husnu commited on
Commit
167b8c8
1 Parent(s): 70a11b7

Training in progress, step 3500

Browse files
checkpoint-3500/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "loodos/electra-small-turkish-uncased-discriminator",
3
+ "architectures": [
4
+ "ElectraForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 128,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 256,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1024,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "electra",
17
+ "num_attention_heads": 4,
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
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.15.0",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8d08aca78f489e163c93e5054239f62f1f094f684c8170a4411ee6ecbb6110
3
+ size 109498141
checkpoint-3500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42bc267ec3f47ed324eaea3e80c3555a90a16167ee72507bc0e7b1fa0ce69f09
3
+ size 54776045
checkpoint-3500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0ef0e7a1ec7304bab999a64193c6d2d776eb7af9363b6eedd08102f17139f1
3
+ size 14503
checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcba4a84c340116e7a0518ad0be03f63e6abff14ff54ab92d49f35749e23a5be
3
+ size 623
checkpoint-3500/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-3500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-3500/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": "/root/.cache/huggingface/transformers/444866c6552ed3ad4574d4ea6433149e5e30eef747074cfa66be2388dadf2646.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "loodos/electra-small-turkish-uncased-discriminator", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
checkpoint-3500/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.847645429362881,
5
+ "global_step": 3500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.69,
12
+ "learning_rate": 1.7691597414589106e-05,
13
+ "loss": 4.128,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 2.7186717987060547,
19
+ "eval_runtime": 6.8658,
20
+ "eval_samples_per_second": 210.754,
21
+ "eval_steps_per_second": 13.254,
22
+ "step": 722
23
+ },
24
+ {
25
+ "epoch": 1.39,
26
+ "learning_rate": 1.538319482917821e-05,
27
+ "loss": 3.0376,
28
+ "step": 1000
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 2.448554039001465,
33
+ "eval_runtime": 6.9162,
34
+ "eval_samples_per_second": 209.22,
35
+ "eval_steps_per_second": 13.158,
36
+ "step": 1444
37
+ },
38
+ {
39
+ "epoch": 2.08,
40
+ "learning_rate": 1.3074792243767314e-05,
41
+ "loss": 2.7618,
42
+ "step": 1500
43
+ },
44
+ {
45
+ "epoch": 2.77,
46
+ "learning_rate": 1.0766389658356418e-05,
47
+ "loss": 2.5304,
48
+ "step": 2000
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 2.348456859588623,
53
+ "eval_runtime": 7.0052,
54
+ "eval_samples_per_second": 206.561,
55
+ "eval_steps_per_second": 12.99,
56
+ "step": 2166
57
+ },
58
+ {
59
+ "epoch": 3.46,
60
+ "learning_rate": 8.457987072945522e-06,
61
+ "loss": 2.4214,
62
+ "step": 2500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_loss": 2.0450046062469482,
67
+ "eval_runtime": 6.9443,
68
+ "eval_samples_per_second": 208.371,
69
+ "eval_steps_per_second": 13.104,
70
+ "step": 2888
71
+ },
72
+ {
73
+ "epoch": 4.16,
74
+ "learning_rate": 6.1495844875346266e-06,
75
+ "loss": 2.2208,
76
+ "step": 3000
77
+ },
78
+ {
79
+ "epoch": 4.85,
80
+ "learning_rate": 3.841181902123731e-06,
81
+ "loss": 2.1568,
82
+ "step": 3500
83
+ }
84
+ ],
85
+ "max_steps": 4332,
86
+ "num_train_epochs": 6,
87
+ "total_flos": 1226347294685184.0,
88
+ "trial_name": null,
89
+ "trial_params": null
90
+ }
checkpoint-3500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f59f77975d8e31159a76d6f258f7fb03c99048c15d507345621a56c397d0996
3
+ size 3247
checkpoint-3500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a0af67201568179f1a046bb2b7363fe446662f1fceeea5849921001b6523d54
3
  size 54776045
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42bc267ec3f47ed324eaea3e80c3555a90a16167ee72507bc0e7b1fa0ce69f09
3
  size 54776045
runs/Jan15_05-37-52_b97e1d8ba7c6/events.out.tfevents.1642225094.b97e1d8ba7c6.72.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51e3ce9197a7573e2372e0ad0e2f8fb97714040b309fbc09d1c014b9bee6ef4a
3
- size 5703
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:073d0adc83c0253d5eb894bc7d8632fe2966f8fbe9984c15841a1ff14d7af1d6
3
+ size 5860