Training in progress, step 500
Browse files- last-checkpoint/config.json +0 -26
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/special_tokens_map.json +0 -1
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -1
- last-checkpoint/trainer_state.json +0 -42
- last-checkpoint/vocab.txt +0 -0
- pytorch_model.bin +1 -1
- last-checkpoint/scheduler.pt → runs/Jan15_03-42-30_17a47eed43af/1642218184.8190882/events.out.tfevents.1642218184.17a47eed43af.73.5 +2 -2
- last-checkpoint/training_args.bin → runs/Jan15_03-42-30_17a47eed43af/events.out.tfevents.1642218184.17a47eed43af.73.4 +2 -2
- training_args.bin +1 -1
last-checkpoint/config.json
DELETED
@@ -1,26 +0,0 @@
|
|
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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:a10cb34cf7dbb7af44bdb9cb96dfdb3259896556bb26f9f7efab451322dc92c7
|
3 |
-
size 101537765
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:19d1674f8348f66f7b609132b675da3830f352bd6006b5476a8eddd63b9f5969
|
3 |
-
size 50783921
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:161a19621de4200192d7bfc0821c090063f1431ba8769f731b08d1a533e974c1
|
3 |
-
size 14503
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
|
last-checkpoint/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
last-checkpoint/tokenizer_config.json
DELETED
@@ -1 +0,0 @@
|
|
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"}
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,42 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.4285714285714286,
|
5 |
-
"global_step": 1500,
|
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": 4.4387,
|
14 |
-
"step": 500
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.95,
|
18 |
-
"learning_rate": 1.3650793650793652e-05,
|
19 |
-
"loss": 3.5954,
|
20 |
-
"step": 1000
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 1.0,
|
24 |
-
"eval_loss": 3.0800042152404785,
|
25 |
-
"eval_runtime": 6.2492,
|
26 |
-
"eval_samples_per_second": 327.561,
|
27 |
-
"eval_steps_per_second": 20.483,
|
28 |
-
"step": 1050
|
29 |
-
},
|
30 |
-
{
|
31 |
-
"epoch": 1.43,
|
32 |
-
"learning_rate": 1.0476190476190477e-05,
|
33 |
-
"loss": 3.224,
|
34 |
-
"step": 1500
|
35 |
-
}
|
36 |
-
],
|
37 |
-
"max_steps": 3150,
|
38 |
-
"num_train_epochs": 3,
|
39 |
-
"total_flos": 261981867400704.0,
|
40 |
-
"trial_name": null,
|
41 |
-
"trial_params": null
|
42 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/vocab.txt
DELETED
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 50783921
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5ef80522c882cd946ff55e32cdf88d79d1ce96d86a32409a07e98b1073068a9
|
3 |
size 50783921
|
last-checkpoint/scheduler.pt → runs/Jan15_03-42-30_17a47eed43af/1642218184.8190882/events.out.tfevents.1642218184.17a47eed43af.73.5
RENAMED
@@ -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 sha256:99e7fbe74293f6d8c986c35706a356d92204ff7a8f786ec706dbfce51ec257c1
|
3 |
+
size 4931
|
last-checkpoint/training_args.bin → runs/Jan15_03-42-30_17a47eed43af/events.out.tfevents.1642218184.17a47eed43af.73.4
RENAMED
@@ -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:e5b60865fa53728c9ad4327cfad682e961ca815eee704811cc204b619b1d9832
|
3 |
+
size 3648
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3183
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08e0c898a8b74a0dd26f8ce2ea38dae929a487f3583ae15ea4540c4b05fda3b5
|
3 |
size 3183
|