Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May18_11-03-34_gpu4-119-5/events.out.tfevents.1715994452.gpu4-119-5.2210814.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1794 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO-2/phi-2-gpo-v34-merged-i1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-gpo-v7-i2
|
| 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-gpo-v7-i2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO-2/phi-2-gpo-v34-merged-i1](https://huggingface.co/DUAL-GPO-2/phi-2-gpo-v34-merged-i1) 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 |
+
- num_devices: 3
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 48
|
| 45 |
+
- total_eval_batch_size: 12
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.7.1
|
| 58 |
+
- Transformers 4.36.2
|
| 59 |
+
- Pytorch 2.1.2+cu121
|
| 60 |
+
- Datasets 2.14.6
|
| 61 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167807296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4324b35cfd2b12cbb440e5531043cf5c5bffc94ac31de3e625bc8fc776f4c816
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.6514112674713135,
|
| 4 |
+
"train_runtime": 16819.2653,
|
| 5 |
+
"train_samples": 60000,
|
| 6 |
+
"train_samples_per_second": 3.567,
|
| 7 |
+
"train_steps_per_second": 0.074
|
| 8 |
+
}
|
runs/May18_11-03-34_gpu4-119-5/events.out.tfevents.1715994452.gpu4-119-5.2210814.0
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:fe8da2850534a7e2a0c99164094ee90d1ad952bee9decc2954afaf10ec3fffce
|
| 3 |
+
size 84935
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.6514112674713135,
|
| 4 |
+
"train_runtime": 16819.2653,
|
| 5 |
+
"train_samples": 60000,
|
| 6 |
+
"train_samples_per_second": 3.567,
|
| 7 |
+
"train_steps_per_second": 0.074
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1794 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1250,
|
| 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": 4e-08,
|
| 14 |
+
"logits/chosen": -0.21237623691558838,
|
| 15 |
+
"logits/rejected": -0.020425911992788315,
|
| 16 |
+
"logps/chosen": -339.1651306152344,
|
| 17 |
+
"logps/rejected": -403.4797058105469,
|
| 18 |
+
"loss": 2.2013,
|
| 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": 4.0000000000000003e-07,
|
| 28 |
+
"logits/chosen": -0.1229037418961525,
|
| 29 |
+
"logits/rejected": -0.09083450585603714,
|
| 30 |
+
"logps/chosen": -409.6603698730469,
|
| 31 |
+
"logps/rejected": -385.8681640625,
|
| 32 |
+
"loss": 2.2536,
|
| 33 |
+
"rewards/accuracies": 0.3125,
|
| 34 |
+
"rewards/chosen": 0.0001750251540215686,
|
| 35 |
+
"rewards/margins": -0.0002073741634376347,
|
| 36 |
+
"rewards/rejected": 0.0003823993029072881,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 8.000000000000001e-07,
|
| 42 |
+
"logits/chosen": -0.2033734768629074,
|
| 43 |
+
"logits/rejected": -0.14241939783096313,
|
| 44 |
+
"logps/chosen": -430.78778076171875,
|
| 45 |
+
"logps/rejected": -420.1714782714844,
|
| 46 |
+
"loss": 2.0797,
|
| 47 |
+
"rewards/accuracies": 0.46875,
|
| 48 |
+
"rewards/chosen": -7.134475890779868e-05,
|
| 49 |
+
"rewards/margins": 0.0001290472282562405,
|
| 50 |
+
"rewards/rejected": -0.00020039197988808155,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 56 |
+
"logits/chosen": -0.1662522554397583,
|
| 57 |
+
"logits/rejected": -0.07332392036914825,
|
| 58 |
+
"logps/chosen": -389.4374084472656,
|
| 59 |
+
"logps/rejected": -392.1519775390625,
|
| 60 |
+
"loss": 2.1227,
|
| 61 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 62 |
+
"rewards/chosen": -0.0009240208892151713,
|
| 63 |
+
"rewards/margins": 0.00010561713861534372,
|
| 64 |
+
"rewards/rejected": -0.001029637991450727,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 70 |
+
"logits/chosen": -0.18387895822525024,
|
| 71 |
+
"logits/rejected": -0.09537571668624878,
|
| 72 |
+
"logps/chosen": -394.1351013183594,
|
| 73 |
+
"logps/rejected": -378.9622497558594,
|
| 74 |
+
"loss": 2.1895,
|
| 75 |
+
"rewards/accuracies": 0.5,
|
| 76 |
+
"rewards/chosen": -0.0023726867511868477,
|
| 77 |
+
"rewards/margins": 0.000768904690630734,
|
| 78 |
+
"rewards/rejected": -0.003141591791063547,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 84 |
+
"logits/chosen": -0.18213973939418793,
|
| 85 |
+
"logits/rejected": -0.09330956637859344,
|
| 86 |
+
"logps/chosen": -374.6993713378906,
|
| 87 |
+
"logps/rejected": -371.1645812988281,
|
| 88 |
+
"loss": 2.1547,
|
| 89 |
+
"rewards/accuracies": 0.606249988079071,
|
| 90 |
+
"rewards/chosen": -0.0057793245650827885,
|
| 91 |
+
"rewards/margins": 0.0022816271521151066,
|
| 92 |
+
"rewards/rejected": -0.00806095264852047,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 98 |
+
"logits/chosen": -0.1841249316930771,
|
| 99 |
+
"logits/rejected": -0.1609618067741394,
|
| 100 |
+
"logps/chosen": -420.17218017578125,
|
| 101 |
+
"logps/rejected": -388.83990478515625,
|
| 102 |
+
"loss": 2.1266,
|
| 103 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 104 |
+
"rewards/chosen": -0.013447234407067299,
|
| 105 |
+
"rewards/margins": 0.004250804893672466,
|
| 106 |
+
"rewards/rejected": -0.01769803836941719,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 112 |
+
"logits/chosen": -0.1828843504190445,
|
| 113 |
+
"logits/rejected": -0.12139382213354111,
|
| 114 |
+
"logps/chosen": -453.1728515625,
|
| 115 |
+
"logps/rejected": -439.40167236328125,
|
| 116 |
+
"loss": 2.1854,
|
| 117 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 118 |
+
"rewards/chosen": -0.03316130489110947,
|
| 119 |
+
"rewards/margins": 0.01242602989077568,
|
| 120 |
+
"rewards/rejected": -0.045587338507175446,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06,
|
| 125 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 126 |
+
"logits/chosen": -0.18017946183681488,
|
| 127 |
+
"logits/rejected": -0.16199861466884613,
|
| 128 |
+
"logps/chosen": -492.6966857910156,
|
| 129 |
+
"logps/rejected": -502.58282470703125,
|
| 130 |
+
"loss": 2.0852,
|
| 131 |
+
"rewards/accuracies": 0.637499988079071,
|
| 132 |
+
"rewards/chosen": -0.06695900857448578,
|
| 133 |
+
"rewards/margins": 0.03570399060845375,
|
| 134 |
+
"rewards/rejected": -0.10266300290822983,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 140 |
+
"logits/chosen": -0.17906096577644348,
|
| 141 |
+
"logits/rejected": -0.16469471156597137,
|
| 142 |
+
"logps/chosen": -588.4837036132812,
|
| 143 |
+
"logps/rejected": -648.6444702148438,
|
| 144 |
+
"loss": 1.9145,
|
| 145 |
+
"rewards/accuracies": 0.606249988079071,
|
| 146 |
+
"rewards/chosen": -0.16310617327690125,
|
| 147 |
+
"rewards/margins": 0.08765674382448196,
|
| 148 |
+
"rewards/rejected": -0.2507628798484802,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08,
|
| 153 |
+
"learning_rate": 4.000000000000001e-06,
|
| 154 |
+
"logits/chosen": -0.20857279002666473,
|
| 155 |
+
"logits/rejected": -0.19442644715309143,
|
| 156 |
+
"logps/chosen": -678.5848388671875,
|
| 157 |
+
"logps/rejected": -815.7537231445312,
|
| 158 |
+
"loss": 1.9158,
|
| 159 |
+
"rewards/accuracies": 0.59375,
|
| 160 |
+
"rewards/chosen": -0.2612169682979584,
|
| 161 |
+
"rewards/margins": 0.18096813559532166,
|
| 162 |
+
"rewards/rejected": -0.44218510389328003,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09,
|
| 167 |
+
"learning_rate": 4.4e-06,
|
| 168 |
+
"logits/chosen": -0.23685956001281738,
|
| 169 |
+
"logits/rejected": -0.1955154836177826,
|
| 170 |
+
"logps/chosen": -766.2359619140625,
|
| 171 |
+
"logps/rejected": -969.7020263671875,
|
| 172 |
+
"loss": 1.8551,
|
| 173 |
+
"rewards/accuracies": 0.612500011920929,
|
| 174 |
+
"rewards/chosen": -0.3886342942714691,
|
| 175 |
+
"rewards/margins": 0.19053591787815094,
|
| 176 |
+
"rewards/rejected": -0.5791702270507812,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 4.800000000000001e-06,
|
| 182 |
+
"logits/chosen": -0.23603197932243347,
|
| 183 |
+
"logits/rejected": -0.17843177914619446,
|
| 184 |
+
"logps/chosen": -816.71826171875,
|
| 185 |
+
"logps/rejected": -1092.5975341796875,
|
| 186 |
+
"loss": 1.8855,
|
| 187 |
+
"rewards/accuracies": 0.637499988079071,
|
| 188 |
+
"rewards/chosen": -0.38946443796157837,
|
| 189 |
+
"rewards/margins": 0.2521887421607971,
|
| 190 |
+
"rewards/rejected": -0.6416531205177307,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1,
|
| 195 |
+
"learning_rate": 4.999756310023261e-06,
|
| 196 |
+
"logits/chosen": -0.2602929472923279,
|
| 197 |
+
"logits/rejected": -0.20586004853248596,
|
| 198 |
+
"logps/chosen": -778.2180786132812,
|
| 199 |
+
"logps/rejected": -966.8118286132812,
|
| 200 |
+
"loss": 1.8652,
|
| 201 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 202 |
+
"rewards/chosen": -0.38287556171417236,
|
| 203 |
+
"rewards/margins": 0.1863778531551361,
|
| 204 |
+
"rewards/rejected": -0.5692533850669861,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.11,
|
| 209 |
+
"learning_rate": 4.997807075247147e-06,
|
| 210 |
+
"logits/chosen": -0.2347811758518219,
|
| 211 |
+
"logits/rejected": -0.1346631944179535,
|
| 212 |
+
"logps/chosen": -744.4739379882812,
|
| 213 |
+
"logps/rejected": -884.68994140625,
|
| 214 |
+
"loss": 1.9158,
|
| 215 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 216 |
+
"rewards/chosen": -0.3381068706512451,
|
| 217 |
+
"rewards/margins": 0.1455555260181427,
|
| 218 |
+
"rewards/rejected": -0.4836624264717102,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 4.993910125649561e-06,
|
| 224 |
+
"logits/chosen": -0.24987225234508514,
|
| 225 |
+
"logits/rejected": -0.2068624198436737,
|
| 226 |
+
"logps/chosen": -865.6614379882812,
|
| 227 |
+
"logps/rejected": -1111.9520263671875,
|
| 228 |
+
"loss": 1.9346,
|
| 229 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 230 |
+
"rewards/chosen": -0.43612995743751526,
|
| 231 |
+
"rewards/margins": 0.25621694326400757,
|
| 232 |
+
"rewards/rejected": -0.6923469305038452,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13,
|
| 237 |
+
"learning_rate": 4.988068499954578e-06,
|
| 238 |
+
"logits/chosen": -0.2418244630098343,
|
| 239 |
+
"logits/rejected": -0.1966630518436432,
|
| 240 |
+
"logps/chosen": -785.2879028320312,
|
| 241 |
+
"logps/rejected": -991.7936401367188,
|
| 242 |
+
"loss": 1.8176,
|
| 243 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 244 |
+
"rewards/chosen": -0.39799419045448303,
|
| 245 |
+
"rewards/margins": 0.18280699849128723,
|
| 246 |
+
"rewards/rejected": -0.580801248550415,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"learning_rate": 4.980286753286196e-06,
|
| 252 |
+
"logits/chosen": -0.18229472637176514,
|
| 253 |
+
"logits/rejected": -0.09505169093608856,
|
| 254 |
+
"logps/chosen": -779.7567138671875,
|
| 255 |
+
"logps/rejected": -905.3895263671875,
|
| 256 |
+
"loss": 1.9224,
|
| 257 |
+
"rewards/accuracies": 0.574999988079071,
|
| 258 |
+
"rewards/chosen": -0.34025901556015015,
|
| 259 |
+
"rewards/margins": 0.165119469165802,
|
| 260 |
+
"rewards/rejected": -0.5053785443305969,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14,
|
| 265 |
+
"learning_rate": 4.970570953616383e-06,
|
| 266 |
+
"logits/chosen": -0.24447326362133026,
|
| 267 |
+
"logits/rejected": -0.18509261310100555,
|
| 268 |
+
"logps/chosen": -806.5858154296875,
|
| 269 |
+
"logps/rejected": -1070.8280029296875,
|
| 270 |
+
"loss": 1.8121,
|
| 271 |
+
"rewards/accuracies": 0.6875,
|
| 272 |
+
"rewards/chosen": -0.3903842568397522,
|
| 273 |
+
"rewards/margins": 0.23679156601428986,
|
| 274 |
+
"rewards/rejected": -0.6271758079528809,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15,
|
| 279 |
+
"learning_rate": 4.958928677033465e-06,
|
| 280 |
+
"logits/chosen": -0.22912044823169708,
|
| 281 |
+
"logits/rejected": -0.22532768547534943,
|
| 282 |
+
"logps/chosen": -948.6514892578125,
|
| 283 |
+
"logps/rejected": -1230.310302734375,
|
| 284 |
+
"loss": 1.7871,
|
| 285 |
+
"rewards/accuracies": 0.643750011920929,
|
| 286 |
+
"rewards/chosen": -0.5143545866012573,
|
| 287 |
+
"rewards/margins": 0.28488418459892273,
|
| 288 |
+
"rewards/rejected": -0.7992388010025024,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16,
|
| 293 |
+
"learning_rate": 4.9453690018345144e-06,
|
| 294 |
+
"logits/chosen": -0.2154952734708786,
|
| 295 |
+
"logits/rejected": -0.17434343695640564,
|
| 296 |
+
"logps/chosen": -969.3416748046875,
|
| 297 |
+
"logps/rejected": -1133.4462890625,
|
| 298 |
+
"loss": 1.9032,
|
| 299 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 300 |
+
"rewards/chosen": -0.5185384750366211,
|
| 301 |
+
"rewards/margins": 0.21671628952026367,
|
| 302 |
+
"rewards/rejected": -0.7352547645568848,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 4.9299025014463665e-06,
|
| 308 |
+
"logits/chosen": -0.20597633719444275,
|
| 309 |
+
"logits/rejected": -0.13240107893943787,
|
| 310 |
+
"logps/chosen": -952.5860595703125,
|
| 311 |
+
"logps/rejected": -1088.127685546875,
|
| 312 |
+
"loss": 1.774,
|
| 313 |
+
"rewards/accuracies": 0.675000011920929,
|
| 314 |
+
"rewards/chosen": -0.4815760552883148,
|
| 315 |
+
"rewards/margins": 0.22714009881019592,
|
| 316 |
+
"rewards/rejected": -0.708716094493866,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"learning_rate": 4.912541236180779e-06,
|
| 322 |
+
"logits/chosen": -0.16825485229492188,
|
| 323 |
+
"logits/rejected": -0.1814446598291397,
|
| 324 |
+
"logps/chosen": -859.4645385742188,
|
| 325 |
+
"logps/rejected": -1155.5140380859375,
|
| 326 |
+
"loss": 1.6983,
|
| 327 |
+
"rewards/accuracies": 0.606249988079071,
|
| 328 |
+
"rewards/chosen": -0.46208739280700684,
|
| 329 |
+
"rewards/margins": 0.26932135224342346,
|
| 330 |
+
"rewards/rejected": -0.7314087152481079,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.18,
|
| 335 |
+
"learning_rate": 4.893298743830168e-06,
|
| 336 |
+
"logits/chosen": -0.1780141294002533,
|
| 337 |
+
"logits/rejected": -0.1537729650735855,
|
| 338 |
+
"logps/chosen": -854.94189453125,
|
| 339 |
+
"logps/rejected": -1050.1890869140625,
|
| 340 |
+
"loss": 1.8135,
|
| 341 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 342 |
+
"rewards/chosen": -0.4414963722229004,
|
| 343 |
+
"rewards/margins": 0.22997328639030457,
|
| 344 |
+
"rewards/rejected": -0.6714696884155273,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.19,
|
| 349 |
+
"learning_rate": 4.8721900291112415e-06,
|
| 350 |
+
"logits/chosen": -0.15549209713935852,
|
| 351 |
+
"logits/rejected": -0.1134282797574997,
|
| 352 |
+
"logps/chosen": -820.55224609375,
|
| 353 |
+
"logps/rejected": -1063.4244384765625,
|
| 354 |
+
"loss": 1.7236,
|
| 355 |
+
"rewards/accuracies": 0.699999988079071,
|
| 356 |
+
"rewards/chosen": -0.39099445939064026,
|
| 357 |
+
"rewards/margins": 0.22765907645225525,
|
| 358 |
+
"rewards/rejected": -0.6186535954475403,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2,
|
| 363 |
+
"learning_rate": 4.849231551964771e-06,
|
| 364 |
+
"logits/chosen": -0.12339262664318085,
|
| 365 |
+
"logits/rejected": -0.13772717118263245,
|
| 366 |
+
"logps/chosen": -767.2117919921875,
|
| 367 |
+
"logps/rejected": -1062.240966796875,
|
| 368 |
+
"loss": 1.6988,
|
| 369 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 370 |
+
"rewards/chosen": -0.41696324944496155,
|
| 371 |
+
"rewards/margins": 0.25669869780540466,
|
| 372 |
+
"rewards/rejected": -0.6736618876457214,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21,
|
| 377 |
+
"learning_rate": 4.824441214720629e-06,
|
| 378 |
+
"logits/chosen": -0.12506547570228577,
|
| 379 |
+
"logits/rejected": -0.1212812289595604,
|
| 380 |
+
"logps/chosen": -927.6405029296875,
|
| 381 |
+
"logps/rejected": -1118.3206787109375,
|
| 382 |
+
"loss": 1.6725,
|
| 383 |
+
"rewards/accuracies": 0.668749988079071,
|
| 384 |
+
"rewards/chosen": -0.45764121413230896,
|
| 385 |
+
"rewards/margins": 0.23505349457263947,
|
| 386 |
+
"rewards/rejected": -0.6926947832107544,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 4.7978383481380865e-06,
|
| 392 |
+
"logits/chosen": -0.17072610557079315,
|
| 393 |
+
"logits/rejected": -0.15457463264465332,
|
| 394 |
+
"logps/chosen": -907.0338745117188,
|
| 395 |
+
"logps/rejected": -1103.2227783203125,
|
| 396 |
+
"loss": 1.9004,
|
| 397 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 398 |
+
"rewards/chosen": -0.5299123525619507,
|
| 399 |
+
"rewards/margins": 0.2055232971906662,
|
| 400 |
+
"rewards/rejected": -0.7354356646537781,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.22,
|
| 405 |
+
"learning_rate": 4.769443696332272e-06,
|
| 406 |
+
"logits/chosen": -0.17946860194206238,
|
| 407 |
+
"logits/rejected": -0.12909087538719177,
|
| 408 |
+
"logps/chosen": -944.4387817382812,
|
| 409 |
+
"logps/rejected": -1121.226806640625,
|
| 410 |
+
"loss": 1.8032,
|
| 411 |
+
"rewards/accuracies": 0.606249988079071,
|
| 412 |
+
"rewards/chosen": -0.5064274668693542,
|
| 413 |
+
"rewards/margins": 0.1990656554698944,
|
| 414 |
+
"rewards/rejected": -0.705493152141571,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.23,
|
| 419 |
+
"learning_rate": 4.7392794005985324e-06,
|
| 420 |
+
"logits/chosen": -0.19116660952568054,
|
| 421 |
+
"logits/rejected": -0.19017921388149261,
|
| 422 |
+
"logps/chosen": -936.3536987304688,
|
| 423 |
+
"logps/rejected": -1282.28125,
|
| 424 |
+
"loss": 1.5663,
|
| 425 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 426 |
+
"rewards/chosen": -0.5539158582687378,
|
| 427 |
+
"rewards/margins": 0.33316585421562195,
|
| 428 |
+
"rewards/rejected": -0.8870818018913269,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24,
|
| 433 |
+
"learning_rate": 4.707368982147318e-06,
|
| 434 |
+
"logits/chosen": -0.1529879868030548,
|
| 435 |
+
"logits/rejected": -0.12170819938182831,
|
| 436 |
+
"logps/chosen": -992.0021362304688,
|
| 437 |
+
"logps/rejected": -1266.134521484375,
|
| 438 |
+
"loss": 1.6594,
|
| 439 |
+
"rewards/accuracies": 0.625,
|
| 440 |
+
"rewards/chosen": -0.5842385292053223,
|
| 441 |
+
"rewards/margins": 0.28491389751434326,
|
| 442 |
+
"rewards/rejected": -0.8691525459289551,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.25,
|
| 447 |
+
"learning_rate": 4.673737323763048e-06,
|
| 448 |
+
"logits/chosen": -0.13799923658370972,
|
| 449 |
+
"logits/rejected": -0.11788105964660645,
|
| 450 |
+
"logps/chosen": -874.9791259765625,
|
| 451 |
+
"logps/rejected": -1244.6304931640625,
|
| 452 |
+
"loss": 1.6174,
|
| 453 |
+
"rewards/accuracies": 0.75,
|
| 454 |
+
"rewards/chosen": -0.48227429389953613,
|
| 455 |
+
"rewards/margins": 0.33959290385246277,
|
| 456 |
+
"rewards/rejected": -0.8218671679496765,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.26,
|
| 461 |
+
"learning_rate": 4.638410650401267e-06,
|
| 462 |
+
"logits/chosen": -0.09933747351169586,
|
| 463 |
+
"logits/rejected": -0.0572042241692543,
|
| 464 |
+
"logps/chosen": -885.7242431640625,
|
| 465 |
+
"logps/rejected": -1079.048583984375,
|
| 466 |
+
"loss": 1.684,
|
| 467 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 468 |
+
"rewards/chosen": -0.47158098220825195,
|
| 469 |
+
"rewards/margins": 0.20864149928092957,
|
| 470 |
+
"rewards/rejected": -0.6802224516868591,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.26,
|
| 475 |
+
"learning_rate": 4.601416508739211e-06,
|
| 476 |
+
"logits/chosen": -0.10739854723215103,
|
| 477 |
+
"logits/rejected": -0.08502750098705292,
|
| 478 |
+
"logps/chosen": -963.4494018554688,
|
| 479 |
+
"logps/rejected": -1153.433349609375,
|
| 480 |
+
"loss": 1.6356,
|
| 481 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 482 |
+
"rewards/chosen": -0.5099435448646545,
|
| 483 |
+
"rewards/margins": 0.2381589412689209,
|
| 484 |
+
"rewards/rejected": -0.7481025457382202,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.27,
|
| 489 |
+
"learning_rate": 4.562783745695738e-06,
|
| 490 |
+
"logits/chosen": -0.16697099804878235,
|
| 491 |
+
"logits/rejected": -0.14366139471530914,
|
| 492 |
+
"logps/chosen": -860.5040283203125,
|
| 493 |
+
"logps/rejected": -1141.27685546875,
|
| 494 |
+
"loss": 1.6149,
|
| 495 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 496 |
+
"rewards/chosen": -0.4745675027370453,
|
| 497 |
+
"rewards/margins": 0.276507169008255,
|
| 498 |
+
"rewards/rejected": -0.7510746717453003,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.28,
|
| 503 |
+
"learning_rate": 4.522542485937369e-06,
|
| 504 |
+
"logits/chosen": -0.11317078024148941,
|
| 505 |
+
"logits/rejected": -0.07480302453041077,
|
| 506 |
+
"logps/chosen": -983.2384033203125,
|
| 507 |
+
"logps/rejected": -1304.386962890625,
|
| 508 |
+
"loss": 1.7718,
|
| 509 |
+
"rewards/accuracies": 0.699999988079071,
|
| 510 |
+
"rewards/chosen": -0.5476148724555969,
|
| 511 |
+
"rewards/margins": 0.34910523891448975,
|
| 512 |
+
"rewards/rejected": -0.8967201113700867,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.29,
|
| 517 |
+
"learning_rate": 4.4807241083879774e-06,
|
| 518 |
+
"logits/chosen": -0.12416689097881317,
|
| 519 |
+
"logits/rejected": -0.1058887392282486,
|
| 520 |
+
"logps/chosen": -879.2247924804688,
|
| 521 |
+
"logps/rejected": -1108.842529296875,
|
| 522 |
+
"loss": 1.6448,
|
| 523 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 524 |
+
"rewards/chosen": -0.4638194441795349,
|
| 525 |
+
"rewards/margins": 0.2646525502204895,
|
| 526 |
+
"rewards/rejected": -0.7284719944000244,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3,
|
| 531 |
+
"learning_rate": 4.437361221760449e-06,
|
| 532 |
+
"logits/chosen": -0.15833915770053864,
|
| 533 |
+
"logits/rejected": -0.10952518880367279,
|
| 534 |
+
"logps/chosen": -856.3928833007812,
|
| 535 |
+
"logps/rejected": -1185.8890380859375,
|
| 536 |
+
"loss": 1.6059,
|
| 537 |
+
"rewards/accuracies": 0.706250011920929,
|
| 538 |
+
"rewards/chosen": -0.47408080101013184,
|
| 539 |
+
"rewards/margins": 0.3529198169708252,
|
| 540 |
+
"rewards/rejected": -0.827000617980957,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3,
|
| 545 |
+
"learning_rate": 4.3924876391293915e-06,
|
| 546 |
+
"logits/chosen": -0.1157221645116806,
|
| 547 |
+
"logits/rejected": -0.11532659828662872,
|
| 548 |
+
"logps/chosen": -977.6126708984375,
|
| 549 |
+
"logps/rejected": -1276.198486328125,
|
| 550 |
+
"loss": 1.6257,
|
| 551 |
+
"rewards/accuracies": 0.675000011920929,
|
| 552 |
+
"rewards/chosen": -0.558844804763794,
|
| 553 |
+
"rewards/margins": 0.3456457555294037,
|
| 554 |
+
"rewards/rejected": -0.9044904708862305,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.31,
|
| 559 |
+
"learning_rate": 4.346138351564711e-06,
|
| 560 |
+
"logits/chosen": -0.08272431790828705,
|
| 561 |
+
"logits/rejected": -0.06370075047016144,
|
| 562 |
+
"logps/chosen": -987.0380859375,
|
| 563 |
+
"logps/rejected": -1292.915771484375,
|
| 564 |
+
"loss": 1.704,
|
| 565 |
+
"rewards/accuracies": 0.675000011920929,
|
| 566 |
+
"rewards/chosen": -0.5780712366104126,
|
| 567 |
+
"rewards/margins": 0.3437100052833557,
|
| 568 |
+
"rewards/rejected": -0.9217812418937683,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.32,
|
| 573 |
+
"learning_rate": 4.2983495008466285e-06,
|
| 574 |
+
"logits/chosen": -0.12420694530010223,
|
| 575 |
+
"logits/rejected": -0.08448062092065811,
|
| 576 |
+
"logps/chosen": -891.9703369140625,
|
| 577 |
+
"logps/rejected": -1206.5775146484375,
|
| 578 |
+
"loss": 1.6398,
|
| 579 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 580 |
+
"rewards/chosen": -0.49519339203834534,
|
| 581 |
+
"rewards/margins": 0.30879420042037964,
|
| 582 |
+
"rewards/rejected": -0.8039876222610474,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.33,
|
| 587 |
+
"learning_rate": 4.249158351283414e-06,
|
| 588 |
+
"logits/chosen": -0.05765647441148758,
|
| 589 |
+
"logits/rejected": -0.07125648856163025,
|
| 590 |
+
"logps/chosen": -906.8709106445312,
|
| 591 |
+
"logps/rejected": -1206.505126953125,
|
| 592 |
+
"loss": 1.6809,
|
| 593 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 594 |
+
"rewards/chosen": -0.5138260126113892,
|
| 595 |
+
"rewards/margins": 0.2949921488761902,
|
| 596 |
+
"rewards/rejected": -0.8088181614875793,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34,
|
| 601 |
+
"learning_rate": 4.198603260653792e-06,
|
| 602 |
+
"logits/chosen": -0.05834274739027023,
|
| 603 |
+
"logits/rejected": -0.06940310448408127,
|
| 604 |
+
"logps/chosen": -890.9304809570312,
|
| 605 |
+
"logps/rejected": -1269.909423828125,
|
| 606 |
+
"loss": 1.6515,
|
| 607 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 608 |
+
"rewards/chosen": -0.48780736327171326,
|
| 609 |
+
"rewards/margins": 0.38115113973617554,
|
| 610 |
+
"rewards/rejected": -0.8689583539962769,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.34,
|
| 615 |
+
"learning_rate": 4.146723650296701e-06,
|
| 616 |
+
"logits/chosen": -0.05108857899904251,
|
| 617 |
+
"logits/rejected": -0.03374727442860603,
|
| 618 |
+
"logps/chosen": -964.2681884765625,
|
| 619 |
+
"logps/rejected": -1255.4764404296875,
|
| 620 |
+
"loss": 1.5672,
|
| 621 |
+
"rewards/accuracies": 0.6875,
|
| 622 |
+
"rewards/chosen": -0.5296367406845093,
|
| 623 |
+
"rewards/margins": 0.31283584237098694,
|
| 624 |
+
"rewards/rejected": -0.8424724340438843,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.35,
|
| 629 |
+
"learning_rate": 4.093559974371725e-06,
|
| 630 |
+
"logits/chosen": 0.002035899553447962,
|
| 631 |
+
"logits/rejected": -0.05042330548167229,
|
| 632 |
+
"logps/chosen": -1061.304443359375,
|
| 633 |
+
"logps/rejected": -1401.3017578125,
|
| 634 |
+
"loss": 1.7551,
|
| 635 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 636 |
+
"rewards/chosen": -0.6395093202590942,
|
| 637 |
+
"rewards/margins": 0.3655704855918884,
|
| 638 |
+
"rewards/rejected": -1.005079746246338,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.36,
|
| 643 |
+
"learning_rate": 4.039153688314146e-06,
|
| 644 |
+
"logits/chosen": -0.039297740906476974,
|
| 645 |
+
"logits/rejected": -0.07409851998090744,
|
| 646 |
+
"logps/chosen": -919.8971557617188,
|
| 647 |
+
"logps/rejected": -1238.085693359375,
|
| 648 |
+
"loss": 1.7409,
|
| 649 |
+
"rewards/accuracies": 0.65625,
|
| 650 |
+
"rewards/chosen": -0.54268878698349,
|
| 651 |
+
"rewards/margins": 0.30365562438964844,
|
| 652 |
+
"rewards/rejected": -0.8463443517684937,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.37,
|
| 657 |
+
"learning_rate": 3.983547216509254e-06,
|
| 658 |
+
"logits/chosen": -0.05830153077840805,
|
| 659 |
+
"logits/rejected": -0.010070801712572575,
|
| 660 |
+
"logps/chosen": -911.67529296875,
|
| 661 |
+
"logps/rejected": -1207.1807861328125,
|
| 662 |
+
"loss": 1.5601,
|
| 663 |
+
"rewards/accuracies": 0.71875,
|
| 664 |
+
"rewards/chosen": -0.4990604519844055,
|
| 665 |
+
"rewards/margins": 0.32518327236175537,
|
| 666 |
+
"rewards/rejected": -0.8242437243461609,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38,
|
| 671 |
+
"learning_rate": 3.92678391921108e-06,
|
| 672 |
+
"logits/chosen": -0.03084222413599491,
|
| 673 |
+
"logits/rejected": -0.033790141344070435,
|
| 674 |
+
"logps/chosen": -880.0311279296875,
|
| 675 |
+
"logps/rejected": -1202.804443359375,
|
| 676 |
+
"loss": 1.5018,
|
| 677 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 678 |
+
"rewards/chosen": -0.4940199851989746,
|
| 679 |
+
"rewards/margins": 0.34093010425567627,
|
| 680 |
+
"rewards/rejected": -0.8349500894546509,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.38,
|
| 685 |
+
"learning_rate": 3.868908058731376e-06,
|
| 686 |
+
"logits/chosen": -0.04235939309000969,
|
| 687 |
+
"logits/rejected": -0.03030604124069214,
|
| 688 |
+
"logps/chosen": -948.1820068359375,
|
| 689 |
+
"logps/rejected": -1385.6903076171875,
|
| 690 |
+
"loss": 1.5846,
|
| 691 |
+
"rewards/accuracies": 0.731249988079071,
|
| 692 |
+
"rewards/chosen": -0.5281907916069031,
|
| 693 |
+
"rewards/margins": 0.44982367753982544,
|
| 694 |
+
"rewards/rejected": -0.9780144691467285,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.39,
|
| 699 |
+
"learning_rate": 3.8099647649251984e-06,
|
| 700 |
+
"logits/chosen": -0.016060033813118935,
|
| 701 |
+
"logits/rejected": 0.0315425805747509,
|
| 702 |
+
"logps/chosen": -872.0232543945312,
|
| 703 |
+
"logps/rejected": -1230.6595458984375,
|
| 704 |
+
"loss": 1.5608,
|
| 705 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 706 |
+
"rewards/chosen": -0.49027585983276367,
|
| 707 |
+
"rewards/margins": 0.3540174663066864,
|
| 708 |
+
"rewards/rejected": -0.8442932963371277,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4,
|
| 713 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 714 |
+
"logits/chosen": 0.008252490311861038,
|
| 715 |
+
"logits/rejected": -0.006942494306713343,
|
| 716 |
+
"logps/chosen": -965.0009765625,
|
| 717 |
+
"logps/rejected": -1298.984375,
|
| 718 |
+
"loss": 1.5949,
|
| 719 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 720 |
+
"rewards/chosen": -0.5271399617195129,
|
| 721 |
+
"rewards/margins": 0.34466665983200073,
|
| 722 |
+
"rewards/rejected": -0.8718066215515137,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.41,
|
| 727 |
+
"learning_rate": 3.689060522675689e-06,
|
| 728 |
+
"logits/chosen": 0.05910163372755051,
|
| 729 |
+
"logits/rejected": 0.038642317056655884,
|
| 730 |
+
"logps/chosen": -1022.37109375,
|
| 731 |
+
"logps/rejected": -1327.8564453125,
|
| 732 |
+
"loss": 1.71,
|
| 733 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 734 |
+
"rewards/chosen": -0.5376920700073242,
|
| 735 |
+
"rewards/margins": 0.3471304476261139,
|
| 736 |
+
"rewards/rejected": -0.8848224878311157,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.42,
|
| 741 |
+
"learning_rate": 3.627193851723577e-06,
|
| 742 |
+
"logits/chosen": 0.04024091362953186,
|
| 743 |
+
"logits/rejected": 0.05306211858987808,
|
| 744 |
+
"logps/chosen": -803.6287231445312,
|
| 745 |
+
"logps/rejected": -1148.608154296875,
|
| 746 |
+
"loss": 1.6553,
|
| 747 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 748 |
+
"rewards/chosen": -0.42975902557373047,
|
| 749 |
+
"rewards/margins": 0.3103187680244446,
|
| 750 |
+
"rewards/rejected": -0.7400776743888855,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.42,
|
| 755 |
+
"learning_rate": 3.564448228912682e-06,
|
| 756 |
+
"logits/chosen": 0.0793144553899765,
|
| 757 |
+
"logits/rejected": 0.07511784881353378,
|
| 758 |
+
"logps/chosen": -946.8004760742188,
|
| 759 |
+
"logps/rejected": -1296.5035400390625,
|
| 760 |
+
"loss": 1.6789,
|
| 761 |
+
"rewards/accuracies": 0.699999988079071,
|
| 762 |
+
"rewards/chosen": -0.511221706867218,
|
| 763 |
+
"rewards/margins": 0.3727003335952759,
|
| 764 |
+
"rewards/rejected": -0.8839219808578491,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.43,
|
| 769 |
+
"learning_rate": 3.5008725813922383e-06,
|
| 770 |
+
"logits/chosen": 0.04899642989039421,
|
| 771 |
+
"logits/rejected": 0.07576090097427368,
|
| 772 |
+
"logps/chosen": -968.6793823242188,
|
| 773 |
+
"logps/rejected": -1360.913330078125,
|
| 774 |
+
"loss": 1.5873,
|
| 775 |
+
"rewards/accuracies": 0.762499988079071,
|
| 776 |
+
"rewards/chosen": -0.5624467134475708,
|
| 777 |
+
"rewards/margins": 0.3971159756183624,
|
| 778 |
+
"rewards/rejected": -0.9595626592636108,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.44,
|
| 783 |
+
"learning_rate": 3.436516483539781e-06,
|
| 784 |
+
"logits/chosen": 0.07961883395910263,
|
| 785 |
+
"logits/rejected": 0.07691974937915802,
|
| 786 |
+
"logps/chosen": -1067.054931640625,
|
| 787 |
+
"logps/rejected": -1277.112548828125,
|
| 788 |
+
"loss": 1.7135,
|
| 789 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 790 |
+
"rewards/chosen": -0.5898305773735046,
|
| 791 |
+
"rewards/margins": 0.2757055163383484,
|
| 792 |
+
"rewards/rejected": -0.8655362129211426,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.45,
|
| 797 |
+
"learning_rate": 3.3714301183045382e-06,
|
| 798 |
+
"logits/chosen": 0.05680055543780327,
|
| 799 |
+
"logits/rejected": 0.030003631487488747,
|
| 800 |
+
"logps/chosen": -970.2757568359375,
|
| 801 |
+
"logps/rejected": -1333.9105224609375,
|
| 802 |
+
"loss": 1.6507,
|
| 803 |
+
"rewards/accuracies": 0.6875,
|
| 804 |
+
"rewards/chosen": -0.5233026742935181,
|
| 805 |
+
"rewards/margins": 0.37386059761047363,
|
| 806 |
+
"rewards/rejected": -0.8971632719039917,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.46,
|
| 811 |
+
"learning_rate": 3.3056642380762783e-06,
|
| 812 |
+
"logits/chosen": 0.03873239830136299,
|
| 813 |
+
"logits/rejected": 0.08405943214893341,
|
| 814 |
+
"logps/chosen": -984.0048828125,
|
| 815 |
+
"logps/rejected": -1360.584228515625,
|
| 816 |
+
"loss": 1.6165,
|
| 817 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 818 |
+
"rewards/chosen": -0.5443267226219177,
|
| 819 |
+
"rewards/margins": 0.3884132504463196,
|
| 820 |
+
"rewards/rejected": -0.9327400922775269,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.46,
|
| 825 |
+
"learning_rate": 3.2392701251101172e-06,
|
| 826 |
+
"logits/chosen": 0.037966854870319366,
|
| 827 |
+
"logits/rejected": 0.02861429750919342,
|
| 828 |
+
"logps/chosen": -917.8508911132812,
|
| 829 |
+
"logps/rejected": -1293.6751708984375,
|
| 830 |
+
"loss": 1.5682,
|
| 831 |
+
"rewards/accuracies": 0.706250011920929,
|
| 832 |
+
"rewards/chosen": -0.5233009457588196,
|
| 833 |
+
"rewards/margins": 0.3688820004463196,
|
| 834 |
+
"rewards/rejected": -0.8921829462051392,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.47,
|
| 839 |
+
"learning_rate": 3.1722995515381644e-06,
|
| 840 |
+
"logits/chosen": 0.047953229397535324,
|
| 841 |
+
"logits/rejected": 0.08454461395740509,
|
| 842 |
+
"logps/chosen": -1099.385009765625,
|
| 843 |
+
"logps/rejected": -1388.120849609375,
|
| 844 |
+
"loss": 1.6362,
|
| 845 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 846 |
+
"rewards/chosen": -0.6879197955131531,
|
| 847 |
+
"rewards/margins": 0.29069215059280396,
|
| 848 |
+
"rewards/rejected": -0.978611946105957,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.48,
|
| 853 |
+
"learning_rate": 3.1048047389991693e-06,
|
| 854 |
+
"logits/chosen": 0.091717928647995,
|
| 855 |
+
"logits/rejected": 0.09912924468517303,
|
| 856 |
+
"logps/chosen": -909.0963745117188,
|
| 857 |
+
"logps/rejected": -1410.45751953125,
|
| 858 |
+
"loss": 1.5942,
|
| 859 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 860 |
+
"rewards/chosen": -0.4968685209751129,
|
| 861 |
+
"rewards/margins": 0.4905162453651428,
|
| 862 |
+
"rewards/rejected": -0.9873846769332886,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.49,
|
| 867 |
+
"learning_rate": 3.0368383179176584e-06,
|
| 868 |
+
"logits/chosen": 0.07560348510742188,
|
| 869 |
+
"logits/rejected": 0.06965458393096924,
|
| 870 |
+
"logps/chosen": -914.50634765625,
|
| 871 |
+
"logps/rejected": -1271.376220703125,
|
| 872 |
+
"loss": 1.6215,
|
| 873 |
+
"rewards/accuracies": 0.675000011920929,
|
| 874 |
+
"rewards/chosen": -0.5211359262466431,
|
| 875 |
+
"rewards/margins": 0.3135939836502075,
|
| 876 |
+
"rewards/rejected": -0.8347299695014954,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5,
|
| 881 |
+
"learning_rate": 2.9684532864643123e-06,
|
| 882 |
+
"logits/chosen": 0.11191339790821075,
|
| 883 |
+
"logits/rejected": 0.12147488445043564,
|
| 884 |
+
"logps/chosen": -939.2978515625,
|
| 885 |
+
"logps/rejected": -1317.5257568359375,
|
| 886 |
+
"loss": 1.71,
|
| 887 |
+
"rewards/accuracies": 0.71875,
|
| 888 |
+
"rewards/chosen": -0.5019097328186035,
|
| 889 |
+
"rewards/margins": 0.36823293566703796,
|
| 890 |
+
"rewards/rejected": -0.8701427578926086,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5,
|
| 895 |
+
"learning_rate": 2.8997029692295875e-06,
|
| 896 |
+
"logits/chosen": 0.08082602918148041,
|
| 897 |
+
"logits/rejected": 0.11734504997730255,
|
| 898 |
+
"logps/chosen": -875.3718872070312,
|
| 899 |
+
"logps/rejected": -1250.5029296875,
|
| 900 |
+
"loss": 1.5481,
|
| 901 |
+
"rewards/accuracies": 0.737500011920929,
|
| 902 |
+
"rewards/chosen": -0.4535561203956604,
|
| 903 |
+
"rewards/margins": 0.38246890902519226,
|
| 904 |
+
"rewards/rejected": -0.8360249400138855,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.51,
|
| 909 |
+
"learning_rate": 2.8306409756428067e-06,
|
| 910 |
+
"logits/chosen": 0.08714647591114044,
|
| 911 |
+
"logits/rejected": 0.09734050184488297,
|
| 912 |
+
"logps/chosen": -969.7335815429688,
|
| 913 |
+
"logps/rejected": -1301.7027587890625,
|
| 914 |
+
"loss": 1.5968,
|
| 915 |
+
"rewards/accuracies": 0.668749988079071,
|
| 916 |
+
"rewards/chosen": -0.5595206022262573,
|
| 917 |
+
"rewards/margins": 0.35599860548973083,
|
| 918 |
+
"rewards/rejected": -0.9155190587043762,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.52,
|
| 923 |
+
"learning_rate": 2.761321158169134e-06,
|
| 924 |
+
"logits/chosen": 0.006733921356499195,
|
| 925 |
+
"logits/rejected": 0.03773912042379379,
|
| 926 |
+
"logps/chosen": -1084.8623046875,
|
| 927 |
+
"logps/rejected": -1479.010498046875,
|
| 928 |
+
"loss": 1.5928,
|
| 929 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 930 |
+
"rewards/chosen": -0.6584538221359253,
|
| 931 |
+
"rewards/margins": 0.4003337025642395,
|
| 932 |
+
"rewards/rejected": -1.0587873458862305,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.53,
|
| 937 |
+
"learning_rate": 2.6917975703170466e-06,
|
| 938 |
+
"logits/chosen": 0.10130703449249268,
|
| 939 |
+
"logits/rejected": 0.09567786753177643,
|
| 940 |
+
"logps/chosen": -978.0599365234375,
|
| 941 |
+
"logps/rejected": -1393.5048828125,
|
| 942 |
+
"loss": 1.5646,
|
| 943 |
+
"rewards/accuracies": 0.731249988079071,
|
| 944 |
+
"rewards/chosen": -0.5595641136169434,
|
| 945 |
+
"rewards/margins": 0.4086734652519226,
|
| 946 |
+
"rewards/rejected": -0.9682376980781555,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.54,
|
| 951 |
+
"learning_rate": 2.6221244244890336e-06,
|
| 952 |
+
"logits/chosen": 0.10669932514429092,
|
| 953 |
+
"logits/rejected": 0.08464895188808441,
|
| 954 |
+
"logps/chosen": -792.4083251953125,
|
| 955 |
+
"logps/rejected": -1029.5029296875,
|
| 956 |
+
"loss": 1.63,
|
| 957 |
+
"rewards/accuracies": 0.65625,
|
| 958 |
+
"rewards/chosen": -0.4270346760749817,
|
| 959 |
+
"rewards/margins": 0.26256269216537476,
|
| 960 |
+
"rewards/rejected": -0.6895973682403564,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.54,
|
| 965 |
+
"learning_rate": 2.5523560497083927e-06,
|
| 966 |
+
"logits/chosen": 0.11974094063043594,
|
| 967 |
+
"logits/rejected": 0.13801291584968567,
|
| 968 |
+
"logps/chosen": -934.68310546875,
|
| 969 |
+
"logps/rejected": -1160.298828125,
|
| 970 |
+
"loss": 1.6015,
|
| 971 |
+
"rewards/accuracies": 0.71875,
|
| 972 |
+
"rewards/chosen": -0.4680783152580261,
|
| 973 |
+
"rewards/margins": 0.2951990067958832,
|
| 974 |
+
"rewards/rejected": -0.7632774114608765,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.55,
|
| 979 |
+
"learning_rate": 2.482546849255096e-06,
|
| 980 |
+
"logits/chosen": 0.11049097776412964,
|
| 981 |
+
"logits/rejected": 0.18580587208271027,
|
| 982 |
+
"logps/chosen": -908.0875244140625,
|
| 983 |
+
"logps/rejected": -1278.4056396484375,
|
| 984 |
+
"loss": 1.5788,
|
| 985 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 986 |
+
"rewards/chosen": -0.46382030844688416,
|
| 987 |
+
"rewards/margins": 0.3706962466239929,
|
| 988 |
+
"rewards/rejected": -0.8345165252685547,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.56,
|
| 993 |
+
"learning_rate": 2.4127512582437486e-06,
|
| 994 |
+
"logits/chosen": 0.1090225949883461,
|
| 995 |
+
"logits/rejected": 0.11428926140069962,
|
| 996 |
+
"logps/chosen": -887.1666259765625,
|
| 997 |
+
"logps/rejected": -1290.92236328125,
|
| 998 |
+
"loss": 1.6283,
|
| 999 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1000 |
+
"rewards/chosen": -0.47191792726516724,
|
| 1001 |
+
"rewards/margins": 0.4161871075630188,
|
| 1002 |
+
"rewards/rejected": -0.8881050944328308,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.57,
|
| 1007 |
+
"learning_rate": 2.3430237011767166e-06,
|
| 1008 |
+
"logits/chosen": 0.08914731442928314,
|
| 1009 |
+
"logits/rejected": 0.09316228330135345,
|
| 1010 |
+
"logps/chosen": -951.3321533203125,
|
| 1011 |
+
"logps/rejected": -1253.3704833984375,
|
| 1012 |
+
"loss": 1.5467,
|
| 1013 |
+
"rewards/accuracies": 0.71875,
|
| 1014 |
+
"rewards/chosen": -0.5280056595802307,
|
| 1015 |
+
"rewards/margins": 0.3312267065048218,
|
| 1016 |
+
"rewards/rejected": -0.8592323064804077,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.58,
|
| 1021 |
+
"learning_rate": 2.2734185495055503e-06,
|
| 1022 |
+
"logits/chosen": 0.10006880760192871,
|
| 1023 |
+
"logits/rejected": 0.10086695849895477,
|
| 1024 |
+
"logps/chosen": -909.28271484375,
|
| 1025 |
+
"logps/rejected": -1240.0157470703125,
|
| 1026 |
+
"loss": 1.532,
|
| 1027 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1028 |
+
"rewards/chosen": -0.4997311234474182,
|
| 1029 |
+
"rewards/margins": 0.3538741171360016,
|
| 1030 |
+
"rewards/rejected": -0.8536051511764526,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.58,
|
| 1035 |
+
"learning_rate": 2.2039900792337477e-06,
|
| 1036 |
+
"logits/chosen": 0.08773048967123032,
|
| 1037 |
+
"logits/rejected": 0.10859861224889755,
|
| 1038 |
+
"logps/chosen": -968.7990112304688,
|
| 1039 |
+
"logps/rejected": -1337.583740234375,
|
| 1040 |
+
"loss": 1.6446,
|
| 1041 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1042 |
+
"rewards/chosen": -0.5440322160720825,
|
| 1043 |
+
"rewards/margins": 0.3773999512195587,
|
| 1044 |
+
"rewards/rejected": -0.9214321374893188,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.59,
|
| 1049 |
+
"learning_rate": 2.134792428593971e-06,
|
| 1050 |
+
"logits/chosen": 0.10109611600637436,
|
| 1051 |
+
"logits/rejected": 0.1010131984949112,
|
| 1052 |
+
"logps/chosen": -934.5894775390625,
|
| 1053 |
+
"logps/rejected": -1251.2464599609375,
|
| 1054 |
+
"loss": 1.647,
|
| 1055 |
+
"rewards/accuracies": 0.78125,
|
| 1056 |
+
"rewards/chosen": -0.5000175833702087,
|
| 1057 |
+
"rewards/margins": 0.3368659019470215,
|
| 1058 |
+
"rewards/rejected": -0.836883544921875,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6,
|
| 1063 |
+
"learning_rate": 2.0658795558326745e-06,
|
| 1064 |
+
"logits/chosen": 0.07538788765668869,
|
| 1065 |
+
"logits/rejected": 0.03233175352215767,
|
| 1066 |
+
"logps/chosen": -919.93994140625,
|
| 1067 |
+
"logps/rejected": -1380.2998046875,
|
| 1068 |
+
"loss": 1.5396,
|
| 1069 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1070 |
+
"rewards/chosen": -0.5493655800819397,
|
| 1071 |
+
"rewards/margins": 0.42367228865623474,
|
| 1072 |
+
"rewards/rejected": -0.9730378985404968,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.61,
|
| 1077 |
+
"learning_rate": 1.997305197135089e-06,
|
| 1078 |
+
"logits/chosen": 0.016186673194169998,
|
| 1079 |
+
"logits/rejected": 0.035506926476955414,
|
| 1080 |
+
"logps/chosen": -1090.354736328125,
|
| 1081 |
+
"logps/rejected": -1475.09912109375,
|
| 1082 |
+
"loss": 1.5146,
|
| 1083 |
+
"rewards/accuracies": 0.75,
|
| 1084 |
+
"rewards/chosen": -0.6771215200424194,
|
| 1085 |
+
"rewards/margins": 0.3887900412082672,
|
| 1086 |
+
"rewards/rejected": -1.0659115314483643,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.62,
|
| 1091 |
+
"learning_rate": 1.9291228247233607e-06,
|
| 1092 |
+
"logits/chosen": 0.0642293244600296,
|
| 1093 |
+
"logits/rejected": 0.07756002992391586,
|
| 1094 |
+
"logps/chosen": -1072.716064453125,
|
| 1095 |
+
"logps/rejected": -1393.173583984375,
|
| 1096 |
+
"loss": 1.6319,
|
| 1097 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1098 |
+
"rewards/chosen": -0.648370623588562,
|
| 1099 |
+
"rewards/margins": 0.35922181606292725,
|
| 1100 |
+
"rewards/rejected": -1.0075924396514893,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.62,
|
| 1105 |
+
"learning_rate": 1.8613856051605242e-06,
|
| 1106 |
+
"logits/chosen": 0.09995916485786438,
|
| 1107 |
+
"logits/rejected": 0.059368181973695755,
|
| 1108 |
+
"logps/chosen": -991.5946044921875,
|
| 1109 |
+
"logps/rejected": -1411.4442138671875,
|
| 1110 |
+
"loss": 1.4733,
|
| 1111 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1112 |
+
"rewards/chosen": -0.5653289556503296,
|
| 1113 |
+
"rewards/margins": 0.4559949040412903,
|
| 1114 |
+
"rewards/rejected": -1.0213239192962646,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.63,
|
| 1119 |
+
"learning_rate": 1.7941463578928088e-06,
|
| 1120 |
+
"logits/chosen": 0.07716236263513565,
|
| 1121 |
+
"logits/rejected": 0.08072565495967865,
|
| 1122 |
+
"logps/chosen": -1078.119384765625,
|
| 1123 |
+
"logps/rejected": -1377.1890869140625,
|
| 1124 |
+
"loss": 1.5073,
|
| 1125 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1126 |
+
"rewards/chosen": -0.629800021648407,
|
| 1127 |
+
"rewards/margins": 0.32973819971084595,
|
| 1128 |
+
"rewards/rejected": -0.9595381617546082,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.64,
|
| 1133 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 1134 |
+
"logits/chosen": 0.08353432267904282,
|
| 1135 |
+
"logits/rejected": 0.11776747554540634,
|
| 1136 |
+
"logps/chosen": -1066.1820068359375,
|
| 1137 |
+
"logps/rejected": -1459.1993408203125,
|
| 1138 |
+
"loss": 1.472,
|
| 1139 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1140 |
+
"rewards/chosen": -0.587757408618927,
|
| 1141 |
+
"rewards/margins": 0.4555942416191101,
|
| 1142 |
+
"rewards/rejected": -1.0433517694473267,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.65,
|
| 1147 |
+
"learning_rate": 1.661371075624363e-06,
|
| 1148 |
+
"logits/chosen": 0.07389640808105469,
|
| 1149 |
+
"logits/rejected": 0.02921133115887642,
|
| 1150 |
+
"logps/chosen": -1045.249755859375,
|
| 1151 |
+
"logps/rejected": -1426.687744140625,
|
| 1152 |
+
"loss": 1.5891,
|
| 1153 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1154 |
+
"rewards/chosen": -0.6339725255966187,
|
| 1155 |
+
"rewards/margins": 0.38414081931114197,
|
| 1156 |
+
"rewards/rejected": -1.018113374710083,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.66,
|
| 1161 |
+
"learning_rate": 1.5959385747947697e-06,
|
| 1162 |
+
"logits/chosen": 0.08418832719326019,
|
| 1163 |
+
"logits/rejected": 0.059553779661655426,
|
| 1164 |
+
"logps/chosen": -903.3878173828125,
|
| 1165 |
+
"logps/rejected": -1283.9080810546875,
|
| 1166 |
+
"loss": 1.4831,
|
| 1167 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1168 |
+
"rewards/chosen": -0.5188735127449036,
|
| 1169 |
+
"rewards/margins": 0.38101640343666077,
|
| 1170 |
+
"rewards/rejected": -0.8998898267745972,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.66,
|
| 1175 |
+
"learning_rate": 1.5312110338697427e-06,
|
| 1176 |
+
"logits/chosen": 0.07461550831794739,
|
| 1177 |
+
"logits/rejected": 0.09411834180355072,
|
| 1178 |
+
"logps/chosen": -978.8884887695312,
|
| 1179 |
+
"logps/rejected": -1332.2344970703125,
|
| 1180 |
+
"loss": 1.6651,
|
| 1181 |
+
"rewards/accuracies": 0.65625,
|
| 1182 |
+
"rewards/chosen": -0.5540666580200195,
|
| 1183 |
+
"rewards/margins": 0.3479211926460266,
|
| 1184 |
+
"rewards/rejected": -0.9019878506660461,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.67,
|
| 1189 |
+
"learning_rate": 1.467238925438646e-06,
|
| 1190 |
+
"logits/chosen": 0.126978799700737,
|
| 1191 |
+
"logits/rejected": 0.15114851295948029,
|
| 1192 |
+
"logps/chosen": -988.6935424804688,
|
| 1193 |
+
"logps/rejected": -1252.6251220703125,
|
| 1194 |
+
"loss": 1.4992,
|
| 1195 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1196 |
+
"rewards/chosen": -0.5259130597114563,
|
| 1197 |
+
"rewards/margins": 0.3344604969024658,
|
| 1198 |
+
"rewards/rejected": -0.8603734970092773,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.68,
|
| 1203 |
+
"learning_rate": 1.4040721330273063e-06,
|
| 1204 |
+
"logits/chosen": 0.13616199791431427,
|
| 1205 |
+
"logits/rejected": 0.10154382139444351,
|
| 1206 |
+
"logps/chosen": -930.3357543945312,
|
| 1207 |
+
"logps/rejected": -1316.8492431640625,
|
| 1208 |
+
"loss": 1.5081,
|
| 1209 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1210 |
+
"rewards/chosen": -0.538154125213623,
|
| 1211 |
+
"rewards/margins": 0.3978419005870819,
|
| 1212 |
+
"rewards/rejected": -0.9359959363937378,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.69,
|
| 1217 |
+
"learning_rate": 1.3417599122003464e-06,
|
| 1218 |
+
"logits/chosen": 0.10873869806528091,
|
| 1219 |
+
"logits/rejected": 0.08275686204433441,
|
| 1220 |
+
"logps/chosen": -944.9284057617188,
|
| 1221 |
+
"logps/rejected": -1242.4952392578125,
|
| 1222 |
+
"loss": 1.4874,
|
| 1223 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1224 |
+
"rewards/chosen": -0.5550948977470398,
|
| 1225 |
+
"rewards/margins": 0.30027762055397034,
|
| 1226 |
+
"rewards/rejected": -0.8553726077079773,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7,
|
| 1231 |
+
"learning_rate": 1.280350852153168e-06,
|
| 1232 |
+
"logits/chosen": 0.13027873635292053,
|
| 1233 |
+
"logits/rejected": 0.12578675150871277,
|
| 1234 |
+
"logps/chosen": -937.29345703125,
|
| 1235 |
+
"logps/rejected": -1311.0787353515625,
|
| 1236 |
+
"loss": 1.5071,
|
| 1237 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1238 |
+
"rewards/chosen": -0.5160200595855713,
|
| 1239 |
+
"rewards/margins": 0.4040035307407379,
|
| 1240 |
+
"rewards/rejected": -0.9200236201286316,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7,
|
| 1245 |
+
"learning_rate": 1.2198928378235717e-06,
|
| 1246 |
+
"logits/chosen": 0.08686872571706772,
|
| 1247 |
+
"logits/rejected": 0.118919238448143,
|
| 1248 |
+
"logps/chosen": -991.64208984375,
|
| 1249 |
+
"logps/rejected": -1404.045166015625,
|
| 1250 |
+
"loss": 1.4595,
|
| 1251 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1252 |
+
"rewards/chosen": -0.5468842387199402,
|
| 1253 |
+
"rewards/margins": 0.4538387656211853,
|
| 1254 |
+
"rewards/rejected": -1.0007230043411255,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.71,
|
| 1259 |
+
"learning_rate": 1.160433012552508e-06,
|
| 1260 |
+
"logits/chosen": 0.054034192115068436,
|
| 1261 |
+
"logits/rejected": 0.07009950280189514,
|
| 1262 |
+
"logps/chosen": -1012.7716674804688,
|
| 1263 |
+
"logps/rejected": -1450.068359375,
|
| 1264 |
+
"loss": 1.5362,
|
| 1265 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1266 |
+
"rewards/chosen": -0.5747925043106079,
|
| 1267 |
+
"rewards/margins": 0.4582456648349762,
|
| 1268 |
+
"rewards/rejected": -1.0330379009246826,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.72,
|
| 1273 |
+
"learning_rate": 1.1020177413231334e-06,
|
| 1274 |
+
"logits/chosen": 0.06726670265197754,
|
| 1275 |
+
"logits/rejected": 0.07763611525297165,
|
| 1276 |
+
"logps/chosen": -1003.4699096679688,
|
| 1277 |
+
"logps/rejected": -1429.7281494140625,
|
| 1278 |
+
"loss": 1.6021,
|
| 1279 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1280 |
+
"rewards/chosen": -0.5936052799224854,
|
| 1281 |
+
"rewards/margins": 0.4537973403930664,
|
| 1282 |
+
"rewards/rejected": -1.0474026203155518,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.73,
|
| 1287 |
+
"learning_rate": 1.0446925746067768e-06,
|
| 1288 |
+
"logits/chosen": 0.08046019077301025,
|
| 1289 |
+
"logits/rejected": 0.09484287351369858,
|
| 1290 |
+
"logps/chosen": -1176.3572998046875,
|
| 1291 |
+
"logps/rejected": -1445.795166015625,
|
| 1292 |
+
"loss": 1.6634,
|
| 1293 |
+
"rewards/accuracies": 0.6875,
|
| 1294 |
+
"rewards/chosen": -0.7165821194648743,
|
| 1295 |
+
"rewards/margins": 0.31557074189186096,
|
| 1296 |
+
"rewards/rejected": -1.0321528911590576,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.74,
|
| 1301 |
+
"learning_rate": 9.88502212844063e-07,
|
| 1302 |
+
"logits/chosen": 0.09446735680103302,
|
| 1303 |
+
"logits/rejected": 0.1036868467926979,
|
| 1304 |
+
"logps/chosen": -1062.044677734375,
|
| 1305 |
+
"logps/rejected": -1472.5697021484375,
|
| 1306 |
+
"loss": 1.6091,
|
| 1307 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1308 |
+
"rewards/chosen": -0.6323626637458801,
|
| 1309 |
+
"rewards/margins": 0.4094136357307434,
|
| 1310 |
+
"rewards/rejected": -1.041776180267334,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.74,
|
| 1315 |
+
"learning_rate": 9.334904715888496e-07,
|
| 1316 |
+
"logits/chosen": 0.07529421150684357,
|
| 1317 |
+
"logits/rejected": 0.08289067447185516,
|
| 1318 |
+
"logps/chosen": -970.4074096679688,
|
| 1319 |
+
"logps/rejected": -1391.994140625,
|
| 1320 |
+
"loss": 1.4436,
|
| 1321 |
+
"rewards/accuracies": 0.71875,
|
| 1322 |
+
"rewards/chosen": -0.546066403388977,
|
| 1323 |
+
"rewards/margins": 0.4431384205818176,
|
| 1324 |
+
"rewards/rejected": -0.9892047643661499,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.75,
|
| 1329 |
+
"learning_rate": 8.797002473421729e-07,
|
| 1330 |
+
"logits/chosen": 0.11385681480169296,
|
| 1331 |
+
"logits/rejected": 0.07344277948141098,
|
| 1332 |
+
"logps/chosen": -1011.7611083984375,
|
| 1333 |
+
"logps/rejected": -1272.4300537109375,
|
| 1334 |
+
"loss": 1.5694,
|
| 1335 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1336 |
+
"rewards/chosen": -0.5955858826637268,
|
| 1337 |
+
"rewards/margins": 0.2856913208961487,
|
| 1338 |
+
"rewards/rejected": -0.8812772035598755,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.76,
|
| 1343 |
+
"learning_rate": 8.271734841028553e-07,
|
| 1344 |
+
"logits/chosen": 0.14825263619422913,
|
| 1345 |
+
"logits/rejected": 0.12270005792379379,
|
| 1346 |
+
"logps/chosen": -1037.7218017578125,
|
| 1347 |
+
"logps/rejected": -1463.168212890625,
|
| 1348 |
+
"loss": 1.4799,
|
| 1349 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1350 |
+
"rewards/chosen": -0.5987383723258972,
|
| 1351 |
+
"rewards/margins": 0.4431166648864746,
|
| 1352 |
+
"rewards/rejected": -1.0418550968170166,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.77,
|
| 1357 |
+
"learning_rate": 7.759511406608255e-07,
|
| 1358 |
+
"logits/chosen": 0.1073087602853775,
|
| 1359 |
+
"logits/rejected": 0.09663400799036026,
|
| 1360 |
+
"logps/chosen": -948.8695068359375,
|
| 1361 |
+
"logps/rejected": -1318.7125244140625,
|
| 1362 |
+
"loss": 1.6156,
|
| 1363 |
+
"rewards/accuracies": 0.6875,
|
| 1364 |
+
"rewards/chosen": -0.5697445869445801,
|
| 1365 |
+
"rewards/margins": 0.38244208693504333,
|
| 1366 |
+
"rewards/rejected": -0.9521867036819458,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.78,
|
| 1371 |
+
"learning_rate": 7.260731586586983e-07,
|
| 1372 |
+
"logits/chosen": 0.13227181136608124,
|
| 1373 |
+
"logits/rejected": 0.1124822273850441,
|
| 1374 |
+
"logps/chosen": -1044.2213134765625,
|
| 1375 |
+
"logps/rejected": -1377.6756591796875,
|
| 1376 |
+
"loss": 1.486,
|
| 1377 |
+
"rewards/accuracies": 0.6875,
|
| 1378 |
+
"rewards/chosen": -0.6263742446899414,
|
| 1379 |
+
"rewards/margins": 0.3383250832557678,
|
| 1380 |
+
"rewards/rejected": -0.9646994471549988,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.78,
|
| 1385 |
+
"learning_rate": 6.775784314464717e-07,
|
| 1386 |
+
"logits/chosen": 0.15785950422286987,
|
| 1387 |
+
"logits/rejected": 0.13977470993995667,
|
| 1388 |
+
"logps/chosen": -1023.9119262695312,
|
| 1389 |
+
"logps/rejected": -1362.277587890625,
|
| 1390 |
+
"loss": 1.4655,
|
| 1391 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1392 |
+
"rewards/chosen": -0.579637885093689,
|
| 1393 |
+
"rewards/margins": 0.39033398032188416,
|
| 1394 |
+
"rewards/rejected": -0.9699718356132507,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.79,
|
| 1399 |
+
"learning_rate": 6.305047737536707e-07,
|
| 1400 |
+
"logits/chosen": 0.08758912980556488,
|
| 1401 |
+
"logits/rejected": 0.12277774512767792,
|
| 1402 |
+
"logps/chosen": -999.2574462890625,
|
| 1403 |
+
"logps/rejected": -1349.63720703125,
|
| 1404 |
+
"loss": 1.5246,
|
| 1405 |
+
"rewards/accuracies": 0.6875,
|
| 1406 |
+
"rewards/chosen": -0.5825763940811157,
|
| 1407 |
+
"rewards/margins": 0.368095338344574,
|
| 1408 |
+
"rewards/rejected": -0.9506716728210449,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8,
|
| 1413 |
+
"learning_rate": 5.848888922025553e-07,
|
| 1414 |
+
"logits/chosen": 0.11750923097133636,
|
| 1415 |
+
"logits/rejected": 0.12221167236566544,
|
| 1416 |
+
"logps/chosen": -1051.95654296875,
|
| 1417 |
+
"logps/rejected": -1356.2454833984375,
|
| 1418 |
+
"loss": 1.5642,
|
| 1419 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1420 |
+
"rewards/chosen": -0.6182184219360352,
|
| 1421 |
+
"rewards/margins": 0.3450503945350647,
|
| 1422 |
+
"rewards/rejected": -0.9632687568664551,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.81,
|
| 1427 |
+
"learning_rate": 5.407663566854008e-07,
|
| 1428 |
+
"logits/chosen": 0.06591792404651642,
|
| 1429 |
+
"logits/rejected": 0.09111978113651276,
|
| 1430 |
+
"logps/chosen": -1000.8797607421875,
|
| 1431 |
+
"logps/rejected": -1322.9415283203125,
|
| 1432 |
+
"loss": 1.5276,
|
| 1433 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1434 |
+
"rewards/chosen": -0.5938758254051208,
|
| 1435 |
+
"rewards/margins": 0.35901254415512085,
|
| 1436 |
+
"rewards/rejected": -0.9528884887695312,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.82,
|
| 1441 |
+
"learning_rate": 4.981715726281666e-07,
|
| 1442 |
+
"logits/chosen": 0.11376409232616425,
|
| 1443 |
+
"logits/rejected": 0.09700876474380493,
|
| 1444 |
+
"logps/chosen": -1020.0313720703125,
|
| 1445 |
+
"logps/rejected": -1457.311767578125,
|
| 1446 |
+
"loss": 1.3381,
|
| 1447 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1448 |
+
"rewards/chosen": -0.6390109062194824,
|
| 1449 |
+
"rewards/margins": 0.4118656516075134,
|
| 1450 |
+
"rewards/rejected": -1.0508766174316406,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.82,
|
| 1455 |
+
"learning_rate": 4.5713775416217884e-07,
|
| 1456 |
+
"logits/chosen": 0.10929641872644424,
|
| 1457 |
+
"logits/rejected": 0.10328598320484161,
|
| 1458 |
+
"logps/chosen": -1016.06591796875,
|
| 1459 |
+
"logps/rejected": -1392.699462890625,
|
| 1460 |
+
"loss": 1.5685,
|
| 1461 |
+
"rewards/accuracies": 0.71875,
|
| 1462 |
+
"rewards/chosen": -0.6151790022850037,
|
| 1463 |
+
"rewards/margins": 0.3843514025211334,
|
| 1464 |
+
"rewards/rejected": -0.9995304942131042,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.83,
|
| 1469 |
+
"learning_rate": 4.1769689822475147e-07,
|
| 1470 |
+
"logits/chosen": 0.12536247074604034,
|
| 1471 |
+
"logits/rejected": 0.10010683536529541,
|
| 1472 |
+
"logps/chosen": -1026.385986328125,
|
| 1473 |
+
"logps/rejected": -1466.6982421875,
|
| 1474 |
+
"loss": 1.5254,
|
| 1475 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1476 |
+
"rewards/chosen": -0.6345069408416748,
|
| 1477 |
+
"rewards/margins": 0.4376339018344879,
|
| 1478 |
+
"rewards/rejected": -1.0721409320831299,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.84,
|
| 1483 |
+
"learning_rate": 3.798797596089351e-07,
|
| 1484 |
+
"logits/chosen": 0.11945215612649918,
|
| 1485 |
+
"logits/rejected": 0.1324438452720642,
|
| 1486 |
+
"logps/chosen": -1003.3302612304688,
|
| 1487 |
+
"logps/rejected": -1490.3330078125,
|
| 1488 |
+
"loss": 1.4181,
|
| 1489 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1490 |
+
"rewards/chosen": -0.604376494884491,
|
| 1491 |
+
"rewards/margins": 0.43948906660079956,
|
| 1492 |
+
"rewards/rejected": -1.0438655614852905,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.85,
|
| 1497 |
+
"learning_rate": 3.4371582698185636e-07,
|
| 1498 |
+
"logits/chosen": 0.11982687562704086,
|
| 1499 |
+
"logits/rejected": 0.11596560478210449,
|
| 1500 |
+
"logps/chosen": -965.4796752929688,
|
| 1501 |
+
"logps/rejected": -1305.4368896484375,
|
| 1502 |
+
"loss": 1.4891,
|
| 1503 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1504 |
+
"rewards/chosen": -0.5759687423706055,
|
| 1505 |
+
"rewards/margins": 0.33464914560317993,
|
| 1506 |
+
"rewards/rejected": -0.9106179475784302,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.86,
|
| 1511 |
+
"learning_rate": 3.092332998903416e-07,
|
| 1512 |
+
"logits/chosen": 0.11303956806659698,
|
| 1513 |
+
"logits/rejected": 0.12296398729085922,
|
| 1514 |
+
"logps/chosen": -1185.8704833984375,
|
| 1515 |
+
"logps/rejected": -1574.617919921875,
|
| 1516 |
+
"loss": 1.4492,
|
| 1517 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1518 |
+
"rewards/chosen": -0.7027804255485535,
|
| 1519 |
+
"rewards/margins": 0.45428234338760376,
|
| 1520 |
+
"rewards/rejected": -1.1570627689361572,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.86,
|
| 1525 |
+
"learning_rate": 2.764590667717562e-07,
|
| 1526 |
+
"logits/chosen": 0.11120734363794327,
|
| 1527 |
+
"logits/rejected": 0.07134538888931274,
|
| 1528 |
+
"logps/chosen": -1128.311279296875,
|
| 1529 |
+
"logps/rejected": -1455.035888671875,
|
| 1530 |
+
"loss": 1.5757,
|
| 1531 |
+
"rewards/accuracies": 0.71875,
|
| 1532 |
+
"rewards/chosen": -0.6751740574836731,
|
| 1533 |
+
"rewards/margins": 0.3886902928352356,
|
| 1534 |
+
"rewards/rejected": -1.0638644695281982,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.87,
|
| 1539 |
+
"learning_rate": 2.454186839872158e-07,
|
| 1540 |
+
"logits/chosen": 0.13448989391326904,
|
| 1541 |
+
"logits/rejected": 0.13337567448616028,
|
| 1542 |
+
"logps/chosen": -1010.8844604492188,
|
| 1543 |
+
"logps/rejected": -1454.37841796875,
|
| 1544 |
+
"loss": 1.5715,
|
| 1545 |
+
"rewards/accuracies": 0.75,
|
| 1546 |
+
"rewards/chosen": -0.6244133710861206,
|
| 1547 |
+
"rewards/margins": 0.4344162344932556,
|
| 1548 |
+
"rewards/rejected": -1.058829665184021,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.88,
|
| 1553 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 1554 |
+
"logits/chosen": 0.13915595412254333,
|
| 1555 |
+
"logits/rejected": 0.1342434138059616,
|
| 1556 |
+
"logps/chosen": -1146.306396484375,
|
| 1557 |
+
"logps/rejected": -1514.5679931640625,
|
| 1558 |
+
"loss": 1.5751,
|
| 1559 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1560 |
+
"rewards/chosen": -0.6373551487922668,
|
| 1561 |
+
"rewards/margins": 0.4376014173030853,
|
| 1562 |
+
"rewards/rejected": -1.0749565362930298,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.89,
|
| 1567 |
+
"learning_rate": 1.8863491596921745e-07,
|
| 1568 |
+
"logits/chosen": 0.15741156041622162,
|
| 1569 |
+
"logits/rejected": 0.13911879062652588,
|
| 1570 |
+
"logps/chosen": -1010.8033447265625,
|
| 1571 |
+
"logps/rejected": -1388.541015625,
|
| 1572 |
+
"loss": 1.5382,
|
| 1573 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1574 |
+
"rewards/chosen": -0.5765799283981323,
|
| 1575 |
+
"rewards/margins": 0.40866199135780334,
|
| 1576 |
+
"rewards/rejected": -0.9852418899536133,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9,
|
| 1581 |
+
"learning_rate": 1.629358090099639e-07,
|
| 1582 |
+
"logits/chosen": 0.13894052803516388,
|
| 1583 |
+
"logits/rejected": 0.13587644696235657,
|
| 1584 |
+
"logps/chosen": -981.1856689453125,
|
| 1585 |
+
"logps/rejected": -1380.902587890625,
|
| 1586 |
+
"loss": 1.5256,
|
| 1587 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1588 |
+
"rewards/chosen": -0.5833259224891663,
|
| 1589 |
+
"rewards/margins": 0.4001302719116211,
|
| 1590 |
+
"rewards/rejected": -0.9834562540054321,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9,
|
| 1595 |
+
"learning_rate": 1.3905907440629752e-07,
|
| 1596 |
+
"logits/chosen": 0.1367521584033966,
|
| 1597 |
+
"logits/rejected": 0.10814319550991058,
|
| 1598 |
+
"logps/chosen": -1037.4566650390625,
|
| 1599 |
+
"logps/rejected": -1406.663818359375,
|
| 1600 |
+
"loss": 1.5083,
|
| 1601 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1602 |
+
"rewards/chosen": -0.5931031703948975,
|
| 1603 |
+
"rewards/margins": 0.40140143036842346,
|
| 1604 |
+
"rewards/rejected": -0.9945046305656433,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.91,
|
| 1609 |
+
"learning_rate": 1.1702333051763271e-07,
|
| 1610 |
+
"logits/chosen": 0.13864858448505402,
|
| 1611 |
+
"logits/rejected": 0.10779663175344467,
|
| 1612 |
+
"logps/chosen": -968.2605590820312,
|
| 1613 |
+
"logps/rejected": -1421.97900390625,
|
| 1614 |
+
"loss": 1.4325,
|
| 1615 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1616 |
+
"rewards/chosen": -0.553028404712677,
|
| 1617 |
+
"rewards/margins": 0.45522522926330566,
|
| 1618 |
+
"rewards/rejected": -1.0082536935806274,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.92,
|
| 1623 |
+
"learning_rate": 9.684576015420277e-08,
|
| 1624 |
+
"logits/chosen": 0.1990373134613037,
|
| 1625 |
+
"logits/rejected": 0.15076985955238342,
|
| 1626 |
+
"logps/chosen": -959.9166259765625,
|
| 1627 |
+
"logps/rejected": -1385.095703125,
|
| 1628 |
+
"loss": 1.4883,
|
| 1629 |
+
"rewards/accuracies": 0.75,
|
| 1630 |
+
"rewards/chosen": -0.5342432856559753,
|
| 1631 |
+
"rewards/margins": 0.45701155066490173,
|
| 1632 |
+
"rewards/rejected": -0.9912548065185547,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.93,
|
| 1637 |
+
"learning_rate": 7.854209717842231e-08,
|
| 1638 |
+
"logits/chosen": 0.167617067694664,
|
| 1639 |
+
"logits/rejected": 0.16784724593162537,
|
| 1640 |
+
"logps/chosen": -999.2423095703125,
|
| 1641 |
+
"logps/rejected": -1370.2662353515625,
|
| 1642 |
+
"loss": 1.4697,
|
| 1643 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1644 |
+
"rewards/chosen": -0.5615602135658264,
|
| 1645 |
+
"rewards/margins": 0.4337054193019867,
|
| 1646 |
+
"rewards/rejected": -0.9952656030654907,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.94,
|
| 1651 |
+
"learning_rate": 6.212661423609184e-08,
|
| 1652 |
+
"logits/chosen": 0.1487255096435547,
|
| 1653 |
+
"logits/rejected": 0.17393285036087036,
|
| 1654 |
+
"logps/chosen": -991.5260009765625,
|
| 1655 |
+
"logps/rejected": -1270.6396484375,
|
| 1656 |
+
"loss": 1.7102,
|
| 1657 |
+
"rewards/accuracies": 0.637499988079071,
|
| 1658 |
+
"rewards/chosen": -0.5859721899032593,
|
| 1659 |
+
"rewards/margins": 0.29911959171295166,
|
| 1660 |
+
"rewards/rejected": -0.8850919008255005,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.94,
|
| 1665 |
+
"learning_rate": 4.761211162702117e-08,
|
| 1666 |
+
"logits/chosen": 0.12677620351314545,
|
| 1667 |
+
"logits/rejected": 0.1536310613155365,
|
| 1668 |
+
"logps/chosen": -1026.4810791015625,
|
| 1669 |
+
"logps/rejected": -1375.422119140625,
|
| 1670 |
+
"loss": 1.5775,
|
| 1671 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1672 |
+
"rewards/chosen": -0.6072763800621033,
|
| 1673 |
+
"rewards/margins": 0.3752721846103668,
|
| 1674 |
+
"rewards/rejected": -0.982548713684082,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.95,
|
| 1679 |
+
"learning_rate": 3.5009907323737826e-08,
|
| 1680 |
+
"logits/chosen": 0.13358378410339355,
|
| 1681 |
+
"logits/rejected": 0.13474227488040924,
|
| 1682 |
+
"logps/chosen": -1048.68994140625,
|
| 1683 |
+
"logps/rejected": -1420.0101318359375,
|
| 1684 |
+
"loss": 1.5444,
|
| 1685 |
+
"rewards/accuracies": 0.71875,
|
| 1686 |
+
"rewards/chosen": -0.6096453070640564,
|
| 1687 |
+
"rewards/margins": 0.3957948684692383,
|
| 1688 |
+
"rewards/rejected": -1.00544011592865,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.96,
|
| 1693 |
+
"learning_rate": 2.4329828146074096e-08,
|
| 1694 |
+
"logits/chosen": 0.10293509066104889,
|
| 1695 |
+
"logits/rejected": 0.08836082369089127,
|
| 1696 |
+
"logps/chosen": -981.24755859375,
|
| 1697 |
+
"logps/rejected": -1432.976318359375,
|
| 1698 |
+
"loss": 1.4505,
|
| 1699 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1700 |
+
"rewards/chosen": -0.5690222382545471,
|
| 1701 |
+
"rewards/margins": 0.4183219075202942,
|
| 1702 |
+
"rewards/rejected": -0.9873440861701965,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.97,
|
| 1707 |
+
"learning_rate": 1.5580202098509078e-08,
|
| 1708 |
+
"logits/chosen": 0.09086032956838608,
|
| 1709 |
+
"logits/rejected": 0.0959467664361,
|
| 1710 |
+
"logps/chosen": -972.2115478515625,
|
| 1711 |
+
"logps/rejected": -1355.9515380859375,
|
| 1712 |
+
"loss": 1.4382,
|
| 1713 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1714 |
+
"rewards/chosen": -0.5868245959281921,
|
| 1715 |
+
"rewards/margins": 0.3957366347312927,
|
| 1716 |
+
"rewards/rejected": -0.9825612306594849,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.98,
|
| 1721 |
+
"learning_rate": 8.767851876239075e-09,
|
| 1722 |
+
"logits/chosen": 0.12658867239952087,
|
| 1723 |
+
"logits/rejected": 0.1394813060760498,
|
| 1724 |
+
"logps/chosen": -984.2681884765625,
|
| 1725 |
+
"logps/rejected": -1267.7216796875,
|
| 1726 |
+
"loss": 1.5614,
|
| 1727 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1728 |
+
"rewards/chosen": -0.5679751634597778,
|
| 1729 |
+
"rewards/margins": 0.30647456645965576,
|
| 1730 |
+
"rewards/rejected": -0.8744497299194336,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.98,
|
| 1735 |
+
"learning_rate": 3.8980895450474455e-09,
|
| 1736 |
+
"logits/chosen": 0.11635242402553558,
|
| 1737 |
+
"logits/rejected": 0.08196248859167099,
|
| 1738 |
+
"logps/chosen": -1042.649169921875,
|
| 1739 |
+
"logps/rejected": -1407.2928466796875,
|
| 1740 |
+
"loss": 1.603,
|
| 1741 |
+
"rewards/accuracies": 0.6875,
|
| 1742 |
+
"rewards/chosen": -0.5844318270683289,
|
| 1743 |
+
"rewards/margins": 0.4090692400932312,
|
| 1744 |
+
"rewards/rejected": -0.9935010671615601,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.99,
|
| 1749 |
+
"learning_rate": 9.747123991141193e-10,
|
| 1750 |
+
"logits/chosen": 0.1424560546875,
|
| 1751 |
+
"logits/rejected": 0.1417275071144104,
|
| 1752 |
+
"logps/chosen": -1018.15234375,
|
| 1753 |
+
"logps/rejected": -1289.4718017578125,
|
| 1754 |
+
"loss": 1.4991,
|
| 1755 |
+
"rewards/accuracies": 0.65625,
|
| 1756 |
+
"rewards/chosen": -0.5752192735671997,
|
| 1757 |
+
"rewards/margins": 0.3309435248374939,
|
| 1758 |
+
"rewards/rejected": -0.9061626195907593,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.0,
|
| 1763 |
+
"learning_rate": 0.0,
|
| 1764 |
+
"logits/chosen": 0.11531805992126465,
|
| 1765 |
+
"logits/rejected": 0.14260968565940857,
|
| 1766 |
+
"logps/chosen": -945.6492919921875,
|
| 1767 |
+
"logps/rejected": -1332.210693359375,
|
| 1768 |
+
"loss": 1.5185,
|
| 1769 |
+
"rewards/accuracies": 0.75,
|
| 1770 |
+
"rewards/chosen": -0.5279589891433716,
|
| 1771 |
+
"rewards/margins": 0.39913317561149597,
|
| 1772 |
+
"rewards/rejected": -0.9270921945571899,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.0,
|
| 1777 |
+
"step": 1250,
|
| 1778 |
+
"total_flos": 0.0,
|
| 1779 |
+
"train_loss": 1.6514112674713135,
|
| 1780 |
+
"train_runtime": 16819.2653,
|
| 1781 |
+
"train_samples_per_second": 3.567,
|
| 1782 |
+
"train_steps_per_second": 0.074
|
| 1783 |
+
}
|
| 1784 |
+
],
|
| 1785 |
+
"logging_steps": 10,
|
| 1786 |
+
"max_steps": 1250,
|
| 1787 |
+
"num_input_tokens_seen": 0,
|
| 1788 |
+
"num_train_epochs": 1,
|
| 1789 |
+
"save_steps": 100,
|
| 1790 |
+
"total_flos": 0.0,
|
| 1791 |
+
"train_batch_size": 4,
|
| 1792 |
+
"trial_name": null,
|
| 1793 |
+
"trial_params": null
|
| 1794 |
+
}
|