Upload 14 files
Browse files- checkpoint-36300/adapter_config.json +17 -0
- checkpoint-36300/adapter_model.bin +3 -0
- checkpoint-36300/optimizer.pt +3 -0
- checkpoint-36300/pytorch_model.bin +3 -0
- checkpoint-36300/rng_state_0.pth +3 -0
- checkpoint-36300/rng_state_1.pth +3 -0
- checkpoint-36300/rng_state_2.pth +3 -0
- checkpoint-36300/rng_state_3.pth +3 -0
- checkpoint-36300/scaler.pt +3 -0
- checkpoint-36300/scheduler.pt +3 -0
- checkpoint-36300/tokenizer.model +3 -0
- checkpoint-36300/tokenizer_config.json +33 -0
- checkpoint-36300/trainer_state.json +0 -0
- checkpoint-36300/training_args.bin +3 -0
checkpoint-36300/adapter_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "/mnt/data1/sheshuaijie/Data/PLM/chinese-llama-plus-13b",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"lora_alpha": 32,
|
8 |
+
"lora_dropout": 0.1,
|
9 |
+
"modules_to_save": null,
|
10 |
+
"peft_type": "LORA",
|
11 |
+
"r": 32,
|
12 |
+
"target_modules": [
|
13 |
+
"q_proj",
|
14 |
+
"v_proj"
|
15 |
+
],
|
16 |
+
"task_type": "CAUSAL_LM"
|
17 |
+
}
|
checkpoint-36300/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
|
3 |
+
size 443
|
checkpoint-36300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:954d6d4e11f695aa78ad8084ac30d28590a0f291c74186f51cf16bcf75f03658
|
3 |
+
size 209810181
|
checkpoint-36300/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be14669de7543b949c5377fb6a9fd5cd9ace38b095111581d7775a8bea24ec6f
|
3 |
+
size 104915277
|
checkpoint-36300/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a4b1e0c6aa1054baf649107706e23e43d0524e57d2c879379a66b359c236f89
|
3 |
+
size 17655
|
checkpoint-36300/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1126e10dae4970ecfea897c064e1739f8e75a137609b083e4725082ca0f34382
|
3 |
+
size 17655
|
checkpoint-36300/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94a9bd76c9fd92d05741d0c4779d186adf221f7d5e6ad526fe49fa6d8f1f96cb
|
3 |
+
size 17655
|
checkpoint-36300/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:995a1beaf9896ac470ab5c11b4e4435700c2119cf7bc09dc32e7b308f61ed0f9
|
3 |
+
size 17655
|
checkpoint-36300/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eca67721b24472642ed2d0451299d347c0f6a8a8c77e8525def0323102f1b8bd
|
3 |
+
size 557
|
checkpoint-36300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6de231a507557b548f4307ee3554c522e47736041380eaaa49f83b6425cdfb64
|
3 |
+
size 627
|
checkpoint-36300/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d967e855b1213a439df6c8ce2791f869c84b4f3b6cfacf22b86440b8192a2f8
|
3 |
+
size 757972
|
checkpoint-36300/tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"model_max_length": 1000000000000000019884624838656,
|
22 |
+
"pad_token": null,
|
23 |
+
"sp_model_kwargs": {},
|
24 |
+
"tokenizer_class": "LlamaTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
checkpoint-36300/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-36300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22ccdf47375cc0c10d09f7d4e3339d66e050251fc9407dea9c956dba57326bc3
|
3 |
+
size 4155
|