Training in progress, step 50
Browse files- adapter_config.json +8 -5
- adapter_model.safetensors +2 -2
- special_tokens_map.json +1 -7
- tokenizer.json +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -1,12 +1,11 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "google/gemma-
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
9 |
-
"layer_replication": null,
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
@@ -16,12 +15,16 @@
|
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"q_proj"
|
|
|
|
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2b",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
|
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
+
"r": 4,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"up_proj",
|
26 |
+
"o_proj",
|
27 |
+
"v_proj"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"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 sha256:3ee028ecb6a255159117033295f4a3147fc065794b57d314c2673beb6bbd8132
|
3 |
+
size 14331480
|
special_tokens_map.json
CHANGED
@@ -13,13 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
17 |
-
"content": "<pad>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<eos>",
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
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:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
|
3 |
+
size 17477553
|
tokenizer_config.json
CHANGED
@@ -40,7 +40,7 @@
|
|
40 |
"eos_token": "<eos>",
|
41 |
"legacy": null,
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
-
"pad_token": "<
|
44 |
"sp_model_kwargs": {},
|
45 |
"spaces_between_special_tokens": false,
|
46 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
40 |
"eos_token": "<eos>",
|
41 |
"legacy": null,
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<eos>",
|
44 |
"sp_model_kwargs": {},
|
45 |
"spaces_between_special_tokens": false,
|
46 |
"tokenizer_class": "GemmaTokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87d48ae495b5ec2c27967d9f014a93b0c34aeb37541db2e058a8c64ecf8e6a16
|
3 |
size 4856
|