Model save
Browse files- README.md +62 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May15_10-27-10_gpu4-119-5/events.out.tfevents.1715732933.gpu4-119-5.2951744.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -0
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: DUAL-GPO-2/zephyr-7b-irepo-new-i2
|
| 9 |
+
model-index:
|
| 10 |
+
- name: zephyr-7b-gpo-v7-i3
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# zephyr-7b-gpo-v7-i3
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [DUAL-GPO-2/zephyr-7b-irepo-new-i2](https://huggingface.co/DUAL-GPO-2/zephyr-7b-irepo-new-i2) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 2
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- total_eval_batch_size: 4
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- PEFT 0.7.1
|
| 59 |
+
- Transformers 4.36.2
|
| 60 |
+
- Pytorch 2.1.2+cu121
|
| 61 |
+
- Datasets 2.14.6
|
| 62 |
+
- 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 671150064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da11e2a013dbf8a224cc30c50626315111b655c2c06133272256b53d819f4298
|
| 3 |
size 671150064
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.18001604646046956,
|
| 4 |
+
"train_runtime": 15472.4916,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 0.969,
|
| 7 |
+
"train_steps_per_second": 0.121
|
| 8 |
+
}
|
runs/May15_10-27-10_gpu4-119-5/events.out.tfevents.1715732933.gpu4-119-5.2951744.0
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:bb3dd9b8bdd4c86fa04418d003d23d664cd0b606a03e3ee36baaab51519e8d6a
|
| 3 |
+
size 123964
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.18001604646046956,
|
| 4 |
+
"train_runtime": 15472.4916,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 0.969,
|
| 7 |
+
"train_steps_per_second": 0.121
|
| 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": -1.4655269384384155,
|
| 15 |
+
"logits/rejected": -1.033621907234192,
|
| 16 |
+
"logps/chosen": -459.0647277832031,
|
| 17 |
+
"logps/rejected": -1330.877197265625,
|
| 18 |
+
"loss": 0.3828,
|
| 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": -1.5051629543304443,
|
| 29 |
+
"logits/rejected": -0.712297260761261,
|
| 30 |
+
"logps/chosen": -705.1040649414062,
|
| 31 |
+
"logps/rejected": -1360.2410888671875,
|
| 32 |
+
"loss": 0.3114,
|
| 33 |
+
"rewards/accuracies": 0.3888888955116272,
|
| 34 |
+
"rewards/chosen": 0.0001662555441725999,
|
| 35 |
+
"rewards/margins": 2.4516626581316814e-05,
|
| 36 |
+
"rewards/rejected": 0.00014173888484947383,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": -1.3879754543304443,
|
| 43 |
+
"logits/rejected": -0.8259027600288391,
|
| 44 |
+
"logps/chosen": -617.7056884765625,
|
| 45 |
+
"logps/rejected": -1266.44580078125,
|
| 46 |
+
"loss": 0.3413,
|
| 47 |
+
"rewards/accuracies": 0.550000011920929,
|
| 48 |
+
"rewards/chosen": -0.00024980775197036564,
|
| 49 |
+
"rewards/margins": 0.0005200988380238414,
|
| 50 |
+
"rewards/rejected": -0.0007699066773056984,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": -1.4345638751983643,
|
| 57 |
+
"logits/rejected": -0.8269219398498535,
|
| 58 |
+
"logps/chosen": -646.2857055664062,
|
| 59 |
+
"logps/rejected": -1389.702392578125,
|
| 60 |
+
"loss": 0.3747,
|
| 61 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 62 |
+
"rewards/chosen": 0.0002903448767028749,
|
| 63 |
+
"rewards/margins": 0.00816894881427288,
|
| 64 |
+
"rewards/rejected": -0.007878603413701057,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": -1.4127135276794434,
|
| 71 |
+
"logits/rejected": -0.9716196060180664,
|
| 72 |
+
"logps/chosen": -517.2140502929688,
|
| 73 |
+
"logps/rejected": -1226.396728515625,
|
| 74 |
+
"loss": 0.3177,
|
| 75 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 76 |
+
"rewards/chosen": -0.001012824010103941,
|
| 77 |
+
"rewards/margins": 0.01804637908935547,
|
| 78 |
+
"rewards/rejected": -0.019059203565120697,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": -1.5345873832702637,
|
| 85 |
+
"logits/rejected": -0.6556589603424072,
|
| 86 |
+
"logps/chosen": -707.1253051757812,
|
| 87 |
+
"logps/rejected": -1423.584228515625,
|
| 88 |
+
"loss": 0.2566,
|
| 89 |
+
"rewards/accuracies": 0.75,
|
| 90 |
+
"rewards/chosen": -0.006385817192494869,
|
| 91 |
+
"rewards/margins": 0.05405501276254654,
|
| 92 |
+
"rewards/rejected": -0.06044083088636398,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": -1.244545340538025,
|
| 99 |
+
"logits/rejected": -0.7255198359489441,
|
| 100 |
+
"logps/chosen": -639.6641845703125,
|
| 101 |
+
"logps/rejected": -1549.7298583984375,
|
| 102 |
+
"loss": 0.2391,
|
| 103 |
+
"rewards/accuracies": 0.800000011920929,
|
| 104 |
+
"rewards/chosen": -0.07489156723022461,
|
| 105 |
+
"rewards/margins": 0.12882688641548157,
|
| 106 |
+
"rewards/rejected": -0.20371845364570618,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": -1.3547617197036743,
|
| 113 |
+
"logits/rejected": -0.35274913907051086,
|
| 114 |
+
"logps/chosen": -767.3015747070312,
|
| 115 |
+
"logps/rejected": -1636.340087890625,
|
| 116 |
+
"loss": 0.2003,
|
| 117 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 118 |
+
"rewards/chosen": -0.19739916920661926,
|
| 119 |
+
"rewards/margins": 0.2098737508058548,
|
| 120 |
+
"rewards/rejected": -0.40727296471595764,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": -1.2055673599243164,
|
| 127 |
+
"logits/rejected": -0.5075792074203491,
|
| 128 |
+
"logps/chosen": -786.0068969726562,
|
| 129 |
+
"logps/rejected": -1766.186767578125,
|
| 130 |
+
"loss": 0.1685,
|
| 131 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 132 |
+
"rewards/chosen": -0.15041813254356384,
|
| 133 |
+
"rewards/margins": 0.2894287705421448,
|
| 134 |
+
"rewards/rejected": -0.4398469030857086,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": -1.478634238243103,
|
| 141 |
+
"logits/rejected": -0.5144511461257935,
|
| 142 |
+
"logps/chosen": -730.87890625,
|
| 143 |
+
"logps/rejected": -1668.932861328125,
|
| 144 |
+
"loss": 0.1939,
|
| 145 |
+
"rewards/accuracies": 0.75,
|
| 146 |
+
"rewards/chosen": -0.16476184129714966,
|
| 147 |
+
"rewards/margins": 0.24078884720802307,
|
| 148 |
+
"rewards/rejected": -0.4055507183074951,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": -1.4973030090332031,
|
| 155 |
+
"logits/rejected": -0.6912057399749756,
|
| 156 |
+
"logps/chosen": -791.8748779296875,
|
| 157 |
+
"logps/rejected": -1806.0367431640625,
|
| 158 |
+
"loss": 0.2125,
|
| 159 |
+
"rewards/accuracies": 0.75,
|
| 160 |
+
"rewards/chosen": -0.21075236797332764,
|
| 161 |
+
"rewards/margins": 0.25144320726394653,
|
| 162 |
+
"rewards/rejected": -0.46219557523727417,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": -1.3953739404678345,
|
| 169 |
+
"logits/rejected": -0.6119239926338196,
|
| 170 |
+
"logps/chosen": -722.7054443359375,
|
| 171 |
+
"logps/rejected": -1811.979736328125,
|
| 172 |
+
"loss": 0.1752,
|
| 173 |
+
"rewards/accuracies": 0.800000011920929,
|
| 174 |
+
"rewards/chosen": -0.16878579556941986,
|
| 175 |
+
"rewards/margins": 0.3092211186885834,
|
| 176 |
+
"rewards/rejected": -0.47800692915916443,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": -1.4477260112762451,
|
| 183 |
+
"logits/rejected": -1.145725965499878,
|
| 184 |
+
"logps/chosen": -636.2543334960938,
|
| 185 |
+
"logps/rejected": -1560.247802734375,
|
| 186 |
+
"loss": 0.2261,
|
| 187 |
+
"rewards/accuracies": 0.699999988079071,
|
| 188 |
+
"rewards/chosen": -0.21692097187042236,
|
| 189 |
+
"rewards/margins": 0.2692717909812927,
|
| 190 |
+
"rewards/rejected": -0.4861927628517151,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": -1.4003589153289795,
|
| 197 |
+
"logits/rejected": -0.4936106204986572,
|
| 198 |
+
"logps/chosen": -758.2838134765625,
|
| 199 |
+
"logps/rejected": -1723.779052734375,
|
| 200 |
+
"loss": 0.1853,
|
| 201 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 202 |
+
"rewards/chosen": -0.25890326499938965,
|
| 203 |
+
"rewards/margins": 0.23604793846607208,
|
| 204 |
+
"rewards/rejected": -0.4949512481689453,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": -1.0825198888778687,
|
| 211 |
+
"logits/rejected": 0.35903090238571167,
|
| 212 |
+
"logps/chosen": -885.7689208984375,
|
| 213 |
+
"logps/rejected": -1848.095947265625,
|
| 214 |
+
"loss": 0.2007,
|
| 215 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 216 |
+
"rewards/chosen": -0.23516646027565002,
|
| 217 |
+
"rewards/margins": 0.2823827266693115,
|
| 218 |
+
"rewards/rejected": -0.5175491571426392,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": -1.4162981510162354,
|
| 225 |
+
"logits/rejected": -0.7130796313285828,
|
| 226 |
+
"logps/chosen": -671.996337890625,
|
| 227 |
+
"logps/rejected": -1514.2220458984375,
|
| 228 |
+
"loss": 0.2171,
|
| 229 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 230 |
+
"rewards/chosen": -0.09221184998750687,
|
| 231 |
+
"rewards/margins": 0.2251388132572174,
|
| 232 |
+
"rewards/rejected": -0.31735068559646606,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": -1.5083972215652466,
|
| 239 |
+
"logits/rejected": -0.1440640687942505,
|
| 240 |
+
"logps/chosen": -748.1359252929688,
|
| 241 |
+
"logps/rejected": -1689.578369140625,
|
| 242 |
+
"loss": 0.2096,
|
| 243 |
+
"rewards/accuracies": 0.75,
|
| 244 |
+
"rewards/chosen": -0.1878463327884674,
|
| 245 |
+
"rewards/margins": 0.28401127457618713,
|
| 246 |
+
"rewards/rejected": -0.47185754776000977,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": -1.432492733001709,
|
| 253 |
+
"logits/rejected": -0.35446396470069885,
|
| 254 |
+
"logps/chosen": -667.8497314453125,
|
| 255 |
+
"logps/rejected": -1559.5621337890625,
|
| 256 |
+
"loss": 0.2264,
|
| 257 |
+
"rewards/accuracies": 0.699999988079071,
|
| 258 |
+
"rewards/chosen": -0.10573254525661469,
|
| 259 |
+
"rewards/margins": 0.13765206933021545,
|
| 260 |
+
"rewards/rejected": -0.24338459968566895,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": -1.4102504253387451,
|
| 267 |
+
"logits/rejected": -0.08080820739269257,
|
| 268 |
+
"logps/chosen": -640.1746215820312,
|
| 269 |
+
"logps/rejected": -1653.6851806640625,
|
| 270 |
+
"loss": 0.4574,
|
| 271 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 272 |
+
"rewards/chosen": -0.04140184074640274,
|
| 273 |
+
"rewards/margins": 0.3433176875114441,
|
| 274 |
+
"rewards/rejected": -0.3847195506095886,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": -1.5038793087005615,
|
| 281 |
+
"logits/rejected": -0.5108478665351868,
|
| 282 |
+
"logps/chosen": -650.073974609375,
|
| 283 |
+
"logps/rejected": -1593.111083984375,
|
| 284 |
+
"loss": 0.2165,
|
| 285 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 286 |
+
"rewards/chosen": -0.015623539686203003,
|
| 287 |
+
"rewards/margins": 0.13894978165626526,
|
| 288 |
+
"rewards/rejected": -0.15457329154014587,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": -1.4442822933197021,
|
| 295 |
+
"logits/rejected": -0.47450265288352966,
|
| 296 |
+
"logps/chosen": -636.0139770507812,
|
| 297 |
+
"logps/rejected": -1700.844482421875,
|
| 298 |
+
"loss": 0.2143,
|
| 299 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 300 |
+
"rewards/chosen": -0.03425021469593048,
|
| 301 |
+
"rewards/margins": 0.2377198487520218,
|
| 302 |
+
"rewards/rejected": -0.27197009325027466,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": -1.405047059059143,
|
| 309 |
+
"logits/rejected": -0.5784617066383362,
|
| 310 |
+
"logps/chosen": -678.7222290039062,
|
| 311 |
+
"logps/rejected": -1632.005615234375,
|
| 312 |
+
"loss": 0.2189,
|
| 313 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 314 |
+
"rewards/chosen": -0.10118959844112396,
|
| 315 |
+
"rewards/margins": 0.24721214175224304,
|
| 316 |
+
"rewards/rejected": -0.3484017848968506,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": -1.4955471754074097,
|
| 323 |
+
"logits/rejected": -0.4132479727268219,
|
| 324 |
+
"logps/chosen": -838.4027099609375,
|
| 325 |
+
"logps/rejected": -1668.740966796875,
|
| 326 |
+
"loss": 0.2038,
|
| 327 |
+
"rewards/accuracies": 0.75,
|
| 328 |
+
"rewards/chosen": -0.18389900028705597,
|
| 329 |
+
"rewards/margins": 0.2373250424861908,
|
| 330 |
+
"rewards/rejected": -0.42122405767440796,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": -1.2583847045898438,
|
| 337 |
+
"logits/rejected": -0.5125802755355835,
|
| 338 |
+
"logps/chosen": -804.1488037109375,
|
| 339 |
+
"logps/rejected": -1768.70703125,
|
| 340 |
+
"loss": 0.2087,
|
| 341 |
+
"rewards/accuracies": 0.824999988079071,
|
| 342 |
+
"rewards/chosen": -0.16385242342948914,
|
| 343 |
+
"rewards/margins": 0.26760467886924744,
|
| 344 |
+
"rewards/rejected": -0.4314571022987366,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": -1.3879817724227905,
|
| 351 |
+
"logits/rejected": -0.7601082921028137,
|
| 352 |
+
"logps/chosen": -643.2053833007812,
|
| 353 |
+
"logps/rejected": -1582.4229736328125,
|
| 354 |
+
"loss": 0.2098,
|
| 355 |
+
"rewards/accuracies": 0.75,
|
| 356 |
+
"rewards/chosen": -0.08198627084493637,
|
| 357 |
+
"rewards/margins": 0.24419136345386505,
|
| 358 |
+
"rewards/rejected": -0.3261776566505432,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": -1.2820708751678467,
|
| 365 |
+
"logits/rejected": -0.7363845109939575,
|
| 366 |
+
"logps/chosen": -591.2818603515625,
|
| 367 |
+
"logps/rejected": -1653.382080078125,
|
| 368 |
+
"loss": 0.1716,
|
| 369 |
+
"rewards/accuracies": 0.925000011920929,
|
| 370 |
+
"rewards/chosen": -0.055700987577438354,
|
| 371 |
+
"rewards/margins": 0.2979794144630432,
|
| 372 |
+
"rewards/rejected": -0.35368040204048157,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": -1.5291858911514282,
|
| 379 |
+
"logits/rejected": -0.19423088431358337,
|
| 380 |
+
"logps/chosen": -732.954833984375,
|
| 381 |
+
"logps/rejected": -1630.454833984375,
|
| 382 |
+
"loss": 0.227,
|
| 383 |
+
"rewards/accuracies": 0.800000011920929,
|
| 384 |
+
"rewards/chosen": -0.09654470533132553,
|
| 385 |
+
"rewards/margins": 0.2725062370300293,
|
| 386 |
+
"rewards/rejected": -0.36905092000961304,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": -1.2763826847076416,
|
| 393 |
+
"logits/rejected": -0.358491986989975,
|
| 394 |
+
"logps/chosen": -659.6267700195312,
|
| 395 |
+
"logps/rejected": -1627.0989990234375,
|
| 396 |
+
"loss": 0.1989,
|
| 397 |
+
"rewards/accuracies": 0.800000011920929,
|
| 398 |
+
"rewards/chosen": -0.10589329153299332,
|
| 399 |
+
"rewards/margins": 0.22936058044433594,
|
| 400 |
+
"rewards/rejected": -0.33525389432907104,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": -1.4150131940841675,
|
| 407 |
+
"logits/rejected": -0.5769174695014954,
|
| 408 |
+
"logps/chosen": -790.4682006835938,
|
| 409 |
+
"logps/rejected": -1594.6312255859375,
|
| 410 |
+
"loss": 0.1994,
|
| 411 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 412 |
+
"rewards/chosen": -0.1530950367450714,
|
| 413 |
+
"rewards/margins": 0.20400938391685486,
|
| 414 |
+
"rewards/rejected": -0.3571043908596039,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": -1.5317466259002686,
|
| 421 |
+
"logits/rejected": -0.8124315142631531,
|
| 422 |
+
"logps/chosen": -732.0606079101562,
|
| 423 |
+
"logps/rejected": -1573.697021484375,
|
| 424 |
+
"loss": 0.192,
|
| 425 |
+
"rewards/accuracies": 0.699999988079071,
|
| 426 |
+
"rewards/chosen": -0.16247740387916565,
|
| 427 |
+
"rewards/margins": 0.23650550842285156,
|
| 428 |
+
"rewards/rejected": -0.3989828824996948,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": -1.3253892660140991,
|
| 435 |
+
"logits/rejected": -0.6317247152328491,
|
| 436 |
+
"logps/chosen": -800.7886962890625,
|
| 437 |
+
"logps/rejected": -1812.166259765625,
|
| 438 |
+
"loss": 0.1507,
|
| 439 |
+
"rewards/accuracies": 0.800000011920929,
|
| 440 |
+
"rewards/chosen": -0.15501004457473755,
|
| 441 |
+
"rewards/margins": 0.2739163339138031,
|
| 442 |
+
"rewards/rejected": -0.42892640829086304,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": -1.4076381921768188,
|
| 449 |
+
"logits/rejected": -0.5177509188652039,
|
| 450 |
+
"logps/chosen": -560.181396484375,
|
| 451 |
+
"logps/rejected": -1555.759521484375,
|
| 452 |
+
"loss": 0.1571,
|
| 453 |
+
"rewards/accuracies": 0.75,
|
| 454 |
+
"rewards/chosen": -0.08090414851903915,
|
| 455 |
+
"rewards/margins": 0.30350688099861145,
|
| 456 |
+
"rewards/rejected": -0.3844110071659088,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": -1.5608190298080444,
|
| 463 |
+
"logits/rejected": -0.4406317174434662,
|
| 464 |
+
"logps/chosen": -630.440673828125,
|
| 465 |
+
"logps/rejected": -1558.788818359375,
|
| 466 |
+
"loss": 0.2186,
|
| 467 |
+
"rewards/accuracies": 0.699999988079071,
|
| 468 |
+
"rewards/chosen": -0.11196412891149521,
|
| 469 |
+
"rewards/margins": 0.19183890521526337,
|
| 470 |
+
"rewards/rejected": -0.303803026676178,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": -1.414440631866455,
|
| 477 |
+
"logits/rejected": -0.49061527848243713,
|
| 478 |
+
"logps/chosen": -724.7615966796875,
|
| 479 |
+
"logps/rejected": -1786.733642578125,
|
| 480 |
+
"loss": 0.172,
|
| 481 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 482 |
+
"rewards/chosen": -0.12826617062091827,
|
| 483 |
+
"rewards/margins": 0.3003011643886566,
|
| 484 |
+
"rewards/rejected": -0.4285673499107361,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": -1.4440535306930542,
|
| 491 |
+
"logits/rejected": -0.4736519753932953,
|
| 492 |
+
"logps/chosen": -700.4628295898438,
|
| 493 |
+
"logps/rejected": -1750.1715087890625,
|
| 494 |
+
"loss": 0.1702,
|
| 495 |
+
"rewards/accuracies": 0.800000011920929,
|
| 496 |
+
"rewards/chosen": -0.10472197830677032,
|
| 497 |
+
"rewards/margins": 0.2777271866798401,
|
| 498 |
+
"rewards/rejected": -0.38244912028312683,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": -1.5601012706756592,
|
| 505 |
+
"logits/rejected": -0.19679054617881775,
|
| 506 |
+
"logps/chosen": -773.9390869140625,
|
| 507 |
+
"logps/rejected": -1652.917724609375,
|
| 508 |
+
"loss": 0.1594,
|
| 509 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 510 |
+
"rewards/chosen": -0.13721729815006256,
|
| 511 |
+
"rewards/margins": 0.26322948932647705,
|
| 512 |
+
"rewards/rejected": -0.40044674277305603,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": -1.5175647735595703,
|
| 519 |
+
"logits/rejected": -0.5158883333206177,
|
| 520 |
+
"logps/chosen": -730.0354614257812,
|
| 521 |
+
"logps/rejected": -1762.952880859375,
|
| 522 |
+
"loss": 0.226,
|
| 523 |
+
"rewards/accuracies": 0.925000011920929,
|
| 524 |
+
"rewards/chosen": -0.15878579020500183,
|
| 525 |
+
"rewards/margins": 0.2685873210430145,
|
| 526 |
+
"rewards/rejected": -0.42737311124801636,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": -1.2855349779129028,
|
| 533 |
+
"logits/rejected": -0.4378298819065094,
|
| 534 |
+
"logps/chosen": -668.7643432617188,
|
| 535 |
+
"logps/rejected": -1692.6859130859375,
|
| 536 |
+
"loss": 0.1967,
|
| 537 |
+
"rewards/accuracies": 0.800000011920929,
|
| 538 |
+
"rewards/chosen": -0.16277587413787842,
|
| 539 |
+
"rewards/margins": 0.2703282833099365,
|
| 540 |
+
"rewards/rejected": -0.43310412764549255,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": -1.5854368209838867,
|
| 547 |
+
"logits/rejected": -0.7641209959983826,
|
| 548 |
+
"logps/chosen": -760.0360107421875,
|
| 549 |
+
"logps/rejected": -1679.648681640625,
|
| 550 |
+
"loss": 0.2054,
|
| 551 |
+
"rewards/accuracies": 0.699999988079071,
|
| 552 |
+
"rewards/chosen": -0.1432400643825531,
|
| 553 |
+
"rewards/margins": 0.27862492203712463,
|
| 554 |
+
"rewards/rejected": -0.42186498641967773,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": -1.2518047094345093,
|
| 561 |
+
"logits/rejected": 0.1541678011417389,
|
| 562 |
+
"logps/chosen": -620.4710693359375,
|
| 563 |
+
"logps/rejected": -1564.021240234375,
|
| 564 |
+
"loss": 0.163,
|
| 565 |
+
"rewards/accuracies": 0.800000011920929,
|
| 566 |
+
"rewards/chosen": -0.08593844622373581,
|
| 567 |
+
"rewards/margins": 0.3075733780860901,
|
| 568 |
+
"rewards/rejected": -0.3935117721557617,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": -1.3414735794067383,
|
| 575 |
+
"logits/rejected": 0.27303165197372437,
|
| 576 |
+
"logps/chosen": -734.915771484375,
|
| 577 |
+
"logps/rejected": -1726.513671875,
|
| 578 |
+
"loss": 0.1809,
|
| 579 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 580 |
+
"rewards/chosen": -0.1514008492231369,
|
| 581 |
+
"rewards/margins": 0.3023954927921295,
|
| 582 |
+
"rewards/rejected": -0.45379629731178284,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": -1.6200311183929443,
|
| 589 |
+
"logits/rejected": -0.9766647219657898,
|
| 590 |
+
"logps/chosen": -630.611328125,
|
| 591 |
+
"logps/rejected": -1720.3140869140625,
|
| 592 |
+
"loss": 0.1582,
|
| 593 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 594 |
+
"rewards/chosen": -0.14615099132061005,
|
| 595 |
+
"rewards/margins": 0.30823230743408203,
|
| 596 |
+
"rewards/rejected": -0.45438331365585327,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": -1.6855354309082031,
|
| 603 |
+
"logits/rejected": -0.5985993146896362,
|
| 604 |
+
"logps/chosen": -717.0406494140625,
|
| 605 |
+
"logps/rejected": -1674.328369140625,
|
| 606 |
+
"loss": 0.157,
|
| 607 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 608 |
+
"rewards/chosen": -0.14980314671993256,
|
| 609 |
+
"rewards/margins": 0.27969104051589966,
|
| 610 |
+
"rewards/rejected": -0.42949414253234863,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": -1.5795036554336548,
|
| 617 |
+
"logits/rejected": -0.012340852990746498,
|
| 618 |
+
"logps/chosen": -767.9241943359375,
|
| 619 |
+
"logps/rejected": -1746.126220703125,
|
| 620 |
+
"loss": 0.1509,
|
| 621 |
+
"rewards/accuracies": 0.875,
|
| 622 |
+
"rewards/chosen": -0.19612105190753937,
|
| 623 |
+
"rewards/margins": 0.31204092502593994,
|
| 624 |
+
"rewards/rejected": -0.5081619024276733,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": -1.335930585861206,
|
| 631 |
+
"logits/rejected": 0.10618801414966583,
|
| 632 |
+
"logps/chosen": -792.5811767578125,
|
| 633 |
+
"logps/rejected": -1725.929443359375,
|
| 634 |
+
"loss": 0.1641,
|
| 635 |
+
"rewards/accuracies": 0.75,
|
| 636 |
+
"rewards/chosen": -0.20740894973278046,
|
| 637 |
+
"rewards/margins": 0.2866581678390503,
|
| 638 |
+
"rewards/rejected": -0.49406710267066956,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": -1.4894254207611084,
|
| 645 |
+
"logits/rejected": -0.4472936987876892,
|
| 646 |
+
"logps/chosen": -812.9591674804688,
|
| 647 |
+
"logps/rejected": -1778.461181640625,
|
| 648 |
+
"loss": 0.1515,
|
| 649 |
+
"rewards/accuracies": 0.824999988079071,
|
| 650 |
+
"rewards/chosen": -0.16330209374427795,
|
| 651 |
+
"rewards/margins": 0.321885883808136,
|
| 652 |
+
"rewards/rejected": -0.48518800735473633,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": -1.3552906513214111,
|
| 659 |
+
"logits/rejected": 0.43209949135780334,
|
| 660 |
+
"logps/chosen": -839.5066528320312,
|
| 661 |
+
"logps/rejected": -1581.7581787109375,
|
| 662 |
+
"loss": 0.1617,
|
| 663 |
+
"rewards/accuracies": 0.75,
|
| 664 |
+
"rewards/chosen": -0.18863311409950256,
|
| 665 |
+
"rewards/margins": 0.24536097049713135,
|
| 666 |
+
"rewards/rejected": -0.4339941143989563,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": -1.4539438486099243,
|
| 673 |
+
"logits/rejected": -0.8116742968559265,
|
| 674 |
+
"logps/chosen": -729.900634765625,
|
| 675 |
+
"logps/rejected": -1769.510986328125,
|
| 676 |
+
"loss": 0.1622,
|
| 677 |
+
"rewards/accuracies": 0.75,
|
| 678 |
+
"rewards/chosen": -0.18170835077762604,
|
| 679 |
+
"rewards/margins": 0.3435843884944916,
|
| 680 |
+
"rewards/rejected": -0.5252927541732788,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": -1.2978649139404297,
|
| 687 |
+
"logits/rejected": -0.1232295036315918,
|
| 688 |
+
"logps/chosen": -824.3473510742188,
|
| 689 |
+
"logps/rejected": -1865.825439453125,
|
| 690 |
+
"loss": 0.1567,
|
| 691 |
+
"rewards/accuracies": 0.875,
|
| 692 |
+
"rewards/chosen": -0.14898522198200226,
|
| 693 |
+
"rewards/margins": 0.2702946960926056,
|
| 694 |
+
"rewards/rejected": -0.41927990317344666,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": -1.4946939945220947,
|
| 701 |
+
"logits/rejected": 0.050956688821315765,
|
| 702 |
+
"logps/chosen": -708.5657958984375,
|
| 703 |
+
"logps/rejected": -1557.0811767578125,
|
| 704 |
+
"loss": 0.2028,
|
| 705 |
+
"rewards/accuracies": 0.800000011920929,
|
| 706 |
+
"rewards/chosen": -0.09371930360794067,
|
| 707 |
+
"rewards/margins": 0.19662004709243774,
|
| 708 |
+
"rewards/rejected": -0.2903393507003784,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": -1.3152101039886475,
|
| 715 |
+
"logits/rejected": 0.32155555486679077,
|
| 716 |
+
"logps/chosen": -701.7420654296875,
|
| 717 |
+
"logps/rejected": -1673.237548828125,
|
| 718 |
+
"loss": 0.1656,
|
| 719 |
+
"rewards/accuracies": 0.824999988079071,
|
| 720 |
+
"rewards/chosen": -0.127631276845932,
|
| 721 |
+
"rewards/margins": 0.2853541970252991,
|
| 722 |
+
"rewards/rejected": -0.4129854738712311,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": -1.159698247909546,
|
| 729 |
+
"logits/rejected": 1.021859884262085,
|
| 730 |
+
"logps/chosen": -789.81884765625,
|
| 731 |
+
"logps/rejected": -1585.963623046875,
|
| 732 |
+
"loss": 0.1666,
|
| 733 |
+
"rewards/accuracies": 0.75,
|
| 734 |
+
"rewards/chosen": -0.21442024409770966,
|
| 735 |
+
"rewards/margins": 0.22131362557411194,
|
| 736 |
+
"rewards/rejected": -0.4357338845729828,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": -1.3945280313491821,
|
| 743 |
+
"logits/rejected": -0.13302992284297943,
|
| 744 |
+
"logps/chosen": -911.0645751953125,
|
| 745 |
+
"logps/rejected": -1837.2916259765625,
|
| 746 |
+
"loss": 0.1831,
|
| 747 |
+
"rewards/accuracies": 0.824999988079071,
|
| 748 |
+
"rewards/chosen": -0.24346116185188293,
|
| 749 |
+
"rewards/margins": 0.2620731592178345,
|
| 750 |
+
"rewards/rejected": -0.505534291267395,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": -1.38224458694458,
|
| 757 |
+
"logits/rejected": -0.5236114859580994,
|
| 758 |
+
"logps/chosen": -886.48583984375,
|
| 759 |
+
"logps/rejected": -1802.9521484375,
|
| 760 |
+
"loss": 0.2098,
|
| 761 |
+
"rewards/accuracies": 0.675000011920929,
|
| 762 |
+
"rewards/chosen": -0.29623985290527344,
|
| 763 |
+
"rewards/margins": 0.2730676829814911,
|
| 764 |
+
"rewards/rejected": -0.5693076252937317,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": -1.3253287076950073,
|
| 771 |
+
"logits/rejected": 0.04275239259004593,
|
| 772 |
+
"logps/chosen": -765.50048828125,
|
| 773 |
+
"logps/rejected": -1691.4166259765625,
|
| 774 |
+
"loss": 0.1454,
|
| 775 |
+
"rewards/accuracies": 0.800000011920929,
|
| 776 |
+
"rewards/chosen": -0.12114331871271133,
|
| 777 |
+
"rewards/margins": 0.28145861625671387,
|
| 778 |
+
"rewards/rejected": -0.4026018977165222,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": -1.505723237991333,
|
| 785 |
+
"logits/rejected": -0.5302447080612183,
|
| 786 |
+
"logps/chosen": -686.806396484375,
|
| 787 |
+
"logps/rejected": -1857.9820556640625,
|
| 788 |
+
"loss": 0.1407,
|
| 789 |
+
"rewards/accuracies": 0.925000011920929,
|
| 790 |
+
"rewards/chosen": -0.05712117999792099,
|
| 791 |
+
"rewards/margins": 0.3960820138454437,
|
| 792 |
+
"rewards/rejected": -0.4532032012939453,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": -1.3196251392364502,
|
| 799 |
+
"logits/rejected": -0.7369681596755981,
|
| 800 |
+
"logps/chosen": -761.491943359375,
|
| 801 |
+
"logps/rejected": -1692.483642578125,
|
| 802 |
+
"loss": 0.1989,
|
| 803 |
+
"rewards/accuracies": 0.800000011920929,
|
| 804 |
+
"rewards/chosen": -0.09536974877119064,
|
| 805 |
+
"rewards/margins": 0.2588408887386322,
|
| 806 |
+
"rewards/rejected": -0.35421064496040344,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": -1.2871177196502686,
|
| 813 |
+
"logits/rejected": -0.42333096265792847,
|
| 814 |
+
"logps/chosen": -770.8462524414062,
|
| 815 |
+
"logps/rejected": -1845.9010009765625,
|
| 816 |
+
"loss": 0.1735,
|
| 817 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 818 |
+
"rewards/chosen": -0.19140848517417908,
|
| 819 |
+
"rewards/margins": 0.343218058347702,
|
| 820 |
+
"rewards/rejected": -0.5346266031265259,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": -1.2731715440750122,
|
| 827 |
+
"logits/rejected": -0.4260900616645813,
|
| 828 |
+
"logps/chosen": -621.0642700195312,
|
| 829 |
+
"logps/rejected": -1537.65966796875,
|
| 830 |
+
"loss": 0.1433,
|
| 831 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 832 |
+
"rewards/chosen": -0.14984165132045746,
|
| 833 |
+
"rewards/margins": 0.2771284878253937,
|
| 834 |
+
"rewards/rejected": -0.42697015404701233,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": -1.1939516067504883,
|
| 841 |
+
"logits/rejected": -0.4788111746311188,
|
| 842 |
+
"logps/chosen": -734.4415893554688,
|
| 843 |
+
"logps/rejected": -1785.6878662109375,
|
| 844 |
+
"loss": 0.1775,
|
| 845 |
+
"rewards/accuracies": 0.824999988079071,
|
| 846 |
+
"rewards/chosen": -0.16298024356365204,
|
| 847 |
+
"rewards/margins": 0.288863867521286,
|
| 848 |
+
"rewards/rejected": -0.45184412598609924,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": -1.243289828300476,
|
| 855 |
+
"logits/rejected": -0.7459559440612793,
|
| 856 |
+
"logps/chosen": -627.3175048828125,
|
| 857 |
+
"logps/rejected": -1805.260498046875,
|
| 858 |
+
"loss": 0.1346,
|
| 859 |
+
"rewards/accuracies": 0.875,
|
| 860 |
+
"rewards/chosen": -0.09667791426181793,
|
| 861 |
+
"rewards/margins": 0.37870708107948303,
|
| 862 |
+
"rewards/rejected": -0.47538501024246216,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": -1.5651763677597046,
|
| 869 |
+
"logits/rejected": -0.5712302327156067,
|
| 870 |
+
"logps/chosen": -705.9287719726562,
|
| 871 |
+
"logps/rejected": -1588.61279296875,
|
| 872 |
+
"loss": 0.1316,
|
| 873 |
+
"rewards/accuracies": 0.800000011920929,
|
| 874 |
+
"rewards/chosen": -0.10819022357463837,
|
| 875 |
+
"rewards/margins": 0.26426267623901367,
|
| 876 |
+
"rewards/rejected": -0.37245288491249084,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": -1.372422218322754,
|
| 883 |
+
"logits/rejected": -0.3783385157585144,
|
| 884 |
+
"logps/chosen": -720.2787475585938,
|
| 885 |
+
"logps/rejected": -1659.054931640625,
|
| 886 |
+
"loss": 0.1541,
|
| 887 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 888 |
+
"rewards/chosen": -0.09280645102262497,
|
| 889 |
+
"rewards/margins": 0.30042776465415955,
|
| 890 |
+
"rewards/rejected": -0.3932341933250427,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": -1.4179317951202393,
|
| 897 |
+
"logits/rejected": -0.7052455544471741,
|
| 898 |
+
"logps/chosen": -801.2463989257812,
|
| 899 |
+
"logps/rejected": -1756.431884765625,
|
| 900 |
+
"loss": 0.169,
|
| 901 |
+
"rewards/accuracies": 0.925000011920929,
|
| 902 |
+
"rewards/chosen": -0.1531040519475937,
|
| 903 |
+
"rewards/margins": 0.31313425302505493,
|
| 904 |
+
"rewards/rejected": -0.4662383496761322,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": -1.1481022834777832,
|
| 911 |
+
"logits/rejected": 0.5914746522903442,
|
| 912 |
+
"logps/chosen": -755.81103515625,
|
| 913 |
+
"logps/rejected": -1772.6920166015625,
|
| 914 |
+
"loss": 0.2111,
|
| 915 |
+
"rewards/accuracies": 0.800000011920929,
|
| 916 |
+
"rewards/chosen": -0.15703272819519043,
|
| 917 |
+
"rewards/margins": 0.31566134095191956,
|
| 918 |
+
"rewards/rejected": -0.47269406914711,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": -1.2507625818252563,
|
| 925 |
+
"logits/rejected": -0.3694377839565277,
|
| 926 |
+
"logps/chosen": -659.0304565429688,
|
| 927 |
+
"logps/rejected": -1531.488525390625,
|
| 928 |
+
"loss": 0.1981,
|
| 929 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 930 |
+
"rewards/chosen": -0.08185335248708725,
|
| 931 |
+
"rewards/margins": 0.20337195694446564,
|
| 932 |
+
"rewards/rejected": -0.2852253317832947,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": -1.4763983488082886,
|
| 939 |
+
"logits/rejected": -0.03595398738980293,
|
| 940 |
+
"logps/chosen": -728.7596435546875,
|
| 941 |
+
"logps/rejected": -1576.779052734375,
|
| 942 |
+
"loss": 0.1871,
|
| 943 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 944 |
+
"rewards/chosen": -0.1268945336341858,
|
| 945 |
+
"rewards/margins": 0.21409745514392853,
|
| 946 |
+
"rewards/rejected": -0.3409919738769531,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": -1.0833264589309692,
|
| 953 |
+
"logits/rejected": -0.46659836173057556,
|
| 954 |
+
"logps/chosen": -780.9652099609375,
|
| 955 |
+
"logps/rejected": -1779.447998046875,
|
| 956 |
+
"loss": 0.1612,
|
| 957 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 958 |
+
"rewards/chosen": -0.17059431970119476,
|
| 959 |
+
"rewards/margins": 0.328458696603775,
|
| 960 |
+
"rewards/rejected": -0.4990530014038086,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": -1.399720549583435,
|
| 967 |
+
"logits/rejected": -0.561631977558136,
|
| 968 |
+
"logps/chosen": -789.7105102539062,
|
| 969 |
+
"logps/rejected": -1804.3443603515625,
|
| 970 |
+
"loss": 0.1701,
|
| 971 |
+
"rewards/accuracies": 0.875,
|
| 972 |
+
"rewards/chosen": -0.12060783058404922,
|
| 973 |
+
"rewards/margins": 0.3465253710746765,
|
| 974 |
+
"rewards/rejected": -0.46713313460350037,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": -1.2853963375091553,
|
| 981 |
+
"logits/rejected": -0.2969803214073181,
|
| 982 |
+
"logps/chosen": -711.6168823242188,
|
| 983 |
+
"logps/rejected": -1566.543701171875,
|
| 984 |
+
"loss": 0.1855,
|
| 985 |
+
"rewards/accuracies": 0.699999988079071,
|
| 986 |
+
"rewards/chosen": -0.159945547580719,
|
| 987 |
+
"rewards/margins": 0.22837324440479279,
|
| 988 |
+
"rewards/rejected": -0.3883187770843506,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": -1.2532896995544434,
|
| 995 |
+
"logits/rejected": -0.5551369786262512,
|
| 996 |
+
"logps/chosen": -636.3924560546875,
|
| 997 |
+
"logps/rejected": -1902.0989990234375,
|
| 998 |
+
"loss": 0.17,
|
| 999 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1000 |
+
"rewards/chosen": -0.1209067553281784,
|
| 1001 |
+
"rewards/margins": 0.3948102295398712,
|
| 1002 |
+
"rewards/rejected": -0.5157170295715332,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": -1.4191337823867798,
|
| 1009 |
+
"logits/rejected": -0.11001946777105331,
|
| 1010 |
+
"logps/chosen": -713.93212890625,
|
| 1011 |
+
"logps/rejected": -1656.491943359375,
|
| 1012 |
+
"loss": 0.1692,
|
| 1013 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1014 |
+
"rewards/chosen": -0.07871367037296295,
|
| 1015 |
+
"rewards/margins": 0.2747347354888916,
|
| 1016 |
+
"rewards/rejected": -0.35344842076301575,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": -1.3239977359771729,
|
| 1023 |
+
"logits/rejected": -0.34808486700057983,
|
| 1024 |
+
"logps/chosen": -781.5916137695312,
|
| 1025 |
+
"logps/rejected": -1643.9801025390625,
|
| 1026 |
+
"loss": 0.1728,
|
| 1027 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1028 |
+
"rewards/chosen": -0.1793273687362671,
|
| 1029 |
+
"rewards/margins": 0.2667609453201294,
|
| 1030 |
+
"rewards/rejected": -0.4460883140563965,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": -1.5411983728408813,
|
| 1037 |
+
"logits/rejected": -0.2094588726758957,
|
| 1038 |
+
"logps/chosen": -853.9683837890625,
|
| 1039 |
+
"logps/rejected": -1529.486572265625,
|
| 1040 |
+
"loss": 0.8403,
|
| 1041 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1042 |
+
"rewards/chosen": -0.16295142471790314,
|
| 1043 |
+
"rewards/margins": 0.15665379166603088,
|
| 1044 |
+
"rewards/rejected": -0.3196052312850952,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": -1.6163041591644287,
|
| 1051 |
+
"logits/rejected": -0.5802554488182068,
|
| 1052 |
+
"logps/chosen": -680.8773193359375,
|
| 1053 |
+
"logps/rejected": -1595.187744140625,
|
| 1054 |
+
"loss": 0.247,
|
| 1055 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1056 |
+
"rewards/chosen": -0.054552387446165085,
|
| 1057 |
+
"rewards/margins": 0.15820157527923584,
|
| 1058 |
+
"rewards/rejected": -0.21275396645069122,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": -1.4396401643753052,
|
| 1065 |
+
"logits/rejected": -0.4410804212093353,
|
| 1066 |
+
"logps/chosen": -692.0823974609375,
|
| 1067 |
+
"logps/rejected": -1640.334228515625,
|
| 1068 |
+
"loss": 0.2633,
|
| 1069 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1070 |
+
"rewards/chosen": -0.04884466528892517,
|
| 1071 |
+
"rewards/margins": 0.16748689115047455,
|
| 1072 |
+
"rewards/rejected": -0.2163315713405609,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": -1.5297174453735352,
|
| 1079 |
+
"logits/rejected": -0.6668530106544495,
|
| 1080 |
+
"logps/chosen": -611.5433349609375,
|
| 1081 |
+
"logps/rejected": -1556.078125,
|
| 1082 |
+
"loss": 0.2196,
|
| 1083 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1084 |
+
"rewards/chosen": -0.033245183527469635,
|
| 1085 |
+
"rewards/margins": 0.21886444091796875,
|
| 1086 |
+
"rewards/rejected": -0.2521096169948578,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": -1.5771548748016357,
|
| 1093 |
+
"logits/rejected": -0.4002736508846283,
|
| 1094 |
+
"logps/chosen": -641.4221801757812,
|
| 1095 |
+
"logps/rejected": -1400.081298828125,
|
| 1096 |
+
"loss": 0.2114,
|
| 1097 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1098 |
+
"rewards/chosen": -0.03950526565313339,
|
| 1099 |
+
"rewards/margins": 0.1628362238407135,
|
| 1100 |
+
"rewards/rejected": -0.2023414820432663,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": -1.587998628616333,
|
| 1107 |
+
"logits/rejected": -0.8064206838607788,
|
| 1108 |
+
"logps/chosen": -660.1177978515625,
|
| 1109 |
+
"logps/rejected": -1664.508056640625,
|
| 1110 |
+
"loss": 0.2068,
|
| 1111 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1112 |
+
"rewards/chosen": -0.0692194476723671,
|
| 1113 |
+
"rewards/margins": 0.28254234790802,
|
| 1114 |
+
"rewards/rejected": -0.3517618179321289,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": -1.5779733657836914,
|
| 1121 |
+
"logits/rejected": -0.9056744575500488,
|
| 1122 |
+
"logps/chosen": -644.6177978515625,
|
| 1123 |
+
"logps/rejected": -1487.890869140625,
|
| 1124 |
+
"loss": 0.1864,
|
| 1125 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1126 |
+
"rewards/chosen": -0.09771857410669327,
|
| 1127 |
+
"rewards/margins": 0.18923287093639374,
|
| 1128 |
+
"rewards/rejected": -0.2869514524936676,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": -1.4548509120941162,
|
| 1135 |
+
"logits/rejected": -0.490948349237442,
|
| 1136 |
+
"logps/chosen": -806.4798583984375,
|
| 1137 |
+
"logps/rejected": -1708.6116943359375,
|
| 1138 |
+
"loss": 0.1662,
|
| 1139 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1140 |
+
"rewards/chosen": -0.1382991373538971,
|
| 1141 |
+
"rewards/margins": 0.2544620931148529,
|
| 1142 |
+
"rewards/rejected": -0.3927612006664276,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": -1.2813379764556885,
|
| 1149 |
+
"logits/rejected": -0.6146308183670044,
|
| 1150 |
+
"logps/chosen": -652.1132202148438,
|
| 1151 |
+
"logps/rejected": -1596.59619140625,
|
| 1152 |
+
"loss": 0.2302,
|
| 1153 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1154 |
+
"rewards/chosen": -0.10586214065551758,
|
| 1155 |
+
"rewards/margins": 0.2745637595653534,
|
| 1156 |
+
"rewards/rejected": -0.38042590022087097,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": -1.5315301418304443,
|
| 1163 |
+
"logits/rejected": -0.7480667233467102,
|
| 1164 |
+
"logps/chosen": -580.1861572265625,
|
| 1165 |
+
"logps/rejected": -1714.6907958984375,
|
| 1166 |
+
"loss": 0.1641,
|
| 1167 |
+
"rewards/accuracies": 0.875,
|
| 1168 |
+
"rewards/chosen": -0.04294740408658981,
|
| 1169 |
+
"rewards/margins": 0.34141218662261963,
|
| 1170 |
+
"rewards/rejected": -0.38435959815979004,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": -1.462127447128296,
|
| 1177 |
+
"logits/rejected": -0.8618795275688171,
|
| 1178 |
+
"logps/chosen": -741.3155517578125,
|
| 1179 |
+
"logps/rejected": -1888.650146484375,
|
| 1180 |
+
"loss": 0.1266,
|
| 1181 |
+
"rewards/accuracies": 0.949999988079071,
|
| 1182 |
+
"rewards/chosen": -0.09163922816514969,
|
| 1183 |
+
"rewards/margins": 0.3773654103279114,
|
| 1184 |
+
"rewards/rejected": -0.46900463104248047,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": -1.6406835317611694,
|
| 1191 |
+
"logits/rejected": -0.5775340795516968,
|
| 1192 |
+
"logps/chosen": -797.4598999023438,
|
| 1193 |
+
"logps/rejected": -1779.310302734375,
|
| 1194 |
+
"loss": 0.1442,
|
| 1195 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1196 |
+
"rewards/chosen": -0.11959085613489151,
|
| 1197 |
+
"rewards/margins": 0.32207822799682617,
|
| 1198 |
+
"rewards/rejected": -0.4416690468788147,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": -1.3674832582473755,
|
| 1205 |
+
"logits/rejected": -0.03007361851632595,
|
| 1206 |
+
"logps/chosen": -736.8541870117188,
|
| 1207 |
+
"logps/rejected": -1707.4468994140625,
|
| 1208 |
+
"loss": 0.1866,
|
| 1209 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1210 |
+
"rewards/chosen": -0.08552592992782593,
|
| 1211 |
+
"rewards/margins": 0.30176034569740295,
|
| 1212 |
+
"rewards/rejected": -0.3872862458229065,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": -1.206857442855835,
|
| 1219 |
+
"logits/rejected": -0.4066374897956848,
|
| 1220 |
+
"logps/chosen": -732.4100341796875,
|
| 1221 |
+
"logps/rejected": -1567.50048828125,
|
| 1222 |
+
"loss": 0.193,
|
| 1223 |
+
"rewards/accuracies": 0.75,
|
| 1224 |
+
"rewards/chosen": -0.09428885579109192,
|
| 1225 |
+
"rewards/margins": 0.255453884601593,
|
| 1226 |
+
"rewards/rejected": -0.34974271059036255,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": -1.2475948333740234,
|
| 1233 |
+
"logits/rejected": -0.3390772342681885,
|
| 1234 |
+
"logps/chosen": -550.7503662109375,
|
| 1235 |
+
"logps/rejected": -1530.1998291015625,
|
| 1236 |
+
"loss": 0.1633,
|
| 1237 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1238 |
+
"rewards/chosen": -0.018922504037618637,
|
| 1239 |
+
"rewards/margins": 0.2624686658382416,
|
| 1240 |
+
"rewards/rejected": -0.2813911437988281,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": -1.1934720277786255,
|
| 1247 |
+
"logits/rejected": -0.11626192182302475,
|
| 1248 |
+
"logps/chosen": -602.2255859375,
|
| 1249 |
+
"logps/rejected": -1660.957763671875,
|
| 1250 |
+
"loss": 0.1537,
|
| 1251 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1252 |
+
"rewards/chosen": -0.03315038979053497,
|
| 1253 |
+
"rewards/margins": 0.32097241282463074,
|
| 1254 |
+
"rewards/rejected": -0.3541228175163269,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": -1.501976728439331,
|
| 1261 |
+
"logits/rejected": -0.6784012913703918,
|
| 1262 |
+
"logps/chosen": -589.7467041015625,
|
| 1263 |
+
"logps/rejected": -1566.115478515625,
|
| 1264 |
+
"loss": 0.1589,
|
| 1265 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1266 |
+
"rewards/chosen": -0.06981668621301651,
|
| 1267 |
+
"rewards/margins": 0.30536967515945435,
|
| 1268 |
+
"rewards/rejected": -0.3751864433288574,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": -1.683624267578125,
|
| 1275 |
+
"logits/rejected": -0.6069055795669556,
|
| 1276 |
+
"logps/chosen": -765.5227661132812,
|
| 1277 |
+
"logps/rejected": -1787.843017578125,
|
| 1278 |
+
"loss": 0.1679,
|
| 1279 |
+
"rewards/accuracies": 0.875,
|
| 1280 |
+
"rewards/chosen": -0.0950092300772667,
|
| 1281 |
+
"rewards/margins": 0.34752824902534485,
|
| 1282 |
+
"rewards/rejected": -0.44253745675086975,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": -1.5381743907928467,
|
| 1289 |
+
"logits/rejected": -0.275674045085907,
|
| 1290 |
+
"logps/chosen": -740.3082885742188,
|
| 1291 |
+
"logps/rejected": -1551.924560546875,
|
| 1292 |
+
"loss": 0.169,
|
| 1293 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1294 |
+
"rewards/chosen": -0.12154094874858856,
|
| 1295 |
+
"rewards/margins": 0.24538445472717285,
|
| 1296 |
+
"rewards/rejected": -0.3669254183769226,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": -1.3017113208770752,
|
| 1303 |
+
"logits/rejected": -0.47879767417907715,
|
| 1304 |
+
"logps/chosen": -677.2306518554688,
|
| 1305 |
+
"logps/rejected": -1834.7994384765625,
|
| 1306 |
+
"loss": 0.1478,
|
| 1307 |
+
"rewards/accuracies": 0.875,
|
| 1308 |
+
"rewards/chosen": -0.09329520165920258,
|
| 1309 |
+
"rewards/margins": 0.37344565987586975,
|
| 1310 |
+
"rewards/rejected": -0.4667409062385559,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": -1.5965297222137451,
|
| 1317 |
+
"logits/rejected": -0.08967357873916626,
|
| 1318 |
+
"logps/chosen": -750.0841064453125,
|
| 1319 |
+
"logps/rejected": -1768.0572509765625,
|
| 1320 |
+
"loss": 0.1495,
|
| 1321 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1322 |
+
"rewards/chosen": -0.0852770283818245,
|
| 1323 |
+
"rewards/margins": 0.3263811767101288,
|
| 1324 |
+
"rewards/rejected": -0.4116581380367279,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": -1.5777353048324585,
|
| 1331 |
+
"logits/rejected": -0.23106975853443146,
|
| 1332 |
+
"logps/chosen": -790.501953125,
|
| 1333 |
+
"logps/rejected": -1668.7314453125,
|
| 1334 |
+
"loss": 0.2048,
|
| 1335 |
+
"rewards/accuracies": 0.75,
|
| 1336 |
+
"rewards/chosen": -0.14181482791900635,
|
| 1337 |
+
"rewards/margins": 0.2708645462989807,
|
| 1338 |
+
"rewards/rejected": -0.41267937421798706,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": -1.1467679738998413,
|
| 1345 |
+
"logits/rejected": 0.07232928276062012,
|
| 1346 |
+
"logps/chosen": -592.8287963867188,
|
| 1347 |
+
"logps/rejected": -1479.1529541015625,
|
| 1348 |
+
"loss": 0.1978,
|
| 1349 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1350 |
+
"rewards/chosen": -0.032741207629442215,
|
| 1351 |
+
"rewards/margins": 0.26754575967788696,
|
| 1352 |
+
"rewards/rejected": -0.3002869486808777,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": -1.6411889791488647,
|
| 1359 |
+
"logits/rejected": -0.334705650806427,
|
| 1360 |
+
"logps/chosen": -637.6863403320312,
|
| 1361 |
+
"logps/rejected": -1307.0592041015625,
|
| 1362 |
+
"loss": 0.1838,
|
| 1363 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1364 |
+
"rewards/chosen": -0.059777967631816864,
|
| 1365 |
+
"rewards/margins": 0.1975717544555664,
|
| 1366 |
+
"rewards/rejected": -0.25734972953796387,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": -1.4477770328521729,
|
| 1373 |
+
"logits/rejected": -0.447587788105011,
|
| 1374 |
+
"logps/chosen": -725.3448486328125,
|
| 1375 |
+
"logps/rejected": -1688.343994140625,
|
| 1376 |
+
"loss": 0.1638,
|
| 1377 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1378 |
+
"rewards/chosen": -0.07935594022274017,
|
| 1379 |
+
"rewards/margins": 0.2956528663635254,
|
| 1380 |
+
"rewards/rejected": -0.37500879168510437,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": -1.441928505897522,
|
| 1387 |
+
"logits/rejected": -0.4485958516597748,
|
| 1388 |
+
"logps/chosen": -674.2760620117188,
|
| 1389 |
+
"logps/rejected": -1747.831787109375,
|
| 1390 |
+
"loss": 0.1706,
|
| 1391 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1392 |
+
"rewards/chosen": -0.04113630950450897,
|
| 1393 |
+
"rewards/margins": 0.3252195417881012,
|
| 1394 |
+
"rewards/rejected": -0.366355836391449,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": -1.560974359512329,
|
| 1401 |
+
"logits/rejected": -0.35725072026252747,
|
| 1402 |
+
"logps/chosen": -719.2286376953125,
|
| 1403 |
+
"logps/rejected": -1786.9176025390625,
|
| 1404 |
+
"loss": 0.1374,
|
| 1405 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1406 |
+
"rewards/chosen": -0.06295976042747498,
|
| 1407 |
+
"rewards/margins": 0.3578505218029022,
|
| 1408 |
+
"rewards/rejected": -0.4208102822303772,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": -1.5361359119415283,
|
| 1415 |
+
"logits/rejected": -0.5901980996131897,
|
| 1416 |
+
"logps/chosen": -779.523193359375,
|
| 1417 |
+
"logps/rejected": -1766.1044921875,
|
| 1418 |
+
"loss": 0.1344,
|
| 1419 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1420 |
+
"rewards/chosen": -0.07964052259922028,
|
| 1421 |
+
"rewards/margins": 0.3218533396720886,
|
| 1422 |
+
"rewards/rejected": -0.4014938771724701,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": -1.3095166683197021,
|
| 1429 |
+
"logits/rejected": -0.6045408248901367,
|
| 1430 |
+
"logps/chosen": -703.9786376953125,
|
| 1431 |
+
"logps/rejected": -1905.917236328125,
|
| 1432 |
+
"loss": 0.1328,
|
| 1433 |
+
"rewards/accuracies": 0.949999988079071,
|
| 1434 |
+
"rewards/chosen": -0.08165670931339264,
|
| 1435 |
+
"rewards/margins": 0.39877375960350037,
|
| 1436 |
+
"rewards/rejected": -0.4804305136203766,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": -1.4772388935089111,
|
| 1443 |
+
"logits/rejected": -0.006365871522575617,
|
| 1444 |
+
"logps/chosen": -647.6913452148438,
|
| 1445 |
+
"logps/rejected": -1643.7066650390625,
|
| 1446 |
+
"loss": 0.1533,
|
| 1447 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1448 |
+
"rewards/chosen": -0.08445201814174652,
|
| 1449 |
+
"rewards/margins": 0.3088130056858063,
|
| 1450 |
+
"rewards/rejected": -0.3932650089263916,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": -1.480623483657837,
|
| 1457 |
+
"logits/rejected": -0.7142573595046997,
|
| 1458 |
+
"logps/chosen": -687.6082763671875,
|
| 1459 |
+
"logps/rejected": -1855.853515625,
|
| 1460 |
+
"loss": 0.1823,
|
| 1461 |
+
"rewards/accuracies": 0.949999988079071,
|
| 1462 |
+
"rewards/chosen": -0.10191044956445694,
|
| 1463 |
+
"rewards/margins": 0.38636595010757446,
|
| 1464 |
+
"rewards/rejected": -0.48827633261680603,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": -1.3591618537902832,
|
| 1471 |
+
"logits/rejected": -0.5336927771568298,
|
| 1472 |
+
"logps/chosen": -549.4283447265625,
|
| 1473 |
+
"logps/rejected": -1634.71240234375,
|
| 1474 |
+
"loss": 0.1329,
|
| 1475 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1476 |
+
"rewards/chosen": -0.05249984189867973,
|
| 1477 |
+
"rewards/margins": 0.3793482184410095,
|
| 1478 |
+
"rewards/rejected": -0.43184810876846313,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": -1.6825790405273438,
|
| 1485 |
+
"logits/rejected": -0.8754396438598633,
|
| 1486 |
+
"logps/chosen": -707.4894409179688,
|
| 1487 |
+
"logps/rejected": -1693.762939453125,
|
| 1488 |
+
"loss": 0.1264,
|
| 1489 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1490 |
+
"rewards/chosen": -0.05124876648187637,
|
| 1491 |
+
"rewards/margins": 0.3190692365169525,
|
| 1492 |
+
"rewards/rejected": -0.3703179955482483,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": -1.4010018110275269,
|
| 1499 |
+
"logits/rejected": -0.7923344373703003,
|
| 1500 |
+
"logps/chosen": -623.4701538085938,
|
| 1501 |
+
"logps/rejected": -1506.981689453125,
|
| 1502 |
+
"loss": 0.1948,
|
| 1503 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1504 |
+
"rewards/chosen": -0.061522554606199265,
|
| 1505 |
+
"rewards/margins": 0.23432263731956482,
|
| 1506 |
+
"rewards/rejected": -0.2958451807498932,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": -1.5388412475585938,
|
| 1513 |
+
"logits/rejected": -0.185507133603096,
|
| 1514 |
+
"logps/chosen": -622.5823974609375,
|
| 1515 |
+
"logps/rejected": -1469.159912109375,
|
| 1516 |
+
"loss": 0.2035,
|
| 1517 |
+
"rewards/accuracies": 0.75,
|
| 1518 |
+
"rewards/chosen": -0.07265051454305649,
|
| 1519 |
+
"rewards/margins": 0.2589751183986664,
|
| 1520 |
+
"rewards/rejected": -0.33162569999694824,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": -1.4987528324127197,
|
| 1527 |
+
"logits/rejected": -0.6492592096328735,
|
| 1528 |
+
"logps/chosen": -629.9580078125,
|
| 1529 |
+
"logps/rejected": -1712.423095703125,
|
| 1530 |
+
"loss": 0.1277,
|
| 1531 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1532 |
+
"rewards/chosen": -0.05187363177537918,
|
| 1533 |
+
"rewards/margins": 0.3656329810619354,
|
| 1534 |
+
"rewards/rejected": -0.417506605386734,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": -1.4696351289749146,
|
| 1541 |
+
"logits/rejected": -0.2756325900554657,
|
| 1542 |
+
"logps/chosen": -624.1102294921875,
|
| 1543 |
+
"logps/rejected": -1571.719482421875,
|
| 1544 |
+
"loss": 0.1663,
|
| 1545 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1546 |
+
"rewards/chosen": -0.03262772411108017,
|
| 1547 |
+
"rewards/margins": 0.2939130663871765,
|
| 1548 |
+
"rewards/rejected": -0.3265407681465149,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": -1.5407931804656982,
|
| 1555 |
+
"logits/rejected": -0.6150112152099609,
|
| 1556 |
+
"logps/chosen": -606.6552734375,
|
| 1557 |
+
"logps/rejected": -1499.91455078125,
|
| 1558 |
+
"loss": 0.2052,
|
| 1559 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1560 |
+
"rewards/chosen": -0.047359392046928406,
|
| 1561 |
+
"rewards/margins": 0.25734394788742065,
|
| 1562 |
+
"rewards/rejected": -0.30470338463783264,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": -1.5111992359161377,
|
| 1569 |
+
"logits/rejected": -0.6662728786468506,
|
| 1570 |
+
"logps/chosen": -630.7785034179688,
|
| 1571 |
+
"logps/rejected": -1606.4742431640625,
|
| 1572 |
+
"loss": 0.1755,
|
| 1573 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1574 |
+
"rewards/chosen": -0.04623417183756828,
|
| 1575 |
+
"rewards/margins": 0.32483187317848206,
|
| 1576 |
+
"rewards/rejected": -0.37106603384017944,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": -1.3981125354766846,
|
| 1583 |
+
"logits/rejected": -0.36660924553871155,
|
| 1584 |
+
"logps/chosen": -675.8720092773438,
|
| 1585 |
+
"logps/rejected": -1751.074462890625,
|
| 1586 |
+
"loss": 0.1254,
|
| 1587 |
+
"rewards/accuracies": 0.875,
|
| 1588 |
+
"rewards/chosen": -0.03159493952989578,
|
| 1589 |
+
"rewards/margins": 0.329929918050766,
|
| 1590 |
+
"rewards/rejected": -0.3615248203277588,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": -1.5726184844970703,
|
| 1597 |
+
"logits/rejected": -0.76716148853302,
|
| 1598 |
+
"logps/chosen": -569.0755004882812,
|
| 1599 |
+
"logps/rejected": -1726.5882568359375,
|
| 1600 |
+
"loss": 0.1363,
|
| 1601 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1602 |
+
"rewards/chosen": -0.014021654613316059,
|
| 1603 |
+
"rewards/margins": 0.37932100892066956,
|
| 1604 |
+
"rewards/rejected": -0.39334264397621155,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": -1.3213517665863037,
|
| 1611 |
+
"logits/rejected": -0.7754068374633789,
|
| 1612 |
+
"logps/chosen": -576.7313232421875,
|
| 1613 |
+
"logps/rejected": -1728.904541015625,
|
| 1614 |
+
"loss": 0.1591,
|
| 1615 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1616 |
+
"rewards/chosen": -0.05365558713674545,
|
| 1617 |
+
"rewards/margins": 0.3717700242996216,
|
| 1618 |
+
"rewards/rejected": -0.42542558908462524,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": -1.4281871318817139,
|
| 1625 |
+
"logits/rejected": -0.8301714658737183,
|
| 1626 |
+
"logps/chosen": -587.6362915039062,
|
| 1627 |
+
"logps/rejected": -1682.287109375,
|
| 1628 |
+
"loss": 0.1537,
|
| 1629 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1630 |
+
"rewards/chosen": -0.04957905039191246,
|
| 1631 |
+
"rewards/margins": 0.3476232886314392,
|
| 1632 |
+
"rewards/rejected": -0.39720237255096436,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": -1.2723270654678345,
|
| 1639 |
+
"logits/rejected": -0.2873464524745941,
|
| 1640 |
+
"logps/chosen": -679.1395263671875,
|
| 1641 |
+
"logps/rejected": -1777.858154296875,
|
| 1642 |
+
"loss": 0.1868,
|
| 1643 |
+
"rewards/accuracies": 0.925000011920929,
|
| 1644 |
+
"rewards/chosen": -0.02069082297384739,
|
| 1645 |
+
"rewards/margins": 0.3992442190647125,
|
| 1646 |
+
"rewards/rejected": -0.41993504762649536,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": -1.1864560842514038,
|
| 1653 |
+
"logits/rejected": -0.4859984815120697,
|
| 1654 |
+
"logps/chosen": -683.1911010742188,
|
| 1655 |
+
"logps/rejected": -1602.1019287109375,
|
| 1656 |
+
"loss": 0.1687,
|
| 1657 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1658 |
+
"rewards/chosen": -0.018726080656051636,
|
| 1659 |
+
"rewards/margins": 0.29654327034950256,
|
| 1660 |
+
"rewards/rejected": -0.3152693212032318,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": -1.0037411451339722,
|
| 1667 |
+
"logits/rejected": 0.02554410696029663,
|
| 1668 |
+
"logps/chosen": -579.2996826171875,
|
| 1669 |
+
"logps/rejected": -1649.9722900390625,
|
| 1670 |
+
"loss": 0.1673,
|
| 1671 |
+
"rewards/accuracies": 0.875,
|
| 1672 |
+
"rewards/chosen": -0.02113654837012291,
|
| 1673 |
+
"rewards/margins": 0.3451305031776428,
|
| 1674 |
+
"rewards/rejected": -0.36626705527305603,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": -1.3622825145721436,
|
| 1681 |
+
"logits/rejected": -0.4110015332698822,
|
| 1682 |
+
"logps/chosen": -589.6905517578125,
|
| 1683 |
+
"logps/rejected": -1514.8289794921875,
|
| 1684 |
+
"loss": 0.1964,
|
| 1685 |
+
"rewards/accuracies": 0.75,
|
| 1686 |
+
"rewards/chosen": -0.05109922215342522,
|
| 1687 |
+
"rewards/margins": 0.2517136335372925,
|
| 1688 |
+
"rewards/rejected": -0.3028128147125244,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": -1.5205695629119873,
|
| 1695 |
+
"logits/rejected": -0.16487915813922882,
|
| 1696 |
+
"logps/chosen": -619.509521484375,
|
| 1697 |
+
"logps/rejected": -1595.480712890625,
|
| 1698 |
+
"loss": 0.1832,
|
| 1699 |
+
"rewards/accuracies": 0.875,
|
| 1700 |
+
"rewards/chosen": -0.04752761498093605,
|
| 1701 |
+
"rewards/margins": 0.3229573965072632,
|
| 1702 |
+
"rewards/rejected": -0.37048497796058655,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": -1.4372893571853638,
|
| 1709 |
+
"logits/rejected": -0.820128321647644,
|
| 1710 |
+
"logps/chosen": -563.7713623046875,
|
| 1711 |
+
"logps/rejected": -1725.425048828125,
|
| 1712 |
+
"loss": 0.1289,
|
| 1713 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1714 |
+
"rewards/chosen": -0.05251551419496536,
|
| 1715 |
+
"rewards/margins": 0.3404791057109833,
|
| 1716 |
+
"rewards/rejected": -0.3929946720600128,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": -1.4803403615951538,
|
| 1723 |
+
"logits/rejected": -0.7152812480926514,
|
| 1724 |
+
"logps/chosen": -526.8184814453125,
|
| 1725 |
+
"logps/rejected": -1638.043212890625,
|
| 1726 |
+
"loss": 0.1768,
|
| 1727 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1728 |
+
"rewards/chosen": -0.02356002852320671,
|
| 1729 |
+
"rewards/margins": 0.35318613052368164,
|
| 1730 |
+
"rewards/rejected": -0.37674617767333984,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": -1.5741603374481201,
|
| 1737 |
+
"logits/rejected": -0.42631644010543823,
|
| 1738 |
+
"logps/chosen": -597.0006103515625,
|
| 1739 |
+
"logps/rejected": -1670.453369140625,
|
| 1740 |
+
"loss": 0.1572,
|
| 1741 |
+
"rewards/accuracies": 0.875,
|
| 1742 |
+
"rewards/chosen": -0.043170906603336334,
|
| 1743 |
+
"rewards/margins": 0.3142518401145935,
|
| 1744 |
+
"rewards/rejected": -0.35742273926734924,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": -1.4529565572738647,
|
| 1751 |
+
"logits/rejected": -0.5520704984664917,
|
| 1752 |
+
"logps/chosen": -587.2677001953125,
|
| 1753 |
+
"logps/rejected": -1800.4755859375,
|
| 1754 |
+
"loss": 0.1516,
|
| 1755 |
+
"rewards/accuracies": 0.925000011920929,
|
| 1756 |
+
"rewards/chosen": -0.017983034253120422,
|
| 1757 |
+
"rewards/margins": 0.37644895911216736,
|
| 1758 |
+
"rewards/rejected": -0.39443203806877136,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": -1.5385555028915405,
|
| 1765 |
+
"logits/rejected": -0.7931126952171326,
|
| 1766 |
+
"logps/chosen": -644.555419921875,
|
| 1767 |
+
"logps/rejected": -1826.6881103515625,
|
| 1768 |
+
"loss": 0.1694,
|
| 1769 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1770 |
+
"rewards/chosen": -0.06908350437879562,
|
| 1771 |
+
"rewards/margins": 0.3630077540874481,
|
| 1772 |
+
"rewards/rejected": -0.43209123611450195,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": -1.5401626825332642,
|
| 1779 |
+
"logits/rejected": -0.22812063992023468,
|
| 1780 |
+
"logps/chosen": -567.6744384765625,
|
| 1781 |
+
"logps/rejected": -1582.8587646484375,
|
| 1782 |
+
"loss": 0.1796,
|
| 1783 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1784 |
+
"rewards/chosen": -0.0517122745513916,
|
| 1785 |
+
"rewards/margins": 0.33719173073768616,
|
| 1786 |
+
"rewards/rejected": -0.38890397548675537,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": -1.204032301902771,
|
| 1793 |
+
"logits/rejected": -0.2607814073562622,
|
| 1794 |
+
"logps/chosen": -608.66015625,
|
| 1795 |
+
"logps/rejected": -1682.341796875,
|
| 1796 |
+
"loss": 0.1114,
|
| 1797 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1798 |
+
"rewards/chosen": -0.014287752099335194,
|
| 1799 |
+
"rewards/margins": 0.3475797176361084,
|
| 1800 |
+
"rewards/rejected": -0.3618674874305725,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": -1.3903391361236572,
|
| 1807 |
+
"logits/rejected": -0.7587147951126099,
|
| 1808 |
+
"logps/chosen": -676.6446533203125,
|
| 1809 |
+
"logps/rejected": -1709.818603515625,
|
| 1810 |
+
"loss": 0.1956,
|
| 1811 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1812 |
+
"rewards/chosen": -0.056112587451934814,
|
| 1813 |
+
"rewards/margins": 0.281891405582428,
|
| 1814 |
+
"rewards/rejected": -0.3380039930343628,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": -1.519988775253296,
|
| 1821 |
+
"logits/rejected": -1.1464245319366455,
|
| 1822 |
+
"logps/chosen": -668.7023315429688,
|
| 1823 |
+
"logps/rejected": -1754.447265625,
|
| 1824 |
+
"loss": 0.1628,
|
| 1825 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1826 |
+
"rewards/chosen": -0.07075043022632599,
|
| 1827 |
+
"rewards/margins": 0.3179227113723755,
|
| 1828 |
+
"rewards/rejected": -0.38867321610450745,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": -1.45747971534729,
|
| 1835 |
+
"logits/rejected": -0.840915858745575,
|
| 1836 |
+
"logps/chosen": -672.7967529296875,
|
| 1837 |
+
"logps/rejected": -1663.6207275390625,
|
| 1838 |
+
"loss": 0.1768,
|
| 1839 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1840 |
+
"rewards/chosen": -0.05158332735300064,
|
| 1841 |
+
"rewards/margins": 0.32626426219940186,
|
| 1842 |
+
"rewards/rejected": -0.3778475821018219,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": -1.3014637231826782,
|
| 1849 |
+
"logits/rejected": -0.45695143938064575,
|
| 1850 |
+
"logps/chosen": -718.7424926757812,
|
| 1851 |
+
"logps/rejected": -1485.810302734375,
|
| 1852 |
+
"loss": 0.1979,
|
| 1853 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1854 |
+
"rewards/chosen": -0.08161523938179016,
|
| 1855 |
+
"rewards/margins": 0.20484736561775208,
|
| 1856 |
+
"rewards/rejected": -0.28646257519721985,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": -1.557997465133667,
|
| 1863 |
+
"logits/rejected": 0.1897609382867813,
|
| 1864 |
+
"logps/chosen": -638.6654052734375,
|
| 1865 |
+
"logps/rejected": -1694.9169921875,
|
| 1866 |
+
"loss": 0.1563,
|
| 1867 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1868 |
+
"rewards/chosen": -0.0795014351606369,
|
| 1869 |
+
"rewards/margins": 0.33878716826438904,
|
| 1870 |
+
"rewards/rejected": -0.41828861832618713,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": -1.5720739364624023,
|
| 1877 |
+
"logits/rejected": -0.3039505183696747,
|
| 1878 |
+
"logps/chosen": -629.5435791015625,
|
| 1879 |
+
"logps/rejected": -1699.1048583984375,
|
| 1880 |
+
"loss": 0.1449,
|
| 1881 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1882 |
+
"rewards/chosen": -0.02949734404683113,
|
| 1883 |
+
"rewards/margins": 0.3422970175743103,
|
| 1884 |
+
"rewards/rejected": -0.37179437279701233,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": -1.4923521280288696,
|
| 1891 |
+
"logits/rejected": -0.543735682964325,
|
| 1892 |
+
"logps/chosen": -737.5084838867188,
|
| 1893 |
+
"logps/rejected": -1615.936279296875,
|
| 1894 |
+
"loss": 0.1457,
|
| 1895 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1896 |
+
"rewards/chosen": -0.060771964490413666,
|
| 1897 |
+
"rewards/margins": 0.2899934649467468,
|
| 1898 |
+
"rewards/rejected": -0.3507654070854187,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": -1.5359987020492554,
|
| 1905 |
+
"logits/rejected": -0.2435634583234787,
|
| 1906 |
+
"logps/chosen": -701.9688720703125,
|
| 1907 |
+
"logps/rejected": -1746.5748291015625,
|
| 1908 |
+
"loss": 0.1456,
|
| 1909 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1910 |
+
"rewards/chosen": -0.04527285322546959,
|
| 1911 |
+
"rewards/margins": 0.3345581889152527,
|
| 1912 |
+
"rewards/rejected": -0.3798310160636902,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": -1.4265598058700562,
|
| 1919 |
+
"logits/rejected": -0.9259235262870789,
|
| 1920 |
+
"logps/chosen": -662.4346923828125,
|
| 1921 |
+
"logps/rejected": -1895.0230712890625,
|
| 1922 |
+
"loss": 0.1388,
|
| 1923 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1924 |
+
"rewards/chosen": -0.036455560475587845,
|
| 1925 |
+
"rewards/margins": 0.42975935339927673,
|
| 1926 |
+
"rewards/rejected": -0.46621495485305786,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": -1.4489424228668213,
|
| 1933 |
+
"logits/rejected": -0.3130696713924408,
|
| 1934 |
+
"logps/chosen": -677.5928955078125,
|
| 1935 |
+
"logps/rejected": -1693.2991943359375,
|
| 1936 |
+
"loss": 0.1653,
|
| 1937 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1938 |
+
"rewards/chosen": -0.07123799622058868,
|
| 1939 |
+
"rewards/margins": 0.33964475989341736,
|
| 1940 |
+
"rewards/rejected": -0.41088271141052246,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": -1.332637071609497,
|
| 1947 |
+
"logits/rejected": -0.8693612217903137,
|
| 1948 |
+
"logps/chosen": -744.2261962890625,
|
| 1949 |
+
"logps/rejected": -1811.7154541015625,
|
| 1950 |
+
"loss": 0.1795,
|
| 1951 |
+
"rewards/accuracies": 0.875,
|
| 1952 |
+
"rewards/chosen": -0.06084796041250229,
|
| 1953 |
+
"rewards/margins": 0.39476925134658813,
|
| 1954 |
+
"rewards/rejected": -0.45561712980270386,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": -1.3288590908050537,
|
| 1961 |
+
"logits/rejected": -0.16629138588905334,
|
| 1962 |
+
"logps/chosen": -530.2454833984375,
|
| 1963 |
+
"logps/rejected": -1626.1544189453125,
|
| 1964 |
+
"loss": 0.1609,
|
| 1965 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1966 |
+
"rewards/chosen": -0.031980741769075394,
|
| 1967 |
+
"rewards/margins": 0.3823274075984955,
|
| 1968 |
+
"rewards/rejected": -0.4143081605434418,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": -1.291416883468628,
|
| 1975 |
+
"logits/rejected": -0.6190372705459595,
|
| 1976 |
+
"logps/chosen": -561.5321044921875,
|
| 1977 |
+
"logps/rejected": -1744.47265625,
|
| 1978 |
+
"loss": 0.1245,
|
| 1979 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1980 |
+
"rewards/chosen": -0.05614073947072029,
|
| 1981 |
+
"rewards/margins": 0.41081467270851135,
|
| 1982 |
+
"rewards/rejected": -0.46695536375045776,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": -1.505129098892212,
|
| 1989 |
+
"logits/rejected": -0.4506317973136902,
|
| 1990 |
+
"logps/chosen": -740.1429443359375,
|
| 1991 |
+
"logps/rejected": -1584.6307373046875,
|
| 1992 |
+
"loss": 0.1815,
|
| 1993 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1994 |
+
"rewards/chosen": -0.08272895216941833,
|
| 1995 |
+
"rewards/margins": 0.3045782446861267,
|
| 1996 |
+
"rewards/rejected": -0.38730719685554504,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": -1.6013845205307007,
|
| 2003 |
+
"logits/rejected": -0.6014512777328491,
|
| 2004 |
+
"logps/chosen": -796.7876586914062,
|
| 2005 |
+
"logps/rejected": -1698.9300537109375,
|
| 2006 |
+
"loss": 0.1551,
|
| 2007 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2008 |
+
"rewards/chosen": -0.09957234561443329,
|
| 2009 |
+
"rewards/margins": 0.32322657108306885,
|
| 2010 |
+
"rewards/rejected": -0.42279893159866333,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": -1.514638900756836,
|
| 2017 |
+
"logits/rejected": -0.8343914747238159,
|
| 2018 |
+
"logps/chosen": -563.3963012695312,
|
| 2019 |
+
"logps/rejected": -1506.22509765625,
|
| 2020 |
+
"loss": 0.154,
|
| 2021 |
+
"rewards/accuracies": 0.800000011920929,
|
| 2022 |
+
"rewards/chosen": -0.046018943190574646,
|
| 2023 |
+
"rewards/margins": 0.339202880859375,
|
| 2024 |
+
"rewards/rejected": -0.38522180914878845,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": -1.4705476760864258,
|
| 2031 |
+
"logits/rejected": -0.28175801038742065,
|
| 2032 |
+
"logps/chosen": -615.4827880859375,
|
| 2033 |
+
"logps/rejected": -1487.244873046875,
|
| 2034 |
+
"loss": 0.1992,
|
| 2035 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 2036 |
+
"rewards/chosen": -0.07384703308343887,
|
| 2037 |
+
"rewards/margins": 0.31356969475746155,
|
| 2038 |
+
"rewards/rejected": -0.38741669058799744,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": -1.1992992162704468,
|
| 2045 |
+
"logits/rejected": -0.007973253726959229,
|
| 2046 |
+
"logps/chosen": -689.2235107421875,
|
| 2047 |
+
"logps/rejected": -1613.805419921875,
|
| 2048 |
+
"loss": 0.1647,
|
| 2049 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2050 |
+
"rewards/chosen": -0.06208137422800064,
|
| 2051 |
+
"rewards/margins": 0.2548282742500305,
|
| 2052 |
+
"rewards/rejected": -0.31690964102745056,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": -1.626381278038025,
|
| 2059 |
+
"logits/rejected": -0.5168036222457886,
|
| 2060 |
+
"logps/chosen": -666.3912963867188,
|
| 2061 |
+
"logps/rejected": -1561.929443359375,
|
| 2062 |
+
"loss": 0.1865,
|
| 2063 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2064 |
+
"rewards/chosen": -0.033760882914066315,
|
| 2065 |
+
"rewards/margins": 0.2637539803981781,
|
| 2066 |
+
"rewards/rejected": -0.2975148558616638,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": -1.593224287033081,
|
| 2073 |
+
"logits/rejected": -0.7308230400085449,
|
| 2074 |
+
"logps/chosen": -683.6494750976562,
|
| 2075 |
+
"logps/rejected": -1443.498046875,
|
| 2076 |
+
"loss": 0.1364,
|
| 2077 |
+
"rewards/accuracies": 0.75,
|
| 2078 |
+
"rewards/chosen": -0.04548930376768112,
|
| 2079 |
+
"rewards/margins": 0.2794992923736572,
|
| 2080 |
+
"rewards/rejected": -0.32498857378959656,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": -1.511319637298584,
|
| 2087 |
+
"logits/rejected": -0.5918843150138855,
|
| 2088 |
+
"logps/chosen": -622.5799560546875,
|
| 2089 |
+
"logps/rejected": -1675.676513671875,
|
| 2090 |
+
"loss": 0.1608,
|
| 2091 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2092 |
+
"rewards/chosen": -0.02713722549378872,
|
| 2093 |
+
"rewards/margins": 0.3606105446815491,
|
| 2094 |
+
"rewards/rejected": -0.38774776458740234,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": -1.368607997894287,
|
| 2101 |
+
"logits/rejected": -0.45999422669410706,
|
| 2102 |
+
"logps/chosen": -757.634033203125,
|
| 2103 |
+
"logps/rejected": -1727.1351318359375,
|
| 2104 |
+
"loss": 0.1844,
|
| 2105 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2106 |
+
"rewards/chosen": -0.09356950223445892,
|
| 2107 |
+
"rewards/margins": 0.31011396646499634,
|
| 2108 |
+
"rewards/rejected": -0.40368348360061646,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": -1.2475618124008179,
|
| 2115 |
+
"logits/rejected": -0.4017241895198822,
|
| 2116 |
+
"logps/chosen": -602.7681884765625,
|
| 2117 |
+
"logps/rejected": -1880.391357421875,
|
| 2118 |
+
"loss": 0.1404,
|
| 2119 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2120 |
+
"rewards/chosen": -0.045240744948387146,
|
| 2121 |
+
"rewards/margins": 0.4169200360774994,
|
| 2122 |
+
"rewards/rejected": -0.46216076612472534,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": -1.4531586170196533,
|
| 2129 |
+
"logits/rejected": -0.3959062695503235,
|
| 2130 |
+
"logps/chosen": -570.5740966796875,
|
| 2131 |
+
"logps/rejected": -1546.8111572265625,
|
| 2132 |
+
"loss": 0.1931,
|
| 2133 |
+
"rewards/accuracies": 0.75,
|
| 2134 |
+
"rewards/chosen": -0.03957132622599602,
|
| 2135 |
+
"rewards/margins": 0.31827348470687866,
|
| 2136 |
+
"rewards/rejected": -0.3578447699546814,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": -1.5894256830215454,
|
| 2143 |
+
"logits/rejected": -0.623005747795105,
|
| 2144 |
+
"logps/chosen": -632.9057006835938,
|
| 2145 |
+
"logps/rejected": -1672.952392578125,
|
| 2146 |
+
"loss": 0.1696,
|
| 2147 |
+
"rewards/accuracies": 0.875,
|
| 2148 |
+
"rewards/chosen": -0.04810899868607521,
|
| 2149 |
+
"rewards/margins": 0.34946009516716003,
|
| 2150 |
+
"rewards/rejected": -0.39756911993026733,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": -1.3502144813537598,
|
| 2157 |
+
"logits/rejected": -0.1807008981704712,
|
| 2158 |
+
"logps/chosen": -697.3865356445312,
|
| 2159 |
+
"logps/rejected": -1577.202392578125,
|
| 2160 |
+
"loss": 0.2037,
|
| 2161 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2162 |
+
"rewards/chosen": -0.07229883968830109,
|
| 2163 |
+
"rewards/margins": 0.25227028131484985,
|
| 2164 |
+
"rewards/rejected": -0.32456910610198975,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": -1.3591182231903076,
|
| 2171 |
+
"logits/rejected": 0.20267681777477264,
|
| 2172 |
+
"logps/chosen": -638.6739501953125,
|
| 2173 |
+
"logps/rejected": -1786.9075927734375,
|
| 2174 |
+
"loss": 0.1373,
|
| 2175 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2176 |
+
"rewards/chosen": -0.047617390751838684,
|
| 2177 |
+
"rewards/margins": 0.37514036893844604,
|
| 2178 |
+
"rewards/rejected": -0.42275771498680115,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": -1.493379831314087,
|
| 2185 |
+
"logits/rejected": -0.6154463887214661,
|
| 2186 |
+
"logps/chosen": -659.9649658203125,
|
| 2187 |
+
"logps/rejected": -1666.797607421875,
|
| 2188 |
+
"loss": 0.1751,
|
| 2189 |
+
"rewards/accuracies": 0.800000011920929,
|
| 2190 |
+
"rewards/chosen": -0.07380831241607666,
|
| 2191 |
+
"rewards/margins": 0.35080844163894653,
|
| 2192 |
+
"rewards/rejected": -0.4246167242527008,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": -1.4797322750091553,
|
| 2199 |
+
"logits/rejected": -0.10699132829904556,
|
| 2200 |
+
"logps/chosen": -754.7605590820312,
|
| 2201 |
+
"logps/rejected": -1794.226318359375,
|
| 2202 |
+
"loss": 0.2233,
|
| 2203 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2204 |
+
"rewards/chosen": -0.12164326012134552,
|
| 2205 |
+
"rewards/margins": 0.3239572048187256,
|
| 2206 |
+
"rewards/rejected": -0.4456004500389099,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": -1.5567706823349,
|
| 2213 |
+
"logits/rejected": -0.7062613368034363,
|
| 2214 |
+
"logps/chosen": -536.9071044921875,
|
| 2215 |
+
"logps/rejected": -1462.166015625,
|
| 2216 |
+
"loss": 0.1451,
|
| 2217 |
+
"rewards/accuracies": 0.75,
|
| 2218 |
+
"rewards/chosen": -0.053076934069395065,
|
| 2219 |
+
"rewards/margins": 0.29014062881469727,
|
| 2220 |
+
"rewards/rejected": -0.3432175815105438,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": -1.2004096508026123,
|
| 2227 |
+
"logits/rejected": 0.3028511106967926,
|
| 2228 |
+
"logps/chosen": -590.0845947265625,
|
| 2229 |
+
"logps/rejected": -1635.791259765625,
|
| 2230 |
+
"loss": 0.1189,
|
| 2231 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2232 |
+
"rewards/chosen": -0.05340021103620529,
|
| 2233 |
+
"rewards/margins": 0.3109533488750458,
|
| 2234 |
+
"rewards/rejected": -0.36435359716415405,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": -1.3777801990509033,
|
| 2241 |
+
"logits/rejected": -0.9794471859931946,
|
| 2242 |
+
"logps/chosen": -539.28125,
|
| 2243 |
+
"logps/rejected": -1819.6597900390625,
|
| 2244 |
+
"loss": 0.1304,
|
| 2245 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2246 |
+
"rewards/chosen": -0.03970905393362045,
|
| 2247 |
+
"rewards/margins": 0.4206715524196625,
|
| 2248 |
+
"rewards/rejected": -0.4603806436061859,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": -1.5900253057479858,
|
| 2255 |
+
"logits/rejected": -0.42086416482925415,
|
| 2256 |
+
"logps/chosen": -595.1795043945312,
|
| 2257 |
+
"logps/rejected": -1580.691650390625,
|
| 2258 |
+
"loss": 0.1431,
|
| 2259 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2260 |
+
"rewards/chosen": -0.05671688914299011,
|
| 2261 |
+
"rewards/margins": 0.2946508824825287,
|
| 2262 |
+
"rewards/rejected": -0.3513677716255188,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": -1.5492194890975952,
|
| 2269 |
+
"logits/rejected": -0.7254107594490051,
|
| 2270 |
+
"logps/chosen": -581.7901000976562,
|
| 2271 |
+
"logps/rejected": -1662.1865234375,
|
| 2272 |
+
"loss": 0.1538,
|
| 2273 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2274 |
+
"rewards/chosen": -0.062152404338121414,
|
| 2275 |
+
"rewards/margins": 0.3534555435180664,
|
| 2276 |
+
"rewards/rejected": -0.41560792922973633,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": -1.5322610139846802,
|
| 2283 |
+
"logits/rejected": -0.7641068696975708,
|
| 2284 |
+
"logps/chosen": -629.3922119140625,
|
| 2285 |
+
"logps/rejected": -1690.0902099609375,
|
| 2286 |
+
"loss": 0.1418,
|
| 2287 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2288 |
+
"rewards/chosen": -0.07075804471969604,
|
| 2289 |
+
"rewards/margins": 0.3472130596637726,
|
| 2290 |
+
"rewards/rejected": -0.417971134185791,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": -1.4690418243408203,
|
| 2297 |
+
"logits/rejected": 0.6738583445549011,
|
| 2298 |
+
"logps/chosen": -743.3259887695312,
|
| 2299 |
+
"logps/rejected": -1512.999267578125,
|
| 2300 |
+
"loss": 0.1463,
|
| 2301 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2302 |
+
"rewards/chosen": -0.09778312593698502,
|
| 2303 |
+
"rewards/margins": 0.22856023907661438,
|
| 2304 |
+
"rewards/rejected": -0.326343297958374,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": -1.1898796558380127,
|
| 2311 |
+
"logits/rejected": -0.6296781301498413,
|
| 2312 |
+
"logps/chosen": -518.149658203125,
|
| 2313 |
+
"logps/rejected": -1747.592041015625,
|
| 2314 |
+
"loss": 0.1682,
|
| 2315 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2316 |
+
"rewards/chosen": -0.04969874396920204,
|
| 2317 |
+
"rewards/margins": 0.3809133768081665,
|
| 2318 |
+
"rewards/rejected": -0.43061214685440063,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": -1.4317132234573364,
|
| 2325 |
+
"logits/rejected": -0.8821698427200317,
|
| 2326 |
+
"logps/chosen": -600.8050537109375,
|
| 2327 |
+
"logps/rejected": -1730.260986328125,
|
| 2328 |
+
"loss": 0.1383,
|
| 2329 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2330 |
+
"rewards/chosen": -0.05417864769697189,
|
| 2331 |
+
"rewards/margins": 0.30406099557876587,
|
| 2332 |
+
"rewards/rejected": -0.35823965072631836,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": -1.2985970973968506,
|
| 2339 |
+
"logits/rejected": -0.2940817177295685,
|
| 2340 |
+
"logps/chosen": -608.9534912109375,
|
| 2341 |
+
"logps/rejected": -1598.25341796875,
|
| 2342 |
+
"loss": 0.136,
|
| 2343 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2344 |
+
"rewards/chosen": -0.019482949748635292,
|
| 2345 |
+
"rewards/margins": 0.32808607816696167,
|
| 2346 |
+
"rewards/rejected": -0.3475690186023712,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": -1.2966607809066772,
|
| 2353 |
+
"logits/rejected": -0.3843843936920166,
|
| 2354 |
+
"logps/chosen": -576.9232788085938,
|
| 2355 |
+
"logps/rejected": -1571.2894287109375,
|
| 2356 |
+
"loss": 0.146,
|
| 2357 |
+
"rewards/accuracies": 0.800000011920929,
|
| 2358 |
+
"rewards/chosen": -0.06475577503442764,
|
| 2359 |
+
"rewards/margins": 0.31269264221191406,
|
| 2360 |
+
"rewards/rejected": -0.3774484097957611,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": -1.3799948692321777,
|
| 2367 |
+
"logits/rejected": -0.3981359302997589,
|
| 2368 |
+
"logps/chosen": -604.2813720703125,
|
| 2369 |
+
"logps/rejected": -1830.979248046875,
|
| 2370 |
+
"loss": 0.1423,
|
| 2371 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2372 |
+
"rewards/chosen": -0.0683603435754776,
|
| 2373 |
+
"rewards/margins": 0.379177987575531,
|
| 2374 |
+
"rewards/rejected": -0.4475383162498474,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": -1.4023206233978271,
|
| 2381 |
+
"logits/rejected": -0.3547496497631073,
|
| 2382 |
+
"logps/chosen": -787.7603149414062,
|
| 2383 |
+
"logps/rejected": -1988.9703369140625,
|
| 2384 |
+
"loss": 0.1179,
|
| 2385 |
+
"rewards/accuracies": 1.0,
|
| 2386 |
+
"rewards/chosen": -0.04920545220375061,
|
| 2387 |
+
"rewards/margins": 0.41018810868263245,
|
| 2388 |
+
"rewards/rejected": -0.45939356088638306,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": -1.5553520917892456,
|
| 2395 |
+
"logits/rejected": -0.3330727219581604,
|
| 2396 |
+
"logps/chosen": -664.6277465820312,
|
| 2397 |
+
"logps/rejected": -1760.999755859375,
|
| 2398 |
+
"loss": 0.1363,
|
| 2399 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2400 |
+
"rewards/chosen": -0.040573738515377045,
|
| 2401 |
+
"rewards/margins": 0.36900395154953003,
|
| 2402 |
+
"rewards/rejected": -0.4095776677131653,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": -1.4014623165130615,
|
| 2409 |
+
"logits/rejected": -0.6149917840957642,
|
| 2410 |
+
"logps/chosen": -655.154541015625,
|
| 2411 |
+
"logps/rejected": -1673.4769287109375,
|
| 2412 |
+
"loss": 0.1396,
|
| 2413 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2414 |
+
"rewards/chosen": -0.08275039494037628,
|
| 2415 |
+
"rewards/margins": 0.34146302938461304,
|
| 2416 |
+
"rewards/rejected": -0.4242134690284729,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": -1.4432154893875122,
|
| 2423 |
+
"logits/rejected": -0.2376745045185089,
|
| 2424 |
+
"logps/chosen": -578.2418823242188,
|
| 2425 |
+
"logps/rejected": -1667.619384765625,
|
| 2426 |
+
"loss": 0.122,
|
| 2427 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2428 |
+
"rewards/chosen": -0.06366704404354095,
|
| 2429 |
+
"rewards/margins": 0.3130820393562317,
|
| 2430 |
+
"rewards/rejected": -0.37674909830093384,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": -1.3630592823028564,
|
| 2437 |
+
"logits/rejected": -0.21227815747261047,
|
| 2438 |
+
"logps/chosen": -532.6649169921875,
|
| 2439 |
+
"logps/rejected": -1589.3013916015625,
|
| 2440 |
+
"loss": 0.1758,
|
| 2441 |
+
"rewards/accuracies": 0.875,
|
| 2442 |
+
"rewards/chosen": -0.03975344076752663,
|
| 2443 |
+
"rewards/margins": 0.3338061273097992,
|
| 2444 |
+
"rewards/rejected": -0.37355953454971313,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": -1.54172945022583,
|
| 2451 |
+
"logits/rejected": -0.21348455548286438,
|
| 2452 |
+
"logps/chosen": -780.7069702148438,
|
| 2453 |
+
"logps/rejected": -1701.29296875,
|
| 2454 |
+
"loss": 0.186,
|
| 2455 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2456 |
+
"rewards/chosen": -0.08455196768045425,
|
| 2457 |
+
"rewards/margins": 0.28723907470703125,
|
| 2458 |
+
"rewards/rejected": -0.3717910051345825,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": -1.3796813488006592,
|
| 2465 |
+
"logits/rejected": 0.4848087430000305,
|
| 2466 |
+
"logps/chosen": -621.2150268554688,
|
| 2467 |
+
"logps/rejected": -1688.8896484375,
|
| 2468 |
+
"loss": 0.117,
|
| 2469 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2470 |
+
"rewards/chosen": -0.057764243334531784,
|
| 2471 |
+
"rewards/margins": 0.32786962389945984,
|
| 2472 |
+
"rewards/rejected": -0.3856338858604431,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": -1.475338101387024,
|
| 2479 |
+
"logits/rejected": -0.41871923208236694,
|
| 2480 |
+
"logps/chosen": -615.502685546875,
|
| 2481 |
+
"logps/rejected": -1646.4254150390625,
|
| 2482 |
+
"loss": 0.1425,
|
| 2483 |
+
"rewards/accuracies": 0.875,
|
| 2484 |
+
"rewards/chosen": -0.07283326983451843,
|
| 2485 |
+
"rewards/margins": 0.3077198565006256,
|
| 2486 |
+
"rewards/rejected": -0.38055309653282166,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": -1.38540518283844,
|
| 2493 |
+
"logits/rejected": -0.8147419095039368,
|
| 2494 |
+
"logps/chosen": -595.4188232421875,
|
| 2495 |
+
"logps/rejected": -1683.2845458984375,
|
| 2496 |
+
"loss": 0.1805,
|
| 2497 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2498 |
+
"rewards/chosen": -0.05248613283038139,
|
| 2499 |
+
"rewards/margins": 0.3240980803966522,
|
| 2500 |
+
"rewards/rejected": -0.3765842318534851,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": -1.3075553178787231,
|
| 2507 |
+
"logits/rejected": -0.05613366514444351,
|
| 2508 |
+
"logps/chosen": -711.91357421875,
|
| 2509 |
+
"logps/rejected": -1785.665283203125,
|
| 2510 |
+
"loss": 0.1703,
|
| 2511 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2512 |
+
"rewards/chosen": -0.08939728140830994,
|
| 2513 |
+
"rewards/margins": 0.3216257691383362,
|
| 2514 |
+
"rewards/rejected": -0.4110230505466461,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": -1.4797890186309814,
|
| 2521 |
+
"logits/rejected": 0.0037591219879686832,
|
| 2522 |
+
"logps/chosen": -605.4852905273438,
|
| 2523 |
+
"logps/rejected": -1533.518310546875,
|
| 2524 |
+
"loss": 0.1475,
|
| 2525 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2526 |
+
"rewards/chosen": -0.05776011943817139,
|
| 2527 |
+
"rewards/margins": 0.2979200482368469,
|
| 2528 |
+
"rewards/rejected": -0.3556801676750183,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": -1.4468438625335693,
|
| 2535 |
+
"logits/rejected": -0.6082602739334106,
|
| 2536 |
+
"logps/chosen": -594.7930908203125,
|
| 2537 |
+
"logps/rejected": -1680.8695068359375,
|
| 2538 |
+
"loss": 0.1701,
|
| 2539 |
+
"rewards/accuracies": 0.875,
|
| 2540 |
+
"rewards/chosen": -0.04611823707818985,
|
| 2541 |
+
"rewards/margins": 0.32163435220718384,
|
| 2542 |
+
"rewards/rejected": -0.3677525818347931,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": -1.326982855796814,
|
| 2549 |
+
"logits/rejected": -0.7402676343917847,
|
| 2550 |
+
"logps/chosen": -599.7637939453125,
|
| 2551 |
+
"logps/rejected": -1530.202392578125,
|
| 2552 |
+
"loss": 0.1555,
|
| 2553 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2554 |
+
"rewards/chosen": -0.056166619062423706,
|
| 2555 |
+
"rewards/margins": 0.27239522337913513,
|
| 2556 |
+
"rewards/rejected": -0.32856184244155884,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": -1.4013383388519287,
|
| 2563 |
+
"logits/rejected": -0.5074108839035034,
|
| 2564 |
+
"logps/chosen": -622.0450439453125,
|
| 2565 |
+
"logps/rejected": -1639.010498046875,
|
| 2566 |
+
"loss": 0.1346,
|
| 2567 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2568 |
+
"rewards/chosen": -0.10727888345718384,
|
| 2569 |
+
"rewards/margins": 0.3056369721889496,
|
| 2570 |
+
"rewards/rejected": -0.4129158854484558,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": -1.490671992301941,
|
| 2577 |
+
"logits/rejected": -0.3455984890460968,
|
| 2578 |
+
"logps/chosen": -638.0214233398438,
|
| 2579 |
+
"logps/rejected": -1695.2183837890625,
|
| 2580 |
+
"loss": 0.175,
|
| 2581 |
+
"rewards/accuracies": 0.875,
|
| 2582 |
+
"rewards/chosen": -0.05133664608001709,
|
| 2583 |
+
"rewards/margins": 0.35318809747695923,
|
| 2584 |
+
"rewards/rejected": -0.4045247435569763,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": -1.2905375957489014,
|
| 2591 |
+
"logits/rejected": -0.5379937887191772,
|
| 2592 |
+
"logps/chosen": -673.1795654296875,
|
| 2593 |
+
"logps/rejected": -1559.984619140625,
|
| 2594 |
+
"loss": 0.1556,
|
| 2595 |
+
"rewards/accuracies": 0.800000011920929,
|
| 2596 |
+
"rewards/chosen": -0.07675811648368835,
|
| 2597 |
+
"rewards/margins": 0.2697897255420685,
|
| 2598 |
+
"rewards/rejected": -0.34654784202575684,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": -1.4194942712783813,
|
| 2605 |
+
"logits/rejected": -0.6771696209907532,
|
| 2606 |
+
"logps/chosen": -676.0364379882812,
|
| 2607 |
+
"logps/rejected": -1739.635498046875,
|
| 2608 |
+
"loss": 0.1438,
|
| 2609 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2610 |
+
"rewards/chosen": -0.07915320247411728,
|
| 2611 |
+
"rewards/margins": 0.31377238035202026,
|
| 2612 |
+
"rewards/rejected": -0.39292556047439575,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": -1.5524300336837769,
|
| 2619 |
+
"logits/rejected": -0.5318177342414856,
|
| 2620 |
+
"logps/chosen": -544.7901611328125,
|
| 2621 |
+
"logps/rejected": -1705.066162109375,
|
| 2622 |
+
"loss": 0.1563,
|
| 2623 |
+
"rewards/accuracies": 0.875,
|
| 2624 |
+
"rewards/chosen": -0.04058445617556572,
|
| 2625 |
+
"rewards/margins": 0.38282185792922974,
|
| 2626 |
+
"rewards/rejected": -0.4234062731266022,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": -1.2659026384353638,
|
| 2633 |
+
"logits/rejected": -0.41987451910972595,
|
| 2634 |
+
"logps/chosen": -756.4010009765625,
|
| 2635 |
+
"logps/rejected": -1763.924560546875,
|
| 2636 |
+
"loss": 0.1601,
|
| 2637 |
+
"rewards/accuracies": 0.875,
|
| 2638 |
+
"rewards/chosen": -0.0818880945444107,
|
| 2639 |
+
"rewards/margins": 0.3468380570411682,
|
| 2640 |
+
"rewards/rejected": -0.4287261962890625,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 0.18001604646046956,
|
| 2648 |
+
"train_runtime": 15472.4916,
|
| 2649 |
+
"train_samples_per_second": 0.969,
|
| 2650 |
+
"train_steps_per_second": 0.121
|
| 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": 2,
|
| 2660 |
+
"trial_name": null,
|
| 2661 |
+
"trial_params": null
|
| 2662 |
+
}
|