Training in progress, step 25
Browse files- adapter_config.json +4 -15
- adapter_model.safetensors +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +0 -1
- training_args.bin +2 -2
adapter_config.json
CHANGED
|
@@ -3,9 +3,6 @@
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "google/gemma-2b",
|
| 5 |
"bias": "none",
|
| 6 |
-
"corda_config": null,
|
| 7 |
-
"eva_config": null,
|
| 8 |
-
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
| 10 |
"inference_mode": true,
|
| 11 |
"init_lora_weights": true,
|
|
@@ -14,27 +11,19 @@
|
|
| 14 |
"layers_to_transform": null,
|
| 15 |
"loftq_config": {},
|
| 16 |
"lora_alpha": 16,
|
| 17 |
-
"
|
| 18 |
-
"lora_dropout": 0.1,
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
-
"modules_to_save":
|
| 22 |
-
"classifier",
|
| 23 |
-
"score"
|
| 24 |
-
],
|
| 25 |
"peft_type": "LORA",
|
| 26 |
-
"qalora_group_size": 16,
|
| 27 |
"r": 64,
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
-
"target_parameters": null,
|
| 35 |
"task_type": "SEQ_CLS",
|
| 36 |
-
"trainable_token_indices": null,
|
| 37 |
"use_dora": false,
|
| 38 |
-
"use_qalora": false,
|
| 39 |
"use_rslora": false
|
| 40 |
}
|
|
|
|
| 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,
|
|
|
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.2,
|
|
|
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
|
|
|
|
|
|
|
|
|
| 18 |
"peft_type": "LORA",
|
|
|
|
| 19 |
"r": 64,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
],
|
|
|
|
| 26 |
"task_type": "SEQ_CLS",
|
|
|
|
| 27 |
"use_dora": false,
|
|
|
|
| 28 |
"use_rslora": false
|
| 29 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 29509144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e5a81c44763407771b8f5d270cfe4514ad9bdf6514a4b65e86cb1b90fcaca94
|
| 3 |
size 29509144
|
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 sha256:0e2426d8041e7d5ce3cf519fb3edc6a4810caed0a0680d1d7a0b662e17cd2583
|
| 3 |
+
size 17518789
|
tokenizer_config.json
CHANGED
|
@@ -1746,7 +1746,6 @@
|
|
| 1746 |
"bos_token": "<bos>",
|
| 1747 |
"clean_up_tokenization_spaces": false,
|
| 1748 |
"eos_token": "<eos>",
|
| 1749 |
-
"extra_special_tokens": {},
|
| 1750 |
"model_max_length": 1000000000000000019884624838656,
|
| 1751 |
"pad_token": "<eos>",
|
| 1752 |
"sp_model_kwargs": {},
|
|
|
|
| 1746 |
"bos_token": "<bos>",
|
| 1747 |
"clean_up_tokenization_spaces": false,
|
| 1748 |
"eos_token": "<eos>",
|
|
|
|
| 1749 |
"model_max_length": 1000000000000000019884624838656,
|
| 1750 |
"pad_token": "<eos>",
|
| 1751 |
"sp_model_kwargs": {},
|
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:ecc217cda65006b6c0778194ee02d7d0172504502249c99b581e03630d1ade02
|
| 3 |
+
size 5393
|