Training in progress, epoch 0
Browse files- adapter_config.json +4 -8
- adapter_model.safetensors +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -10,24 +10,20 @@
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
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 |
-
"gate_proj",
|
25 |
-
"up_proj",
|
26 |
"k_proj",
|
27 |
-
"down_proj",
|
28 |
-
"o_proj",
|
29 |
"v_proj",
|
30 |
-
"
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 4096,
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 2048,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
|
|
|
|
24 |
"k_proj",
|
|
|
|
|
25 |
"v_proj",
|
26 |
+
"o_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"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:af6b16200d042cebd41f79f7fa5c68776c5b1b73b231c7648afd4162a3a4e25e
|
3 |
+
size 1610621688
|
tokenizer_config.json
CHANGED
@@ -116,7 +116,7 @@
|
|
116 |
}
|
117 |
},
|
118 |
"bos_token": "<s>",
|
119 |
-
"chat_template": "{
|
120 |
"clean_up_tokenization_spaces": false,
|
121 |
"eos_token": "<|endoftext|>",
|
122 |
"legacy": false,
|
|
|
116 |
}
|
117 |
},
|
118 |
"bos_token": "<s>",
|
119 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
120 |
"clean_up_tokenization_spaces": false,
|
121 |
"eos_token": "<|endoftext|>",
|
122 |
"legacy": false,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9a9beb0e00cc4220fcaa18974224cb658778a261da50b3b96a382b7e2cab492
|
3 |
size 4984
|