End of training
Browse files- .gitignore +1 -0
- config.json +33 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- runs/Jun03_06-17-28_2eb1349808b8/1685773058.9298337/events.out.tfevents.1685773058.2eb1349808b8.296.1 +3 -0
- runs/Jun03_06-17-28_2eb1349808b8/events.out.tfevents.1685773058.2eb1349808b8.296.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigscience/bloomz-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": "4.30.0.dev0",
|
30 |
+
"unk_token_id": 0,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 250880
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.30.0.dev0"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd93f77344d1f38235c2bebd60c47fedca1aa0c7d881250386b694a4cd4bfd65
|
3 |
+
size 2236957537
|
runs/Jun03_06-17-28_2eb1349808b8/1685773058.9298337/events.out.tfevents.1685773058.2eb1349808b8.296.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e202f327f3fcbaadd29ecdcadc7a2bdebe21ad28710b0cc75590aafd64fc802
|
3 |
+
size 5895
|
runs/Jun03_06-17-28_2eb1349808b8/events.out.tfevents.1685773058.2eb1349808b8.296.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7adee9131040c2e33f8d02d773418728c42fd874fac8093fe7815ad266045018
|
3 |
+
size 9172
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9be7a03c3fcad60ed6f4515c994d6e6945182554ab6fd11215d6160b261552f2
|
3 |
+
size 3899
|