Training in progress, step 100
Browse files
config.json
CHANGED
@@ -3,6 +3,7 @@
|
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
@@ -19,7 +20,7 @@
|
|
19 |
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "bfloat16",
|
22 |
-
"transformers_version": "4.
|
23 |
"use_cache": false,
|
24 |
"vocab_size": 32000
|
25 |
}
|
|
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
|
|
20 |
"sliding_window": 4096,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.37.2",
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32000
|
26 |
}
|
runs/Feb12_03-28-32_amaterasu/events.out.tfevents.1707709267.amaterasu.825352.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b2ab191451c18e868a4bc74a0430633f7a06392145c3744a6fbb13475135d61
|
3 |
+
size 7658
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9240c81ee7380aeb6e0fbc3a9722b83a9afe12b5228a5bc522342a9b93d7401
|
3 |
+
size 5880
|