Model save
Browse files- README.md +59 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May20_23-07-59_gpu4-119-5/events.out.tfevents.1716210636.gpu4-119-5.1061584.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -0
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-i0
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-irepo-chatml-v9-i1
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# phi-2-irepo-chatml-v9-i1
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-i0](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-i0) on the None dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
### Framework versions
|
| 54 |
+
|
| 55 |
+
- PEFT 0.7.1
|
| 56 |
+
- Transformers 4.36.2
|
| 57 |
+
- Pytorch 2.1.2+cu121
|
| 58 |
+
- Datasets 2.14.6
|
| 59 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335579632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2a966ff9edd7eeaeaa5d43160b42241bcb0e1915fc2b765d0d98b266f1ee3bb
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1858275575319926,
|
| 4 |
+
"train_runtime": 11460.3939,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 2.618,
|
| 7 |
+
"train_steps_per_second": 0.164
|
| 8 |
+
}
|
runs/May20_23-07-59_gpu4-119-5/events.out.tfevents.1716210636.gpu4-119-5.1061584.0
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 sha256:30ddf0d6b08b0f16cff2820859462593a0458faa1b998c8d0446adb1ee20f469
|
| 3 |
+
size 124312
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1858275575319926,
|
| 4 |
+
"train_runtime": 11460.3939,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 2.618,
|
| 7 |
+
"train_steps_per_second": 0.164
|
| 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": 0.09963524341583252,
|
| 15 |
+
"logits/rejected": 0.17411324381828308,
|
| 16 |
+
"logps/chosen": -378.2606506347656,
|
| 17 |
+
"logps/rejected": -386.1599426269531,
|
| 18 |
+
"loss": 0.21,
|
| 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": 0.1553082913160324,
|
| 29 |
+
"logits/rejected": 0.24615353345870972,
|
| 30 |
+
"logps/chosen": -397.8062438964844,
|
| 31 |
+
"logps/rejected": -394.25341796875,
|
| 32 |
+
"loss": 0.2045,
|
| 33 |
+
"rewards/accuracies": 0.2777777910232544,
|
| 34 |
+
"rewards/chosen": -0.0005843756953254342,
|
| 35 |
+
"rewards/margins": -3.1117440812522545e-05,
|
| 36 |
+
"rewards/rejected": -0.0005532581708393991,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": 0.3212467432022095,
|
| 43 |
+
"logits/rejected": 0.24689868092536926,
|
| 44 |
+
"logps/chosen": -409.90167236328125,
|
| 45 |
+
"logps/rejected": -409.5082092285156,
|
| 46 |
+
"loss": 0.2087,
|
| 47 |
+
"rewards/accuracies": 0.3687500059604645,
|
| 48 |
+
"rewards/chosen": -0.0009676044574007392,
|
| 49 |
+
"rewards/margins": 5.4393574828282e-05,
|
| 50 |
+
"rewards/rejected": -0.0010219980031251907,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": 0.22952334582805634,
|
| 57 |
+
"logits/rejected": 0.2672143876552582,
|
| 58 |
+
"logps/chosen": -385.3333740234375,
|
| 59 |
+
"logps/rejected": -392.8493957519531,
|
| 60 |
+
"loss": 0.2137,
|
| 61 |
+
"rewards/accuracies": 0.28125,
|
| 62 |
+
"rewards/chosen": -0.0009394015069119632,
|
| 63 |
+
"rewards/margins": -8.656540012452751e-05,
|
| 64 |
+
"rewards/rejected": -0.0008528361213393509,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": 0.24455244839191437,
|
| 71 |
+
"logits/rejected": 0.14430980384349823,
|
| 72 |
+
"logps/chosen": -414.5653381347656,
|
| 73 |
+
"logps/rejected": -410.3203125,
|
| 74 |
+
"loss": 0.2186,
|
| 75 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 76 |
+
"rewards/chosen": -0.0006429333006963134,
|
| 77 |
+
"rewards/margins": 7.077780173858628e-05,
|
| 78 |
+
"rewards/rejected": -0.0007137111388146877,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": 0.16719885170459747,
|
| 85 |
+
"logits/rejected": 0.19559958577156067,
|
| 86 |
+
"logps/chosen": -388.90740966796875,
|
| 87 |
+
"logps/rejected": -379.8285827636719,
|
| 88 |
+
"loss": 0.2026,
|
| 89 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 90 |
+
"rewards/chosen": -3.721771645359695e-05,
|
| 91 |
+
"rewards/margins": -9.795947335078381e-06,
|
| 92 |
+
"rewards/rejected": -2.742178003245499e-05,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": 0.2627559304237366,
|
| 99 |
+
"logits/rejected": 0.2265670746564865,
|
| 100 |
+
"logps/chosen": -355.0706787109375,
|
| 101 |
+
"logps/rejected": -372.27508544921875,
|
| 102 |
+
"loss": 0.2185,
|
| 103 |
+
"rewards/accuracies": 0.39375001192092896,
|
| 104 |
+
"rewards/chosen": 0.00125337322242558,
|
| 105 |
+
"rewards/margins": 0.00012534942652564496,
|
| 106 |
+
"rewards/rejected": 0.0011280238395556808,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": 0.15168386697769165,
|
| 113 |
+
"logits/rejected": 0.3290417194366455,
|
| 114 |
+
"logps/chosen": -432.84197998046875,
|
| 115 |
+
"logps/rejected": -418.5240783691406,
|
| 116 |
+
"loss": 0.2123,
|
| 117 |
+
"rewards/accuracies": 0.40625,
|
| 118 |
+
"rewards/chosen": 0.0038177906535565853,
|
| 119 |
+
"rewards/margins": 0.00015494157560169697,
|
| 120 |
+
"rewards/rejected": 0.003662849310785532,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": 0.150368332862854,
|
| 127 |
+
"logits/rejected": 0.2564127445220947,
|
| 128 |
+
"logps/chosen": -402.29449462890625,
|
| 129 |
+
"logps/rejected": -372.3401184082031,
|
| 130 |
+
"loss": 0.2282,
|
| 131 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 132 |
+
"rewards/chosen": 0.006463122554123402,
|
| 133 |
+
"rewards/margins": 0.00028264717548154294,
|
| 134 |
+
"rewards/rejected": 0.00618047546595335,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": 0.19279547035694122,
|
| 141 |
+
"logits/rejected": 0.3653843104839325,
|
| 142 |
+
"logps/chosen": -433.8819885253906,
|
| 143 |
+
"logps/rejected": -433.3250427246094,
|
| 144 |
+
"loss": 0.2121,
|
| 145 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 146 |
+
"rewards/chosen": 0.008460921235382557,
|
| 147 |
+
"rewards/margins": 0.0003720732347574085,
|
| 148 |
+
"rewards/rejected": 0.008088847622275352,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": 0.187942236661911,
|
| 155 |
+
"logits/rejected": 0.30413854122161865,
|
| 156 |
+
"logps/chosen": -415.242431640625,
|
| 157 |
+
"logps/rejected": -411.3409118652344,
|
| 158 |
+
"loss": 0.2096,
|
| 159 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 160 |
+
"rewards/chosen": 0.006011855788528919,
|
| 161 |
+
"rewards/margins": 0.0004307249910198152,
|
| 162 |
+
"rewards/rejected": 0.005581130273640156,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": 0.18410541117191315,
|
| 169 |
+
"logits/rejected": 0.22288016974925995,
|
| 170 |
+
"logps/chosen": -402.7239685058594,
|
| 171 |
+
"logps/rejected": -401.08685302734375,
|
| 172 |
+
"loss": 0.2072,
|
| 173 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 174 |
+
"rewards/chosen": 0.002768724225461483,
|
| 175 |
+
"rewards/margins": 0.00032299422309733927,
|
| 176 |
+
"rewards/rejected": 0.0024457299150526524,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": 0.23630130290985107,
|
| 183 |
+
"logits/rejected": 0.2844993472099304,
|
| 184 |
+
"logps/chosen": -436.46624755859375,
|
| 185 |
+
"logps/rejected": -418.0640563964844,
|
| 186 |
+
"loss": 0.2094,
|
| 187 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 188 |
+
"rewards/chosen": 0.0015008236514404416,
|
| 189 |
+
"rewards/margins": 0.000703630386851728,
|
| 190 |
+
"rewards/rejected": 0.0007971933227963746,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": 0.1779193878173828,
|
| 197 |
+
"logits/rejected": 0.2234630137681961,
|
| 198 |
+
"logps/chosen": -445.2749938964844,
|
| 199 |
+
"logps/rejected": -395.0121154785156,
|
| 200 |
+
"loss": 0.218,
|
| 201 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 202 |
+
"rewards/chosen": 0.0037746974267065525,
|
| 203 |
+
"rewards/margins": 0.000721289194189012,
|
| 204 |
+
"rewards/rejected": 0.0030534083489328623,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": 0.21873219311237335,
|
| 211 |
+
"logits/rejected": 0.28560131788253784,
|
| 212 |
+
"logps/chosen": -386.23992919921875,
|
| 213 |
+
"logps/rejected": -392.177978515625,
|
| 214 |
+
"loss": 0.2085,
|
| 215 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 216 |
+
"rewards/chosen": 0.005661582108587027,
|
| 217 |
+
"rewards/margins": 0.001634161570109427,
|
| 218 |
+
"rewards/rejected": 0.004027421120554209,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": 0.14144310355186462,
|
| 225 |
+
"logits/rejected": 0.21909043192863464,
|
| 226 |
+
"logps/chosen": -410.2815856933594,
|
| 227 |
+
"logps/rejected": -409.62420654296875,
|
| 228 |
+
"loss": 0.2042,
|
| 229 |
+
"rewards/accuracies": 0.5,
|
| 230 |
+
"rewards/chosen": 0.002802160568535328,
|
| 231 |
+
"rewards/margins": 0.002337489277124405,
|
| 232 |
+
"rewards/rejected": 0.0004646713496185839,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": 0.15275654196739197,
|
| 239 |
+
"logits/rejected": 0.18240560591220856,
|
| 240 |
+
"logps/chosen": -368.1477966308594,
|
| 241 |
+
"logps/rejected": -379.97052001953125,
|
| 242 |
+
"loss": 0.2084,
|
| 243 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 244 |
+
"rewards/chosen": -0.0024238377809524536,
|
| 245 |
+
"rewards/margins": 0.0018925836775451899,
|
| 246 |
+
"rewards/rejected": -0.0043164207600057125,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": 0.16948816180229187,
|
| 253 |
+
"logits/rejected": 0.27625542879104614,
|
| 254 |
+
"logps/chosen": -439.19580078125,
|
| 255 |
+
"logps/rejected": -423.7747497558594,
|
| 256 |
+
"loss": 0.1964,
|
| 257 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 258 |
+
"rewards/chosen": -0.010004468262195587,
|
| 259 |
+
"rewards/margins": 0.0029372868593782187,
|
| 260 |
+
"rewards/rejected": -0.01294175535440445,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": 0.14220403134822845,
|
| 267 |
+
"logits/rejected": 0.17016319930553436,
|
| 268 |
+
"logps/chosen": -402.444091796875,
|
| 269 |
+
"logps/rejected": -399.7784729003906,
|
| 270 |
+
"loss": 0.2215,
|
| 271 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 272 |
+
"rewards/chosen": -0.017413243651390076,
|
| 273 |
+
"rewards/margins": 0.005264014936983585,
|
| 274 |
+
"rewards/rejected": -0.022677261382341385,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": 0.12951701879501343,
|
| 281 |
+
"logits/rejected": 0.24623069167137146,
|
| 282 |
+
"logps/chosen": -468.02325439453125,
|
| 283 |
+
"logps/rejected": -468.9815979003906,
|
| 284 |
+
"loss": 0.1973,
|
| 285 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 286 |
+
"rewards/chosen": -0.03261370584368706,
|
| 287 |
+
"rewards/margins": 0.006805351935327053,
|
| 288 |
+
"rewards/rejected": -0.039419058710336685,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": 0.052798859775066376,
|
| 295 |
+
"logits/rejected": 0.23226705193519592,
|
| 296 |
+
"logps/chosen": -469.90753173828125,
|
| 297 |
+
"logps/rejected": -448.4300842285156,
|
| 298 |
+
"loss": 0.1876,
|
| 299 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 300 |
+
"rewards/chosen": -0.05150008201599121,
|
| 301 |
+
"rewards/margins": 0.006041003856807947,
|
| 302 |
+
"rewards/rejected": -0.05754108354449272,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": 0.08435344696044922,
|
| 309 |
+
"logits/rejected": 0.16326232254505157,
|
| 310 |
+
"logps/chosen": -446.05584716796875,
|
| 311 |
+
"logps/rejected": -458.54217529296875,
|
| 312 |
+
"loss": 0.2059,
|
| 313 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 314 |
+
"rewards/chosen": -0.06337223947048187,
|
| 315 |
+
"rewards/margins": 0.008098254911601543,
|
| 316 |
+
"rewards/rejected": -0.07147050648927689,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": 0.14515891671180725,
|
| 323 |
+
"logits/rejected": 0.1300167292356491,
|
| 324 |
+
"logps/chosen": -490.72271728515625,
|
| 325 |
+
"logps/rejected": -501.8885803222656,
|
| 326 |
+
"loss": 0.2165,
|
| 327 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 328 |
+
"rewards/chosen": -0.06726966798305511,
|
| 329 |
+
"rewards/margins": 0.010882614180445671,
|
| 330 |
+
"rewards/rejected": -0.07815226912498474,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": 0.14549218118190765,
|
| 337 |
+
"logits/rejected": 0.11253325641155243,
|
| 338 |
+
"logps/chosen": -450.588623046875,
|
| 339 |
+
"logps/rejected": -453.873291015625,
|
| 340 |
+
"loss": 0.2008,
|
| 341 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 342 |
+
"rewards/chosen": -0.0649234801530838,
|
| 343 |
+
"rewards/margins": 0.012732243165373802,
|
| 344 |
+
"rewards/rejected": -0.07765571773052216,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": 0.17049750685691833,
|
| 351 |
+
"logits/rejected": 0.08599407970905304,
|
| 352 |
+
"logps/chosen": -452.00152587890625,
|
| 353 |
+
"logps/rejected": -478.6534118652344,
|
| 354 |
+
"loss": 0.2,
|
| 355 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 356 |
+
"rewards/chosen": -0.07021967321634293,
|
| 357 |
+
"rewards/margins": 0.01245578657835722,
|
| 358 |
+
"rewards/rejected": -0.08267545700073242,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": 0.08762475103139877,
|
| 365 |
+
"logits/rejected": 0.15931396186351776,
|
| 366 |
+
"logps/chosen": -472.1898498535156,
|
| 367 |
+
"logps/rejected": -486.1856994628906,
|
| 368 |
+
"loss": 0.1904,
|
| 369 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 370 |
+
"rewards/chosen": -0.08154710382223129,
|
| 371 |
+
"rewards/margins": 0.02140663005411625,
|
| 372 |
+
"rewards/rejected": -0.10295373201370239,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": 0.052127450704574585,
|
| 379 |
+
"logits/rejected": 0.011202364228665829,
|
| 380 |
+
"logps/chosen": -450.86712646484375,
|
| 381 |
+
"logps/rejected": -529.0736083984375,
|
| 382 |
+
"loss": 0.1943,
|
| 383 |
+
"rewards/accuracies": 0.4375,
|
| 384 |
+
"rewards/chosen": -0.0922573059797287,
|
| 385 |
+
"rewards/margins": 0.03915147855877876,
|
| 386 |
+
"rewards/rejected": -0.13140878081321716,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": 0.02654929831624031,
|
| 393 |
+
"logits/rejected": 0.14042030274868011,
|
| 394 |
+
"logps/chosen": -490.01922607421875,
|
| 395 |
+
"logps/rejected": -497.9236755371094,
|
| 396 |
+
"loss": 0.2082,
|
| 397 |
+
"rewards/accuracies": 0.40625,
|
| 398 |
+
"rewards/chosen": -0.10826190561056137,
|
| 399 |
+
"rewards/margins": 0.021642591804265976,
|
| 400 |
+
"rewards/rejected": -0.12990449368953705,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": 0.09107808768749237,
|
| 407 |
+
"logits/rejected": 0.08074366301298141,
|
| 408 |
+
"logps/chosen": -493.1717834472656,
|
| 409 |
+
"logps/rejected": -526.7948608398438,
|
| 410 |
+
"loss": 0.1922,
|
| 411 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 412 |
+
"rewards/chosen": -0.09491624683141708,
|
| 413 |
+
"rewards/margins": 0.02360902726650238,
|
| 414 |
+
"rewards/rejected": -0.11852526664733887,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": -0.01798112317919731,
|
| 421 |
+
"logits/rejected": 0.14514566957950592,
|
| 422 |
+
"logps/chosen": -473.822021484375,
|
| 423 |
+
"logps/rejected": -492.75079345703125,
|
| 424 |
+
"loss": 0.1917,
|
| 425 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 426 |
+
"rewards/chosen": -0.0761452168226242,
|
| 427 |
+
"rewards/margins": 0.02504543401300907,
|
| 428 |
+
"rewards/rejected": -0.10119066387414932,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": 0.012573105283081532,
|
| 435 |
+
"logits/rejected": 0.08077313005924225,
|
| 436 |
+
"logps/chosen": -461.69134521484375,
|
| 437 |
+
"logps/rejected": -452.34393310546875,
|
| 438 |
+
"loss": 0.2008,
|
| 439 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 440 |
+
"rewards/chosen": -0.07385671138763428,
|
| 441 |
+
"rewards/margins": 0.022219108417630196,
|
| 442 |
+
"rewards/rejected": -0.09607584029436111,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": 0.0107968058437109,
|
| 449 |
+
"logits/rejected": 0.017728794366121292,
|
| 450 |
+
"logps/chosen": -512.6489868164062,
|
| 451 |
+
"logps/rejected": -566.363525390625,
|
| 452 |
+
"loss": 0.1829,
|
| 453 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 454 |
+
"rewards/chosen": -0.09047379344701767,
|
| 455 |
+
"rewards/margins": 0.04145172983407974,
|
| 456 |
+
"rewards/rejected": -0.1319255381822586,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": -0.0678163543343544,
|
| 463 |
+
"logits/rejected": 0.10408651828765869,
|
| 464 |
+
"logps/chosen": -535.5982055664062,
|
| 465 |
+
"logps/rejected": -556.8341064453125,
|
| 466 |
+
"loss": 0.1803,
|
| 467 |
+
"rewards/accuracies": 0.543749988079071,
|
| 468 |
+
"rewards/chosen": -0.1051037460565567,
|
| 469 |
+
"rewards/margins": 0.029761528596282005,
|
| 470 |
+
"rewards/rejected": -0.13486526906490326,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": -0.04091095179319382,
|
| 477 |
+
"logits/rejected": -0.0030039071571081877,
|
| 478 |
+
"logps/chosen": -553.9273681640625,
|
| 479 |
+
"logps/rejected": -610.8055419921875,
|
| 480 |
+
"loss": 0.1908,
|
| 481 |
+
"rewards/accuracies": 0.53125,
|
| 482 |
+
"rewards/chosen": -0.12315535545349121,
|
| 483 |
+
"rewards/margins": 0.04520713910460472,
|
| 484 |
+
"rewards/rejected": -0.16836249828338623,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": -0.1246240958571434,
|
| 491 |
+
"logits/rejected": -0.03937938064336777,
|
| 492 |
+
"logps/chosen": -490.50030517578125,
|
| 493 |
+
"logps/rejected": -532.2816162109375,
|
| 494 |
+
"loss": 0.1887,
|
| 495 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 496 |
+
"rewards/chosen": -0.11805293709039688,
|
| 497 |
+
"rewards/margins": 0.02471679449081421,
|
| 498 |
+
"rewards/rejected": -0.1427697390317917,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": -0.08421911299228668,
|
| 505 |
+
"logits/rejected": 0.008182203397154808,
|
| 506 |
+
"logps/chosen": -535.670654296875,
|
| 507 |
+
"logps/rejected": -536.1793212890625,
|
| 508 |
+
"loss": 0.1949,
|
| 509 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 510 |
+
"rewards/chosen": -0.10835033655166626,
|
| 511 |
+
"rewards/margins": 0.03422056883573532,
|
| 512 |
+
"rewards/rejected": -0.1425708830356598,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": -0.07014905661344528,
|
| 519 |
+
"logits/rejected": -0.006586342118680477,
|
| 520 |
+
"logps/chosen": -494.0985412597656,
|
| 521 |
+
"logps/rejected": -525.9044189453125,
|
| 522 |
+
"loss": 0.2065,
|
| 523 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 524 |
+
"rewards/chosen": -0.10610511153936386,
|
| 525 |
+
"rewards/margins": 0.0382779985666275,
|
| 526 |
+
"rewards/rejected": -0.14438311755657196,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": -0.0900832936167717,
|
| 533 |
+
"logits/rejected": -0.10245800018310547,
|
| 534 |
+
"logps/chosen": -572.3137817382812,
|
| 535 |
+
"logps/rejected": -617.9874267578125,
|
| 536 |
+
"loss": 0.2156,
|
| 537 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 538 |
+
"rewards/chosen": -0.12338846921920776,
|
| 539 |
+
"rewards/margins": 0.036996591836214066,
|
| 540 |
+
"rewards/rejected": -0.16038507223129272,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": -0.051192570477724075,
|
| 547 |
+
"logits/rejected": -0.02001297101378441,
|
| 548 |
+
"logps/chosen": -547.9758911132812,
|
| 549 |
+
"logps/rejected": -576.4624633789062,
|
| 550 |
+
"loss": 0.1939,
|
| 551 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 552 |
+
"rewards/chosen": -0.10065815597772598,
|
| 553 |
+
"rewards/margins": 0.02802097424864769,
|
| 554 |
+
"rewards/rejected": -0.12867912650108337,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": -0.14838102459907532,
|
| 561 |
+
"logits/rejected": 0.1484626680612564,
|
| 562 |
+
"logps/chosen": -494.1825256347656,
|
| 563 |
+
"logps/rejected": -524.7642822265625,
|
| 564 |
+
"loss": 0.1967,
|
| 565 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 566 |
+
"rewards/chosen": -0.08151207864284515,
|
| 567 |
+
"rewards/margins": 0.032111816108226776,
|
| 568 |
+
"rewards/rejected": -0.11362389475107193,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": -0.046164363622665405,
|
| 575 |
+
"logits/rejected": -0.03798365592956543,
|
| 576 |
+
"logps/chosen": -472.62677001953125,
|
| 577 |
+
"logps/rejected": -500.4376525878906,
|
| 578 |
+
"loss": 0.1883,
|
| 579 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 580 |
+
"rewards/chosen": -0.07655288279056549,
|
| 581 |
+
"rewards/margins": 0.039138298481702805,
|
| 582 |
+
"rewards/rejected": -0.1156911849975586,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": -0.1458251178264618,
|
| 589 |
+
"logits/rejected": -0.0393032506108284,
|
| 590 |
+
"logps/chosen": -436.66033935546875,
|
| 591 |
+
"logps/rejected": -447.3544006347656,
|
| 592 |
+
"loss": 0.2138,
|
| 593 |
+
"rewards/accuracies": 0.375,
|
| 594 |
+
"rewards/chosen": -0.08541758358478546,
|
| 595 |
+
"rewards/margins": 0.011176596395671368,
|
| 596 |
+
"rewards/rejected": -0.0965941846370697,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": -0.15639075636863708,
|
| 603 |
+
"logits/rejected": -0.010832506231963634,
|
| 604 |
+
"logps/chosen": -489.99151611328125,
|
| 605 |
+
"logps/rejected": -543.11767578125,
|
| 606 |
+
"loss": 0.1843,
|
| 607 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 608 |
+
"rewards/chosen": -0.09636662900447845,
|
| 609 |
+
"rewards/margins": 0.04293360933661461,
|
| 610 |
+
"rewards/rejected": -0.13930022716522217,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": -0.22076280415058136,
|
| 617 |
+
"logits/rejected": -0.018700700253248215,
|
| 618 |
+
"logps/chosen": -517.91455078125,
|
| 619 |
+
"logps/rejected": -551.0287475585938,
|
| 620 |
+
"loss": 0.1901,
|
| 621 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 622 |
+
"rewards/chosen": -0.11141178756952286,
|
| 623 |
+
"rewards/margins": 0.033164333552122116,
|
| 624 |
+
"rewards/rejected": -0.14457611739635468,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": -0.15695324540138245,
|
| 631 |
+
"logits/rejected": -0.08840291202068329,
|
| 632 |
+
"logps/chosen": -491.2373046875,
|
| 633 |
+
"logps/rejected": -511.56781005859375,
|
| 634 |
+
"loss": 0.1891,
|
| 635 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 636 |
+
"rewards/chosen": -0.10444734245538712,
|
| 637 |
+
"rewards/margins": 0.04566046595573425,
|
| 638 |
+
"rewards/rejected": -0.15010783076286316,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": -0.11595731973648071,
|
| 645 |
+
"logits/rejected": -0.128843754529953,
|
| 646 |
+
"logps/chosen": -557.0236206054688,
|
| 647 |
+
"logps/rejected": -633.2085571289062,
|
| 648 |
+
"loss": 0.2007,
|
| 649 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 650 |
+
"rewards/chosen": -0.12254992872476578,
|
| 651 |
+
"rewards/margins": 0.05843643471598625,
|
| 652 |
+
"rewards/rejected": -0.18098635971546173,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": -0.08469126373529434,
|
| 659 |
+
"logits/rejected": -0.03279350325465202,
|
| 660 |
+
"logps/chosen": -486.62078857421875,
|
| 661 |
+
"logps/rejected": -515.3419799804688,
|
| 662 |
+
"loss": 0.1855,
|
| 663 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 664 |
+
"rewards/chosen": -0.0999387800693512,
|
| 665 |
+
"rewards/margins": 0.04227910935878754,
|
| 666 |
+
"rewards/rejected": -0.14221788942813873,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": -0.1471957415342331,
|
| 673 |
+
"logits/rejected": -0.05932598561048508,
|
| 674 |
+
"logps/chosen": -474.94915771484375,
|
| 675 |
+
"logps/rejected": -536.3035888671875,
|
| 676 |
+
"loss": 0.1819,
|
| 677 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 678 |
+
"rewards/chosen": -0.0976475328207016,
|
| 679 |
+
"rewards/margins": 0.04680894687771797,
|
| 680 |
+
"rewards/rejected": -0.14445647597312927,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": -0.17284898459911346,
|
| 687 |
+
"logits/rejected": -0.1464369297027588,
|
| 688 |
+
"logps/chosen": -502.36578369140625,
|
| 689 |
+
"logps/rejected": -583.7872314453125,
|
| 690 |
+
"loss": 0.1724,
|
| 691 |
+
"rewards/accuracies": 0.518750011920929,
|
| 692 |
+
"rewards/chosen": -0.10467234998941422,
|
| 693 |
+
"rewards/margins": 0.052542489022016525,
|
| 694 |
+
"rewards/rejected": -0.15721485018730164,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": -0.21725276112556458,
|
| 701 |
+
"logits/rejected": -0.14681020379066467,
|
| 702 |
+
"logps/chosen": -523.1455078125,
|
| 703 |
+
"logps/rejected": -577.9979248046875,
|
| 704 |
+
"loss": 0.184,
|
| 705 |
+
"rewards/accuracies": 0.512499988079071,
|
| 706 |
+
"rewards/chosen": -0.09476028382778168,
|
| 707 |
+
"rewards/margins": 0.056237511336803436,
|
| 708 |
+
"rewards/rejected": -0.15099778771400452,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": -0.2188795506954193,
|
| 715 |
+
"logits/rejected": -0.24383120238780975,
|
| 716 |
+
"logps/chosen": -541.2039794921875,
|
| 717 |
+
"logps/rejected": -610.45166015625,
|
| 718 |
+
"loss": 0.1864,
|
| 719 |
+
"rewards/accuracies": 0.550000011920929,
|
| 720 |
+
"rewards/chosen": -0.11351511627435684,
|
| 721 |
+
"rewards/margins": 0.044019803404808044,
|
| 722 |
+
"rewards/rejected": -0.1575349122285843,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": -0.2326229363679886,
|
| 729 |
+
"logits/rejected": -0.15911969542503357,
|
| 730 |
+
"logps/chosen": -494.03302001953125,
|
| 731 |
+
"logps/rejected": -544.4476318359375,
|
| 732 |
+
"loss": 0.1756,
|
| 733 |
+
"rewards/accuracies": 0.512499988079071,
|
| 734 |
+
"rewards/chosen": -0.09819264709949493,
|
| 735 |
+
"rewards/margins": 0.056823331862688065,
|
| 736 |
+
"rewards/rejected": -0.1550159752368927,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": -0.16317172348499298,
|
| 743 |
+
"logits/rejected": -0.1998225897550583,
|
| 744 |
+
"logps/chosen": -530.8056640625,
|
| 745 |
+
"logps/rejected": -605.7437133789062,
|
| 746 |
+
"loss": 0.1588,
|
| 747 |
+
"rewards/accuracies": 0.606249988079071,
|
| 748 |
+
"rewards/chosen": -0.09498073905706406,
|
| 749 |
+
"rewards/margins": 0.07860372215509415,
|
| 750 |
+
"rewards/rejected": -0.1735844761133194,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": -0.17353829741477966,
|
| 757 |
+
"logits/rejected": -0.20073547959327698,
|
| 758 |
+
"logps/chosen": -539.7728271484375,
|
| 759 |
+
"logps/rejected": -576.4498901367188,
|
| 760 |
+
"loss": 0.1832,
|
| 761 |
+
"rewards/accuracies": 0.53125,
|
| 762 |
+
"rewards/chosen": -0.10605832189321518,
|
| 763 |
+
"rewards/margins": 0.05749889463186264,
|
| 764 |
+
"rewards/rejected": -0.16355721652507782,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": -0.17195938527584076,
|
| 771 |
+
"logits/rejected": -0.15436215698719025,
|
| 772 |
+
"logps/chosen": -502.6675720214844,
|
| 773 |
+
"logps/rejected": -537.3475341796875,
|
| 774 |
+
"loss": 0.2008,
|
| 775 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 776 |
+
"rewards/chosen": -0.10046552121639252,
|
| 777 |
+
"rewards/margins": 0.028822993859648705,
|
| 778 |
+
"rewards/rejected": -0.12928852438926697,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": -0.21576860547065735,
|
| 785 |
+
"logits/rejected": -0.22100479900836945,
|
| 786 |
+
"logps/chosen": -528.4920654296875,
|
| 787 |
+
"logps/rejected": -600.3697509765625,
|
| 788 |
+
"loss": 0.1657,
|
| 789 |
+
"rewards/accuracies": 0.53125,
|
| 790 |
+
"rewards/chosen": -0.11002079397439957,
|
| 791 |
+
"rewards/margins": 0.06445158272981644,
|
| 792 |
+
"rewards/rejected": -0.1744723618030548,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": -0.2724868655204773,
|
| 799 |
+
"logits/rejected": -0.18154220283031464,
|
| 800 |
+
"logps/chosen": -534.0877075195312,
|
| 801 |
+
"logps/rejected": -585.4654541015625,
|
| 802 |
+
"loss": 0.1745,
|
| 803 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 804 |
+
"rewards/chosen": -0.11277395486831665,
|
| 805 |
+
"rewards/margins": 0.05171126872301102,
|
| 806 |
+
"rewards/rejected": -0.16448521614074707,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": -0.29137545824050903,
|
| 813 |
+
"logits/rejected": -0.1960664540529251,
|
| 814 |
+
"logps/chosen": -543.6236572265625,
|
| 815 |
+
"logps/rejected": -613.0497436523438,
|
| 816 |
+
"loss": 0.1896,
|
| 817 |
+
"rewards/accuracies": 0.5,
|
| 818 |
+
"rewards/chosen": -0.11756434291601181,
|
| 819 |
+
"rewards/margins": 0.049765445291996,
|
| 820 |
+
"rewards/rejected": -0.16732977330684662,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": -0.24844829738140106,
|
| 827 |
+
"logits/rejected": -0.17800265550613403,
|
| 828 |
+
"logps/chosen": -483.45697021484375,
|
| 829 |
+
"logps/rejected": -549.9342041015625,
|
| 830 |
+
"loss": 0.1642,
|
| 831 |
+
"rewards/accuracies": 0.512499988079071,
|
| 832 |
+
"rewards/chosen": -0.10112373530864716,
|
| 833 |
+
"rewards/margins": 0.06612999737262726,
|
| 834 |
+
"rewards/rejected": -0.16725373268127441,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": -0.35919591784477234,
|
| 841 |
+
"logits/rejected": -0.2761411964893341,
|
| 842 |
+
"logps/chosen": -489.17852783203125,
|
| 843 |
+
"logps/rejected": -502.04022216796875,
|
| 844 |
+
"loss": 0.1868,
|
| 845 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 846 |
+
"rewards/chosen": -0.09544913470745087,
|
| 847 |
+
"rewards/margins": 0.05491846054792404,
|
| 848 |
+
"rewards/rejected": -0.1503675878047943,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": -0.254047155380249,
|
| 855 |
+
"logits/rejected": -0.24359670281410217,
|
| 856 |
+
"logps/chosen": -517.5626220703125,
|
| 857 |
+
"logps/rejected": -570.8585205078125,
|
| 858 |
+
"loss": 0.1936,
|
| 859 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 860 |
+
"rewards/chosen": -0.10336007177829742,
|
| 861 |
+
"rewards/margins": 0.06461663544178009,
|
| 862 |
+
"rewards/rejected": -0.16797669231891632,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": -0.3495100736618042,
|
| 869 |
+
"logits/rejected": -0.22493663430213928,
|
| 870 |
+
"logps/chosen": -526.2481079101562,
|
| 871 |
+
"logps/rejected": -611.931396484375,
|
| 872 |
+
"loss": 0.1684,
|
| 873 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 874 |
+
"rewards/chosen": -0.10717520862817764,
|
| 875 |
+
"rewards/margins": 0.07210040837526321,
|
| 876 |
+
"rewards/rejected": -0.17927563190460205,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": -0.28394874930381775,
|
| 883 |
+
"logits/rejected": -0.2587239146232605,
|
| 884 |
+
"logps/chosen": -567.471435546875,
|
| 885 |
+
"logps/rejected": -639.43310546875,
|
| 886 |
+
"loss": 0.1944,
|
| 887 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 888 |
+
"rewards/chosen": -0.11128894239664078,
|
| 889 |
+
"rewards/margins": 0.06409231573343277,
|
| 890 |
+
"rewards/rejected": -0.17538125813007355,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": -0.28350967168807983,
|
| 897 |
+
"logits/rejected": -0.277797669172287,
|
| 898 |
+
"logps/chosen": -476.7294921875,
|
| 899 |
+
"logps/rejected": -528.3859252929688,
|
| 900 |
+
"loss": 0.1746,
|
| 901 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 902 |
+
"rewards/chosen": -0.07711435854434967,
|
| 903 |
+
"rewards/margins": 0.0645236223936081,
|
| 904 |
+
"rewards/rejected": -0.14163798093795776,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": -0.3298090100288391,
|
| 911 |
+
"logits/rejected": -0.27090325951576233,
|
| 912 |
+
"logps/chosen": -543.4595947265625,
|
| 913 |
+
"logps/rejected": -586.7649536132812,
|
| 914 |
+
"loss": 0.1706,
|
| 915 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 916 |
+
"rewards/chosen": -0.08748660981655121,
|
| 917 |
+
"rewards/margins": 0.06710480898618698,
|
| 918 |
+
"rewards/rejected": -0.1545914113521576,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": -0.3356090188026428,
|
| 925 |
+
"logits/rejected": -0.14076504111289978,
|
| 926 |
+
"logps/chosen": -532.180908203125,
|
| 927 |
+
"logps/rejected": -585.5838623046875,
|
| 928 |
+
"loss": 0.1865,
|
| 929 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 930 |
+
"rewards/chosen": -0.09366744011640549,
|
| 931 |
+
"rewards/margins": 0.046517182141542435,
|
| 932 |
+
"rewards/rejected": -0.14018462598323822,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": -0.2658724784851074,
|
| 939 |
+
"logits/rejected": -0.2869165539741516,
|
| 940 |
+
"logps/chosen": -479.1338806152344,
|
| 941 |
+
"logps/rejected": -522.8956298828125,
|
| 942 |
+
"loss": 0.1859,
|
| 943 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 944 |
+
"rewards/chosen": -0.07211341708898544,
|
| 945 |
+
"rewards/margins": 0.050303440541028976,
|
| 946 |
+
"rewards/rejected": -0.12241685390472412,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": -0.3326638340950012,
|
| 953 |
+
"logits/rejected": -0.3534831404685974,
|
| 954 |
+
"logps/chosen": -465.98046875,
|
| 955 |
+
"logps/rejected": -551.1593017578125,
|
| 956 |
+
"loss": 0.1817,
|
| 957 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 958 |
+
"rewards/chosen": -0.06464243680238724,
|
| 959 |
+
"rewards/margins": 0.06546784937381744,
|
| 960 |
+
"rewards/rejected": -0.13011027872562408,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": -0.2847468852996826,
|
| 967 |
+
"logits/rejected": -0.3084865212440491,
|
| 968 |
+
"logps/chosen": -466.17431640625,
|
| 969 |
+
"logps/rejected": -591.4989624023438,
|
| 970 |
+
"loss": 0.169,
|
| 971 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 972 |
+
"rewards/chosen": -0.06827010214328766,
|
| 973 |
+
"rewards/margins": 0.08749465644359589,
|
| 974 |
+
"rewards/rejected": -0.15576477348804474,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": -0.29794925451278687,
|
| 981 |
+
"logits/rejected": -0.2838256359100342,
|
| 982 |
+
"logps/chosen": -505.8924255371094,
|
| 983 |
+
"logps/rejected": -569.5626831054688,
|
| 984 |
+
"loss": 0.173,
|
| 985 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 986 |
+
"rewards/chosen": -0.08569585531949997,
|
| 987 |
+
"rewards/margins": 0.058602042496204376,
|
| 988 |
+
"rewards/rejected": -0.14429791271686554,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": -0.4137333333492279,
|
| 995 |
+
"logits/rejected": -0.201189324259758,
|
| 996 |
+
"logps/chosen": -520.5211181640625,
|
| 997 |
+
"logps/rejected": -567.9163208007812,
|
| 998 |
+
"loss": 0.1771,
|
| 999 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1000 |
+
"rewards/chosen": -0.07455627620220184,
|
| 1001 |
+
"rewards/margins": 0.06876102834939957,
|
| 1002 |
+
"rewards/rejected": -0.1433172971010208,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": -0.3251053988933563,
|
| 1009 |
+
"logits/rejected": -0.21724073588848114,
|
| 1010 |
+
"logps/chosen": -457.90692138671875,
|
| 1011 |
+
"logps/rejected": -512.7808837890625,
|
| 1012 |
+
"loss": 0.1777,
|
| 1013 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1014 |
+
"rewards/chosen": -0.0669245719909668,
|
| 1015 |
+
"rewards/margins": 0.05744165927171707,
|
| 1016 |
+
"rewards/rejected": -0.12436623871326447,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": -0.20694856345653534,
|
| 1023 |
+
"logits/rejected": -0.2958626449108124,
|
| 1024 |
+
"logps/chosen": -455.8350524902344,
|
| 1025 |
+
"logps/rejected": -536.2254638671875,
|
| 1026 |
+
"loss": 0.1935,
|
| 1027 |
+
"rewards/accuracies": 0.5,
|
| 1028 |
+
"rewards/chosen": -0.0645083338022232,
|
| 1029 |
+
"rewards/margins": 0.06103675439953804,
|
| 1030 |
+
"rewards/rejected": -0.12554509937763214,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": -0.3800198435783386,
|
| 1037 |
+
"logits/rejected": -0.2641103267669678,
|
| 1038 |
+
"logps/chosen": -480.8030700683594,
|
| 1039 |
+
"logps/rejected": -521.5682373046875,
|
| 1040 |
+
"loss": 0.2025,
|
| 1041 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1042 |
+
"rewards/chosen": -0.07129710167646408,
|
| 1043 |
+
"rewards/margins": 0.04021110758185387,
|
| 1044 |
+
"rewards/rejected": -0.11150821298360825,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": -0.35266560316085815,
|
| 1051 |
+
"logits/rejected": -0.21721109747886658,
|
| 1052 |
+
"logps/chosen": -503.35357666015625,
|
| 1053 |
+
"logps/rejected": -518.2500610351562,
|
| 1054 |
+
"loss": 0.1928,
|
| 1055 |
+
"rewards/accuracies": 0.46875,
|
| 1056 |
+
"rewards/chosen": -0.07125665247440338,
|
| 1057 |
+
"rewards/margins": 0.034123968333005905,
|
| 1058 |
+
"rewards/rejected": -0.10538061708211899,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": -0.303008496761322,
|
| 1065 |
+
"logits/rejected": -0.3047345280647278,
|
| 1066 |
+
"logps/chosen": -447.089599609375,
|
| 1067 |
+
"logps/rejected": -469.61590576171875,
|
| 1068 |
+
"loss": 0.1992,
|
| 1069 |
+
"rewards/accuracies": 0.40625,
|
| 1070 |
+
"rewards/chosen": -0.06738699972629547,
|
| 1071 |
+
"rewards/margins": 0.027302343398332596,
|
| 1072 |
+
"rewards/rejected": -0.09468933939933777,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": -0.29965728521347046,
|
| 1079 |
+
"logits/rejected": -0.2571870982646942,
|
| 1080 |
+
"logps/chosen": -450.4271545410156,
|
| 1081 |
+
"logps/rejected": -482.21502685546875,
|
| 1082 |
+
"loss": 0.1935,
|
| 1083 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1084 |
+
"rewards/chosen": -0.055190593004226685,
|
| 1085 |
+
"rewards/margins": 0.04364421218633652,
|
| 1086 |
+
"rewards/rejected": -0.0988348051905632,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": -0.290757954120636,
|
| 1093 |
+
"logits/rejected": -0.3262009024620056,
|
| 1094 |
+
"logps/chosen": -449.7730407714844,
|
| 1095 |
+
"logps/rejected": -520.2115478515625,
|
| 1096 |
+
"loss": 0.1599,
|
| 1097 |
+
"rewards/accuracies": 0.59375,
|
| 1098 |
+
"rewards/chosen": -0.05544726923108101,
|
| 1099 |
+
"rewards/margins": 0.06180447340011597,
|
| 1100 |
+
"rewards/rejected": -0.11725173890590668,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": -0.3281220495700836,
|
| 1107 |
+
"logits/rejected": -0.2547357678413391,
|
| 1108 |
+
"logps/chosen": -441.2623596191406,
|
| 1109 |
+
"logps/rejected": -495.96368408203125,
|
| 1110 |
+
"loss": 0.1915,
|
| 1111 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1112 |
+
"rewards/chosen": -0.0586274154484272,
|
| 1113 |
+
"rewards/margins": 0.03878774121403694,
|
| 1114 |
+
"rewards/rejected": -0.09741516411304474,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": -0.41046142578125,
|
| 1121 |
+
"logits/rejected": -0.29820680618286133,
|
| 1122 |
+
"logps/chosen": -447.24151611328125,
|
| 1123 |
+
"logps/rejected": -473.2769470214844,
|
| 1124 |
+
"loss": 0.1898,
|
| 1125 |
+
"rewards/accuracies": 0.4375,
|
| 1126 |
+
"rewards/chosen": -0.07239285856485367,
|
| 1127 |
+
"rewards/margins": 0.03644294664263725,
|
| 1128 |
+
"rewards/rejected": -0.10883580148220062,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": -0.35609519481658936,
|
| 1135 |
+
"logits/rejected": -0.2902910113334656,
|
| 1136 |
+
"logps/chosen": -469.17706298828125,
|
| 1137 |
+
"logps/rejected": -546.7158203125,
|
| 1138 |
+
"loss": 0.1788,
|
| 1139 |
+
"rewards/accuracies": 0.53125,
|
| 1140 |
+
"rewards/chosen": -0.05905740335583687,
|
| 1141 |
+
"rewards/margins": 0.06316393613815308,
|
| 1142 |
+
"rewards/rejected": -0.12222135066986084,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": -0.2686077356338501,
|
| 1149 |
+
"logits/rejected": -0.2707546055316925,
|
| 1150 |
+
"logps/chosen": -522.1178588867188,
|
| 1151 |
+
"logps/rejected": -570.613525390625,
|
| 1152 |
+
"loss": 0.1825,
|
| 1153 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1154 |
+
"rewards/chosen": -0.07459238916635513,
|
| 1155 |
+
"rewards/margins": 0.061357058584690094,
|
| 1156 |
+
"rewards/rejected": -0.13594944775104523,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": -0.38130688667297363,
|
| 1163 |
+
"logits/rejected": -0.14519771933555603,
|
| 1164 |
+
"logps/chosen": -474.2879943847656,
|
| 1165 |
+
"logps/rejected": -492.1015625,
|
| 1166 |
+
"loss": 0.1804,
|
| 1167 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1168 |
+
"rewards/chosen": -0.049582771956920624,
|
| 1169 |
+
"rewards/margins": 0.04935313016176224,
|
| 1170 |
+
"rewards/rejected": -0.09893589466810226,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": -0.2872348427772522,
|
| 1177 |
+
"logits/rejected": -0.2791721224784851,
|
| 1178 |
+
"logps/chosen": -485.4851989746094,
|
| 1179 |
+
"logps/rejected": -571.0114135742188,
|
| 1180 |
+
"loss": 0.1743,
|
| 1181 |
+
"rewards/accuracies": 0.5625,
|
| 1182 |
+
"rewards/chosen": -0.060776274651288986,
|
| 1183 |
+
"rewards/margins": 0.06890632957220078,
|
| 1184 |
+
"rewards/rejected": -0.12968261539936066,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": -0.3343026041984558,
|
| 1191 |
+
"logits/rejected": -0.2967159152030945,
|
| 1192 |
+
"logps/chosen": -441.74713134765625,
|
| 1193 |
+
"logps/rejected": -455.7685546875,
|
| 1194 |
+
"loss": 0.1898,
|
| 1195 |
+
"rewards/accuracies": 0.4375,
|
| 1196 |
+
"rewards/chosen": -0.05669083446264267,
|
| 1197 |
+
"rewards/margins": 0.04281865060329437,
|
| 1198 |
+
"rewards/rejected": -0.09950948506593704,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": -0.31694555282592773,
|
| 1205 |
+
"logits/rejected": -0.23448070883750916,
|
| 1206 |
+
"logps/chosen": -505.189208984375,
|
| 1207 |
+
"logps/rejected": -574.4694213867188,
|
| 1208 |
+
"loss": 0.1641,
|
| 1209 |
+
"rewards/accuracies": 0.625,
|
| 1210 |
+
"rewards/chosen": -0.06701242923736572,
|
| 1211 |
+
"rewards/margins": 0.07507143914699554,
|
| 1212 |
+
"rewards/rejected": -0.14208386838436127,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": -0.36678022146224976,
|
| 1219 |
+
"logits/rejected": -0.22024087607860565,
|
| 1220 |
+
"logps/chosen": -481.8533630371094,
|
| 1221 |
+
"logps/rejected": -517.580078125,
|
| 1222 |
+
"loss": 0.1795,
|
| 1223 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1224 |
+
"rewards/chosen": -0.08131915330886841,
|
| 1225 |
+
"rewards/margins": 0.054040372371673584,
|
| 1226 |
+
"rewards/rejected": -0.135359525680542,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": -0.31432998180389404,
|
| 1233 |
+
"logits/rejected": -0.3275941014289856,
|
| 1234 |
+
"logps/chosen": -486.9906311035156,
|
| 1235 |
+
"logps/rejected": -556.7380981445312,
|
| 1236 |
+
"loss": 0.1659,
|
| 1237 |
+
"rewards/accuracies": 0.5,
|
| 1238 |
+
"rewards/chosen": -0.0830111876130104,
|
| 1239 |
+
"rewards/margins": 0.08041650056838989,
|
| 1240 |
+
"rewards/rejected": -0.1634276807308197,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": -0.3552636504173279,
|
| 1247 |
+
"logits/rejected": -0.12550072371959686,
|
| 1248 |
+
"logps/chosen": -442.874267578125,
|
| 1249 |
+
"logps/rejected": -486.37457275390625,
|
| 1250 |
+
"loss": 0.1946,
|
| 1251 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1252 |
+
"rewards/chosen": -0.06523702293634415,
|
| 1253 |
+
"rewards/margins": 0.0638941302895546,
|
| 1254 |
+
"rewards/rejected": -0.12913115322589874,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": -0.44293370842933655,
|
| 1261 |
+
"logits/rejected": -0.206680566072464,
|
| 1262 |
+
"logps/chosen": -426.76861572265625,
|
| 1263 |
+
"logps/rejected": -496.85565185546875,
|
| 1264 |
+
"loss": 0.1725,
|
| 1265 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1266 |
+
"rewards/chosen": -0.06692390143871307,
|
| 1267 |
+
"rewards/margins": 0.07236063480377197,
|
| 1268 |
+
"rewards/rejected": -0.13928455114364624,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": -0.35239410400390625,
|
| 1275 |
+
"logits/rejected": -0.22438523173332214,
|
| 1276 |
+
"logps/chosen": -493.1455078125,
|
| 1277 |
+
"logps/rejected": -538.7332153320312,
|
| 1278 |
+
"loss": 0.189,
|
| 1279 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1280 |
+
"rewards/chosen": -0.08153922855854034,
|
| 1281 |
+
"rewards/margins": 0.05397678166627884,
|
| 1282 |
+
"rewards/rejected": -0.13551601767539978,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": -0.28043216466903687,
|
| 1289 |
+
"logits/rejected": -0.32117584347724915,
|
| 1290 |
+
"logps/chosen": -489.95855712890625,
|
| 1291 |
+
"logps/rejected": -528.5255737304688,
|
| 1292 |
+
"loss": 0.1694,
|
| 1293 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1294 |
+
"rewards/chosen": -0.07012003660202026,
|
| 1295 |
+
"rewards/margins": 0.05748220160603523,
|
| 1296 |
+
"rewards/rejected": -0.1276022493839264,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": -0.30975884199142456,
|
| 1303 |
+
"logits/rejected": -0.28235483169555664,
|
| 1304 |
+
"logps/chosen": -523.9342041015625,
|
| 1305 |
+
"logps/rejected": -557.6265869140625,
|
| 1306 |
+
"loss": 0.1987,
|
| 1307 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1308 |
+
"rewards/chosen": -0.08475781232118607,
|
| 1309 |
+
"rewards/margins": 0.04346821457147598,
|
| 1310 |
+
"rewards/rejected": -0.12822601199150085,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": -0.3483017385005951,
|
| 1317 |
+
"logits/rejected": -0.30833274126052856,
|
| 1318 |
+
"logps/chosen": -446.2549743652344,
|
| 1319 |
+
"logps/rejected": -472.79736328125,
|
| 1320 |
+
"loss": 0.1947,
|
| 1321 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 1322 |
+
"rewards/chosen": -0.07903579622507095,
|
| 1323 |
+
"rewards/margins": 0.04975394904613495,
|
| 1324 |
+
"rewards/rejected": -0.1287897378206253,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": -0.34173694252967834,
|
| 1331 |
+
"logits/rejected": -0.2428359091281891,
|
| 1332 |
+
"logps/chosen": -514.5177612304688,
|
| 1333 |
+
"logps/rejected": -543.485595703125,
|
| 1334 |
+
"loss": 0.174,
|
| 1335 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1336 |
+
"rewards/chosen": -0.06802085787057877,
|
| 1337 |
+
"rewards/margins": 0.06197448447346687,
|
| 1338 |
+
"rewards/rejected": -0.12999534606933594,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": -0.2911175787448883,
|
| 1345 |
+
"logits/rejected": -0.26822999119758606,
|
| 1346 |
+
"logps/chosen": -492.79412841796875,
|
| 1347 |
+
"logps/rejected": -546.5845947265625,
|
| 1348 |
+
"loss": 0.1747,
|
| 1349 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1350 |
+
"rewards/chosen": -0.068579763174057,
|
| 1351 |
+
"rewards/margins": 0.06541167199611664,
|
| 1352 |
+
"rewards/rejected": -0.13399145007133484,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": -0.3150990307331085,
|
| 1359 |
+
"logits/rejected": -0.25644177198410034,
|
| 1360 |
+
"logps/chosen": -497.47216796875,
|
| 1361 |
+
"logps/rejected": -579.6931762695312,
|
| 1362 |
+
"loss": 0.1752,
|
| 1363 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1364 |
+
"rewards/chosen": -0.059874940663576126,
|
| 1365 |
+
"rewards/margins": 0.06721685081720352,
|
| 1366 |
+
"rewards/rejected": -0.12709179520606995,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": -0.31079426407814026,
|
| 1373 |
+
"logits/rejected": -0.3151572346687317,
|
| 1374 |
+
"logps/chosen": -463.4168395996094,
|
| 1375 |
+
"logps/rejected": -555.4398193359375,
|
| 1376 |
+
"loss": 0.1846,
|
| 1377 |
+
"rewards/accuracies": 0.5,
|
| 1378 |
+
"rewards/chosen": -0.0642518401145935,
|
| 1379 |
+
"rewards/margins": 0.05405072122812271,
|
| 1380 |
+
"rewards/rejected": -0.11830256134271622,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": -0.22878186404705048,
|
| 1387 |
+
"logits/rejected": -0.21153822541236877,
|
| 1388 |
+
"logps/chosen": -510.89837646484375,
|
| 1389 |
+
"logps/rejected": -539.2826538085938,
|
| 1390 |
+
"loss": 0.175,
|
| 1391 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 1392 |
+
"rewards/chosen": -0.05998819321393967,
|
| 1393 |
+
"rewards/margins": 0.06107606738805771,
|
| 1394 |
+
"rewards/rejected": -0.12106426060199738,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": -0.34622281789779663,
|
| 1401 |
+
"logits/rejected": -0.25016504526138306,
|
| 1402 |
+
"logps/chosen": -429.02178955078125,
|
| 1403 |
+
"logps/rejected": -502.2627868652344,
|
| 1404 |
+
"loss": 0.1741,
|
| 1405 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1406 |
+
"rewards/chosen": -0.05254564806818962,
|
| 1407 |
+
"rewards/margins": 0.06378427147865295,
|
| 1408 |
+
"rewards/rejected": -0.11632990837097168,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": -0.37311479449272156,
|
| 1415 |
+
"logits/rejected": -0.20994921028614044,
|
| 1416 |
+
"logps/chosen": -451.9130859375,
|
| 1417 |
+
"logps/rejected": -485.57061767578125,
|
| 1418 |
+
"loss": 0.1822,
|
| 1419 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1420 |
+
"rewards/chosen": -0.05379350110888481,
|
| 1421 |
+
"rewards/margins": 0.04739636927843094,
|
| 1422 |
+
"rewards/rejected": -0.10118986666202545,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": -0.34606754779815674,
|
| 1429 |
+
"logits/rejected": -0.33781155943870544,
|
| 1430 |
+
"logps/chosen": -458.77392578125,
|
| 1431 |
+
"logps/rejected": -538.665283203125,
|
| 1432 |
+
"loss": 0.1762,
|
| 1433 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1434 |
+
"rewards/chosen": -0.04491495341062546,
|
| 1435 |
+
"rewards/margins": 0.07754696160554886,
|
| 1436 |
+
"rewards/rejected": -0.12246191501617432,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": -0.3478602468967438,
|
| 1443 |
+
"logits/rejected": -0.3592594563961029,
|
| 1444 |
+
"logps/chosen": -426.89324951171875,
|
| 1445 |
+
"logps/rejected": -497.1231994628906,
|
| 1446 |
+
"loss": 0.1811,
|
| 1447 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1448 |
+
"rewards/chosen": -0.05246494337916374,
|
| 1449 |
+
"rewards/margins": 0.06296879798173904,
|
| 1450 |
+
"rewards/rejected": -0.11543373763561249,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": -0.30938345193862915,
|
| 1457 |
+
"logits/rejected": -0.36706987023353577,
|
| 1458 |
+
"logps/chosen": -438.70477294921875,
|
| 1459 |
+
"logps/rejected": -479.84930419921875,
|
| 1460 |
+
"loss": 0.185,
|
| 1461 |
+
"rewards/accuracies": 0.38749998807907104,
|
| 1462 |
+
"rewards/chosen": -0.06825192272663116,
|
| 1463 |
+
"rewards/margins": 0.051073990762233734,
|
| 1464 |
+
"rewards/rejected": -0.1193259134888649,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": -0.30941054224967957,
|
| 1471 |
+
"logits/rejected": -0.3541705310344696,
|
| 1472 |
+
"logps/chosen": -500.3165588378906,
|
| 1473 |
+
"logps/rejected": -547.2388916015625,
|
| 1474 |
+
"loss": 0.1648,
|
| 1475 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1476 |
+
"rewards/chosen": -0.0632004514336586,
|
| 1477 |
+
"rewards/margins": 0.0647406131029129,
|
| 1478 |
+
"rewards/rejected": -0.1279410421848297,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": -0.369188129901886,
|
| 1485 |
+
"logits/rejected": -0.2474605143070221,
|
| 1486 |
+
"logps/chosen": -482.4578552246094,
|
| 1487 |
+
"logps/rejected": -470.77178955078125,
|
| 1488 |
+
"loss": 0.2005,
|
| 1489 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 1490 |
+
"rewards/chosen": -0.06637545675039291,
|
| 1491 |
+
"rewards/margins": 0.03153007850050926,
|
| 1492 |
+
"rewards/rejected": -0.09790553897619247,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": -0.323347270488739,
|
| 1499 |
+
"logits/rejected": -0.30056172609329224,
|
| 1500 |
+
"logps/chosen": -450.601318359375,
|
| 1501 |
+
"logps/rejected": -498.0372619628906,
|
| 1502 |
+
"loss": 0.1822,
|
| 1503 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1504 |
+
"rewards/chosen": -0.06100805476307869,
|
| 1505 |
+
"rewards/margins": 0.048852551728487015,
|
| 1506 |
+
"rewards/rejected": -0.1098606139421463,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": -0.37067005038261414,
|
| 1513 |
+
"logits/rejected": -0.28159070014953613,
|
| 1514 |
+
"logps/chosen": -450.1123046875,
|
| 1515 |
+
"logps/rejected": -492.94903564453125,
|
| 1516 |
+
"loss": 0.177,
|
| 1517 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1518 |
+
"rewards/chosen": -0.054400503635406494,
|
| 1519 |
+
"rewards/margins": 0.05063963681459427,
|
| 1520 |
+
"rewards/rejected": -0.10504014790058136,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": -0.3574444651603699,
|
| 1527 |
+
"logits/rejected": -0.26874804496765137,
|
| 1528 |
+
"logps/chosen": -471.46002197265625,
|
| 1529 |
+
"logps/rejected": -542.9146728515625,
|
| 1530 |
+
"loss": 0.1728,
|
| 1531 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1532 |
+
"rewards/chosen": -0.06453348696231842,
|
| 1533 |
+
"rewards/margins": 0.07580892741680145,
|
| 1534 |
+
"rewards/rejected": -0.14034239947795868,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": -0.2806636393070221,
|
| 1541 |
+
"logits/rejected": -0.29087376594543457,
|
| 1542 |
+
"logps/chosen": -486.2430725097656,
|
| 1543 |
+
"logps/rejected": -514.122314453125,
|
| 1544 |
+
"loss": 0.1749,
|
| 1545 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1546 |
+
"rewards/chosen": -0.07113119959831238,
|
| 1547 |
+
"rewards/margins": 0.05178775265812874,
|
| 1548 |
+
"rewards/rejected": -0.12291894853115082,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": -0.4109742045402527,
|
| 1555 |
+
"logits/rejected": -0.32353344559669495,
|
| 1556 |
+
"logps/chosen": -539.9480590820312,
|
| 1557 |
+
"logps/rejected": -556.8568725585938,
|
| 1558 |
+
"loss": 0.1739,
|
| 1559 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1560 |
+
"rewards/chosen": -0.07678203284740448,
|
| 1561 |
+
"rewards/margins": 0.04964344576001167,
|
| 1562 |
+
"rewards/rejected": -0.12642547488212585,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": -0.33106154203414917,
|
| 1569 |
+
"logits/rejected": -0.22853222489356995,
|
| 1570 |
+
"logps/chosen": -463.4998474121094,
|
| 1571 |
+
"logps/rejected": -510.4764709472656,
|
| 1572 |
+
"loss": 0.1836,
|
| 1573 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1574 |
+
"rewards/chosen": -0.0651940405368805,
|
| 1575 |
+
"rewards/margins": 0.05113544315099716,
|
| 1576 |
+
"rewards/rejected": -0.11632947623729706,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": -0.4000775218009949,
|
| 1583 |
+
"logits/rejected": -0.16853252053260803,
|
| 1584 |
+
"logps/chosen": -520.6731567382812,
|
| 1585 |
+
"logps/rejected": -535.2789306640625,
|
| 1586 |
+
"loss": 0.1777,
|
| 1587 |
+
"rewards/accuracies": 0.5,
|
| 1588 |
+
"rewards/chosen": -0.06823070347309113,
|
| 1589 |
+
"rewards/margins": 0.046103235334157944,
|
| 1590 |
+
"rewards/rejected": -0.11433394253253937,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": -0.3381574749946594,
|
| 1597 |
+
"logits/rejected": -0.22323736548423767,
|
| 1598 |
+
"logps/chosen": -483.09814453125,
|
| 1599 |
+
"logps/rejected": -513.6597900390625,
|
| 1600 |
+
"loss": 0.2054,
|
| 1601 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 1602 |
+
"rewards/chosen": -0.06595513969659805,
|
| 1603 |
+
"rewards/margins": 0.043463800102472305,
|
| 1604 |
+
"rewards/rejected": -0.10941894352436066,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": -0.34239357709884644,
|
| 1611 |
+
"logits/rejected": -0.3451228439807892,
|
| 1612 |
+
"logps/chosen": -495.82403564453125,
|
| 1613 |
+
"logps/rejected": -536.5828857421875,
|
| 1614 |
+
"loss": 0.1641,
|
| 1615 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1616 |
+
"rewards/chosen": -0.05730292201042175,
|
| 1617 |
+
"rewards/margins": 0.05639542266726494,
|
| 1618 |
+
"rewards/rejected": -0.11369834840297699,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": -0.23302578926086426,
|
| 1625 |
+
"logits/rejected": -0.3353923261165619,
|
| 1626 |
+
"logps/chosen": -467.14642333984375,
|
| 1627 |
+
"logps/rejected": -511.3815002441406,
|
| 1628 |
+
"loss": 0.1702,
|
| 1629 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1630 |
+
"rewards/chosen": -0.05319993942975998,
|
| 1631 |
+
"rewards/margins": 0.055631499737501144,
|
| 1632 |
+
"rewards/rejected": -0.10883144289255142,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": -0.3332996964454651,
|
| 1639 |
+
"logits/rejected": -0.34316807985305786,
|
| 1640 |
+
"logps/chosen": -486.32373046875,
|
| 1641 |
+
"logps/rejected": -549.6057739257812,
|
| 1642 |
+
"loss": 0.1644,
|
| 1643 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 1644 |
+
"rewards/chosen": -0.06252233684062958,
|
| 1645 |
+
"rewards/margins": 0.06708262860774994,
|
| 1646 |
+
"rewards/rejected": -0.1296049803495407,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": -0.34824302792549133,
|
| 1653 |
+
"logits/rejected": -0.19805127382278442,
|
| 1654 |
+
"logps/chosen": -435.487060546875,
|
| 1655 |
+
"logps/rejected": -514.4375610351562,
|
| 1656 |
+
"loss": 0.1957,
|
| 1657 |
+
"rewards/accuracies": 0.53125,
|
| 1658 |
+
"rewards/chosen": -0.06748778373003006,
|
| 1659 |
+
"rewards/margins": 0.052836887538433075,
|
| 1660 |
+
"rewards/rejected": -0.12032465636730194,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": -0.4363935589790344,
|
| 1667 |
+
"logits/rejected": -0.2699471712112427,
|
| 1668 |
+
"logps/chosen": -517.750732421875,
|
| 1669 |
+
"logps/rejected": -548.2755126953125,
|
| 1670 |
+
"loss": 0.1871,
|
| 1671 |
+
"rewards/accuracies": 0.5,
|
| 1672 |
+
"rewards/chosen": -0.08836901187896729,
|
| 1673 |
+
"rewards/margins": 0.04405100643634796,
|
| 1674 |
+
"rewards/rejected": -0.13242003321647644,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": -0.3290655016899109,
|
| 1681 |
+
"logits/rejected": -0.3122135400772095,
|
| 1682 |
+
"logps/chosen": -466.1502990722656,
|
| 1683 |
+
"logps/rejected": -535.735107421875,
|
| 1684 |
+
"loss": 0.1699,
|
| 1685 |
+
"rewards/accuracies": 0.5,
|
| 1686 |
+
"rewards/chosen": -0.07871656864881516,
|
| 1687 |
+
"rewards/margins": 0.06162920594215393,
|
| 1688 |
+
"rewards/rejected": -0.14034578204154968,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": -0.35683125257492065,
|
| 1695 |
+
"logits/rejected": -0.28000420331954956,
|
| 1696 |
+
"logps/chosen": -494.61016845703125,
|
| 1697 |
+
"logps/rejected": -513.5484619140625,
|
| 1698 |
+
"loss": 0.1875,
|
| 1699 |
+
"rewards/accuracies": 0.46875,
|
| 1700 |
+
"rewards/chosen": -0.07970693707466125,
|
| 1701 |
+
"rewards/margins": 0.04146048426628113,
|
| 1702 |
+
"rewards/rejected": -0.12116742134094238,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": -0.3199581801891327,
|
| 1709 |
+
"logits/rejected": -0.30323344469070435,
|
| 1710 |
+
"logps/chosen": -484.8779296875,
|
| 1711 |
+
"logps/rejected": -546.8536987304688,
|
| 1712 |
+
"loss": 0.1711,
|
| 1713 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1714 |
+
"rewards/chosen": -0.07513175904750824,
|
| 1715 |
+
"rewards/margins": 0.05645768716931343,
|
| 1716 |
+
"rewards/rejected": -0.13158944249153137,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": -0.2838456928730011,
|
| 1723 |
+
"logits/rejected": -0.31488656997680664,
|
| 1724 |
+
"logps/chosen": -470.95025634765625,
|
| 1725 |
+
"logps/rejected": -502.6404724121094,
|
| 1726 |
+
"loss": 0.1864,
|
| 1727 |
+
"rewards/accuracies": 0.46875,
|
| 1728 |
+
"rewards/chosen": -0.07776617258787155,
|
| 1729 |
+
"rewards/margins": 0.044505417346954346,
|
| 1730 |
+
"rewards/rejected": -0.1222715824842453,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": -0.2862758934497833,
|
| 1737 |
+
"logits/rejected": -0.38872987031936646,
|
| 1738 |
+
"logps/chosen": -515.7428588867188,
|
| 1739 |
+
"logps/rejected": -601.1578369140625,
|
| 1740 |
+
"loss": 0.1767,
|
| 1741 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 1742 |
+
"rewards/chosen": -0.08725148439407349,
|
| 1743 |
+
"rewards/margins": 0.07090319693088531,
|
| 1744 |
+
"rewards/rejected": -0.15815469622612,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": -0.35917767882347107,
|
| 1751 |
+
"logits/rejected": -0.39498478174209595,
|
| 1752 |
+
"logps/chosen": -512.1259765625,
|
| 1753 |
+
"logps/rejected": -557.6096801757812,
|
| 1754 |
+
"loss": 0.1919,
|
| 1755 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1756 |
+
"rewards/chosen": -0.08681392669677734,
|
| 1757 |
+
"rewards/margins": 0.055614955723285675,
|
| 1758 |
+
"rewards/rejected": -0.14242888987064362,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": -0.3822699189186096,
|
| 1765 |
+
"logits/rejected": -0.2847387194633484,
|
| 1766 |
+
"logps/chosen": -531.32861328125,
|
| 1767 |
+
"logps/rejected": -538.8329467773438,
|
| 1768 |
+
"loss": 0.1865,
|
| 1769 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1770 |
+
"rewards/chosen": -0.09042377769947052,
|
| 1771 |
+
"rewards/margins": 0.047544240951538086,
|
| 1772 |
+
"rewards/rejected": -0.1379680335521698,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": -0.2868042588233948,
|
| 1779 |
+
"logits/rejected": -0.39659756422042847,
|
| 1780 |
+
"logps/chosen": -440.13201904296875,
|
| 1781 |
+
"logps/rejected": -505.8741760253906,
|
| 1782 |
+
"loss": 0.168,
|
| 1783 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1784 |
+
"rewards/chosen": -0.06821772456169128,
|
| 1785 |
+
"rewards/margins": 0.07103266566991806,
|
| 1786 |
+
"rewards/rejected": -0.13925038278102875,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": -0.267185777425766,
|
| 1793 |
+
"logits/rejected": -0.3715210556983948,
|
| 1794 |
+
"logps/chosen": -508.6048278808594,
|
| 1795 |
+
"logps/rejected": -551.8297119140625,
|
| 1796 |
+
"loss": 0.1861,
|
| 1797 |
+
"rewards/accuracies": 0.46875,
|
| 1798 |
+
"rewards/chosen": -0.08317936956882477,
|
| 1799 |
+
"rewards/margins": 0.04879546910524368,
|
| 1800 |
+
"rewards/rejected": -0.13197484612464905,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": -0.40115490555763245,
|
| 1807 |
+
"logits/rejected": -0.3220266103744507,
|
| 1808 |
+
"logps/chosen": -511.22564697265625,
|
| 1809 |
+
"logps/rejected": -581.5658569335938,
|
| 1810 |
+
"loss": 0.1907,
|
| 1811 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 1812 |
+
"rewards/chosen": -0.07654689252376556,
|
| 1813 |
+
"rewards/margins": 0.05669323727488518,
|
| 1814 |
+
"rewards/rejected": -0.13324013352394104,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": -0.4519384801387787,
|
| 1821 |
+
"logits/rejected": -0.3560634255409241,
|
| 1822 |
+
"logps/chosen": -482.3561096191406,
|
| 1823 |
+
"logps/rejected": -541.8218383789062,
|
| 1824 |
+
"loss": 0.1587,
|
| 1825 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1826 |
+
"rewards/chosen": -0.07603658735752106,
|
| 1827 |
+
"rewards/margins": 0.062384773045778275,
|
| 1828 |
+
"rewards/rejected": -0.13842137157917023,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": -0.45893383026123047,
|
| 1835 |
+
"logits/rejected": -0.34163400530815125,
|
| 1836 |
+
"logps/chosen": -470.9329528808594,
|
| 1837 |
+
"logps/rejected": -551.7818603515625,
|
| 1838 |
+
"loss": 0.1698,
|
| 1839 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1840 |
+
"rewards/chosen": -0.07042945921421051,
|
| 1841 |
+
"rewards/margins": 0.07146573066711426,
|
| 1842 |
+
"rewards/rejected": -0.14189518988132477,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": -0.30523496866226196,
|
| 1849 |
+
"logits/rejected": -0.35816168785095215,
|
| 1850 |
+
"logps/chosen": -522.6578979492188,
|
| 1851 |
+
"logps/rejected": -601.38818359375,
|
| 1852 |
+
"loss": 0.1701,
|
| 1853 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 1854 |
+
"rewards/chosen": -0.08582588285207748,
|
| 1855 |
+
"rewards/margins": 0.06938043236732483,
|
| 1856 |
+
"rewards/rejected": -0.15520630776882172,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": -0.4220711290836334,
|
| 1863 |
+
"logits/rejected": -0.37211546301841736,
|
| 1864 |
+
"logps/chosen": -488.38916015625,
|
| 1865 |
+
"logps/rejected": -604.0801391601562,
|
| 1866 |
+
"loss": 0.1738,
|
| 1867 |
+
"rewards/accuracies": 0.5625,
|
| 1868 |
+
"rewards/chosen": -0.07974353432655334,
|
| 1869 |
+
"rewards/margins": 0.086810402572155,
|
| 1870 |
+
"rewards/rejected": -0.16655394434928894,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": -0.4147316515445709,
|
| 1877 |
+
"logits/rejected": -0.3836427628993988,
|
| 1878 |
+
"logps/chosen": -502.61083984375,
|
| 1879 |
+
"logps/rejected": -578.9619140625,
|
| 1880 |
+
"loss": 0.1864,
|
| 1881 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1882 |
+
"rewards/chosen": -0.08877801150083542,
|
| 1883 |
+
"rewards/margins": 0.07549368590116501,
|
| 1884 |
+
"rewards/rejected": -0.16427169740200043,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": -0.38667914271354675,
|
| 1891 |
+
"logits/rejected": -0.432734876871109,
|
| 1892 |
+
"logps/chosen": -504.5563049316406,
|
| 1893 |
+
"logps/rejected": -590.4224853515625,
|
| 1894 |
+
"loss": 0.1893,
|
| 1895 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1896 |
+
"rewards/chosen": -0.08736555278301239,
|
| 1897 |
+
"rewards/margins": 0.06142817810177803,
|
| 1898 |
+
"rewards/rejected": -0.14879372715950012,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": -0.44079136848449707,
|
| 1905 |
+
"logits/rejected": -0.32765600085258484,
|
| 1906 |
+
"logps/chosen": -426.31103515625,
|
| 1907 |
+
"logps/rejected": -458.25,
|
| 1908 |
+
"loss": 0.1883,
|
| 1909 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1910 |
+
"rewards/chosen": -0.06336107105016708,
|
| 1911 |
+
"rewards/margins": 0.05088551715016365,
|
| 1912 |
+
"rewards/rejected": -0.11424658447504044,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": -0.41225147247314453,
|
| 1919 |
+
"logits/rejected": -0.35755234956741333,
|
| 1920 |
+
"logps/chosen": -410.5465393066406,
|
| 1921 |
+
"logps/rejected": -444.13201904296875,
|
| 1922 |
+
"loss": 0.1893,
|
| 1923 |
+
"rewards/accuracies": 0.38749998807907104,
|
| 1924 |
+
"rewards/chosen": -0.07661779224872589,
|
| 1925 |
+
"rewards/margins": 0.043170757591724396,
|
| 1926 |
+
"rewards/rejected": -0.11978854984045029,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": -0.43255501985549927,
|
| 1933 |
+
"logits/rejected": -0.3273727297782898,
|
| 1934 |
+
"logps/chosen": -493.48895263671875,
|
| 1935 |
+
"logps/rejected": -553.6163330078125,
|
| 1936 |
+
"loss": 0.1807,
|
| 1937 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1938 |
+
"rewards/chosen": -0.0860995277762413,
|
| 1939 |
+
"rewards/margins": 0.05855479836463928,
|
| 1940 |
+
"rewards/rejected": -0.1446543186903,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": -0.49861329793930054,
|
| 1947 |
+
"logits/rejected": -0.3107123374938965,
|
| 1948 |
+
"logps/chosen": -458.6407775878906,
|
| 1949 |
+
"logps/rejected": -507.7791442871094,
|
| 1950 |
+
"loss": 0.1735,
|
| 1951 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1952 |
+
"rewards/chosen": -0.06812812387943268,
|
| 1953 |
+
"rewards/margins": 0.05930028110742569,
|
| 1954 |
+
"rewards/rejected": -0.12742839753627777,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": -0.43581169843673706,
|
| 1961 |
+
"logits/rejected": -0.3831300139427185,
|
| 1962 |
+
"logps/chosen": -505.4359436035156,
|
| 1963 |
+
"logps/rejected": -514.2116088867188,
|
| 1964 |
+
"loss": 0.191,
|
| 1965 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1966 |
+
"rewards/chosen": -0.08728592097759247,
|
| 1967 |
+
"rewards/margins": 0.043969061225652695,
|
| 1968 |
+
"rewards/rejected": -0.13125498592853546,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": -0.4287847876548767,
|
| 1975 |
+
"logits/rejected": -0.3385041356086731,
|
| 1976 |
+
"logps/chosen": -453.57763671875,
|
| 1977 |
+
"logps/rejected": -497.10394287109375,
|
| 1978 |
+
"loss": 0.1644,
|
| 1979 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1980 |
+
"rewards/chosen": -0.06731972098350525,
|
| 1981 |
+
"rewards/margins": 0.06951483339071274,
|
| 1982 |
+
"rewards/rejected": -0.13683456182479858,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": -0.45681437849998474,
|
| 1989 |
+
"logits/rejected": -0.33320799469947815,
|
| 1990 |
+
"logps/chosen": -503.00701904296875,
|
| 1991 |
+
"logps/rejected": -537.3406982421875,
|
| 1992 |
+
"loss": 0.186,
|
| 1993 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1994 |
+
"rewards/chosen": -0.08495952188968658,
|
| 1995 |
+
"rewards/margins": 0.056953202933073044,
|
| 1996 |
+
"rewards/rejected": -0.14191272854804993,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": -0.3651468753814697,
|
| 2003 |
+
"logits/rejected": -0.4669302999973297,
|
| 2004 |
+
"logps/chosen": -472.07421875,
|
| 2005 |
+
"logps/rejected": -524.6736450195312,
|
| 2006 |
+
"loss": 0.1901,
|
| 2007 |
+
"rewards/accuracies": 0.46875,
|
| 2008 |
+
"rewards/chosen": -0.0767470970749855,
|
| 2009 |
+
"rewards/margins": 0.049060117453336716,
|
| 2010 |
+
"rewards/rejected": -0.12580721080303192,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": -0.42758917808532715,
|
| 2017 |
+
"logits/rejected": -0.3809109330177307,
|
| 2018 |
+
"logps/chosen": -458.9986877441406,
|
| 2019 |
+
"logps/rejected": -511.10076904296875,
|
| 2020 |
+
"loss": 0.1656,
|
| 2021 |
+
"rewards/accuracies": 0.46875,
|
| 2022 |
+
"rewards/chosen": -0.061626553535461426,
|
| 2023 |
+
"rewards/margins": 0.05785534530878067,
|
| 2024 |
+
"rewards/rejected": -0.11948190629482269,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": -0.45241889357566833,
|
| 2031 |
+
"logits/rejected": -0.48053082823753357,
|
| 2032 |
+
"logps/chosen": -479.00628662109375,
|
| 2033 |
+
"logps/rejected": -570.8079223632812,
|
| 2034 |
+
"loss": 0.1688,
|
| 2035 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 2036 |
+
"rewards/chosen": -0.07606343924999237,
|
| 2037 |
+
"rewards/margins": 0.077184297144413,
|
| 2038 |
+
"rewards/rejected": -0.15324774384498596,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": -0.4044586718082428,
|
| 2045 |
+
"logits/rejected": -0.4395798146724701,
|
| 2046 |
+
"logps/chosen": -458.71307373046875,
|
| 2047 |
+
"logps/rejected": -535.9743041992188,
|
| 2048 |
+
"loss": 0.1802,
|
| 2049 |
+
"rewards/accuracies": 0.543749988079071,
|
| 2050 |
+
"rewards/chosen": -0.07682407647371292,
|
| 2051 |
+
"rewards/margins": 0.062133777886629105,
|
| 2052 |
+
"rewards/rejected": -0.13895784318447113,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": -0.5003517866134644,
|
| 2059 |
+
"logits/rejected": -0.33631640672683716,
|
| 2060 |
+
"logps/chosen": -469.9927673339844,
|
| 2061 |
+
"logps/rejected": -499.16119384765625,
|
| 2062 |
+
"loss": 0.1919,
|
| 2063 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 2064 |
+
"rewards/chosen": -0.08875006437301636,
|
| 2065 |
+
"rewards/margins": 0.04381968826055527,
|
| 2066 |
+
"rewards/rejected": -0.13256976008415222,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": -0.4493805766105652,
|
| 2073 |
+
"logits/rejected": -0.3728955388069153,
|
| 2074 |
+
"logps/chosen": -463.2948303222656,
|
| 2075 |
+
"logps/rejected": -491.2294006347656,
|
| 2076 |
+
"loss": 0.1858,
|
| 2077 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 2078 |
+
"rewards/chosen": -0.07361346483230591,
|
| 2079 |
+
"rewards/margins": 0.06247217208147049,
|
| 2080 |
+
"rewards/rejected": -0.1360856294631958,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": -0.4490404725074768,
|
| 2087 |
+
"logits/rejected": -0.4013081192970276,
|
| 2088 |
+
"logps/chosen": -473.97869873046875,
|
| 2089 |
+
"logps/rejected": -497.76239013671875,
|
| 2090 |
+
"loss": 0.1927,
|
| 2091 |
+
"rewards/accuracies": 0.4375,
|
| 2092 |
+
"rewards/chosen": -0.0837077870965004,
|
| 2093 |
+
"rewards/margins": 0.04747476428747177,
|
| 2094 |
+
"rewards/rejected": -0.13118253648281097,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": -0.4343733787536621,
|
| 2101 |
+
"logits/rejected": -0.32414108514785767,
|
| 2102 |
+
"logps/chosen": -459.42059326171875,
|
| 2103 |
+
"logps/rejected": -485.1878967285156,
|
| 2104 |
+
"loss": 0.1714,
|
| 2105 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 2106 |
+
"rewards/chosen": -0.08275729417800903,
|
| 2107 |
+
"rewards/margins": 0.050310492515563965,
|
| 2108 |
+
"rewards/rejected": -0.133067786693573,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": -0.38409170508384705,
|
| 2115 |
+
"logits/rejected": -0.36326664686203003,
|
| 2116 |
+
"logps/chosen": -479.1509704589844,
|
| 2117 |
+
"logps/rejected": -543.0540161132812,
|
| 2118 |
+
"loss": 0.1888,
|
| 2119 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 2120 |
+
"rewards/chosen": -0.08453266322612762,
|
| 2121 |
+
"rewards/margins": 0.05342210456728935,
|
| 2122 |
+
"rewards/rejected": -0.13795478641986847,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": -0.3777012526988983,
|
| 2129 |
+
"logits/rejected": -0.4088537096977234,
|
| 2130 |
+
"logps/chosen": -484.7447204589844,
|
| 2131 |
+
"logps/rejected": -536.444091796875,
|
| 2132 |
+
"loss": 0.1752,
|
| 2133 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 2134 |
+
"rewards/chosen": -0.08025570213794708,
|
| 2135 |
+
"rewards/margins": 0.061404865235090256,
|
| 2136 |
+
"rewards/rejected": -0.14166057109832764,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": -0.4726890027523041,
|
| 2143 |
+
"logits/rejected": -0.31746143102645874,
|
| 2144 |
+
"logps/chosen": -519.90869140625,
|
| 2145 |
+
"logps/rejected": -538.6578369140625,
|
| 2146 |
+
"loss": 0.1785,
|
| 2147 |
+
"rewards/accuracies": 0.574999988079071,
|
| 2148 |
+
"rewards/chosen": -0.07591833174228668,
|
| 2149 |
+
"rewards/margins": 0.06365291029214859,
|
| 2150 |
+
"rewards/rejected": -0.13957123458385468,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": -0.5020835399627686,
|
| 2157 |
+
"logits/rejected": -0.37848636507987976,
|
| 2158 |
+
"logps/chosen": -493.8661193847656,
|
| 2159 |
+
"logps/rejected": -555.9498901367188,
|
| 2160 |
+
"loss": 0.1738,
|
| 2161 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2162 |
+
"rewards/chosen": -0.08122778683900833,
|
| 2163 |
+
"rewards/margins": 0.06830001622438431,
|
| 2164 |
+
"rewards/rejected": -0.14952778816223145,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": -0.44509878754615784,
|
| 2171 |
+
"logits/rejected": -0.3348652720451355,
|
| 2172 |
+
"logps/chosen": -458.56353759765625,
|
| 2173 |
+
"logps/rejected": -519.80029296875,
|
| 2174 |
+
"loss": 0.1837,
|
| 2175 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 2176 |
+
"rewards/chosen": -0.07414525747299194,
|
| 2177 |
+
"rewards/margins": 0.07978249341249466,
|
| 2178 |
+
"rewards/rejected": -0.153927743434906,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": -0.4507269859313965,
|
| 2185 |
+
"logits/rejected": -0.28932178020477295,
|
| 2186 |
+
"logps/chosen": -517.053955078125,
|
| 2187 |
+
"logps/rejected": -568.24658203125,
|
| 2188 |
+
"loss": 0.1837,
|
| 2189 |
+
"rewards/accuracies": 0.518750011920929,
|
| 2190 |
+
"rewards/chosen": -0.08871571719646454,
|
| 2191 |
+
"rewards/margins": 0.0724785327911377,
|
| 2192 |
+
"rewards/rejected": -0.16119424998760223,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": -0.44717317819595337,
|
| 2199 |
+
"logits/rejected": -0.3539753556251526,
|
| 2200 |
+
"logps/chosen": -513.8165283203125,
|
| 2201 |
+
"logps/rejected": -546.3040771484375,
|
| 2202 |
+
"loss": 0.183,
|
| 2203 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 2204 |
+
"rewards/chosen": -0.08804842829704285,
|
| 2205 |
+
"rewards/margins": 0.05240340158343315,
|
| 2206 |
+
"rewards/rejected": -0.1404518187046051,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": -0.4437643885612488,
|
| 2213 |
+
"logits/rejected": -0.43425798416137695,
|
| 2214 |
+
"logps/chosen": -429.33642578125,
|
| 2215 |
+
"logps/rejected": -503.93695068359375,
|
| 2216 |
+
"loss": 0.1803,
|
| 2217 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 2218 |
+
"rewards/chosen": -0.06738166511058807,
|
| 2219 |
+
"rewards/margins": 0.07205136865377426,
|
| 2220 |
+
"rewards/rejected": -0.13943304121494293,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": -0.42230138182640076,
|
| 2227 |
+
"logits/rejected": -0.33158788084983826,
|
| 2228 |
+
"logps/chosen": -474.5384826660156,
|
| 2229 |
+
"logps/rejected": -532.5901489257812,
|
| 2230 |
+
"loss": 0.1876,
|
| 2231 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 2232 |
+
"rewards/chosen": -0.08723129332065582,
|
| 2233 |
+
"rewards/margins": 0.050881870090961456,
|
| 2234 |
+
"rewards/rejected": -0.13811317086219788,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": -0.4339612126350403,
|
| 2241 |
+
"logits/rejected": -0.4076845645904541,
|
| 2242 |
+
"logps/chosen": -514.6712036132812,
|
| 2243 |
+
"logps/rejected": -599.03955078125,
|
| 2244 |
+
"loss": 0.1866,
|
| 2245 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2246 |
+
"rewards/chosen": -0.09284873306751251,
|
| 2247 |
+
"rewards/margins": 0.05939553305506706,
|
| 2248 |
+
"rewards/rejected": -0.15224425494670868,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": -0.35802894830703735,
|
| 2255 |
+
"logits/rejected": -0.42679715156555176,
|
| 2256 |
+
"logps/chosen": -499.3904724121094,
|
| 2257 |
+
"logps/rejected": -601.59619140625,
|
| 2258 |
+
"loss": 0.1633,
|
| 2259 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 2260 |
+
"rewards/chosen": -0.08157524466514587,
|
| 2261 |
+
"rewards/margins": 0.08413099497556686,
|
| 2262 |
+
"rewards/rejected": -0.16570623219013214,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": -0.47917836904525757,
|
| 2269 |
+
"logits/rejected": -0.3484811782836914,
|
| 2270 |
+
"logps/chosen": -485.848388671875,
|
| 2271 |
+
"logps/rejected": -538.3430786132812,
|
| 2272 |
+
"loss": 0.1783,
|
| 2273 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 2274 |
+
"rewards/chosen": -0.08013377338647842,
|
| 2275 |
+
"rewards/margins": 0.0631137266755104,
|
| 2276 |
+
"rewards/rejected": -0.14324750006198883,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": -0.4456513524055481,
|
| 2283 |
+
"logits/rejected": -0.32365337014198303,
|
| 2284 |
+
"logps/chosen": -411.17755126953125,
|
| 2285 |
+
"logps/rejected": -458.21923828125,
|
| 2286 |
+
"loss": 0.1884,
|
| 2287 |
+
"rewards/accuracies": 0.46875,
|
| 2288 |
+
"rewards/chosen": -0.06910572201013565,
|
| 2289 |
+
"rewards/margins": 0.057366736233234406,
|
| 2290 |
+
"rewards/rejected": -0.12647245824337006,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": -0.39375001192092896,
|
| 2297 |
+
"logits/rejected": -0.37620794773101807,
|
| 2298 |
+
"logps/chosen": -486.57952880859375,
|
| 2299 |
+
"logps/rejected": -546.0811157226562,
|
| 2300 |
+
"loss": 0.1909,
|
| 2301 |
+
"rewards/accuracies": 0.512499988079071,
|
| 2302 |
+
"rewards/chosen": -0.07672485709190369,
|
| 2303 |
+
"rewards/margins": 0.0658622533082962,
|
| 2304 |
+
"rewards/rejected": -0.1425871104001999,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": -0.4211618900299072,
|
| 2311 |
+
"logits/rejected": -0.3744751513004303,
|
| 2312 |
+
"logps/chosen": -487.8899841308594,
|
| 2313 |
+
"logps/rejected": -532.0867309570312,
|
| 2314 |
+
"loss": 0.1696,
|
| 2315 |
+
"rewards/accuracies": 0.512499988079071,
|
| 2316 |
+
"rewards/chosen": -0.08219683170318604,
|
| 2317 |
+
"rewards/margins": 0.05911056324839592,
|
| 2318 |
+
"rewards/rejected": -0.14130739867687225,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": -0.44197311997413635,
|
| 2325 |
+
"logits/rejected": -0.36461585760116577,
|
| 2326 |
+
"logps/chosen": -481.8468322753906,
|
| 2327 |
+
"logps/rejected": -576.697021484375,
|
| 2328 |
+
"loss": 0.173,
|
| 2329 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 2330 |
+
"rewards/chosen": -0.06508458405733109,
|
| 2331 |
+
"rewards/margins": 0.08507412672042847,
|
| 2332 |
+
"rewards/rejected": -0.15015868842601776,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": -0.5129082798957825,
|
| 2339 |
+
"logits/rejected": -0.3829159140586853,
|
| 2340 |
+
"logps/chosen": -495.10162353515625,
|
| 2341 |
+
"logps/rejected": -520.402587890625,
|
| 2342 |
+
"loss": 0.184,
|
| 2343 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 2344 |
+
"rewards/chosen": -0.08100192248821259,
|
| 2345 |
+
"rewards/margins": 0.04889564588665962,
|
| 2346 |
+
"rewards/rejected": -0.1298975646495819,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": -0.308317631483078,
|
| 2353 |
+
"logits/rejected": -0.4445367455482483,
|
| 2354 |
+
"logps/chosen": -456.50860595703125,
|
| 2355 |
+
"logps/rejected": -507.1785583496094,
|
| 2356 |
+
"loss": 0.1696,
|
| 2357 |
+
"rewards/accuracies": 0.53125,
|
| 2358 |
+
"rewards/chosen": -0.06736288219690323,
|
| 2359 |
+
"rewards/margins": 0.06645634770393372,
|
| 2360 |
+
"rewards/rejected": -0.13381922245025635,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": -0.4731658399105072,
|
| 2367 |
+
"logits/rejected": -0.40087780356407166,
|
| 2368 |
+
"logps/chosen": -472.3287048339844,
|
| 2369 |
+
"logps/rejected": -530.8348388671875,
|
| 2370 |
+
"loss": 0.1823,
|
| 2371 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2372 |
+
"rewards/chosen": -0.07341121137142181,
|
| 2373 |
+
"rewards/margins": 0.05679051950573921,
|
| 2374 |
+
"rewards/rejected": -0.13020172715187073,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": -0.43905097246170044,
|
| 2381 |
+
"logits/rejected": -0.4049570560455322,
|
| 2382 |
+
"logps/chosen": -467.10504150390625,
|
| 2383 |
+
"logps/rejected": -543.2198486328125,
|
| 2384 |
+
"loss": 0.1844,
|
| 2385 |
+
"rewards/accuracies": 0.5,
|
| 2386 |
+
"rewards/chosen": -0.09198932349681854,
|
| 2387 |
+
"rewards/margins": 0.05702856183052063,
|
| 2388 |
+
"rewards/rejected": -0.14901788532733917,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": -0.4321065843105316,
|
| 2395 |
+
"logits/rejected": -0.3883914649486542,
|
| 2396 |
+
"logps/chosen": -507.26641845703125,
|
| 2397 |
+
"logps/rejected": -551.1337280273438,
|
| 2398 |
+
"loss": 0.1953,
|
| 2399 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 2400 |
+
"rewards/chosen": -0.08602117002010345,
|
| 2401 |
+
"rewards/margins": 0.05450272560119629,
|
| 2402 |
+
"rewards/rejected": -0.14052391052246094,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": -0.42082422971725464,
|
| 2409 |
+
"logits/rejected": -0.41699376702308655,
|
| 2410 |
+
"logps/chosen": -464.18939208984375,
|
| 2411 |
+
"logps/rejected": -534.9678344726562,
|
| 2412 |
+
"loss": 0.1756,
|
| 2413 |
+
"rewards/accuracies": 0.512499988079071,
|
| 2414 |
+
"rewards/chosen": -0.07923159748315811,
|
| 2415 |
+
"rewards/margins": 0.06845531612634659,
|
| 2416 |
+
"rewards/rejected": -0.1476869136095047,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": -0.45704323053359985,
|
| 2423 |
+
"logits/rejected": -0.3829982876777649,
|
| 2424 |
+
"logps/chosen": -516.6412353515625,
|
| 2425 |
+
"logps/rejected": -563.4931640625,
|
| 2426 |
+
"loss": 0.1887,
|
| 2427 |
+
"rewards/accuracies": 0.550000011920929,
|
| 2428 |
+
"rewards/chosen": -0.08942435681819916,
|
| 2429 |
+
"rewards/margins": 0.07117379456758499,
|
| 2430 |
+
"rewards/rejected": -0.16059814393520355,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": -0.4678065776824951,
|
| 2437 |
+
"logits/rejected": -0.39768505096435547,
|
| 2438 |
+
"logps/chosen": -384.6977233886719,
|
| 2439 |
+
"logps/rejected": -438.79754638671875,
|
| 2440 |
+
"loss": 0.1838,
|
| 2441 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 2442 |
+
"rewards/chosen": -0.05616065859794617,
|
| 2443 |
+
"rewards/margins": 0.054783742874860764,
|
| 2444 |
+
"rewards/rejected": -0.11094440519809723,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": -0.45986437797546387,
|
| 2451 |
+
"logits/rejected": -0.3251883089542389,
|
| 2452 |
+
"logps/chosen": -523.9485473632812,
|
| 2453 |
+
"logps/rejected": -555.4884033203125,
|
| 2454 |
+
"loss": 0.1823,
|
| 2455 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 2456 |
+
"rewards/chosen": -0.0797450989484787,
|
| 2457 |
+
"rewards/margins": 0.05564265325665474,
|
| 2458 |
+
"rewards/rejected": -0.13538774847984314,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": -0.4108913540840149,
|
| 2465 |
+
"logits/rejected": -0.2947922945022583,
|
| 2466 |
+
"logps/chosen": -538.8464965820312,
|
| 2467 |
+
"logps/rejected": -580.0211791992188,
|
| 2468 |
+
"loss": 0.192,
|
| 2469 |
+
"rewards/accuracies": 0.5625,
|
| 2470 |
+
"rewards/chosen": -0.09397675096988678,
|
| 2471 |
+
"rewards/margins": 0.05662484094500542,
|
| 2472 |
+
"rewards/rejected": -0.1506015956401825,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": -0.31575465202331543,
|
| 2479 |
+
"logits/rejected": -0.376641184091568,
|
| 2480 |
+
"logps/chosen": -487.80633544921875,
|
| 2481 |
+
"logps/rejected": -575.765625,
|
| 2482 |
+
"loss": 0.1692,
|
| 2483 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 2484 |
+
"rewards/chosen": -0.0703391507267952,
|
| 2485 |
+
"rewards/margins": 0.08664790540933609,
|
| 2486 |
+
"rewards/rejected": -0.1569870412349701,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": -0.414639949798584,
|
| 2493 |
+
"logits/rejected": -0.43213406205177307,
|
| 2494 |
+
"logps/chosen": -588.9749755859375,
|
| 2495 |
+
"logps/rejected": -631.2474365234375,
|
| 2496 |
+
"loss": 0.1871,
|
| 2497 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 2498 |
+
"rewards/chosen": -0.09701113402843475,
|
| 2499 |
+
"rewards/margins": 0.057556282728910446,
|
| 2500 |
+
"rewards/rejected": -0.1545674204826355,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": -0.42236852645874023,
|
| 2507 |
+
"logits/rejected": -0.3948751389980316,
|
| 2508 |
+
"logps/chosen": -486.19598388671875,
|
| 2509 |
+
"logps/rejected": -501.712646484375,
|
| 2510 |
+
"loss": 0.1907,
|
| 2511 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 2512 |
+
"rewards/chosen": -0.08502433449029922,
|
| 2513 |
+
"rewards/margins": 0.051293183118104935,
|
| 2514 |
+
"rewards/rejected": -0.13631752133369446,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": -0.4508518576622009,
|
| 2521 |
+
"logits/rejected": -0.2803448438644409,
|
| 2522 |
+
"logps/chosen": -528.0969848632812,
|
| 2523 |
+
"logps/rejected": -578.2789306640625,
|
| 2524 |
+
"loss": 0.1681,
|
| 2525 |
+
"rewards/accuracies": 0.512499988079071,
|
| 2526 |
+
"rewards/chosen": -0.0905873253941536,
|
| 2527 |
+
"rewards/margins": 0.07002563774585724,
|
| 2528 |
+
"rewards/rejected": -0.16061295568943024,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": -0.4513494372367859,
|
| 2535 |
+
"logits/rejected": -0.4356984496116638,
|
| 2536 |
+
"logps/chosen": -499.56884765625,
|
| 2537 |
+
"logps/rejected": -582.083740234375,
|
| 2538 |
+
"loss": 0.1743,
|
| 2539 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 2540 |
+
"rewards/chosen": -0.08331683278083801,
|
| 2541 |
+
"rewards/margins": 0.07355960458517075,
|
| 2542 |
+
"rewards/rejected": -0.15687642991542816,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": -0.46016424894332886,
|
| 2549 |
+
"logits/rejected": -0.29402580857276917,
|
| 2550 |
+
"logps/chosen": -451.9331970214844,
|
| 2551 |
+
"logps/rejected": -494.04815673828125,
|
| 2552 |
+
"loss": 0.1806,
|
| 2553 |
+
"rewards/accuracies": 0.53125,
|
| 2554 |
+
"rewards/chosen": -0.0696534812450409,
|
| 2555 |
+
"rewards/margins": 0.06958705186843872,
|
| 2556 |
+
"rewards/rejected": -0.13924053311347961,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": -0.501002848148346,
|
| 2563 |
+
"logits/rejected": -0.35800036787986755,
|
| 2564 |
+
"logps/chosen": -489.6319274902344,
|
| 2565 |
+
"logps/rejected": -548.3452758789062,
|
| 2566 |
+
"loss": 0.1739,
|
| 2567 |
+
"rewards/accuracies": 0.550000011920929,
|
| 2568 |
+
"rewards/chosen": -0.08254210650920868,
|
| 2569 |
+
"rewards/margins": 0.06711296737194061,
|
| 2570 |
+
"rewards/rejected": -0.1496550738811493,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": -0.42636099457740784,
|
| 2577 |
+
"logits/rejected": -0.3364613652229309,
|
| 2578 |
+
"logps/chosen": -483.1874084472656,
|
| 2579 |
+
"logps/rejected": -515.3287353515625,
|
| 2580 |
+
"loss": 0.172,
|
| 2581 |
+
"rewards/accuracies": 0.53125,
|
| 2582 |
+
"rewards/chosen": -0.07863263040781021,
|
| 2583 |
+
"rewards/margins": 0.057226501405239105,
|
| 2584 |
+
"rewards/rejected": -0.1358591467142105,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": -0.45698413252830505,
|
| 2591 |
+
"logits/rejected": -0.3893563151359558,
|
| 2592 |
+
"logps/chosen": -492.31610107421875,
|
| 2593 |
+
"logps/rejected": -549.0144653320312,
|
| 2594 |
+
"loss": 0.1795,
|
| 2595 |
+
"rewards/accuracies": 0.518750011920929,
|
| 2596 |
+
"rewards/chosen": -0.08794066309928894,
|
| 2597 |
+
"rewards/margins": 0.055044692009687424,
|
| 2598 |
+
"rewards/rejected": -0.14298535883426666,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": -0.4179384112358093,
|
| 2605 |
+
"logits/rejected": -0.3843657672405243,
|
| 2606 |
+
"logps/chosen": -512.0191650390625,
|
| 2607 |
+
"logps/rejected": -557.4730224609375,
|
| 2608 |
+
"loss": 0.1648,
|
| 2609 |
+
"rewards/accuracies": 0.53125,
|
| 2610 |
+
"rewards/chosen": -0.07361841946840286,
|
| 2611 |
+
"rewards/margins": 0.06739214807748795,
|
| 2612 |
+
"rewards/rejected": -0.141010582447052,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": -0.4060386121273041,
|
| 2619 |
+
"logits/rejected": -0.3960750699043274,
|
| 2620 |
+
"logps/chosen": -479.4234313964844,
|
| 2621 |
+
"logps/rejected": -551.9636840820312,
|
| 2622 |
+
"loss": 0.1975,
|
| 2623 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 2624 |
+
"rewards/chosen": -0.08916465938091278,
|
| 2625 |
+
"rewards/margins": 0.05007479339838028,
|
| 2626 |
+
"rewards/rejected": -0.13923944532871246,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": -0.42799386382102966,
|
| 2633 |
+
"logits/rejected": -0.3839925229549408,
|
| 2634 |
+
"logps/chosen": -454.05499267578125,
|
| 2635 |
+
"logps/rejected": -501.215087890625,
|
| 2636 |
+
"loss": 0.1847,
|
| 2637 |
+
"rewards/accuracies": 0.46875,
|
| 2638 |
+
"rewards/chosen": -0.07664839923381805,
|
| 2639 |
+
"rewards/margins": 0.05011936277151108,
|
| 2640 |
+
"rewards/rejected": -0.12676775455474854,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 0.1858275575319926,
|
| 2648 |
+
"train_runtime": 11460.3939,
|
| 2649 |
+
"train_samples_per_second": 2.618,
|
| 2650 |
+
"train_steps_per_second": 0.164
|
| 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 |
+
}
|