mem_cpu_alloc_delta": 91254784,
17
+ "train_mem_cpu_peaked_delta": 187301888,
18
+ "train_mem_gpu_alloc_delta": 1379092992,
19
+ "train_mem_gpu_peaked_delta": 3560779776,
20
+ "train_runtime": 678.8041,
21
+ "train_samples": 8551,
22
+ "train_samples_per_second": 1.184
23
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/electra-base-discriminator",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "embedding_size": 768,
8
+ "finetuning_task": "cola",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "electra",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "summary_activation": "gelu",
22
+ "summary_last_dropout": 0.1,
23
+ "summary_type": "first",
24
+ "summary_use_proj": true,
25
+ "transformers_version": "4.6.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 30522
28
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.4410819411277771,
4
+ "eval_matthews_correlation": 0.6730906275905355,
5
+ "eval_mem_cpu_alloc_delta": 4009984,
6
+ "eval_mem_cpu_peaked_delta": 0,
7
+ "eval_mem_gpu_alloc_delta": 0,
8
+ "eval_mem_gpu_peaked_delta": 34656256,
9
+ "eval_runtime": 7.315,
10
+ "eval_samples": 1043,
11
+ "eval_samples_per_second": 142.583
12
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8cae3fe1aae208f8e44914e985eb046c29ac3c896ea722d72a663af50bd4ee
3
+ size 438023702
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-base-discriminator"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 3198349312,
4
+ "init_mem_cpu_peaked_delta": 319799296,
5
+ "init_mem_gpu_alloc_delta": 439072256,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 91254784,
8
+ "train_mem_cpu_peaked_delta": 187301888,
9
+ "train_mem_gpu_alloc_delta": 1379092992,
10
+ "train_mem_gpu_peaked_delta": 3560779776,
11
+ "train_runtime": 678.8041,
12
+ "train_samples": 8551,
13
+ "train_samples_per_second": 1.184
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 804,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.87,
12
+ "learning_rate": 7.5621890547263685e-06,
13
+ "loss": 0.3292,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 3.0,
18
+ "step": 804,
19
+ "total_flos": 2156995090202112.0,
20
+ "train_runtime": 678.8041,
21
+ "train_samples_per_second": 1.184
22
+ }
23
+ ],
24
+ "max_steps": 804,
25
+ "num_train_epochs": 3,
26
+ "total_flos": 2156995090202112.0,
27
+ "trial_name": null,
28
+ "trial_params": null
29
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e0eb9739087c11fc130fd51c84c146f2547c946e2802a77036531ebfbfd50b7
3
+ size 2415
vocab.txt ADDED
The diff for this file is too large to render. See raw diff