wvangils commited on
Commit
b498d05
1 Parent(s): 7e6b422

Training in progress, step 500

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloom-350m",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForCausalLM"
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
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "masked_softmax_fusion": true,
16
+ "model_type": "bloom",
17
+ "n_embed": 1024,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "num_attention_heads": 16,
21
+ "offset_alibi": 100,
22
+ "pad_token_id": 3,
23
+ "pretraining_tp": 1,
24
+ "seq_length": 2048,
25
+ "skip_bias_add": true,
26
+ "skip_bias_add_qkv": false,
27
+ "slow_but_exact": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.20.1",
30
+ "unk_token_id": 0,
31
+ "use_cache": true,
32
+ "vocab_size": 250880
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b28923af190cf2d048712c223d519ec7275d7daee781586760260a3f812fef
3
+ size 2236955191
runs/Jul05_07-14-05_65f7dc285c3c/1657005376.4644568/events.out.tfevents.1657005376.65f7dc285c3c.72.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bee6ce2a1a36b8c2cc7c078b063a714e6f7da539816665af9dd7b8ea9f8eabe
3
+ size 5388
runs/Jul05_07-14-05_65f7dc285c3c/events.out.tfevents.1657005376.65f7dc285c3c.72.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f084f3b5a526420ccb9adbef6bcb391ef9ba9bc6d02ae41e26d00bfb749bc448
3
+ size 3928
runs/Jul05_07-20-11_65f7dc285c3c/1657005626.3306565/events.out.tfevents.1657005626.65f7dc285c3c.311.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739ffc66122866974c09458c49796665eeae32d6b1480d6b424ffc517ccfe6b3
3
+ size 5388
runs/Jul05_07-20-11_65f7dc285c3c/events.out.tfevents.1657005626.65f7dc285c3c.311.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb1c30375d3df7a1423b6805c0fe1f8f5b51d87927bb0b4e99e2391b5271842
3
+ size 5055
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58217c1808e7a50e97d2b7d93c0143a74bd16f27dc3ed8a713014019f4394dc5
3
+ size 14500696
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "bigscience/bloom-350m",
7
+ "pad_token": "<pad>",
8
+ "special_tokens_map_file": null,
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 sha256:49919343999277f2b2085ffded1ba971ca10f85a20d9df0813c33cb669a56f4d
3
+ size 3375