Model save
Browse files- README.md +3 -7
- adapter_config.json +4 -4
- all_results.json +7 -7
- eval_results.json +4 -4
- train_results.json +3 -3
- trainer_state.json +3 -3
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,13 +2,9 @@
|
|
2 |
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
-
- generated_from_trainer
|
7 |
- trl
|
8 |
- sft
|
9 |
- generated_from_trainer
|
10 |
-
datasets:
|
11 |
-
- ruozhiba
|
12 |
base_model: 01-ai/Yi-6B
|
13 |
model-index:
|
14 |
- name: Yi-6B-ruozhiba-5e-4-50
|
@@ -20,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
# Yi-6B-ruozhiba-5e-4-50
|
22 |
|
23 |
-
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the
|
24 |
It achieves the following results on the evaluation set:
|
25 |
-
- Loss:
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -79,6 +75,6 @@ The following hyperparameters were used during training:
|
|
79 |
|
80 |
- PEFT 0.7.1
|
81 |
- Transformers 4.36.2
|
82 |
-
- Pytorch 2.
|
83 |
- Datasets 2.14.6
|
84 |
- Tokenizers 0.15.2
|
|
|
2 |
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
|
|
|
|
8 |
base_model: 01-ai/Yi-6B
|
9 |
model-index:
|
10 |
- name: Yi-6B-ruozhiba-5e-4-50
|
|
|
16 |
|
17 |
# Yi-6B-ruozhiba-5e-4-50
|
18 |
|
19 |
+
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 4.1158
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
75 |
|
76 |
- PEFT 0.7.1
|
77 |
- Transformers 4.36.2
|
78 |
+
- Pytorch 2.3.0+cu121
|
79 |
- Datasets 2.14.6
|
80 |
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"gate_proj",
|
23 |
"k_proj",
|
24 |
-
"o_proj",
|
25 |
"v_proj",
|
|
|
|
|
|
|
26 |
"down_proj",
|
27 |
-
"up_proj"
|
28 |
-
"q_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"k_proj",
|
|
|
23 |
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"o_proj",
|
27 |
"down_proj",
|
28 |
+
"up_proj"
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime": 6.
|
5 |
"eval_samples": 23,
|
6 |
-
"eval_samples_per_second": 3.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
"train_loss": 0.0,
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 217,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second":
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"eval_loss": 4.1158246994018555,
|
4 |
+
"eval_runtime": 6.5886,
|
5 |
"eval_samples": 23,
|
6 |
+
"eval_samples_per_second": 3.491,
|
7 |
+
"eval_steps_per_second": 0.911,
|
8 |
"train_loss": 0.0,
|
9 |
+
"train_runtime": 11.9759,
|
10 |
"train_samples": 217,
|
11 |
+
"train_samples_per_second": 181.197,
|
12 |
+
"train_steps_per_second": 45.925
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime": 6.
|
5 |
"eval_samples": 23,
|
6 |
-
"eval_samples_per_second": 3.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"eval_loss": 4.1158246994018555,
|
4 |
+
"eval_runtime": 6.5886,
|
5 |
"eval_samples": 23,
|
6 |
+
"eval_samples_per_second": 3.491,
|
7 |
+
"eval_steps_per_second": 0.911
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
"train_loss": 0.0,
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 217,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
"train_loss": 0.0,
|
4 |
+
"train_runtime": 11.9759,
|
5 |
"train_samples": 217,
|
6 |
+
"train_samples_per_second": 181.197,
|
7 |
+
"train_steps_per_second": 45.925
|
8 |
}
|
trainer_state.json
CHANGED
@@ -2011,9 +2011,9 @@
|
|
2011 |
"step": 1100,
|
2012 |
"total_flos": 3.792163606268314e+16,
|
2013 |
"train_loss": 0.0,
|
2014 |
-
"train_runtime":
|
2015 |
-
"train_samples_per_second":
|
2016 |
-
"train_steps_per_second":
|
2017 |
}
|
2018 |
],
|
2019 |
"logging_steps": 4,
|
|
|
2011 |
"step": 1100,
|
2012 |
"total_flos": 3.792163606268314e+16,
|
2013 |
"train_loss": 0.0,
|
2014 |
+
"train_runtime": 11.9759,
|
2015 |
+
"train_samples_per_second": 181.197,
|
2016 |
+
"train_steps_per_second": 45.925
|
2017 |
}
|
2018 |
],
|
2019 |
"logging_steps": 4,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80a8894d431c206e6e47301949f4364b55937f8e0dfc94c3023d0b32796629fd
|
3 |
size 4792
|