Training in progress, step 2000
Browse files- checkpoint-2000/config.json +30 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/pytorch_model.bin +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +1 -0
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer_config.json +1 -0
- checkpoint-2000/trainer_state.json +56 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2000/vocab.txt +0 -0
- pytorch_model.bin +1 -1
- runs/Jan15_05-37-52_b97e1d8ba7c6/events.out.tfevents.1642225094.b97e1d8ba7c6.72.0 +2 -2
checkpoint-2000/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-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:210feb794d6c32596b7d4c58bf562414b9c350744da7a591b465da4c96a37585
|
3 |
+
size 109498141
|
checkpoint-2000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fb417fa220b162eb67dfc71854c62998ec52642664d5ab725a9d3a6f163073f
|
3 |
+
size 54776045
|
checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f5c13898f322b872f7eff156b8263ba00612ba532ab0f3a934aa6aab3941c9d
|
3 |
+
size 14503
|
checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd26edfc0dc425d9d08064e32a4295f509680936eeed61163af09e34bc5a5a2a
|
3 |
+
size 623
|
checkpoint-2000/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-2000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
checkpoint-2000/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-2000/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.770083102493075,
|
5 |
+
"global_step": 2000,
|
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 |
+
"max_steps": 4332,
|
52 |
+
"num_train_epochs": 6,
|
53 |
+
"total_flos": 700826230766592.0,
|
54 |
+
"trial_name": null,
|
55 |
+
"trial_params": null
|
56 |
+
}
|
checkpoint-2000/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-2000/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:
|
3 |
size 54776045
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fb417fa220b162eb67dfc71854c62998ec52642664d5ab725a9d3a6f163073f
|
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:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24ee5c122ceaf45edaf328b66161c57fc9f38878e7ff50a51af97a7f0798e10c
|
3 |
+
size 4847
|