Model save
Browse files- README.md +59 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May20_19-11-50_gpu4-119-5/events.out.tfevents.1716196487.gpu4-119-5.943168.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
tags:
|
4 |
+
- trl
|
5 |
+
- dpo
|
6 |
+
- generated_from_trainer
|
7 |
+
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-i0
|
8 |
+
model-index:
|
9 |
+
- name: phi-2-irepo-chatml-v7-i1
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# phi-2-irepo-chatml-v7-i1
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-i0](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-i0) on the None dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-06
|
38 |
+
- train_batch_size: 4
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- gradient_accumulation_steps: 4
|
43 |
+
- total_train_batch_size: 16
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
47 |
+
- num_epochs: 1
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- PEFT 0.7.1
|
56 |
+
- Transformers 4.36.2
|
57 |
+
- Pytorch 2.1.2+cu121
|
58 |
+
- Datasets 2.14.6
|
59 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335579632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51e938a1f150390dcc16a71af6f49694e97500b566bb2cd0a2ac9edb46e94e0e
|
3 |
size 335579632
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.20694573613802592,
|
4 |
+
"train_runtime": 16535.0328,
|
5 |
+
"train_samples": 30000,
|
6 |
+
"train_samples_per_second": 1.814,
|
7 |
+
"train_steps_per_second": 0.113
|
8 |
+
}
|
runs/May20_19-11-50_gpu4-119-5/events.out.tfevents.1716196487.gpu4-119-5.943168.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff4f751f8b55bbb47771266b4c1e7e8a8cd47b5bf506462e5b76964acaf2c8cf
|
3 |
+
size 124312
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.20694573613802592,
|
4 |
+
"train_runtime": 16535.0328,
|
5 |
+
"train_samples": 30000,
|
6 |
+
"train_samples_per_second": 1.814,
|
7 |
+
"train_steps_per_second": 0.113
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2662 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1875,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2.6595744680851065e-08,
|
14 |
+
"logits/chosen": 0.41994422674179077,
|
15 |
+
"logits/rejected": 0.44097208976745605,
|
16 |
+
"logps/chosen": -255.3050537109375,
|
17 |
+
"logps/rejected": -278.9874572753906,
|
18 |
+
"loss": 0.247,
|
19 |
+
"rewards/accuracies": 0.0,
|
20 |
+
"rewards/chosen": 0.0,
|
21 |
+
"rewards/margins": 0.0,
|
22 |
+
"rewards/rejected": 0.0,
|
23 |
+
"step": 1
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"learning_rate": 2.6595744680851066e-07,
|
28 |
+
"logits/chosen": 0.3012881875038147,
|
29 |
+
"logits/rejected": 0.3096545338630676,
|
30 |
+
"logps/chosen": -280.16510009765625,
|
31 |
+
"logps/rejected": -291.20611572265625,
|
32 |
+
"loss": 0.2072,
|
33 |
+
"rewards/accuracies": 0.2083333283662796,
|
34 |
+
"rewards/chosen": -0.00013855236466042697,
|
35 |
+
"rewards/margins": -6.587021289305994e-06,
|
36 |
+
"rewards/rejected": -0.0001319653238169849,
|
37 |
+
"step": 10
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.01,
|
41 |
+
"learning_rate": 5.319148936170213e-07,
|
42 |
+
"logits/chosen": 0.31470876932144165,
|
43 |
+
"logits/rejected": 0.31193265318870544,
|
44 |
+
"logps/chosen": -327.54095458984375,
|
45 |
+
"logps/rejected": -344.1315612792969,
|
46 |
+
"loss": 0.2101,
|
47 |
+
"rewards/accuracies": 0.23125000298023224,
|
48 |
+
"rewards/chosen": -0.00020987121388316154,
|
49 |
+
"rewards/margins": -7.895669841673225e-05,
|
50 |
+
"rewards/rejected": -0.0001309145154664293,
|
51 |
+
"step": 20
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 7.97872340425532e-07,
|
56 |
+
"logits/chosen": 0.3390754163265228,
|
57 |
+
"logits/rejected": 0.35239648818969727,
|
58 |
+
"logps/chosen": -248.12741088867188,
|
59 |
+
"logps/rejected": -250.649658203125,
|
60 |
+
"loss": 0.2173,
|
61 |
+
"rewards/accuracies": 0.26875001192092896,
|
62 |
+
"rewards/chosen": -0.00013244706497061998,
|
63 |
+
"rewards/margins": 4.99083471368067e-05,
|
64 |
+
"rewards/rejected": -0.00018235540483146906,
|
65 |
+
"step": 30
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.02,
|
69 |
+
"learning_rate": 1.0638297872340427e-06,
|
70 |
+
"logits/chosen": 0.3102382719516754,
|
71 |
+
"logits/rejected": 0.32991108298301697,
|
72 |
+
"logps/chosen": -301.28411865234375,
|
73 |
+
"logps/rejected": -329.452880859375,
|
74 |
+
"loss": 0.2161,
|
75 |
+
"rewards/accuracies": 0.25,
|
76 |
+
"rewards/chosen": -0.00040395656833425164,
|
77 |
+
"rewards/margins": 8.279903340735473e-06,
|
78 |
+
"rewards/rejected": -0.00041223643347620964,
|
79 |
+
"step": 40
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.03,
|
83 |
+
"learning_rate": 1.3297872340425533e-06,
|
84 |
+
"logits/chosen": 0.34786778688430786,
|
85 |
+
"logits/rejected": 0.35041943192481995,
|
86 |
+
"logps/chosen": -254.66000366210938,
|
87 |
+
"logps/rejected": -254.5922393798828,
|
88 |
+
"loss": 0.2075,
|
89 |
+
"rewards/accuracies": 0.24375000596046448,
|
90 |
+
"rewards/chosen": -0.00043535622535273433,
|
91 |
+
"rewards/margins": 2.4446379029541276e-05,
|
92 |
+
"rewards/rejected": -0.0004598026571329683,
|
93 |
+
"step": 50
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.03,
|
97 |
+
"learning_rate": 1.595744680851064e-06,
|
98 |
+
"logits/chosen": 0.28234267234802246,
|
99 |
+
"logits/rejected": 0.3171209692955017,
|
100 |
+
"logps/chosen": -284.116943359375,
|
101 |
+
"logps/rejected": -319.9707946777344,
|
102 |
+
"loss": 0.2174,
|
103 |
+
"rewards/accuracies": 0.24375000596046448,
|
104 |
+
"rewards/chosen": -0.00010556467896094546,
|
105 |
+
"rewards/margins": -1.569558480696287e-05,
|
106 |
+
"rewards/rejected": -8.986910688690841e-05,
|
107 |
+
"step": 60
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.04,
|
111 |
+
"learning_rate": 1.8617021276595745e-06,
|
112 |
+
"logits/chosen": 0.32085567712783813,
|
113 |
+
"logits/rejected": 0.3497418761253357,
|
114 |
+
"logps/chosen": -317.13531494140625,
|
115 |
+
"logps/rejected": -336.9044494628906,
|
116 |
+
"loss": 0.1988,
|
117 |
+
"rewards/accuracies": 0.3125,
|
118 |
+
"rewards/chosen": -0.0005014509661123157,
|
119 |
+
"rewards/margins": 4.7156230721157044e-05,
|
120 |
+
"rewards/rejected": -0.0005486071459017694,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.04,
|
125 |
+
"learning_rate": 2.1276595744680853e-06,
|
126 |
+
"logits/chosen": 0.28880470991134644,
|
127 |
+
"logits/rejected": 0.3247111141681671,
|
128 |
+
"logps/chosen": -284.1805114746094,
|
129 |
+
"logps/rejected": -306.4732666015625,
|
130 |
+
"loss": 0.1987,
|
131 |
+
"rewards/accuracies": 0.2750000059604645,
|
132 |
+
"rewards/chosen": 0.00016313868400175124,
|
133 |
+
"rewards/margins": 0.00013786499039269984,
|
134 |
+
"rewards/rejected": 2.5273693609051406e-05,
|
135 |
+
"step": 80
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05,
|
139 |
+
"learning_rate": 2.393617021276596e-06,
|
140 |
+
"logits/chosen": 0.33655500411987305,
|
141 |
+
"logits/rejected": 0.3271638751029968,
|
142 |
+
"logps/chosen": -257.6504821777344,
|
143 |
+
"logps/rejected": -280.1950988769531,
|
144 |
+
"loss": 0.205,
|
145 |
+
"rewards/accuracies": 0.25,
|
146 |
+
"rewards/chosen": -0.00013443852367345244,
|
147 |
+
"rewards/margins": 3.99285345338285e-05,
|
148 |
+
"rewards/rejected": -0.00017436707275919616,
|
149 |
+
"step": 90
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.05,
|
153 |
+
"learning_rate": 2.6595744680851065e-06,
|
154 |
+
"logits/chosen": 0.30501195788383484,
|
155 |
+
"logits/rejected": 0.30879053473472595,
|
156 |
+
"logps/chosen": -291.9537048339844,
|
157 |
+
"logps/rejected": -314.95623779296875,
|
158 |
+
"loss": 0.2111,
|
159 |
+
"rewards/accuracies": 0.3125,
|
160 |
+
"rewards/chosen": -1.4989857845648658e-05,
|
161 |
+
"rewards/margins": 0.0001315394474659115,
|
162 |
+
"rewards/rejected": -0.0001465293171349913,
|
163 |
+
"step": 100
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.06,
|
167 |
+
"learning_rate": 2.9255319148936174e-06,
|
168 |
+
"logits/chosen": 0.3248497545719147,
|
169 |
+
"logits/rejected": 0.32843533158302307,
|
170 |
+
"logps/chosen": -305.5889587402344,
|
171 |
+
"logps/rejected": -315.61578369140625,
|
172 |
+
"loss": 0.2001,
|
173 |
+
"rewards/accuracies": 0.23125000298023224,
|
174 |
+
"rewards/chosen": -0.0013872724957764149,
|
175 |
+
"rewards/margins": -4.216738307150081e-05,
|
176 |
+
"rewards/rejected": -0.0013451050035655499,
|
177 |
+
"step": 110
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.06,
|
181 |
+
"learning_rate": 3.191489361702128e-06,
|
182 |
+
"logits/chosen": 0.2866339087486267,
|
183 |
+
"logits/rejected": 0.315407931804657,
|
184 |
+
"logps/chosen": -271.4537048339844,
|
185 |
+
"logps/rejected": -288.8186950683594,
|
186 |
+
"loss": 0.2086,
|
187 |
+
"rewards/accuracies": 0.2874999940395355,
|
188 |
+
"rewards/chosen": -0.0016517008189111948,
|
189 |
+
"rewards/margins": 0.00013306428445503116,
|
190 |
+
"rewards/rejected": -0.0017847649287432432,
|
191 |
+
"step": 120
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.07,
|
195 |
+
"learning_rate": 3.457446808510639e-06,
|
196 |
+
"logits/chosen": 0.231134295463562,
|
197 |
+
"logits/rejected": 0.3182562291622162,
|
198 |
+
"logps/chosen": -296.9430847167969,
|
199 |
+
"logps/rejected": -304.53387451171875,
|
200 |
+
"loss": 0.2098,
|
201 |
+
"rewards/accuracies": 0.3375000059604645,
|
202 |
+
"rewards/chosen": -0.002512121107429266,
|
203 |
+
"rewards/margins": 0.00019210236496292055,
|
204 |
+
"rewards/rejected": -0.002704223617911339,
|
205 |
+
"step": 130
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.07,
|
209 |
+
"learning_rate": 3.723404255319149e-06,
|
210 |
+
"logits/chosen": 0.27288615703582764,
|
211 |
+
"logits/rejected": 0.30947965383529663,
|
212 |
+
"logps/chosen": -304.9461975097656,
|
213 |
+
"logps/rejected": -314.1529235839844,
|
214 |
+
"loss": 0.2097,
|
215 |
+
"rewards/accuracies": 0.2874999940395355,
|
216 |
+
"rewards/chosen": -0.003562493249773979,
|
217 |
+
"rewards/margins": 0.0003294651978649199,
|
218 |
+
"rewards/rejected": -0.003891958389431238,
|
219 |
+
"step": 140
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.08,
|
223 |
+
"learning_rate": 3.98936170212766e-06,
|
224 |
+
"logits/chosen": 0.2627570331096649,
|
225 |
+
"logits/rejected": 0.34792831540107727,
|
226 |
+
"logps/chosen": -272.2464294433594,
|
227 |
+
"logps/rejected": -296.91107177734375,
|
228 |
+
"loss": 0.218,
|
229 |
+
"rewards/accuracies": 0.3375000059604645,
|
230 |
+
"rewards/chosen": -0.0038285471964627504,
|
231 |
+
"rewards/margins": 0.0007261269493028522,
|
232 |
+
"rewards/rejected": -0.0045546735636889935,
|
233 |
+
"step": 150
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.09,
|
237 |
+
"learning_rate": 4.255319148936171e-06,
|
238 |
+
"logits/chosen": 0.27352815866470337,
|
239 |
+
"logits/rejected": 0.30977898836135864,
|
240 |
+
"logps/chosen": -315.76251220703125,
|
241 |
+
"logps/rejected": -325.41546630859375,
|
242 |
+
"loss": 0.2011,
|
243 |
+
"rewards/accuracies": 0.26875001192092896,
|
244 |
+
"rewards/chosen": -0.0019420146709308028,
|
245 |
+
"rewards/margins": 0.0003213664167560637,
|
246 |
+
"rewards/rejected": -0.0022633811458945274,
|
247 |
+
"step": 160
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.09,
|
251 |
+
"learning_rate": 4.521276595744681e-06,
|
252 |
+
"logits/chosen": 0.30782410502433777,
|
253 |
+
"logits/rejected": 0.26858752965927124,
|
254 |
+
"logps/chosen": -291.3421630859375,
|
255 |
+
"logps/rejected": -320.3433837890625,
|
256 |
+
"loss": 0.2131,
|
257 |
+
"rewards/accuracies": 0.2874999940395355,
|
258 |
+
"rewards/chosen": 0.00032241392182186246,
|
259 |
+
"rewards/margins": 0.0007240624399855733,
|
260 |
+
"rewards/rejected": -0.00040164851816371083,
|
261 |
+
"step": 170
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.1,
|
265 |
+
"learning_rate": 4.787234042553192e-06,
|
266 |
+
"logits/chosen": 0.24440982937812805,
|
267 |
+
"logits/rejected": 0.2718171179294586,
|
268 |
+
"logps/chosen": -296.61517333984375,
|
269 |
+
"logps/rejected": -307.93157958984375,
|
270 |
+
"loss": 0.2069,
|
271 |
+
"rewards/accuracies": 0.29374998807907104,
|
272 |
+
"rewards/chosen": -0.00043370993807911873,
|
273 |
+
"rewards/margins": 0.00036561707383953035,
|
274 |
+
"rewards/rejected": -0.0007993269828148186,
|
275 |
+
"step": 180
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.1,
|
279 |
+
"learning_rate": 4.999982660399688e-06,
|
280 |
+
"logits/chosen": 0.17186453938484192,
|
281 |
+
"logits/rejected": 0.16024716198444366,
|
282 |
+
"logps/chosen": -247.7923126220703,
|
283 |
+
"logps/rejected": -246.61996459960938,
|
284 |
+
"loss": 0.2256,
|
285 |
+
"rewards/accuracies": 0.26875001192092896,
|
286 |
+
"rewards/chosen": -0.00252458150498569,
|
287 |
+
"rewards/margins": 0.00020101522386539727,
|
288 |
+
"rewards/rejected": -0.0027255965396761894,
|
289 |
+
"step": 190
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.11,
|
293 |
+
"learning_rate": 4.99937579964398e-06,
|
294 |
+
"logits/chosen": 0.14718958735466003,
|
295 |
+
"logits/rejected": 0.217782661318779,
|
296 |
+
"logps/chosen": -305.3340759277344,
|
297 |
+
"logps/rejected": -323.8966064453125,
|
298 |
+
"loss": 0.1991,
|
299 |
+
"rewards/accuracies": 0.32499998807907104,
|
300 |
+
"rewards/chosen": -0.0030492418445646763,
|
301 |
+
"rewards/margins": 3.36905250151176e-05,
|
302 |
+
"rewards/rejected": -0.0030829322058707476,
|
303 |
+
"step": 200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.11,
|
307 |
+
"learning_rate": 4.9979021993870645e-06,
|
308 |
+
"logits/chosen": 0.18054236471652985,
|
309 |
+
"logits/rejected": 0.1431611180305481,
|
310 |
+
"logps/chosen": -289.236328125,
|
311 |
+
"logps/rejected": -295.9798278808594,
|
312 |
+
"loss": 0.2109,
|
313 |
+
"rewards/accuracies": 0.21875,
|
314 |
+
"rewards/chosen": -0.0029132370837032795,
|
315 |
+
"rewards/margins": -0.0005081830895505846,
|
316 |
+
"rewards/rejected": -0.0024050544016063213,
|
317 |
+
"step": 210
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.12,
|
321 |
+
"learning_rate": 4.995562370647553e-06,
|
322 |
+
"logits/chosen": 0.17394112050533295,
|
323 |
+
"logits/rejected": 0.17676064372062683,
|
324 |
+
"logps/chosen": -295.6396179199219,
|
325 |
+
"logps/rejected": -312.4654235839844,
|
326 |
+
"loss": 0.201,
|
327 |
+
"rewards/accuracies": 0.32499998807907104,
|
328 |
+
"rewards/chosen": -0.0027714716270565987,
|
329 |
+
"rewards/margins": 0.0016848895465955138,
|
330 |
+
"rewards/rejected": -0.004456360824406147,
|
331 |
+
"step": 220
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.12,
|
335 |
+
"learning_rate": 4.992357124836838e-06,
|
336 |
+
"logits/chosen": 0.1840275675058365,
|
337 |
+
"logits/rejected": 0.1552029550075531,
|
338 |
+
"logps/chosen": -324.6024169921875,
|
339 |
+
"logps/rejected": -344.926513671875,
|
340 |
+
"loss": 0.2192,
|
341 |
+
"rewards/accuracies": 0.34375,
|
342 |
+
"rewards/chosen": -0.004003914073109627,
|
343 |
+
"rewards/margins": 0.0011075122747570276,
|
344 |
+
"rewards/rejected": -0.005111426115036011,
|
345 |
+
"step": 230
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.13,
|
349 |
+
"learning_rate": 4.9882875734777044e-06,
|
350 |
+
"logits/chosen": 0.15174627304077148,
|
351 |
+
"logits/rejected": 0.15548208355903625,
|
352 |
+
"logps/chosen": -301.86090087890625,
|
353 |
+
"logps/rejected": -324.1502380371094,
|
354 |
+
"loss": 0.2128,
|
355 |
+
"rewards/accuracies": 0.33125001192092896,
|
356 |
+
"rewards/chosen": -0.00383182754740119,
|
357 |
+
"rewards/margins": 0.00154831912368536,
|
358 |
+
"rewards/rejected": -0.00538014667108655,
|
359 |
+
"step": 240
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.13,
|
363 |
+
"learning_rate": 4.983355127818882e-06,
|
364 |
+
"logits/chosen": 0.1338830292224884,
|
365 |
+
"logits/rejected": 0.126266211271286,
|
366 |
+
"logps/chosen": -244.6050262451172,
|
367 |
+
"logps/rejected": -272.59906005859375,
|
368 |
+
"loss": 0.2059,
|
369 |
+
"rewards/accuracies": 0.2750000059604645,
|
370 |
+
"rewards/chosen": -0.002967983018606901,
|
371 |
+
"rewards/margins": 0.00032762493356131017,
|
372 |
+
"rewards/rejected": -0.00329560786485672,
|
373 |
+
"step": 250
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.14,
|
377 |
+
"learning_rate": 4.977561498345639e-06,
|
378 |
+
"logits/chosen": 0.14223454892635345,
|
379 |
+
"logits/rejected": 0.11773631721735,
|
380 |
+
"logps/chosen": -312.8759460449219,
|
381 |
+
"logps/rejected": -332.5674743652344,
|
382 |
+
"loss": 0.2178,
|
383 |
+
"rewards/accuracies": 0.3499999940395355,
|
384 |
+
"rewards/chosen": -0.002887751441448927,
|
385 |
+
"rewards/margins": 0.002338848076760769,
|
386 |
+
"rewards/rejected": -0.005226599983870983,
|
387 |
+
"step": 260
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.14,
|
391 |
+
"learning_rate": 4.970908694186624e-06,
|
392 |
+
"logits/chosen": 0.054258234798908234,
|
393 |
+
"logits/rejected": 0.049981165677309036,
|
394 |
+
"logps/chosen": -252.06396484375,
|
395 |
+
"logps/rejected": -297.46844482421875,
|
396 |
+
"loss": 0.2038,
|
397 |
+
"rewards/accuracies": 0.375,
|
398 |
+
"rewards/chosen": -0.003387606469914317,
|
399 |
+
"rewards/margins": 0.004537281580269337,
|
400 |
+
"rewards/rejected": -0.007924887351691723,
|
401 |
+
"step": 270
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.15,
|
405 |
+
"learning_rate": 4.9633990224171305e-06,
|
406 |
+
"logits/chosen": -0.030563954263925552,
|
407 |
+
"logits/rejected": 0.0610717348754406,
|
408 |
+
"logps/chosen": -299.67572021484375,
|
409 |
+
"logps/rejected": -325.629638671875,
|
410 |
+
"loss": 0.2046,
|
411 |
+
"rewards/accuracies": 0.3125,
|
412 |
+
"rewards/chosen": -0.015065389685332775,
|
413 |
+
"rewards/margins": 0.004181383643299341,
|
414 |
+
"rewards/rejected": -0.019246775656938553,
|
415 |
+
"step": 280
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.15,
|
419 |
+
"learning_rate": 4.955035087259046e-06,
|
420 |
+
"logits/chosen": 0.021658485755324364,
|
421 |
+
"logits/rejected": 0.0002574294921942055,
|
422 |
+
"logps/chosen": -279.9824523925781,
|
423 |
+
"logps/rejected": -308.2466125488281,
|
424 |
+
"loss": 0.2082,
|
425 |
+
"rewards/accuracies": 0.35624998807907104,
|
426 |
+
"rewards/chosen": -0.0099684102460742,
|
427 |
+
"rewards/margins": 0.003934068605303764,
|
428 |
+
"rewards/rejected": -0.013902479782700539,
|
429 |
+
"step": 290
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.16,
|
433 |
+
"learning_rate": 4.945819789177756e-06,
|
434 |
+
"logits/chosen": -0.02307768724858761,
|
435 |
+
"logits/rejected": 0.027991438284516335,
|
436 |
+
"logps/chosen": -297.05120849609375,
|
437 |
+
"logps/rejected": -306.86993408203125,
|
438 |
+
"loss": 0.214,
|
439 |
+
"rewards/accuracies": 0.3187499940395355,
|
440 |
+
"rewards/chosen": -0.003176984842866659,
|
441 |
+
"rewards/margins": 0.0040995096787810326,
|
442 |
+
"rewards/rejected": -0.00727649312466383,
|
443 |
+
"step": 300
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.17,
|
447 |
+
"learning_rate": 4.935756323876306e-06,
|
448 |
+
"logits/chosen": -0.04134337604045868,
|
449 |
+
"logits/rejected": -0.06087446212768555,
|
450 |
+
"logps/chosen": -291.1628723144531,
|
451 |
+
"logps/rejected": -304.87701416015625,
|
452 |
+
"loss": 0.2055,
|
453 |
+
"rewards/accuracies": 0.3125,
|
454 |
+
"rewards/chosen": -0.0040726205334067345,
|
455 |
+
"rewards/margins": 0.005008176900446415,
|
456 |
+
"rewards/rejected": -0.009080798365175724,
|
457 |
+
"step": 310
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.17,
|
461 |
+
"learning_rate": 4.924848181187199e-06,
|
462 |
+
"logits/chosen": -0.08453729003667831,
|
463 |
+
"logits/rejected": -0.09256991744041443,
|
464 |
+
"logps/chosen": -261.996337890625,
|
465 |
+
"logps/rejected": -302.02056884765625,
|
466 |
+
"loss": 0.204,
|
467 |
+
"rewards/accuracies": 0.3125,
|
468 |
+
"rewards/chosen": -0.00689683947712183,
|
469 |
+
"rewards/margins": 0.011717710644006729,
|
470 |
+
"rewards/rejected": -0.018614551052451134,
|
471 |
+
"step": 320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.18,
|
475 |
+
"learning_rate": 4.913099143862173e-06,
|
476 |
+
"logits/chosen": -0.1567036509513855,
|
477 |
+
"logits/rejected": -0.11430159956216812,
|
478 |
+
"logps/chosen": -293.12091064453125,
|
479 |
+
"logps/rejected": -317.5729064941406,
|
480 |
+
"loss": 0.1985,
|
481 |
+
"rewards/accuracies": 0.30000001192092896,
|
482 |
+
"rewards/chosen": -0.014261825010180473,
|
483 |
+
"rewards/margins": 0.005913619417697191,
|
484 |
+
"rewards/rejected": -0.020175445824861526,
|
485 |
+
"step": 330
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.18,
|
489 |
+
"learning_rate": 4.900513286260416e-06,
|
490 |
+
"logits/chosen": -0.1313917338848114,
|
491 |
+
"logits/rejected": -0.13553771376609802,
|
492 |
+
"logps/chosen": -293.6689758300781,
|
493 |
+
"logps/rejected": -307.853271484375,
|
494 |
+
"loss": 0.2022,
|
495 |
+
"rewards/accuracies": 0.30000001192092896,
|
496 |
+
"rewards/chosen": -0.00804301630705595,
|
497 |
+
"rewards/margins": 0.005196637008339167,
|
498 |
+
"rewards/rejected": -0.013239651918411255,
|
499 |
+
"step": 340
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.19,
|
503 |
+
"learning_rate": 4.887094972935645e-06,
|
504 |
+
"logits/chosen": -0.11833436787128448,
|
505 |
+
"logits/rejected": -0.11948303878307343,
|
506 |
+
"logps/chosen": -305.84649658203125,
|
507 |
+
"logps/rejected": -327.93115234375,
|
508 |
+
"loss": 0.199,
|
509 |
+
"rewards/accuracies": 0.30000001192092896,
|
510 |
+
"rewards/chosen": 0.005626929923892021,
|
511 |
+
"rewards/margins": 0.005307743325829506,
|
512 |
+
"rewards/rejected": 0.0003191869764123112,
|
513 |
+
"step": 350
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.19,
|
517 |
+
"learning_rate": 4.87284885712256e-06,
|
518 |
+
"logits/chosen": -0.1287965327501297,
|
519 |
+
"logits/rejected": -0.07743237912654877,
|
520 |
+
"logps/chosen": -305.2966613769531,
|
521 |
+
"logps/rejected": -322.216064453125,
|
522 |
+
"loss": 0.2042,
|
523 |
+
"rewards/accuracies": 0.2874999940395355,
|
524 |
+
"rewards/chosen": 0.013340242207050323,
|
525 |
+
"rewards/margins": 0.006324528716504574,
|
526 |
+
"rewards/rejected": 0.007015712559223175,
|
527 |
+
"step": 360
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.2,
|
531 |
+
"learning_rate": 4.857779879123181e-06,
|
532 |
+
"logits/chosen": -0.13824257254600525,
|
533 |
+
"logits/rejected": -0.17385557293891907,
|
534 |
+
"logps/chosen": -271.77142333984375,
|
535 |
+
"logps/rejected": -285.82611083984375,
|
536 |
+
"loss": 0.2166,
|
537 |
+
"rewards/accuracies": 0.30000001192092896,
|
538 |
+
"rewards/chosen": 0.012355504557490349,
|
539 |
+
"rewards/margins": 0.004869457334280014,
|
540 |
+
"rewards/rejected": 0.0074860467575490475,
|
541 |
+
"step": 370
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.2,
|
545 |
+
"learning_rate": 4.841893264593643e-06,
|
546 |
+
"logits/chosen": -0.1971556842327118,
|
547 |
+
"logits/rejected": -0.14368289709091187,
|
548 |
+
"logps/chosen": -289.67315673828125,
|
549 |
+
"logps/rejected": -294.14239501953125,
|
550 |
+
"loss": 0.2142,
|
551 |
+
"rewards/accuracies": 0.2750000059604645,
|
552 |
+
"rewards/chosen": 0.014088312163949013,
|
553 |
+
"rewards/margins": 0.0018969494849443436,
|
554 |
+
"rewards/rejected": 0.01219136081635952,
|
555 |
+
"step": 380
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.21,
|
559 |
+
"learning_rate": 4.825194522732023e-06,
|
560 |
+
"logits/chosen": -0.15685835480690002,
|
561 |
+
"logits/rejected": -0.14415477216243744,
|
562 |
+
"logps/chosen": -258.82476806640625,
|
563 |
+
"logps/rejected": -279.218505859375,
|
564 |
+
"loss": 0.2035,
|
565 |
+
"rewards/accuracies": 0.29374998807907104,
|
566 |
+
"rewards/chosen": 0.012283021584153175,
|
567 |
+
"rewards/margins": 0.007540999446064234,
|
568 |
+
"rewards/rejected": 0.004742022603750229,
|
569 |
+
"step": 390
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.21,
|
573 |
+
"learning_rate": 4.807689444367853e-06,
|
574 |
+
"logits/chosen": -0.10798895359039307,
|
575 |
+
"logits/rejected": -0.06372461467981339,
|
576 |
+
"logps/chosen": -314.35968017578125,
|
577 |
+
"logps/rejected": -325.0350036621094,
|
578 |
+
"loss": 0.2124,
|
579 |
+
"rewards/accuracies": 0.36250001192092896,
|
580 |
+
"rewards/chosen": 0.015810634940862656,
|
581 |
+
"rewards/margins": 0.0051138391718268394,
|
582 |
+
"rewards/rejected": 0.01069679670035839,
|
583 |
+
"step": 400
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.22,
|
587 |
+
"learning_rate": 4.78938409995396e-06,
|
588 |
+
"logits/chosen": -0.12151198089122772,
|
589 |
+
"logits/rejected": -0.1099950298666954,
|
590 |
+
"logps/chosen": -265.03253173828125,
|
591 |
+
"logps/rejected": -293.6728210449219,
|
592 |
+
"loss": 0.2046,
|
593 |
+
"rewards/accuracies": 0.28125,
|
594 |
+
"rewards/chosen": 0.008226810023188591,
|
595 |
+
"rewards/margins": 0.003223727224394679,
|
596 |
+
"rewards/rejected": 0.005003082565963268,
|
597 |
+
"step": 410
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.22,
|
601 |
+
"learning_rate": 4.770284837461342e-06,
|
602 |
+
"logits/chosen": -0.09874553233385086,
|
603 |
+
"logits/rejected": -0.10907171666622162,
|
604 |
+
"logps/chosen": -299.97259521484375,
|
605 |
+
"logps/rejected": -309.26495361328125,
|
606 |
+
"loss": 0.2047,
|
607 |
+
"rewards/accuracies": 0.30000001192092896,
|
608 |
+
"rewards/chosen": 0.009101228788495064,
|
609 |
+
"rewards/margins": 0.0020746844820678234,
|
610 |
+
"rewards/rejected": 0.00702654430642724,
|
611 |
+
"step": 420
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.23,
|
615 |
+
"learning_rate": 4.7503982801778015e-06,
|
616 |
+
"logits/chosen": -0.09576672315597534,
|
617 |
+
"logits/rejected": -0.08475270867347717,
|
618 |
+
"logps/chosen": -258.3625793457031,
|
619 |
+
"logps/rejected": -288.2427673339844,
|
620 |
+
"loss": 0.2207,
|
621 |
+
"rewards/accuracies": 0.28125,
|
622 |
+
"rewards/chosen": 0.013314478099346161,
|
623 |
+
"rewards/margins": 0.005582061596214771,
|
624 |
+
"rewards/rejected": 0.00773241650313139,
|
625 |
+
"step": 430
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.23,
|
629 |
+
"learning_rate": 4.729731324411104e-06,
|
630 |
+
"logits/chosen": -0.11287762224674225,
|
631 |
+
"logits/rejected": -0.1189860925078392,
|
632 |
+
"logps/chosen": -269.3243713378906,
|
633 |
+
"logps/rejected": -290.4499206542969,
|
634 |
+
"loss": 0.2115,
|
635 |
+
"rewards/accuracies": 0.32499998807907104,
|
636 |
+
"rewards/chosen": 0.006840028800070286,
|
637 |
+
"rewards/margins": 0.003011752385646105,
|
638 |
+
"rewards/rejected": 0.0038282759487628937,
|
639 |
+
"step": 440
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.24,
|
643 |
+
"learning_rate": 4.7082911370974645e-06,
|
644 |
+
"logits/chosen": -0.06270084530115128,
|
645 |
+
"logits/rejected": -0.11760212481021881,
|
646 |
+
"logps/chosen": -266.041259765625,
|
647 |
+
"logps/rejected": -278.55743408203125,
|
648 |
+
"loss": 0.219,
|
649 |
+
"rewards/accuracies": 0.28125,
|
650 |
+
"rewards/chosen": 0.014174575917422771,
|
651 |
+
"rewards/margins": 0.0036397804506123066,
|
652 |
+
"rewards/rejected": 0.010534795001149178,
|
653 |
+
"step": 450
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.25,
|
657 |
+
"learning_rate": 4.68608515331618e-06,
|
658 |
+
"logits/chosen": -0.08950970321893692,
|
659 |
+
"logits/rejected": -0.12192481756210327,
|
660 |
+
"logps/chosen": -220.92153930664062,
|
661 |
+
"logps/rejected": -227.0800018310547,
|
662 |
+
"loss": 0.2105,
|
663 |
+
"rewards/accuracies": 0.2562499940395355,
|
664 |
+
"rewards/chosen": 0.00980322528630495,
|
665 |
+
"rewards/margins": 0.003905829042196274,
|
666 |
+
"rewards/rejected": 0.005897396244108677,
|
667 |
+
"step": 460
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.25,
|
671 |
+
"learning_rate": 4.663121073711269e-06,
|
672 |
+
"logits/chosen": -0.14287583529949188,
|
673 |
+
"logits/rejected": -0.11475469172000885,
|
674 |
+
"logps/chosen": -249.2185821533203,
|
675 |
+
"logps/rejected": -269.6126708984375,
|
676 |
+
"loss": 0.224,
|
677 |
+
"rewards/accuracies": 0.3187499940395355,
|
678 |
+
"rewards/chosen": 0.009408132173120975,
|
679 |
+
"rewards/margins": 0.007567667867988348,
|
680 |
+
"rewards/rejected": 0.0018404644215479493,
|
681 |
+
"step": 470
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.26,
|
685 |
+
"learning_rate": 4.63940686182103e-06,
|
686 |
+
"logits/chosen": -0.13410678505897522,
|
687 |
+
"logits/rejected": -0.1070268377661705,
|
688 |
+
"logps/chosen": -276.46856689453125,
|
689 |
+
"logps/rejected": -310.9843444824219,
|
690 |
+
"loss": 0.2096,
|
691 |
+
"rewards/accuracies": 0.3499999940395355,
|
692 |
+
"rewards/chosen": 0.0070691583678126335,
|
693 |
+
"rewards/margins": 0.010405855253338814,
|
694 |
+
"rewards/rejected": -0.003336697118356824,
|
695 |
+
"step": 480
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.26,
|
699 |
+
"learning_rate": 4.614950741316425e-06,
|
700 |
+
"logits/chosen": -0.21566160023212433,
|
701 |
+
"logits/rejected": -0.18181584775447845,
|
702 |
+
"logps/chosen": -219.1405487060547,
|
703 |
+
"logps/rejected": -248.4638671875,
|
704 |
+
"loss": 0.1972,
|
705 |
+
"rewards/accuracies": 0.26249998807907104,
|
706 |
+
"rewards/chosen": 0.007403376046568155,
|
707 |
+
"rewards/margins": 0.004462541546672583,
|
708 |
+
"rewards/rejected": 0.0029408347327262163,
|
709 |
+
"step": 490
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.27,
|
713 |
+
"learning_rate": 4.589761193149254e-06,
|
714 |
+
"logits/chosen": -0.17594993114471436,
|
715 |
+
"logits/rejected": -0.1787882298231125,
|
716 |
+
"logps/chosen": -248.833251953125,
|
717 |
+
"logps/rejected": -265.1255798339844,
|
718 |
+
"loss": 0.2058,
|
719 |
+
"rewards/accuracies": 0.28125,
|
720 |
+
"rewards/chosen": 0.005866335239261389,
|
721 |
+
"rewards/margins": 0.008035833016037941,
|
722 |
+
"rewards/rejected": -0.002169497776776552,
|
723 |
+
"step": 500
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.27,
|
727 |
+
"learning_rate": 4.563846952611112e-06,
|
728 |
+
"logits/chosen": -0.2459220141172409,
|
729 |
+
"logits/rejected": -0.21481938660144806,
|
730 |
+
"logps/chosen": -290.0213623046875,
|
731 |
+
"logps/rejected": -324.1817321777344,
|
732 |
+
"loss": 0.1908,
|
733 |
+
"rewards/accuracies": 0.3499999940395355,
|
734 |
+
"rewards/chosen": 0.0015872556250542402,
|
735 |
+
"rewards/margins": 0.011338635347783566,
|
736 |
+
"rewards/rejected": -0.009751381352543831,
|
737 |
+
"step": 510
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.28,
|
741 |
+
"learning_rate": 4.537217006304141e-06,
|
742 |
+
"logits/chosen": -0.22694924473762512,
|
743 |
+
"logits/rejected": -0.22461485862731934,
|
744 |
+
"logps/chosen": -272.0402526855469,
|
745 |
+
"logps/rejected": -286.1138916015625,
|
746 |
+
"loss": 0.2185,
|
747 |
+
"rewards/accuracies": 0.26875001192092896,
|
748 |
+
"rewards/chosen": -1.9139843061566353e-05,
|
749 |
+
"rewards/margins": 0.00025601504603400826,
|
750 |
+
"rewards/rejected": -0.00027515500551089644,
|
751 |
+
"step": 520
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.28,
|
755 |
+
"learning_rate": 4.50988058902464e-06,
|
756 |
+
"logits/chosen": -0.2873474061489105,
|
757 |
+
"logits/rejected": -0.24353663623332977,
|
758 |
+
"logps/chosen": -319.0919189453125,
|
759 |
+
"logps/rejected": -352.68621826171875,
|
760 |
+
"loss": 0.2102,
|
761 |
+
"rewards/accuracies": 0.3375000059604645,
|
762 |
+
"rewards/chosen": 0.011865551583468914,
|
763 |
+
"rewards/margins": 0.006343546323478222,
|
764 |
+
"rewards/rejected": 0.005522005259990692,
|
765 |
+
"step": 530
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.29,
|
769 |
+
"learning_rate": 4.481847180560593e-06,
|
770 |
+
"logits/chosen": -0.2149961292743683,
|
771 |
+
"logits/rejected": -0.22789709270000458,
|
772 |
+
"logps/chosen": -286.41851806640625,
|
773 |
+
"logps/rejected": -297.98248291015625,
|
774 |
+
"loss": 0.2049,
|
775 |
+
"rewards/accuracies": 0.30000001192092896,
|
776 |
+
"rewards/chosen": 0.010984813794493675,
|
777 |
+
"rewards/margins": 0.0014541022246703506,
|
778 |
+
"rewards/rejected": 0.009530710987746716,
|
779 |
+
"step": 540
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.29,
|
783 |
+
"learning_rate": 4.453126502404253e-06,
|
784 |
+
"logits/chosen": -0.2241373062133789,
|
785 |
+
"logits/rejected": -0.1860576570034027,
|
786 |
+
"logps/chosen": -279.4507141113281,
|
787 |
+
"logps/rejected": -281.85516357421875,
|
788 |
+
"loss": 0.2199,
|
789 |
+
"rewards/accuracies": 0.32499998807907104,
|
790 |
+
"rewards/chosen": 0.020039092749357224,
|
791 |
+
"rewards/margins": 0.0005937496898695827,
|
792 |
+
"rewards/rejected": 0.019445344805717468,
|
793 |
+
"step": 550
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.3,
|
797 |
+
"learning_rate": 4.423728514380892e-06,
|
798 |
+
"logits/chosen": -0.18391680717468262,
|
799 |
+
"logits/rejected": -0.162066251039505,
|
800 |
+
"logps/chosen": -269.0604248046875,
|
801 |
+
"logps/rejected": -299.13055419921875,
|
802 |
+
"loss": 0.1967,
|
803 |
+
"rewards/accuracies": 0.33125001192092896,
|
804 |
+
"rewards/chosen": 0.025296321138739586,
|
805 |
+
"rewards/margins": 0.006020676344633102,
|
806 |
+
"rewards/rejected": 0.019275646656751633,
|
807 |
+
"step": 560
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.3,
|
811 |
+
"learning_rate": 4.393663411194918e-06,
|
812 |
+
"logits/chosen": -0.15143278241157532,
|
813 |
+
"logits/rejected": -0.1272958219051361,
|
814 |
+
"logps/chosen": -275.3654479980469,
|
815 |
+
"logps/rejected": -332.71636962890625,
|
816 |
+
"loss": 0.2102,
|
817 |
+
"rewards/accuracies": 0.3375000059604645,
|
818 |
+
"rewards/chosen": 0.024300305172801018,
|
819 |
+
"rewards/margins": 0.006145091727375984,
|
820 |
+
"rewards/rejected": 0.018155213445425034,
|
821 |
+
"step": 570
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.31,
|
825 |
+
"learning_rate": 4.362941618894523e-06,
|
826 |
+
"logits/chosen": -0.24861934781074524,
|
827 |
+
"logits/rejected": -0.21499958634376526,
|
828 |
+
"logps/chosen": -242.86181640625,
|
829 |
+
"logps/rejected": -256.13409423828125,
|
830 |
+
"loss": 0.2059,
|
831 |
+
"rewards/accuracies": 0.26875001192092896,
|
832 |
+
"rewards/chosen": 0.01787170208990574,
|
833 |
+
"rewards/margins": 0.002406838582828641,
|
834 |
+
"rewards/rejected": 0.015464862808585167,
|
835 |
+
"step": 580
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.31,
|
839 |
+
"learning_rate": 4.331573791256116e-06,
|
840 |
+
"logits/chosen": -0.24243931472301483,
|
841 |
+
"logits/rejected": -0.20876605808734894,
|
842 |
+
"logps/chosen": -222.46432495117188,
|
843 |
+
"logps/rejected": -240.7364044189453,
|
844 |
+
"loss": 0.2187,
|
845 |
+
"rewards/accuracies": 0.2874999940395355,
|
846 |
+
"rewards/chosen": 0.02379140630364418,
|
847 |
+
"rewards/margins": 0.004867316223680973,
|
848 |
+
"rewards/rejected": 0.018924091011285782,
|
849 |
+
"step": 590
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.32,
|
853 |
+
"learning_rate": 4.299570806089786e-06,
|
854 |
+
"logits/chosen": -0.25369709730148315,
|
855 |
+
"logits/rejected": -0.26770374178886414,
|
856 |
+
"logps/chosen": -262.30889892578125,
|
857 |
+
"logps/rejected": -301.822998046875,
|
858 |
+
"loss": 0.2092,
|
859 |
+
"rewards/accuracies": 0.3499999940395355,
|
860 |
+
"rewards/chosen": 0.024355897679924965,
|
861 |
+
"rewards/margins": 0.008627799339592457,
|
862 |
+
"rewards/rejected": 0.015728099271655083,
|
863 |
+
"step": 600
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.33,
|
867 |
+
"learning_rate": 4.266943761467057e-06,
|
868 |
+
"logits/chosen": -0.278990775346756,
|
869 |
+
"logits/rejected": -0.23303751647472382,
|
870 |
+
"logps/chosen": -281.37811279296875,
|
871 |
+
"logps/rejected": -289.0556945800781,
|
872 |
+
"loss": 0.1924,
|
873 |
+
"rewards/accuracies": 0.30000001192092896,
|
874 |
+
"rewards/chosen": 0.028277212753891945,
|
875 |
+
"rewards/margins": 0.003026631660759449,
|
876 |
+
"rewards/rejected": 0.02525058388710022,
|
877 |
+
"step": 610
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.33,
|
881 |
+
"learning_rate": 4.233703971872287e-06,
|
882 |
+
"logits/chosen": -0.2651432752609253,
|
883 |
+
"logits/rejected": -0.23803620040416718,
|
884 |
+
"logps/chosen": -274.52972412109375,
|
885 |
+
"logps/rejected": -284.91864013671875,
|
886 |
+
"loss": 0.2075,
|
887 |
+
"rewards/accuracies": 0.30000001192092896,
|
888 |
+
"rewards/chosen": 0.029297566041350365,
|
889 |
+
"rewards/margins": 0.0042782137170434,
|
890 |
+
"rewards/rejected": 0.02501935325562954,
|
891 |
+
"step": 620
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.34,
|
895 |
+
"learning_rate": 4.1998629642789925e-06,
|
896 |
+
"logits/chosen": -0.2681610584259033,
|
897 |
+
"logits/rejected": -0.2098967581987381,
|
898 |
+
"logps/chosen": -273.29522705078125,
|
899 |
+
"logps/rejected": -307.06207275390625,
|
900 |
+
"loss": 0.2109,
|
901 |
+
"rewards/accuracies": 0.35624998807907104,
|
902 |
+
"rewards/chosen": 0.026482801884412766,
|
903 |
+
"rewards/margins": 0.008065291680395603,
|
904 |
+
"rewards/rejected": 0.018417512997984886,
|
905 |
+
"step": 630
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.34,
|
909 |
+
"learning_rate": 4.165432474152505e-06,
|
910 |
+
"logits/chosen": -0.2867113947868347,
|
911 |
+
"logits/rejected": -0.3026007413864136,
|
912 |
+
"logps/chosen": -258.7665100097656,
|
913 |
+
"logps/rejected": -276.9542541503906,
|
914 |
+
"loss": 0.1981,
|
915 |
+
"rewards/accuracies": 0.30000001192092896,
|
916 |
+
"rewards/chosen": 0.03178761154413223,
|
917 |
+
"rewards/margins": 0.0078035155311226845,
|
918 |
+
"rewards/rejected": 0.023984093219041824,
|
919 |
+
"step": 640
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.35,
|
923 |
+
"learning_rate": 4.130424441380308e-06,
|
924 |
+
"logits/chosen": -0.3068264424800873,
|
925 |
+
"logits/rejected": -0.2953132390975952,
|
926 |
+
"logps/chosen": -278.3927001953125,
|
927 |
+
"logps/rejected": -294.95611572265625,
|
928 |
+
"loss": 0.2182,
|
929 |
+
"rewards/accuracies": 0.29374998807907104,
|
930 |
+
"rewards/chosen": 0.024625886231660843,
|
931 |
+
"rewards/margins": 0.0047270385548472404,
|
932 |
+
"rewards/rejected": 0.019898848608136177,
|
933 |
+
"step": 650
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.35,
|
937 |
+
"learning_rate": 4.09485100613151e-06,
|
938 |
+
"logits/chosen": -0.3508884310722351,
|
939 |
+
"logits/rejected": -0.3666234314441681,
|
940 |
+
"logps/chosen": -255.5622100830078,
|
941 |
+
"logps/rejected": -267.3009033203125,
|
942 |
+
"loss": 0.2199,
|
943 |
+
"rewards/accuracies": 0.3125,
|
944 |
+
"rewards/chosen": 0.025408515706658363,
|
945 |
+
"rewards/margins": 0.0033288276754319668,
|
946 |
+
"rewards/rejected": 0.02207968756556511,
|
947 |
+
"step": 660
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.36,
|
951 |
+
"learning_rate": 4.058724504646834e-06,
|
952 |
+
"logits/chosen": -0.27611714601516724,
|
953 |
+
"logits/rejected": -0.2742993235588074,
|
954 |
+
"logps/chosen": -255.03402709960938,
|
955 |
+
"logps/rejected": -279.2400207519531,
|
956 |
+
"loss": 0.1928,
|
957 |
+
"rewards/accuracies": 0.3125,
|
958 |
+
"rewards/chosen": 0.026569899171590805,
|
959 |
+
"rewards/margins": 0.006919047329574823,
|
960 |
+
"rewards/rejected": 0.01965085044503212,
|
961 |
+
"step": 670
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.36,
|
965 |
+
"learning_rate": 4.022057464960632e-06,
|
966 |
+
"logits/chosen": -0.29631996154785156,
|
967 |
+
"logits/rejected": -0.3354335427284241,
|
968 |
+
"logps/chosen": -224.5742645263672,
|
969 |
+
"logps/rejected": -251.43563842773438,
|
970 |
+
"loss": 0.2081,
|
971 |
+
"rewards/accuracies": 0.29374998807907104,
|
972 |
+
"rewards/chosen": 0.02301851287484169,
|
973 |
+
"rewards/margins": 0.00754903256893158,
|
974 |
+
"rewards/rejected": 0.015469479374587536,
|
975 |
+
"step": 680
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.37,
|
979 |
+
"learning_rate": 3.984862602556383e-06,
|
980 |
+
"logits/chosen": -0.3194465637207031,
|
981 |
+
"logits/rejected": -0.2741653025150299,
|
982 |
+
"logps/chosen": -292.7205505371094,
|
983 |
+
"logps/rejected": -280.698486328125,
|
984 |
+
"loss": 0.2113,
|
985 |
+
"rewards/accuracies": 0.24375000596046448,
|
986 |
+
"rewards/chosen": 0.01744149625301361,
|
987 |
+
"rewards/margins": -0.002081270096823573,
|
988 |
+
"rewards/rejected": 0.019522765651345253,
|
989 |
+
"step": 690
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.37,
|
993 |
+
"learning_rate": 3.947152815957187e-06,
|
994 |
+
"logits/chosen": -0.3113805949687958,
|
995 |
+
"logits/rejected": -0.27869972586631775,
|
996 |
+
"logps/chosen": -267.34503173828125,
|
997 |
+
"logps/rejected": -260.38397216796875,
|
998 |
+
"loss": 0.2177,
|
999 |
+
"rewards/accuracies": 0.3187499940395355,
|
1000 |
+
"rewards/chosen": 0.03015447035431862,
|
1001 |
+
"rewards/margins": 0.002841535024344921,
|
1002 |
+
"rewards/rejected": 0.027312934398651123,
|
1003 |
+
"step": 700
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.38,
|
1007 |
+
"learning_rate": 3.908941182252785e-06,
|
1008 |
+
"logits/chosen": -0.2623198926448822,
|
1009 |
+
"logits/rejected": -0.2412450760602951,
|
1010 |
+
"logps/chosen": -268.50933837890625,
|
1011 |
+
"logps/rejected": -307.6174621582031,
|
1012 |
+
"loss": 0.1982,
|
1013 |
+
"rewards/accuracies": 0.30000001192092896,
|
1014 |
+
"rewards/chosen": 0.025938820093870163,
|
1015 |
+
"rewards/margins": 0.005723121576011181,
|
1016 |
+
"rewards/rejected": 0.020215699449181557,
|
1017 |
+
"step": 710
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.38,
|
1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
1022 |
+
"logits/chosen": -0.26187169551849365,
|
1023 |
+
"logits/rejected": -0.2671493887901306,
|
1024 |
+
"logps/chosen": -234.5527801513672,
|
1025 |
+
"logps/rejected": -276.95465087890625,
|
1026 |
+
"loss": 0.2124,
|
1027 |
+
"rewards/accuracies": 0.33125001192092896,
|
1028 |
+
"rewards/chosen": 0.02780374325811863,
|
1029 |
+
"rewards/margins": 0.00728409830480814,
|
1030 |
+
"rewards/rejected": 0.020519645884633064,
|
1031 |
+
"step": 720
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.39,
|
1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
1036 |
+
"logits/chosen": -0.31342610716819763,
|
1037 |
+
"logits/rejected": -0.3103486895561218,
|
1038 |
+
"logps/chosen": -272.54730224609375,
|
1039 |
+
"logps/rejected": -289.4356384277344,
|
1040 |
+
"loss": 0.1874,
|
1041 |
+
"rewards/accuracies": 0.34375,
|
1042 |
+
"rewards/chosen": 0.025291483849287033,
|
1043 |
+
"rewards/margins": 0.0070581152103841305,
|
1044 |
+
"rewards/rejected": 0.018233366310596466,
|
1045 |
+
"step": 730
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.39,
|
1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
1050 |
+
"logits/chosen": -0.31440383195877075,
|
1051 |
+
"logits/rejected": -0.32669904828071594,
|
1052 |
+
"logps/chosen": -278.309814453125,
|
1053 |
+
"logps/rejected": -316.8228759765625,
|
1054 |
+
"loss": 0.202,
|
1055 |
+
"rewards/accuracies": 0.40625,
|
1056 |
+
"rewards/chosen": 0.032375235110521317,
|
1057 |
+
"rewards/margins": 0.007661235518753529,
|
1058 |
+
"rewards/rejected": 0.024713998660445213,
|
1059 |
+
"step": 740
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.4,
|
1063 |
+
"learning_rate": 3.751343712378639e-06,
|
1064 |
+
"logits/chosen": -0.3353944420814514,
|
1065 |
+
"logits/rejected": -0.3212040364742279,
|
1066 |
+
"logps/chosen": -254.7311553955078,
|
1067 |
+
"logps/rejected": -263.9468994140625,
|
1068 |
+
"loss": 0.2265,
|
1069 |
+
"rewards/accuracies": 0.2874999940395355,
|
1070 |
+
"rewards/chosen": 0.020177539438009262,
|
1071 |
+
"rewards/margins": 0.003813125193119049,
|
1072 |
+
"rewards/rejected": 0.016364412382245064,
|
1073 |
+
"step": 750
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.41,
|
1077 |
+
"learning_rate": 3.710824928548546e-06,
|
1078 |
+
"logits/chosen": -0.4110103249549866,
|
1079 |
+
"logits/rejected": -0.38202887773513794,
|
1080 |
+
"logps/chosen": -304.6473693847656,
|
1081 |
+
"logps/rejected": -348.3372802734375,
|
1082 |
+
"loss": 0.204,
|
1083 |
+
"rewards/accuracies": 0.36250001192092896,
|
1084 |
+
"rewards/chosen": 0.028538638725876808,
|
1085 |
+
"rewards/margins": 0.008010391145944595,
|
1086 |
+
"rewards/rejected": 0.020528245717287064,
|
1087 |
+
"step": 760
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.41,
|
1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
1092 |
+
"logits/chosen": -0.37583234906196594,
|
1093 |
+
"logits/rejected": -0.39775121212005615,
|
1094 |
+
"logps/chosen": -250.30337524414062,
|
1095 |
+
"logps/rejected": -283.32464599609375,
|
1096 |
+
"loss": 0.198,
|
1097 |
+
"rewards/accuracies": 0.29374998807907104,
|
1098 |
+
"rewards/chosen": 0.023627078160643578,
|
1099 |
+
"rewards/margins": 0.008884016424417496,
|
1100 |
+
"rewards/rejected": 0.014743062667548656,
|
1101 |
+
"step": 770
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.42,
|
1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
1106 |
+
"logits/chosen": -0.40414610505104065,
|
1107 |
+
"logits/rejected": -0.37960129976272583,
|
1108 |
+
"logps/chosen": -300.35296630859375,
|
1109 |
+
"logps/rejected": -304.61834716796875,
|
1110 |
+
"loss": 0.215,
|
1111 |
+
"rewards/accuracies": 0.32499998807907104,
|
1112 |
+
"rewards/chosen": 0.021693145856261253,
|
1113 |
+
"rewards/margins": 0.002025413792580366,
|
1114 |
+
"rewards/rejected": 0.01966773346066475,
|
1115 |
+
"step": 780
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.42,
|
1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
1120 |
+
"logits/chosen": -0.3469582498073578,
|
1121 |
+
"logits/rejected": -0.2765125632286072,
|
1122 |
+
"logps/chosen": -248.47525024414062,
|
1123 |
+
"logps/rejected": -262.3398132324219,
|
1124 |
+
"loss": 0.2054,
|
1125 |
+
"rewards/accuracies": 0.28125,
|
1126 |
+
"rewards/chosen": 0.023630034178495407,
|
1127 |
+
"rewards/margins": 0.006072540767490864,
|
1128 |
+
"rewards/rejected": 0.01755749061703682,
|
1129 |
+
"step": 790
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.43,
|
1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
1134 |
+
"logits/chosen": -0.31192153692245483,
|
1135 |
+
"logits/rejected": -0.3198978304862976,
|
1136 |
+
"logps/chosen": -264.4431457519531,
|
1137 |
+
"logps/rejected": -276.5923156738281,
|
1138 |
+
"loss": 0.1997,
|
1139 |
+
"rewards/accuracies": 0.2874999940395355,
|
1140 |
+
"rewards/chosen": 0.019144730642437935,
|
1141 |
+
"rewards/margins": 0.007585918065160513,
|
1142 |
+
"rewards/rejected": 0.011558813974261284,
|
1143 |
+
"step": 800
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.43,
|
1147 |
+
"learning_rate": 3.502218634729447e-06,
|
1148 |
+
"logits/chosen": -0.3657092750072479,
|
1149 |
+
"logits/rejected": -0.36896997690200806,
|
1150 |
+
"logps/chosen": -285.9904479980469,
|
1151 |
+
"logps/rejected": -304.4721984863281,
|
1152 |
+
"loss": 0.2131,
|
1153 |
+
"rewards/accuracies": 0.28125,
|
1154 |
+
"rewards/chosen": 0.01876096799969673,
|
1155 |
+
"rewards/margins": 0.0027052960358560085,
|
1156 |
+
"rewards/rejected": 0.016055669635534286,
|
1157 |
+
"step": 810
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.44,
|
1161 |
+
"learning_rate": 3.459396185441265e-06,
|
1162 |
+
"logits/chosen": -0.3460562825202942,
|
1163 |
+
"logits/rejected": -0.32295316457748413,
|
1164 |
+
"logps/chosen": -223.621337890625,
|
1165 |
+
"logps/rejected": -230.530029296875,
|
1166 |
+
"loss": 0.2041,
|
1167 |
+
"rewards/accuracies": 0.28125,
|
1168 |
+
"rewards/chosen": 0.020683612674474716,
|
1169 |
+
"rewards/margins": 0.004844160284847021,
|
1170 |
+
"rewards/rejected": 0.015839453786611557,
|
1171 |
+
"step": 820
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.44,
|
1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
1176 |
+
"logits/chosen": -0.2728729844093323,
|
1177 |
+
"logits/rejected": -0.27788490056991577,
|
1178 |
+
"logps/chosen": -268.2927551269531,
|
1179 |
+
"logps/rejected": -274.38690185546875,
|
1180 |
+
"loss": 0.2068,
|
1181 |
+
"rewards/accuracies": 0.3062500059604645,
|
1182 |
+
"rewards/chosen": 0.019065286964178085,
|
1183 |
+
"rewards/margins": 0.0036661080084741116,
|
1184 |
+
"rewards/rejected": 0.015399177558720112,
|
1185 |
+
"step": 830
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.45,
|
1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
1190 |
+
"logits/chosen": -0.3043738603591919,
|
1191 |
+
"logits/rejected": -0.2903715968132019,
|
1192 |
+
"logps/chosen": -255.2548370361328,
|
1193 |
+
"logps/rejected": -280.83477783203125,
|
1194 |
+
"loss": 0.209,
|
1195 |
+
"rewards/accuracies": 0.25,
|
1196 |
+
"rewards/chosen": 0.01805216260254383,
|
1197 |
+
"rewards/margins": 0.002792063634842634,
|
1198 |
+
"rewards/rejected": 0.01526009850203991,
|
1199 |
+
"step": 840
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.45,
|
1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
1204 |
+
"logits/chosen": -0.3053690195083618,
|
1205 |
+
"logits/rejected": -0.3325154483318329,
|
1206 |
+
"logps/chosen": -249.2985382080078,
|
1207 |
+
"logps/rejected": -285.81744384765625,
|
1208 |
+
"loss": 0.209,
|
1209 |
+
"rewards/accuracies": 0.3125,
|
1210 |
+
"rewards/chosen": 0.02784855104982853,
|
1211 |
+
"rewards/margins": 0.010397961363196373,
|
1212 |
+
"rewards/rejected": 0.017450589686632156,
|
1213 |
+
"step": 850
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.46,
|
1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
1218 |
+
"logits/chosen": -0.3305487334728241,
|
1219 |
+
"logits/rejected": -0.3348706364631653,
|
1220 |
+
"logps/chosen": -256.72357177734375,
|
1221 |
+
"logps/rejected": -275.69354248046875,
|
1222 |
+
"loss": 0.195,
|
1223 |
+
"rewards/accuracies": 0.2874999940395355,
|
1224 |
+
"rewards/chosen": 0.027434032410383224,
|
1225 |
+
"rewards/margins": 0.0030927606858313084,
|
1226 |
+
"rewards/rejected": 0.024341274052858353,
|
1227 |
+
"step": 860
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.46,
|
1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
1232 |
+
"logits/chosen": -0.3463178873062134,
|
1233 |
+
"logits/rejected": -0.3138378858566284,
|
1234 |
+
"logps/chosen": -270.30596923828125,
|
1235 |
+
"logps/rejected": -297.59344482421875,
|
1236 |
+
"loss": 0.2149,
|
1237 |
+
"rewards/accuracies": 0.3375000059604645,
|
1238 |
+
"rewards/chosen": 0.02239718660712242,
|
1239 |
+
"rewards/margins": 0.007217752281576395,
|
1240 |
+
"rewards/rejected": 0.015179434791207314,
|
1241 |
+
"step": 870
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.47,
|
1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
1246 |
+
"logits/chosen": -0.3470946252346039,
|
1247 |
+
"logits/rejected": -0.2967691421508789,
|
1248 |
+
"logps/chosen": -262.6204528808594,
|
1249 |
+
"logps/rejected": -301.16021728515625,
|
1250 |
+
"loss": 0.2051,
|
1251 |
+
"rewards/accuracies": 0.26875001192092896,
|
1252 |
+
"rewards/chosen": 0.02056020125746727,
|
1253 |
+
"rewards/margins": 0.0049241771921515465,
|
1254 |
+
"rewards/rejected": 0.015636026859283447,
|
1255 |
+
"step": 880
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.47,
|
1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
1260 |
+
"logits/chosen": -0.3337462842464447,
|
1261 |
+
"logits/rejected": -0.3448733985424042,
|
1262 |
+
"logps/chosen": -290.02923583984375,
|
1263 |
+
"logps/rejected": -320.1620178222656,
|
1264 |
+
"loss": 0.2,
|
1265 |
+
"rewards/accuracies": 0.33125001192092896,
|
1266 |
+
"rewards/chosen": 0.02383309230208397,
|
1267 |
+
"rewards/margins": 0.01055764127522707,
|
1268 |
+
"rewards/rejected": 0.013275451958179474,
|
1269 |
+
"step": 890
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.48,
|
1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
1274 |
+
"logits/chosen": -0.35830608010292053,
|
1275 |
+
"logits/rejected": -0.353718101978302,
|
1276 |
+
"logps/chosen": -252.27413940429688,
|
1277 |
+
"logps/rejected": -262.99957275390625,
|
1278 |
+
"loss": 0.207,
|
1279 |
+
"rewards/accuracies": 0.30000001192092896,
|
1280 |
+
"rewards/chosen": 0.015391258522868156,
|
1281 |
+
"rewards/margins": 0.0036770054139196873,
|
1282 |
+
"rewards/rejected": 0.011714254505932331,
|
1283 |
+
"step": 900
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.49,
|
1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
1288 |
+
"logits/chosen": -0.30209046602249146,
|
1289 |
+
"logits/rejected": -0.3192787766456604,
|
1290 |
+
"logps/chosen": -286.3800354003906,
|
1291 |
+
"logps/rejected": -281.1745910644531,
|
1292 |
+
"loss": 0.2099,
|
1293 |
+
"rewards/accuracies": 0.28125,
|
1294 |
+
"rewards/chosen": 0.0164722241461277,
|
1295 |
+
"rewards/margins": 0.0019333992386236787,
|
1296 |
+
"rewards/rejected": 0.014538826420903206,
|
1297 |
+
"step": 910
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.49,
|
1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
1302 |
+
"logits/chosen": -0.2973942458629608,
|
1303 |
+
"logits/rejected": -0.3040563464164734,
|
1304 |
+
"logps/chosen": -284.22100830078125,
|
1305 |
+
"logps/rejected": -326.08551025390625,
|
1306 |
+
"loss": 0.2,
|
1307 |
+
"rewards/accuracies": 0.3499999940395355,
|
1308 |
+
"rewards/chosen": 0.019569557160139084,
|
1309 |
+
"rewards/margins": 0.011648133397102356,
|
1310 |
+
"rewards/rejected": 0.007921423763036728,
|
1311 |
+
"step": 920
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.5,
|
1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
1316 |
+
"logits/chosen": -0.3307463824748993,
|
1317 |
+
"logits/rejected": -0.2803489863872528,
|
1318 |
+
"logps/chosen": -278.6820068359375,
|
1319 |
+
"logps/rejected": -318.23333740234375,
|
1320 |
+
"loss": 0.2145,
|
1321 |
+
"rewards/accuracies": 0.3187499940395355,
|
1322 |
+
"rewards/chosen": 0.021947836503386497,
|
1323 |
+
"rewards/margins": 0.008288668468594551,
|
1324 |
+
"rewards/rejected": 0.013659171760082245,
|
1325 |
+
"step": 930
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.5,
|
1329 |
+
"learning_rate": 2.923928174004094e-06,
|
1330 |
+
"logits/chosen": -0.2774783968925476,
|
1331 |
+
"logits/rejected": -0.287009060382843,
|
1332 |
+
"logps/chosen": -306.74951171875,
|
1333 |
+
"logps/rejected": -352.70037841796875,
|
1334 |
+
"loss": 0.1975,
|
1335 |
+
"rewards/accuracies": 0.42500001192092896,
|
1336 |
+
"rewards/chosen": 0.021842315793037415,
|
1337 |
+
"rewards/margins": 0.012494521215558052,
|
1338 |
+
"rewards/rejected": 0.009347794577479362,
|
1339 |
+
"step": 940
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.51,
|
1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
1344 |
+
"logits/chosen": -0.3110584616661072,
|
1345 |
+
"logits/rejected": -0.2976732850074768,
|
1346 |
+
"logps/chosen": -263.1468505859375,
|
1347 |
+
"logps/rejected": -299.36834716796875,
|
1348 |
+
"loss": 0.2162,
|
1349 |
+
"rewards/accuracies": 0.30000001192092896,
|
1350 |
+
"rewards/chosen": 0.02124103158712387,
|
1351 |
+
"rewards/margins": 0.007206873502582312,
|
1352 |
+
"rewards/rejected": 0.014034159481525421,
|
1353 |
+
"step": 950
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.51,
|
1357 |
+
"learning_rate": 2.831892028246968e-06,
|
1358 |
+
"logits/chosen": -0.2773077189922333,
|
1359 |
+
"logits/rejected": -0.27867287397384644,
|
1360 |
+
"logps/chosen": -244.27871704101562,
|
1361 |
+
"logps/rejected": -311.6878967285156,
|
1362 |
+
"loss": 0.2025,
|
1363 |
+
"rewards/accuracies": 0.33125001192092896,
|
1364 |
+
"rewards/chosen": 0.026071447879076004,
|
1365 |
+
"rewards/margins": 0.012237906455993652,
|
1366 |
+
"rewards/rejected": 0.013833543285727501,
|
1367 |
+
"step": 960
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.52,
|
1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
1372 |
+
"logits/chosen": -0.30510154366493225,
|
1373 |
+
"logits/rejected": -0.3271741569042206,
|
1374 |
+
"logps/chosen": -284.21990966796875,
|
1375 |
+
"logps/rejected": -316.27313232421875,
|
1376 |
+
"loss": 0.2202,
|
1377 |
+
"rewards/accuracies": 0.33125001192092896,
|
1378 |
+
"rewards/chosen": 0.022279905155301094,
|
1379 |
+
"rewards/margins": 0.007268127985298634,
|
1380 |
+
"rewards/rejected": 0.015011775307357311,
|
1381 |
+
"step": 970
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.52,
|
1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
1386 |
+
"logits/chosen": -0.36560115218162537,
|
1387 |
+
"logits/rejected": -0.30673733353614807,
|
1388 |
+
"logps/chosen": -299.2345275878906,
|
1389 |
+
"logps/rejected": -282.7044982910156,
|
1390 |
+
"loss": 0.2174,
|
1391 |
+
"rewards/accuracies": 0.2562499940395355,
|
1392 |
+
"rewards/chosen": 0.01567717455327511,
|
1393 |
+
"rewards/margins": -0.0012121463660150766,
|
1394 |
+
"rewards/rejected": 0.01688932254910469,
|
1395 |
+
"step": 980
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.53,
|
1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
1400 |
+
"logits/chosen": -0.33714741468429565,
|
1401 |
+
"logits/rejected": -0.28691935539245605,
|
1402 |
+
"logps/chosen": -266.865966796875,
|
1403 |
+
"logps/rejected": -300.762939453125,
|
1404 |
+
"loss": 0.1991,
|
1405 |
+
"rewards/accuracies": 0.29374998807907104,
|
1406 |
+
"rewards/chosen": 0.0294143445789814,
|
1407 |
+
"rewards/margins": 0.008245664648711681,
|
1408 |
+
"rewards/rejected": 0.021168678998947144,
|
1409 |
+
"step": 990
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.53,
|
1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
1414 |
+
"logits/chosen": -0.2915731370449066,
|
1415 |
+
"logits/rejected": -0.24867181479930878,
|
1416 |
+
"logps/chosen": -282.2441101074219,
|
1417 |
+
"logps/rejected": -286.1959228515625,
|
1418 |
+
"loss": 0.1965,
|
1419 |
+
"rewards/accuracies": 0.3062500059604645,
|
1420 |
+
"rewards/chosen": 0.025241781026124954,
|
1421 |
+
"rewards/margins": 0.0037514586001634598,
|
1422 |
+
"rewards/rejected": 0.021490320563316345,
|
1423 |
+
"step": 1000
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.54,
|
1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
1428 |
+
"logits/chosen": -0.28083381056785583,
|
1429 |
+
"logits/rejected": -0.29559266567230225,
|
1430 |
+
"logps/chosen": -283.65484619140625,
|
1431 |
+
"logps/rejected": -310.78387451171875,
|
1432 |
+
"loss": 0.2098,
|
1433 |
+
"rewards/accuracies": 0.32499998807907104,
|
1434 |
+
"rewards/chosen": 0.028087038546800613,
|
1435 |
+
"rewards/margins": 0.0046967873349785805,
|
1436 |
+
"rewards/rejected": 0.023390252143144608,
|
1437 |
+
"step": 1010
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.54,
|
1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
1442 |
+
"logits/chosen": -0.2830182909965515,
|
1443 |
+
"logits/rejected": -0.28061428666114807,
|
1444 |
+
"logps/chosen": -273.9687194824219,
|
1445 |
+
"logps/rejected": -298.3106689453125,
|
1446 |
+
"loss": 0.2072,
|
1447 |
+
"rewards/accuracies": 0.3062500059604645,
|
1448 |
+
"rewards/chosen": 0.025423675775527954,
|
1449 |
+
"rewards/margins": 0.006900913082063198,
|
1450 |
+
"rewards/rejected": 0.018522759899497032,
|
1451 |
+
"step": 1020
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.55,
|
1455 |
+
"learning_rate": 2.506983377077741e-06,
|
1456 |
+
"logits/chosen": -0.2505617141723633,
|
1457 |
+
"logits/rejected": -0.2675876021385193,
|
1458 |
+
"logps/chosen": -269.5409851074219,
|
1459 |
+
"logps/rejected": -285.0895080566406,
|
1460 |
+
"loss": 0.205,
|
1461 |
+
"rewards/accuracies": 0.34375,
|
1462 |
+
"rewards/chosen": 0.026411527767777443,
|
1463 |
+
"rewards/margins": 0.0052161491475999355,
|
1464 |
+
"rewards/rejected": 0.02119537815451622,
|
1465 |
+
"step": 1030
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.55,
|
1469 |
+
"learning_rate": 2.460429130941289e-06,
|
1470 |
+
"logits/chosen": -0.2733067572116852,
|
1471 |
+
"logits/rejected": -0.24096527695655823,
|
1472 |
+
"logps/chosen": -231.34054565429688,
|
1473 |
+
"logps/rejected": -242.85177612304688,
|
1474 |
+
"loss": 0.2126,
|
1475 |
+
"rewards/accuracies": 0.26249998807907104,
|
1476 |
+
"rewards/chosen": 0.0189601369202137,
|
1477 |
+
"rewards/margins": 0.005297792609781027,
|
1478 |
+
"rewards/rejected": 0.013662343844771385,
|
1479 |
+
"step": 1040
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.56,
|
1483 |
+
"learning_rate": 2.413888607285192e-06,
|
1484 |
+
"logits/chosen": -0.330772340297699,
|
1485 |
+
"logits/rejected": -0.27838239073753357,
|
1486 |
+
"logps/chosen": -248.7228546142578,
|
1487 |
+
"logps/rejected": -279.42071533203125,
|
1488 |
+
"loss": 0.2178,
|
1489 |
+
"rewards/accuracies": 0.2874999940395355,
|
1490 |
+
"rewards/chosen": 0.020268592983484268,
|
1491 |
+
"rewards/margins": 0.005627959035336971,
|
1492 |
+
"rewards/rejected": 0.014640633948147297,
|
1493 |
+
"step": 1050
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.57,
|
1497 |
+
"learning_rate": 2.367377945543249e-06,
|
1498 |
+
"logits/chosen": -0.32522693276405334,
|
1499 |
+
"logits/rejected": -0.26629459857940674,
|
1500 |
+
"logps/chosen": -245.46865844726562,
|
1501 |
+
"logps/rejected": -254.28073120117188,
|
1502 |
+
"loss": 0.2134,
|
1503 |
+
"rewards/accuracies": 0.24375000596046448,
|
1504 |
+
"rewards/chosen": 0.021207790821790695,
|
1505 |
+
"rewards/margins": 0.0022269729524850845,
|
1506 |
+
"rewards/rejected": 0.01898081973195076,
|
1507 |
+
"step": 1060
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.57,
|
1511 |
+
"learning_rate": 2.320913274793676e-06,
|
1512 |
+
"logits/chosen": -0.3246033787727356,
|
1513 |
+
"logits/rejected": -0.28526002168655396,
|
1514 |
+
"logps/chosen": -275.1258239746094,
|
1515 |
+
"logps/rejected": -282.76788330078125,
|
1516 |
+
"loss": 0.214,
|
1517 |
+
"rewards/accuracies": 0.3375000059604645,
|
1518 |
+
"rewards/chosen": 0.029394343495368958,
|
1519 |
+
"rewards/margins": 0.003130835946649313,
|
1520 |
+
"rewards/rejected": 0.026263505220413208,
|
1521 |
+
"step": 1070
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.58,
|
1525 |
+
"learning_rate": 2.27451070816582e-06,
|
1526 |
+
"logits/chosen": -0.31318122148513794,
|
1527 |
+
"logits/rejected": -0.3022027015686035,
|
1528 |
+
"logps/chosen": -289.7471923828125,
|
1529 |
+
"logps/rejected": -316.6593322753906,
|
1530 |
+
"loss": 0.2139,
|
1531 |
+
"rewards/accuracies": 0.3187499940395355,
|
1532 |
+
"rewards/chosen": 0.03029504418373108,
|
1533 |
+
"rewards/margins": 0.008487190119922161,
|
1534 |
+
"rewards/rejected": 0.021807854995131493,
|
1535 |
+
"step": 1080
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.58,
|
1539 |
+
"learning_rate": 2.228186337252414e-06,
|
1540 |
+
"logits/chosen": -0.32163310050964355,
|
1541 |
+
"logits/rejected": -0.2794838547706604,
|
1542 |
+
"logps/chosen": -237.8488311767578,
|
1543 |
+
"logps/rejected": -261.3009948730469,
|
1544 |
+
"loss": 0.2022,
|
1545 |
+
"rewards/accuracies": 0.2874999940395355,
|
1546 |
+
"rewards/chosen": 0.024872692301869392,
|
1547 |
+
"rewards/margins": 0.006985250860452652,
|
1548 |
+
"rewards/rejected": 0.01788743957877159,
|
1549 |
+
"step": 1090
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.59,
|
1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
1554 |
+
"logits/chosen": -0.33526480197906494,
|
1555 |
+
"logits/rejected": -0.3139267563819885,
|
1556 |
+
"logps/chosen": -314.11761474609375,
|
1557 |
+
"logps/rejected": -324.87353515625,
|
1558 |
+
"loss": 0.2031,
|
1559 |
+
"rewards/accuracies": 0.3125,
|
1560 |
+
"rewards/chosen": 0.026857828721404076,
|
1561 |
+
"rewards/margins": 0.0052116261795163155,
|
1562 |
+
"rewards/rejected": 0.021646203473210335,
|
1563 |
+
"step": 1100
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.59,
|
1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
1568 |
+
"logits/chosen": -0.3513597846031189,
|
1569 |
+
"logits/rejected": -0.3594262897968292,
|
1570 |
+
"logps/chosen": -252.52978515625,
|
1571 |
+
"logps/rejected": -294.7911376953125,
|
1572 |
+
"loss": 0.2068,
|
1573 |
+
"rewards/accuracies": 0.3375000059604645,
|
1574 |
+
"rewards/chosen": 0.03454085439443588,
|
1575 |
+
"rewards/margins": 0.009111504070460796,
|
1576 |
+
"rewards/rejected": 0.02542934939265251,
|
1577 |
+
"step": 1110
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.6,
|
1581 |
+
"learning_rate": 2.089842874558849e-06,
|
1582 |
+
"logits/chosen": -0.3378306031227112,
|
1583 |
+
"logits/rejected": -0.35515913367271423,
|
1584 |
+
"logps/chosen": -246.19320678710938,
|
1585 |
+
"logps/rejected": -299.27508544921875,
|
1586 |
+
"loss": 0.2069,
|
1587 |
+
"rewards/accuracies": 0.3187499940395355,
|
1588 |
+
"rewards/chosen": 0.03665949031710625,
|
1589 |
+
"rewards/margins": 0.01151054073125124,
|
1590 |
+
"rewards/rejected": 0.02514895237982273,
|
1591 |
+
"step": 1120
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.6,
|
1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
1596 |
+
"logits/chosen": -0.3291921317577362,
|
1597 |
+
"logits/rejected": -0.3076435923576355,
|
1598 |
+
"logps/chosen": -245.3810577392578,
|
1599 |
+
"logps/rejected": -282.0654296875,
|
1600 |
+
"loss": 0.1944,
|
1601 |
+
"rewards/accuracies": 0.32499998807907104,
|
1602 |
+
"rewards/chosen": 0.03457210958003998,
|
1603 |
+
"rewards/margins": 0.012660647742450237,
|
1604 |
+
"rewards/rejected": 0.02191145531833172,
|
1605 |
+
"step": 1130
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.61,
|
1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
1610 |
+
"logits/chosen": -0.4073921740055084,
|
1611 |
+
"logits/rejected": -0.4076351523399353,
|
1612 |
+
"logps/chosen": -243.7863311767578,
|
1613 |
+
"logps/rejected": -278.9535217285156,
|
1614 |
+
"loss": 0.2071,
|
1615 |
+
"rewards/accuracies": 0.3187499940395355,
|
1616 |
+
"rewards/chosen": 0.031270626932382584,
|
1617 |
+
"rewards/margins": 0.011814272962510586,
|
1618 |
+
"rewards/rejected": 0.019456351175904274,
|
1619 |
+
"step": 1140
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.61,
|
1623 |
+
"learning_rate": 1.95277923333053e-06,
|
1624 |
+
"logits/chosen": -0.3861219882965088,
|
1625 |
+
"logits/rejected": -0.3469892144203186,
|
1626 |
+
"logps/chosen": -302.31243896484375,
|
1627 |
+
"logps/rejected": -358.0201721191406,
|
1628 |
+
"loss": 0.2139,
|
1629 |
+
"rewards/accuracies": 0.3812499940395355,
|
1630 |
+
"rewards/chosen": 0.033745743334293365,
|
1631 |
+
"rewards/margins": 0.011395677924156189,
|
1632 |
+
"rewards/rejected": 0.022350067272782326,
|
1633 |
+
"step": 1150
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.62,
|
1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
1638 |
+
"logits/chosen": -0.382877379655838,
|
1639 |
+
"logits/rejected": -0.3579499423503876,
|
1640 |
+
"logps/chosen": -255.16983032226562,
|
1641 |
+
"logps/rejected": -281.951904296875,
|
1642 |
+
"loss": 0.1989,
|
1643 |
+
"rewards/accuracies": 0.3062500059604645,
|
1644 |
+
"rewards/chosen": 0.026954079046845436,
|
1645 |
+
"rewards/margins": 0.005889051593840122,
|
1646 |
+
"rewards/rejected": 0.02106502838432789,
|
1647 |
+
"step": 1160
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.62,
|
1651 |
+
"learning_rate": 1.862325890344643e-06,
|
1652 |
+
"logits/chosen": -0.41709408164024353,
|
1653 |
+
"logits/rejected": -0.3790467381477356,
|
1654 |
+
"logps/chosen": -237.56845092773438,
|
1655 |
+
"logps/rejected": -253.5933074951172,
|
1656 |
+
"loss": 0.2093,
|
1657 |
+
"rewards/accuracies": 0.3187499940395355,
|
1658 |
+
"rewards/chosen": 0.02573922835290432,
|
1659 |
+
"rewards/margins": 0.006860650144517422,
|
1660 |
+
"rewards/rejected": 0.018878577277064323,
|
1661 |
+
"step": 1170
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.63,
|
1665 |
+
"learning_rate": 1.817423095982972e-06,
|
1666 |
+
"logits/chosen": -0.4551427364349365,
|
1667 |
+
"logits/rejected": -0.4378645420074463,
|
1668 |
+
"logps/chosen": -259.9010925292969,
|
1669 |
+
"logps/rejected": -296.59539794921875,
|
1670 |
+
"loss": 0.1942,
|
1671 |
+
"rewards/accuracies": 0.3125,
|
1672 |
+
"rewards/chosen": 0.02989533171057701,
|
1673 |
+
"rewards/margins": 0.01016165129840374,
|
1674 |
+
"rewards/rejected": 0.01973368227481842,
|
1675 |
+
"step": 1180
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.63,
|
1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
1680 |
+
"logits/chosen": -0.34378260374069214,
|
1681 |
+
"logits/rejected": -0.34789830446243286,
|
1682 |
+
"logps/chosen": -238.48300170898438,
|
1683 |
+
"logps/rejected": -260.9052429199219,
|
1684 |
+
"loss": 0.211,
|
1685 |
+
"rewards/accuracies": 0.33125001192092896,
|
1686 |
+
"rewards/chosen": 0.027008891105651855,
|
1687 |
+
"rewards/margins": 0.00940448883920908,
|
1688 |
+
"rewards/rejected": 0.01760440319776535,
|
1689 |
+
"step": 1190
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.64,
|
1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
1694 |
+
"logits/chosen": -0.4389713406562805,
|
1695 |
+
"logits/rejected": -0.4431864619255066,
|
1696 |
+
"logps/chosen": -286.2460632324219,
|
1697 |
+
"logps/rejected": -335.5301208496094,
|
1698 |
+
"loss": 0.2002,
|
1699 |
+
"rewards/accuracies": 0.3499999940395355,
|
1700 |
+
"rewards/chosen": 0.024310097098350525,
|
1701 |
+
"rewards/margins": 0.011298440396785736,
|
1702 |
+
"rewards/rejected": 0.013011658564209938,
|
1703 |
+
"step": 1200
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.65,
|
1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
1708 |
+
"logits/chosen": -0.44720926880836487,
|
1709 |
+
"logits/rejected": -0.40391507744789124,
|
1710 |
+
"logps/chosen": -310.9598083496094,
|
1711 |
+
"logps/rejected": -295.41510009765625,
|
1712 |
+
"loss": 0.2271,
|
1713 |
+
"rewards/accuracies": 0.3187499940395355,
|
1714 |
+
"rewards/chosen": 0.024556024000048637,
|
1715 |
+
"rewards/margins": 0.003975218627601862,
|
1716 |
+
"rewards/rejected": 0.020580807700753212,
|
1717 |
+
"step": 1210
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.65,
|
1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
1722 |
+
"logits/chosen": -0.4026651382446289,
|
1723 |
+
"logits/rejected": -0.4319339692592621,
|
1724 |
+
"logps/chosen": -235.80569458007812,
|
1725 |
+
"logps/rejected": -272.6563415527344,
|
1726 |
+
"loss": 0.195,
|
1727 |
+
"rewards/accuracies": 0.29374998807907104,
|
1728 |
+
"rewards/chosen": 0.02504395879805088,
|
1729 |
+
"rewards/margins": 0.005421781446784735,
|
1730 |
+
"rewards/rejected": 0.019622178748250008,
|
1731 |
+
"step": 1220
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.66,
|
1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
1736 |
+
"logits/chosen": -0.4050057530403137,
|
1737 |
+
"logits/rejected": -0.3732849657535553,
|
1738 |
+
"logps/chosen": -269.2541809082031,
|
1739 |
+
"logps/rejected": -283.1937561035156,
|
1740 |
+
"loss": 0.2061,
|
1741 |
+
"rewards/accuracies": 0.3062500059604645,
|
1742 |
+
"rewards/chosen": 0.025783170014619827,
|
1743 |
+
"rewards/margins": 0.005010620225220919,
|
1744 |
+
"rewards/rejected": 0.020772550255060196,
|
1745 |
+
"step": 1230
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.66,
|
1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
1750 |
+
"logits/chosen": -0.38786306977272034,
|
1751 |
+
"logits/rejected": -0.41273707151412964,
|
1752 |
+
"logps/chosen": -281.177734375,
|
1753 |
+
"logps/rejected": -291.16522216796875,
|
1754 |
+
"loss": 0.1982,
|
1755 |
+
"rewards/accuracies": 0.29374998807907104,
|
1756 |
+
"rewards/chosen": 0.024268019944429398,
|
1757 |
+
"rewards/margins": 0.006826480384916067,
|
1758 |
+
"rewards/rejected": 0.017441539093852043,
|
1759 |
+
"step": 1240
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.67,
|
1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
1764 |
+
"logits/chosen": -0.3743259310722351,
|
1765 |
+
"logits/rejected": -0.42252597212791443,
|
1766 |
+
"logps/chosen": -276.8372497558594,
|
1767 |
+
"logps/rejected": -302.574951171875,
|
1768 |
+
"loss": 0.2033,
|
1769 |
+
"rewards/accuracies": 0.3375000059604645,
|
1770 |
+
"rewards/chosen": 0.027395809069275856,
|
1771 |
+
"rewards/margins": 0.0073099941946566105,
|
1772 |
+
"rewards/rejected": 0.020085815340280533,
|
1773 |
+
"step": 1250
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.67,
|
1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
1778 |
+
"logits/chosen": -0.411508172750473,
|
1779 |
+
"logits/rejected": -0.40416446328163147,
|
1780 |
+
"logps/chosen": -303.2101745605469,
|
1781 |
+
"logps/rejected": -330.8990173339844,
|
1782 |
+
"loss": 0.1967,
|
1783 |
+
"rewards/accuracies": 0.3375000059604645,
|
1784 |
+
"rewards/chosen": 0.030878880992531776,
|
1785 |
+
"rewards/margins": 0.006534040905535221,
|
1786 |
+
"rewards/rejected": 0.02434483729302883,
|
1787 |
+
"step": 1260
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.68,
|
1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
1792 |
+
"logits/chosen": -0.4163438677787781,
|
1793 |
+
"logits/rejected": -0.4173736572265625,
|
1794 |
+
"logps/chosen": -227.8070068359375,
|
1795 |
+
"logps/rejected": -288.9392395019531,
|
1796 |
+
"loss": 0.1975,
|
1797 |
+
"rewards/accuracies": 0.39375001192092896,
|
1798 |
+
"rewards/chosen": 0.029939154163002968,
|
1799 |
+
"rewards/margins": 0.019917789846658707,
|
1800 |
+
"rewards/rejected": 0.010021360591053963,
|
1801 |
+
"step": 1270
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.68,
|
1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
1806 |
+
"logits/chosen": -0.4054839611053467,
|
1807 |
+
"logits/rejected": -0.37493056058883667,
|
1808 |
+
"logps/chosen": -272.3634033203125,
|
1809 |
+
"logps/rejected": -300.8335266113281,
|
1810 |
+
"loss": 0.1959,
|
1811 |
+
"rewards/accuracies": 0.30000001192092896,
|
1812 |
+
"rewards/chosen": 0.025880863890051842,
|
1813 |
+
"rewards/margins": 0.006764904595911503,
|
1814 |
+
"rewards/rejected": 0.019115960225462914,
|
1815 |
+
"step": 1280
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.69,
|
1819 |
+
"learning_rate": 1.342475111403298e-06,
|
1820 |
+
"logits/chosen": -0.43276605010032654,
|
1821 |
+
"logits/rejected": -0.3933637738227844,
|
1822 |
+
"logps/chosen": -277.875244140625,
|
1823 |
+
"logps/rejected": -315.5643310546875,
|
1824 |
+
"loss": 0.2086,
|
1825 |
+
"rewards/accuracies": 0.32499998807907104,
|
1826 |
+
"rewards/chosen": 0.02479017712175846,
|
1827 |
+
"rewards/margins": 0.009227531030774117,
|
1828 |
+
"rewards/rejected": 0.015562644228339195,
|
1829 |
+
"step": 1290
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.69,
|
1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
1834 |
+
"logits/chosen": -0.4051785469055176,
|
1835 |
+
"logits/rejected": -0.4154541492462158,
|
1836 |
+
"logps/chosen": -284.35870361328125,
|
1837 |
+
"logps/rejected": -343.5641174316406,
|
1838 |
+
"loss": 0.1946,
|
1839 |
+
"rewards/accuracies": 0.39375001192092896,
|
1840 |
+
"rewards/chosen": 0.030164774507284164,
|
1841 |
+
"rewards/margins": 0.018032994121313095,
|
1842 |
+
"rewards/rejected": 0.012131785042583942,
|
1843 |
+
"step": 1300
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.7,
|
1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
1848 |
+
"logits/chosen": -0.39242345094680786,
|
1849 |
+
"logits/rejected": -0.4176657795906067,
|
1850 |
+
"logps/chosen": -265.1470947265625,
|
1851 |
+
"logps/rejected": -283.01898193359375,
|
1852 |
+
"loss": 0.2152,
|
1853 |
+
"rewards/accuracies": 0.29374998807907104,
|
1854 |
+
"rewards/chosen": 0.01843050867319107,
|
1855 |
+
"rewards/margins": 0.00565576646476984,
|
1856 |
+
"rewards/rejected": 0.012774743139743805,
|
1857 |
+
"step": 1310
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.7,
|
1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
1862 |
+
"logits/chosen": -0.46165138483047485,
|
1863 |
+
"logits/rejected": -0.4150448739528656,
|
1864 |
+
"logps/chosen": -259.72576904296875,
|
1865 |
+
"logps/rejected": -290.30096435546875,
|
1866 |
+
"loss": 0.2172,
|
1867 |
+
"rewards/accuracies": 0.33125001192092896,
|
1868 |
+
"rewards/chosen": 0.019215788692235947,
|
1869 |
+
"rewards/margins": 0.008153979666531086,
|
1870 |
+
"rewards/rejected": 0.011061809957027435,
|
1871 |
+
"step": 1320
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.71,
|
1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
1876 |
+
"logits/chosen": -0.447805255651474,
|
1877 |
+
"logits/rejected": -0.4743974208831787,
|
1878 |
+
"logps/chosen": -299.7063903808594,
|
1879 |
+
"logps/rejected": -316.0007629394531,
|
1880 |
+
"loss": 0.2131,
|
1881 |
+
"rewards/accuracies": 0.32499998807907104,
|
1882 |
+
"rewards/chosen": 0.022526143118739128,
|
1883 |
+
"rewards/margins": 0.008774956688284874,
|
1884 |
+
"rewards/rejected": 0.013751191087067127,
|
1885 |
+
"step": 1330
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.71,
|
1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
1890 |
+
"logits/chosen": -0.4054747521877289,
|
1891 |
+
"logits/rejected": -0.3948088586330414,
|
1892 |
+
"logps/chosen": -269.71209716796875,
|
1893 |
+
"logps/rejected": -296.8516540527344,
|
1894 |
+
"loss": 0.1979,
|
1895 |
+
"rewards/accuracies": 0.32499998807907104,
|
1896 |
+
"rewards/chosen": 0.024300457909703255,
|
1897 |
+
"rewards/margins": 0.012143954634666443,
|
1898 |
+
"rewards/rejected": 0.012156503275036812,
|
1899 |
+
"step": 1340
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.72,
|
1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
1904 |
+
"logits/chosen": -0.44318923354148865,
|
1905 |
+
"logits/rejected": -0.4359446167945862,
|
1906 |
+
"logps/chosen": -267.4984436035156,
|
1907 |
+
"logps/rejected": -290.05694580078125,
|
1908 |
+
"loss": 0.2111,
|
1909 |
+
"rewards/accuracies": 0.32499998807907104,
|
1910 |
+
"rewards/chosen": 0.019330361858010292,
|
1911 |
+
"rewards/margins": 0.010160105302929878,
|
1912 |
+
"rewards/rejected": 0.00917025562375784,
|
1913 |
+
"step": 1350
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.73,
|
1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
1918 |
+
"logits/chosen": -0.40256720781326294,
|
1919 |
+
"logits/rejected": -0.4148158133029938,
|
1920 |
+
"logps/chosen": -269.02618408203125,
|
1921 |
+
"logps/rejected": -296.11041259765625,
|
1922 |
+
"loss": 0.2057,
|
1923 |
+
"rewards/accuracies": 0.2750000059604645,
|
1924 |
+
"rewards/chosen": 0.019753821194171906,
|
1925 |
+
"rewards/margins": 0.003918430767953396,
|
1926 |
+
"rewards/rejected": 0.015835389494895935,
|
1927 |
+
"step": 1360
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.73,
|
1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
1932 |
+
"logits/chosen": -0.43118053674697876,
|
1933 |
+
"logits/rejected": -0.4353235363960266,
|
1934 |
+
"logps/chosen": -219.4114227294922,
|
1935 |
+
"logps/rejected": -289.5980529785156,
|
1936 |
+
"loss": 0.1959,
|
1937 |
+
"rewards/accuracies": 0.34375,
|
1938 |
+
"rewards/chosen": 0.01978078857064247,
|
1939 |
+
"rewards/margins": 0.01855427958071232,
|
1940 |
+
"rewards/rejected": 0.0012265086406841874,
|
1941 |
+
"step": 1370
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.74,
|
1945 |
+
"learning_rate": 9.89046155758058e-07,
|
1946 |
+
"logits/chosen": -0.40550509095191956,
|
1947 |
+
"logits/rejected": -0.34553685784339905,
|
1948 |
+
"logps/chosen": -281.02508544921875,
|
1949 |
+
"logps/rejected": -293.77801513671875,
|
1950 |
+
"loss": 0.2007,
|
1951 |
+
"rewards/accuracies": 0.3125,
|
1952 |
+
"rewards/chosen": 0.015590362250804901,
|
1953 |
+
"rewards/margins": 0.009258143603801727,
|
1954 |
+
"rewards/rejected": 0.0063322195783257484,
|
1955 |
+
"step": 1380
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 0.74,
|
1959 |
+
"learning_rate": 9.52219425716534e-07,
|
1960 |
+
"logits/chosen": -0.4825696349143982,
|
1961 |
+
"logits/rejected": -0.46453267335891724,
|
1962 |
+
"logps/chosen": -277.46527099609375,
|
1963 |
+
"logps/rejected": -294.99041748046875,
|
1964 |
+
"loss": 0.2056,
|
1965 |
+
"rewards/accuracies": 0.28125,
|
1966 |
+
"rewards/chosen": 0.020664995536208153,
|
1967 |
+
"rewards/margins": 0.008111684583127499,
|
1968 |
+
"rewards/rejected": 0.01255331002175808,
|
1969 |
+
"step": 1390
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.75,
|
1973 |
+
"learning_rate": 9.15929438714262e-07,
|
1974 |
+
"logits/chosen": -0.4495898187160492,
|
1975 |
+
"logits/rejected": -0.4320181906223297,
|
1976 |
+
"logps/chosen": -319.02703857421875,
|
1977 |
+
"logps/rejected": -341.0379943847656,
|
1978 |
+
"loss": 0.1993,
|
1979 |
+
"rewards/accuracies": 0.32499998807907104,
|
1980 |
+
"rewards/chosen": 0.020045015960931778,
|
1981 |
+
"rewards/margins": 0.009719369933009148,
|
1982 |
+
"rewards/rejected": 0.01032564602792263,
|
1983 |
+
"step": 1400
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.75,
|
1987 |
+
"learning_rate": 8.801887794794911e-07,
|
1988 |
+
"logits/chosen": -0.40276139974594116,
|
1989 |
+
"logits/rejected": -0.43361392617225647,
|
1990 |
+
"logps/chosen": -240.11416625976562,
|
1991 |
+
"logps/rejected": -250.44827270507812,
|
1992 |
+
"loss": 0.2006,
|
1993 |
+
"rewards/accuracies": 0.2874999940395355,
|
1994 |
+
"rewards/chosen": 0.018377160653471947,
|
1995 |
+
"rewards/margins": 0.01084678340703249,
|
1996 |
+
"rewards/rejected": 0.007530376315116882,
|
1997 |
+
"step": 1410
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.76,
|
2001 |
+
"learning_rate": 8.450098422432787e-07,
|
2002 |
+
"logits/chosen": -0.4492071270942688,
|
2003 |
+
"logits/rejected": -0.4732417166233063,
|
2004 |
+
"logps/chosen": -304.6590270996094,
|
2005 |
+
"logps/rejected": -320.5320739746094,
|
2006 |
+
"loss": 0.2072,
|
2007 |
+
"rewards/accuracies": 0.3062500059604645,
|
2008 |
+
"rewards/chosen": 0.01209027785807848,
|
2009 |
+
"rewards/margins": 0.009711054153740406,
|
2010 |
+
"rewards/rejected": 0.0023792237043380737,
|
2011 |
+
"step": 1420
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.76,
|
2015 |
+
"learning_rate": 8.104048264413858e-07,
|
2016 |
+
"logits/chosen": -0.3988429605960846,
|
2017 |
+
"logits/rejected": -0.39577528834342957,
|
2018 |
+
"logps/chosen": -239.76278686523438,
|
2019 |
+
"logps/rejected": -274.7440490722656,
|
2020 |
+
"loss": 0.2002,
|
2021 |
+
"rewards/accuracies": 0.33125001192092896,
|
2022 |
+
"rewards/chosen": 0.01936698704957962,
|
2023 |
+
"rewards/margins": 0.015584215521812439,
|
2024 |
+
"rewards/rejected": 0.0037827729247510433,
|
2025 |
+
"step": 1430
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.77,
|
2029 |
+
"learning_rate": 7.763857324837321e-07,
|
2030 |
+
"logits/chosen": -0.39769840240478516,
|
2031 |
+
"logits/rejected": -0.4869154095649719,
|
2032 |
+
"logps/chosen": -306.97052001953125,
|
2033 |
+
"logps/rejected": -341.172607421875,
|
2034 |
+
"loss": 0.2137,
|
2035 |
+
"rewards/accuracies": 0.3499999940395355,
|
2036 |
+
"rewards/chosen": 0.01544914674013853,
|
2037 |
+
"rewards/margins": 0.01086854375898838,
|
2038 |
+
"rewards/rejected": 0.004580603446811438,
|
2039 |
+
"step": 1440
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.77,
|
2043 |
+
"learning_rate": 7.429643575928605e-07,
|
2044 |
+
"logits/chosen": -0.4462651312351227,
|
2045 |
+
"logits/rejected": -0.45454901456832886,
|
2046 |
+
"logps/chosen": -272.3761901855469,
|
2047 |
+
"logps/rejected": -300.822509765625,
|
2048 |
+
"loss": 0.2174,
|
2049 |
+
"rewards/accuracies": 0.29374998807907104,
|
2050 |
+
"rewards/chosen": 0.012530229985713959,
|
2051 |
+
"rewards/margins": 0.0049475752748548985,
|
2052 |
+
"rewards/rejected": 0.007582654245197773,
|
2053 |
+
"step": 1450
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.78,
|
2057 |
+
"learning_rate": 7.101522917128709e-07,
|
2058 |
+
"logits/chosen": -0.40284043550491333,
|
2059 |
+
"logits/rejected": -0.43488210439682007,
|
2060 |
+
"logps/chosen": -252.0594024658203,
|
2061 |
+
"logps/rejected": -309.368408203125,
|
2062 |
+
"loss": 0.2068,
|
2063 |
+
"rewards/accuracies": 0.4000000059604645,
|
2064 |
+
"rewards/chosen": 0.022649750113487244,
|
2065 |
+
"rewards/margins": 0.019699372351169586,
|
2066 |
+
"rewards/rejected": 0.002950376598164439,
|
2067 |
+
"step": 1460
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.78,
|
2071 |
+
"learning_rate": 6.779609134902312e-07,
|
2072 |
+
"logits/chosen": -0.45037612318992615,
|
2073 |
+
"logits/rejected": -0.4128038287162781,
|
2074 |
+
"logps/chosen": -235.04953002929688,
|
2075 |
+
"logps/rejected": -276.83453369140625,
|
2076 |
+
"loss": 0.2024,
|
2077 |
+
"rewards/accuracies": 0.30000001192092896,
|
2078 |
+
"rewards/chosen": 0.012530568055808544,
|
2079 |
+
"rewards/margins": 0.013141656294465065,
|
2080 |
+
"rewards/rejected": -0.0006110899848863482,
|
2081 |
+
"step": 1470
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 0.79,
|
2085 |
+
"learning_rate": 6.464013863278629e-07,
|
2086 |
+
"logits/chosen": -0.41907772421836853,
|
2087 |
+
"logits/rejected": -0.43223705887794495,
|
2088 |
+
"logps/chosen": -335.57958984375,
|
2089 |
+
"logps/rejected": -339.4792785644531,
|
2090 |
+
"loss": 0.2068,
|
2091 |
+
"rewards/accuracies": 0.32499998807907104,
|
2092 |
+
"rewards/chosen": 0.008910799399018288,
|
2093 |
+
"rewards/margins": 0.006074207369238138,
|
2094 |
+
"rewards/rejected": 0.002836592961102724,
|
2095 |
+
"step": 1480
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.79,
|
2099 |
+
"learning_rate": 6.154846545138696e-07,
|
2100 |
+
"logits/chosen": -0.4513935148715973,
|
2101 |
+
"logits/rejected": -0.4283982217311859,
|
2102 |
+
"logps/chosen": -293.88079833984375,
|
2103 |
+
"logps/rejected": -323.3922119140625,
|
2104 |
+
"loss": 0.2166,
|
2105 |
+
"rewards/accuracies": 0.3499999940395355,
|
2106 |
+
"rewards/chosen": 0.019896145910024643,
|
2107 |
+
"rewards/margins": 0.011627765372395515,
|
2108 |
+
"rewards/rejected": 0.008268382400274277,
|
2109 |
+
"step": 1490
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.8,
|
2113 |
+
"learning_rate": 5.852214394262515e-07,
|
2114 |
+
"logits/chosen": -0.4485366940498352,
|
2115 |
+
"logits/rejected": -0.4402342736721039,
|
2116 |
+
"logps/chosen": -282.20526123046875,
|
2117 |
+
"logps/rejected": -319.2931213378906,
|
2118 |
+
"loss": 0.2056,
|
2119 |
+
"rewards/accuracies": 0.32499998807907104,
|
2120 |
+
"rewards/chosen": 0.013388392515480518,
|
2121 |
+
"rewards/margins": 0.012794624082744122,
|
2122 |
+
"rewards/rejected": 0.000593768258113414,
|
2123 |
+
"step": 1500
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 0.81,
|
2127 |
+
"learning_rate": 5.556222358149191e-07,
|
2128 |
+
"logits/chosen": -0.46508869528770447,
|
2129 |
+
"logits/rejected": -0.44511333107948303,
|
2130 |
+
"logps/chosen": -306.74212646484375,
|
2131 |
+
"logps/rejected": -336.5767517089844,
|
2132 |
+
"loss": 0.1951,
|
2133 |
+
"rewards/accuracies": 0.3375000059604645,
|
2134 |
+
"rewards/chosen": 0.014937457628548145,
|
2135 |
+
"rewards/margins": 0.012279443442821503,
|
2136 |
+
"rewards/rejected": 0.0026580151170492172,
|
2137 |
+
"step": 1510
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 0.81,
|
2141 |
+
"learning_rate": 5.266973081622992e-07,
|
2142 |
+
"logits/chosen": -0.4336974024772644,
|
2143 |
+
"logits/rejected": -0.4386768937110901,
|
2144 |
+
"logps/chosen": -276.2127990722656,
|
2145 |
+
"logps/rejected": -314.35894775390625,
|
2146 |
+
"loss": 0.2138,
|
2147 |
+
"rewards/accuracies": 0.34375,
|
2148 |
+
"rewards/chosen": 0.01599228009581566,
|
2149 |
+
"rewards/margins": 0.015695402398705482,
|
2150 |
+
"rewards/rejected": 0.00029687798814848065,
|
2151 |
+
"step": 1520
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.82,
|
2155 |
+
"learning_rate": 4.984566871237942e-07,
|
2156 |
+
"logits/chosen": -0.42907437682151794,
|
2157 |
+
"logits/rejected": -0.45513230562210083,
|
2158 |
+
"logps/chosen": -255.0353546142578,
|
2159 |
+
"logps/rejected": -301.3641662597656,
|
2160 |
+
"loss": 0.195,
|
2161 |
+
"rewards/accuracies": 0.30000001192092896,
|
2162 |
+
"rewards/chosen": 0.011285373941063881,
|
2163 |
+
"rewards/margins": 0.015537778846919537,
|
2164 |
+
"rewards/rejected": -0.004252408631145954,
|
2165 |
+
"step": 1530
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 0.82,
|
2169 |
+
"learning_rate": 4.709101660493251e-07,
|
2170 |
+
"logits/chosen": -0.4831358790397644,
|
2171 |
+
"logits/rejected": -0.4467880129814148,
|
2172 |
+
"logps/chosen": -278.4053955078125,
|
2173 |
+
"logps/rejected": -315.4570617675781,
|
2174 |
+
"loss": 0.1998,
|
2175 |
+
"rewards/accuracies": 0.33125001192092896,
|
2176 |
+
"rewards/chosen": 0.014852491207420826,
|
2177 |
+
"rewards/margins": 0.015064602717757225,
|
2178 |
+
"rewards/rejected": -0.00021211188868619502,
|
2179 |
+
"step": 1540
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 0.83,
|
2183 |
+
"learning_rate": 4.440672975871743e-07,
|
2184 |
+
"logits/chosen": -0.46845632791519165,
|
2185 |
+
"logits/rejected": -0.43739065527915955,
|
2186 |
+
"logps/chosen": -276.8359375,
|
2187 |
+
"logps/rejected": -319.9267883300781,
|
2188 |
+
"loss": 0.2153,
|
2189 |
+
"rewards/accuracies": 0.33125001192092896,
|
2190 |
+
"rewards/chosen": 0.011290190741419792,
|
2191 |
+
"rewards/margins": 0.008315078914165497,
|
2192 |
+
"rewards/rejected": 0.002975111361593008,
|
2193 |
+
"step": 1550
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.83,
|
2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
2198 |
+
"logits/chosen": -0.41762232780456543,
|
2199 |
+
"logits/rejected": -0.3986124098300934,
|
2200 |
+
"logps/chosen": -287.2295227050781,
|
2201 |
+
"logps/rejected": -293.7361755371094,
|
2202 |
+
"loss": 0.2257,
|
2203 |
+
"rewards/accuracies": 0.25,
|
2204 |
+
"rewards/chosen": 0.011349224485456944,
|
2205 |
+
"rewards/margins": 0.0031309097539633512,
|
2206 |
+
"rewards/rejected": 0.008218314498662949,
|
2207 |
+
"step": 1560
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.84,
|
2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
2212 |
+
"logits/chosen": -0.4659145772457123,
|
2213 |
+
"logits/rejected": -0.5180898904800415,
|
2214 |
+
"logps/chosen": -250.5138397216797,
|
2215 |
+
"logps/rejected": -294.9307861328125,
|
2216 |
+
"loss": 0.203,
|
2217 |
+
"rewards/accuracies": 0.32499998807907104,
|
2218 |
+
"rewards/chosen": 0.015681695193052292,
|
2219 |
+
"rewards/margins": 0.01762702874839306,
|
2220 |
+
"rewards/rejected": -0.0019453342538326979,
|
2221 |
+
"step": 1570
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.84,
|
2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
2226 |
+
"logits/chosen": -0.46653518080711365,
|
2227 |
+
"logits/rejected": -0.4424509108066559,
|
2228 |
+
"logps/chosen": -245.3058624267578,
|
2229 |
+
"logps/rejected": -291.9484558105469,
|
2230 |
+
"loss": 0.1848,
|
2231 |
+
"rewards/accuracies": 0.30000001192092896,
|
2232 |
+
"rewards/chosen": 0.020799651741981506,
|
2233 |
+
"rewards/margins": 0.01163767371326685,
|
2234 |
+
"rewards/rejected": 0.009161979891359806,
|
2235 |
+
"step": 1580
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.85,
|
2239 |
+
"learning_rate": 3.43914795137566e-07,
|
2240 |
+
"logits/chosen": -0.5105794668197632,
|
2241 |
+
"logits/rejected": -0.46027788519859314,
|
2242 |
+
"logps/chosen": -267.0513610839844,
|
2243 |
+
"logps/rejected": -316.2474365234375,
|
2244 |
+
"loss": 0.2101,
|
2245 |
+
"rewards/accuracies": 0.33125001192092896,
|
2246 |
+
"rewards/chosen": 0.025547105818986893,
|
2247 |
+
"rewards/margins": 0.014689281582832336,
|
2248 |
+
"rewards/rejected": 0.010857820510864258,
|
2249 |
+
"step": 1590
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.85,
|
2253 |
+
"learning_rate": 3.207248277852901e-07,
|
2254 |
+
"logits/chosen": -0.4583914279937744,
|
2255 |
+
"logits/rejected": -0.4020233154296875,
|
2256 |
+
"logps/chosen": -307.8725891113281,
|
2257 |
+
"logps/rejected": -330.9596252441406,
|
2258 |
+
"loss": 0.2184,
|
2259 |
+
"rewards/accuracies": 0.3499999940395355,
|
2260 |
+
"rewards/chosen": 0.005914419423788786,
|
2261 |
+
"rewards/margins": 0.0035868945997208357,
|
2262 |
+
"rewards/rejected": 0.0023275248240679502,
|
2263 |
+
"step": 1600
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 0.86,
|
2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
2268 |
+
"logits/chosen": -0.47686338424682617,
|
2269 |
+
"logits/rejected": -0.4638807773590088,
|
2270 |
+
"logps/chosen": -276.5890197753906,
|
2271 |
+
"logps/rejected": -311.7373352050781,
|
2272 |
+
"loss": 0.2044,
|
2273 |
+
"rewards/accuracies": 0.34375,
|
2274 |
+
"rewards/chosen": 0.009661246091127396,
|
2275 |
+
"rewards/margins": 0.008756840601563454,
|
2276 |
+
"rewards/rejected": 0.0009044073522090912,
|
2277 |
+
"step": 1610
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.86,
|
2281 |
+
"learning_rate": 2.766198756040153e-07,
|
2282 |
+
"logits/chosen": -0.5123279094696045,
|
2283 |
+
"logits/rejected": -0.5023345351219177,
|
2284 |
+
"logps/chosen": -325.7563171386719,
|
2285 |
+
"logps/rejected": -341.7509765625,
|
2286 |
+
"loss": 0.2056,
|
2287 |
+
"rewards/accuracies": 0.375,
|
2288 |
+
"rewards/chosen": 0.01731071248650551,
|
2289 |
+
"rewards/margins": 0.012032909318804741,
|
2290 |
+
"rewards/rejected": 0.005277802236378193,
|
2291 |
+
"step": 1620
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 0.87,
|
2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
2296 |
+
"logits/chosen": -0.42395853996276855,
|
2297 |
+
"logits/rejected": -0.40241509675979614,
|
2298 |
+
"logps/chosen": -260.11376953125,
|
2299 |
+
"logps/rejected": -274.5872802734375,
|
2300 |
+
"loss": 0.2063,
|
2301 |
+
"rewards/accuracies": 0.2750000059604645,
|
2302 |
+
"rewards/chosen": 0.007420125417411327,
|
2303 |
+
"rewards/margins": 0.003118096850812435,
|
2304 |
+
"rewards/rejected": 0.0043020290322601795,
|
2305 |
+
"step": 1630
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 0.87,
|
2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
2310 |
+
"logits/chosen": -0.4700084626674652,
|
2311 |
+
"logits/rejected": -0.48075324296951294,
|
2312 |
+
"logps/chosen": -251.65200805664062,
|
2313 |
+
"logps/rejected": -273.92889404296875,
|
2314 |
+
"loss": 0.202,
|
2315 |
+
"rewards/accuracies": 0.3125,
|
2316 |
+
"rewards/chosen": 0.01748984307050705,
|
2317 |
+
"rewards/margins": 0.006852374877780676,
|
2318 |
+
"rewards/rejected": 0.010637464001774788,
|
2319 |
+
"step": 1640
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.88,
|
2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
2324 |
+
"logits/chosen": -0.4547249674797058,
|
2325 |
+
"logits/rejected": -0.49483567476272583,
|
2326 |
+
"logps/chosen": -257.3490905761719,
|
2327 |
+
"logps/rejected": -283.01068115234375,
|
2328 |
+
"loss": 0.2061,
|
2329 |
+
"rewards/accuracies": 0.30000001192092896,
|
2330 |
+
"rewards/chosen": 0.012025897391140461,
|
2331 |
+
"rewards/margins": 0.010915794409811497,
|
2332 |
+
"rewards/rejected": 0.0011101035634055734,
|
2333 |
+
"step": 1650
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 0.89,
|
2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
2338 |
+
"logits/chosen": -0.425775945186615,
|
2339 |
+
"logits/rejected": -0.39094358682632446,
|
2340 |
+
"logps/chosen": -268.5893859863281,
|
2341 |
+
"logps/rejected": -291.09295654296875,
|
2342 |
+
"loss": 0.2173,
|
2343 |
+
"rewards/accuracies": 0.3375000059604645,
|
2344 |
+
"rewards/chosen": 0.01688522659242153,
|
2345 |
+
"rewards/margins": 0.008994406089186668,
|
2346 |
+
"rewards/rejected": 0.007890822365880013,
|
2347 |
+
"step": 1660
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 0.89,
|
2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
2352 |
+
"logits/chosen": -0.4601113796234131,
|
2353 |
+
"logits/rejected": -0.5219780802726746,
|
2354 |
+
"logps/chosen": -286.64410400390625,
|
2355 |
+
"logps/rejected": -286.85223388671875,
|
2356 |
+
"loss": 0.2119,
|
2357 |
+
"rewards/accuracies": 0.2750000059604645,
|
2358 |
+
"rewards/chosen": 0.012106504291296005,
|
2359 |
+
"rewards/margins": 0.0008594643441028893,
|
2360 |
+
"rewards/rejected": 0.011247038841247559,
|
2361 |
+
"step": 1670
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.9,
|
2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
2366 |
+
"logits/chosen": -0.4205317497253418,
|
2367 |
+
"logits/rejected": -0.40168771147727966,
|
2368 |
+
"logps/chosen": -293.42626953125,
|
2369 |
+
"logps/rejected": -321.1906433105469,
|
2370 |
+
"loss": 0.2134,
|
2371 |
+
"rewards/accuracies": 0.34375,
|
2372 |
+
"rewards/chosen": 0.0118024330586195,
|
2373 |
+
"rewards/margins": 0.013113128952682018,
|
2374 |
+
"rewards/rejected": -0.0013106951955705881,
|
2375 |
+
"step": 1680
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 0.9,
|
2379 |
+
"learning_rate": 1.469004986021355e-07,
|
2380 |
+
"logits/chosen": -0.4995250105857849,
|
2381 |
+
"logits/rejected": -0.4347379803657532,
|
2382 |
+
"logps/chosen": -279.1140441894531,
|
2383 |
+
"logps/rejected": -305.504638671875,
|
2384 |
+
"loss": 0.1933,
|
2385 |
+
"rewards/accuracies": 0.3062500059604645,
|
2386 |
+
"rewards/chosen": 0.014054737985134125,
|
2387 |
+
"rewards/margins": 0.010226726531982422,
|
2388 |
+
"rewards/rejected": 0.003828010056167841,
|
2389 |
+
"step": 1690
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 0.91,
|
2393 |
+
"learning_rate": 1.315856680127367e-07,
|
2394 |
+
"logits/chosen": -0.42301422357559204,
|
2395 |
+
"logits/rejected": -0.4993847906589508,
|
2396 |
+
"logps/chosen": -293.3585510253906,
|
2397 |
+
"logps/rejected": -314.04095458984375,
|
2398 |
+
"loss": 0.2044,
|
2399 |
+
"rewards/accuracies": 0.30000001192092896,
|
2400 |
+
"rewards/chosen": 0.01272254716604948,
|
2401 |
+
"rewards/margins": 0.008608581498265266,
|
2402 |
+
"rewards/rejected": 0.004113964736461639,
|
2403 |
+
"step": 1700
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 0.91,
|
2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
2408 |
+
"logits/chosen": -0.4361719489097595,
|
2409 |
+
"logits/rejected": -0.4560726284980774,
|
2410 |
+
"logps/chosen": -283.5252990722656,
|
2411 |
+
"logps/rejected": -320.2547607421875,
|
2412 |
+
"loss": 0.2074,
|
2413 |
+
"rewards/accuracies": 0.3187499940395355,
|
2414 |
+
"rewards/chosen": 0.008978287689387798,
|
2415 |
+
"rewards/margins": 0.010601527988910675,
|
2416 |
+
"rewards/rejected": -0.001623238087631762,
|
2417 |
+
"step": 1710
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 0.92,
|
2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
2422 |
+
"logits/chosen": -0.409717857837677,
|
2423 |
+
"logits/rejected": -0.43887776136398315,
|
2424 |
+
"logps/chosen": -274.9674072265625,
|
2425 |
+
"logps/rejected": -320.1651916503906,
|
2426 |
+
"loss": 0.2081,
|
2427 |
+
"rewards/accuracies": 0.3062500059604645,
|
2428 |
+
"rewards/chosen": 0.014241678640246391,
|
2429 |
+
"rewards/margins": 0.013103106990456581,
|
2430 |
+
"rewards/rejected": 0.0011385709512978792,
|
2431 |
+
"step": 1720
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 0.92,
|
2435 |
+
"learning_rate": 9.058894027791643e-08,
|
2436 |
+
"logits/chosen": -0.49651774764060974,
|
2437 |
+
"logits/rejected": -0.4656089246273041,
|
2438 |
+
"logps/chosen": -239.1632843017578,
|
2439 |
+
"logps/rejected": -252.4584503173828,
|
2440 |
+
"loss": 0.2061,
|
2441 |
+
"rewards/accuracies": 0.23749999701976776,
|
2442 |
+
"rewards/chosen": 0.015118755400180817,
|
2443 |
+
"rewards/margins": 0.006344223860651255,
|
2444 |
+
"rewards/rejected": 0.0087745301425457,
|
2445 |
+
"step": 1730
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 0.93,
|
2449 |
+
"learning_rate": 7.858841583008592e-08,
|
2450 |
+
"logits/chosen": -0.42512744665145874,
|
2451 |
+
"logits/rejected": -0.46020737290382385,
|
2452 |
+
"logps/chosen": -251.6322784423828,
|
2453 |
+
"logps/rejected": -235.462158203125,
|
2454 |
+
"loss": 0.1982,
|
2455 |
+
"rewards/accuracies": 0.23125000298023224,
|
2456 |
+
"rewards/chosen": 0.009195510298013687,
|
2457 |
+
"rewards/margins": -0.0015735321212559938,
|
2458 |
+
"rewards/rejected": 0.010769042186439037,
|
2459 |
+
"step": 1740
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 0.93,
|
2463 |
+
"learning_rate": 6.742759426686313e-08,
|
2464 |
+
"logits/chosen": -0.3904110789299011,
|
2465 |
+
"logits/rejected": -0.4210638999938965,
|
2466 |
+
"logps/chosen": -246.4021759033203,
|
2467 |
+
"logps/rejected": -279.08160400390625,
|
2468 |
+
"loss": 0.1995,
|
2469 |
+
"rewards/accuracies": 0.29374998807907104,
|
2470 |
+
"rewards/chosen": 0.020919088274240494,
|
2471 |
+
"rewards/margins": 0.016136836260557175,
|
2472 |
+
"rewards/rejected": 0.004782252479344606,
|
2473 |
+
"step": 1750
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 0.94,
|
2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
2478 |
+
"logits/chosen": -0.5139604806900024,
|
2479 |
+
"logits/rejected": -0.4221692681312561,
|
2480 |
+
"logps/chosen": -285.17803955078125,
|
2481 |
+
"logps/rejected": -315.17071533203125,
|
2482 |
+
"loss": 0.1886,
|
2483 |
+
"rewards/accuracies": 0.35624998807907104,
|
2484 |
+
"rewards/chosen": 0.01321653462946415,
|
2485 |
+
"rewards/margins": 0.010121813975274563,
|
2486 |
+
"rewards/rejected": 0.003094720421358943,
|
2487 |
+
"step": 1760
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 0.94,
|
2491 |
+
"learning_rate": 4.764024876318357e-08,
|
2492 |
+
"logits/chosen": -0.48494213819503784,
|
2493 |
+
"logits/rejected": -0.4467412531375885,
|
2494 |
+
"logps/chosen": -319.4140319824219,
|
2495 |
+
"logps/rejected": -333.9644775390625,
|
2496 |
+
"loss": 0.2053,
|
2497 |
+
"rewards/accuracies": 0.29374998807907104,
|
2498 |
+
"rewards/chosen": 0.00665741041302681,
|
2499 |
+
"rewards/margins": 0.0072568124160170555,
|
2500 |
+
"rewards/rejected": -0.0005994020029902458,
|
2501 |
+
"step": 1770
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 0.95,
|
2505 |
+
"learning_rate": 3.902058672559633e-08,
|
2506 |
+
"logits/chosen": -0.4710802435874939,
|
2507 |
+
"logits/rejected": -0.44002991914749146,
|
2508 |
+
"logps/chosen": -266.371337890625,
|
2509 |
+
"logps/rejected": -304.83526611328125,
|
2510 |
+
"loss": 0.2004,
|
2511 |
+
"rewards/accuracies": 0.3375000059604645,
|
2512 |
+
"rewards/chosen": 0.013240337371826172,
|
2513 |
+
"rewards/margins": 0.00819102581590414,
|
2514 |
+
"rewards/rejected": 0.005049312487244606,
|
2515 |
+
"step": 1780
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 0.95,
|
2519 |
+
"learning_rate": 3.125434899876933e-08,
|
2520 |
+
"logits/chosen": -0.46560755372047424,
|
2521 |
+
"logits/rejected": -0.4170166552066803,
|
2522 |
+
"logps/chosen": -273.154052734375,
|
2523 |
+
"logps/rejected": -292.3708801269531,
|
2524 |
+
"loss": 0.2181,
|
2525 |
+
"rewards/accuracies": 0.2750000059604645,
|
2526 |
+
"rewards/chosen": 0.012563738040626049,
|
2527 |
+
"rewards/margins": 0.008571961894631386,
|
2528 |
+
"rewards/rejected": 0.003991776145994663,
|
2529 |
+
"step": 1790
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.96,
|
2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
2534 |
+
"logits/chosen": -0.4589017927646637,
|
2535 |
+
"logits/rejected": -0.46233731508255005,
|
2536 |
+
"logps/chosen": -330.4123840332031,
|
2537 |
+
"logps/rejected": -345.12005615234375,
|
2538 |
+
"loss": 0.2102,
|
2539 |
+
"rewards/accuracies": 0.35624998807907104,
|
2540 |
+
"rewards/chosen": 0.016749653965234756,
|
2541 |
+
"rewards/margins": 0.009503444656729698,
|
2542 |
+
"rewards/rejected": 0.0072462051175534725,
|
2543 |
+
"step": 1800
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 0.97,
|
2547 |
+
"learning_rate": 1.829262236869772e-08,
|
2548 |
+
"logits/chosen": -0.4653870463371277,
|
2549 |
+
"logits/rejected": -0.4221324324607849,
|
2550 |
+
"logps/chosen": -295.13922119140625,
|
2551 |
+
"logps/rejected": -343.47979736328125,
|
2552 |
+
"loss": 0.2124,
|
2553 |
+
"rewards/accuracies": 0.36250001192092896,
|
2554 |
+
"rewards/chosen": 0.014039866626262665,
|
2555 |
+
"rewards/margins": 0.011893939226865768,
|
2556 |
+
"rewards/rejected": 0.0021459278650581837,
|
2557 |
+
"step": 1810
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 0.97,
|
2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
2562 |
+
"logits/chosen": -0.4033223092556,
|
2563 |
+
"logits/rejected": -0.4376245439052582,
|
2564 |
+
"logps/chosen": -233.1123504638672,
|
2565 |
+
"logps/rejected": -269.4231262207031,
|
2566 |
+
"loss": 0.2073,
|
2567 |
+
"rewards/accuracies": 0.26875001192092896,
|
2568 |
+
"rewards/chosen": 0.012142864055931568,
|
2569 |
+
"rewards/margins": 0.008770270273089409,
|
2570 |
+
"rewards/rejected": 0.003372594015672803,
|
2571 |
+
"step": 1820
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 0.98,
|
2575 |
+
"learning_rate": 8.773046908123195e-09,
|
2576 |
+
"logits/chosen": -0.41063612699508667,
|
2577 |
+
"logits/rejected": -0.4108348488807678,
|
2578 |
+
"logps/chosen": -305.08514404296875,
|
2579 |
+
"logps/rejected": -316.0191955566406,
|
2580 |
+
"loss": 0.1879,
|
2581 |
+
"rewards/accuracies": 0.36250001192092896,
|
2582 |
+
"rewards/chosen": 0.011063008569180965,
|
2583 |
+
"rewards/margins": 0.007611425127834082,
|
2584 |
+
"rewards/rejected": 0.0034515834413468838,
|
2585 |
+
"step": 1830
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 0.98,
|
2589 |
+
"learning_rate": 5.308379077080817e-09,
|
2590 |
+
"logits/chosen": -0.4463173449039459,
|
2591 |
+
"logits/rejected": -0.427543967962265,
|
2592 |
+
"logps/chosen": -271.1603088378906,
|
2593 |
+
"logps/rejected": -276.7561950683594,
|
2594 |
+
"loss": 0.2193,
|
2595 |
+
"rewards/accuracies": 0.33125001192092896,
|
2596 |
+
"rewards/chosen": 0.013324853964149952,
|
2597 |
+
"rewards/margins": 0.00910397619009018,
|
2598 |
+
"rewards/rejected": 0.00422087823972106,
|
2599 |
+
"step": 1840
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 0.99,
|
2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
2604 |
+
"logits/chosen": -0.4519821107387543,
|
2605 |
+
"logits/rejected": -0.45307645201683044,
|
2606 |
+
"logps/chosen": -291.6419982910156,
|
2607 |
+
"logps/rejected": -338.31207275390625,
|
2608 |
+
"loss": 0.1975,
|
2609 |
+
"rewards/accuracies": 0.3062500059604645,
|
2610 |
+
"rewards/chosen": 0.009216098114848137,
|
2611 |
+
"rewards/margins": 0.009984901174902916,
|
2612 |
+
"rewards/rejected": -0.00076880311826244,
|
2613 |
+
"step": 1850
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 0.99,
|
2617 |
+
"learning_rate": 9.752902257023633e-10,
|
2618 |
+
"logits/chosen": -0.4056398272514343,
|
2619 |
+
"logits/rejected": -0.39859509468078613,
|
2620 |
+
"logps/chosen": -206.9446258544922,
|
2621 |
+
"logps/rejected": -251.4867401123047,
|
2622 |
+
"loss": 0.1943,
|
2623 |
+
"rewards/accuracies": 0.2874999940395355,
|
2624 |
+
"rewards/chosen": 0.016167674213647842,
|
2625 |
+
"rewards/margins": 0.014986155554652214,
|
2626 |
+
"rewards/rejected": 0.0011815171455964446,
|
2627 |
+
"step": 1860
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 1.0,
|
2631 |
+
"learning_rate": 1.083718442532189e-10,
|
2632 |
+
"logits/chosen": -0.47832536697387695,
|
2633 |
+
"logits/rejected": -0.42318111658096313,
|
2634 |
+
"logps/chosen": -300.47515869140625,
|
2635 |
+
"logps/rejected": -325.100830078125,
|
2636 |
+
"loss": 0.217,
|
2637 |
+
"rewards/accuracies": 0.3125,
|
2638 |
+
"rewards/chosen": 0.00793883390724659,
|
2639 |
+
"rewards/margins": 0.004473513457924128,
|
2640 |
+
"rewards/rejected": 0.0034653202164918184,
|
2641 |
+
"step": 1870
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 1.0,
|
2645 |
+
"step": 1875,
|
2646 |
+
"total_flos": 0.0,
|
2647 |
+
"train_loss": 0.20694573613802592,
|
2648 |
+
"train_runtime": 16535.0328,
|
2649 |
+
"train_samples_per_second": 1.814,
|
2650 |
+
"train_steps_per_second": 0.113
|
2651 |
+
}
|
2652 |
+
],
|
2653 |
+
"logging_steps": 10,
|
2654 |
+
"max_steps": 1875,
|
2655 |
+
"num_input_tokens_seen": 0,
|
2656 |
+
"num_train_epochs": 1,
|
2657 |
+
"save_steps": 100,
|
2658 |
+
"total_flos": 0.0,
|
2659 |
+
"train_batch_size": 4,
|
2660 |
+
"trial_name": null,
|
2661 |
+
"trial_params": null
|
2662 |
+
}
|