Training in progress, step 100
Browse files- config.json +2 -1
- tokenizer.json +1 -0
- tokenizer_config.json +2 -0
- training_args.bin +2 -2
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": "4.41.1",
|
| 24 |
"use_cache": false,
|
| 25 |
"vocab_size": 32000
|
| 26 |
}
|
tokenizer.json
CHANGED
|
@@ -134,6 +134,7 @@
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
|
|
|
| 137 |
"vocab": {
|
| 138 |
"<unk>": 0,
|
| 139 |
"<s>": 1,
|
|
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
| 137 |
+
"ignore_merges": false,
|
| 138 |
"vocab": {
|
| 139 |
"<unk>": 0,
|
| 140 |
"<s>": 1,
|
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 sha256:9d82fb75ea1dbe9f0635fa43a9bb3ebb23deea5beb1189c22b55411c77abbf30
|
| 3 |
+
size 6456
|