Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +37 -0
- gaudi_config.json +31 -0
- pytorch_model.bin +3 -0
- runs/Oct15_11-05-59_ip-172-31-90-245/1665831971.283621/events.out.tfevents.1665831971.ip-172-31-90-245.5761.1 +3 -0
- runs/Oct15_11-05-59_ip-172-31-90-245/events.out.tfevents.1665831971.ip-172-31-90-245.5761.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"finetuning_task": "xnli",
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0,
|
20 |
+
"LABEL_1": 1,
|
21 |
+
"LABEL_2": 2
|
22 |
+
},
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "distilbert",
|
25 |
+
"n_heads": 12,
|
26 |
+
"n_layers": 6,
|
27 |
+
"output_past": true,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"qa_dropout": 0.1,
|
31 |
+
"seq_classif_dropout": 0.2,
|
32 |
+
"sinusoidal_pos_embds": false,
|
33 |
+
"tie_weights_": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.23.1",
|
36 |
+
"vocab_size": 119547
|
37 |
+
}
|
gaudi_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"hmp_bf16_ops": [
|
3 |
+
"add",
|
4 |
+
"addmm",
|
5 |
+
"bmm",
|
6 |
+
"div",
|
7 |
+
"dropout",
|
8 |
+
"gelu",
|
9 |
+
"iadd",
|
10 |
+
"linear",
|
11 |
+
"layer_norm",
|
12 |
+
"matmul",
|
13 |
+
"mm",
|
14 |
+
"rsub",
|
15 |
+
"softmax",
|
16 |
+
"truediv"
|
17 |
+
],
|
18 |
+
"hmp_fp32_ops": [
|
19 |
+
"cross_entropy",
|
20 |
+
"embedding",
|
21 |
+
"nll_loss",
|
22 |
+
"log_softmax"
|
23 |
+
],
|
24 |
+
"hmp_is_verbose": false,
|
25 |
+
"hmp_opt_level": "O1",
|
26 |
+
"optimum_version": "1.4.0",
|
27 |
+
"transformers_version": "4.23.1",
|
28 |
+
"use_fused_adam": true,
|
29 |
+
"use_fused_clip_norm": true,
|
30 |
+
"use_habana_mixed_precision": true
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1821c4546782ad70290d68e7f729badad689e7f96865de2874ba01ad4a88e025
|
3 |
+
size 541340785
|
runs/Oct15_11-05-59_ip-172-31-90-245/1665831971.283621/events.out.tfevents.1665831971.ip-172-31-90-245.5761.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55545ea8cb97c192c2631b7c3a7d7a3b8e5b8a958269257766c8d97a470f6940
|
3 |
+
size 5715
|
runs/Oct15_11-05-59_ip-172-31-90-245/events.out.tfevents.1665831971.ip-172-31-90-245.5761.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb2e59da35204a31935c19e03b329db481d1849a8ff3f9f5c2cab593142d553
|
3 |
+
size 8330
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "distilbert-base-multilingual-cased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01265cbe97b9cd8ed288f0a28725145bc96e06bb4cf10b63f9160c5065df8dea
|
3 |
+
size 3567
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|