Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May12_23-48-01_gpu4-119-5/events.out.tfevents.1715521821.gpu4-119-5.3218502.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: DUAL-GPO/phi-2-gpo-new-i0
|
| 9 |
+
model-index:
|
| 10 |
+
- name: phi-2-gpo-v8-i1
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# phi-2-gpo-v8-i1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- PEFT 0.7.1
|
| 57 |
+
- Transformers 4.36.2
|
| 58 |
+
- Pytorch 2.1.2+cu121
|
| 59 |
+
- Datasets 2.14.6
|
| 60 |
+
- 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 167807296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:015513342de17be17f1a98a800fd7202f6429565a25d1b4771ff95b08207326d
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.23145956670443216,
|
| 4 |
+
"train_runtime": 17376.0848,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 1.727,
|
| 7 |
+
"train_steps_per_second": 0.108
|
| 8 |
+
}
|
runs/May12_23-48-01_gpu4-119-5/events.out.tfevents.1715521821.gpu4-119-5.3218502.0
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:ee3ba100073c0dd2f5c22c2e370c6a130c7430b12243b3ba96c8b7db9e2660c2
|
| 3 |
+
size 124226
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.23145956670443216,
|
| 4 |
+
"train_runtime": 17376.0848,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 1.727,
|
| 7 |
+
"train_steps_per_second": 0.108
|
| 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": 0.24484609067440033,
|
| 15 |
+
"logits/rejected": 0.2733721137046814,
|
| 16 |
+
"logps/chosen": -382.60247802734375,
|
| 17 |
+
"logps/rejected": -260.64013671875,
|
| 18 |
+
"loss": 0.3272,
|
| 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": 0.04333009943366051,
|
| 29 |
+
"logits/rejected": 0.2742147743701935,
|
| 30 |
+
"logps/chosen": -312.38092041015625,
|
| 31 |
+
"logps/rejected": -271.8465881347656,
|
| 32 |
+
"loss": 0.3266,
|
| 33 |
+
"rewards/accuracies": 0.4305555522441864,
|
| 34 |
+
"rewards/chosen": -6.604947702726349e-05,
|
| 35 |
+
"rewards/margins": -4.0390281355939806e-05,
|
| 36 |
+
"rewards/rejected": -2.565919203334488e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": 0.14737281203269958,
|
| 43 |
+
"logits/rejected": 0.26748910546302795,
|
| 44 |
+
"logps/chosen": -351.84014892578125,
|
| 45 |
+
"logps/rejected": -283.82989501953125,
|
| 46 |
+
"loss": 0.3538,
|
| 47 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 48 |
+
"rewards/chosen": 4.673796411225339e-06,
|
| 49 |
+
"rewards/margins": -5.658002191921696e-05,
|
| 50 |
+
"rewards/rejected": 6.125382788013667e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": 0.08816106617450714,
|
| 57 |
+
"logits/rejected": 0.21678781509399414,
|
| 58 |
+
"logps/chosen": -344.03814697265625,
|
| 59 |
+
"logps/rejected": -279.57830810546875,
|
| 60 |
+
"loss": 0.3558,
|
| 61 |
+
"rewards/accuracies": 0.40625,
|
| 62 |
+
"rewards/chosen": -6.16505931247957e-05,
|
| 63 |
+
"rewards/margins": -0.0001463174121454358,
|
| 64 |
+
"rewards/rejected": 8.466680446872488e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": 0.12371940910816193,
|
| 71 |
+
"logits/rejected": 0.18927700817584991,
|
| 72 |
+
"logps/chosen": -326.63323974609375,
|
| 73 |
+
"logps/rejected": -280.051025390625,
|
| 74 |
+
"loss": 0.2908,
|
| 75 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 76 |
+
"rewards/chosen": 0.00011619376164162531,
|
| 77 |
+
"rewards/margins": -1.4456210010393988e-05,
|
| 78 |
+
"rewards/rejected": 0.00013064996164757758,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": 0.03745291382074356,
|
| 85 |
+
"logits/rejected": 0.17850083112716675,
|
| 86 |
+
"logps/chosen": -333.9073486328125,
|
| 87 |
+
"logps/rejected": -289.7876892089844,
|
| 88 |
+
"loss": 0.3622,
|
| 89 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 90 |
+
"rewards/chosen": 0.00023793391301296651,
|
| 91 |
+
"rewards/margins": 0.00018272039596922696,
|
| 92 |
+
"rewards/rejected": 5.521355342352763e-05,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": 0.05472108721733093,
|
| 99 |
+
"logits/rejected": 0.256857305765152,
|
| 100 |
+
"logps/chosen": -351.0667419433594,
|
| 101 |
+
"logps/rejected": -273.13787841796875,
|
| 102 |
+
"loss": 0.34,
|
| 103 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 104 |
+
"rewards/chosen": 0.000246922456426546,
|
| 105 |
+
"rewards/margins": 0.00023249602236319333,
|
| 106 |
+
"rewards/rejected": 1.4426443158299662e-05,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": 0.05988805368542671,
|
| 113 |
+
"logits/rejected": 0.22936634719371796,
|
| 114 |
+
"logps/chosen": -292.13360595703125,
|
| 115 |
+
"logps/rejected": -273.4328308105469,
|
| 116 |
+
"loss": 0.339,
|
| 117 |
+
"rewards/accuracies": 0.581250011920929,
|
| 118 |
+
"rewards/chosen": 0.0005934828659519553,
|
| 119 |
+
"rewards/margins": 0.000584075809456408,
|
| 120 |
+
"rewards/rejected": 9.407010111317504e-06,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": 0.09555818885564804,
|
| 127 |
+
"logits/rejected": 0.28471559286117554,
|
| 128 |
+
"logps/chosen": -417.53369140625,
|
| 129 |
+
"logps/rejected": -316.70379638671875,
|
| 130 |
+
"loss": 0.3408,
|
| 131 |
+
"rewards/accuracies": 0.675000011920929,
|
| 132 |
+
"rewards/chosen": 0.0012717883801087737,
|
| 133 |
+
"rewards/margins": 0.0011722706258296967,
|
| 134 |
+
"rewards/rejected": 9.951768151950091e-05,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": 0.0800800547003746,
|
| 141 |
+
"logits/rejected": 0.24734680354595184,
|
| 142 |
+
"logps/chosen": -357.4005432128906,
|
| 143 |
+
"logps/rejected": -265.1945495605469,
|
| 144 |
+
"loss": 0.3418,
|
| 145 |
+
"rewards/accuracies": 0.71875,
|
| 146 |
+
"rewards/chosen": 0.0021034968085587025,
|
| 147 |
+
"rewards/margins": 0.001932466751895845,
|
| 148 |
+
"rewards/rejected": 0.00017103021673392504,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": 0.07155252248048782,
|
| 155 |
+
"logits/rejected": 0.21769502758979797,
|
| 156 |
+
"logps/chosen": -328.1473693847656,
|
| 157 |
+
"logps/rejected": -286.50335693359375,
|
| 158 |
+
"loss": 0.3372,
|
| 159 |
+
"rewards/accuracies": 0.71875,
|
| 160 |
+
"rewards/chosen": 0.0025882914196699858,
|
| 161 |
+
"rewards/margins": 0.002097602002322674,
|
| 162 |
+
"rewards/rejected": 0.0004906897665932775,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": 0.11561211198568344,
|
| 169 |
+
"logits/rejected": 0.235809326171875,
|
| 170 |
+
"logps/chosen": -371.8827209472656,
|
| 171 |
+
"logps/rejected": -298.6903991699219,
|
| 172 |
+
"loss": 0.3574,
|
| 173 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 174 |
+
"rewards/chosen": 0.0038680892903357744,
|
| 175 |
+
"rewards/margins": 0.0038350392132997513,
|
| 176 |
+
"rewards/rejected": 3.3050309866666794e-05,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": 0.1021943911910057,
|
| 183 |
+
"logits/rejected": 0.2624170482158661,
|
| 184 |
+
"logps/chosen": -338.0439758300781,
|
| 185 |
+
"logps/rejected": -303.2659912109375,
|
| 186 |
+
"loss": 0.3179,
|
| 187 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 188 |
+
"rewards/chosen": 0.006541919894516468,
|
| 189 |
+
"rewards/margins": 0.007115885615348816,
|
| 190 |
+
"rewards/rejected": -0.000573965604417026,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": 0.1403232365846634,
|
| 197 |
+
"logits/rejected": 0.2289782017469406,
|
| 198 |
+
"logps/chosen": -322.43145751953125,
|
| 199 |
+
"logps/rejected": -290.4974670410156,
|
| 200 |
+
"loss": 0.3224,
|
| 201 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 202 |
+
"rewards/chosen": 0.007107354700565338,
|
| 203 |
+
"rewards/margins": 0.009225147776305676,
|
| 204 |
+
"rewards/rejected": -0.0021177921444177628,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": 0.10777691751718521,
|
| 211 |
+
"logits/rejected": 0.3141722083091736,
|
| 212 |
+
"logps/chosen": -403.12591552734375,
|
| 213 |
+
"logps/rejected": -301.6325988769531,
|
| 214 |
+
"loss": 0.3034,
|
| 215 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 216 |
+
"rewards/chosen": 0.009438706561923027,
|
| 217 |
+
"rewards/margins": 0.01668398641049862,
|
| 218 |
+
"rewards/rejected": -0.007245280779898167,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": 0.144662007689476,
|
| 225 |
+
"logits/rejected": 0.29330867528915405,
|
| 226 |
+
"logps/chosen": -332.96417236328125,
|
| 227 |
+
"logps/rejected": -288.76763916015625,
|
| 228 |
+
"loss": 0.3229,
|
| 229 |
+
"rewards/accuracies": 0.737500011920929,
|
| 230 |
+
"rewards/chosen": 0.008229254744946957,
|
| 231 |
+
"rewards/margins": 0.020817989483475685,
|
| 232 |
+
"rewards/rejected": -0.012588733807206154,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": 0.13444170355796814,
|
| 239 |
+
"logits/rejected": 0.27335208654403687,
|
| 240 |
+
"logps/chosen": -375.7054443359375,
|
| 241 |
+
"logps/rejected": -343.5438232421875,
|
| 242 |
+
"loss": 0.3046,
|
| 243 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 244 |
+
"rewards/chosen": -0.012767407111823559,
|
| 245 |
+
"rewards/margins": 0.03700178116559982,
|
| 246 |
+
"rewards/rejected": -0.049769192934036255,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": 0.15973123908042908,
|
| 253 |
+
"logits/rejected": 0.3123999238014221,
|
| 254 |
+
"logps/chosen": -407.84600830078125,
|
| 255 |
+
"logps/rejected": -383.7323913574219,
|
| 256 |
+
"loss": 0.2715,
|
| 257 |
+
"rewards/accuracies": 0.737500011920929,
|
| 258 |
+
"rewards/chosen": -0.050918400287628174,
|
| 259 |
+
"rewards/margins": 0.05725928395986557,
|
| 260 |
+
"rewards/rejected": -0.10817768424749374,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": 0.17064544558525085,
|
| 267 |
+
"logits/rejected": 0.2910129129886627,
|
| 268 |
+
"logps/chosen": -472.98193359375,
|
| 269 |
+
"logps/rejected": -524.0833129882812,
|
| 270 |
+
"loss": 0.2907,
|
| 271 |
+
"rewards/accuracies": 0.65625,
|
| 272 |
+
"rewards/chosen": -0.16761399805545807,
|
| 273 |
+
"rewards/margins": 0.09154665470123291,
|
| 274 |
+
"rewards/rejected": -0.2591606676578522,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": 0.22318069636821747,
|
| 281 |
+
"logits/rejected": 0.33600229024887085,
|
| 282 |
+
"logps/chosen": -601.25390625,
|
| 283 |
+
"logps/rejected": -670.4763793945312,
|
| 284 |
+
"loss": 0.2971,
|
| 285 |
+
"rewards/accuracies": 0.6875,
|
| 286 |
+
"rewards/chosen": -0.23291774094104767,
|
| 287 |
+
"rewards/margins": 0.13643768429756165,
|
| 288 |
+
"rewards/rejected": -0.3693554401397705,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": 0.2132268249988556,
|
| 295 |
+
"logits/rejected": 0.3239246606826782,
|
| 296 |
+
"logps/chosen": -533.351806640625,
|
| 297 |
+
"logps/rejected": -600.036376953125,
|
| 298 |
+
"loss": 0.2656,
|
| 299 |
+
"rewards/accuracies": 0.737500011920929,
|
| 300 |
+
"rewards/chosen": -0.18504436314105988,
|
| 301 |
+
"rewards/margins": 0.11939746141433716,
|
| 302 |
+
"rewards/rejected": -0.3044418692588806,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": 0.19825667142868042,
|
| 309 |
+
"logits/rejected": 0.28912845253944397,
|
| 310 |
+
"logps/chosen": -540.4673461914062,
|
| 311 |
+
"logps/rejected": -592.4431762695312,
|
| 312 |
+
"loss": 0.2631,
|
| 313 |
+
"rewards/accuracies": 0.706250011920929,
|
| 314 |
+
"rewards/chosen": -0.19064101576805115,
|
| 315 |
+
"rewards/margins": 0.1160808652639389,
|
| 316 |
+
"rewards/rejected": -0.30672189593315125,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": 0.20192313194274902,
|
| 323 |
+
"logits/rejected": 0.3630911707878113,
|
| 324 |
+
"logps/chosen": -584.4435424804688,
|
| 325 |
+
"logps/rejected": -627.2318115234375,
|
| 326 |
+
"loss": 0.2925,
|
| 327 |
+
"rewards/accuracies": 0.625,
|
| 328 |
+
"rewards/chosen": -0.23791804909706116,
|
| 329 |
+
"rewards/margins": 0.10572359710931778,
|
| 330 |
+
"rewards/rejected": -0.3436416685581207,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": 0.2386132925748825,
|
| 337 |
+
"logits/rejected": 0.37924957275390625,
|
| 338 |
+
"logps/chosen": -515.5679931640625,
|
| 339 |
+
"logps/rejected": -620.7157592773438,
|
| 340 |
+
"loss": 0.2397,
|
| 341 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 342 |
+
"rewards/chosen": -0.1845434010028839,
|
| 343 |
+
"rewards/margins": 0.14988870918750763,
|
| 344 |
+
"rewards/rejected": -0.33443212509155273,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": 0.26459917426109314,
|
| 351 |
+
"logits/rejected": 0.4155924320220947,
|
| 352 |
+
"logps/chosen": -588.0615844726562,
|
| 353 |
+
"logps/rejected": -641.0905151367188,
|
| 354 |
+
"loss": 0.2725,
|
| 355 |
+
"rewards/accuracies": 0.668749988079071,
|
| 356 |
+
"rewards/chosen": -0.22051545977592468,
|
| 357 |
+
"rewards/margins": 0.13321301341056824,
|
| 358 |
+
"rewards/rejected": -0.3537284731864929,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": 0.272189199924469,
|
| 365 |
+
"logits/rejected": 0.39367181062698364,
|
| 366 |
+
"logps/chosen": -541.9008178710938,
|
| 367 |
+
"logps/rejected": -633.7440185546875,
|
| 368 |
+
"loss": 0.2557,
|
| 369 |
+
"rewards/accuracies": 0.71875,
|
| 370 |
+
"rewards/chosen": -0.212556391954422,
|
| 371 |
+
"rewards/margins": 0.14239820837974548,
|
| 372 |
+
"rewards/rejected": -0.3549546003341675,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": 0.2471778690814972,
|
| 379 |
+
"logits/rejected": 0.3926684260368347,
|
| 380 |
+
"logps/chosen": -590.729736328125,
|
| 381 |
+
"logps/rejected": -684.1608276367188,
|
| 382 |
+
"loss": 0.2675,
|
| 383 |
+
"rewards/accuracies": 0.6875,
|
| 384 |
+
"rewards/chosen": -0.25724658370018005,
|
| 385 |
+
"rewards/margins": 0.1302761733531952,
|
| 386 |
+
"rewards/rejected": -0.38752275705337524,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": 0.28343576192855835,
|
| 393 |
+
"logits/rejected": 0.40314382314682007,
|
| 394 |
+
"logps/chosen": -634.3505859375,
|
| 395 |
+
"logps/rejected": -726.0316772460938,
|
| 396 |
+
"loss": 0.2491,
|
| 397 |
+
"rewards/accuracies": 0.731249988079071,
|
| 398 |
+
"rewards/chosen": -0.26509755849838257,
|
| 399 |
+
"rewards/margins": 0.15606968104839325,
|
| 400 |
+
"rewards/rejected": -0.4211672246456146,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": 0.2620583474636078,
|
| 407 |
+
"logits/rejected": 0.44860973954200745,
|
| 408 |
+
"logps/chosen": -647.643798828125,
|
| 409 |
+
"logps/rejected": -790.6961669921875,
|
| 410 |
+
"loss": 0.239,
|
| 411 |
+
"rewards/accuracies": 0.737500011920929,
|
| 412 |
+
"rewards/chosen": -0.3211327791213989,
|
| 413 |
+
"rewards/margins": 0.18398535251617432,
|
| 414 |
+
"rewards/rejected": -0.505118191242218,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": 0.2921401858329773,
|
| 421 |
+
"logits/rejected": 0.3832509219646454,
|
| 422 |
+
"logps/chosen": -621.01708984375,
|
| 423 |
+
"logps/rejected": -749.591552734375,
|
| 424 |
+
"loss": 0.2637,
|
| 425 |
+
"rewards/accuracies": 0.706250011920929,
|
| 426 |
+
"rewards/chosen": -0.2830132246017456,
|
| 427 |
+
"rewards/margins": 0.17077818512916565,
|
| 428 |
+
"rewards/rejected": -0.45379146933555603,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": 0.25945979356765747,
|
| 435 |
+
"logits/rejected": 0.3613050580024719,
|
| 436 |
+
"logps/chosen": -625.9049072265625,
|
| 437 |
+
"logps/rejected": -672.7540893554688,
|
| 438 |
+
"loss": 0.2865,
|
| 439 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 440 |
+
"rewards/chosen": -0.249430850148201,
|
| 441 |
+
"rewards/margins": 0.13059653341770172,
|
| 442 |
+
"rewards/rejected": -0.3800273835659027,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": 0.2395036220550537,
|
| 449 |
+
"logits/rejected": 0.403165340423584,
|
| 450 |
+
"logps/chosen": -589.790283203125,
|
| 451 |
+
"logps/rejected": -662.6749267578125,
|
| 452 |
+
"loss": 0.2506,
|
| 453 |
+
"rewards/accuracies": 0.71875,
|
| 454 |
+
"rewards/chosen": -0.23766255378723145,
|
| 455 |
+
"rewards/margins": 0.1399877816438675,
|
| 456 |
+
"rewards/rejected": -0.37765032052993774,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": 0.22068071365356445,
|
| 463 |
+
"logits/rejected": 0.3754776120185852,
|
| 464 |
+
"logps/chosen": -586.9141845703125,
|
| 465 |
+
"logps/rejected": -691.4939575195312,
|
| 466 |
+
"loss": 0.2237,
|
| 467 |
+
"rewards/accuracies": 0.731249988079071,
|
| 468 |
+
"rewards/chosen": -0.2247442901134491,
|
| 469 |
+
"rewards/margins": 0.1634247750043869,
|
| 470 |
+
"rewards/rejected": -0.3881690800189972,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": 0.30473384261131287,
|
| 477 |
+
"logits/rejected": 0.3405100703239441,
|
| 478 |
+
"logps/chosen": -584.8270874023438,
|
| 479 |
+
"logps/rejected": -695.466796875,
|
| 480 |
+
"loss": 0.2435,
|
| 481 |
+
"rewards/accuracies": 0.731249988079071,
|
| 482 |
+
"rewards/chosen": -0.24067524075508118,
|
| 483 |
+
"rewards/margins": 0.1444186419248581,
|
| 484 |
+
"rewards/rejected": -0.3850938677787781,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": 0.21341583132743835,
|
| 491 |
+
"logits/rejected": 0.35156476497650146,
|
| 492 |
+
"logps/chosen": -598.0617065429688,
|
| 493 |
+
"logps/rejected": -732.0949096679688,
|
| 494 |
+
"loss": 0.2782,
|
| 495 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 496 |
+
"rewards/chosen": -0.25233131647109985,
|
| 497 |
+
"rewards/margins": 0.16543644666671753,
|
| 498 |
+
"rewards/rejected": -0.41776782274246216,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": 0.18200455605983734,
|
| 505 |
+
"logits/rejected": 0.29839521646499634,
|
| 506 |
+
"logps/chosen": -616.2686767578125,
|
| 507 |
+
"logps/rejected": -624.9378662109375,
|
| 508 |
+
"loss": 0.277,
|
| 509 |
+
"rewards/accuracies": 0.675000011920929,
|
| 510 |
+
"rewards/chosen": -0.23792997002601624,
|
| 511 |
+
"rewards/margins": 0.10732170194387436,
|
| 512 |
+
"rewards/rejected": -0.3452516794204712,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": 0.1593484878540039,
|
| 519 |
+
"logits/rejected": 0.2911715507507324,
|
| 520 |
+
"logps/chosen": -610.3870239257812,
|
| 521 |
+
"logps/rejected": -689.4932861328125,
|
| 522 |
+
"loss": 0.2368,
|
| 523 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 524 |
+
"rewards/chosen": -0.23754961788654327,
|
| 525 |
+
"rewards/margins": 0.149972602725029,
|
| 526 |
+
"rewards/rejected": -0.38752222061157227,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": 0.24016913771629333,
|
| 533 |
+
"logits/rejected": 0.27100852131843567,
|
| 534 |
+
"logps/chosen": -611.1376953125,
|
| 535 |
+
"logps/rejected": -736.8298950195312,
|
| 536 |
+
"loss": 0.2271,
|
| 537 |
+
"rewards/accuracies": 0.731249988079071,
|
| 538 |
+
"rewards/chosen": -0.26364389061927795,
|
| 539 |
+
"rewards/margins": 0.16632166504859924,
|
| 540 |
+
"rewards/rejected": -0.4299655556678772,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": 0.20674113929271698,
|
| 547 |
+
"logits/rejected": 0.3422744572162628,
|
| 548 |
+
"logps/chosen": -657.8020629882812,
|
| 549 |
+
"logps/rejected": -761.3865966796875,
|
| 550 |
+
"loss": 0.2234,
|
| 551 |
+
"rewards/accuracies": 0.737500011920929,
|
| 552 |
+
"rewards/chosen": -0.29639673233032227,
|
| 553 |
+
"rewards/margins": 0.1845850795507431,
|
| 554 |
+
"rewards/rejected": -0.48098182678222656,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": 0.2215661108493805,
|
| 561 |
+
"logits/rejected": 0.37389490008354187,
|
| 562 |
+
"logps/chosen": -650.2525634765625,
|
| 563 |
+
"logps/rejected": -728.6116943359375,
|
| 564 |
+
"loss": 0.2679,
|
| 565 |
+
"rewards/accuracies": 0.65625,
|
| 566 |
+
"rewards/chosen": -0.31919926404953003,
|
| 567 |
+
"rewards/margins": 0.15174493193626404,
|
| 568 |
+
"rewards/rejected": -0.47094422578811646,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": 0.2118716537952423,
|
| 575 |
+
"logits/rejected": 0.3723188638687134,
|
| 576 |
+
"logps/chosen": -704.6563720703125,
|
| 577 |
+
"logps/rejected": -808.8038330078125,
|
| 578 |
+
"loss": 0.2123,
|
| 579 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 580 |
+
"rewards/chosen": -0.31687626242637634,
|
| 581 |
+
"rewards/margins": 0.1988348513841629,
|
| 582 |
+
"rewards/rejected": -0.5157111883163452,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": 0.22452159225940704,
|
| 589 |
+
"logits/rejected": 0.37957900762557983,
|
| 590 |
+
"logps/chosen": -664.1927490234375,
|
| 591 |
+
"logps/rejected": -804.2332153320312,
|
| 592 |
+
"loss": 0.2293,
|
| 593 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 594 |
+
"rewards/chosen": -0.32922399044036865,
|
| 595 |
+
"rewards/margins": 0.18910188972949982,
|
| 596 |
+
"rewards/rejected": -0.5183258652687073,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": 0.2467646598815918,
|
| 603 |
+
"logits/rejected": 0.4089822769165039,
|
| 604 |
+
"logps/chosen": -735.5042114257812,
|
| 605 |
+
"logps/rejected": -830.4088134765625,
|
| 606 |
+
"loss": 0.2384,
|
| 607 |
+
"rewards/accuracies": 0.71875,
|
| 608 |
+
"rewards/chosen": -0.35978516936302185,
|
| 609 |
+
"rewards/margins": 0.164186030626297,
|
| 610 |
+
"rewards/rejected": -0.5239711999893188,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": 0.2413889616727829,
|
| 617 |
+
"logits/rejected": 0.336980938911438,
|
| 618 |
+
"logps/chosen": -716.7408447265625,
|
| 619 |
+
"logps/rejected": -788.5014038085938,
|
| 620 |
+
"loss": 0.2541,
|
| 621 |
+
"rewards/accuracies": 0.737500011920929,
|
| 622 |
+
"rewards/chosen": -0.32929089665412903,
|
| 623 |
+
"rewards/margins": 0.17145808041095734,
|
| 624 |
+
"rewards/rejected": -0.5007489919662476,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": 0.24484267830848694,
|
| 631 |
+
"logits/rejected": 0.3694288730621338,
|
| 632 |
+
"logps/chosen": -679.9339599609375,
|
| 633 |
+
"logps/rejected": -745.811279296875,
|
| 634 |
+
"loss": 0.2733,
|
| 635 |
+
"rewards/accuracies": 0.71875,
|
| 636 |
+
"rewards/chosen": -0.31394630670547485,
|
| 637 |
+
"rewards/margins": 0.154400035738945,
|
| 638 |
+
"rewards/rejected": -0.46834641695022583,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": 0.21108904480934143,
|
| 645 |
+
"logits/rejected": 0.41315707564353943,
|
| 646 |
+
"logps/chosen": -622.7232666015625,
|
| 647 |
+
"logps/rejected": -786.5183715820312,
|
| 648 |
+
"loss": 0.2156,
|
| 649 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 650 |
+
"rewards/chosen": -0.2859620153903961,
|
| 651 |
+
"rewards/margins": 0.19183282554149628,
|
| 652 |
+
"rewards/rejected": -0.477794885635376,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": 0.20401279628276825,
|
| 659 |
+
"logits/rejected": 0.33231475949287415,
|
| 660 |
+
"logps/chosen": -675.4547729492188,
|
| 661 |
+
"logps/rejected": -823.3021240234375,
|
| 662 |
+
"loss": 0.2434,
|
| 663 |
+
"rewards/accuracies": 0.762499988079071,
|
| 664 |
+
"rewards/chosen": -0.3432995080947876,
|
| 665 |
+
"rewards/margins": 0.17998036742210388,
|
| 666 |
+
"rewards/rejected": -0.5232799053192139,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": 0.2568013668060303,
|
| 673 |
+
"logits/rejected": 0.4122098982334137,
|
| 674 |
+
"logps/chosen": -765.1724853515625,
|
| 675 |
+
"logps/rejected": -959.1907348632812,
|
| 676 |
+
"loss": 0.1761,
|
| 677 |
+
"rewards/accuracies": 0.768750011920929,
|
| 678 |
+
"rewards/chosen": -0.40182775259017944,
|
| 679 |
+
"rewards/margins": 0.24152612686157227,
|
| 680 |
+
"rewards/rejected": -0.6433539390563965,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": 0.2044995129108429,
|
| 687 |
+
"logits/rejected": 0.43161505460739136,
|
| 688 |
+
"logps/chosen": -713.668701171875,
|
| 689 |
+
"logps/rejected": -906.75732421875,
|
| 690 |
+
"loss": 0.2101,
|
| 691 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 692 |
+
"rewards/chosen": -0.3692263960838318,
|
| 693 |
+
"rewards/margins": 0.2429826259613037,
|
| 694 |
+
"rewards/rejected": -0.6122089624404907,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": 0.17913873493671417,
|
| 701 |
+
"logits/rejected": 0.2993609309196472,
|
| 702 |
+
"logps/chosen": -633.526611328125,
|
| 703 |
+
"logps/rejected": -757.5572509765625,
|
| 704 |
+
"loss": 0.2595,
|
| 705 |
+
"rewards/accuracies": 0.706250011920929,
|
| 706 |
+
"rewards/chosen": -0.3094690442085266,
|
| 707 |
+
"rewards/margins": 0.1829945147037506,
|
| 708 |
+
"rewards/rejected": -0.4924635887145996,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": 0.15795853734016418,
|
| 715 |
+
"logits/rejected": 0.2824157774448395,
|
| 716 |
+
"logps/chosen": -617.8711547851562,
|
| 717 |
+
"logps/rejected": -708.7660522460938,
|
| 718 |
+
"loss": 0.243,
|
| 719 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 720 |
+
"rewards/chosen": -0.2822186350822449,
|
| 721 |
+
"rewards/margins": 0.15801504254341125,
|
| 722 |
+
"rewards/rejected": -0.4402337074279785,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": 0.1760106384754181,
|
| 729 |
+
"logits/rejected": 0.37177279591560364,
|
| 730 |
+
"logps/chosen": -664.34765625,
|
| 731 |
+
"logps/rejected": -775.051513671875,
|
| 732 |
+
"loss": 0.2209,
|
| 733 |
+
"rewards/accuracies": 0.737500011920929,
|
| 734 |
+
"rewards/chosen": -0.27559608221054077,
|
| 735 |
+
"rewards/margins": 0.18908929824829102,
|
| 736 |
+
"rewards/rejected": -0.4646853506565094,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": 0.14940790832042694,
|
| 743 |
+
"logits/rejected": 0.3582964241504669,
|
| 744 |
+
"logps/chosen": -674.0979614257812,
|
| 745 |
+
"logps/rejected": -782.9205932617188,
|
| 746 |
+
"loss": 0.2616,
|
| 747 |
+
"rewards/accuracies": 0.699999988079071,
|
| 748 |
+
"rewards/chosen": -0.32881468534469604,
|
| 749 |
+
"rewards/margins": 0.18159161508083344,
|
| 750 |
+
"rewards/rejected": -0.5104063153266907,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": 0.16591671109199524,
|
| 757 |
+
"logits/rejected": 0.2972433567047119,
|
| 758 |
+
"logps/chosen": -665.7161865234375,
|
| 759 |
+
"logps/rejected": -733.9686889648438,
|
| 760 |
+
"loss": 0.227,
|
| 761 |
+
"rewards/accuracies": 0.675000011920929,
|
| 762 |
+
"rewards/chosen": -0.3075326979160309,
|
| 763 |
+
"rewards/margins": 0.16415508091449738,
|
| 764 |
+
"rewards/rejected": -0.47168779373168945,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": 0.22560055553913116,
|
| 771 |
+
"logits/rejected": 0.29765042662620544,
|
| 772 |
+
"logps/chosen": -669.79443359375,
|
| 773 |
+
"logps/rejected": -775.9317626953125,
|
| 774 |
+
"loss": 0.2387,
|
| 775 |
+
"rewards/accuracies": 0.768750011920929,
|
| 776 |
+
"rewards/chosen": -0.3137567639350891,
|
| 777 |
+
"rewards/margins": 0.17480607330799103,
|
| 778 |
+
"rewards/rejected": -0.48856282234191895,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": 0.17669783532619476,
|
| 785 |
+
"logits/rejected": 0.35067084431648254,
|
| 786 |
+
"logps/chosen": -771.7174072265625,
|
| 787 |
+
"logps/rejected": -894.76416015625,
|
| 788 |
+
"loss": 0.2047,
|
| 789 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 790 |
+
"rewards/chosen": -0.3670485317707062,
|
| 791 |
+
"rewards/margins": 0.2496991902589798,
|
| 792 |
+
"rewards/rejected": -0.6167477369308472,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": 0.18999402225017548,
|
| 799 |
+
"logits/rejected": 0.3391267955303192,
|
| 800 |
+
"logps/chosen": -684.16943359375,
|
| 801 |
+
"logps/rejected": -815.6094360351562,
|
| 802 |
+
"loss": 0.2587,
|
| 803 |
+
"rewards/accuracies": 0.71875,
|
| 804 |
+
"rewards/chosen": -0.3591926693916321,
|
| 805 |
+
"rewards/margins": 0.1908990740776062,
|
| 806 |
+
"rewards/rejected": -0.5500917434692383,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": 0.14545580744743347,
|
| 813 |
+
"logits/rejected": 0.4434194564819336,
|
| 814 |
+
"logps/chosen": -728.5840454101562,
|
| 815 |
+
"logps/rejected": -858.6510009765625,
|
| 816 |
+
"loss": 0.2285,
|
| 817 |
+
"rewards/accuracies": 0.75,
|
| 818 |
+
"rewards/chosen": -0.343728631734848,
|
| 819 |
+
"rewards/margins": 0.2311449944972992,
|
| 820 |
+
"rewards/rejected": -0.5748736262321472,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": 0.23178081214427948,
|
| 827 |
+
"logits/rejected": 0.35969728231430054,
|
| 828 |
+
"logps/chosen": -674.2166137695312,
|
| 829 |
+
"logps/rejected": -835.3448486328125,
|
| 830 |
+
"loss": 0.1914,
|
| 831 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 832 |
+
"rewards/chosen": -0.3182132840156555,
|
| 833 |
+
"rewards/margins": 0.23260562121868134,
|
| 834 |
+
"rewards/rejected": -0.5508188605308533,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": 0.23522010445594788,
|
| 841 |
+
"logits/rejected": 0.3881956934928894,
|
| 842 |
+
"logps/chosen": -717.13720703125,
|
| 843 |
+
"logps/rejected": -823.9237060546875,
|
| 844 |
+
"loss": 0.2441,
|
| 845 |
+
"rewards/accuracies": 0.800000011920929,
|
| 846 |
+
"rewards/chosen": -0.3153195381164551,
|
| 847 |
+
"rewards/margins": 0.22255754470825195,
|
| 848 |
+
"rewards/rejected": -0.537877082824707,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": 0.18161171674728394,
|
| 855 |
+
"logits/rejected": 0.3819955289363861,
|
| 856 |
+
"logps/chosen": -676.7005004882812,
|
| 857 |
+
"logps/rejected": -885.69384765625,
|
| 858 |
+
"loss": 0.1855,
|
| 859 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 860 |
+
"rewards/chosen": -0.3431881070137024,
|
| 861 |
+
"rewards/margins": 0.26160916686058044,
|
| 862 |
+
"rewards/rejected": -0.6047972440719604,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": 0.15835508704185486,
|
| 869 |
+
"logits/rejected": 0.3054640293121338,
|
| 870 |
+
"logps/chosen": -675.2325439453125,
|
| 871 |
+
"logps/rejected": -845.0226440429688,
|
| 872 |
+
"loss": 0.2303,
|
| 873 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 874 |
+
"rewards/chosen": -0.3516426086425781,
|
| 875 |
+
"rewards/margins": 0.2019956409931183,
|
| 876 |
+
"rewards/rejected": -0.5536382794380188,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": 0.19981974363327026,
|
| 883 |
+
"logits/rejected": 0.31465253233909607,
|
| 884 |
+
"logps/chosen": -674.1165771484375,
|
| 885 |
+
"logps/rejected": -779.7503051757812,
|
| 886 |
+
"loss": 0.2182,
|
| 887 |
+
"rewards/accuracies": 0.737500011920929,
|
| 888 |
+
"rewards/chosen": -0.30122750997543335,
|
| 889 |
+
"rewards/margins": 0.17384760081768036,
|
| 890 |
+
"rewards/rejected": -0.4750750660896301,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": 0.13447639346122742,
|
| 897 |
+
"logits/rejected": 0.3254922926425934,
|
| 898 |
+
"logps/chosen": -601.1633911132812,
|
| 899 |
+
"logps/rejected": -713.8211669921875,
|
| 900 |
+
"loss": 0.2735,
|
| 901 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 902 |
+
"rewards/chosen": -0.26304560899734497,
|
| 903 |
+
"rewards/margins": 0.1775732934474945,
|
| 904 |
+
"rewards/rejected": -0.4406188428401947,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": 0.1678907424211502,
|
| 911 |
+
"logits/rejected": 0.29623210430145264,
|
| 912 |
+
"logps/chosen": -637.0558471679688,
|
| 913 |
+
"logps/rejected": -760.5277099609375,
|
| 914 |
+
"loss": 0.2456,
|
| 915 |
+
"rewards/accuracies": 0.71875,
|
| 916 |
+
"rewards/chosen": -0.29105207324028015,
|
| 917 |
+
"rewards/margins": 0.1802116334438324,
|
| 918 |
+
"rewards/rejected": -0.4712636470794678,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": 0.18655350804328918,
|
| 925 |
+
"logits/rejected": 0.3515748381614685,
|
| 926 |
+
"logps/chosen": -621.6171875,
|
| 927 |
+
"logps/rejected": -770.1412963867188,
|
| 928 |
+
"loss": 0.2009,
|
| 929 |
+
"rewards/accuracies": 0.793749988079071,
|
| 930 |
+
"rewards/chosen": -0.2730523347854614,
|
| 931 |
+
"rewards/margins": 0.20337846875190735,
|
| 932 |
+
"rewards/rejected": -0.476430743932724,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": 0.2070898562669754,
|
| 939 |
+
"logits/rejected": 0.3552184998989105,
|
| 940 |
+
"logps/chosen": -644.9053955078125,
|
| 941 |
+
"logps/rejected": -800.6888427734375,
|
| 942 |
+
"loss": 0.2057,
|
| 943 |
+
"rewards/accuracies": 0.793749988079071,
|
| 944 |
+
"rewards/chosen": -0.2831494212150574,
|
| 945 |
+
"rewards/margins": 0.21793799102306366,
|
| 946 |
+
"rewards/rejected": -0.501087486743927,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": 0.16107818484306335,
|
| 953 |
+
"logits/rejected": 0.32218271493911743,
|
| 954 |
+
"logps/chosen": -676.8900146484375,
|
| 955 |
+
"logps/rejected": -834.2060546875,
|
| 956 |
+
"loss": 0.1891,
|
| 957 |
+
"rewards/accuracies": 0.731249988079071,
|
| 958 |
+
"rewards/chosen": -0.3277270495891571,
|
| 959 |
+
"rewards/margins": 0.22579827904701233,
|
| 960 |
+
"rewards/rejected": -0.5535253286361694,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": 0.20739403367042542,
|
| 967 |
+
"logits/rejected": 0.26471713185310364,
|
| 968 |
+
"logps/chosen": -687.0540161132812,
|
| 969 |
+
"logps/rejected": -849.7962646484375,
|
| 970 |
+
"loss": 0.2414,
|
| 971 |
+
"rewards/accuracies": 0.737500011920929,
|
| 972 |
+
"rewards/chosen": -0.37053388357162476,
|
| 973 |
+
"rewards/margins": 0.19931861758232117,
|
| 974 |
+
"rewards/rejected": -0.5698524713516235,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": 0.20264072716236115,
|
| 981 |
+
"logits/rejected": 0.2857401669025421,
|
| 982 |
+
"logps/chosen": -638.552734375,
|
| 983 |
+
"logps/rejected": -793.6614990234375,
|
| 984 |
+
"loss": 0.2271,
|
| 985 |
+
"rewards/accuracies": 0.731249988079071,
|
| 986 |
+
"rewards/chosen": -0.32019636034965515,
|
| 987 |
+
"rewards/margins": 0.1985076367855072,
|
| 988 |
+
"rewards/rejected": -0.5187040567398071,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": 0.17015784978866577,
|
| 995 |
+
"logits/rejected": 0.25645551085472107,
|
| 996 |
+
"logps/chosen": -696.7833862304688,
|
| 997 |
+
"logps/rejected": -824.9973754882812,
|
| 998 |
+
"loss": 0.2486,
|
| 999 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1000 |
+
"rewards/chosen": -0.36269837617874146,
|
| 1001 |
+
"rewards/margins": 0.18247218430042267,
|
| 1002 |
+
"rewards/rejected": -0.5451706051826477,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": 0.2156047374010086,
|
| 1009 |
+
"logits/rejected": 0.20423674583435059,
|
| 1010 |
+
"logps/chosen": -619.2033081054688,
|
| 1011 |
+
"logps/rejected": -690.5067138671875,
|
| 1012 |
+
"loss": 0.3245,
|
| 1013 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1014 |
+
"rewards/chosen": -0.32582998275756836,
|
| 1015 |
+
"rewards/margins": 0.12705637514591217,
|
| 1016 |
+
"rewards/rejected": -0.45288634300231934,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": 0.14758387207984924,
|
| 1023 |
+
"logits/rejected": 0.3225356340408325,
|
| 1024 |
+
"logps/chosen": -671.9241333007812,
|
| 1025 |
+
"logps/rejected": -804.1224365234375,
|
| 1026 |
+
"loss": 0.2129,
|
| 1027 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1028 |
+
"rewards/chosen": -0.30027109384536743,
|
| 1029 |
+
"rewards/margins": 0.19518795609474182,
|
| 1030 |
+
"rewards/rejected": -0.49545907974243164,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": 0.1207294911146164,
|
| 1037 |
+
"logits/rejected": 0.3056190311908722,
|
| 1038 |
+
"logps/chosen": -655.4552001953125,
|
| 1039 |
+
"logps/rejected": -807.0453491210938,
|
| 1040 |
+
"loss": 0.1871,
|
| 1041 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1042 |
+
"rewards/chosen": -0.29568520188331604,
|
| 1043 |
+
"rewards/margins": 0.21632209420204163,
|
| 1044 |
+
"rewards/rejected": -0.5120072960853577,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": 0.17697741091251373,
|
| 1051 |
+
"logits/rejected": 0.2939094603061676,
|
| 1052 |
+
"logps/chosen": -667.5819091796875,
|
| 1053 |
+
"logps/rejected": -791.62353515625,
|
| 1054 |
+
"loss": 0.2156,
|
| 1055 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1056 |
+
"rewards/chosen": -0.32927432656288147,
|
| 1057 |
+
"rewards/margins": 0.17469336092472076,
|
| 1058 |
+
"rewards/rejected": -0.5039676427841187,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": 0.15482628345489502,
|
| 1065 |
+
"logits/rejected": 0.3409688174724579,
|
| 1066 |
+
"logps/chosen": -716.8922119140625,
|
| 1067 |
+
"logps/rejected": -896.0595703125,
|
| 1068 |
+
"loss": 0.1907,
|
| 1069 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1070 |
+
"rewards/chosen": -0.35755792260169983,
|
| 1071 |
+
"rewards/margins": 0.24695225059986115,
|
| 1072 |
+
"rewards/rejected": -0.6045101881027222,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": 0.17361067235469818,
|
| 1079 |
+
"logits/rejected": 0.3247506320476532,
|
| 1080 |
+
"logps/chosen": -759.477294921875,
|
| 1081 |
+
"logps/rejected": -859.95703125,
|
| 1082 |
+
"loss": 0.2266,
|
| 1083 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1084 |
+
"rewards/chosen": -0.3791542947292328,
|
| 1085 |
+
"rewards/margins": 0.19504983723163605,
|
| 1086 |
+
"rewards/rejected": -0.5742040872573853,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": 0.1680970937013626,
|
| 1093 |
+
"logits/rejected": 0.3031509816646576,
|
| 1094 |
+
"logps/chosen": -673.4447021484375,
|
| 1095 |
+
"logps/rejected": -791.8770751953125,
|
| 1096 |
+
"loss": 0.2111,
|
| 1097 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1098 |
+
"rewards/chosen": -0.33166688680648804,
|
| 1099 |
+
"rewards/margins": 0.19004380702972412,
|
| 1100 |
+
"rewards/rejected": -0.5217106938362122,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": 0.1661594659090042,
|
| 1107 |
+
"logits/rejected": 0.29215800762176514,
|
| 1108 |
+
"logps/chosen": -656.0603637695312,
|
| 1109 |
+
"logps/rejected": -792.6107788085938,
|
| 1110 |
+
"loss": 0.2202,
|
| 1111 |
+
"rewards/accuracies": 0.71875,
|
| 1112 |
+
"rewards/chosen": -0.33995765447616577,
|
| 1113 |
+
"rewards/margins": 0.1824071854352951,
|
| 1114 |
+
"rewards/rejected": -0.5223647952079773,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": 0.1200464516878128,
|
| 1121 |
+
"logits/rejected": 0.2862261235713959,
|
| 1122 |
+
"logps/chosen": -711.8590087890625,
|
| 1123 |
+
"logps/rejected": -884.7125244140625,
|
| 1124 |
+
"loss": 0.1871,
|
| 1125 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1126 |
+
"rewards/chosen": -0.3494313359260559,
|
| 1127 |
+
"rewards/margins": 0.2312242090702057,
|
| 1128 |
+
"rewards/rejected": -0.5806554555892944,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": 0.11773556470870972,
|
| 1135 |
+
"logits/rejected": 0.29994910955429077,
|
| 1136 |
+
"logps/chosen": -680.5064086914062,
|
| 1137 |
+
"logps/rejected": -856.234375,
|
| 1138 |
+
"loss": 0.1885,
|
| 1139 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1140 |
+
"rewards/chosen": -0.35676535964012146,
|
| 1141 |
+
"rewards/margins": 0.22748513519763947,
|
| 1142 |
+
"rewards/rejected": -0.5842504501342773,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": 0.09288445115089417,
|
| 1149 |
+
"logits/rejected": 0.33626627922058105,
|
| 1150 |
+
"logps/chosen": -774.9942626953125,
|
| 1151 |
+
"logps/rejected": -963.0445556640625,
|
| 1152 |
+
"loss": 0.2172,
|
| 1153 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1154 |
+
"rewards/chosen": -0.40824300050735474,
|
| 1155 |
+
"rewards/margins": 0.24136242270469666,
|
| 1156 |
+
"rewards/rejected": -0.649605393409729,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": 0.1620679795742035,
|
| 1163 |
+
"logits/rejected": 0.31993260979652405,
|
| 1164 |
+
"logps/chosen": -728.768798828125,
|
| 1165 |
+
"logps/rejected": -806.7156982421875,
|
| 1166 |
+
"loss": 0.2566,
|
| 1167 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1168 |
+
"rewards/chosen": -0.3659815490245819,
|
| 1169 |
+
"rewards/margins": 0.17412114143371582,
|
| 1170 |
+
"rewards/rejected": -0.5401026606559753,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": 0.14278681576251984,
|
| 1177 |
+
"logits/rejected": 0.32590746879577637,
|
| 1178 |
+
"logps/chosen": -703.8787231445312,
|
| 1179 |
+
"logps/rejected": -857.1585083007812,
|
| 1180 |
+
"loss": 0.2124,
|
| 1181 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1182 |
+
"rewards/chosen": -0.3663283884525299,
|
| 1183 |
+
"rewards/margins": 0.21885888278484344,
|
| 1184 |
+
"rewards/rejected": -0.5851873159408569,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": 0.19465771317481995,
|
| 1191 |
+
"logits/rejected": 0.28358665108680725,
|
| 1192 |
+
"logps/chosen": -671.1470336914062,
|
| 1193 |
+
"logps/rejected": -810.312744140625,
|
| 1194 |
+
"loss": 0.2081,
|
| 1195 |
+
"rewards/accuracies": 0.75,
|
| 1196 |
+
"rewards/chosen": -0.31882521510124207,
|
| 1197 |
+
"rewards/margins": 0.20828664302825928,
|
| 1198 |
+
"rewards/rejected": -0.5271118879318237,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": 0.12119020521640778,
|
| 1205 |
+
"logits/rejected": 0.3242005705833435,
|
| 1206 |
+
"logps/chosen": -680.9307861328125,
|
| 1207 |
+
"logps/rejected": -822.7205810546875,
|
| 1208 |
+
"loss": 0.2258,
|
| 1209 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1210 |
+
"rewards/chosen": -0.328025221824646,
|
| 1211 |
+
"rewards/margins": 0.21506837010383606,
|
| 1212 |
+
"rewards/rejected": -0.5430935621261597,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": 0.11271035671234131,
|
| 1219 |
+
"logits/rejected": 0.2887061536312103,
|
| 1220 |
+
"logps/chosen": -675.8961181640625,
|
| 1221 |
+
"logps/rejected": -808.447265625,
|
| 1222 |
+
"loss": 0.2158,
|
| 1223 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1224 |
+
"rewards/chosen": -0.29701152443885803,
|
| 1225 |
+
"rewards/margins": 0.21012258529663086,
|
| 1226 |
+
"rewards/rejected": -0.5071341395378113,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": 0.15118266642093658,
|
| 1233 |
+
"logits/rejected": 0.29830652475357056,
|
| 1234 |
+
"logps/chosen": -648.36767578125,
|
| 1235 |
+
"logps/rejected": -793.2464599609375,
|
| 1236 |
+
"loss": 0.2488,
|
| 1237 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1238 |
+
"rewards/chosen": -0.30504560470581055,
|
| 1239 |
+
"rewards/margins": 0.21465754508972168,
|
| 1240 |
+
"rewards/rejected": -0.5197031497955322,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": 0.10310302674770355,
|
| 1247 |
+
"logits/rejected": 0.26414334774017334,
|
| 1248 |
+
"logps/chosen": -628.9229736328125,
|
| 1249 |
+
"logps/rejected": -789.9716186523438,
|
| 1250 |
+
"loss": 0.2024,
|
| 1251 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1252 |
+
"rewards/chosen": -0.2890340983867645,
|
| 1253 |
+
"rewards/margins": 0.2192925661802292,
|
| 1254 |
+
"rewards/rejected": -0.5083267092704773,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": 0.12954168021678925,
|
| 1261 |
+
"logits/rejected": 0.2752276659011841,
|
| 1262 |
+
"logps/chosen": -620.2590942382812,
|
| 1263 |
+
"logps/rejected": -767.0093994140625,
|
| 1264 |
+
"loss": 0.2052,
|
| 1265 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1266 |
+
"rewards/chosen": -0.275544673204422,
|
| 1267 |
+
"rewards/margins": 0.21567711234092712,
|
| 1268 |
+
"rewards/rejected": -0.4912218153476715,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": 0.12713904678821564,
|
| 1275 |
+
"logits/rejected": 0.2954176068305969,
|
| 1276 |
+
"logps/chosen": -646.6031494140625,
|
| 1277 |
+
"logps/rejected": -788.7861938476562,
|
| 1278 |
+
"loss": 0.2272,
|
| 1279 |
+
"rewards/accuracies": 0.71875,
|
| 1280 |
+
"rewards/chosen": -0.2984674274921417,
|
| 1281 |
+
"rewards/margins": 0.20731091499328613,
|
| 1282 |
+
"rewards/rejected": -0.5057783722877502,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": 0.11980082839727402,
|
| 1289 |
+
"logits/rejected": 0.20131537318229675,
|
| 1290 |
+
"logps/chosen": -652.871337890625,
|
| 1291 |
+
"logps/rejected": -815.8560791015625,
|
| 1292 |
+
"loss": 0.2053,
|
| 1293 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1294 |
+
"rewards/chosen": -0.2841240167617798,
|
| 1295 |
+
"rewards/margins": 0.2087261974811554,
|
| 1296 |
+
"rewards/rejected": -0.49285024404525757,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": 0.11366409063339233,
|
| 1303 |
+
"logits/rejected": 0.20989951491355896,
|
| 1304 |
+
"logps/chosen": -632.2529296875,
|
| 1305 |
+
"logps/rejected": -742.0712280273438,
|
| 1306 |
+
"loss": 0.2521,
|
| 1307 |
+
"rewards/accuracies": 0.637499988079071,
|
| 1308 |
+
"rewards/chosen": -0.30224618315696716,
|
| 1309 |
+
"rewards/margins": 0.17021192610263824,
|
| 1310 |
+
"rewards/rejected": -0.4724581241607666,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": 0.12950178980827332,
|
| 1317 |
+
"logits/rejected": 0.205675408244133,
|
| 1318 |
+
"logps/chosen": -666.3436279296875,
|
| 1319 |
+
"logps/rejected": -803.6804809570312,
|
| 1320 |
+
"loss": 0.2306,
|
| 1321 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1322 |
+
"rewards/chosen": -0.3005353808403015,
|
| 1323 |
+
"rewards/margins": 0.2294267863035202,
|
| 1324 |
+
"rewards/rejected": -0.5299621820449829,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": 0.09100206196308136,
|
| 1331 |
+
"logits/rejected": 0.23861780762672424,
|
| 1332 |
+
"logps/chosen": -660.6749267578125,
|
| 1333 |
+
"logps/rejected": -811.4717407226562,
|
| 1334 |
+
"loss": 0.2064,
|
| 1335 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1336 |
+
"rewards/chosen": -0.2903476655483246,
|
| 1337 |
+
"rewards/margins": 0.21249572932720184,
|
| 1338 |
+
"rewards/rejected": -0.50284343957901,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": 0.11082760244607925,
|
| 1345 |
+
"logits/rejected": 0.23662987351417542,
|
| 1346 |
+
"logps/chosen": -665.4554443359375,
|
| 1347 |
+
"logps/rejected": -868.9638671875,
|
| 1348 |
+
"loss": 0.201,
|
| 1349 |
+
"rewards/accuracies": 0.75,
|
| 1350 |
+
"rewards/chosen": -0.34308990836143494,
|
| 1351 |
+
"rewards/margins": 0.24668097496032715,
|
| 1352 |
+
"rewards/rejected": -0.5897709131240845,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": 0.15180227160453796,
|
| 1359 |
+
"logits/rejected": 0.21313562989234924,
|
| 1360 |
+
"logps/chosen": -717.8250732421875,
|
| 1361 |
+
"logps/rejected": -806.0482177734375,
|
| 1362 |
+
"loss": 0.2638,
|
| 1363 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1364 |
+
"rewards/chosen": -0.3388670086860657,
|
| 1365 |
+
"rewards/margins": 0.1811041533946991,
|
| 1366 |
+
"rewards/rejected": -0.5199711322784424,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": 0.07411827147006989,
|
| 1373 |
+
"logits/rejected": 0.16980966925621033,
|
| 1374 |
+
"logps/chosen": -684.9701538085938,
|
| 1375 |
+
"logps/rejected": -862.4952392578125,
|
| 1376 |
+
"loss": 0.2099,
|
| 1377 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1378 |
+
"rewards/chosen": -0.362778902053833,
|
| 1379 |
+
"rewards/margins": 0.2055092304944992,
|
| 1380 |
+
"rewards/rejected": -0.5682881474494934,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": 0.10116670280694962,
|
| 1387 |
+
"logits/rejected": 0.21950002014636993,
|
| 1388 |
+
"logps/chosen": -674.0352783203125,
|
| 1389 |
+
"logps/rejected": -800.4089965820312,
|
| 1390 |
+
"loss": 0.2249,
|
| 1391 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1392 |
+
"rewards/chosen": -0.3368411660194397,
|
| 1393 |
+
"rewards/margins": 0.1978548765182495,
|
| 1394 |
+
"rewards/rejected": -0.5346960425376892,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": 0.0984363779425621,
|
| 1401 |
+
"logits/rejected": 0.2318364828824997,
|
| 1402 |
+
"logps/chosen": -728.8323974609375,
|
| 1403 |
+
"logps/rejected": -877.23681640625,
|
| 1404 |
+
"loss": 0.2061,
|
| 1405 |
+
"rewards/accuracies": 0.78125,
|
| 1406 |
+
"rewards/chosen": -0.36335819959640503,
|
| 1407 |
+
"rewards/margins": 0.22163307666778564,
|
| 1408 |
+
"rewards/rejected": -0.5849912762641907,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": 0.12672573328018188,
|
| 1415 |
+
"logits/rejected": 0.19936290383338928,
|
| 1416 |
+
"logps/chosen": -735.6030883789062,
|
| 1417 |
+
"logps/rejected": -855.2264404296875,
|
| 1418 |
+
"loss": 0.2383,
|
| 1419 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1420 |
+
"rewards/chosen": -0.3681355118751526,
|
| 1421 |
+
"rewards/margins": 0.18624527752399445,
|
| 1422 |
+
"rewards/rejected": -0.5543807744979858,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": 0.09366180747747421,
|
| 1429 |
+
"logits/rejected": 0.24154536426067352,
|
| 1430 |
+
"logps/chosen": -741.3905029296875,
|
| 1431 |
+
"logps/rejected": -863.9640502929688,
|
| 1432 |
+
"loss": 0.2183,
|
| 1433 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1434 |
+
"rewards/chosen": -0.3723335266113281,
|
| 1435 |
+
"rewards/margins": 0.20260421931743622,
|
| 1436 |
+
"rewards/rejected": -0.5749377608299255,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": 0.12707850337028503,
|
| 1443 |
+
"logits/rejected": 0.262873113155365,
|
| 1444 |
+
"logps/chosen": -742.9122314453125,
|
| 1445 |
+
"logps/rejected": -812.1138916015625,
|
| 1446 |
+
"loss": 0.2556,
|
| 1447 |
+
"rewards/accuracies": 0.71875,
|
| 1448 |
+
"rewards/chosen": -0.34759730100631714,
|
| 1449 |
+
"rewards/margins": 0.17379847168922424,
|
| 1450 |
+
"rewards/rejected": -0.5213958024978638,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": 0.06376073509454727,
|
| 1457 |
+
"logits/rejected": 0.2528199851512909,
|
| 1458 |
+
"logps/chosen": -648.4464721679688,
|
| 1459 |
+
"logps/rejected": -814.0970458984375,
|
| 1460 |
+
"loss": 0.238,
|
| 1461 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1462 |
+
"rewards/chosen": -0.31961458921432495,
|
| 1463 |
+
"rewards/margins": 0.20580220222473145,
|
| 1464 |
+
"rewards/rejected": -0.5254167318344116,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": 0.08957502990961075,
|
| 1471 |
+
"logits/rejected": 0.18970297276973724,
|
| 1472 |
+
"logps/chosen": -675.5179443359375,
|
| 1473 |
+
"logps/rejected": -772.6138916015625,
|
| 1474 |
+
"loss": 0.2382,
|
| 1475 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1476 |
+
"rewards/chosen": -0.31163010001182556,
|
| 1477 |
+
"rewards/margins": 0.17897368967533112,
|
| 1478 |
+
"rewards/rejected": -0.49060383439064026,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": 0.12193132936954498,
|
| 1485 |
+
"logits/rejected": 0.2238079011440277,
|
| 1486 |
+
"logps/chosen": -623.6652221679688,
|
| 1487 |
+
"logps/rejected": -791.8870849609375,
|
| 1488 |
+
"loss": 0.1977,
|
| 1489 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1490 |
+
"rewards/chosen": -0.3007582128047943,
|
| 1491 |
+
"rewards/margins": 0.20639415085315704,
|
| 1492 |
+
"rewards/rejected": -0.5071523785591125,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": 0.09605869650840759,
|
| 1499 |
+
"logits/rejected": 0.18777312338352203,
|
| 1500 |
+
"logps/chosen": -642.5596313476562,
|
| 1501 |
+
"logps/rejected": -781.3046875,
|
| 1502 |
+
"loss": 0.1997,
|
| 1503 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1504 |
+
"rewards/chosen": -0.30638837814331055,
|
| 1505 |
+
"rewards/margins": 0.18436425924301147,
|
| 1506 |
+
"rewards/rejected": -0.490752637386322,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": 0.09697475284337997,
|
| 1513 |
+
"logits/rejected": 0.21658281981945038,
|
| 1514 |
+
"logps/chosen": -663.3118286132812,
|
| 1515 |
+
"logps/rejected": -803.4898681640625,
|
| 1516 |
+
"loss": 0.1913,
|
| 1517 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1518 |
+
"rewards/chosen": -0.2993699908256531,
|
| 1519 |
+
"rewards/margins": 0.22615595161914825,
|
| 1520 |
+
"rewards/rejected": -0.5255259275436401,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": 0.1070629209280014,
|
| 1527 |
+
"logits/rejected": 0.25807613134384155,
|
| 1528 |
+
"logps/chosen": -694.64111328125,
|
| 1529 |
+
"logps/rejected": -816.5810546875,
|
| 1530 |
+
"loss": 0.2196,
|
| 1531 |
+
"rewards/accuracies": 0.78125,
|
| 1532 |
+
"rewards/chosen": -0.32364705204963684,
|
| 1533 |
+
"rewards/margins": 0.22359292209148407,
|
| 1534 |
+
"rewards/rejected": -0.5472399592399597,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": 0.11755505949258804,
|
| 1541 |
+
"logits/rejected": 0.33424052596092224,
|
| 1542 |
+
"logps/chosen": -726.0146484375,
|
| 1543 |
+
"logps/rejected": -885.8994140625,
|
| 1544 |
+
"loss": 0.2243,
|
| 1545 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1546 |
+
"rewards/chosen": -0.37689560651779175,
|
| 1547 |
+
"rewards/margins": 0.21640503406524658,
|
| 1548 |
+
"rewards/rejected": -0.5933005809783936,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": 0.08579425513744354,
|
| 1555 |
+
"logits/rejected": 0.2378162145614624,
|
| 1556 |
+
"logps/chosen": -713.3672485351562,
|
| 1557 |
+
"logps/rejected": -939.802734375,
|
| 1558 |
+
"loss": 0.1748,
|
| 1559 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1560 |
+
"rewards/chosen": -0.37114056944847107,
|
| 1561 |
+
"rewards/margins": 0.28332680463790894,
|
| 1562 |
+
"rewards/rejected": -0.6544674038887024,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": 0.06883491575717926,
|
| 1569 |
+
"logits/rejected": 0.21484391391277313,
|
| 1570 |
+
"logps/chosen": -713.2088623046875,
|
| 1571 |
+
"logps/rejected": -950.1226806640625,
|
| 1572 |
+
"loss": 0.2204,
|
| 1573 |
+
"rewards/accuracies": 0.75,
|
| 1574 |
+
"rewards/chosen": -0.38237085938453674,
|
| 1575 |
+
"rewards/margins": 0.26614242792129517,
|
| 1576 |
+
"rewards/rejected": -0.6485133171081543,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": 0.12803800404071808,
|
| 1583 |
+
"logits/rejected": 0.1985175758600235,
|
| 1584 |
+
"logps/chosen": -675.037841796875,
|
| 1585 |
+
"logps/rejected": -824.63427734375,
|
| 1586 |
+
"loss": 0.2147,
|
| 1587 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1588 |
+
"rewards/chosen": -0.3487189710140228,
|
| 1589 |
+
"rewards/margins": 0.19292229413986206,
|
| 1590 |
+
"rewards/rejected": -0.5416412949562073,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": 0.08092626929283142,
|
| 1597 |
+
"logits/rejected": 0.22723694145679474,
|
| 1598 |
+
"logps/chosen": -757.0364990234375,
|
| 1599 |
+
"logps/rejected": -870.3096923828125,
|
| 1600 |
+
"loss": 0.1899,
|
| 1601 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1602 |
+
"rewards/chosen": -0.3505310118198395,
|
| 1603 |
+
"rewards/margins": 0.22947946190834045,
|
| 1604 |
+
"rewards/rejected": -0.5800104141235352,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": 0.10787869989871979,
|
| 1611 |
+
"logits/rejected": 0.1968112587928772,
|
| 1612 |
+
"logps/chosen": -630.917236328125,
|
| 1613 |
+
"logps/rejected": -771.1486206054688,
|
| 1614 |
+
"loss": 0.2133,
|
| 1615 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1616 |
+
"rewards/chosen": -0.3110920190811157,
|
| 1617 |
+
"rewards/margins": 0.18016596138477325,
|
| 1618 |
+
"rewards/rejected": -0.4912579655647278,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": 0.1406387984752655,
|
| 1625 |
+
"logits/rejected": 0.22435446083545685,
|
| 1626 |
+
"logps/chosen": -709.8244018554688,
|
| 1627 |
+
"logps/rejected": -844.6785278320312,
|
| 1628 |
+
"loss": 0.2164,
|
| 1629 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1630 |
+
"rewards/chosen": -0.34992507100105286,
|
| 1631 |
+
"rewards/margins": 0.2139689177274704,
|
| 1632 |
+
"rewards/rejected": -0.5638940334320068,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": 0.13347899913787842,
|
| 1639 |
+
"logits/rejected": 0.2880741059780121,
|
| 1640 |
+
"logps/chosen": -704.9302978515625,
|
| 1641 |
+
"logps/rejected": -873.6126708984375,
|
| 1642 |
+
"loss": 0.2,
|
| 1643 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1644 |
+
"rewards/chosen": -0.3522919714450836,
|
| 1645 |
+
"rewards/margins": 0.2265801876783371,
|
| 1646 |
+
"rewards/rejected": -0.5788721442222595,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": 0.08221012353897095,
|
| 1653 |
+
"logits/rejected": 0.25464189052581787,
|
| 1654 |
+
"logps/chosen": -757.3726806640625,
|
| 1655 |
+
"logps/rejected": -926.8704223632812,
|
| 1656 |
+
"loss": 0.2066,
|
| 1657 |
+
"rewards/accuracies": 0.78125,
|
| 1658 |
+
"rewards/chosen": -0.37381109595298767,
|
| 1659 |
+
"rewards/margins": 0.23461690545082092,
|
| 1660 |
+
"rewards/rejected": -0.6084280014038086,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": 0.13979586958885193,
|
| 1667 |
+
"logits/rejected": 0.24614198505878448,
|
| 1668 |
+
"logps/chosen": -731.94140625,
|
| 1669 |
+
"logps/rejected": -828.9541015625,
|
| 1670 |
+
"loss": 0.2687,
|
| 1671 |
+
"rewards/accuracies": 0.6875,
|
| 1672 |
+
"rewards/chosen": -0.3592011630535126,
|
| 1673 |
+
"rewards/margins": 0.1861731857061386,
|
| 1674 |
+
"rewards/rejected": -0.5453742742538452,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": 0.09579949080944061,
|
| 1681 |
+
"logits/rejected": 0.22970926761627197,
|
| 1682 |
+
"logps/chosen": -669.8802490234375,
|
| 1683 |
+
"logps/rejected": -843.9857177734375,
|
| 1684 |
+
"loss": 0.2002,
|
| 1685 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1686 |
+
"rewards/chosen": -0.3365887999534607,
|
| 1687 |
+
"rewards/margins": 0.22111590206623077,
|
| 1688 |
+
"rewards/rejected": -0.5577046275138855,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": 0.1350405365228653,
|
| 1695 |
+
"logits/rejected": 0.2594318985939026,
|
| 1696 |
+
"logps/chosen": -712.8129272460938,
|
| 1697 |
+
"logps/rejected": -832.94677734375,
|
| 1698 |
+
"loss": 0.2323,
|
| 1699 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1700 |
+
"rewards/chosen": -0.34674012660980225,
|
| 1701 |
+
"rewards/margins": 0.1996394544839859,
|
| 1702 |
+
"rewards/rejected": -0.5463796257972717,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": 0.16419488191604614,
|
| 1709 |
+
"logits/rejected": 0.25972408056259155,
|
| 1710 |
+
"logps/chosen": -692.2588500976562,
|
| 1711 |
+
"logps/rejected": -844.2239990234375,
|
| 1712 |
+
"loss": 0.2063,
|
| 1713 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1714 |
+
"rewards/chosen": -0.3172731101512909,
|
| 1715 |
+
"rewards/margins": 0.21843883395195007,
|
| 1716 |
+
"rewards/rejected": -0.5357118844985962,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": 0.12711533904075623,
|
| 1723 |
+
"logits/rejected": 0.24427728354930878,
|
| 1724 |
+
"logps/chosen": -723.783935546875,
|
| 1725 |
+
"logps/rejected": -863.6396484375,
|
| 1726 |
+
"loss": 0.2058,
|
| 1727 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1728 |
+
"rewards/chosen": -0.33928173780441284,
|
| 1729 |
+
"rewards/margins": 0.23463325202465057,
|
| 1730 |
+
"rewards/rejected": -0.5739150047302246,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": 0.10758714377880096,
|
| 1737 |
+
"logits/rejected": 0.2805503308773041,
|
| 1738 |
+
"logps/chosen": -701.0147705078125,
|
| 1739 |
+
"logps/rejected": -815.3477783203125,
|
| 1740 |
+
"loss": 0.2015,
|
| 1741 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1742 |
+
"rewards/chosen": -0.3337828814983368,
|
| 1743 |
+
"rewards/margins": 0.2107526808977127,
|
| 1744 |
+
"rewards/rejected": -0.5445355176925659,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": 0.12466589361429214,
|
| 1751 |
+
"logits/rejected": 0.26773038506507874,
|
| 1752 |
+
"logps/chosen": -640.2819213867188,
|
| 1753 |
+
"logps/rejected": -786.9939575195312,
|
| 1754 |
+
"loss": 0.2169,
|
| 1755 |
+
"rewards/accuracies": 0.71875,
|
| 1756 |
+
"rewards/chosen": -0.33266982436180115,
|
| 1757 |
+
"rewards/margins": 0.1839940994977951,
|
| 1758 |
+
"rewards/rejected": -0.5166639089584351,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": 0.12364304065704346,
|
| 1765 |
+
"logits/rejected": 0.25227856636047363,
|
| 1766 |
+
"logps/chosen": -671.4842529296875,
|
| 1767 |
+
"logps/rejected": -803.79345703125,
|
| 1768 |
+
"loss": 0.2247,
|
| 1769 |
+
"rewards/accuracies": 0.71875,
|
| 1770 |
+
"rewards/chosen": -0.3221370577812195,
|
| 1771 |
+
"rewards/margins": 0.21037554740905762,
|
| 1772 |
+
"rewards/rejected": -0.5325126051902771,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": 0.13939639925956726,
|
| 1779 |
+
"logits/rejected": 0.23471331596374512,
|
| 1780 |
+
"logps/chosen": -714.9220581054688,
|
| 1781 |
+
"logps/rejected": -864.4716796875,
|
| 1782 |
+
"loss": 0.2297,
|
| 1783 |
+
"rewards/accuracies": 0.71875,
|
| 1784 |
+
"rewards/chosen": -0.3482537567615509,
|
| 1785 |
+
"rewards/margins": 0.22038355469703674,
|
| 1786 |
+
"rewards/rejected": -0.5686372518539429,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": 0.16542884707450867,
|
| 1793 |
+
"logits/rejected": 0.24698495864868164,
|
| 1794 |
+
"logps/chosen": -668.9215698242188,
|
| 1795 |
+
"logps/rejected": -835.5013427734375,
|
| 1796 |
+
"loss": 0.191,
|
| 1797 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1798 |
+
"rewards/chosen": -0.3274608254432678,
|
| 1799 |
+
"rewards/margins": 0.2046995609998703,
|
| 1800 |
+
"rewards/rejected": -0.5321604013442993,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": 0.15713492035865784,
|
| 1807 |
+
"logits/rejected": 0.2516704201698303,
|
| 1808 |
+
"logps/chosen": -739.1085815429688,
|
| 1809 |
+
"logps/rejected": -858.5968627929688,
|
| 1810 |
+
"loss": 0.2318,
|
| 1811 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1812 |
+
"rewards/chosen": -0.36160725355148315,
|
| 1813 |
+
"rewards/margins": 0.20901015400886536,
|
| 1814 |
+
"rewards/rejected": -0.5706173777580261,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": 0.10080404579639435,
|
| 1821 |
+
"logits/rejected": 0.24557176232337952,
|
| 1822 |
+
"logps/chosen": -697.7256469726562,
|
| 1823 |
+
"logps/rejected": -914.9107666015625,
|
| 1824 |
+
"loss": 0.1877,
|
| 1825 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1826 |
+
"rewards/chosen": -0.3470718264579773,
|
| 1827 |
+
"rewards/margins": 0.25500741600990295,
|
| 1828 |
+
"rewards/rejected": -0.6020792722702026,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": 0.12770727276802063,
|
| 1835 |
+
"logits/rejected": 0.19649390876293182,
|
| 1836 |
+
"logps/chosen": -698.4237060546875,
|
| 1837 |
+
"logps/rejected": -831.1112060546875,
|
| 1838 |
+
"loss": 0.2174,
|
| 1839 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1840 |
+
"rewards/chosen": -0.36567771434783936,
|
| 1841 |
+
"rewards/margins": 0.18466141819953918,
|
| 1842 |
+
"rewards/rejected": -0.5503391623497009,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": 0.1088666170835495,
|
| 1849 |
+
"logits/rejected": 0.26579782366752625,
|
| 1850 |
+
"logps/chosen": -697.934326171875,
|
| 1851 |
+
"logps/rejected": -863.8990478515625,
|
| 1852 |
+
"loss": 0.184,
|
| 1853 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1854 |
+
"rewards/chosen": -0.32992303371429443,
|
| 1855 |
+
"rewards/margins": 0.2491859644651413,
|
| 1856 |
+
"rewards/rejected": -0.5791090130805969,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": 0.1179809719324112,
|
| 1863 |
+
"logits/rejected": 0.21980592608451843,
|
| 1864 |
+
"logps/chosen": -690.4783935546875,
|
| 1865 |
+
"logps/rejected": -883.32861328125,
|
| 1866 |
+
"loss": 0.1656,
|
| 1867 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1868 |
+
"rewards/chosen": -0.32375839352607727,
|
| 1869 |
+
"rewards/margins": 0.27088266611099243,
|
| 1870 |
+
"rewards/rejected": -0.5946410298347473,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": 0.10531783103942871,
|
| 1877 |
+
"logits/rejected": 0.2298382818698883,
|
| 1878 |
+
"logps/chosen": -704.1119384765625,
|
| 1879 |
+
"logps/rejected": -891.2111206054688,
|
| 1880 |
+
"loss": 0.2144,
|
| 1881 |
+
"rewards/accuracies": 0.78125,
|
| 1882 |
+
"rewards/chosen": -0.3464652895927429,
|
| 1883 |
+
"rewards/margins": 0.23750798404216766,
|
| 1884 |
+
"rewards/rejected": -0.5839732885360718,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": 0.06631898880004883,
|
| 1891 |
+
"logits/rejected": 0.25904709100723267,
|
| 1892 |
+
"logps/chosen": -726.3780517578125,
|
| 1893 |
+
"logps/rejected": -875.1380615234375,
|
| 1894 |
+
"loss": 0.2532,
|
| 1895 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1896 |
+
"rewards/chosen": -0.3661043047904968,
|
| 1897 |
+
"rewards/margins": 0.18917004764080048,
|
| 1898 |
+
"rewards/rejected": -0.5552743673324585,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": 0.1238614097237587,
|
| 1905 |
+
"logits/rejected": 0.25796738266944885,
|
| 1906 |
+
"logps/chosen": -661.4393310546875,
|
| 1907 |
+
"logps/rejected": -795.7490844726562,
|
| 1908 |
+
"loss": 0.1855,
|
| 1909 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1910 |
+
"rewards/chosen": -0.29050904512405396,
|
| 1911 |
+
"rewards/margins": 0.2389696091413498,
|
| 1912 |
+
"rewards/rejected": -0.5294786691665649,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": 0.09917294979095459,
|
| 1919 |
+
"logits/rejected": 0.21815705299377441,
|
| 1920 |
+
"logps/chosen": -659.0029296875,
|
| 1921 |
+
"logps/rejected": -792.0519409179688,
|
| 1922 |
+
"loss": 0.224,
|
| 1923 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1924 |
+
"rewards/chosen": -0.3168398439884186,
|
| 1925 |
+
"rewards/margins": 0.19915297627449036,
|
| 1926 |
+
"rewards/rejected": -0.5159928202629089,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": 0.09248078614473343,
|
| 1933 |
+
"logits/rejected": 0.21158233284950256,
|
| 1934 |
+
"logps/chosen": -678.2177734375,
|
| 1935 |
+
"logps/rejected": -867.001953125,
|
| 1936 |
+
"loss": 0.1935,
|
| 1937 |
+
"rewards/accuracies": 0.78125,
|
| 1938 |
+
"rewards/chosen": -0.31002795696258545,
|
| 1939 |
+
"rewards/margins": 0.25347810983657837,
|
| 1940 |
+
"rewards/rejected": -0.5635061264038086,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": 0.1292383223772049,
|
| 1947 |
+
"logits/rejected": 0.24721387028694153,
|
| 1948 |
+
"logps/chosen": -677.2322998046875,
|
| 1949 |
+
"logps/rejected": -853.12939453125,
|
| 1950 |
+
"loss": 0.2384,
|
| 1951 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1952 |
+
"rewards/chosen": -0.33947324752807617,
|
| 1953 |
+
"rewards/margins": 0.2104976624250412,
|
| 1954 |
+
"rewards/rejected": -0.5499709248542786,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": 0.13778840005397797,
|
| 1961 |
+
"logits/rejected": 0.22406592965126038,
|
| 1962 |
+
"logps/chosen": -707.752197265625,
|
| 1963 |
+
"logps/rejected": -878.6907958984375,
|
| 1964 |
+
"loss": 0.2185,
|
| 1965 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1966 |
+
"rewards/chosen": -0.3595397472381592,
|
| 1967 |
+
"rewards/margins": 0.2256437987089157,
|
| 1968 |
+
"rewards/rejected": -0.5851835012435913,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": 0.14451025426387787,
|
| 1975 |
+
"logits/rejected": 0.23547664284706116,
|
| 1976 |
+
"logps/chosen": -704.7767333984375,
|
| 1977 |
+
"logps/rejected": -874.5423583984375,
|
| 1978 |
+
"loss": 0.2143,
|
| 1979 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1980 |
+
"rewards/chosen": -0.36400097608566284,
|
| 1981 |
+
"rewards/margins": 0.21412873268127441,
|
| 1982 |
+
"rewards/rejected": -0.5781297087669373,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": 0.057539235800504684,
|
| 1989 |
+
"logits/rejected": 0.250136137008667,
|
| 1990 |
+
"logps/chosen": -740.0396118164062,
|
| 1991 |
+
"logps/rejected": -905.1911010742188,
|
| 1992 |
+
"loss": 0.169,
|
| 1993 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1994 |
+
"rewards/chosen": -0.3726292550563812,
|
| 1995 |
+
"rewards/margins": 0.24727007746696472,
|
| 1996 |
+
"rewards/rejected": -0.619899332523346,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": 0.061049748212099075,
|
| 2003 |
+
"logits/rejected": 0.25947609543800354,
|
| 2004 |
+
"logps/chosen": -725.9439697265625,
|
| 2005 |
+
"logps/rejected": -906.8638916015625,
|
| 2006 |
+
"loss": 0.234,
|
| 2007 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2008 |
+
"rewards/chosen": -0.38042646646499634,
|
| 2009 |
+
"rewards/margins": 0.21715033054351807,
|
| 2010 |
+
"rewards/rejected": -0.5975767970085144,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": 0.10633182525634766,
|
| 2017 |
+
"logits/rejected": 0.19451837241649628,
|
| 2018 |
+
"logps/chosen": -708.9187622070312,
|
| 2019 |
+
"logps/rejected": -866.9814453125,
|
| 2020 |
+
"loss": 0.2272,
|
| 2021 |
+
"rewards/accuracies": 0.71875,
|
| 2022 |
+
"rewards/chosen": -0.3733717203140259,
|
| 2023 |
+
"rewards/margins": 0.21014182269573212,
|
| 2024 |
+
"rewards/rejected": -0.5835135579109192,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": 0.12362603843212128,
|
| 2031 |
+
"logits/rejected": 0.2242850810289383,
|
| 2032 |
+
"logps/chosen": -738.5260009765625,
|
| 2033 |
+
"logps/rejected": -900.5517578125,
|
| 2034 |
+
"loss": 0.1976,
|
| 2035 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2036 |
+
"rewards/chosen": -0.39003950357437134,
|
| 2037 |
+
"rewards/margins": 0.22742080688476562,
|
| 2038 |
+
"rewards/rejected": -0.6174603700637817,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": 0.10756851732730865,
|
| 2045 |
+
"logits/rejected": 0.2637716233730316,
|
| 2046 |
+
"logps/chosen": -668.5317993164062,
|
| 2047 |
+
"logps/rejected": -864.6610107421875,
|
| 2048 |
+
"loss": 0.2104,
|
| 2049 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2050 |
+
"rewards/chosen": -0.3528197407722473,
|
| 2051 |
+
"rewards/margins": 0.22202415764331818,
|
| 2052 |
+
"rewards/rejected": -0.5748439431190491,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": 0.13962891697883606,
|
| 2059 |
+
"logits/rejected": 0.20390410721302032,
|
| 2060 |
+
"logps/chosen": -674.7015380859375,
|
| 2061 |
+
"logps/rejected": -883.2214965820312,
|
| 2062 |
+
"loss": 0.182,
|
| 2063 |
+
"rewards/accuracies": 0.75,
|
| 2064 |
+
"rewards/chosen": -0.3491703271865845,
|
| 2065 |
+
"rewards/margins": 0.23920337855815887,
|
| 2066 |
+
"rewards/rejected": -0.5883737206459045,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": 0.11834552139043808,
|
| 2073 |
+
"logits/rejected": 0.21453364193439484,
|
| 2074 |
+
"logps/chosen": -725.1397705078125,
|
| 2075 |
+
"logps/rejected": -918.6031494140625,
|
| 2076 |
+
"loss": 0.2117,
|
| 2077 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2078 |
+
"rewards/chosen": -0.38278132677078247,
|
| 2079 |
+
"rewards/margins": 0.2413547784090042,
|
| 2080 |
+
"rewards/rejected": -0.6241360902786255,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": 0.11449946463108063,
|
| 2087 |
+
"logits/rejected": 0.25861063599586487,
|
| 2088 |
+
"logps/chosen": -732.5802612304688,
|
| 2089 |
+
"logps/rejected": -897.5850830078125,
|
| 2090 |
+
"loss": 0.1954,
|
| 2091 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2092 |
+
"rewards/chosen": -0.3760877251625061,
|
| 2093 |
+
"rewards/margins": 0.24298934638500214,
|
| 2094 |
+
"rewards/rejected": -0.6190770864486694,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": 0.12956863641738892,
|
| 2101 |
+
"logits/rejected": 0.2529379427433014,
|
| 2102 |
+
"logps/chosen": -747.3843994140625,
|
| 2103 |
+
"logps/rejected": -893.8402099609375,
|
| 2104 |
+
"loss": 0.2207,
|
| 2105 |
+
"rewards/accuracies": 0.71875,
|
| 2106 |
+
"rewards/chosen": -0.38915324211120605,
|
| 2107 |
+
"rewards/margins": 0.20487980544567108,
|
| 2108 |
+
"rewards/rejected": -0.5940330624580383,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": 0.1093892902135849,
|
| 2115 |
+
"logits/rejected": 0.25721386075019836,
|
| 2116 |
+
"logps/chosen": -754.2517700195312,
|
| 2117 |
+
"logps/rejected": -897.6614990234375,
|
| 2118 |
+
"loss": 0.1903,
|
| 2119 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2120 |
+
"rewards/chosen": -0.3746017813682556,
|
| 2121 |
+
"rewards/margins": 0.22877414524555206,
|
| 2122 |
+
"rewards/rejected": -0.6033759117126465,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": 0.16093885898590088,
|
| 2129 |
+
"logits/rejected": 0.24726077914237976,
|
| 2130 |
+
"logps/chosen": -697.4678955078125,
|
| 2131 |
+
"logps/rejected": -852.6463623046875,
|
| 2132 |
+
"loss": 0.2077,
|
| 2133 |
+
"rewards/accuracies": 0.75,
|
| 2134 |
+
"rewards/chosen": -0.343566358089447,
|
| 2135 |
+
"rewards/margins": 0.22954010963439941,
|
| 2136 |
+
"rewards/rejected": -0.5731065273284912,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": 0.105752132833004,
|
| 2143 |
+
"logits/rejected": 0.14859572052955627,
|
| 2144 |
+
"logps/chosen": -721.93701171875,
|
| 2145 |
+
"logps/rejected": -894.5123291015625,
|
| 2146 |
+
"loss": 0.2127,
|
| 2147 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2148 |
+
"rewards/chosen": -0.38259005546569824,
|
| 2149 |
+
"rewards/margins": 0.21411553025245667,
|
| 2150 |
+
"rewards/rejected": -0.5967055559158325,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": 0.10524594783782959,
|
| 2157 |
+
"logits/rejected": 0.2024340182542801,
|
| 2158 |
+
"logps/chosen": -694.057373046875,
|
| 2159 |
+
"logps/rejected": -898.6950073242188,
|
| 2160 |
+
"loss": 0.2056,
|
| 2161 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 2162 |
+
"rewards/chosen": -0.3508402407169342,
|
| 2163 |
+
"rewards/margins": 0.23787379264831543,
|
| 2164 |
+
"rewards/rejected": -0.5887140035629272,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": 0.13965895771980286,
|
| 2171 |
+
"logits/rejected": 0.2609595060348511,
|
| 2172 |
+
"logps/chosen": -718.2183837890625,
|
| 2173 |
+
"logps/rejected": -927.0887451171875,
|
| 2174 |
+
"loss": 0.1829,
|
| 2175 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2176 |
+
"rewards/chosen": -0.3423174321651459,
|
| 2177 |
+
"rewards/margins": 0.2680014967918396,
|
| 2178 |
+
"rewards/rejected": -0.6103189587593079,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": 0.08242682367563248,
|
| 2185 |
+
"logits/rejected": 0.258888840675354,
|
| 2186 |
+
"logps/chosen": -728.785400390625,
|
| 2187 |
+
"logps/rejected": -884.2569580078125,
|
| 2188 |
+
"loss": 0.1945,
|
| 2189 |
+
"rewards/accuracies": 0.75,
|
| 2190 |
+
"rewards/chosen": -0.3698558211326599,
|
| 2191 |
+
"rewards/margins": 0.2148553878068924,
|
| 2192 |
+
"rewards/rejected": -0.5847111940383911,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": 0.06701900064945221,
|
| 2199 |
+
"logits/rejected": 0.24965231120586395,
|
| 2200 |
+
"logps/chosen": -727.2434692382812,
|
| 2201 |
+
"logps/rejected": -851.6761474609375,
|
| 2202 |
+
"loss": 0.2054,
|
| 2203 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 2204 |
+
"rewards/chosen": -0.36560553312301636,
|
| 2205 |
+
"rewards/margins": 0.19481703639030457,
|
| 2206 |
+
"rewards/rejected": -0.5604225397109985,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": 0.10284195840358734,
|
| 2213 |
+
"logits/rejected": 0.2730451226234436,
|
| 2214 |
+
"logps/chosen": -668.3700561523438,
|
| 2215 |
+
"logps/rejected": -831.0675659179688,
|
| 2216 |
+
"loss": 0.23,
|
| 2217 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2218 |
+
"rewards/chosen": -0.3593829274177551,
|
| 2219 |
+
"rewards/margins": 0.2011059820652008,
|
| 2220 |
+
"rewards/rejected": -0.5604888796806335,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": 0.13599783182144165,
|
| 2227 |
+
"logits/rejected": 0.35692065954208374,
|
| 2228 |
+
"logps/chosen": -757.5804443359375,
|
| 2229 |
+
"logps/rejected": -899.2823486328125,
|
| 2230 |
+
"loss": 0.199,
|
| 2231 |
+
"rewards/accuracies": 0.78125,
|
| 2232 |
+
"rewards/chosen": -0.37098321318626404,
|
| 2233 |
+
"rewards/margins": 0.23468928039073944,
|
| 2234 |
+
"rewards/rejected": -0.6056725978851318,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": 0.0868467465043068,
|
| 2241 |
+
"logits/rejected": 0.2526485323905945,
|
| 2242 |
+
"logps/chosen": -700.9779052734375,
|
| 2243 |
+
"logps/rejected": -871.28759765625,
|
| 2244 |
+
"loss": 0.2033,
|
| 2245 |
+
"rewards/accuracies": 0.78125,
|
| 2246 |
+
"rewards/chosen": -0.3747710585594177,
|
| 2247 |
+
"rewards/margins": 0.22533288598060608,
|
| 2248 |
+
"rewards/rejected": -0.6001039743423462,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": 0.1354844868183136,
|
| 2255 |
+
"logits/rejected": 0.23974338173866272,
|
| 2256 |
+
"logps/chosen": -731.3267822265625,
|
| 2257 |
+
"logps/rejected": -881.2257080078125,
|
| 2258 |
+
"loss": 0.2081,
|
| 2259 |
+
"rewards/accuracies": 0.75,
|
| 2260 |
+
"rewards/chosen": -0.3920326828956604,
|
| 2261 |
+
"rewards/margins": 0.2153809517621994,
|
| 2262 |
+
"rewards/rejected": -0.607413649559021,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": 0.09572525322437286,
|
| 2269 |
+
"logits/rejected": 0.2735249698162079,
|
| 2270 |
+
"logps/chosen": -741.9659423828125,
|
| 2271 |
+
"logps/rejected": -868.5421752929688,
|
| 2272 |
+
"loss": 0.1862,
|
| 2273 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2274 |
+
"rewards/chosen": -0.36106202006340027,
|
| 2275 |
+
"rewards/margins": 0.24586737155914307,
|
| 2276 |
+
"rewards/rejected": -0.6069294214248657,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": 0.11158449947834015,
|
| 2283 |
+
"logits/rejected": 0.2957077920436859,
|
| 2284 |
+
"logps/chosen": -739.4963989257812,
|
| 2285 |
+
"logps/rejected": -893.3660278320312,
|
| 2286 |
+
"loss": 0.2249,
|
| 2287 |
+
"rewards/accuracies": 0.71875,
|
| 2288 |
+
"rewards/chosen": -0.34823960065841675,
|
| 2289 |
+
"rewards/margins": 0.24774250388145447,
|
| 2290 |
+
"rewards/rejected": -0.5959821343421936,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": 0.08035390824079514,
|
| 2297 |
+
"logits/rejected": 0.30342569947242737,
|
| 2298 |
+
"logps/chosen": -726.1354370117188,
|
| 2299 |
+
"logps/rejected": -874.1571044921875,
|
| 2300 |
+
"loss": 0.2268,
|
| 2301 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2302 |
+
"rewards/chosen": -0.3561965823173523,
|
| 2303 |
+
"rewards/margins": 0.23391160368919373,
|
| 2304 |
+
"rewards/rejected": -0.5901081562042236,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": 0.11884896457195282,
|
| 2311 |
+
"logits/rejected": 0.2436933070421219,
|
| 2312 |
+
"logps/chosen": -684.6835327148438,
|
| 2313 |
+
"logps/rejected": -855.82080078125,
|
| 2314 |
+
"loss": 0.1687,
|
| 2315 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2316 |
+
"rewards/chosen": -0.35456180572509766,
|
| 2317 |
+
"rewards/margins": 0.2304537296295166,
|
| 2318 |
+
"rewards/rejected": -0.585015594959259,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": 0.11550426483154297,
|
| 2325 |
+
"logits/rejected": 0.23713016510009766,
|
| 2326 |
+
"logps/chosen": -683.0443115234375,
|
| 2327 |
+
"logps/rejected": -845.1898193359375,
|
| 2328 |
+
"loss": 0.2047,
|
| 2329 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2330 |
+
"rewards/chosen": -0.3718727231025696,
|
| 2331 |
+
"rewards/margins": 0.1886688768863678,
|
| 2332 |
+
"rewards/rejected": -0.560541570186615,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": 0.0976637750864029,
|
| 2339 |
+
"logits/rejected": 0.2651471495628357,
|
| 2340 |
+
"logps/chosen": -690.2272338867188,
|
| 2341 |
+
"logps/rejected": -833.02490234375,
|
| 2342 |
+
"loss": 0.2112,
|
| 2343 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2344 |
+
"rewards/chosen": -0.34249281883239746,
|
| 2345 |
+
"rewards/margins": 0.2113989293575287,
|
| 2346 |
+
"rewards/rejected": -0.5538917779922485,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": 0.16379910707473755,
|
| 2353 |
+
"logits/rejected": 0.21980710327625275,
|
| 2354 |
+
"logps/chosen": -689.8270263671875,
|
| 2355 |
+
"logps/rejected": -867.986328125,
|
| 2356 |
+
"loss": 0.1975,
|
| 2357 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2358 |
+
"rewards/chosen": -0.3630715310573578,
|
| 2359 |
+
"rewards/margins": 0.21778926253318787,
|
| 2360 |
+
"rewards/rejected": -0.5808607935905457,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": 0.1122732162475586,
|
| 2367 |
+
"logits/rejected": 0.25381821393966675,
|
| 2368 |
+
"logps/chosen": -688.6129150390625,
|
| 2369 |
+
"logps/rejected": -869.9622802734375,
|
| 2370 |
+
"loss": 0.1925,
|
| 2371 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2372 |
+
"rewards/chosen": -0.3432803153991699,
|
| 2373 |
+
"rewards/margins": 0.24642963707447052,
|
| 2374 |
+
"rewards/rejected": -0.5897098779678345,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": 0.09772084653377533,
|
| 2381 |
+
"logits/rejected": 0.2000305950641632,
|
| 2382 |
+
"logps/chosen": -650.7125854492188,
|
| 2383 |
+
"logps/rejected": -843.9298706054688,
|
| 2384 |
+
"loss": 0.2155,
|
| 2385 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2386 |
+
"rewards/chosen": -0.3303535580635071,
|
| 2387 |
+
"rewards/margins": 0.22402143478393555,
|
| 2388 |
+
"rewards/rejected": -0.5543749928474426,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": 0.09905121475458145,
|
| 2395 |
+
"logits/rejected": 0.244928240776062,
|
| 2396 |
+
"logps/chosen": -736.1495971679688,
|
| 2397 |
+
"logps/rejected": -871.73876953125,
|
| 2398 |
+
"loss": 0.2122,
|
| 2399 |
+
"rewards/accuracies": 0.668749988079071,
|
| 2400 |
+
"rewards/chosen": -0.37346401810646057,
|
| 2401 |
+
"rewards/margins": 0.20723024010658264,
|
| 2402 |
+
"rewards/rejected": -0.5806942582130432,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": 0.12118308246135712,
|
| 2409 |
+
"logits/rejected": 0.2801864743232727,
|
| 2410 |
+
"logps/chosen": -676.4124755859375,
|
| 2411 |
+
"logps/rejected": -808.5712890625,
|
| 2412 |
+
"loss": 0.2199,
|
| 2413 |
+
"rewards/accuracies": 0.699999988079071,
|
| 2414 |
+
"rewards/chosen": -0.34813016653060913,
|
| 2415 |
+
"rewards/margins": 0.19372887909412384,
|
| 2416 |
+
"rewards/rejected": -0.5418590307235718,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": 0.12361860275268555,
|
| 2423 |
+
"logits/rejected": 0.21096520125865936,
|
| 2424 |
+
"logps/chosen": -694.0318603515625,
|
| 2425 |
+
"logps/rejected": -827.3196411132812,
|
| 2426 |
+
"loss": 0.2125,
|
| 2427 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2428 |
+
"rewards/chosen": -0.31590598821640015,
|
| 2429 |
+
"rewards/margins": 0.2430771291255951,
|
| 2430 |
+
"rewards/rejected": -0.5589831471443176,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": 0.10681068897247314,
|
| 2437 |
+
"logits/rejected": 0.29420608282089233,
|
| 2438 |
+
"logps/chosen": -736.9918823242188,
|
| 2439 |
+
"logps/rejected": -838.1085205078125,
|
| 2440 |
+
"loss": 0.2178,
|
| 2441 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2442 |
+
"rewards/chosen": -0.3317691385746002,
|
| 2443 |
+
"rewards/margins": 0.2118922919034958,
|
| 2444 |
+
"rewards/rejected": -0.5436614155769348,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": 0.11358167231082916,
|
| 2451 |
+
"logits/rejected": 0.2305765599012375,
|
| 2452 |
+
"logps/chosen": -730.17236328125,
|
| 2453 |
+
"logps/rejected": -913.6432495117188,
|
| 2454 |
+
"loss": 0.2143,
|
| 2455 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2456 |
+
"rewards/chosen": -0.38126105070114136,
|
| 2457 |
+
"rewards/margins": 0.22439336776733398,
|
| 2458 |
+
"rewards/rejected": -0.6056543588638306,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": 0.13343390822410583,
|
| 2465 |
+
"logits/rejected": 0.19125545024871826,
|
| 2466 |
+
"logps/chosen": -663.9968872070312,
|
| 2467 |
+
"logps/rejected": -848.60205078125,
|
| 2468 |
+
"loss": 0.2123,
|
| 2469 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2470 |
+
"rewards/chosen": -0.33876559138298035,
|
| 2471 |
+
"rewards/margins": 0.2210654318332672,
|
| 2472 |
+
"rewards/rejected": -0.5598310232162476,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": 0.11130712181329727,
|
| 2479 |
+
"logits/rejected": 0.20762452483177185,
|
| 2480 |
+
"logps/chosen": -697.3875122070312,
|
| 2481 |
+
"logps/rejected": -888.5732421875,
|
| 2482 |
+
"loss": 0.1992,
|
| 2483 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2484 |
+
"rewards/chosen": -0.36774367094039917,
|
| 2485 |
+
"rewards/margins": 0.21223720908164978,
|
| 2486 |
+
"rewards/rejected": -0.5799809098243713,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": 0.16033565998077393,
|
| 2493 |
+
"logits/rejected": 0.24279725551605225,
|
| 2494 |
+
"logps/chosen": -707.9478149414062,
|
| 2495 |
+
"logps/rejected": -846.6570434570312,
|
| 2496 |
+
"loss": 0.2023,
|
| 2497 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2498 |
+
"rewards/chosen": -0.34674227237701416,
|
| 2499 |
+
"rewards/margins": 0.22830457985401154,
|
| 2500 |
+
"rewards/rejected": -0.5750468969345093,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": 0.08853977173566818,
|
| 2507 |
+
"logits/rejected": 0.2430170327425003,
|
| 2508 |
+
"logps/chosen": -619.2088623046875,
|
| 2509 |
+
"logps/rejected": -804.2175903320312,
|
| 2510 |
+
"loss": 0.2185,
|
| 2511 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2512 |
+
"rewards/chosen": -0.3369048237800598,
|
| 2513 |
+
"rewards/margins": 0.20054855942726135,
|
| 2514 |
+
"rewards/rejected": -0.5374533534049988,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": 0.12984086573123932,
|
| 2521 |
+
"logits/rejected": 0.2853730022907257,
|
| 2522 |
+
"logps/chosen": -716.5003662109375,
|
| 2523 |
+
"logps/rejected": -883.9786987304688,
|
| 2524 |
+
"loss": 0.1965,
|
| 2525 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 2526 |
+
"rewards/chosen": -0.36456966400146484,
|
| 2527 |
+
"rewards/margins": 0.23666837811470032,
|
| 2528 |
+
"rewards/rejected": -0.6012380123138428,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": 0.14794301986694336,
|
| 2535 |
+
"logits/rejected": 0.24739143252372742,
|
| 2536 |
+
"logps/chosen": -699.23828125,
|
| 2537 |
+
"logps/rejected": -848.26953125,
|
| 2538 |
+
"loss": 0.1938,
|
| 2539 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2540 |
+
"rewards/chosen": -0.3432579040527344,
|
| 2541 |
+
"rewards/margins": 0.21511439979076385,
|
| 2542 |
+
"rewards/rejected": -0.5583722591400146,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": 0.06064503267407417,
|
| 2549 |
+
"logits/rejected": 0.2626185119152069,
|
| 2550 |
+
"logps/chosen": -677.8721923828125,
|
| 2551 |
+
"logps/rejected": -822.1427612304688,
|
| 2552 |
+
"loss": 0.2081,
|
| 2553 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2554 |
+
"rewards/chosen": -0.3421019911766052,
|
| 2555 |
+
"rewards/margins": 0.22748549282550812,
|
| 2556 |
+
"rewards/rejected": -0.5695875287055969,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": 0.10713140666484833,
|
| 2563 |
+
"logits/rejected": 0.28815895318984985,
|
| 2564 |
+
"logps/chosen": -721.2071533203125,
|
| 2565 |
+
"logps/rejected": -887.7745361328125,
|
| 2566 |
+
"loss": 0.2041,
|
| 2567 |
+
"rewards/accuracies": 0.793749988079071,
|
| 2568 |
+
"rewards/chosen": -0.33774304389953613,
|
| 2569 |
+
"rewards/margins": 0.25622567534446716,
|
| 2570 |
+
"rewards/rejected": -0.5939687490463257,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": 0.1304168999195099,
|
| 2577 |
+
"logits/rejected": 0.24140071868896484,
|
| 2578 |
+
"logps/chosen": -741.6827392578125,
|
| 2579 |
+
"logps/rejected": -876.1754150390625,
|
| 2580 |
+
"loss": 0.2191,
|
| 2581 |
+
"rewards/accuracies": 0.793749988079071,
|
| 2582 |
+
"rewards/chosen": -0.36193975806236267,
|
| 2583 |
+
"rewards/margins": 0.23083019256591797,
|
| 2584 |
+
"rewards/rejected": -0.592769980430603,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": 0.11551783233880997,
|
| 2591 |
+
"logits/rejected": 0.2661217153072357,
|
| 2592 |
+
"logps/chosen": -677.058837890625,
|
| 2593 |
+
"logps/rejected": -856.2086181640625,
|
| 2594 |
+
"loss": 0.2126,
|
| 2595 |
+
"rewards/accuracies": 0.75,
|
| 2596 |
+
"rewards/chosen": -0.3589734733104706,
|
| 2597 |
+
"rewards/margins": 0.21206960082054138,
|
| 2598 |
+
"rewards/rejected": -0.571043074131012,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": 0.11670766770839691,
|
| 2605 |
+
"logits/rejected": 0.2479906976222992,
|
| 2606 |
+
"logps/chosen": -728.128662109375,
|
| 2607 |
+
"logps/rejected": -841.5104370117188,
|
| 2608 |
+
"loss": 0.2705,
|
| 2609 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2610 |
+
"rewards/chosen": -0.3727620840072632,
|
| 2611 |
+
"rewards/margins": 0.18247419595718384,
|
| 2612 |
+
"rewards/rejected": -0.555236279964447,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": 0.054696790874004364,
|
| 2619 |
+
"logits/rejected": 0.19346895813941956,
|
| 2620 |
+
"logps/chosen": -699.7024536132812,
|
| 2621 |
+
"logps/rejected": -866.5377197265625,
|
| 2622 |
+
"loss": 0.2164,
|
| 2623 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2624 |
+
"rewards/chosen": -0.36183029413223267,
|
| 2625 |
+
"rewards/margins": 0.21843652427196503,
|
| 2626 |
+
"rewards/rejected": -0.5802668333053589,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": 0.07530347257852554,
|
| 2633 |
+
"logits/rejected": 0.30514389276504517,
|
| 2634 |
+
"logps/chosen": -705.9031982421875,
|
| 2635 |
+
"logps/rejected": -897.6741943359375,
|
| 2636 |
+
"loss": 0.2217,
|
| 2637 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2638 |
+
"rewards/chosen": -0.3515733778476715,
|
| 2639 |
+
"rewards/margins": 0.2382936030626297,
|
| 2640 |
+
"rewards/rejected": -0.5898669958114624,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 0.23145956670443216,
|
| 2648 |
+
"train_runtime": 17376.0848,
|
| 2649 |
+
"train_samples_per_second": 1.727,
|
| 2650 |
+
"train_steps_per_second": 0.108
|
| 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 |
+
}
|