wangrongsheng
commited on
Commit
·
f87df86
1
Parent(s):
85d28ef
Upload 7 files
Browse files- adapter_config.json +16 -0
- adapter_model.bin +3 -0
- all_results.json +7 -0
- finetuning_args.bin +3 -0
- train_results.json +7 -0
- trainer_state.json +25 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "THUDM/chatglm-6b",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"lora_alpha": 32.0,
|
8 |
+
"lora_dropout": 0.1,
|
9 |
+
"modules_to_save": null,
|
10 |
+
"peft_type": "LORA",
|
11 |
+
"r": 8,
|
12 |
+
"target_modules": [
|
13 |
+
"query_key_value"
|
14 |
+
],
|
15 |
+
"task_type": "CAUSAL_LM"
|
16 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50f11de0ea817f4b7e6dd59f4e8b6e5a4b1f24096d219ec25cc28ecf96995ce5
|
3 |
+
size 14700825
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.43,
|
3 |
+
"train_loss": 2.851648183969351,
|
4 |
+
"train_runtime": 100924.6831,
|
5 |
+
"train_samples_per_second": 11.195,
|
6 |
+
"train_steps_per_second": 0.001
|
7 |
+
}
|
finetuning_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0d21be8c105704d26792b0b5ff588414e9de8cdb4d00194854d7cec1b515a17
|
3 |
+
size 895
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.43,
|
3 |
+
"train_loss": 2.851648183969351,
|
4 |
+
"train_runtime": 100924.6831,
|
5 |
+
"train_samples_per_second": 11.195,
|
6 |
+
"train_steps_per_second": 0.001
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.425092041914471,
|
5 |
+
"global_step": 130,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 9.43,
|
12 |
+
"step": 130,
|
13 |
+
"total_flos": 8.795614315739038e+18,
|
14 |
+
"train_loss": 2.851648183969351,
|
15 |
+
"train_runtime": 100924.6831,
|
16 |
+
"train_samples_per_second": 11.195,
|
17 |
+
"train_steps_per_second": 0.001
|
18 |
+
}
|
19 |
+
],
|
20 |
+
"max_steps": 130,
|
21 |
+
"num_train_epochs": 10,
|
22 |
+
"total_flos": 8.795614315739038e+18,
|
23 |
+
"trial_name": null,
|
24 |
+
"trial_params": null
|
25 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a186dab50aca045ae82a96e18c433e74b1f271c5694a28464dae1bafd38194d
|
3 |
+
size 3707
|