请结合原模型使用
Browse files
lunyu-2023.5.16/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e2e2a4db41c5047a5086c106b022105ed29a7d5ceb9a9d849a396f21ef62f75
|
3 |
+
size 234962509
|
lunyu-2023.5.16/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29520d3bbca7e98da338e099608e104adb5549010b5da9f25b72a775a438e09d
|
3 |
+
size 469895045
|
lunyu-2023.5.16/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1004d2eca03b28175501650ca48a3679af1f94c698a2d211e8dc0c1d31d23d0
|
3 |
+
size 15597
|
lunyu-2023.5.16/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8894add6cf5ff4d4049868d7614fbae0eb98e7ffb617edb8d94b4cd7e15ebd0d
|
3 |
+
size 557
|
lunyu-2023.5.16/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:896a20d9a959705b9d46ef5fc21020cd00586512bcab315a0ad82fc5610fa9fe
|
3 |
+
size 627
|
lunyu-2023.5.16/trainer_state.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 57.142857142857146,
|
5 |
+
"global_step": 400,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 7.14,
|
12 |
+
"learning_rate": 8.850000000000001e-05,
|
13 |
+
"loss": 1.8163,
|
14 |
+
"step": 50
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 14.29,
|
18 |
+
"learning_rate": 7.6e-05,
|
19 |
+
"loss": 0.0145,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 21.43,
|
24 |
+
"learning_rate": 6.35e-05,
|
25 |
+
"loss": 0.0015,
|
26 |
+
"step": 150
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 28.57,
|
30 |
+
"learning_rate": 5.1000000000000006e-05,
|
31 |
+
"loss": 0.0007,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 35.71,
|
36 |
+
"learning_rate": 3.85e-05,
|
37 |
+
"loss": 0.0006,
|
38 |
+
"step": 250
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 42.86,
|
42 |
+
"learning_rate": 2.6000000000000002e-05,
|
43 |
+
"loss": 0.0005,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 50.0,
|
48 |
+
"learning_rate": 1.3500000000000001e-05,
|
49 |
+
"loss": 0.0004,
|
50 |
+
"step": 350
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 57.14,
|
54 |
+
"learning_rate": 1.0000000000000002e-06,
|
55 |
+
"loss": 0.0004,
|
56 |
+
"step": 400
|
57 |
+
}
|
58 |
+
],
|
59 |
+
"max_steps": 400,
|
60 |
+
"num_train_epochs": 58,
|
61 |
+
"total_flos": 5098502646595584.0,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": null
|
64 |
+
}
|
lunyu-2023.5.16/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b6cd9e81d87d8ac0c44bfcfa8ebcb4472d6e6f46d3b7ee0fb029c4ee00b2aee
|
3 |
+
size 3579
|