End of training
Browse files- .gitignore +1 -0
- config.json +32 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- runs/May29_19-29-20_ab90e9b58720/1685388565.3926353/events.out.tfevents.1685388565.ab90e9b58720.32.1 +3 -0
- runs/May29_19-29-20_ab90e9b58720/1685390657.6171994/events.out.tfevents.1685390657.ab90e9b58720.32.3 +3 -0
- runs/May29_19-29-20_ab90e9b58720/events.out.tfevents.1685388565.ab90e9b58720.32.0 +3 -0
- runs/May29_19-29-20_ab90e9b58720/events.out.tfevents.1685390657.ab90e9b58720.32.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sai1881/bloom-560m-pre-train-v2",
|
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 |
+
"skip_bias_add": true,
|
25 |
+
"skip_bias_add_qkv": false,
|
26 |
+
"slow_but_exact": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.28.1",
|
29 |
+
"unk_token_id": 0,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250880
|
32 |
+
}
|
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": "4.28.1"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71da8d4d95ca4ad43b79713f7ba9c3820b25a731f32e586734033104b5f548c9
|
3 |
+
size 2236957537
|
runs/May29_19-29-20_ab90e9b58720/1685388565.3926353/events.out.tfevents.1685388565.ab90e9b58720.32.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a893d3e9abe9eaa0255071bdf6ca631174fe66cd48729c021eb273a7c6024ff
|
3 |
+
size 5873
|
runs/May29_19-29-20_ab90e9b58720/1685390657.6171994/events.out.tfevents.1685390657.ab90e9b58720.32.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3902e2510ab3bc491e5c3fe80bb6b51e2fd910b150413190d4046b2b01690910
|
3 |
+
size 5873
|
runs/May29_19-29-20_ab90e9b58720/events.out.tfevents.1685388565.ab90e9b58720.32.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea15e348178203ce4fb1d3d70d5e66d09b495443a36af670b5b87178df62bef2
|
3 |
+
size 6417
|
runs/May29_19-29-20_ab90e9b58720/events.out.tfevents.1685390657.ab90e9b58720.32.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:879a5288e50d1746bf09025255b8126049c41ccc96d6a97b0fae510d0b270e96
|
3 |
+
size 4151
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e9533da53abc245ecf094d9b65ac8d43018ccf7c4e7dd12b0c7cafeb457a0e8
|
3 |
+
size 3643
|