Training in progress, epoch 1
Browse files- config.json +1 -1
- model.safetensors +1 -1
- runs/Apr29_11-02-17_ce670796da63/events.out.tfevents.1714388538.ce670796da63.3096.0 +3 -0
- tokenizer.json +25 -4
- tokenizer_config.json +2 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -30,7 +30,7 @@
|
|
30 |
"rotary_pct": 0.25,
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "float32",
|
33 |
-
"transformers_version": "4.
|
34 |
"use_cache": true,
|
35 |
"use_parallel_residual": true,
|
36 |
"vocab_size": 50304
|
|
|
30 |
"rotary_pct": 0.25,
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.40.1",
|
34 |
"use_cache": true,
|
35 |
"use_parallel_residual": true,
|
36 |
"vocab_size": 50304
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 494780976
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e733f05f8b5c80e80d6ee5ad0db0d4a839a7c8c5d5c00145079ac99ba7533713
|
3 |
size 494780976
|
runs/Apr29_11-02-17_ce670796da63/events.out.tfevents.1714388538.ce670796da63.3096.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:180cca7d91896ce328c8c30adad335ed41e52bf0cab8920def92030bfbbfcb4e
|
3 |
+
size 6097
|
tokenizer.json
CHANGED
@@ -248,10 +248,30 @@
|
|
248 |
"use_regex": true
|
249 |
},
|
250 |
"post_processor": {
|
251 |
-
"type": "
|
252 |
-
"
|
253 |
-
|
254 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
255 |
},
|
256 |
"decoder": {
|
257 |
"type": "ByteLevel",
|
@@ -267,6 +287,7 @@
|
|
267 |
"end_of_word_suffix": null,
|
268 |
"fuse_unk": false,
|
269 |
"byte_fallback": false,
|
|
|
270 |
"vocab": {
|
271 |
"<|endoftext|>": 0,
|
272 |
"<|padding|>": 1,
|
|
|
248 |
"use_regex": true
|
249 |
},
|
250 |
"post_processor": {
|
251 |
+
"type": "TemplateProcessing",
|
252 |
+
"single": [
|
253 |
+
{
|
254 |
+
"Sequence": {
|
255 |
+
"id": "A",
|
256 |
+
"type_id": 0
|
257 |
+
}
|
258 |
+
}
|
259 |
+
],
|
260 |
+
"pair": [
|
261 |
+
{
|
262 |
+
"Sequence": {
|
263 |
+
"id": "A",
|
264 |
+
"type_id": 0
|
265 |
+
}
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"Sequence": {
|
269 |
+
"id": "B",
|
270 |
+
"type_id": 1
|
271 |
+
}
|
272 |
+
}
|
273 |
+
],
|
274 |
+
"special_tokens": {}
|
275 |
},
|
276 |
"decoder": {
|
277 |
"type": "ByteLevel",
|
|
|
287 |
"end_of_word_suffix": null,
|
288 |
"fuse_unk": false,
|
289 |
"byte_fallback": false,
|
290 |
+
"ignore_merges": false,
|
291 |
"vocab": {
|
292 |
"<|endoftext|>": 0,
|
293 |
"<|padding|>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
"add_prefix_space": false,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
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 sha256:29d36ba4aa4a1d289b4c0ae4d88f448204aacc1b1e867d1dbc75c34de3e9d2b9
|
3 |
+
size 5048
|