nbroad HF staff commited on
Commit
bb75bcb
1 Parent(s): a51a25f

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.21.1",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
eval_nbest_predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959618658cc6a852c6fdb0124852bd5cfa0df0a72f89b93fd0bd7862bad52b3c
3
+ size 102676894
eval_null_odds.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
gaudi_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hmp_bf16_ops": [
3
+ "add",
4
+ "addmm",
5
+ "bmm",
6
+ "conv1d",
7
+ "div",
8
+ "dropout",
9
+ "gelu",
10
+ "iadd",
11
+ "linear",
12
+ "layer_norm",
13
+ "matmul",
14
+ "mm",
15
+ "rsub",
16
+ "softmax",
17
+ "truediv"
18
+ ],
19
+ "hmp_fp32_ops": [
20
+ "embedding",
21
+ "nll_loss",
22
+ "log_softmax"
23
+ ],
24
+ "hmp_is_verbose": false,
25
+ "hmp_opt_level": "O1",
26
+ "optimum_version": "1.3.0",
27
+ "transformers_version": "4.21.1",
28
+ "use_fused_adam": true,
29
+ "use_fused_clip_norm": true,
30
+ "use_habana_mixed_precision": true
31
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1acbc182b226bf55337ae5823bb727375a9d234a3c053414e0dbf7dc86448307
3
+ size 496294641
runs/Aug17_04-01-53_ip-172-31-85-26/1660708942.075391/events.out.tfevents.1660708942.ip-172-31-85-26.17194.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ba4439942c3f9d4b3236adc5d9e677f69d6ffe5b9f623445d5342d32f30d476
3
+ size 5652
runs/Aug17_04-01-53_ip-172-31-85-26/events.out.tfevents.1660708942.ip-172-31-85-26.17194.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd78cc4b7307b639865a903be333a7e1d44a0308187d9dd3479675f8b0881291
3
+ size 6422
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64fd49aeb41377c44c90115ce08ffeae031ffaa1486ada6974a784d8f6c331b8
3
+ size 3439
vocab.json ADDED
The diff for this file is too large to render. See raw diff