Training in progress, step 300
Browse files- adapter_config.json +5 -5
- training_args.bin +1 -1
- training_config.json +2 -2
adapter_config.json
CHANGED
@@ -14,13 +14,13 @@
|
|
14 |
"r": 64,
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
-
"
|
18 |
-
"q_proj",
|
19 |
-
"v_proj",
|
20 |
"k_proj",
|
|
|
21 |
"up_proj",
|
22 |
-
"
|
23 |
-
"
|
|
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
14 |
"r": 64,
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
+
"gate_proj",
|
|
|
|
|
18 |
"k_proj",
|
19 |
+
"q_proj",
|
20 |
"up_proj",
|
21 |
+
"down_proj",
|
22 |
+
"v_proj",
|
23 |
+
"o_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6264
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee2ec909333d3905200788230f22925c9ffad5b1eaa153c525a871e6167df588
|
3 |
size 6264
|
training_config.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"experiment_key": "base",
|
3 |
"save_safetensors": true,
|
4 |
"max_shard_size": "10GB",
|
5 |
-
"local_rank":
|
6 |
"use_gradient_checkpointing": true,
|
7 |
"trainer_key": "lm",
|
8 |
"force_fp32": false,
|
@@ -27,7 +27,7 @@
|
|
27 |
"quantized_hub_private_repo": null,
|
28 |
"dataset_key": "desc2json",
|
29 |
"train_local_path_to_data": "./train.jsonl",
|
30 |
-
"eval_local_path_to_data":
|
31 |
"shuffle": true,
|
32 |
"max_eval_samples": 1000,
|
33 |
"add_eval_to_train_if_no_path": false,
|
|
|
2 |
"experiment_key": "base",
|
3 |
"save_safetensors": true,
|
4 |
"max_shard_size": "10GB",
|
5 |
+
"local_rank": 1,
|
6 |
"use_gradient_checkpointing": true,
|
7 |
"trainer_key": "lm",
|
8 |
"force_fp32": false,
|
|
|
27 |
"quantized_hub_private_repo": null,
|
28 |
"dataset_key": "desc2json",
|
29 |
"train_local_path_to_data": "./train.jsonl",
|
30 |
+
"eval_local_path_to_data": "./eval.jsonl",
|
31 |
"shuffle": true,
|
32 |
"max_eval_samples": 1000,
|
33 |
"add_eval_to_train_if_no_path": false,
|