Training in progress, step 500
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +33 -0
- pytorch_model.bin +3 -0
- runs/Aug24_08-50-54_387e86878758/1661331081.949263/events.out.tfevents.1661331081.387e86878758.205.1 +3 -0
- runs/Aug24_08-50-54_387e86878758/events.out.tfevents.1661331081.387e86878758.205.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +11 -0
- training_args.bin +3 -0
.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 |
+
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-560m",
|
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 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_head": 16,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 24,
|
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": "4.21.1",
|
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:a95a5d6c125113535273c7c75b7f3b50237b7ee660a7dd8f8c541c9014750d02
|
3 |
+
size 2236955191
|
runs/Aug24_08-50-54_387e86878758/1661331081.949263/events.out.tfevents.1661331081.387e86878758.205.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a887a5baef3eb81dd6a6d45c713019f7f478908bf7bf2f3f51a99710ee7dffc
|
3 |
+
size 5464
|
runs/Aug24_08-50-54_387e86878758/events.out.tfevents.1661331081.387e86878758.205.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b05bc77cb66df32dd9d1dbeaf4a3a5a2de2185438bdc8f2f533e2dadd6b97b2e
|
3 |
+
size 5125
|
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:cc1131840e5b7be0eaf14a5f26e1b8e5564065dc56368c779fb9a0f1fdafabdd
|
3 |
+
size 14500596
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"name_or_path": "bigscience/bloom-560m",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"padding_side": "left",
|
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 sha256:70b23cfea5ce09f2e9200baea3cfb93b77b1522272543d1c1db2b41d75089c92
|
3 |
+
size 3439
|