Training in progress, step 31
Browse files- adapter_config.json +5 -8
- adapter_model.safetensors +2 -2
- config.json +1 -1
- tokenizer_config.json +0 -16
- training_args.bin +2 -2
adapter_config.json
CHANGED
@@ -13,22 +13,19 @@
|
|
13 |
"lora_dropout": 0.1,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
-
"modules_to_save":
|
17 |
-
"embed_tokens",
|
18 |
-
"lm_head"
|
19 |
-
],
|
20 |
"peft_type": "LORA",
|
21 |
"r": 16,
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
-
"
|
26 |
-
"o_proj",
|
27 |
"q_proj",
|
|
|
28 |
"v_proj",
|
29 |
"down_proj",
|
30 |
-
"
|
31 |
-
"
|
32 |
],
|
33 |
"task_type": "CAUSAL_LM",
|
34 |
"use_rslora": false
|
|
|
13 |
"lora_dropout": 0.1,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
|
|
|
|
|
|
17 |
"peft_type": "LORA",
|
18 |
"r": 16,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"gate_proj",
|
|
|
23 |
"q_proj",
|
24 |
+
"up_proj",
|
25 |
"v_proj",
|
26 |
"down_proj",
|
27 |
+
"k_proj",
|
28 |
+
"o_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": 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:bd3686256b7ec74df9cbf5a30be3e57dc64e1fef33ce243a2557d8b1e7ccf766
|
3 |
+
size 83946192
|
config.json
CHANGED
@@ -22,5 +22,5 @@
|
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.38.0.dev0",
|
24 |
"use_cache": false,
|
25 |
-
"vocab_size":
|
26 |
}
|
|
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.38.0.dev0",
|
24 |
"use_cache": false,
|
25 |
+
"vocab_size": 32000
|
26 |
}
|
tokenizer_config.json
CHANGED
@@ -25,22 +25,6 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "function_token",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": false
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "conversation_token",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false,
|
43 |
-
"special": false
|
44 |
}
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
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:d50f11a95e1eddb77c0fc35354918b475fd0da0af52232636216c228afc4352a
|
3 |
+
size 5560
|