Training in progress, step 200
Browse files- adapter_config.json +5 -4
- adapter_model.safetensors +2 -2
- config.json +1 -1
- tokenizer.json +18 -0
- tokenizer_config.json +16 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -15,7 +15,8 @@
|
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": [
|
18 |
-
"
|
|
|
19 |
"lm_head"
|
20 |
],
|
21 |
"peft_type": "LORA",
|
@@ -23,10 +24,10 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"dense_4h_to_h",
|
28 |
"dense_h_to_4h",
|
29 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": [
|
18 |
+
"embed_in",
|
19 |
+
"embed_out",
|
20 |
"lm_head"
|
21 |
],
|
22 |
"peft_type": "LORA",
|
|
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
27 |
+
"dense",
|
|
|
28 |
"dense_h_to_4h",
|
29 |
+
"query_key_value",
|
30 |
+
"dense_4h_to_h"
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
adapter_model.safetensors
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 sha256:9add6957d0638490738073dec6d51b0fc0f74d099bfc1fc6c65dc528d628492f
|
3 |
+
size 159266376
|
config.json
CHANGED
@@ -22,7 +22,7 @@
|
|
22 |
"rotary_emb_base": 10000,
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
-
"torch_dtype": "
|
26 |
"transformers_version": "4.41.2",
|
27 |
"use_cache": false,
|
28 |
"use_parallel_residual": true,
|
|
|
22 |
"rotary_emb_base": 10000,
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float16",
|
26 |
"transformers_version": "4.41.2",
|
27 |
"use_cache": false,
|
28 |
"use_parallel_residual": true,
|
tokenizer.json
CHANGED
@@ -236,6 +236,24 @@
|
|
236 |
"rstrip": false,
|
237 |
"normalized": false,
|
238 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
239 |
}
|
240 |
],
|
241 |
"normalizer": {
|
|
|
236 |
"rstrip": false,
|
237 |
"normalized": false,
|
238 |
"special": true
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"id": 50278,
|
242 |
+
"content": "[INST]",
|
243 |
+
"single_word": false,
|
244 |
+
"lstrip": false,
|
245 |
+
"rstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"special": false
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"id": 50279,
|
251 |
+
"content": "[/INST]",
|
252 |
+
"single_word": false,
|
253 |
+
"lstrip": false,
|
254 |
+
"rstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"special": false
|
257 |
}
|
258 |
],
|
259 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -210,6 +210,22 @@
|
|
210 |
"rstrip": false,
|
211 |
"single_word": false,
|
212 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
213 |
}
|
214 |
},
|
215 |
"bos_token": "<|endoftext|>",
|
|
|
210 |
"rstrip": false,
|
211 |
"single_word": false,
|
212 |
"special": true
|
213 |
+
},
|
214 |
+
"50278": {
|
215 |
+
"content": "[INST]",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"50279": {
|
223 |
+
"content": "[/INST]",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": false
|
229 |
}
|
230 |
},
|
231 |
"bos_token": "<|endoftext|>",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0169f40afff071e757b0e090b369d1620ba5cf0efeaea3a91b4e744854f175d1
|
3 |
size 6072
|