Model save
Browse files- README.md +1 -5
- adapter_config.json +1 -1
- all_results.json +4 -4
- runs/May13_09-10-25_gpu4-119-5/events.out.tfevents.1715555531.gpu4-119-5.4068129.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +4 -4
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,14 +2,10 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
-
- generated_from_trainer
|
7 |
- trl
|
8 |
- dpo
|
9 |
- generated_from_trainer
|
10 |
base_model: DUAL-GPO/phi-2-gpo-new-i0
|
11 |
-
datasets:
|
12 |
-
- HuggingFaceH4/ultrafeedback_binarized
|
13 |
model-index:
|
14 |
- name: phi-2-gpo-v9-i1
|
15 |
results: []
|
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
# phi-2-gpo-v9-i1
|
22 |
|
23 |
-
This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
8 |
base_model: DUAL-GPO/phi-2-gpo-new-i0
|
|
|
|
|
9 |
model-index:
|
10 |
- name: phi-2-gpo-v9-i1
|
11 |
results: []
|
|
|
16 |
|
17 |
# phi-2-gpo-v9-i1
|
18 |
|
19 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the None dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
adapter_config.json
CHANGED
@@ -19,9 +19,9 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"v_proj",
|
23 |
"k_proj",
|
24 |
-
"q_proj",
|
25 |
"dense"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
"v_proj",
|
24 |
"k_proj",
|
|
|
25 |
"dense"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 15000,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.00839476689712215,
|
4 |
+
"train_runtime": 333.4674,
|
5 |
"train_samples": 15000,
|
6 |
+
"train_samples_per_second": 44.982,
|
7 |
+
"train_steps_per_second": 2.81
|
8 |
}
|
runs/May13_09-10-25_gpu4-119-5/events.out.tfevents.1715555531.gpu4-119-5.4068129.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35669cad78a87d236a882faa9001eea203a2fa59bffc8be5549b4d176b801743
|
3 |
+
size 7079
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 15000,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.00839476689712215,
|
4 |
+
"train_runtime": 333.4674,
|
5 |
"train_samples": 15000,
|
6 |
+
"train_samples_per_second": 44.982,
|
7 |
+
"train_steps_per_second": 2.81
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1328,10 +1328,10 @@
|
|
1328 |
"epoch": 1.0,
|
1329 |
"step": 937,
|
1330 |
"total_flos": 0.0,
|
1331 |
-
"train_loss": 0.
|
1332 |
-
"train_runtime":
|
1333 |
-
"train_samples_per_second":
|
1334 |
-
"train_steps_per_second":
|
1335 |
}
|
1336 |
],
|
1337 |
"logging_steps": 10,
|
|
|
1328 |
"epoch": 1.0,
|
1329 |
"step": 937,
|
1330 |
"total_flos": 0.0,
|
1331 |
+
"train_loss": 0.00839476689712215,
|
1332 |
+
"train_runtime": 333.4674,
|
1333 |
+
"train_samples_per_second": 44.982,
|
1334 |
+
"train_steps_per_second": 2.81
|
1335 |
}
|
1336 |
],
|
1337 |
"logging_steps": 10,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9d0be8b29997dfcbc40993dc81bb9d699905a622742e2f9626ef95fbf042403
|
3 |
size 5816
|