evs commited on
Commit
1afc946
1 Parent(s): 56aa4dc

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloom-560m",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_softmax_in_fp32": true,
9
+ "bias_dropout_fusion": true,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "False",
16
+ "1": "True"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "False": 0,
21
+ "True": 1
22
+ },
23
+ "layer_norm_epsilon": 1e-05,
24
+ "masked_softmax_fusion": true,
25
+ "model_type": "bloom",
26
+ "n_head": 16,
27
+ "n_inner": null,
28
+ "n_layer": 24,
29
+ "offset_alibi": 100,
30
+ "pad_token_id": 3,
31
+ "pretraining_tp": 1,
32
+ "problem_type": "single_label_classification",
33
+ "skip_bias_add": true,
34
+ "skip_bias_add_qkv": false,
35
+ "slow_but_exact": false,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.30.2",
38
+ "unk_token_id": 0,
39
+ "use_cache": true,
40
+ "vocab_size": 250880
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b117efbf13aa0869e3ed21bb29f2e1c073aa697bfbbed381d39ab8b973d9023a
3
+ size 2236965925
runs/Jul06_12-27-31_d90500fb26aa/events.out.tfevents.1688646456.d90500fb26aa.2454.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b9e2d2387b0bfd36f254b3a253b6ff01ed907a8a54260a6412d840b5280eaa
3
+ size 4233
runs/Jul06_12-35-54_d90500fb26aa/events.out.tfevents.1688646958.d90500fb26aa.2454.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c7de50e3f004e01e2a46a0937ea0bc1042e3fe04aeec1bc3eb544928db7e0c
3
+ size 4233
runs/Jul06_12-45-44_d90500fb26aa/events.out.tfevents.1688647547.d90500fb26aa.2454.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736691ddda8130e77f9c305f5e189f11b8ac218ba44b148d9d9ec1c96e1ff082
3
+ size 4556
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
3
+ size 14500471
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "padding_side": "left",
9
+ "tokenizer_class": "BloomTokenizer",
10
+ "unk_token": "<unk>"
11
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8050b1a7b5b6dd08fe99edaca052fb960fc8f24eab403b633678ad1d357ce4cf
3
+ size 3963