Training in progress, step 500
Browse files- checkpoint-500/config.json +26 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +1 -0
- checkpoint-500/tokenizer.json +0 -0
- checkpoint-500/tokenizer_config.json +1 -0
- checkpoint-500/trainer_state.json +22 -0
- checkpoint-500/training_args.bin +3 -0
- checkpoint-500/vocab.txt +0 -0
- config.json +26 -0
- pytorch_model.bin +3 -0
- runs/Jan15_03-33-23_17a47eed43af/1642217637.9498563/events.out.tfevents.1642217637.17a47eed43af.73.1 +3 -0
- runs/Jan15_03-33-23_17a47eed43af/events.out.tfevents.1642217637.17a47eed43af.73.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/xtremedistil-l6-h256-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
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": "bert",
|
17 |
+
"num_attention_heads": 8,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.15.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16190c90f5561dcb301e24b0364115efae58b467d86833fc177daea19122f3b0
|
3 |
+
size 101537765
|
checkpoint-500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6c013aa93e3e1db2efdfeb70212ccd7e8a4d929efb6b2de7a3e0cad26e8e3c0
|
3 |
+
size 50783921
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92685445951bf2e9bb4c82f40105a8191ac600e334aa245b3ddeff1b58e1a9bf
|
3 |
+
size 14503
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a0c4d975e148968fef48533924cd98b3ae5b5c00898586f632bc1a06b04521b
|
3 |
+
size 623
|
checkpoint-500/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-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
checkpoint-500/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, "special_tokens_map_file": null, "name_or_path": "microsoft/xtremedistil-l6-h256-uncased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.47619047619047616,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.48,
|
12 |
+
"learning_rate": 1.6825396825396828e-05,
|
13 |
+
"loss": 4.4123,
|
14 |
+
"step": 500
|
15 |
+
}
|
16 |
+
],
|
17 |
+
"max_steps": 3150,
|
18 |
+
"num_train_epochs": 3,
|
19 |
+
"total_flos": 87360049152000.0,
|
20 |
+
"trial_name": null,
|
21 |
+
"trial_params": null
|
22 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6d45901e9e8d53e63a4135ac255eb371b653d1fe237647a5f474e58931a0ea5
|
3 |
+
size 3183
|
checkpoint-500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/xtremedistil-l6-h256-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
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": "bert",
|
17 |
+
"num_attention_heads": 8,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.15.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6c013aa93e3e1db2efdfeb70212ccd7e8a4d929efb6b2de7a3e0cad26e8e3c0
|
3 |
+
size 50783921
|
runs/Jan15_03-33-23_17a47eed43af/1642217637.9498563/events.out.tfevents.1642217637.17a47eed43af.73.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8288630db3e9b8ca2a541766a23a9102998906ef8e424651da9e82b6290aad0e
|
3 |
+
size 4936
|
runs/Jan15_03-33-23_17a47eed43af/events.out.tfevents.1642217637.17a47eed43af.73.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dde92181615cf5a2e9319aaf4ad719a33306f26a9706fc7a0532394cd0a1acb
|
3 |
+
size 3653
|
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, "special_tokens_map_file": null, "name_or_path": "microsoft/xtremedistil-l6-h256-uncased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6d45901e9e8d53e63a4135ac255eb371b653d1fe237647a5f474e58931a0ea5
|
3 |
+
size 3183
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|