Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May19_21-40-44_gpu4-119-5/events.out.tfevents.1716118958.gpu4-119-5.3876247.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: lole25/zephyr-7b-irepo-i1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: zephyr-7b-gpo-v3-1-i2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# zephyr-7b-gpo-v3-1-i2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [lole25/zephyr-7b-irepo-i1](https://huggingface.co/lole25/zephyr-7b-irepo-i1) on the None dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 2
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 2
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 8
|
| 45 |
+
- total_eval_batch_size: 4
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.7.1
|
| 58 |
+
- Transformers 4.36.2
|
| 59 |
+
- Pytorch 2.1.2+cu121
|
| 60 |
+
- Datasets 2.14.6
|
| 61 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 671150064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d338908d924c695c29f93c3b5da4ed82bb94d2ca89c92502909ba001cffe00e
|
| 3 |
size 671150064
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.06912825773557027,
|
| 4 |
+
"train_runtime": 9941.711,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 1.509,
|
| 7 |
+
"train_steps_per_second": 0.189
|
| 8 |
+
}
|
runs/May19_21-40-44_gpu4-119-5/events.out.tfevents.1716118958.gpu4-119-5.3876247.0
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 sha256:18b777f8e7269edbb0ef648542d689f029e17473f5914fd30e90cce644fc55e1
|
| 3 |
+
size 117111
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.06912825773557027,
|
| 4 |
+
"train_runtime": 9941.711,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 1.509,
|
| 7 |
+
"train_steps_per_second": 0.189
|
| 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": -1.5569357872009277,
|
| 15 |
+
"logits/rejected": -1.1471056938171387,
|
| 16 |
+
"logps/chosen": -378.52911376953125,
|
| 17 |
+
"logps/rejected": -854.833984375,
|
| 18 |
+
"loss": 0.2347,
|
| 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": -1.6401379108428955,
|
| 29 |
+
"logits/rejected": -1.022291898727417,
|
| 30 |
+
"logps/chosen": -509.1824645996094,
|
| 31 |
+
"logps/rejected": -899.5430908203125,
|
| 32 |
+
"loss": 0.2181,
|
| 33 |
+
"rewards/accuracies": 0.4166666567325592,
|
| 34 |
+
"rewards/chosen": -0.00027799332747235894,
|
| 35 |
+
"rewards/margins": -5.683075141860172e-05,
|
| 36 |
+
"rewards/rejected": -0.00022116259788163006,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": -1.6371427774429321,
|
| 43 |
+
"logits/rejected": -1.1658873558044434,
|
| 44 |
+
"logps/chosen": -452.5133361816406,
|
| 45 |
+
"logps/rejected": -771.5206298828125,
|
| 46 |
+
"loss": 0.1959,
|
| 47 |
+
"rewards/accuracies": 0.625,
|
| 48 |
+
"rewards/chosen": 0.0010695771779865026,
|
| 49 |
+
"rewards/margins": 0.0016313500236719847,
|
| 50 |
+
"rewards/rejected": -0.0005617729621008039,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": -1.614117980003357,
|
| 57 |
+
"logits/rejected": -0.9896963834762573,
|
| 58 |
+
"logps/chosen": -505.353271484375,
|
| 59 |
+
"logps/rejected": -859.1238403320312,
|
| 60 |
+
"loss": 0.1969,
|
| 61 |
+
"rewards/accuracies": 0.875,
|
| 62 |
+
"rewards/chosen": 0.005224255379289389,
|
| 63 |
+
"rewards/margins": 0.010899050161242485,
|
| 64 |
+
"rewards/rejected": -0.005674795713275671,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": -1.5090134143829346,
|
| 71 |
+
"logits/rejected": -1.2780263423919678,
|
| 72 |
+
"logps/chosen": -342.17144775390625,
|
| 73 |
+
"logps/rejected": -809.4546508789062,
|
| 74 |
+
"loss": 0.2029,
|
| 75 |
+
"rewards/accuracies": 0.800000011920929,
|
| 76 |
+
"rewards/chosen": 0.01147081796079874,
|
| 77 |
+
"rewards/margins": 0.030131075531244278,
|
| 78 |
+
"rewards/rejected": -0.018660254776477814,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": -1.7051512002944946,
|
| 85 |
+
"logits/rejected": -0.8763967752456665,
|
| 86 |
+
"logps/chosen": -585.2564697265625,
|
| 87 |
+
"logps/rejected": -909.919921875,
|
| 88 |
+
"loss": 0.1786,
|
| 89 |
+
"rewards/accuracies": 0.800000011920929,
|
| 90 |
+
"rewards/chosen": 0.01587619259953499,
|
| 91 |
+
"rewards/margins": 0.05883794277906418,
|
| 92 |
+
"rewards/rejected": -0.04296175390481949,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": -1.5889899730682373,
|
| 99 |
+
"logits/rejected": -1.1295216083526611,
|
| 100 |
+
"logps/chosen": -424.6382751464844,
|
| 101 |
+
"logps/rejected": -895.8190307617188,
|
| 102 |
+
"loss": 0.1636,
|
| 103 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 104 |
+
"rewards/chosen": 0.009497600607573986,
|
| 105 |
+
"rewards/margins": 0.08446536958217621,
|
| 106 |
+
"rewards/rejected": -0.07496776431798935,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": -1.6142644882202148,
|
| 113 |
+
"logits/rejected": -1.1362119913101196,
|
| 114 |
+
"logps/chosen": -428.67236328125,
|
| 115 |
+
"logps/rejected": -934.1236572265625,
|
| 116 |
+
"loss": 0.1257,
|
| 117 |
+
"rewards/accuracies": 0.875,
|
| 118 |
+
"rewards/chosen": 0.003880441188812256,
|
| 119 |
+
"rewards/margins": 0.14223161339759827,
|
| 120 |
+
"rewards/rejected": -0.138351172208786,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": -1.5118087530136108,
|
| 127 |
+
"logits/rejected": -1.1322299242019653,
|
| 128 |
+
"logps/chosen": -615.1442260742188,
|
| 129 |
+
"logps/rejected": -1068.8787841796875,
|
| 130 |
+
"loss": 0.1128,
|
| 131 |
+
"rewards/accuracies": 0.800000011920929,
|
| 132 |
+
"rewards/chosen": -0.06628059595823288,
|
| 133 |
+
"rewards/margins": 0.14910638332366943,
|
| 134 |
+
"rewards/rejected": -0.2153869867324829,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": -1.748167634010315,
|
| 141 |
+
"logits/rejected": -1.1786916255950928,
|
| 142 |
+
"logps/chosen": -513.2774658203125,
|
| 143 |
+
"logps/rejected": -1070.9239501953125,
|
| 144 |
+
"loss": 0.113,
|
| 145 |
+
"rewards/accuracies": 0.824999988079071,
|
| 146 |
+
"rewards/chosen": -0.058650992810726166,
|
| 147 |
+
"rewards/margins": 0.2291336953639984,
|
| 148 |
+
"rewards/rejected": -0.28778475522994995,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": -1.7060625553131104,
|
| 155 |
+
"logits/rejected": -1.0770542621612549,
|
| 156 |
+
"logps/chosen": -546.6444091796875,
|
| 157 |
+
"logps/rejected": -1195.038818359375,
|
| 158 |
+
"loss": 0.1108,
|
| 159 |
+
"rewards/accuracies": 0.800000011920929,
|
| 160 |
+
"rewards/chosen": -0.14496687054634094,
|
| 161 |
+
"rewards/margins": 0.21418336033821106,
|
| 162 |
+
"rewards/rejected": -0.359150230884552,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": -1.6031602621078491,
|
| 169 |
+
"logits/rejected": -1.0294073820114136,
|
| 170 |
+
"logps/chosen": -659.802490234375,
|
| 171 |
+
"logps/rejected": -1333.0833740234375,
|
| 172 |
+
"loss": 0.0903,
|
| 173 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 174 |
+
"rewards/chosen": -0.17693635821342468,
|
| 175 |
+
"rewards/margins": 0.28644508123397827,
|
| 176 |
+
"rewards/rejected": -0.4633813798427582,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": -1.7648108005523682,
|
| 183 |
+
"logits/rejected": -1.4070419073104858,
|
| 184 |
+
"logps/chosen": -478.43487548828125,
|
| 185 |
+
"logps/rejected": -950.3967895507812,
|
| 186 |
+
"loss": 0.1227,
|
| 187 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 188 |
+
"rewards/chosen": -0.1012553796172142,
|
| 189 |
+
"rewards/margins": 0.1941373646259308,
|
| 190 |
+
"rewards/rejected": -0.2953927218914032,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": -1.5940220355987549,
|
| 197 |
+
"logits/rejected": -1.2087233066558838,
|
| 198 |
+
"logps/chosen": -476.9007873535156,
|
| 199 |
+
"logps/rejected": -1160.44580078125,
|
| 200 |
+
"loss": 0.0836,
|
| 201 |
+
"rewards/accuracies": 0.75,
|
| 202 |
+
"rewards/chosen": -0.09528017044067383,
|
| 203 |
+
"rewards/margins": 0.253213495016098,
|
| 204 |
+
"rewards/rejected": -0.34849366545677185,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": -1.2940385341644287,
|
| 211 |
+
"logits/rejected": -0.8031653165817261,
|
| 212 |
+
"logps/chosen": -744.671142578125,
|
| 213 |
+
"logps/rejected": -1387.1114501953125,
|
| 214 |
+
"loss": 0.0972,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.26588675379753113,
|
| 217 |
+
"rewards/margins": 0.2445482313632965,
|
| 218 |
+
"rewards/rejected": -0.5104349851608276,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": -1.6005325317382812,
|
| 225 |
+
"logits/rejected": -1.2362384796142578,
|
| 226 |
+
"logps/chosen": -655.4281005859375,
|
| 227 |
+
"logps/rejected": -1130.398193359375,
|
| 228 |
+
"loss": 0.0971,
|
| 229 |
+
"rewards/accuracies": 0.699999988079071,
|
| 230 |
+
"rewards/chosen": -0.196586474776268,
|
| 231 |
+
"rewards/margins": 0.21370963752269745,
|
| 232 |
+
"rewards/rejected": -0.41029611229896545,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": -1.7509543895721436,
|
| 239 |
+
"logits/rejected": -1.1238092184066772,
|
| 240 |
+
"logps/chosen": -569.5955810546875,
|
| 241 |
+
"logps/rejected": -1124.465576171875,
|
| 242 |
+
"loss": 0.102,
|
| 243 |
+
"rewards/accuracies": 0.675000011920929,
|
| 244 |
+
"rewards/chosen": -0.12171213328838348,
|
| 245 |
+
"rewards/margins": 0.21310141682624817,
|
| 246 |
+
"rewards/rejected": -0.33481353521347046,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": -1.7424652576446533,
|
| 253 |
+
"logits/rejected": -1.2808568477630615,
|
| 254 |
+
"logps/chosen": -563.4480590820312,
|
| 255 |
+
"logps/rejected": -1213.89453125,
|
| 256 |
+
"loss": 0.0727,
|
| 257 |
+
"rewards/accuracies": 0.824999988079071,
|
| 258 |
+
"rewards/chosen": -0.13533855974674225,
|
| 259 |
+
"rewards/margins": 0.23045413196086884,
|
| 260 |
+
"rewards/rejected": -0.3657926917076111,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": -1.6149215698242188,
|
| 267 |
+
"logits/rejected": -1.3036892414093018,
|
| 268 |
+
"logps/chosen": -604.5150146484375,
|
| 269 |
+
"logps/rejected": -1181.5762939453125,
|
| 270 |
+
"loss": 0.0986,
|
| 271 |
+
"rewards/accuracies": 0.875,
|
| 272 |
+
"rewards/chosen": -0.1363724172115326,
|
| 273 |
+
"rewards/margins": 0.24034619331359863,
|
| 274 |
+
"rewards/rejected": -0.3767186105251312,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": -1.6364609003067017,
|
| 281 |
+
"logits/rejected": -0.9650686979293823,
|
| 282 |
+
"logps/chosen": -680.2525634765625,
|
| 283 |
+
"logps/rejected": -1388.20068359375,
|
| 284 |
+
"loss": 0.0492,
|
| 285 |
+
"rewards/accuracies": 0.949999988079071,
|
| 286 |
+
"rewards/chosen": -0.17130868136882782,
|
| 287 |
+
"rewards/margins": 0.3032084107398987,
|
| 288 |
+
"rewards/rejected": -0.4745171070098877,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": -1.5488389730453491,
|
| 295 |
+
"logits/rejected": -1.0396603345870972,
|
| 296 |
+
"logps/chosen": -626.0272216796875,
|
| 297 |
+
"logps/rejected": -1298.0181884765625,
|
| 298 |
+
"loss": 0.0843,
|
| 299 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 300 |
+
"rewards/chosen": -0.1749267876148224,
|
| 301 |
+
"rewards/margins": 0.25047367811203003,
|
| 302 |
+
"rewards/rejected": -0.42540043592453003,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": -1.5960906744003296,
|
| 309 |
+
"logits/rejected": -1.0231754779815674,
|
| 310 |
+
"logps/chosen": -657.3213500976562,
|
| 311 |
+
"logps/rejected": -1247.23974609375,
|
| 312 |
+
"loss": 0.0739,
|
| 313 |
+
"rewards/accuracies": 0.824999988079071,
|
| 314 |
+
"rewards/chosen": -0.20409782230854034,
|
| 315 |
+
"rewards/margins": 0.2475307732820511,
|
| 316 |
+
"rewards/rejected": -0.45162859559059143,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": -1.7341878414154053,
|
| 323 |
+
"logits/rejected": -1.1983798742294312,
|
| 324 |
+
"logps/chosen": -753.7733154296875,
|
| 325 |
+
"logps/rejected": -1359.67626953125,
|
| 326 |
+
"loss": 0.071,
|
| 327 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 328 |
+
"rewards/chosen": -0.2541276514530182,
|
| 329 |
+
"rewards/margins": 0.2833201289176941,
|
| 330 |
+
"rewards/rejected": -0.5374478101730347,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": -1.4590599536895752,
|
| 337 |
+
"logits/rejected": -0.934046745300293,
|
| 338 |
+
"logps/chosen": -695.98046875,
|
| 339 |
+
"logps/rejected": -1367.89453125,
|
| 340 |
+
"loss": 0.0944,
|
| 341 |
+
"rewards/accuracies": 0.824999988079071,
|
| 342 |
+
"rewards/chosen": -0.2104768306016922,
|
| 343 |
+
"rewards/margins": 0.27617698907852173,
|
| 344 |
+
"rewards/rejected": -0.48665380477905273,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": -1.640160322189331,
|
| 351 |
+
"logits/rejected": -1.1560494899749756,
|
| 352 |
+
"logps/chosen": -578.0391845703125,
|
| 353 |
+
"logps/rejected": -1119.09814453125,
|
| 354 |
+
"loss": 0.1005,
|
| 355 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 356 |
+
"rewards/chosen": -0.16664345562458038,
|
| 357 |
+
"rewards/margins": 0.2392512559890747,
|
| 358 |
+
"rewards/rejected": -0.4058946967124939,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": -1.4978324174880981,
|
| 365 |
+
"logits/rejected": -1.134303092956543,
|
| 366 |
+
"logps/chosen": -570.8470458984375,
|
| 367 |
+
"logps/rejected": -1243.4251708984375,
|
| 368 |
+
"loss": 0.0959,
|
| 369 |
+
"rewards/accuracies": 0.875,
|
| 370 |
+
"rewards/chosen": -0.1637270152568817,
|
| 371 |
+
"rewards/margins": 0.2728789150714874,
|
| 372 |
+
"rewards/rejected": -0.43660593032836914,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": -1.788405179977417,
|
| 379 |
+
"logits/rejected": -1.0717966556549072,
|
| 380 |
+
"logps/chosen": -580.3256225585938,
|
| 381 |
+
"logps/rejected": -1118.1702880859375,
|
| 382 |
+
"loss": 0.0845,
|
| 383 |
+
"rewards/accuracies": 0.75,
|
| 384 |
+
"rewards/chosen": -0.1016082763671875,
|
| 385 |
+
"rewards/margins": 0.24942278861999512,
|
| 386 |
+
"rewards/rejected": -0.3510310649871826,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": -1.5624245405197144,
|
| 393 |
+
"logits/rejected": -0.8945890665054321,
|
| 394 |
+
"logps/chosen": -625.0382080078125,
|
| 395 |
+
"logps/rejected": -1272.6126708984375,
|
| 396 |
+
"loss": 0.0823,
|
| 397 |
+
"rewards/accuracies": 0.824999988079071,
|
| 398 |
+
"rewards/chosen": -0.15467065572738647,
|
| 399 |
+
"rewards/margins": 0.27355173230171204,
|
| 400 |
+
"rewards/rejected": -0.4282223582267761,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": -1.5876206159591675,
|
| 407 |
+
"logits/rejected": -1.138290286064148,
|
| 408 |
+
"logps/chosen": -727.9985961914062,
|
| 409 |
+
"logps/rejected": -1291.621826171875,
|
| 410 |
+
"loss": 0.0646,
|
| 411 |
+
"rewards/accuracies": 0.824999988079071,
|
| 412 |
+
"rewards/chosen": -0.23997028172016144,
|
| 413 |
+
"rewards/margins": 0.23828229308128357,
|
| 414 |
+
"rewards/rejected": -0.4782525897026062,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": -1.7230398654937744,
|
| 421 |
+
"logits/rejected": -1.4215495586395264,
|
| 422 |
+
"logps/chosen": -605.0308837890625,
|
| 423 |
+
"logps/rejected": -1185.82861328125,
|
| 424 |
+
"loss": 0.0736,
|
| 425 |
+
"rewards/accuracies": 0.800000011920929,
|
| 426 |
+
"rewards/chosen": -0.17933842539787292,
|
| 427 |
+
"rewards/margins": 0.22512169182300568,
|
| 428 |
+
"rewards/rejected": -0.4044601321220398,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": -1.5644534826278687,
|
| 435 |
+
"logits/rejected": -1.0705270767211914,
|
| 436 |
+
"logps/chosen": -733.014404296875,
|
| 437 |
+
"logps/rejected": -1408.350830078125,
|
| 438 |
+
"loss": 0.0755,
|
| 439 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 440 |
+
"rewards/chosen": -0.2445208728313446,
|
| 441 |
+
"rewards/margins": 0.2835485339164734,
|
| 442 |
+
"rewards/rejected": -0.5280693769454956,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": -1.6218621730804443,
|
| 449 |
+
"logits/rejected": -0.9748885035514832,
|
| 450 |
+
"logps/chosen": -564.2091064453125,
|
| 451 |
+
"logps/rejected": -1149.895263671875,
|
| 452 |
+
"loss": 0.0768,
|
| 453 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 454 |
+
"rewards/chosen": -0.1630648970603943,
|
| 455 |
+
"rewards/margins": 0.2708643972873688,
|
| 456 |
+
"rewards/rejected": -0.43392929434776306,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": -1.7458088397979736,
|
| 463 |
+
"logits/rejected": -1.3406083583831787,
|
| 464 |
+
"logps/chosen": -561.4813232421875,
|
| 465 |
+
"logps/rejected": -1230.68017578125,
|
| 466 |
+
"loss": 0.0746,
|
| 467 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 468 |
+
"rewards/chosen": -0.16397038102149963,
|
| 469 |
+
"rewards/margins": 0.27870216965675354,
|
| 470 |
+
"rewards/rejected": -0.44267258048057556,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": -1.6369669437408447,
|
| 477 |
+
"logits/rejected": -1.1729207038879395,
|
| 478 |
+
"logps/chosen": -627.0284423828125,
|
| 479 |
+
"logps/rejected": -1398.7330322265625,
|
| 480 |
+
"loss": 0.0666,
|
| 481 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 482 |
+
"rewards/chosen": -0.18270769715309143,
|
| 483 |
+
"rewards/margins": 0.31160640716552734,
|
| 484 |
+
"rewards/rejected": -0.49431413412094116,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": -1.6523929834365845,
|
| 491 |
+
"logits/rejected": -1.0893100500106812,
|
| 492 |
+
"logps/chosen": -597.8865966796875,
|
| 493 |
+
"logps/rejected": -1325.775390625,
|
| 494 |
+
"loss": 0.0936,
|
| 495 |
+
"rewards/accuracies": 0.875,
|
| 496 |
+
"rewards/chosen": -0.17563173174858093,
|
| 497 |
+
"rewards/margins": 0.269579142332077,
|
| 498 |
+
"rewards/rejected": -0.44521084427833557,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": -1.7033765316009521,
|
| 505 |
+
"logits/rejected": -1.280895709991455,
|
| 506 |
+
"logps/chosen": -710.4462280273438,
|
| 507 |
+
"logps/rejected": -1266.050048828125,
|
| 508 |
+
"loss": 0.1008,
|
| 509 |
+
"rewards/accuracies": 0.800000011920929,
|
| 510 |
+
"rewards/chosen": -0.2460685521364212,
|
| 511 |
+
"rewards/margins": 0.2334461659193039,
|
| 512 |
+
"rewards/rejected": -0.4795146882534027,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": -1.630501389503479,
|
| 519 |
+
"logits/rejected": -0.9762773513793945,
|
| 520 |
+
"logps/chosen": -765.29248046875,
|
| 521 |
+
"logps/rejected": -1381.234619140625,
|
| 522 |
+
"loss": 0.0966,
|
| 523 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 524 |
+
"rewards/chosen": -0.2656300961971283,
|
| 525 |
+
"rewards/margins": 0.25425031781196594,
|
| 526 |
+
"rewards/rejected": -0.5198804140090942,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": -1.5260308980941772,
|
| 533 |
+
"logits/rejected": -1.0575653314590454,
|
| 534 |
+
"logps/chosen": -580.313232421875,
|
| 535 |
+
"logps/rejected": -1192.9915771484375,
|
| 536 |
+
"loss": 0.0654,
|
| 537 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 538 |
+
"rewards/chosen": -0.16813692450523376,
|
| 539 |
+
"rewards/margins": 0.25473329424858093,
|
| 540 |
+
"rewards/rejected": -0.4228702485561371,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": -1.7011750936508179,
|
| 547 |
+
"logits/rejected": -1.1821006536483765,
|
| 548 |
+
"logps/chosen": -703.5277099609375,
|
| 549 |
+
"logps/rejected": -1323.509033203125,
|
| 550 |
+
"loss": 0.0809,
|
| 551 |
+
"rewards/accuracies": 0.800000011920929,
|
| 552 |
+
"rewards/chosen": -0.2287747859954834,
|
| 553 |
+
"rewards/margins": 0.27832740545272827,
|
| 554 |
+
"rewards/rejected": -0.5071021914482117,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": -1.4276914596557617,
|
| 561 |
+
"logits/rejected": -0.9805229306221008,
|
| 562 |
+
"logps/chosen": -592.0125122070312,
|
| 563 |
+
"logps/rejected": -1193.139892578125,
|
| 564 |
+
"loss": 0.064,
|
| 565 |
+
"rewards/accuracies": 0.800000011920929,
|
| 566 |
+
"rewards/chosen": -0.18544098734855652,
|
| 567 |
+
"rewards/margins": 0.2668260931968689,
|
| 568 |
+
"rewards/rejected": -0.45226702094078064,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": -1.5613304376602173,
|
| 575 |
+
"logits/rejected": -0.8922286033630371,
|
| 576 |
+
"logps/chosen": -665.95556640625,
|
| 577 |
+
"logps/rejected": -1267.384765625,
|
| 578 |
+
"loss": 0.0621,
|
| 579 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 580 |
+
"rewards/chosen": -0.19959279894828796,
|
| 581 |
+
"rewards/margins": 0.29206138849258423,
|
| 582 |
+
"rewards/rejected": -0.4916541576385498,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": -1.9131767749786377,
|
| 589 |
+
"logits/rejected": -1.3205538988113403,
|
| 590 |
+
"logps/chosen": -605.758056640625,
|
| 591 |
+
"logps/rejected": -1235.4910888671875,
|
| 592 |
+
"loss": 0.072,
|
| 593 |
+
"rewards/accuracies": 0.800000011920929,
|
| 594 |
+
"rewards/chosen": -0.17551980912685394,
|
| 595 |
+
"rewards/margins": 0.2815834879875183,
|
| 596 |
+
"rewards/rejected": -0.45710331201553345,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": -1.8387680053710938,
|
| 603 |
+
"logits/rejected": -1.0919946432113647,
|
| 604 |
+
"logps/chosen": -603.5829467773438,
|
| 605 |
+
"logps/rejected": -1248.807861328125,
|
| 606 |
+
"loss": 0.0806,
|
| 607 |
+
"rewards/accuracies": 0.800000011920929,
|
| 608 |
+
"rewards/chosen": -0.17225244641304016,
|
| 609 |
+
"rewards/margins": 0.29293113946914673,
|
| 610 |
+
"rewards/rejected": -0.4651835560798645,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": -1.942421317100525,
|
| 617 |
+
"logits/rejected": -0.9755213856697083,
|
| 618 |
+
"logps/chosen": -629.6397094726562,
|
| 619 |
+
"logps/rejected": -1305.019775390625,
|
| 620 |
+
"loss": 0.0636,
|
| 621 |
+
"rewards/accuracies": 0.875,
|
| 622 |
+
"rewards/chosen": -0.17476651072502136,
|
| 623 |
+
"rewards/margins": 0.336466521024704,
|
| 624 |
+
"rewards/rejected": -0.5112330317497253,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": -1.6092408895492554,
|
| 631 |
+
"logits/rejected": -1.0839555263519287,
|
| 632 |
+
"logps/chosen": -642.392333984375,
|
| 633 |
+
"logps/rejected": -1305.717041015625,
|
| 634 |
+
"loss": 0.0773,
|
| 635 |
+
"rewards/accuracies": 0.824999988079071,
|
| 636 |
+
"rewards/chosen": -0.23566822707653046,
|
| 637 |
+
"rewards/margins": 0.27665117383003235,
|
| 638 |
+
"rewards/rejected": -0.5123193860054016,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": -1.7550840377807617,
|
| 645 |
+
"logits/rejected": -1.3057055473327637,
|
| 646 |
+
"logps/chosen": -744.6429443359375,
|
| 647 |
+
"logps/rejected": -1384.8328857421875,
|
| 648 |
+
"loss": 0.0808,
|
| 649 |
+
"rewards/accuracies": 0.824999988079071,
|
| 650 |
+
"rewards/chosen": -0.25410711765289307,
|
| 651 |
+
"rewards/margins": 0.2785530686378479,
|
| 652 |
+
"rewards/rejected": -0.5326601266860962,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": -1.651061773300171,
|
| 659 |
+
"logits/rejected": -1.0968434810638428,
|
| 660 |
+
"logps/chosen": -696.5147705078125,
|
| 661 |
+
"logps/rejected": -1150.5166015625,
|
| 662 |
+
"loss": 0.0887,
|
| 663 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 664 |
+
"rewards/chosen": -0.24368226528167725,
|
| 665 |
+
"rewards/margins": 0.20816107094287872,
|
| 666 |
+
"rewards/rejected": -0.4518433213233948,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": -1.8011071681976318,
|
| 673 |
+
"logits/rejected": -1.0791230201721191,
|
| 674 |
+
"logps/chosen": -579.2171020507812,
|
| 675 |
+
"logps/rejected": -1126.716552734375,
|
| 676 |
+
"loss": 0.091,
|
| 677 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 678 |
+
"rewards/chosen": -0.13108104467391968,
|
| 679 |
+
"rewards/margins": 0.2670387625694275,
|
| 680 |
+
"rewards/rejected": -0.3981197774410248,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": -1.5227606296539307,
|
| 687 |
+
"logits/rejected": -0.9799526929855347,
|
| 688 |
+
"logps/chosen": -755.5355834960938,
|
| 689 |
+
"logps/rejected": -1411.053955078125,
|
| 690 |
+
"loss": 0.1072,
|
| 691 |
+
"rewards/accuracies": 0.875,
|
| 692 |
+
"rewards/chosen": -0.2255210429430008,
|
| 693 |
+
"rewards/margins": 0.28304630517959595,
|
| 694 |
+
"rewards/rejected": -0.5085673332214355,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": -1.7349796295166016,
|
| 701 |
+
"logits/rejected": -0.942231297492981,
|
| 702 |
+
"logps/chosen": -764.5320434570312,
|
| 703 |
+
"logps/rejected": -1312.6400146484375,
|
| 704 |
+
"loss": 0.0975,
|
| 705 |
+
"rewards/accuracies": 0.875,
|
| 706 |
+
"rewards/chosen": -0.24115994572639465,
|
| 707 |
+
"rewards/margins": 0.24554534256458282,
|
| 708 |
+
"rewards/rejected": -0.4867052435874939,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": -1.5131117105484009,
|
| 715 |
+
"logits/rejected": -1.1059508323669434,
|
| 716 |
+
"logps/chosen": -780.0518798828125,
|
| 717 |
+
"logps/rejected": -1328.439208984375,
|
| 718 |
+
"loss": 0.0985,
|
| 719 |
+
"rewards/accuracies": 0.75,
|
| 720 |
+
"rewards/chosen": -0.3147870600223541,
|
| 721 |
+
"rewards/margins": 0.2081507444381714,
|
| 722 |
+
"rewards/rejected": -0.5229377746582031,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": -1.5837140083312988,
|
| 729 |
+
"logits/rejected": -0.9551746249198914,
|
| 730 |
+
"logps/chosen": -628.8701782226562,
|
| 731 |
+
"logps/rejected": -1158.2474365234375,
|
| 732 |
+
"loss": 0.0979,
|
| 733 |
+
"rewards/accuracies": 0.800000011920929,
|
| 734 |
+
"rewards/chosen": -0.16708222031593323,
|
| 735 |
+
"rewards/margins": 0.24669913947582245,
|
| 736 |
+
"rewards/rejected": -0.41378140449523926,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": -1.6675571203231812,
|
| 743 |
+
"logits/rejected": -0.9593210220336914,
|
| 744 |
+
"logps/chosen": -682.0783081054688,
|
| 745 |
+
"logps/rejected": -1288.447509765625,
|
| 746 |
+
"loss": 0.0898,
|
| 747 |
+
"rewards/accuracies": 0.925000011920929,
|
| 748 |
+
"rewards/chosen": -0.19303472340106964,
|
| 749 |
+
"rewards/margins": 0.25880172848701477,
|
| 750 |
+
"rewards/rejected": -0.4518364369869232,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": -1.6770139932632446,
|
| 757 |
+
"logits/rejected": -0.937613308429718,
|
| 758 |
+
"logps/chosen": -713.4398193359375,
|
| 759 |
+
"logps/rejected": -1368.5531005859375,
|
| 760 |
+
"loss": 0.0852,
|
| 761 |
+
"rewards/accuracies": 0.925000011920929,
|
| 762 |
+
"rewards/chosen": -0.24874809384346008,
|
| 763 |
+
"rewards/margins": 0.315912663936615,
|
| 764 |
+
"rewards/rejected": -0.5646606683731079,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": -1.4941534996032715,
|
| 771 |
+
"logits/rejected": -0.8417922258377075,
|
| 772 |
+
"logps/chosen": -761.2758178710938,
|
| 773 |
+
"logps/rejected": -1347.4490966796875,
|
| 774 |
+
"loss": 0.0908,
|
| 775 |
+
"rewards/accuracies": 0.800000011920929,
|
| 776 |
+
"rewards/chosen": -0.25566571950912476,
|
| 777 |
+
"rewards/margins": 0.26928967237472534,
|
| 778 |
+
"rewards/rejected": -0.5249553918838501,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": -1.638262391090393,
|
| 785 |
+
"logits/rejected": -0.953241229057312,
|
| 786 |
+
"logps/chosen": -680.6768188476562,
|
| 787 |
+
"logps/rejected": -1407.271240234375,
|
| 788 |
+
"loss": 0.0657,
|
| 789 |
+
"rewards/accuracies": 0.925000011920929,
|
| 790 |
+
"rewards/chosen": -0.21453741192817688,
|
| 791 |
+
"rewards/margins": 0.332472026348114,
|
| 792 |
+
"rewards/rejected": -0.5470094084739685,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": -1.597510576248169,
|
| 799 |
+
"logits/rejected": -0.9470292925834656,
|
| 800 |
+
"logps/chosen": -748.9639892578125,
|
| 801 |
+
"logps/rejected": -1390.034912109375,
|
| 802 |
+
"loss": 0.0565,
|
| 803 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 804 |
+
"rewards/chosen": -0.23396451771259308,
|
| 805 |
+
"rewards/margins": 0.3206896483898163,
|
| 806 |
+
"rewards/rejected": -0.5546542406082153,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": -1.550355076789856,
|
| 813 |
+
"logits/rejected": -1.0478793382644653,
|
| 814 |
+
"logps/chosen": -604.4364013671875,
|
| 815 |
+
"logps/rejected": -1344.87841796875,
|
| 816 |
+
"loss": 0.0637,
|
| 817 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 818 |
+
"rewards/chosen": -0.2098585069179535,
|
| 819 |
+
"rewards/margins": 0.31462934613227844,
|
| 820 |
+
"rewards/rejected": -0.5244878530502319,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": -1.533578634262085,
|
| 827 |
+
"logits/rejected": -1.0312515497207642,
|
| 828 |
+
"logps/chosen": -538.365478515625,
|
| 829 |
+
"logps/rejected": -1111.39501953125,
|
| 830 |
+
"loss": 0.0999,
|
| 831 |
+
"rewards/accuracies": 0.75,
|
| 832 |
+
"rewards/chosen": -0.18333378434181213,
|
| 833 |
+
"rewards/margins": 0.26067209243774414,
|
| 834 |
+
"rewards/rejected": -0.4440058767795563,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": -1.4897745847702026,
|
| 841 |
+
"logits/rejected": -1.0129917860031128,
|
| 842 |
+
"logps/chosen": -689.7890014648438,
|
| 843 |
+
"logps/rejected": -1376.696044921875,
|
| 844 |
+
"loss": 0.0581,
|
| 845 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 846 |
+
"rewards/chosen": -0.2648084759712219,
|
| 847 |
+
"rewards/margins": 0.2891417145729065,
|
| 848 |
+
"rewards/rejected": -0.5539501905441284,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": -1.4845857620239258,
|
| 855 |
+
"logits/rejected": -0.9828746914863586,
|
| 856 |
+
"logps/chosen": -596.8510131835938,
|
| 857 |
+
"logps/rejected": -1313.0968017578125,
|
| 858 |
+
"loss": 0.0747,
|
| 859 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 860 |
+
"rewards/chosen": -0.20095543563365936,
|
| 861 |
+
"rewards/margins": 0.307460755109787,
|
| 862 |
+
"rewards/rejected": -0.5084162354469299,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": -1.7313928604125977,
|
| 869 |
+
"logits/rejected": -1.3923299312591553,
|
| 870 |
+
"logps/chosen": -712.3792724609375,
|
| 871 |
+
"logps/rejected": -1243.148681640625,
|
| 872 |
+
"loss": 0.0924,
|
| 873 |
+
"rewards/accuracies": 0.75,
|
| 874 |
+
"rewards/chosen": -0.24510283768177032,
|
| 875 |
+
"rewards/margins": 0.24176783859729767,
|
| 876 |
+
"rewards/rejected": -0.486870676279068,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": -1.5082043409347534,
|
| 883 |
+
"logits/rejected": -0.8806392550468445,
|
| 884 |
+
"logps/chosen": -682.8671875,
|
| 885 |
+
"logps/rejected": -1272.7772216796875,
|
| 886 |
+
"loss": 0.0522,
|
| 887 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 888 |
+
"rewards/chosen": -0.18572933971881866,
|
| 889 |
+
"rewards/margins": 0.2751011252403259,
|
| 890 |
+
"rewards/rejected": -0.46083053946495056,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": -1.6908938884735107,
|
| 897 |
+
"logits/rejected": -0.9967711567878723,
|
| 898 |
+
"logps/chosen": -673.7935180664062,
|
| 899 |
+
"logps/rejected": -1292.220458984375,
|
| 900 |
+
"loss": 0.0842,
|
| 901 |
+
"rewards/accuracies": 0.925000011920929,
|
| 902 |
+
"rewards/chosen": -0.16402257978916168,
|
| 903 |
+
"rewards/margins": 0.3048457205295563,
|
| 904 |
+
"rewards/rejected": -0.46886831521987915,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": -1.3779823780059814,
|
| 911 |
+
"logits/rejected": -0.8789410591125488,
|
| 912 |
+
"logps/chosen": -565.2269287109375,
|
| 913 |
+
"logps/rejected": -1224.1700439453125,
|
| 914 |
+
"loss": 0.0805,
|
| 915 |
+
"rewards/accuracies": 0.875,
|
| 916 |
+
"rewards/chosen": -0.11619114875793457,
|
| 917 |
+
"rewards/margins": 0.29433438181877136,
|
| 918 |
+
"rewards/rejected": -0.41052550077438354,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": -1.4996254444122314,
|
| 925 |
+
"logits/rejected": -1.0665868520736694,
|
| 926 |
+
"logps/chosen": -620.0261840820312,
|
| 927 |
+
"logps/rejected": -1192.489013671875,
|
| 928 |
+
"loss": 0.0758,
|
| 929 |
+
"rewards/accuracies": 0.800000011920929,
|
| 930 |
+
"rewards/chosen": -0.1719478964805603,
|
| 931 |
+
"rewards/margins": 0.2514215111732483,
|
| 932 |
+
"rewards/rejected": -0.4233694076538086,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": -1.6758674383163452,
|
| 939 |
+
"logits/rejected": -1.0761094093322754,
|
| 940 |
+
"logps/chosen": -661.2818603515625,
|
| 941 |
+
"logps/rejected": -1286.9786376953125,
|
| 942 |
+
"loss": 0.043,
|
| 943 |
+
"rewards/accuracies": 0.875,
|
| 944 |
+
"rewards/chosen": -0.1839846819639206,
|
| 945 |
+
"rewards/margins": 0.2680208086967468,
|
| 946 |
+
"rewards/rejected": -0.4520054757595062,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": -1.3314406871795654,
|
| 953 |
+
"logits/rejected": -0.9023712873458862,
|
| 954 |
+
"logps/chosen": -654.1249389648438,
|
| 955 |
+
"logps/rejected": -1329.398193359375,
|
| 956 |
+
"loss": 0.0722,
|
| 957 |
+
"rewards/accuracies": 0.824999988079071,
|
| 958 |
+
"rewards/chosen": -0.1925685852766037,
|
| 959 |
+
"rewards/margins": 0.28446346521377563,
|
| 960 |
+
"rewards/rejected": -0.4770320951938629,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": -1.578636884689331,
|
| 967 |
+
"logits/rejected": -1.0915998220443726,
|
| 968 |
+
"logps/chosen": -740.0035400390625,
|
| 969 |
+
"logps/rejected": -1387.459228515625,
|
| 970 |
+
"loss": 0.0693,
|
| 971 |
+
"rewards/accuracies": 0.875,
|
| 972 |
+
"rewards/chosen": -0.21566300094127655,
|
| 973 |
+
"rewards/margins": 0.3169075846672058,
|
| 974 |
+
"rewards/rejected": -0.5325705409049988,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": -1.5450822114944458,
|
| 981 |
+
"logits/rejected": -0.7816729545593262,
|
| 982 |
+
"logps/chosen": -626.339111328125,
|
| 983 |
+
"logps/rejected": -1215.27734375,
|
| 984 |
+
"loss": 0.0805,
|
| 985 |
+
"rewards/accuracies": 0.800000011920929,
|
| 986 |
+
"rewards/chosen": -0.18071869015693665,
|
| 987 |
+
"rewards/margins": 0.2859996259212494,
|
| 988 |
+
"rewards/rejected": -0.46671828627586365,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": -1.3680191040039062,
|
| 995 |
+
"logits/rejected": -0.8944322466850281,
|
| 996 |
+
"logps/chosen": -557.0673828125,
|
| 997 |
+
"logps/rejected": -1440.092041015625,
|
| 998 |
+
"loss": 0.066,
|
| 999 |
+
"rewards/accuracies": 0.925000011920929,
|
| 1000 |
+
"rewards/chosen": -0.1859458088874817,
|
| 1001 |
+
"rewards/margins": 0.374511182308197,
|
| 1002 |
+
"rewards/rejected": -0.5604569911956787,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": -1.6122426986694336,
|
| 1009 |
+
"logits/rejected": -0.6363096237182617,
|
| 1010 |
+
"logps/chosen": -730.7781372070312,
|
| 1011 |
+
"logps/rejected": -1428.550537109375,
|
| 1012 |
+
"loss": 0.0613,
|
| 1013 |
+
"rewards/accuracies": 0.875,
|
| 1014 |
+
"rewards/chosen": -0.2527967095375061,
|
| 1015 |
+
"rewards/margins": 0.3397744297981262,
|
| 1016 |
+
"rewards/rejected": -0.5925711393356323,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": -1.4658266305923462,
|
| 1023 |
+
"logits/rejected": -0.9103586077690125,
|
| 1024 |
+
"logps/chosen": -749.474365234375,
|
| 1025 |
+
"logps/rejected": -1346.693603515625,
|
| 1026 |
+
"loss": 0.0691,
|
| 1027 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1028 |
+
"rewards/chosen": -0.3004884421825409,
|
| 1029 |
+
"rewards/margins": 0.2709447145462036,
|
| 1030 |
+
"rewards/rejected": -0.5714331865310669,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": -1.651769995689392,
|
| 1037 |
+
"logits/rejected": -0.9803410768508911,
|
| 1038 |
+
"logps/chosen": -826.3870239257812,
|
| 1039 |
+
"logps/rejected": -1311.737548828125,
|
| 1040 |
+
"loss": 0.0961,
|
| 1041 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1042 |
+
"rewards/chosen": -0.3051601052284241,
|
| 1043 |
+
"rewards/margins": 0.23282098770141602,
|
| 1044 |
+
"rewards/rejected": -0.5379811525344849,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": -1.6758012771606445,
|
| 1051 |
+
"logits/rejected": -0.8760524988174438,
|
| 1052 |
+
"logps/chosen": -703.2643432617188,
|
| 1053 |
+
"logps/rejected": -1416.0147705078125,
|
| 1054 |
+
"loss": 0.0536,
|
| 1055 |
+
"rewards/accuracies": 0.875,
|
| 1056 |
+
"rewards/chosen": -0.2222570925951004,
|
| 1057 |
+
"rewards/margins": 0.3216368556022644,
|
| 1058 |
+
"rewards/rejected": -0.5438939332962036,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": -1.5657737255096436,
|
| 1065 |
+
"logits/rejected": -0.6773009300231934,
|
| 1066 |
+
"logps/chosen": -660.05224609375,
|
| 1067 |
+
"logps/rejected": -1413.72412109375,
|
| 1068 |
+
"loss": 0.0704,
|
| 1069 |
+
"rewards/accuracies": 0.949999988079071,
|
| 1070 |
+
"rewards/chosen": -0.17005473375320435,
|
| 1071 |
+
"rewards/margins": 0.3672229051589966,
|
| 1072 |
+
"rewards/rejected": -0.5372776985168457,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": -1.5888159275054932,
|
| 1079 |
+
"logits/rejected": -0.9240763783454895,
|
| 1080 |
+
"logps/chosen": -703.791259765625,
|
| 1081 |
+
"logps/rejected": -1287.2347412109375,
|
| 1082 |
+
"loss": 0.0847,
|
| 1083 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1084 |
+
"rewards/chosen": -0.2002638578414917,
|
| 1085 |
+
"rewards/margins": 0.2807930111885071,
|
| 1086 |
+
"rewards/rejected": -0.4810568690299988,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": -1.5560834407806396,
|
| 1093 |
+
"logits/rejected": -0.8829728960990906,
|
| 1094 |
+
"logps/chosen": -687.9392700195312,
|
| 1095 |
+
"logps/rejected": -1264.13427734375,
|
| 1096 |
+
"loss": 0.0614,
|
| 1097 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1098 |
+
"rewards/chosen": -0.23228220641613007,
|
| 1099 |
+
"rewards/margins": 0.27504783868789673,
|
| 1100 |
+
"rewards/rejected": -0.507330060005188,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": -1.6791499853134155,
|
| 1107 |
+
"logits/rejected": -0.868704617023468,
|
| 1108 |
+
"logps/chosen": -739.4034423828125,
|
| 1109 |
+
"logps/rejected": -1467.380859375,
|
| 1110 |
+
"loss": 0.0709,
|
| 1111 |
+
"rewards/accuracies": 0.875,
|
| 1112 |
+
"rewards/chosen": -0.26428860425949097,
|
| 1113 |
+
"rewards/margins": 0.3761114478111267,
|
| 1114 |
+
"rewards/rejected": -0.6404000520706177,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": -1.6334638595581055,
|
| 1121 |
+
"logits/rejected": -0.9652324914932251,
|
| 1122 |
+
"logps/chosen": -696.2661743164062,
|
| 1123 |
+
"logps/rejected": -1319.149169921875,
|
| 1124 |
+
"loss": 0.0726,
|
| 1125 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1126 |
+
"rewards/chosen": -0.2676045298576355,
|
| 1127 |
+
"rewards/margins": 0.2971785068511963,
|
| 1128 |
+
"rewards/rejected": -0.5647830367088318,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": -1.5483821630477905,
|
| 1135 |
+
"logits/rejected": -0.752991795539856,
|
| 1136 |
+
"logps/chosen": -802.7833251953125,
|
| 1137 |
+
"logps/rejected": -1420.5225830078125,
|
| 1138 |
+
"loss": 0.064,
|
| 1139 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1140 |
+
"rewards/chosen": -0.2800512909889221,
|
| 1141 |
+
"rewards/margins": 0.28601035475730896,
|
| 1142 |
+
"rewards/rejected": -0.5660616159439087,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": -1.4806568622589111,
|
| 1149 |
+
"logits/rejected": -1.0608776807785034,
|
| 1150 |
+
"logps/chosen": -572.4467163085938,
|
| 1151 |
+
"logps/rejected": -1223.5535888671875,
|
| 1152 |
+
"loss": 0.0826,
|
| 1153 |
+
"rewards/accuracies": 0.75,
|
| 1154 |
+
"rewards/chosen": -0.19516542553901672,
|
| 1155 |
+
"rewards/margins": 0.2695198655128479,
|
| 1156 |
+
"rewards/rejected": -0.46468526124954224,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": -1.6573173999786377,
|
| 1163 |
+
"logits/rejected": -0.9227333068847656,
|
| 1164 |
+
"logps/chosen": -583.91357421875,
|
| 1165 |
+
"logps/rejected": -1404.231201171875,
|
| 1166 |
+
"loss": 0.0654,
|
| 1167 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1168 |
+
"rewards/chosen": -0.19101464748382568,
|
| 1169 |
+
"rewards/margins": 0.35477685928344727,
|
| 1170 |
+
"rewards/rejected": -0.5457914471626282,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": -1.5851019620895386,
|
| 1177 |
+
"logits/rejected": -1.1501173973083496,
|
| 1178 |
+
"logps/chosen": -773.6009521484375,
|
| 1179 |
+
"logps/rejected": -1467.8524169921875,
|
| 1180 |
+
"loss": 0.0722,
|
| 1181 |
+
"rewards/accuracies": 0.925000011920929,
|
| 1182 |
+
"rewards/chosen": -0.28683894872665405,
|
| 1183 |
+
"rewards/margins": 0.3111644387245178,
|
| 1184 |
+
"rewards/rejected": -0.5980033874511719,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": -1.7856470346450806,
|
| 1191 |
+
"logits/rejected": -0.7052544951438904,
|
| 1192 |
+
"logps/chosen": -758.5326538085938,
|
| 1193 |
+
"logps/rejected": -1374.1175537109375,
|
| 1194 |
+
"loss": 0.0738,
|
| 1195 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1196 |
+
"rewards/chosen": -0.21995194256305695,
|
| 1197 |
+
"rewards/margins": 0.3128163814544678,
|
| 1198 |
+
"rewards/rejected": -0.5327683687210083,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": -1.5121822357177734,
|
| 1205 |
+
"logits/rejected": -0.6632939577102661,
|
| 1206 |
+
"logps/chosen": -758.4606323242188,
|
| 1207 |
+
"logps/rejected": -1379.579833984375,
|
| 1208 |
+
"loss": 0.0696,
|
| 1209 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1210 |
+
"rewards/chosen": -0.24226677417755127,
|
| 1211 |
+
"rewards/margins": 0.2715800404548645,
|
| 1212 |
+
"rewards/rejected": -0.5138468146324158,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": -1.4147189855575562,
|
| 1219 |
+
"logits/rejected": -0.8505645990371704,
|
| 1220 |
+
"logps/chosen": -685.36865234375,
|
| 1221 |
+
"logps/rejected": -1207.5999755859375,
|
| 1222 |
+
"loss": 0.0923,
|
| 1223 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1224 |
+
"rewards/chosen": -0.20475773513317108,
|
| 1225 |
+
"rewards/margins": 0.26389437913894653,
|
| 1226 |
+
"rewards/rejected": -0.4686520993709564,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": -1.3422014713287354,
|
| 1233 |
+
"logits/rejected": -1.0369704961776733,
|
| 1234 |
+
"logps/chosen": -558.9657592773438,
|
| 1235 |
+
"logps/rejected": -1227.389404296875,
|
| 1236 |
+
"loss": 0.0724,
|
| 1237 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1238 |
+
"rewards/chosen": -0.14610688388347626,
|
| 1239 |
+
"rewards/margins": 0.2603977918624878,
|
| 1240 |
+
"rewards/rejected": -0.40650469064712524,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": -1.413086175918579,
|
| 1247 |
+
"logits/rejected": -0.8006247282028198,
|
| 1248 |
+
"logps/chosen": -568.7772216796875,
|
| 1249 |
+
"logps/rejected": -1355.8843994140625,
|
| 1250 |
+
"loss": 0.066,
|
| 1251 |
+
"rewards/accuracies": 0.949999988079071,
|
| 1252 |
+
"rewards/chosen": -0.1402299702167511,
|
| 1253 |
+
"rewards/margins": 0.332205593585968,
|
| 1254 |
+
"rewards/rejected": -0.4724355638027191,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": -1.7916749715805054,
|
| 1261 |
+
"logits/rejected": -1.1966052055358887,
|
| 1262 |
+
"logps/chosen": -509.91522216796875,
|
| 1263 |
+
"logps/rejected": -1213.2950439453125,
|
| 1264 |
+
"loss": 0.0795,
|
| 1265 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1266 |
+
"rewards/chosen": -0.13929350674152374,
|
| 1267 |
+
"rewards/margins": 0.29636120796203613,
|
| 1268 |
+
"rewards/rejected": -0.43565472960472107,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": -1.959776520729065,
|
| 1275 |
+
"logits/rejected": -1.0398948192596436,
|
| 1276 |
+
"logps/chosen": -717.4497680664062,
|
| 1277 |
+
"logps/rejected": -1357.809814453125,
|
| 1278 |
+
"loss": 0.0751,
|
| 1279 |
+
"rewards/accuracies": 0.875,
|
| 1280 |
+
"rewards/chosen": -0.17033252120018005,
|
| 1281 |
+
"rewards/margins": 0.3062911629676819,
|
| 1282 |
+
"rewards/rejected": -0.47662368416786194,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": -1.7569372653961182,
|
| 1289 |
+
"logits/rejected": -0.9980508089065552,
|
| 1290 |
+
"logps/chosen": -681.2301025390625,
|
| 1291 |
+
"logps/rejected": -1178.5247802734375,
|
| 1292 |
+
"loss": 0.0747,
|
| 1293 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1294 |
+
"rewards/chosen": -0.19839105010032654,
|
| 1295 |
+
"rewards/margins": 0.2534715533256531,
|
| 1296 |
+
"rewards/rejected": -0.4518625736236572,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": -1.4997788667678833,
|
| 1303 |
+
"logits/rejected": -1.0186471939086914,
|
| 1304 |
+
"logps/chosen": -680.5430297851562,
|
| 1305 |
+
"logps/rejected": -1420.2906494140625,
|
| 1306 |
+
"loss": 0.0483,
|
| 1307 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 1308 |
+
"rewards/chosen": -0.212947279214859,
|
| 1309 |
+
"rewards/margins": 0.3238678574562073,
|
| 1310 |
+
"rewards/rejected": -0.5368151664733887,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": -1.8647575378417969,
|
| 1317 |
+
"logits/rejected": -1.020261526107788,
|
| 1318 |
+
"logps/chosen": -713.0181274414062,
|
| 1319 |
+
"logps/rejected": -1391.114013671875,
|
| 1320 |
+
"loss": 0.0696,
|
| 1321 |
+
"rewards/accuracies": 0.925000011920929,
|
| 1322 |
+
"rewards/chosen": -0.1832994669675827,
|
| 1323 |
+
"rewards/margins": 0.3290650248527527,
|
| 1324 |
+
"rewards/rejected": -0.5123645067214966,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": -1.7081159353256226,
|
| 1331 |
+
"logits/rejected": -0.9963458776473999,
|
| 1332 |
+
"logps/chosen": -635.8792724609375,
|
| 1333 |
+
"logps/rejected": -1234.2698974609375,
|
| 1334 |
+
"loss": 0.0705,
|
| 1335 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1336 |
+
"rewards/chosen": -0.1768474280834198,
|
| 1337 |
+
"rewards/margins": 0.28107231855392456,
|
| 1338 |
+
"rewards/rejected": -0.4579196870326996,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": -1.4116071462631226,
|
| 1345 |
+
"logits/rejected": -0.8761368989944458,
|
| 1346 |
+
"logps/chosen": -595.3892211914062,
|
| 1347 |
+
"logps/rejected": -1141.560546875,
|
| 1348 |
+
"loss": 0.0793,
|
| 1349 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1350 |
+
"rewards/chosen": -0.15147005021572113,
|
| 1351 |
+
"rewards/margins": 0.25574880838394165,
|
| 1352 |
+
"rewards/rejected": -0.407218873500824,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": -1.6526048183441162,
|
| 1359 |
+
"logits/rejected": -1.0399147272109985,
|
| 1360 |
+
"logps/chosen": -609.0975341796875,
|
| 1361 |
+
"logps/rejected": -1123.380126953125,
|
| 1362 |
+
"loss": 0.0792,
|
| 1363 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1364 |
+
"rewards/chosen": -0.18281634151935577,
|
| 1365 |
+
"rewards/margins": 0.2393408715724945,
|
| 1366 |
+
"rewards/rejected": -0.4221572279930115,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": -1.5252645015716553,
|
| 1373 |
+
"logits/rejected": -0.9064356088638306,
|
| 1374 |
+
"logps/chosen": -705.7091064453125,
|
| 1375 |
+
"logps/rejected": -1318.63525390625,
|
| 1376 |
+
"loss": 0.0836,
|
| 1377 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1378 |
+
"rewards/chosen": -0.24514424800872803,
|
| 1379 |
+
"rewards/margins": 0.25952351093292236,
|
| 1380 |
+
"rewards/rejected": -0.5046677589416504,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": -1.6756401062011719,
|
| 1387 |
+
"logits/rejected": -1.1370999813079834,
|
| 1388 |
+
"logps/chosen": -696.5738525390625,
|
| 1389 |
+
"logps/rejected": -1390.819580078125,
|
| 1390 |
+
"loss": 0.0636,
|
| 1391 |
+
"rewards/accuracies": 0.925000011920929,
|
| 1392 |
+
"rewards/chosen": -0.19441962242126465,
|
| 1393 |
+
"rewards/margins": 0.326028048992157,
|
| 1394 |
+
"rewards/rejected": -0.5204476714134216,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": -1.6806871891021729,
|
| 1401 |
+
"logits/rejected": -0.9537825584411621,
|
| 1402 |
+
"logps/chosen": -707.53564453125,
|
| 1403 |
+
"logps/rejected": -1410.8720703125,
|
| 1404 |
+
"loss": 0.0615,
|
| 1405 |
+
"rewards/accuracies": 0.875,
|
| 1406 |
+
"rewards/chosen": -0.2122100293636322,
|
| 1407 |
+
"rewards/margins": 0.30375686287879944,
|
| 1408 |
+
"rewards/rejected": -0.5159668922424316,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": -1.6937450170516968,
|
| 1415 |
+
"logits/rejected": -0.8107245564460754,
|
| 1416 |
+
"logps/chosen": -796.8629150390625,
|
| 1417 |
+
"logps/rejected": -1336.6978759765625,
|
| 1418 |
+
"loss": 0.0605,
|
| 1419 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1420 |
+
"rewards/chosen": -0.24894428253173828,
|
| 1421 |
+
"rewards/margins": 0.2776329815387726,
|
| 1422 |
+
"rewards/rejected": -0.5265771746635437,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": -1.3929378986358643,
|
| 1429 |
+
"logits/rejected": -1.027085542678833,
|
| 1430 |
+
"logps/chosen": -734.2984008789062,
|
| 1431 |
+
"logps/rejected": -1459.5130615234375,
|
| 1432 |
+
"loss": 0.0574,
|
| 1433 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1434 |
+
"rewards/chosen": -0.22584040462970734,
|
| 1435 |
+
"rewards/margins": 0.3117733895778656,
|
| 1436 |
+
"rewards/rejected": -0.5376137495040894,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": -1.5820205211639404,
|
| 1443 |
+
"logits/rejected": -0.9477416276931763,
|
| 1444 |
+
"logps/chosen": -645.0429077148438,
|
| 1445 |
+
"logps/rejected": -1322.5606689453125,
|
| 1446 |
+
"loss": 0.0627,
|
| 1447 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1448 |
+
"rewards/chosen": -0.2123514711856842,
|
| 1449 |
+
"rewards/margins": 0.3156682550907135,
|
| 1450 |
+
"rewards/rejected": -0.5280197262763977,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": -1.5610507726669312,
|
| 1457 |
+
"logits/rejected": -1.2100675106048584,
|
| 1458 |
+
"logps/chosen": -643.7442626953125,
|
| 1459 |
+
"logps/rejected": -1385.019287109375,
|
| 1460 |
+
"loss": 0.0935,
|
| 1461 |
+
"rewards/accuracies": 0.925000011920929,
|
| 1462 |
+
"rewards/chosen": -0.22349460422992706,
|
| 1463 |
+
"rewards/margins": 0.3161535859107971,
|
| 1464 |
+
"rewards/rejected": -0.539648175239563,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": -1.4837318658828735,
|
| 1471 |
+
"logits/rejected": -1.084937334060669,
|
| 1472 |
+
"logps/chosen": -602.5631103515625,
|
| 1473 |
+
"logps/rejected": -1196.161865234375,
|
| 1474 |
+
"loss": 0.072,
|
| 1475 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1476 |
+
"rewards/chosen": -0.19741597771644592,
|
| 1477 |
+
"rewards/margins": 0.2487364560365677,
|
| 1478 |
+
"rewards/rejected": -0.44615238904953003,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": -1.7739849090576172,
|
| 1485 |
+
"logits/rejected": -1.2259210348129272,
|
| 1486 |
+
"logps/chosen": -704.445068359375,
|
| 1487 |
+
"logps/rejected": -1330.047119140625,
|
| 1488 |
+
"loss": 0.0771,
|
| 1489 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1490 |
+
"rewards/chosen": -0.18476839363574982,
|
| 1491 |
+
"rewards/margins": 0.2862476408481598,
|
| 1492 |
+
"rewards/rejected": -0.4710160195827484,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": -1.4854525327682495,
|
| 1499 |
+
"logits/rejected": -0.9668752551078796,
|
| 1500 |
+
"logps/chosen": -602.9412841796875,
|
| 1501 |
+
"logps/rejected": -1244.30712890625,
|
| 1502 |
+
"loss": 0.0693,
|
| 1503 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1504 |
+
"rewards/chosen": -0.1880866140127182,
|
| 1505 |
+
"rewards/margins": 0.27652662992477417,
|
| 1506 |
+
"rewards/rejected": -0.46461325883865356,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": -1.6579099893569946,
|
| 1513 |
+
"logits/rejected": -1.1884429454803467,
|
| 1514 |
+
"logps/chosen": -621.8614501953125,
|
| 1515 |
+
"logps/rejected": -1197.624267578125,
|
| 1516 |
+
"loss": 0.0775,
|
| 1517 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1518 |
+
"rewards/chosen": -0.2010684311389923,
|
| 1519 |
+
"rewards/margins": 0.24993105232715607,
|
| 1520 |
+
"rewards/rejected": -0.4509994387626648,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": -1.5667635202407837,
|
| 1527 |
+
"logits/rejected": -1.0707104206085205,
|
| 1528 |
+
"logps/chosen": -598.3284301757812,
|
| 1529 |
+
"logps/rejected": -1302.890380859375,
|
| 1530 |
+
"loss": 0.0719,
|
| 1531 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1532 |
+
"rewards/chosen": -0.1652025729417801,
|
| 1533 |
+
"rewards/margins": 0.3089999854564667,
|
| 1534 |
+
"rewards/rejected": -0.47420254349708557,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": -1.6411329507827759,
|
| 1541 |
+
"logits/rejected": -0.8932744860649109,
|
| 1542 |
+
"logps/chosen": -635.66357421875,
|
| 1543 |
+
"logps/rejected": -1338.457275390625,
|
| 1544 |
+
"loss": 0.0729,
|
| 1545 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1546 |
+
"rewards/chosen": -0.19713297486305237,
|
| 1547 |
+
"rewards/margins": 0.33209219574928284,
|
| 1548 |
+
"rewards/rejected": -0.52922523021698,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": -1.6340553760528564,
|
| 1555 |
+
"logits/rejected": -0.8918849229812622,
|
| 1556 |
+
"logps/chosen": -700.44873046875,
|
| 1557 |
+
"logps/rejected": -1321.0467529296875,
|
| 1558 |
+
"loss": 0.1045,
|
| 1559 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1560 |
+
"rewards/chosen": -0.24557940661907196,
|
| 1561 |
+
"rewards/margins": 0.28524118661880493,
|
| 1562 |
+
"rewards/rejected": -0.5308206677436829,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": -1.6686341762542725,
|
| 1569 |
+
"logits/rejected": -1.1630200147628784,
|
| 1570 |
+
"logps/chosen": -622.9368286132812,
|
| 1571 |
+
"logps/rejected": -1250.1239013671875,
|
| 1572 |
+
"loss": 0.0765,
|
| 1573 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1574 |
+
"rewards/chosen": -0.188968688249588,
|
| 1575 |
+
"rewards/margins": 0.2903675138950348,
|
| 1576 |
+
"rewards/rejected": -0.4793361723423004,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": -1.606802225112915,
|
| 1583 |
+
"logits/rejected": -0.9541341066360474,
|
| 1584 |
+
"logps/chosen": -725.2327270507812,
|
| 1585 |
+
"logps/rejected": -1400.559326171875,
|
| 1586 |
+
"loss": 0.0566,
|
| 1587 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1588 |
+
"rewards/chosen": -0.20348282158374786,
|
| 1589 |
+
"rewards/margins": 0.2979651689529419,
|
| 1590 |
+
"rewards/rejected": -0.5014479756355286,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": -1.7844717502593994,
|
| 1597 |
+
"logits/rejected": -1.3071167469024658,
|
| 1598 |
+
"logps/chosen": -600.643798828125,
|
| 1599 |
+
"logps/rejected": -1224.3431396484375,
|
| 1600 |
+
"loss": 0.0653,
|
| 1601 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1602 |
+
"rewards/chosen": -0.12222178280353546,
|
| 1603 |
+
"rewards/margins": 0.28509068489074707,
|
| 1604 |
+
"rewards/rejected": -0.4073124825954437,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": -1.5732018947601318,
|
| 1611 |
+
"logits/rejected": -1.1557753086090088,
|
| 1612 |
+
"logps/chosen": -515.3253173828125,
|
| 1613 |
+
"logps/rejected": -1262.8011474609375,
|
| 1614 |
+
"loss": 0.0652,
|
| 1615 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1616 |
+
"rewards/chosen": -0.1322193145751953,
|
| 1617 |
+
"rewards/margins": 0.31077098846435547,
|
| 1618 |
+
"rewards/rejected": -0.442990243434906,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": -1.5410287380218506,
|
| 1625 |
+
"logits/rejected": -1.1754248142242432,
|
| 1626 |
+
"logps/chosen": -524.8809814453125,
|
| 1627 |
+
"logps/rejected": -1286.816162109375,
|
| 1628 |
+
"loss": 0.0595,
|
| 1629 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1630 |
+
"rewards/chosen": -0.14767605066299438,
|
| 1631 |
+
"rewards/margins": 0.2989698350429535,
|
| 1632 |
+
"rewards/rejected": -0.4466458857059479,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": -1.4306999444961548,
|
| 1639 |
+
"logits/rejected": -0.7852525115013123,
|
| 1640 |
+
"logps/chosen": -668.5032958984375,
|
| 1641 |
+
"logps/rejected": -1384.123046875,
|
| 1642 |
+
"loss": 0.0601,
|
| 1643 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1644 |
+
"rewards/chosen": -0.19471505284309387,
|
| 1645 |
+
"rewards/margins": 0.3257969617843628,
|
| 1646 |
+
"rewards/rejected": -0.5205119848251343,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": -1.3971048593521118,
|
| 1653 |
+
"logits/rejected": -0.927646279335022,
|
| 1654 |
+
"logps/chosen": -705.084228515625,
|
| 1655 |
+
"logps/rejected": -1310.335205078125,
|
| 1656 |
+
"loss": 0.077,
|
| 1657 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1658 |
+
"rewards/chosen": -0.21002249419689178,
|
| 1659 |
+
"rewards/margins": 0.27293241024017334,
|
| 1660 |
+
"rewards/rejected": -0.4829549193382263,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": -1.394499659538269,
|
| 1667 |
+
"logits/rejected": -0.9891581535339355,
|
| 1668 |
+
"logps/chosen": -564.6983642578125,
|
| 1669 |
+
"logps/rejected": -1220.2957763671875,
|
| 1670 |
+
"loss": 0.0915,
|
| 1671 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1672 |
+
"rewards/chosen": -0.16074185073375702,
|
| 1673 |
+
"rewards/margins": 0.2923213839530945,
|
| 1674 |
+
"rewards/rejected": -0.4530632495880127,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": -1.4173166751861572,
|
| 1681 |
+
"logits/rejected": -1.0692417621612549,
|
| 1682 |
+
"logps/chosen": -611.6875,
|
| 1683 |
+
"logps/rejected": -1175.55419921875,
|
| 1684 |
+
"loss": 0.0834,
|
| 1685 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1686 |
+
"rewards/chosen": -0.19331012666225433,
|
| 1687 |
+
"rewards/margins": 0.24444107711315155,
|
| 1688 |
+
"rewards/rejected": -0.4377512037754059,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": -1.5889681577682495,
|
| 1695 |
+
"logits/rejected": -0.8274670839309692,
|
| 1696 |
+
"logps/chosen": -562.2679443359375,
|
| 1697 |
+
"logps/rejected": -1287.1878662109375,
|
| 1698 |
+
"loss": 0.0698,
|
| 1699 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1700 |
+
"rewards/chosen": -0.14730304479599,
|
| 1701 |
+
"rewards/margins": 0.3559080958366394,
|
| 1702 |
+
"rewards/rejected": -0.5032111406326294,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": -1.555487871170044,
|
| 1709 |
+
"logits/rejected": -1.0957095623016357,
|
| 1710 |
+
"logps/chosen": -603.4686889648438,
|
| 1711 |
+
"logps/rejected": -1382.740234375,
|
| 1712 |
+
"loss": 0.0576,
|
| 1713 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1714 |
+
"rewards/chosen": -0.19595518708229065,
|
| 1715 |
+
"rewards/margins": 0.31043919920921326,
|
| 1716 |
+
"rewards/rejected": -0.5063944458961487,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": -1.5740302801132202,
|
| 1723 |
+
"logits/rejected": -1.0648415088653564,
|
| 1724 |
+
"logps/chosen": -545.7623291015625,
|
| 1725 |
+
"logps/rejected": -1294.9000244140625,
|
| 1726 |
+
"loss": 0.0593,
|
| 1727 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1728 |
+
"rewards/chosen": -0.16540229320526123,
|
| 1729 |
+
"rewards/margins": 0.3433569669723511,
|
| 1730 |
+
"rewards/rejected": -0.5087593197822571,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": -1.6975386142730713,
|
| 1737 |
+
"logits/rejected": -0.972979724407196,
|
| 1738 |
+
"logps/chosen": -599.3750610351562,
|
| 1739 |
+
"logps/rejected": -1323.2943115234375,
|
| 1740 |
+
"loss": 0.0697,
|
| 1741 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1742 |
+
"rewards/chosen": -0.17359238862991333,
|
| 1743 |
+
"rewards/margins": 0.32719483971595764,
|
| 1744 |
+
"rewards/rejected": -0.5007871985435486,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": -1.4844261407852173,
|
| 1751 |
+
"logits/rejected": -1.1203126907348633,
|
| 1752 |
+
"logps/chosen": -650.5365600585938,
|
| 1753 |
+
"logps/rejected": -1473.968994140625,
|
| 1754 |
+
"loss": 0.058,
|
| 1755 |
+
"rewards/accuracies": 0.925000011920929,
|
| 1756 |
+
"rewards/chosen": -0.1938629448413849,
|
| 1757 |
+
"rewards/margins": 0.3511131703853607,
|
| 1758 |
+
"rewards/rejected": -0.5449761748313904,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": -1.6657180786132812,
|
| 1765 |
+
"logits/rejected": -1.084463119506836,
|
| 1766 |
+
"logps/chosen": -700.7429809570312,
|
| 1767 |
+
"logps/rejected": -1405.9703369140625,
|
| 1768 |
+
"loss": 0.079,
|
| 1769 |
+
"rewards/accuracies": 0.875,
|
| 1770 |
+
"rewards/chosen": -0.23423318564891815,
|
| 1771 |
+
"rewards/margins": 0.29485347867012024,
|
| 1772 |
+
"rewards/rejected": -0.5290866494178772,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": -1.6721817255020142,
|
| 1779 |
+
"logits/rejected": -1.380765676498413,
|
| 1780 |
+
"logps/chosen": -583.6463623046875,
|
| 1781 |
+
"logps/rejected": -1295.441650390625,
|
| 1782 |
+
"loss": 0.0835,
|
| 1783 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1784 |
+
"rewards/chosen": -0.1985049545764923,
|
| 1785 |
+
"rewards/margins": 0.2941189706325531,
|
| 1786 |
+
"rewards/rejected": -0.49262386560440063,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": -1.4841744899749756,
|
| 1793 |
+
"logits/rejected": -0.8630777597427368,
|
| 1794 |
+
"logps/chosen": -643.0660400390625,
|
| 1795 |
+
"logps/rejected": -1336.444580078125,
|
| 1796 |
+
"loss": 0.0778,
|
| 1797 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1798 |
+
"rewards/chosen": -0.18584981560707092,
|
| 1799 |
+
"rewards/margins": 0.3217209577560425,
|
| 1800 |
+
"rewards/rejected": -0.507570743560791,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": -1.5687516927719116,
|
| 1807 |
+
"logits/rejected": -1.116389513015747,
|
| 1808 |
+
"logps/chosen": -692.3853759765625,
|
| 1809 |
+
"logps/rejected": -1371.9207763671875,
|
| 1810 |
+
"loss": 0.0825,
|
| 1811 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1812 |
+
"rewards/chosen": -0.21149520576000214,
|
| 1813 |
+
"rewards/margins": 0.29092541337013245,
|
| 1814 |
+
"rewards/rejected": -0.5024206042289734,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": -1.6287143230438232,
|
| 1821 |
+
"logits/rejected": -1.275514006614685,
|
| 1822 |
+
"logps/chosen": -669.5472412109375,
|
| 1823 |
+
"logps/rejected": -1387.4217529296875,
|
| 1824 |
+
"loss": 0.0611,
|
| 1825 |
+
"rewards/accuracies": 0.875,
|
| 1826 |
+
"rewards/chosen": -0.22967293858528137,
|
| 1827 |
+
"rewards/margins": 0.29838404059410095,
|
| 1828 |
+
"rewards/rejected": -0.5280569195747375,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": -1.565351128578186,
|
| 1835 |
+
"logits/rejected": -1.1336759328842163,
|
| 1836 |
+
"logps/chosen": -672.641357421875,
|
| 1837 |
+
"logps/rejected": -1306.2833251953125,
|
| 1838 |
+
"loss": 0.0709,
|
| 1839 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1840 |
+
"rewards/chosen": -0.20514118671417236,
|
| 1841 |
+
"rewards/margins": 0.29974114894866943,
|
| 1842 |
+
"rewards/rejected": -0.5048823356628418,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": -1.4452847242355347,
|
| 1849 |
+
"logits/rejected": -1.112763524055481,
|
| 1850 |
+
"logps/chosen": -749.3744506835938,
|
| 1851 |
+
"logps/rejected": -1290.004150390625,
|
| 1852 |
+
"loss": 0.077,
|
| 1853 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1854 |
+
"rewards/chosen": -0.24272188544273376,
|
| 1855 |
+
"rewards/margins": 0.256221204996109,
|
| 1856 |
+
"rewards/rejected": -0.498943030834198,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": -1.8478819131851196,
|
| 1863 |
+
"logits/rejected": -0.9717103242874146,
|
| 1864 |
+
"logps/chosen": -609.0137329101562,
|
| 1865 |
+
"logps/rejected": -1343.593505859375,
|
| 1866 |
+
"loss": 0.0584,
|
| 1867 |
+
"rewards/accuracies": 0.875,
|
| 1868 |
+
"rewards/chosen": -0.15877112746238708,
|
| 1869 |
+
"rewards/margins": 0.347220242023468,
|
| 1870 |
+
"rewards/rejected": -0.5059913396835327,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": -1.8385093212127686,
|
| 1877 |
+
"logits/rejected": -1.008526086807251,
|
| 1878 |
+
"logps/chosen": -653.6995239257812,
|
| 1879 |
+
"logps/rejected": -1285.072021484375,
|
| 1880 |
+
"loss": 0.0666,
|
| 1881 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1882 |
+
"rewards/chosen": -0.17687949538230896,
|
| 1883 |
+
"rewards/margins": 0.3174961805343628,
|
| 1884 |
+
"rewards/rejected": -0.49437564611434937,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": -1.7583434581756592,
|
| 1891 |
+
"logits/rejected": -1.0419925451278687,
|
| 1892 |
+
"logps/chosen": -690.4033203125,
|
| 1893 |
+
"logps/rejected": -1265.659423828125,
|
| 1894 |
+
"loss": 0.0614,
|
| 1895 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1896 |
+
"rewards/chosen": -0.18742068111896515,
|
| 1897 |
+
"rewards/margins": 0.3070259392261505,
|
| 1898 |
+
"rewards/rejected": -0.49444660544395447,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": -1.6502761840820312,
|
| 1905 |
+
"logits/rejected": -1.0335781574249268,
|
| 1906 |
+
"logps/chosen": -684.777099609375,
|
| 1907 |
+
"logps/rejected": -1356.904541015625,
|
| 1908 |
+
"loss": 0.0649,
|
| 1909 |
+
"rewards/accuracies": 0.875,
|
| 1910 |
+
"rewards/chosen": -0.1998976767063141,
|
| 1911 |
+
"rewards/margins": 0.31228137016296387,
|
| 1912 |
+
"rewards/rejected": -0.5121790170669556,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": -1.586370587348938,
|
| 1919 |
+
"logits/rejected": -1.2236953973770142,
|
| 1920 |
+
"logps/chosen": -682.054931640625,
|
| 1921 |
+
"logps/rejected": -1410.645263671875,
|
| 1922 |
+
"loss": 0.0772,
|
| 1923 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1924 |
+
"rewards/chosen": -0.16813689470291138,
|
| 1925 |
+
"rewards/margins": 0.3100218176841736,
|
| 1926 |
+
"rewards/rejected": -0.47815871238708496,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": -1.5936353206634521,
|
| 1933 |
+
"logits/rejected": -0.8407376408576965,
|
| 1934 |
+
"logps/chosen": -605.4591064453125,
|
| 1935 |
+
"logps/rejected": -1212.3292236328125,
|
| 1936 |
+
"loss": 0.0761,
|
| 1937 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1938 |
+
"rewards/chosen": -0.18272905051708221,
|
| 1939 |
+
"rewards/margins": 0.28132033348083496,
|
| 1940 |
+
"rewards/rejected": -0.46404939889907837,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": -1.4739325046539307,
|
| 1947 |
+
"logits/rejected": -1.010182499885559,
|
| 1948 |
+
"logps/chosen": -632.5126953125,
|
| 1949 |
+
"logps/rejected": -1296.5963134765625,
|
| 1950 |
+
"loss": 0.0674,
|
| 1951 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1952 |
+
"rewards/chosen": -0.16441567242145538,
|
| 1953 |
+
"rewards/margins": 0.30406633019447327,
|
| 1954 |
+
"rewards/rejected": -0.46848195791244507,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": -1.432307243347168,
|
| 1961 |
+
"logits/rejected": -0.9531373977661133,
|
| 1962 |
+
"logps/chosen": -556.3389892578125,
|
| 1963 |
+
"logps/rejected": -1208.9351806640625,
|
| 1964 |
+
"loss": 0.0902,
|
| 1965 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1966 |
+
"rewards/chosen": -0.15656593441963196,
|
| 1967 |
+
"rewards/margins": 0.3002859652042389,
|
| 1968 |
+
"rewards/rejected": -0.45685189962387085,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": -1.424543857574463,
|
| 1975 |
+
"logits/rejected": -1.2399370670318604,
|
| 1976 |
+
"logps/chosen": -589.8561401367188,
|
| 1977 |
+
"logps/rejected": -1314.0848388671875,
|
| 1978 |
+
"loss": 0.0612,
|
| 1979 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 1980 |
+
"rewards/chosen": -0.20633108913898468,
|
| 1981 |
+
"rewards/margins": 0.29661285877227783,
|
| 1982 |
+
"rewards/rejected": -0.5029439330101013,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": -1.7470901012420654,
|
| 1989 |
+
"logits/rejected": -0.9560185670852661,
|
| 1990 |
+
"logps/chosen": -725.0481567382812,
|
| 1991 |
+
"logps/rejected": -1290.740234375,
|
| 1992 |
+
"loss": 0.0812,
|
| 1993 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1994 |
+
"rewards/chosen": -0.21728627383708954,
|
| 1995 |
+
"rewards/margins": 0.2701825797557831,
|
| 1996 |
+
"rewards/rejected": -0.4874688684940338,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": -1.7515980005264282,
|
| 2003 |
+
"logits/rejected": -1.0790961980819702,
|
| 2004 |
+
"logps/chosen": -780.40625,
|
| 2005 |
+
"logps/rejected": -1295.2103271484375,
|
| 2006 |
+
"loss": 0.0703,
|
| 2007 |
+
"rewards/accuracies": 0.875,
|
| 2008 |
+
"rewards/chosen": -0.2122478485107422,
|
| 2009 |
+
"rewards/margins": 0.28053194284439087,
|
| 2010 |
+
"rewards/rejected": -0.4927797317504883,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": -1.7474523782730103,
|
| 2017 |
+
"logits/rejected": -1.2634751796722412,
|
| 2018 |
+
"logps/chosen": -568.755859375,
|
| 2019 |
+
"logps/rejected": -1179.9197998046875,
|
| 2020 |
+
"loss": 0.0782,
|
| 2021 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2022 |
+
"rewards/chosen": -0.16928540170192719,
|
| 2023 |
+
"rewards/margins": 0.2702566385269165,
|
| 2024 |
+
"rewards/rejected": -0.4395419955253601,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": -1.5095304250717163,
|
| 2031 |
+
"logits/rejected": -1.0166012048721313,
|
| 2032 |
+
"logps/chosen": -598.3046264648438,
|
| 2033 |
+
"logps/rejected": -1174.777099609375,
|
| 2034 |
+
"loss": 0.0757,
|
| 2035 |
+
"rewards/accuracies": 0.699999988079071,
|
| 2036 |
+
"rewards/chosen": -0.18509359657764435,
|
| 2037 |
+
"rewards/margins": 0.2518666684627533,
|
| 2038 |
+
"rewards/rejected": -0.43696027994155884,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": -1.4101845026016235,
|
| 2045 |
+
"logits/rejected": -1.092771291732788,
|
| 2046 |
+
"logps/chosen": -667.2734375,
|
| 2047 |
+
"logps/rejected": -1364.451416015625,
|
| 2048 |
+
"loss": 0.0659,
|
| 2049 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2050 |
+
"rewards/chosen": -0.17928771674633026,
|
| 2051 |
+
"rewards/margins": 0.2924876809120178,
|
| 2052 |
+
"rewards/rejected": -0.4717753827571869,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": -1.8168420791625977,
|
| 2059 |
+
"logits/rejected": -1.1101696491241455,
|
| 2060 |
+
"logps/chosen": -688.029052734375,
|
| 2061 |
+
"logps/rejected": -1324.9195556640625,
|
| 2062 |
+
"loss": 0.0877,
|
| 2063 |
+
"rewards/accuracies": 0.875,
|
| 2064 |
+
"rewards/chosen": -0.1806691437959671,
|
| 2065 |
+
"rewards/margins": 0.2972376346588135,
|
| 2066 |
+
"rewards/rejected": -0.4779067933559418,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": -1.6712579727172852,
|
| 2073 |
+
"logits/rejected": -1.150111436843872,
|
| 2074 |
+
"logps/chosen": -659.3943481445312,
|
| 2075 |
+
"logps/rejected": -1223.517822265625,
|
| 2076 |
+
"loss": 0.0633,
|
| 2077 |
+
"rewards/accuracies": 0.75,
|
| 2078 |
+
"rewards/chosen": -0.17544549703598022,
|
| 2079 |
+
"rewards/margins": 0.2652505934238434,
|
| 2080 |
+
"rewards/rejected": -0.4406960904598236,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": -1.6671737432479858,
|
| 2087 |
+
"logits/rejected": -1.052958369255066,
|
| 2088 |
+
"logps/chosen": -633.9606323242188,
|
| 2089 |
+
"logps/rejected": -1298.9013671875,
|
| 2090 |
+
"loss": 0.0725,
|
| 2091 |
+
"rewards/accuracies": 0.875,
|
| 2092 |
+
"rewards/chosen": -0.14675958454608917,
|
| 2093 |
+
"rewards/margins": 0.3194653391838074,
|
| 2094 |
+
"rewards/rejected": -0.4662249982357025,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": -1.67061448097229,
|
| 2101 |
+
"logits/rejected": -0.9715604782104492,
|
| 2102 |
+
"logps/chosen": -676.41748046875,
|
| 2103 |
+
"logps/rejected": -1426.921875,
|
| 2104 |
+
"loss": 0.0659,
|
| 2105 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 2106 |
+
"rewards/chosen": -0.17396974563598633,
|
| 2107 |
+
"rewards/margins": 0.3531404137611389,
|
| 2108 |
+
"rewards/rejected": -0.5271100997924805,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": -1.5575685501098633,
|
| 2115 |
+
"logits/rejected": -1.0988106727600098,
|
| 2116 |
+
"logps/chosen": -639.9945678710938,
|
| 2117 |
+
"logps/rejected": -1345.9605712890625,
|
| 2118 |
+
"loss": 0.0642,
|
| 2119 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2120 |
+
"rewards/chosen": -0.16887350380420685,
|
| 2121 |
+
"rewards/margins": 0.3250221610069275,
|
| 2122 |
+
"rewards/rejected": -0.49389567971229553,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": -1.6690590381622314,
|
| 2129 |
+
"logits/rejected": -1.222768783569336,
|
| 2130 |
+
"logps/chosen": -570.43359375,
|
| 2131 |
+
"logps/rejected": -1150.0074462890625,
|
| 2132 |
+
"loss": 0.0805,
|
| 2133 |
+
"rewards/accuracies": 0.75,
|
| 2134 |
+
"rewards/chosen": -0.14664652943611145,
|
| 2135 |
+
"rewards/margins": 0.266937255859375,
|
| 2136 |
+
"rewards/rejected": -0.41358375549316406,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": -1.7312631607055664,
|
| 2143 |
+
"logits/rejected": -1.1374391317367554,
|
| 2144 |
+
"logps/chosen": -684.4765625,
|
| 2145 |
+
"logps/rejected": -1306.3896484375,
|
| 2146 |
+
"loss": 0.0647,
|
| 2147 |
+
"rewards/accuracies": 0.875,
|
| 2148 |
+
"rewards/chosen": -0.18494835495948792,
|
| 2149 |
+
"rewards/margins": 0.2902507185935974,
|
| 2150 |
+
"rewards/rejected": -0.4751990735530853,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": -1.5153663158416748,
|
| 2157 |
+
"logits/rejected": -0.8972418904304504,
|
| 2158 |
+
"logps/chosen": -728.5112915039062,
|
| 2159 |
+
"logps/rejected": -1351.343994140625,
|
| 2160 |
+
"loss": 0.0615,
|
| 2161 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2162 |
+
"rewards/chosen": -0.18961231410503387,
|
| 2163 |
+
"rewards/margins": 0.2944989502429962,
|
| 2164 |
+
"rewards/rejected": -0.4841112494468689,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": -1.5436667203903198,
|
| 2171 |
+
"logits/rejected": -1.0006486177444458,
|
| 2172 |
+
"logps/chosen": -612.3607788085938,
|
| 2173 |
+
"logps/rejected": -1392.751220703125,
|
| 2174 |
+
"loss": 0.063,
|
| 2175 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2176 |
+
"rewards/chosen": -0.17778488993644714,
|
| 2177 |
+
"rewards/margins": 0.3482268452644348,
|
| 2178 |
+
"rewards/rejected": -0.5260116457939148,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": -1.6940997838974,
|
| 2185 |
+
"logits/rejected": -0.9330794215202332,
|
| 2186 |
+
"logps/chosen": -640.0445556640625,
|
| 2187 |
+
"logps/rejected": -1303.176025390625,
|
| 2188 |
+
"loss": 0.0609,
|
| 2189 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2190 |
+
"rewards/chosen": -0.16365936398506165,
|
| 2191 |
+
"rewards/margins": 0.3356683552265167,
|
| 2192 |
+
"rewards/rejected": -0.4993276596069336,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": -1.6769466400146484,
|
| 2199 |
+
"logits/rejected": -1.0806591510772705,
|
| 2200 |
+
"logps/chosen": -695.0977783203125,
|
| 2201 |
+
"logps/rejected": -1364.507568359375,
|
| 2202 |
+
"loss": 0.0848,
|
| 2203 |
+
"rewards/accuracies": 0.875,
|
| 2204 |
+
"rewards/chosen": -0.19976365566253662,
|
| 2205 |
+
"rewards/margins": 0.30775851011276245,
|
| 2206 |
+
"rewards/rejected": -0.5075221657752991,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": -1.6324169635772705,
|
| 2213 |
+
"logits/rejected": -1.0680665969848633,
|
| 2214 |
+
"logps/chosen": -531.390869140625,
|
| 2215 |
+
"logps/rejected": -1179.87109375,
|
| 2216 |
+
"loss": 0.0585,
|
| 2217 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2218 |
+
"rewards/chosen": -0.14503778517246246,
|
| 2219 |
+
"rewards/margins": 0.3031737208366394,
|
| 2220 |
+
"rewards/rejected": -0.4482114911079407,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": -1.3932682275772095,
|
| 2227 |
+
"logits/rejected": -0.8974223136901855,
|
| 2228 |
+
"logps/chosen": -596.6116333007812,
|
| 2229 |
+
"logps/rejected": -1304.460205078125,
|
| 2230 |
+
"loss": 0.0652,
|
| 2231 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2232 |
+
"rewards/chosen": -0.17924772202968597,
|
| 2233 |
+
"rewards/margins": 0.32127711176872253,
|
| 2234 |
+
"rewards/rejected": -0.5005248785018921,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": -1.5574601888656616,
|
| 2241 |
+
"logits/rejected": -1.1562343835830688,
|
| 2242 |
+
"logps/chosen": -570.518798828125,
|
| 2243 |
+
"logps/rejected": -1341.0030517578125,
|
| 2244 |
+
"loss": 0.0601,
|
| 2245 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2246 |
+
"rewards/chosen": -0.16952624917030334,
|
| 2247 |
+
"rewards/margins": 0.30771198868751526,
|
| 2248 |
+
"rewards/rejected": -0.477238267660141,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": -1.7783597707748413,
|
| 2255 |
+
"logits/rejected": -1.0141966342926025,
|
| 2256 |
+
"logps/chosen": -588.4285888671875,
|
| 2257 |
+
"logps/rejected": -1261.8870849609375,
|
| 2258 |
+
"loss": 0.0478,
|
| 2259 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2260 |
+
"rewards/chosen": -0.14779958128929138,
|
| 2261 |
+
"rewards/margins": 0.32103490829467773,
|
| 2262 |
+
"rewards/rejected": -0.4688344895839691,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": -1.584507942199707,
|
| 2269 |
+
"logits/rejected": -1.1659561395645142,
|
| 2270 |
+
"logps/chosen": -588.9163818359375,
|
| 2271 |
+
"logps/rejected": -1310.104248046875,
|
| 2272 |
+
"loss": 0.0611,
|
| 2273 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2274 |
+
"rewards/chosen": -0.15733642876148224,
|
| 2275 |
+
"rewards/margins": 0.3178580403327942,
|
| 2276 |
+
"rewards/rejected": -0.47519451379776,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": -1.7042678594589233,
|
| 2283 |
+
"logits/rejected": -0.97917640209198,
|
| 2284 |
+
"logps/chosen": -641.7584228515625,
|
| 2285 |
+
"logps/rejected": -1274.931640625,
|
| 2286 |
+
"loss": 0.0733,
|
| 2287 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2288 |
+
"rewards/chosen": -0.1470673382282257,
|
| 2289 |
+
"rewards/margins": 0.30876293778419495,
|
| 2290 |
+
"rewards/rejected": -0.4558301866054535,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": -1.5918161869049072,
|
| 2297 |
+
"logits/rejected": -0.6565667986869812,
|
| 2298 |
+
"logps/chosen": -689.022705078125,
|
| 2299 |
+
"logps/rejected": -1258.276123046875,
|
| 2300 |
+
"loss": 0.057,
|
| 2301 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2302 |
+
"rewards/chosen": -0.19913257658481598,
|
| 2303 |
+
"rewards/margins": 0.2890087962150574,
|
| 2304 |
+
"rewards/rejected": -0.48814138770103455,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": -1.3946174383163452,
|
| 2311 |
+
"logits/rejected": -0.9993401765823364,
|
| 2312 |
+
"logps/chosen": -509.4546813964844,
|
| 2313 |
+
"logps/rejected": -1304.57373046875,
|
| 2314 |
+
"loss": 0.0567,
|
| 2315 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2316 |
+
"rewards/chosen": -0.14354419708251953,
|
| 2317 |
+
"rewards/margins": 0.3309141993522644,
|
| 2318 |
+
"rewards/rejected": -0.47445839643478394,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": -1.566758394241333,
|
| 2325 |
+
"logits/rejected": -1.0273525714874268,
|
| 2326 |
+
"logps/chosen": -628.7932739257812,
|
| 2327 |
+
"logps/rejected": -1379.468017578125,
|
| 2328 |
+
"loss": 0.0589,
|
| 2329 |
+
"rewards/accuracies": 0.875,
|
| 2330 |
+
"rewards/chosen": -0.18863460421562195,
|
| 2331 |
+
"rewards/margins": 0.322934091091156,
|
| 2332 |
+
"rewards/rejected": -0.5115686655044556,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": -1.3873016834259033,
|
| 2339 |
+
"logits/rejected": -1.0786285400390625,
|
| 2340 |
+
"logps/chosen": -586.18994140625,
|
| 2341 |
+
"logps/rejected": -1279.546630859375,
|
| 2342 |
+
"loss": 0.0641,
|
| 2343 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2344 |
+
"rewards/chosen": -0.1676522046327591,
|
| 2345 |
+
"rewards/margins": 0.30437177419662476,
|
| 2346 |
+
"rewards/rejected": -0.47202396392822266,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": -1.485750436782837,
|
| 2353 |
+
"logits/rejected": -1.0917704105377197,
|
| 2354 |
+
"logps/chosen": -545.1902465820312,
|
| 2355 |
+
"logps/rejected": -1163.88232421875,
|
| 2356 |
+
"loss": 0.0665,
|
| 2357 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2358 |
+
"rewards/chosen": -0.15834537148475647,
|
| 2359 |
+
"rewards/margins": 0.2890353500843048,
|
| 2360 |
+
"rewards/rejected": -0.4473806917667389,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": -1.6250501871109009,
|
| 2367 |
+
"logits/rejected": -0.9212428331375122,
|
| 2368 |
+
"logps/chosen": -730.2625122070312,
|
| 2369 |
+
"logps/rejected": -1425.178466796875,
|
| 2370 |
+
"loss": 0.0554,
|
| 2371 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2372 |
+
"rewards/chosen": -0.21810364723205566,
|
| 2373 |
+
"rewards/margins": 0.31878364086151123,
|
| 2374 |
+
"rewards/rejected": -0.5368873476982117,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": -1.6128244400024414,
|
| 2381 |
+
"logits/rejected": -0.892177402973175,
|
| 2382 |
+
"logps/chosen": -818.83154296875,
|
| 2383 |
+
"logps/rejected": -1455.890625,
|
| 2384 |
+
"loss": 0.0571,
|
| 2385 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2386 |
+
"rewards/chosen": -0.2139212191104889,
|
| 2387 |
+
"rewards/margins": 0.3149806261062622,
|
| 2388 |
+
"rewards/rejected": -0.5289018750190735,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": -1.692974328994751,
|
| 2395 |
+
"logits/rejected": -0.840363621711731,
|
| 2396 |
+
"logps/chosen": -631.8255615234375,
|
| 2397 |
+
"logps/rejected": -1351.36181640625,
|
| 2398 |
+
"loss": 0.0581,
|
| 2399 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2400 |
+
"rewards/chosen": -0.16292592883110046,
|
| 2401 |
+
"rewards/margins": 0.3375861942768097,
|
| 2402 |
+
"rewards/rejected": -0.5005121231079102,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": -1.6714107990264893,
|
| 2409 |
+
"logits/rejected": -0.9252397418022156,
|
| 2410 |
+
"logps/chosen": -709.752685546875,
|
| 2411 |
+
"logps/rejected": -1277.791748046875,
|
| 2412 |
+
"loss": 0.0673,
|
| 2413 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2414 |
+
"rewards/chosen": -0.2090533971786499,
|
| 2415 |
+
"rewards/margins": 0.2772943079471588,
|
| 2416 |
+
"rewards/rejected": -0.4863477349281311,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": -1.5991243124008179,
|
| 2423 |
+
"logits/rejected": -1.109691858291626,
|
| 2424 |
+
"logps/chosen": -545.5228271484375,
|
| 2425 |
+
"logps/rejected": -1269.11572265625,
|
| 2426 |
+
"loss": 0.0427,
|
| 2427 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2428 |
+
"rewards/chosen": -0.14758913218975067,
|
| 2429 |
+
"rewards/margins": 0.3135208189487457,
|
| 2430 |
+
"rewards/rejected": -0.4611099660396576,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": -1.5346282720565796,
|
| 2437 |
+
"logits/rejected": -1.0807735919952393,
|
| 2438 |
+
"logps/chosen": -547.136474609375,
|
| 2439 |
+
"logps/rejected": -1270.7979736328125,
|
| 2440 |
+
"loss": 0.0532,
|
| 2441 |
+
"rewards/accuracies": 0.875,
|
| 2442 |
+
"rewards/chosen": -0.16198331117630005,
|
| 2443 |
+
"rewards/margins": 0.3293561637401581,
|
| 2444 |
+
"rewards/rejected": -0.4913395345211029,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": -1.6227678060531616,
|
| 2451 |
+
"logits/rejected": -1.0483043193817139,
|
| 2452 |
+
"logps/chosen": -680.5284423828125,
|
| 2453 |
+
"logps/rejected": -1272.281494140625,
|
| 2454 |
+
"loss": 0.0837,
|
| 2455 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2456 |
+
"rewards/chosen": -0.1814839243888855,
|
| 2457 |
+
"rewards/margins": 0.2653439939022064,
|
| 2458 |
+
"rewards/rejected": -0.44682788848876953,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": -1.5319443941116333,
|
| 2465 |
+
"logits/rejected": -0.925460159778595,
|
| 2466 |
+
"logps/chosen": -579.5850830078125,
|
| 2467 |
+
"logps/rejected": -1320.3759765625,
|
| 2468 |
+
"loss": 0.0402,
|
| 2469 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2470 |
+
"rewards/chosen": -0.17916153371334076,
|
| 2471 |
+
"rewards/margins": 0.3212929368019104,
|
| 2472 |
+
"rewards/rejected": -0.5004544854164124,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": -1.565772294998169,
|
| 2479 |
+
"logits/rejected": -1.096321940422058,
|
| 2480 |
+
"logps/chosen": -534.4620361328125,
|
| 2481 |
+
"logps/rejected": -1283.698486328125,
|
| 2482 |
+
"loss": 0.0594,
|
| 2483 |
+
"rewards/accuracies": 0.875,
|
| 2484 |
+
"rewards/chosen": -0.16089969873428345,
|
| 2485 |
+
"rewards/margins": 0.31563904881477356,
|
| 2486 |
+
"rewards/rejected": -0.4765387177467346,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": -1.536378026008606,
|
| 2493 |
+
"logits/rejected": -1.0789868831634521,
|
| 2494 |
+
"logps/chosen": -596.4452514648438,
|
| 2495 |
+
"logps/rejected": -1328.3414306640625,
|
| 2496 |
+
"loss": 0.065,
|
| 2497 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2498 |
+
"rewards/chosen": -0.1719946265220642,
|
| 2499 |
+
"rewards/margins": 0.3378538489341736,
|
| 2500 |
+
"rewards/rejected": -0.5098485350608826,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": -1.4989714622497559,
|
| 2507 |
+
"logits/rejected": -0.8038862347602844,
|
| 2508 |
+
"logps/chosen": -660.2965087890625,
|
| 2509 |
+
"logps/rejected": -1396.283203125,
|
| 2510 |
+
"loss": 0.0495,
|
| 2511 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2512 |
+
"rewards/chosen": -0.187455415725708,
|
| 2513 |
+
"rewards/margins": 0.32814398407936096,
|
| 2514 |
+
"rewards/rejected": -0.5155993700027466,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": -1.6087837219238281,
|
| 2521 |
+
"logits/rejected": -1.2250018119812012,
|
| 2522 |
+
"logps/chosen": -563.0875854492188,
|
| 2523 |
+
"logps/rejected": -1169.5546875,
|
| 2524 |
+
"loss": 0.0771,
|
| 2525 |
+
"rewards/accuracies": 0.800000011920929,
|
| 2526 |
+
"rewards/chosen": -0.16033567488193512,
|
| 2527 |
+
"rewards/margins": 0.2670869529247284,
|
| 2528 |
+
"rewards/rejected": -0.4274226129055023,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": -1.6887807846069336,
|
| 2535 |
+
"logits/rejected": -1.1670516729354858,
|
| 2536 |
+
"logps/chosen": -587.798583984375,
|
| 2537 |
+
"logps/rejected": -1290.9248046875,
|
| 2538 |
+
"loss": 0.0879,
|
| 2539 |
+
"rewards/accuracies": 0.925000011920929,
|
| 2540 |
+
"rewards/chosen": -0.1586194485425949,
|
| 2541 |
+
"rewards/margins": 0.324545294046402,
|
| 2542 |
+
"rewards/rejected": -0.48316478729248047,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": -1.4965977668762207,
|
| 2549 |
+
"logits/rejected": -1.1161562204360962,
|
| 2550 |
+
"logps/chosen": -609.0550537109375,
|
| 2551 |
+
"logps/rejected": -1276.494140625,
|
| 2552 |
+
"loss": 0.0809,
|
| 2553 |
+
"rewards/accuracies": 0.875,
|
| 2554 |
+
"rewards/chosen": -0.19842302799224854,
|
| 2555 |
+
"rewards/margins": 0.28119295835494995,
|
| 2556 |
+
"rewards/rejected": -0.4796159863471985,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": -1.492071270942688,
|
| 2563 |
+
"logits/rejected": -1.0277793407440186,
|
| 2564 |
+
"logps/chosen": -578.52734375,
|
| 2565 |
+
"logps/rejected": -1304.014404296875,
|
| 2566 |
+
"loss": 0.0619,
|
| 2567 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2568 |
+
"rewards/chosen": -0.19293084740638733,
|
| 2569 |
+
"rewards/margins": 0.2969210743904114,
|
| 2570 |
+
"rewards/rejected": -0.4898518919944763,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": -1.704077124595642,
|
| 2577 |
+
"logits/rejected": -0.9419189691543579,
|
| 2578 |
+
"logps/chosen": -614.6487426757812,
|
| 2579 |
+
"logps/rejected": -1268.572509765625,
|
| 2580 |
+
"loss": 0.0591,
|
| 2581 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2582 |
+
"rewards/chosen": -0.1651904135942459,
|
| 2583 |
+
"rewards/margins": 0.3228462338447571,
|
| 2584 |
+
"rewards/rejected": -0.4880366325378418,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": -1.511736273765564,
|
| 2591 |
+
"logits/rejected": -0.8690618276596069,
|
| 2592 |
+
"logps/chosen": -628.6026611328125,
|
| 2593 |
+
"logps/rejected": -1221.356689453125,
|
| 2594 |
+
"loss": 0.0798,
|
| 2595 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2596 |
+
"rewards/chosen": -0.18123619258403778,
|
| 2597 |
+
"rewards/margins": 0.28583425283432007,
|
| 2598 |
+
"rewards/rejected": -0.46707040071487427,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": -1.657123327255249,
|
| 2605 |
+
"logits/rejected": -1.1370261907577515,
|
| 2606 |
+
"logps/chosen": -642.603515625,
|
| 2607 |
+
"logps/rejected": -1387.967529296875,
|
| 2608 |
+
"loss": 0.0748,
|
| 2609 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 2610 |
+
"rewards/chosen": -0.1762182116508484,
|
| 2611 |
+
"rewards/margins": 0.3377261161804199,
|
| 2612 |
+
"rewards/rejected": -0.5139442682266235,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": -1.7564224004745483,
|
| 2619 |
+
"logits/rejected": -0.7881779074668884,
|
| 2620 |
+
"logps/chosen": -575.2108154296875,
|
| 2621 |
+
"logps/rejected": -1265.4073486328125,
|
| 2622 |
+
"loss": 0.0536,
|
| 2623 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 2624 |
+
"rewards/chosen": -0.15589746832847595,
|
| 2625 |
+
"rewards/margins": 0.3169409930706024,
|
| 2626 |
+
"rewards/rejected": -0.47283846139907837,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": -1.4379812479019165,
|
| 2633 |
+
"logits/rejected": -0.6557310819625854,
|
| 2634 |
+
"logps/chosen": -743.7650146484375,
|
| 2635 |
+
"logps/rejected": -1402.105712890625,
|
| 2636 |
+
"loss": 0.0572,
|
| 2637 |
+
"rewards/accuracies": 0.875,
|
| 2638 |
+
"rewards/chosen": -0.20985308289527893,
|
| 2639 |
+
"rewards/margins": 0.33815231919288635,
|
| 2640 |
+
"rewards/rejected": -0.5480054020881653,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 0.06912825773557027,
|
| 2648 |
+
"train_runtime": 9941.711,
|
| 2649 |
+
"train_samples_per_second": 1.509,
|
| 2650 |
+
"train_steps_per_second": 0.189
|
| 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 |
+
}
|