Training in progress, step 200
Browse files- adapter_config.json +10 -5
- adapter_model.safetensors +1 -1
- tokenizer.model +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +2 -2
adapter_config.json
CHANGED
|
@@ -3,6 +3,9 @@
|
|
| 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,
|
|
@@ -11,6 +14,7 @@
|
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
"lora_alpha": 48,
|
|
|
|
| 14 |
"lora_dropout": 0.1,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
|
@@ -20,15 +24,16 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"q_proj",
|
| 24 |
-
"v_proj",
|
| 25 |
-
"k_proj",
|
| 26 |
-
"gate_proj",
|
| 27 |
"o_proj",
|
|
|
|
|
|
|
| 28 |
"down_proj",
|
| 29 |
-
"
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 32 |
"use_dora": false,
|
| 33 |
"use_rslora": false
|
| 34 |
}
|
|
|
|
| 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 |
"layers_to_transform": null,
|
| 15 |
"loftq_config": {},
|
| 16 |
"lora_alpha": 48,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
"lora_dropout": 0.1,
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
|
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"o_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
"down_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
"use_dora": false,
|
| 38 |
"use_rslora": false
|
| 39 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 117703472
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4c495ac434c7464d8d2b238eac57432f15724663bc71744a6518733ce96622e
|
| 3 |
size 117703472
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
tokenizer_config.json
CHANGED
|
@@ -1746,6 +1746,7 @@
|
|
| 1746 |
"bos_token": "<bos>",
|
| 1747 |
"clean_up_tokenization_spaces": false,
|
| 1748 |
"eos_token": "<eos>",
|
|
|
|
| 1749 |
"model_max_length": 1000000000000000019884624838656,
|
| 1750 |
"pad_token": "<pad>",
|
| 1751 |
"sp_model_kwargs": {},
|
|
|
|
| 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": "<pad>",
|
| 1752 |
"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:c81b4810a5f40306e2fe0e955096b0d4300b4d318710f0723d5f63f7f1ffc04c
|
| 3 |
+
size 5777
|