Model save
Browse files- README.md +59 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- emissions.csv +2 -0
- runs/Sep15_00-09-08_gpu4-119-5/events.out.tfevents.1726323049.gpu4-119-5.439585.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1794 -0
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO/phi-2-ipo-chatml-merged
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-ipo-chatml-lora-30k-50k-i1
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# phi-2-ipo-chatml-lora-30k-50k-i1
|
| 17 |
+
|
| 18 |
+
This model was trained from scratch on the None dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
### Framework versions
|
| 54 |
+
|
| 55 |
+
- PEFT 0.7.1
|
| 56 |
+
- Transformers 4.36.2
|
| 57 |
+
- Pytorch 2.1.2
|
| 58 |
+
- Datasets 2.14.6
|
| 59 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335579632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:167a75d0c8c1cd5c2008c5c0fb7b8ceb6033555eeeeca6c51e5af9d7f2b62a66
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 214327.7246,
|
| 4 |
+
"train_runtime": 12057.8081,
|
| 5 |
+
"train_samples": 20000,
|
| 6 |
+
"train_samples_per_second": 1.659,
|
| 7 |
+
"train_steps_per_second": 0.104
|
| 8 |
+
}
|
emissions.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
| 2 |
+
2024-09-15T03:31:47,codecarbon,495d3c01-4e81-49dc-ad03-7238e06ddb23,12057.812583446503,1.816517465901684,0.00015065066348729614,42.5,418.0,188.74309015274048,0.14234609834833292,2.6467396461004236,0.6302605594394277,3.419346303888181,Australia,AUS,new south wales,,,Linux-5.15.0-84-generic-x86_64-with-glibc2.35,3.10.14,2.2.3,32,Intel(R) Xeon(R) W-3335 CPU @ 3.40GHz,4,4 x NVIDIA GeForce RTX 4090,151.1919,-33.887,503.3149070739746,machine,N,1.0
|
runs/Sep15_00-09-08_gpu4-119-5/events.out.tfevents.1726323049.gpu4-119-5.439585.0
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 sha256:852b88649fc20a729dcd16c2b6df4dbe3741a09b671a49ccf36787e96d71cb5c
|
| 3 |
+
size 85041
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 214327.7246,
|
| 4 |
+
"train_runtime": 12057.8081,
|
| 5 |
+
"train_samples": 20000,
|
| 6 |
+
"train_samples_per_second": 1.659,
|
| 7 |
+
"train_steps_per_second": 0.104
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1794 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 4e-08,
|
| 14 |
+
"logits/chosen": 0.8295156955718994,
|
| 15 |
+
"logits/rejected": 0.6548078060150146,
|
| 16 |
+
"logps/chosen": -326.6375427246094,
|
| 17 |
+
"logps/rejected": -293.72442626953125,
|
| 18 |
+
"loss": 250000.0,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 28 |
+
"logits/chosen": 0.7820703387260437,
|
| 29 |
+
"logits/rejected": 0.8614427447319031,
|
| 30 |
+
"logps/chosen": -289.07513427734375,
|
| 31 |
+
"logps/rejected": -276.29962158203125,
|
| 32 |
+
"loss": 249876.6111,
|
| 33 |
+
"rewards/accuracies": 0.4444444477558136,
|
| 34 |
+
"rewards/chosen": 0.0001525494153611362,
|
| 35 |
+
"rewards/margins": 0.00012419307313393801,
|
| 36 |
+
"rewards/rejected": 2.835636587406043e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 8.000000000000001e-07,
|
| 42 |
+
"logits/chosen": 0.797480583190918,
|
| 43 |
+
"logits/rejected": 0.8103683590888977,
|
| 44 |
+
"logps/chosen": -303.0333251953125,
|
| 45 |
+
"logps/rejected": -317.6231384277344,
|
| 46 |
+
"loss": 250050.475,
|
| 47 |
+
"rewards/accuracies": 0.46875,
|
| 48 |
+
"rewards/chosen": -0.0001646071468712762,
|
| 49 |
+
"rewards/margins": -4.974568582838401e-05,
|
| 50 |
+
"rewards/rejected": -0.0001148614683188498,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 56 |
+
"logits/chosen": 0.7753787040710449,
|
| 57 |
+
"logits/rejected": 0.8598695993423462,
|
| 58 |
+
"logps/chosen": -278.03759765625,
|
| 59 |
+
"logps/rejected": -258.3286437988281,
|
| 60 |
+
"loss": 249960.3,
|
| 61 |
+
"rewards/accuracies": 0.5,
|
| 62 |
+
"rewards/chosen": -0.00019404260092414916,
|
| 63 |
+
"rewards/margins": 4.0378199628321454e-05,
|
| 64 |
+
"rewards/rejected": -0.0002344207896385342,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 70 |
+
"logits/chosen": 0.780045211315155,
|
| 71 |
+
"logits/rejected": 0.8042657971382141,
|
| 72 |
+
"logps/chosen": -326.0252685546875,
|
| 73 |
+
"logps/rejected": -318.72772216796875,
|
| 74 |
+
"loss": 249776.825,
|
| 75 |
+
"rewards/accuracies": 0.512499988079071,
|
| 76 |
+
"rewards/chosen": -0.000730325817130506,
|
| 77 |
+
"rewards/margins": 0.00022414317936636508,
|
| 78 |
+
"rewards/rejected": -0.0009544690256007016,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 84 |
+
"logits/chosen": 0.7937772870063782,
|
| 85 |
+
"logits/rejected": 0.8566519021987915,
|
| 86 |
+
"logps/chosen": -325.046875,
|
| 87 |
+
"logps/rejected": -286.6610107421875,
|
| 88 |
+
"loss": 249859.175,
|
| 89 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 90 |
+
"rewards/chosen": -0.0016889885300770402,
|
| 91 |
+
"rewards/margins": 0.00014180074504110962,
|
| 92 |
+
"rewards/rejected": -0.0018307894933968782,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 98 |
+
"logits/chosen": 0.7670855522155762,
|
| 99 |
+
"logits/rejected": 0.7791861295700073,
|
| 100 |
+
"logps/chosen": -301.5099792480469,
|
| 101 |
+
"logps/rejected": -288.80023193359375,
|
| 102 |
+
"loss": 249517.7,
|
| 103 |
+
"rewards/accuracies": 0.581250011920929,
|
| 104 |
+
"rewards/chosen": -0.002923285122960806,
|
| 105 |
+
"rewards/margins": 0.00048423054977320135,
|
| 106 |
+
"rewards/rejected": -0.003407516051083803,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 112 |
+
"logits/chosen": 0.7704881429672241,
|
| 113 |
+
"logits/rejected": 0.8322450518608093,
|
| 114 |
+
"logps/chosen": -301.4432678222656,
|
| 115 |
+
"logps/rejected": -267.87603759765625,
|
| 116 |
+
"loss": 249107.15,
|
| 117 |
+
"rewards/accuracies": 0.581250011920929,
|
| 118 |
+
"rewards/chosen": -0.005171758122742176,
|
| 119 |
+
"rewards/margins": 0.0008980222046375275,
|
| 120 |
+
"rewards/rejected": -0.0060697803273797035,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06,
|
| 125 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 126 |
+
"logits/chosen": 0.7485744953155518,
|
| 127 |
+
"logits/rejected": 0.7807403206825256,
|
| 128 |
+
"logps/chosen": -301.0188293457031,
|
| 129 |
+
"logps/rejected": -297.59576416015625,
|
| 130 |
+
"loss": 248613.8,
|
| 131 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 132 |
+
"rewards/chosen": -0.00867493450641632,
|
| 133 |
+
"rewards/margins": 0.001399548607878387,
|
| 134 |
+
"rewards/rejected": -0.01007448136806488,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 140 |
+
"logits/chosen": 0.7278767824172974,
|
| 141 |
+
"logits/rejected": 0.7799381017684937,
|
| 142 |
+
"logps/chosen": -347.71319580078125,
|
| 143 |
+
"logps/rejected": -334.35565185546875,
|
| 144 |
+
"loss": 247659.575,
|
| 145 |
+
"rewards/accuracies": 0.606249988079071,
|
| 146 |
+
"rewards/chosen": -0.014293022453784943,
|
| 147 |
+
"rewards/margins": 0.0023766756057739258,
|
| 148 |
+
"rewards/rejected": -0.01666969805955887,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08,
|
| 153 |
+
"learning_rate": 4.000000000000001e-06,
|
| 154 |
+
"logits/chosen": 0.7155344486236572,
|
| 155 |
+
"logits/rejected": 0.861578643321991,
|
| 156 |
+
"logps/chosen": -297.00567626953125,
|
| 157 |
+
"logps/rejected": -267.03668212890625,
|
| 158 |
+
"loss": 246351.1,
|
| 159 |
+
"rewards/accuracies": 0.574999988079071,
|
| 160 |
+
"rewards/chosen": -0.020049724727869034,
|
| 161 |
+
"rewards/margins": 0.0037216537166386843,
|
| 162 |
+
"rewards/rejected": -0.0237713810056448,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09,
|
| 167 |
+
"learning_rate": 4.4e-06,
|
| 168 |
+
"logits/chosen": 0.7031756639480591,
|
| 169 |
+
"logits/rejected": 0.809117317199707,
|
| 170 |
+
"logps/chosen": -364.62908935546875,
|
| 171 |
+
"logps/rejected": -318.9948425292969,
|
| 172 |
+
"loss": 245017.6,
|
| 173 |
+
"rewards/accuracies": 0.625,
|
| 174 |
+
"rewards/chosen": -0.03068319335579872,
|
| 175 |
+
"rewards/margins": 0.005164475180208683,
|
| 176 |
+
"rewards/rejected": -0.03584767132997513,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 4.800000000000001e-06,
|
| 182 |
+
"logits/chosen": 0.6494853496551514,
|
| 183 |
+
"logits/rejected": 0.7721718549728394,
|
| 184 |
+
"logps/chosen": -356.6218566894531,
|
| 185 |
+
"logps/rejected": -313.8863220214844,
|
| 186 |
+
"loss": 241656.95,
|
| 187 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 188 |
+
"rewards/chosen": -0.039860256016254425,
|
| 189 |
+
"rewards/margins": 0.008691919967532158,
|
| 190 |
+
"rewards/rejected": -0.04855217784643173,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1,
|
| 195 |
+
"learning_rate": 4.999756310023261e-06,
|
| 196 |
+
"logits/chosen": 0.6506210565567017,
|
| 197 |
+
"logits/rejected": 0.7414385080337524,
|
| 198 |
+
"logps/chosen": -351.48468017578125,
|
| 199 |
+
"logps/rejected": -338.13531494140625,
|
| 200 |
+
"loss": 240619.55,
|
| 201 |
+
"rewards/accuracies": 0.574999988079071,
|
| 202 |
+
"rewards/chosen": -0.051079101860523224,
|
| 203 |
+
"rewards/margins": 0.01013573445379734,
|
| 204 |
+
"rewards/rejected": -0.06121484562754631,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.11,
|
| 209 |
+
"learning_rate": 4.997807075247147e-06,
|
| 210 |
+
"logits/chosen": 0.6745847463607788,
|
| 211 |
+
"logits/rejected": 0.6169495582580566,
|
| 212 |
+
"logps/chosen": -340.46844482421875,
|
| 213 |
+
"logps/rejected": -357.47381591796875,
|
| 214 |
+
"loss": 238925.075,
|
| 215 |
+
"rewards/accuracies": 0.574999988079071,
|
| 216 |
+
"rewards/chosen": -0.06274016946554184,
|
| 217 |
+
"rewards/margins": 0.012188081629574299,
|
| 218 |
+
"rewards/rejected": -0.07492824643850327,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 4.993910125649561e-06,
|
| 224 |
+
"logits/chosen": 0.5262041687965393,
|
| 225 |
+
"logits/rejected": 0.6367059946060181,
|
| 226 |
+
"logps/chosen": -420.1634826660156,
|
| 227 |
+
"logps/rejected": -407.6827087402344,
|
| 228 |
+
"loss": 237131.75,
|
| 229 |
+
"rewards/accuracies": 0.5625,
|
| 230 |
+
"rewards/chosen": -0.09120262414216995,
|
| 231 |
+
"rewards/margins": 0.01461807917803526,
|
| 232 |
+
"rewards/rejected": -0.10582070052623749,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13,
|
| 237 |
+
"learning_rate": 4.988068499954578e-06,
|
| 238 |
+
"logits/chosen": 0.4250132143497467,
|
| 239 |
+
"logits/rejected": 0.5116867423057556,
|
| 240 |
+
"logps/chosen": -439.47784423828125,
|
| 241 |
+
"logps/rejected": -415.8671875,
|
| 242 |
+
"loss": 233233.4,
|
| 243 |
+
"rewards/accuracies": 0.612500011920929,
|
| 244 |
+
"rewards/chosen": -0.10435976088047028,
|
| 245 |
+
"rewards/margins": 0.01966259442269802,
|
| 246 |
+
"rewards/rejected": -0.12402234971523285,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"learning_rate": 4.980286753286196e-06,
|
| 252 |
+
"logits/chosen": 0.2783159613609314,
|
| 253 |
+
"logits/rejected": 0.397327184677124,
|
| 254 |
+
"logps/chosen": -419.59942626953125,
|
| 255 |
+
"logps/rejected": -415.0672912597656,
|
| 256 |
+
"loss": 235860.125,
|
| 257 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 258 |
+
"rewards/chosen": -0.13993869721889496,
|
| 259 |
+
"rewards/margins": 0.017723705619573593,
|
| 260 |
+
"rewards/rejected": -0.15766240656375885,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14,
|
| 265 |
+
"learning_rate": 4.970570953616383e-06,
|
| 266 |
+
"logits/chosen": 0.29177895188331604,
|
| 267 |
+
"logits/rejected": 0.3751111924648285,
|
| 268 |
+
"logps/chosen": -429.0166015625,
|
| 269 |
+
"logps/rejected": -435.424072265625,
|
| 270 |
+
"loss": 231241.95,
|
| 271 |
+
"rewards/accuracies": 0.550000011920929,
|
| 272 |
+
"rewards/chosen": -0.1576274335384369,
|
| 273 |
+
"rewards/margins": 0.02433793619275093,
|
| 274 |
+
"rewards/rejected": -0.18196536600589752,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15,
|
| 279 |
+
"learning_rate": 4.958928677033465e-06,
|
| 280 |
+
"logits/chosen": 0.26596277952194214,
|
| 281 |
+
"logits/rejected": 0.2121189385652542,
|
| 282 |
+
"logps/chosen": -447.60174560546875,
|
| 283 |
+
"logps/rejected": -477.2583923339844,
|
| 284 |
+
"loss": 224865.525,
|
| 285 |
+
"rewards/accuracies": 0.5625,
|
| 286 |
+
"rewards/chosen": -0.17030256986618042,
|
| 287 |
+
"rewards/margins": 0.033268414437770844,
|
| 288 |
+
"rewards/rejected": -0.20357099175453186,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16,
|
| 293 |
+
"learning_rate": 4.9453690018345144e-06,
|
| 294 |
+
"logits/chosen": 0.097198985517025,
|
| 295 |
+
"logits/rejected": 0.14169301092624664,
|
| 296 |
+
"logps/chosen": -503.57891845703125,
|
| 297 |
+
"logps/rejected": -515.3058471679688,
|
| 298 |
+
"loss": 233179.675,
|
| 299 |
+
"rewards/accuracies": 0.53125,
|
| 300 |
+
"rewards/chosen": -0.21676607429981232,
|
| 301 |
+
"rewards/margins": 0.026259085163474083,
|
| 302 |
+
"rewards/rejected": -0.24302515387535095,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 4.9299025014463665e-06,
|
| 308 |
+
"logits/chosen": 0.11865909397602081,
|
| 309 |
+
"logits/rejected": 0.0950862243771553,
|
| 310 |
+
"logps/chosen": -478.55938720703125,
|
| 311 |
+
"logps/rejected": -504.3150329589844,
|
| 312 |
+
"loss": 222466.05,
|
| 313 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 314 |
+
"rewards/chosen": -0.19287104904651642,
|
| 315 |
+
"rewards/margins": 0.038011640310287476,
|
| 316 |
+
"rewards/rejected": -0.2308826744556427,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"learning_rate": 4.912541236180779e-06,
|
| 322 |
+
"logits/chosen": 0.1145167350769043,
|
| 323 |
+
"logits/rejected": 0.05735859274864197,
|
| 324 |
+
"logps/chosen": -506.91595458984375,
|
| 325 |
+
"logps/rejected": -524.0423583984375,
|
| 326 |
+
"loss": 222774.4,
|
| 327 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 328 |
+
"rewards/chosen": -0.20809824764728546,
|
| 329 |
+
"rewards/margins": 0.03587258234620094,
|
| 330 |
+
"rewards/rejected": -0.24397078156471252,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.18,
|
| 335 |
+
"learning_rate": 4.893298743830168e-06,
|
| 336 |
+
"logits/chosen": 0.05398910492658615,
|
| 337 |
+
"logits/rejected": 0.0433785505592823,
|
| 338 |
+
"logps/chosen": -526.40576171875,
|
| 339 |
+
"logps/rejected": -551.79345703125,
|
| 340 |
+
"loss": 225807.55,
|
| 341 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 342 |
+
"rewards/chosen": -0.23996694386005402,
|
| 343 |
+
"rewards/margins": 0.046754226088523865,
|
| 344 |
+
"rewards/rejected": -0.2867211401462555,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.19,
|
| 349 |
+
"learning_rate": 4.8721900291112415e-06,
|
| 350 |
+
"logits/chosen": 0.07415799796581268,
|
| 351 |
+
"logits/rejected": 0.10433997958898544,
|
| 352 |
+
"logps/chosen": -531.3713989257812,
|
| 353 |
+
"logps/rejected": -559.2561645507812,
|
| 354 |
+
"loss": 227831.775,
|
| 355 |
+
"rewards/accuracies": 0.518750011920929,
|
| 356 |
+
"rewards/chosen": -0.2333986759185791,
|
| 357 |
+
"rewards/margins": 0.03696846216917038,
|
| 358 |
+
"rewards/rejected": -0.2703671157360077,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2,
|
| 363 |
+
"learning_rate": 4.849231551964771e-06,
|
| 364 |
+
"logits/chosen": 0.09013446420431137,
|
| 365 |
+
"logits/rejected": 0.1400720179080963,
|
| 366 |
+
"logps/chosen": -599.9500122070312,
|
| 367 |
+
"logps/rejected": -602.9922485351562,
|
| 368 |
+
"loss": 224383.85,
|
| 369 |
+
"rewards/accuracies": 0.581250011920929,
|
| 370 |
+
"rewards/chosen": -0.26714402437210083,
|
| 371 |
+
"rewards/margins": 0.03883109614253044,
|
| 372 |
+
"rewards/rejected": -0.3059751093387604,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21,
|
| 377 |
+
"learning_rate": 4.824441214720629e-06,
|
| 378 |
+
"logits/chosen": 0.07357914745807648,
|
| 379 |
+
"logits/rejected": 0.07694338262081146,
|
| 380 |
+
"logps/chosen": -634.8258056640625,
|
| 381 |
+
"logps/rejected": -639.3756103515625,
|
| 382 |
+
"loss": 209921.075,
|
| 383 |
+
"rewards/accuracies": 0.59375,
|
| 384 |
+
"rewards/chosen": -0.312286913394928,
|
| 385 |
+
"rewards/margins": 0.05587261915206909,
|
| 386 |
+
"rewards/rejected": -0.3681595027446747,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 4.7978383481380865e-06,
|
| 392 |
+
"logits/chosen": 0.028488850221037865,
|
| 393 |
+
"logits/rejected": -0.008646219037473202,
|
| 394 |
+
"logps/chosen": -654.36181640625,
|
| 395 |
+
"logps/rejected": -680.0220947265625,
|
| 396 |
+
"loss": 224023.2,
|
| 397 |
+
"rewards/accuracies": 0.59375,
|
| 398 |
+
"rewards/chosen": -0.35496431589126587,
|
| 399 |
+
"rewards/margins": 0.04780570790171623,
|
| 400 |
+
"rewards/rejected": -0.4027700424194336,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.22,
|
| 405 |
+
"learning_rate": 4.769443696332272e-06,
|
| 406 |
+
"logits/chosen": 0.05388519912958145,
|
| 407 |
+
"logits/rejected": 0.08880044519901276,
|
| 408 |
+
"logps/chosen": -604.0039672851562,
|
| 409 |
+
"logps/rejected": -608.7615966796875,
|
| 410 |
+
"loss": 220728.7,
|
| 411 |
+
"rewards/accuracies": 0.581250011920929,
|
| 412 |
+
"rewards/chosen": -0.29847094416618347,
|
| 413 |
+
"rewards/margins": 0.047135598957538605,
|
| 414 |
+
"rewards/rejected": -0.3456065058708191,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.23,
|
| 419 |
+
"learning_rate": 4.7392794005985324e-06,
|
| 420 |
+
"logits/chosen": 0.07930080592632294,
|
| 421 |
+
"logits/rejected": 0.13805383443832397,
|
| 422 |
+
"logps/chosen": -595.7717895507812,
|
| 423 |
+
"logps/rejected": -613.3287353515625,
|
| 424 |
+
"loss": 229349.4,
|
| 425 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 426 |
+
"rewards/chosen": -0.3072170615196228,
|
| 427 |
+
"rewards/margins": 0.033545564860105515,
|
| 428 |
+
"rewards/rejected": -0.3407626748085022,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24,
|
| 433 |
+
"learning_rate": 4.707368982147318e-06,
|
| 434 |
+
"logits/chosen": 0.06698635965585709,
|
| 435 |
+
"logits/rejected": 0.12424659729003906,
|
| 436 |
+
"logps/chosen": -706.1388549804688,
|
| 437 |
+
"logps/rejected": -725.2173461914062,
|
| 438 |
+
"loss": 211718.1,
|
| 439 |
+
"rewards/accuracies": 0.65625,
|
| 440 |
+
"rewards/chosen": -0.3826766312122345,
|
| 441 |
+
"rewards/margins": 0.0551617331802845,
|
| 442 |
+
"rewards/rejected": -0.4378383755683899,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.25,
|
| 447 |
+
"learning_rate": 4.673737323763048e-06,
|
| 448 |
+
"logits/chosen": 0.15006323158740997,
|
| 449 |
+
"logits/rejected": 0.13014820218086243,
|
| 450 |
+
"logps/chosen": -740.9302978515625,
|
| 451 |
+
"logps/rejected": -760.7489624023438,
|
| 452 |
+
"loss": 225763.35,
|
| 453 |
+
"rewards/accuracies": 0.59375,
|
| 454 |
+
"rewards/chosen": -0.44331517815589905,
|
| 455 |
+
"rewards/margins": 0.038237761706113815,
|
| 456 |
+
"rewards/rejected": -0.48155292868614197,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.26,
|
| 461 |
+
"learning_rate": 4.638410650401267e-06,
|
| 462 |
+
"logits/chosen": 0.19281049072742462,
|
| 463 |
+
"logits/rejected": 0.1867452710866928,
|
| 464 |
+
"logps/chosen": -709.2954711914062,
|
| 465 |
+
"logps/rejected": -755.7704467773438,
|
| 466 |
+
"loss": 205375.5875,
|
| 467 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 468 |
+
"rewards/chosen": -0.4064555764198303,
|
| 469 |
+
"rewards/margins": 0.06762731820344925,
|
| 470 |
+
"rewards/rejected": -0.474082887172699,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.26,
|
| 475 |
+
"learning_rate": 4.601416508739211e-06,
|
| 476 |
+
"logits/chosen": 0.08930904418230057,
|
| 477 |
+
"logits/rejected": 0.14192309975624084,
|
| 478 |
+
"logps/chosen": -662.8482666015625,
|
| 479 |
+
"logps/rejected": -693.8590087890625,
|
| 480 |
+
"loss": 222503.1,
|
| 481 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 482 |
+
"rewards/chosen": -0.3568669259548187,
|
| 483 |
+
"rewards/margins": 0.04300789535045624,
|
| 484 |
+
"rewards/rejected": -0.39987480640411377,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.27,
|
| 489 |
+
"learning_rate": 4.562783745695738e-06,
|
| 490 |
+
"logits/chosen": 0.18497507274150848,
|
| 491 |
+
"logits/rejected": 0.26277828216552734,
|
| 492 |
+
"logps/chosen": -584.7015380859375,
|
| 493 |
+
"logps/rejected": -564.4039306640625,
|
| 494 |
+
"loss": 227970.925,
|
| 495 |
+
"rewards/accuracies": 0.550000011920929,
|
| 496 |
+
"rewards/chosen": -0.28115934133529663,
|
| 497 |
+
"rewards/margins": 0.03500787168741226,
|
| 498 |
+
"rewards/rejected": -0.3161672055721283,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.28,
|
| 503 |
+
"learning_rate": 4.522542485937369e-06,
|
| 504 |
+
"logits/chosen": 0.13414345681667328,
|
| 505 |
+
"logits/rejected": 0.10634734481573105,
|
| 506 |
+
"logps/chosen": -653.3938598632812,
|
| 507 |
+
"logps/rejected": -691.0509033203125,
|
| 508 |
+
"loss": 217501.25,
|
| 509 |
+
"rewards/accuracies": 0.65625,
|
| 510 |
+
"rewards/chosen": -0.34600910544395447,
|
| 511 |
+
"rewards/margins": 0.051264774054288864,
|
| 512 |
+
"rewards/rejected": -0.39727386832237244,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.29,
|
| 517 |
+
"learning_rate": 4.4807241083879774e-06,
|
| 518 |
+
"logits/chosen": 0.0934506505727768,
|
| 519 |
+
"logits/rejected": 0.13086247444152832,
|
| 520 |
+
"logps/chosen": -666.2071533203125,
|
| 521 |
+
"logps/rejected": -732.3128051757812,
|
| 522 |
+
"loss": 218206.425,
|
| 523 |
+
"rewards/accuracies": 0.574999988079071,
|
| 524 |
+
"rewards/chosen": -0.37724870443344116,
|
| 525 |
+
"rewards/margins": 0.04904107004404068,
|
| 526 |
+
"rewards/rejected": -0.42628973722457886,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3,
|
| 531 |
+
"learning_rate": 4.437361221760449e-06,
|
| 532 |
+
"logits/chosen": 0.018922029063105583,
|
| 533 |
+
"logits/rejected": 0.11000480502843857,
|
| 534 |
+
"logps/chosen": -762.7982788085938,
|
| 535 |
+
"logps/rejected": -766.64794921875,
|
| 536 |
+
"loss": 226796.35,
|
| 537 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 538 |
+
"rewards/chosen": -0.4142926335334778,
|
| 539 |
+
"rewards/margins": 0.044357530772686005,
|
| 540 |
+
"rewards/rejected": -0.4586501121520996,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3,
|
| 545 |
+
"learning_rate": 4.3924876391293915e-06,
|
| 546 |
+
"logits/chosen": 0.0013346634805202484,
|
| 547 |
+
"logits/rejected": 0.05925361439585686,
|
| 548 |
+
"logps/chosen": -744.2739868164062,
|
| 549 |
+
"logps/rejected": -797.4059448242188,
|
| 550 |
+
"loss": 204200.0125,
|
| 551 |
+
"rewards/accuracies": 0.668749988079071,
|
| 552 |
+
"rewards/chosen": -0.42942437529563904,
|
| 553 |
+
"rewards/margins": 0.07275478541851044,
|
| 554 |
+
"rewards/rejected": -0.5021791458129883,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.31,
|
| 559 |
+
"learning_rate": 4.346138351564711e-06,
|
| 560 |
+
"logits/chosen": 0.029370343312621117,
|
| 561 |
+
"logits/rejected": 0.07145482301712036,
|
| 562 |
+
"logps/chosen": -640.0790405273438,
|
| 563 |
+
"logps/rejected": -674.6331787109375,
|
| 564 |
+
"loss": 221114.7,
|
| 565 |
+
"rewards/accuracies": 0.53125,
|
| 566 |
+
"rewards/chosen": -0.3869141936302185,
|
| 567 |
+
"rewards/margins": 0.04503845423460007,
|
| 568 |
+
"rewards/rejected": -0.4319526255130768,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.32,
|
| 573 |
+
"learning_rate": 4.2983495008466285e-06,
|
| 574 |
+
"logits/chosen": 0.05230168625712395,
|
| 575 |
+
"logits/rejected": 0.018671754747629166,
|
| 576 |
+
"logps/chosen": -738.8311767578125,
|
| 577 |
+
"logps/rejected": -783.68310546875,
|
| 578 |
+
"loss": 208442.4125,
|
| 579 |
+
"rewards/accuracies": 0.643750011920929,
|
| 580 |
+
"rewards/chosen": -0.43338528275489807,
|
| 581 |
+
"rewards/margins": 0.06608940660953522,
|
| 582 |
+
"rewards/rejected": -0.4994747042655945,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.33,
|
| 587 |
+
"learning_rate": 4.249158351283414e-06,
|
| 588 |
+
"logits/chosen": 0.004748106934130192,
|
| 589 |
+
"logits/rejected": 0.050472937524318695,
|
| 590 |
+
"logps/chosen": -751.1259155273438,
|
| 591 |
+
"logps/rejected": -791.6265869140625,
|
| 592 |
+
"loss": 211007.475,
|
| 593 |
+
"rewards/accuracies": 0.606249988079071,
|
| 594 |
+
"rewards/chosen": -0.47515082359313965,
|
| 595 |
+
"rewards/margins": 0.06483330577611923,
|
| 596 |
+
"rewards/rejected": -0.5399841070175171,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34,
|
| 601 |
+
"learning_rate": 4.198603260653792e-06,
|
| 602 |
+
"logits/chosen": 0.01909482479095459,
|
| 603 |
+
"logits/rejected": 0.0381409153342247,
|
| 604 |
+
"logps/chosen": -742.4544677734375,
|
| 605 |
+
"logps/rejected": -806.3211669921875,
|
| 606 |
+
"loss": 210379.525,
|
| 607 |
+
"rewards/accuracies": 0.606249988079071,
|
| 608 |
+
"rewards/chosen": -0.457224041223526,
|
| 609 |
+
"rewards/margins": 0.06866325438022614,
|
| 610 |
+
"rewards/rejected": -0.5258872509002686,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.34,
|
| 615 |
+
"learning_rate": 4.146723650296701e-06,
|
| 616 |
+
"logits/chosen": 0.030068010091781616,
|
| 617 |
+
"logits/rejected": 0.03350980207324028,
|
| 618 |
+
"logps/chosen": -775.4443359375,
|
| 619 |
+
"logps/rejected": -830.0377807617188,
|
| 620 |
+
"loss": 212105.15,
|
| 621 |
+
"rewards/accuracies": 0.606249988079071,
|
| 622 |
+
"rewards/chosen": -0.48469358682632446,
|
| 623 |
+
"rewards/margins": 0.06393586099147797,
|
| 624 |
+
"rewards/rejected": -0.5486294627189636,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.35,
|
| 629 |
+
"learning_rate": 4.093559974371725e-06,
|
| 630 |
+
"logits/chosen": -0.027669662609696388,
|
| 631 |
+
"logits/rejected": 0.06110602617263794,
|
| 632 |
+
"logps/chosen": -766.5031127929688,
|
| 633 |
+
"logps/rejected": -828.86181640625,
|
| 634 |
+
"loss": 218775.75,
|
| 635 |
+
"rewards/accuracies": 0.612500011920929,
|
| 636 |
+
"rewards/chosen": -0.46198052167892456,
|
| 637 |
+
"rewards/margins": 0.07218774408102036,
|
| 638 |
+
"rewards/rejected": -0.5341682434082031,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.36,
|
| 643 |
+
"learning_rate": 4.039153688314146e-06,
|
| 644 |
+
"logits/chosen": 0.018282964825630188,
|
| 645 |
+
"logits/rejected": 0.058882780373096466,
|
| 646 |
+
"logps/chosen": -710.2281494140625,
|
| 647 |
+
"logps/rejected": -745.7041625976562,
|
| 648 |
+
"loss": 214898.9,
|
| 649 |
+
"rewards/accuracies": 0.5625,
|
| 650 |
+
"rewards/chosen": -0.40473413467407227,
|
| 651 |
+
"rewards/margins": 0.06730447709560394,
|
| 652 |
+
"rewards/rejected": -0.4720386564731598,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.37,
|
| 657 |
+
"learning_rate": 3.983547216509254e-06,
|
| 658 |
+
"logits/chosen": 0.13433220982551575,
|
| 659 |
+
"logits/rejected": 0.1166907325387001,
|
| 660 |
+
"logps/chosen": -672.626220703125,
|
| 661 |
+
"logps/rejected": -713.3814697265625,
|
| 662 |
+
"loss": 231613.05,
|
| 663 |
+
"rewards/accuracies": 0.518750011920929,
|
| 664 |
+
"rewards/chosen": -0.3828766942024231,
|
| 665 |
+
"rewards/margins": 0.04323703795671463,
|
| 666 |
+
"rewards/rejected": -0.42611369490623474,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38,
|
| 671 |
+
"learning_rate": 3.92678391921108e-06,
|
| 672 |
+
"logits/chosen": 0.053751278668642044,
|
| 673 |
+
"logits/rejected": 0.12324490398168564,
|
| 674 |
+
"logps/chosen": -639.7972412109375,
|
| 675 |
+
"logps/rejected": -757.8414306640625,
|
| 676 |
+
"loss": 197887.3875,
|
| 677 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 678 |
+
"rewards/chosen": -0.37909045815467834,
|
| 679 |
+
"rewards/margins": 0.08440332859754562,
|
| 680 |
+
"rewards/rejected": -0.46349382400512695,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.38,
|
| 685 |
+
"learning_rate": 3.868908058731376e-06,
|
| 686 |
+
"logits/chosen": 0.128374382853508,
|
| 687 |
+
"logits/rejected": 0.13496294617652893,
|
| 688 |
+
"logps/chosen": -594.45263671875,
|
| 689 |
+
"logps/rejected": -646.1005859375,
|
| 690 |
+
"loss": 221224.65,
|
| 691 |
+
"rewards/accuracies": 0.574999988079071,
|
| 692 |
+
"rewards/chosen": -0.334342896938324,
|
| 693 |
+
"rewards/margins": 0.04580118507146835,
|
| 694 |
+
"rewards/rejected": -0.38014405965805054,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.39,
|
| 699 |
+
"learning_rate": 3.8099647649251984e-06,
|
| 700 |
+
"logits/chosen": 0.10510148853063583,
|
| 701 |
+
"logits/rejected": 0.08986426889896393,
|
| 702 |
+
"logps/chosen": -654.1688232421875,
|
| 703 |
+
"logps/rejected": -703.2432861328125,
|
| 704 |
+
"loss": 203631.6625,
|
| 705 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 706 |
+
"rewards/chosen": -0.35530680418014526,
|
| 707 |
+
"rewards/margins": 0.0678824782371521,
|
| 708 |
+
"rewards/rejected": -0.42318931221961975,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4,
|
| 713 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 714 |
+
"logits/chosen": 0.12126519531011581,
|
| 715 |
+
"logits/rejected": 0.19802531599998474,
|
| 716 |
+
"logps/chosen": -756.9439697265625,
|
| 717 |
+
"logps/rejected": -784.077392578125,
|
| 718 |
+
"loss": 214927.525,
|
| 719 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 720 |
+
"rewards/chosen": -0.43085330724716187,
|
| 721 |
+
"rewards/margins": 0.06764908134937286,
|
| 722 |
+
"rewards/rejected": -0.4985024333000183,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.41,
|
| 727 |
+
"learning_rate": 3.689060522675689e-06,
|
| 728 |
+
"logits/chosen": 0.12064807116985321,
|
| 729 |
+
"logits/rejected": 0.12566062808036804,
|
| 730 |
+
"logps/chosen": -851.3665771484375,
|
| 731 |
+
"logps/rejected": -882.310546875,
|
| 732 |
+
"loss": 214672.75,
|
| 733 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 734 |
+
"rewards/chosen": -0.5168792009353638,
|
| 735 |
+
"rewards/margins": 0.06789232790470123,
|
| 736 |
+
"rewards/rejected": -0.5847715139389038,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.42,
|
| 741 |
+
"learning_rate": 3.627193851723577e-06,
|
| 742 |
+
"logits/chosen": 0.06757915019989014,
|
| 743 |
+
"logits/rejected": 0.1305195838212967,
|
| 744 |
+
"logps/chosen": -804.7583618164062,
|
| 745 |
+
"logps/rejected": -930.0843505859375,
|
| 746 |
+
"loss": 201156.9875,
|
| 747 |
+
"rewards/accuracies": 0.637499988079071,
|
| 748 |
+
"rewards/chosen": -0.5027543306350708,
|
| 749 |
+
"rewards/margins": 0.10955546051263809,
|
| 750 |
+
"rewards/rejected": -0.6123097538948059,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.42,
|
| 755 |
+
"learning_rate": 3.564448228912682e-06,
|
| 756 |
+
"logits/chosen": 0.06576359272003174,
|
| 757 |
+
"logits/rejected": 0.11259643733501434,
|
| 758 |
+
"logps/chosen": -678.2341918945312,
|
| 759 |
+
"logps/rejected": -732.47216796875,
|
| 760 |
+
"loss": 206976.4,
|
| 761 |
+
"rewards/accuracies": 0.606249988079071,
|
| 762 |
+
"rewards/chosen": -0.37194186449050903,
|
| 763 |
+
"rewards/margins": 0.07337535172700882,
|
| 764 |
+
"rewards/rejected": -0.44531720876693726,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.43,
|
| 769 |
+
"learning_rate": 3.5008725813922383e-06,
|
| 770 |
+
"logits/chosen": 0.06615754216909409,
|
| 771 |
+
"logits/rejected": 0.15026697516441345,
|
| 772 |
+
"logps/chosen": -624.8627319335938,
|
| 773 |
+
"logps/rejected": -654.1346435546875,
|
| 774 |
+
"loss": 211272.275,
|
| 775 |
+
"rewards/accuracies": 0.643750011920929,
|
| 776 |
+
"rewards/chosen": -0.3046865463256836,
|
| 777 |
+
"rewards/margins": 0.05525575205683708,
|
| 778 |
+
"rewards/rejected": -0.3599422574043274,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.44,
|
| 783 |
+
"learning_rate": 3.436516483539781e-06,
|
| 784 |
+
"logits/chosen": 0.05189785361289978,
|
| 785 |
+
"logits/rejected": 0.08357914537191391,
|
| 786 |
+
"logps/chosen": -621.6806030273438,
|
| 787 |
+
"logps/rejected": -649.3397216796875,
|
| 788 |
+
"loss": 204318.1,
|
| 789 |
+
"rewards/accuracies": 0.643750011920929,
|
| 790 |
+
"rewards/chosen": -0.30943694710731506,
|
| 791 |
+
"rewards/margins": 0.06414629518985748,
|
| 792 |
+
"rewards/rejected": -0.37358322739601135,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.45,
|
| 797 |
+
"learning_rate": 3.3714301183045382e-06,
|
| 798 |
+
"logits/chosen": 0.08765645325183868,
|
| 799 |
+
"logits/rejected": 0.15434232354164124,
|
| 800 |
+
"logps/chosen": -740.7510986328125,
|
| 801 |
+
"logps/rejected": -790.8681030273438,
|
| 802 |
+
"loss": 200112.7625,
|
| 803 |
+
"rewards/accuracies": 0.606249988079071,
|
| 804 |
+
"rewards/chosen": -0.41592878103256226,
|
| 805 |
+
"rewards/margins": 0.07707349956035614,
|
| 806 |
+
"rewards/rejected": -0.493002325296402,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.46,
|
| 811 |
+
"learning_rate": 3.3056642380762783e-06,
|
| 812 |
+
"logits/chosen": 0.04721086472272873,
|
| 813 |
+
"logits/rejected": 0.08238790929317474,
|
| 814 |
+
"logps/chosen": -790.76953125,
|
| 815 |
+
"logps/rejected": -844.1984252929688,
|
| 816 |
+
"loss": 219880.825,
|
| 817 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 818 |
+
"rewards/chosen": -0.4865700304508209,
|
| 819 |
+
"rewards/margins": 0.07380232214927673,
|
| 820 |
+
"rewards/rejected": -0.5603722929954529,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.46,
|
| 825 |
+
"learning_rate": 3.2392701251101172e-06,
|
| 826 |
+
"logits/chosen": 0.10582544654607773,
|
| 827 |
+
"logits/rejected": 0.11523424088954926,
|
| 828 |
+
"logps/chosen": -773.1691284179688,
|
| 829 |
+
"logps/rejected": -811.2911376953125,
|
| 830 |
+
"loss": 219685.05,
|
| 831 |
+
"rewards/accuracies": 0.59375,
|
| 832 |
+
"rewards/chosen": -0.456064373254776,
|
| 833 |
+
"rewards/margins": 0.0640571117401123,
|
| 834 |
+
"rewards/rejected": -0.5201215147972107,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.47,
|
| 839 |
+
"learning_rate": 3.1722995515381644e-06,
|
| 840 |
+
"logits/chosen": 0.0479222796857357,
|
| 841 |
+
"logits/rejected": 0.05860881879925728,
|
| 842 |
+
"logps/chosen": -735.574462890625,
|
| 843 |
+
"logps/rejected": -758.9188232421875,
|
| 844 |
+
"loss": 220162.45,
|
| 845 |
+
"rewards/accuracies": 0.606249988079071,
|
| 846 |
+
"rewards/chosen": -0.40008649230003357,
|
| 847 |
+
"rewards/margins": 0.05989546701312065,
|
| 848 |
+
"rewards/rejected": -0.4599819779396057,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.48,
|
| 853 |
+
"learning_rate": 3.1048047389991693e-06,
|
| 854 |
+
"logits/chosen": 0.09819038212299347,
|
| 855 |
+
"logits/rejected": 0.1414027363061905,
|
| 856 |
+
"logps/chosen": -635.8867797851562,
|
| 857 |
+
"logps/rejected": -698.0687866210938,
|
| 858 |
+
"loss": 208946.475,
|
| 859 |
+
"rewards/accuracies": 0.581250011920929,
|
| 860 |
+
"rewards/chosen": -0.3538115620613098,
|
| 861 |
+
"rewards/margins": 0.06901269406080246,
|
| 862 |
+
"rewards/rejected": -0.42282429337501526,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.49,
|
| 867 |
+
"learning_rate": 3.0368383179176584e-06,
|
| 868 |
+
"logits/chosen": 0.11481986939907074,
|
| 869 |
+
"logits/rejected": 0.15899059176445007,
|
| 870 |
+
"logps/chosen": -702.89013671875,
|
| 871 |
+
"logps/rejected": -717.7106323242188,
|
| 872 |
+
"loss": 212219.25,
|
| 873 |
+
"rewards/accuracies": 0.581250011920929,
|
| 874 |
+
"rewards/chosen": -0.38934019207954407,
|
| 875 |
+
"rewards/margins": 0.05715745687484741,
|
| 876 |
+
"rewards/rejected": -0.4464975893497467,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5,
|
| 881 |
+
"learning_rate": 2.9684532864643123e-06,
|
| 882 |
+
"logits/chosen": 0.1034402847290039,
|
| 883 |
+
"logits/rejected": 0.1860104650259018,
|
| 884 |
+
"logps/chosen": -736.3319091796875,
|
| 885 |
+
"logps/rejected": -767.5115966796875,
|
| 886 |
+
"loss": 213919.125,
|
| 887 |
+
"rewards/accuracies": 0.574999988079071,
|
| 888 |
+
"rewards/chosen": -0.43666261434555054,
|
| 889 |
+
"rewards/margins": 0.06389528512954712,
|
| 890 |
+
"rewards/rejected": -0.5005578994750977,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5,
|
| 895 |
+
"learning_rate": 2.8997029692295875e-06,
|
| 896 |
+
"logits/chosen": 0.13250839710235596,
|
| 897 |
+
"logits/rejected": 0.18815624713897705,
|
| 898 |
+
"logps/chosen": -803.8920288085938,
|
| 899 |
+
"logps/rejected": -863.8623046875,
|
| 900 |
+
"loss": 196412.7,
|
| 901 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 902 |
+
"rewards/chosen": -0.47905057668685913,
|
| 903 |
+
"rewards/margins": 0.08728605508804321,
|
| 904 |
+
"rewards/rejected": -0.5663365721702576,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.51,
|
| 909 |
+
"learning_rate": 2.8306409756428067e-06,
|
| 910 |
+
"logits/chosen": 0.16394320130348206,
|
| 911 |
+
"logits/rejected": 0.13657519221305847,
|
| 912 |
+
"logps/chosen": -779.695556640625,
|
| 913 |
+
"logps/rejected": -837.1370239257812,
|
| 914 |
+
"loss": 206379.325,
|
| 915 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 916 |
+
"rewards/chosen": -0.47375592589378357,
|
| 917 |
+
"rewards/margins": 0.0785304605960846,
|
| 918 |
+
"rewards/rejected": -0.5522863864898682,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.52,
|
| 923 |
+
"learning_rate": 2.761321158169134e-06,
|
| 924 |
+
"logits/chosen": 0.12425035238265991,
|
| 925 |
+
"logits/rejected": 0.18131953477859497,
|
| 926 |
+
"logps/chosen": -850.9552001953125,
|
| 927 |
+
"logps/rejected": -873.2657470703125,
|
| 928 |
+
"loss": 204371.2,
|
| 929 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 930 |
+
"rewards/chosen": -0.4772258698940277,
|
| 931 |
+
"rewards/margins": 0.07543002814054489,
|
| 932 |
+
"rewards/rejected": -0.5526558756828308,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.53,
|
| 937 |
+
"learning_rate": 2.6917975703170466e-06,
|
| 938 |
+
"logits/chosen": 0.04687013849616051,
|
| 939 |
+
"logits/rejected": 0.16662175953388214,
|
| 940 |
+
"logps/chosen": -876.6595458984375,
|
| 941 |
+
"logps/rejected": -889.6097412109375,
|
| 942 |
+
"loss": 216406.05,
|
| 943 |
+
"rewards/accuracies": 0.606249988079071,
|
| 944 |
+
"rewards/chosen": -0.5168339014053345,
|
| 945 |
+
"rewards/margins": 0.05905190110206604,
|
| 946 |
+
"rewards/rejected": -0.5758857727050781,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.54,
|
| 951 |
+
"learning_rate": 2.6221244244890336e-06,
|
| 952 |
+
"logits/chosen": 0.0942823514342308,
|
| 953 |
+
"logits/rejected": 0.16277393698692322,
|
| 954 |
+
"logps/chosen": -913.4798583984375,
|
| 955 |
+
"logps/rejected": -968.29736328125,
|
| 956 |
+
"loss": 201330.075,
|
| 957 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 958 |
+
"rewards/chosen": -0.5632065534591675,
|
| 959 |
+
"rewards/margins": 0.08455005288124084,
|
| 960 |
+
"rewards/rejected": -0.6477565765380859,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.54,
|
| 965 |
+
"learning_rate": 2.5523560497083927e-06,
|
| 966 |
+
"logits/chosen": 0.1031470075249672,
|
| 967 |
+
"logits/rejected": 0.15894286334514618,
|
| 968 |
+
"logps/chosen": -853.4171752929688,
|
| 969 |
+
"logps/rejected": -906.45947265625,
|
| 970 |
+
"loss": 217766.95,
|
| 971 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 972 |
+
"rewards/chosen": -0.5738204121589661,
|
| 973 |
+
"rewards/margins": 0.054585278034210205,
|
| 974 |
+
"rewards/rejected": -0.6284056901931763,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.55,
|
| 979 |
+
"learning_rate": 2.482546849255096e-06,
|
| 980 |
+
"logits/chosen": 0.08062312752008438,
|
| 981 |
+
"logits/rejected": 0.1569138616323471,
|
| 982 |
+
"logps/chosen": -874.7586059570312,
|
| 983 |
+
"logps/rejected": -928.3865966796875,
|
| 984 |
+
"loss": 191898.5375,
|
| 985 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 986 |
+
"rewards/chosen": -0.5526047348976135,
|
| 987 |
+
"rewards/margins": 0.08970547467470169,
|
| 988 |
+
"rewards/rejected": -0.6423102021217346,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.56,
|
| 993 |
+
"learning_rate": 2.4127512582437486e-06,
|
| 994 |
+
"logits/chosen": 0.10366399586200714,
|
| 995 |
+
"logits/rejected": 0.1587708741426468,
|
| 996 |
+
"logps/chosen": -830.5030517578125,
|
| 997 |
+
"logps/rejected": -889.00927734375,
|
| 998 |
+
"loss": 193230.425,
|
| 999 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1000 |
+
"rewards/chosen": -0.5430067777633667,
|
| 1001 |
+
"rewards/margins": 0.09088052809238434,
|
| 1002 |
+
"rewards/rejected": -0.6338872909545898,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.57,
|
| 1007 |
+
"learning_rate": 2.3430237011767166e-06,
|
| 1008 |
+
"logits/chosen": 0.09116552770137787,
|
| 1009 |
+
"logits/rejected": 0.14335498213768005,
|
| 1010 |
+
"logps/chosen": -824.9454345703125,
|
| 1011 |
+
"logps/rejected": -862.0933837890625,
|
| 1012 |
+
"loss": 214825.625,
|
| 1013 |
+
"rewards/accuracies": 0.59375,
|
| 1014 |
+
"rewards/chosen": -0.5117640495300293,
|
| 1015 |
+
"rewards/margins": 0.07259064167737961,
|
| 1016 |
+
"rewards/rejected": -0.5843546986579895,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.58,
|
| 1021 |
+
"learning_rate": 2.2734185495055503e-06,
|
| 1022 |
+
"logits/chosen": 0.09662021696567535,
|
| 1023 |
+
"logits/rejected": 0.1421934813261032,
|
| 1024 |
+
"logps/chosen": -819.3873901367188,
|
| 1025 |
+
"logps/rejected": -846.3427734375,
|
| 1026 |
+
"loss": 205466.7125,
|
| 1027 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 1028 |
+
"rewards/chosen": -0.47142258286476135,
|
| 1029 |
+
"rewards/margins": 0.08721249550580978,
|
| 1030 |
+
"rewards/rejected": -0.5586350560188293,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.58,
|
| 1035 |
+
"learning_rate": 2.2039900792337477e-06,
|
| 1036 |
+
"logits/chosen": 0.12153534591197968,
|
| 1037 |
+
"logits/rejected": 0.1794102042913437,
|
| 1038 |
+
"logps/chosen": -777.436767578125,
|
| 1039 |
+
"logps/rejected": -856.6826171875,
|
| 1040 |
+
"loss": 204512.775,
|
| 1041 |
+
"rewards/accuracies": 0.59375,
|
| 1042 |
+
"rewards/chosen": -0.47006410360336304,
|
| 1043 |
+
"rewards/margins": 0.08860307186841965,
|
| 1044 |
+
"rewards/rejected": -0.5586671233177185,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.59,
|
| 1049 |
+
"learning_rate": 2.134792428593971e-06,
|
| 1050 |
+
"logits/chosen": 0.08428861945867538,
|
| 1051 |
+
"logits/rejected": 0.16267940402030945,
|
| 1052 |
+
"logps/chosen": -780.1156005859375,
|
| 1053 |
+
"logps/rejected": -814.1882934570312,
|
| 1054 |
+
"loss": 215538.6,
|
| 1055 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1056 |
+
"rewards/chosen": -0.4730224609375,
|
| 1057 |
+
"rewards/margins": 0.07011882960796356,
|
| 1058 |
+
"rewards/rejected": -0.54314124584198,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6,
|
| 1063 |
+
"learning_rate": 2.0658795558326745e-06,
|
| 1064 |
+
"logits/chosen": 0.10812600702047348,
|
| 1065 |
+
"logits/rejected": 0.16122448444366455,
|
| 1066 |
+
"logps/chosen": -769.3707885742188,
|
| 1067 |
+
"logps/rejected": -757.4603881835938,
|
| 1068 |
+
"loss": 231473.425,
|
| 1069 |
+
"rewards/accuracies": 0.59375,
|
| 1070 |
+
"rewards/chosen": -0.4337649345397949,
|
| 1071 |
+
"rewards/margins": 0.04006404057145119,
|
| 1072 |
+
"rewards/rejected": -0.4738289713859558,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.61,
|
| 1077 |
+
"learning_rate": 1.997305197135089e-06,
|
| 1078 |
+
"logits/chosen": 0.11236604303121567,
|
| 1079 |
+
"logits/rejected": 0.178950697183609,
|
| 1080 |
+
"logps/chosen": -693.5897827148438,
|
| 1081 |
+
"logps/rejected": -708.540283203125,
|
| 1082 |
+
"loss": 220484.3,
|
| 1083 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1084 |
+
"rewards/chosen": -0.37934717535972595,
|
| 1085 |
+
"rewards/margins": 0.048292335122823715,
|
| 1086 |
+
"rewards/rejected": -0.4276394844055176,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.62,
|
| 1091 |
+
"learning_rate": 1.9291228247233607e-06,
|
| 1092 |
+
"logits/chosen": 0.15532401204109192,
|
| 1093 |
+
"logits/rejected": 0.18017269670963287,
|
| 1094 |
+
"logps/chosen": -744.7501831054688,
|
| 1095 |
+
"logps/rejected": -772.5374145507812,
|
| 1096 |
+
"loss": 203500.3625,
|
| 1097 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 1098 |
+
"rewards/chosen": -0.40235796570777893,
|
| 1099 |
+
"rewards/margins": 0.06978850811719894,
|
| 1100 |
+
"rewards/rejected": -0.4721464216709137,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.62,
|
| 1105 |
+
"learning_rate": 1.8613856051605242e-06,
|
| 1106 |
+
"logits/chosen": 0.15754157304763794,
|
| 1107 |
+
"logits/rejected": 0.12605436146259308,
|
| 1108 |
+
"logps/chosen": -784.3040771484375,
|
| 1109 |
+
"logps/rejected": -816.6812744140625,
|
| 1110 |
+
"loss": 217971.425,
|
| 1111 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1112 |
+
"rewards/chosen": -0.46135205030441284,
|
| 1113 |
+
"rewards/margins": 0.05997233837842941,
|
| 1114 |
+
"rewards/rejected": -0.5213243961334229,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.63,
|
| 1119 |
+
"learning_rate": 1.7941463578928088e-06,
|
| 1120 |
+
"logits/chosen": 0.14722251892089844,
|
| 1121 |
+
"logits/rejected": 0.22689004242420197,
|
| 1122 |
+
"logps/chosen": -791.4058227539062,
|
| 1123 |
+
"logps/rejected": -835.9578857421875,
|
| 1124 |
+
"loss": 198421.35,
|
| 1125 |
+
"rewards/accuracies": 0.637499988079071,
|
| 1126 |
+
"rewards/chosen": -0.45540469884872437,
|
| 1127 |
+
"rewards/margins": 0.08554159849882126,
|
| 1128 |
+
"rewards/rejected": -0.5409462451934814,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.64,
|
| 1133 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 1134 |
+
"logits/chosen": 0.16612738370895386,
|
| 1135 |
+
"logits/rejected": 0.19463475048542023,
|
| 1136 |
+
"logps/chosen": -757.1405639648438,
|
| 1137 |
+
"logps/rejected": -837.064453125,
|
| 1138 |
+
"loss": 209272.275,
|
| 1139 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 1140 |
+
"rewards/chosen": -0.4466177821159363,
|
| 1141 |
+
"rewards/margins": 0.06889412552118301,
|
| 1142 |
+
"rewards/rejected": -0.5155119299888611,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.65,
|
| 1147 |
+
"learning_rate": 1.661371075624363e-06,
|
| 1148 |
+
"logits/chosen": 0.18364760279655457,
|
| 1149 |
+
"logits/rejected": 0.20422661304473877,
|
| 1150 |
+
"logps/chosen": -794.0057983398438,
|
| 1151 |
+
"logps/rejected": -818.2443237304688,
|
| 1152 |
+
"loss": 205674.6875,
|
| 1153 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1154 |
+
"rewards/chosen": -0.47054606676101685,
|
| 1155 |
+
"rewards/margins": 0.07392840087413788,
|
| 1156 |
+
"rewards/rejected": -0.5444744825363159,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.66,
|
| 1161 |
+
"learning_rate": 1.5959385747947697e-06,
|
| 1162 |
+
"logits/chosen": 0.18115699291229248,
|
| 1163 |
+
"logits/rejected": 0.17477403581142426,
|
| 1164 |
+
"logps/chosen": -764.315185546875,
|
| 1165 |
+
"logps/rejected": -809.1729736328125,
|
| 1166 |
+
"loss": 224041.65,
|
| 1167 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1168 |
+
"rewards/chosen": -0.4702480435371399,
|
| 1169 |
+
"rewards/margins": 0.057804904878139496,
|
| 1170 |
+
"rewards/rejected": -0.5280529856681824,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.66,
|
| 1175 |
+
"learning_rate": 1.5312110338697427e-06,
|
| 1176 |
+
"logits/chosen": 0.1292174756526947,
|
| 1177 |
+
"logits/rejected": 0.17837834358215332,
|
| 1178 |
+
"logps/chosen": -689.7651977539062,
|
| 1179 |
+
"logps/rejected": -729.2711181640625,
|
| 1180 |
+
"loss": 207770.6,
|
| 1181 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1182 |
+
"rewards/chosen": -0.3903941512107849,
|
| 1183 |
+
"rewards/margins": 0.06973019987344742,
|
| 1184 |
+
"rewards/rejected": -0.46012434363365173,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.67,
|
| 1189 |
+
"learning_rate": 1.467238925438646e-06,
|
| 1190 |
+
"logits/chosen": 0.15589091181755066,
|
| 1191 |
+
"logits/rejected": 0.2015005648136139,
|
| 1192 |
+
"logps/chosen": -754.8555908203125,
|
| 1193 |
+
"logps/rejected": -806.1656494140625,
|
| 1194 |
+
"loss": 212527.35,
|
| 1195 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1196 |
+
"rewards/chosen": -0.4270619750022888,
|
| 1197 |
+
"rewards/margins": 0.07408256083726883,
|
| 1198 |
+
"rewards/rejected": -0.501144528388977,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.68,
|
| 1203 |
+
"learning_rate": 1.4040721330273063e-06,
|
| 1204 |
+
"logits/chosen": 0.12746846675872803,
|
| 1205 |
+
"logits/rejected": 0.16994647681713104,
|
| 1206 |
+
"logps/chosen": -750.6973876953125,
|
| 1207 |
+
"logps/rejected": -806.6913452148438,
|
| 1208 |
+
"loss": 195321.975,
|
| 1209 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 1210 |
+
"rewards/chosen": -0.43772464990615845,
|
| 1211 |
+
"rewards/margins": 0.08586438000202179,
|
| 1212 |
+
"rewards/rejected": -0.523589015007019,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.69,
|
| 1217 |
+
"learning_rate": 1.3417599122003464e-06,
|
| 1218 |
+
"logits/chosen": 0.1746450811624527,
|
| 1219 |
+
"logits/rejected": 0.18844328820705414,
|
| 1220 |
+
"logps/chosen": -783.6176147460938,
|
| 1221 |
+
"logps/rejected": -806.5670166015625,
|
| 1222 |
+
"loss": 214213.525,
|
| 1223 |
+
"rewards/accuracies": 0.612500011920929,
|
| 1224 |
+
"rewards/chosen": -0.4747697412967682,
|
| 1225 |
+
"rewards/margins": 0.06772130727767944,
|
| 1226 |
+
"rewards/rejected": -0.54249107837677,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7,
|
| 1231 |
+
"learning_rate": 1.280350852153168e-06,
|
| 1232 |
+
"logits/chosen": 0.13849861919879913,
|
| 1233 |
+
"logits/rejected": 0.2154228687286377,
|
| 1234 |
+
"logps/chosen": -784.5640869140625,
|
| 1235 |
+
"logps/rejected": -815.0606689453125,
|
| 1236 |
+
"loss": 192301.8125,
|
| 1237 |
+
"rewards/accuracies": 0.65625,
|
| 1238 |
+
"rewards/chosen": -0.4758680760860443,
|
| 1239 |
+
"rewards/margins": 0.09498603641986847,
|
| 1240 |
+
"rewards/rejected": -0.5708540678024292,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7,
|
| 1245 |
+
"learning_rate": 1.2198928378235717e-06,
|
| 1246 |
+
"logits/chosen": 0.16985270380973816,
|
| 1247 |
+
"logits/rejected": 0.1884302943944931,
|
| 1248 |
+
"logps/chosen": -779.4686279296875,
|
| 1249 |
+
"logps/rejected": -812.2041015625,
|
| 1250 |
+
"loss": 213896.75,
|
| 1251 |
+
"rewards/accuracies": 0.53125,
|
| 1252 |
+
"rewards/chosen": -0.48907041549682617,
|
| 1253 |
+
"rewards/margins": 0.06477129459381104,
|
| 1254 |
+
"rewards/rejected": -0.5538417100906372,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.71,
|
| 1259 |
+
"learning_rate": 1.160433012552508e-06,
|
| 1260 |
+
"logits/chosen": 0.1970738023519516,
|
| 1261 |
+
"logits/rejected": 0.20526520907878876,
|
| 1262 |
+
"logps/chosen": -754.1630249023438,
|
| 1263 |
+
"logps/rejected": -832.0451049804688,
|
| 1264 |
+
"loss": 196734.9625,
|
| 1265 |
+
"rewards/accuracies": 0.625,
|
| 1266 |
+
"rewards/chosen": -0.49033814668655396,
|
| 1267 |
+
"rewards/margins": 0.08532597869634628,
|
| 1268 |
+
"rewards/rejected": -0.5756641626358032,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.72,
|
| 1273 |
+
"learning_rate": 1.1020177413231334e-06,
|
| 1274 |
+
"logits/chosen": 0.2092396467924118,
|
| 1275 |
+
"logits/rejected": 0.2251383364200592,
|
| 1276 |
+
"logps/chosen": -786.1522216796875,
|
| 1277 |
+
"logps/rejected": -857.3021240234375,
|
| 1278 |
+
"loss": 205046.1125,
|
| 1279 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 1280 |
+
"rewards/chosen": -0.505187451839447,
|
| 1281 |
+
"rewards/margins": 0.07834392040967941,
|
| 1282 |
+
"rewards/rejected": -0.583531379699707,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.73,
|
| 1287 |
+
"learning_rate": 1.0446925746067768e-06,
|
| 1288 |
+
"logits/chosen": 0.18920519948005676,
|
| 1289 |
+
"logits/rejected": 0.17220894992351532,
|
| 1290 |
+
"logps/chosen": -789.0540771484375,
|
| 1291 |
+
"logps/rejected": -834.8899536132812,
|
| 1292 |
+
"loss": 198896.5,
|
| 1293 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1294 |
+
"rewards/chosen": -0.4787345826625824,
|
| 1295 |
+
"rewards/margins": 0.08251155912876129,
|
| 1296 |
+
"rewards/rejected": -0.5612461566925049,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.74,
|
| 1301 |
+
"learning_rate": 9.88502212844063e-07,
|
| 1302 |
+
"logits/chosen": 0.15440575778484344,
|
| 1303 |
+
"logits/rejected": 0.1388414055109024,
|
| 1304 |
+
"logps/chosen": -744.649658203125,
|
| 1305 |
+
"logps/rejected": -803.2208251953125,
|
| 1306 |
+
"loss": 216045.15,
|
| 1307 |
+
"rewards/accuracies": 0.59375,
|
| 1308 |
+
"rewards/chosen": -0.475663423538208,
|
| 1309 |
+
"rewards/margins": 0.06261987239122391,
|
| 1310 |
+
"rewards/rejected": -0.5382832288742065,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.74,
|
| 1315 |
+
"learning_rate": 9.334904715888496e-07,
|
| 1316 |
+
"logits/chosen": 0.1935366839170456,
|
| 1317 |
+
"logits/rejected": 0.1987215131521225,
|
| 1318 |
+
"logps/chosen": -768.1312866210938,
|
| 1319 |
+
"logps/rejected": -862.0283203125,
|
| 1320 |
+
"loss": 188496.4125,
|
| 1321 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1322 |
+
"rewards/chosen": -0.46092915534973145,
|
| 1323 |
+
"rewards/margins": 0.09596993029117584,
|
| 1324 |
+
"rewards/rejected": -0.5568991303443909,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.75,
|
| 1329 |
+
"learning_rate": 8.797002473421729e-07,
|
| 1330 |
+
"logits/chosen": 0.14081716537475586,
|
| 1331 |
+
"logits/rejected": 0.20105788111686707,
|
| 1332 |
+
"logps/chosen": -797.4901123046875,
|
| 1333 |
+
"logps/rejected": -844.3346557617188,
|
| 1334 |
+
"loss": 211975.675,
|
| 1335 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1336 |
+
"rewards/chosen": -0.4644051492214203,
|
| 1337 |
+
"rewards/margins": 0.07531893998384476,
|
| 1338 |
+
"rewards/rejected": -0.5397240519523621,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.76,
|
| 1343 |
+
"learning_rate": 8.271734841028553e-07,
|
| 1344 |
+
"logits/chosen": 0.14769385755062103,
|
| 1345 |
+
"logits/rejected": 0.18247342109680176,
|
| 1346 |
+
"logps/chosen": -755.4373779296875,
|
| 1347 |
+
"logps/rejected": -813.0632934570312,
|
| 1348 |
+
"loss": 193557.75,
|
| 1349 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 1350 |
+
"rewards/chosen": -0.4386064112186432,
|
| 1351 |
+
"rewards/margins": 0.09906734526157379,
|
| 1352 |
+
"rewards/rejected": -0.5376737117767334,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.77,
|
| 1357 |
+
"learning_rate": 7.759511406608255e-07,
|
| 1358 |
+
"logits/chosen": 0.16132482886314392,
|
| 1359 |
+
"logits/rejected": 0.20790281891822815,
|
| 1360 |
+
"logps/chosen": -767.7522583007812,
|
| 1361 |
+
"logps/rejected": -800.89453125,
|
| 1362 |
+
"loss": 208434.2625,
|
| 1363 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 1364 |
+
"rewards/chosen": -0.4419415593147278,
|
| 1365 |
+
"rewards/margins": 0.07322575896978378,
|
| 1366 |
+
"rewards/rejected": -0.5151672959327698,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.78,
|
| 1371 |
+
"learning_rate": 7.260731586586983e-07,
|
| 1372 |
+
"logits/chosen": 0.18127396702766418,
|
| 1373 |
+
"logits/rejected": 0.2316737174987793,
|
| 1374 |
+
"logps/chosen": -783.130859375,
|
| 1375 |
+
"logps/rejected": -849.43408203125,
|
| 1376 |
+
"loss": 201358.2875,
|
| 1377 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 1378 |
+
"rewards/chosen": -0.48671525716781616,
|
| 1379 |
+
"rewards/margins": 0.0818987563252449,
|
| 1380 |
+
"rewards/rejected": -0.5686140656471252,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.78,
|
| 1385 |
+
"learning_rate": 6.775784314464717e-07,
|
| 1386 |
+
"logits/chosen": 0.11633706092834473,
|
| 1387 |
+
"logits/rejected": 0.15391342341899872,
|
| 1388 |
+
"logps/chosen": -836.8153076171875,
|
| 1389 |
+
"logps/rejected": -892.5672607421875,
|
| 1390 |
+
"loss": 174914.7875,
|
| 1391 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1392 |
+
"rewards/chosen": -0.4858662486076355,
|
| 1393 |
+
"rewards/margins": 0.11686857044696808,
|
| 1394 |
+
"rewards/rejected": -0.6027349233627319,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.79,
|
| 1399 |
+
"learning_rate": 6.305047737536707e-07,
|
| 1400 |
+
"logits/chosen": 0.1393323391675949,
|
| 1401 |
+
"logits/rejected": 0.16812780499458313,
|
| 1402 |
+
"logps/chosen": -863.9642333984375,
|
| 1403 |
+
"logps/rejected": -920.6380615234375,
|
| 1404 |
+
"loss": 207880.375,
|
| 1405 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1406 |
+
"rewards/chosen": -0.545138955116272,
|
| 1407 |
+
"rewards/margins": 0.08065886050462723,
|
| 1408 |
+
"rewards/rejected": -0.6257978677749634,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8,
|
| 1413 |
+
"learning_rate": 5.848888922025553e-07,
|
| 1414 |
+
"logits/chosen": 0.15241369605064392,
|
| 1415 |
+
"logits/rejected": 0.21405677497386932,
|
| 1416 |
+
"logps/chosen": -807.337890625,
|
| 1417 |
+
"logps/rejected": -870.9757690429688,
|
| 1418 |
+
"loss": 204096.3375,
|
| 1419 |
+
"rewards/accuracies": 0.612500011920929,
|
| 1420 |
+
"rewards/chosen": -0.4976535737514496,
|
| 1421 |
+
"rewards/margins": 0.08147857338190079,
|
| 1422 |
+
"rewards/rejected": -0.5791321992874146,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.81,
|
| 1427 |
+
"learning_rate": 5.407663566854008e-07,
|
| 1428 |
+
"logits/chosen": 0.15341579914093018,
|
| 1429 |
+
"logits/rejected": 0.2227795422077179,
|
| 1430 |
+
"logps/chosen": -824.1964111328125,
|
| 1431 |
+
"logps/rejected": -901.2435302734375,
|
| 1432 |
+
"loss": 186279.7875,
|
| 1433 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1434 |
+
"rewards/chosen": -0.5105653405189514,
|
| 1435 |
+
"rewards/margins": 0.10616906732320786,
|
| 1436 |
+
"rewards/rejected": -0.6167343854904175,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.82,
|
| 1441 |
+
"learning_rate": 4.981715726281666e-07,
|
| 1442 |
+
"logits/chosen": 0.1369406282901764,
|
| 1443 |
+
"logits/rejected": 0.17808625102043152,
|
| 1444 |
+
"logps/chosen": -815.9120483398438,
|
| 1445 |
+
"logps/rejected": -892.9197998046875,
|
| 1446 |
+
"loss": 199104.275,
|
| 1447 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1448 |
+
"rewards/chosen": -0.5129615664482117,
|
| 1449 |
+
"rewards/margins": 0.0987924337387085,
|
| 1450 |
+
"rewards/rejected": -0.6117540597915649,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.82,
|
| 1455 |
+
"learning_rate": 4.5713775416217884e-07,
|
| 1456 |
+
"logits/chosen": 0.17074373364448547,
|
| 1457 |
+
"logits/rejected": 0.17214760184288025,
|
| 1458 |
+
"logps/chosen": -712.3060913085938,
|
| 1459 |
+
"logps/rejected": -775.6600341796875,
|
| 1460 |
+
"loss": 220452.675,
|
| 1461 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1462 |
+
"rewards/chosen": -0.4651338458061218,
|
| 1463 |
+
"rewards/margins": 0.05841842293739319,
|
| 1464 |
+
"rewards/rejected": -0.5235522985458374,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.83,
|
| 1469 |
+
"learning_rate": 4.1769689822475147e-07,
|
| 1470 |
+
"logits/chosen": 0.1837390959262848,
|
| 1471 |
+
"logits/rejected": 0.1595425009727478,
|
| 1472 |
+
"logps/chosen": -760.4705200195312,
|
| 1473 |
+
"logps/rejected": -818.9217529296875,
|
| 1474 |
+
"loss": 202559.575,
|
| 1475 |
+
"rewards/accuracies": 0.606249988079071,
|
| 1476 |
+
"rewards/chosen": -0.45589479804039,
|
| 1477 |
+
"rewards/margins": 0.07983261346817017,
|
| 1478 |
+
"rewards/rejected": -0.5357274413108826,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.84,
|
| 1483 |
+
"learning_rate": 3.798797596089351e-07,
|
| 1484 |
+
"logits/chosen": 0.13117244839668274,
|
| 1485 |
+
"logits/rejected": 0.17568498849868774,
|
| 1486 |
+
"logps/chosen": -819.6179809570312,
|
| 1487 |
+
"logps/rejected": -890.716796875,
|
| 1488 |
+
"loss": 206787.35,
|
| 1489 |
+
"rewards/accuracies": 0.625,
|
| 1490 |
+
"rewards/chosen": -0.5022695660591125,
|
| 1491 |
+
"rewards/margins": 0.08515648543834686,
|
| 1492 |
+
"rewards/rejected": -0.5874260663986206,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.85,
|
| 1497 |
+
"learning_rate": 3.4371582698185636e-07,
|
| 1498 |
+
"logits/chosen": 0.13082125782966614,
|
| 1499 |
+
"logits/rejected": 0.1985786408185959,
|
| 1500 |
+
"logps/chosen": -748.1300048828125,
|
| 1501 |
+
"logps/rejected": -820.7215576171875,
|
| 1502 |
+
"loss": 185068.825,
|
| 1503 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1504 |
+
"rewards/chosen": -0.453665167093277,
|
| 1505 |
+
"rewards/margins": 0.10252256691455841,
|
| 1506 |
+
"rewards/rejected": -0.5561877489089966,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.86,
|
| 1511 |
+
"learning_rate": 3.092332998903416e-07,
|
| 1512 |
+
"logits/chosen": 0.15080007910728455,
|
| 1513 |
+
"logits/rejected": 0.1654890477657318,
|
| 1514 |
+
"logps/chosen": -769.5250854492188,
|
| 1515 |
+
"logps/rejected": -801.05859375,
|
| 1516 |
+
"loss": 207828.275,
|
| 1517 |
+
"rewards/accuracies": 0.637499988079071,
|
| 1518 |
+
"rewards/chosen": -0.46206703782081604,
|
| 1519 |
+
"rewards/margins": 0.07203520834445953,
|
| 1520 |
+
"rewards/rejected": -0.5341022610664368,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.86,
|
| 1525 |
+
"learning_rate": 2.764590667717562e-07,
|
| 1526 |
+
"logits/chosen": 0.15324567258358002,
|
| 1527 |
+
"logits/rejected": 0.15729650855064392,
|
| 1528 |
+
"logps/chosen": -822.15966796875,
|
| 1529 |
+
"logps/rejected": -868.7623291015625,
|
| 1530 |
+
"loss": 186190.1875,
|
| 1531 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1532 |
+
"rewards/chosen": -0.47839221358299255,
|
| 1533 |
+
"rewards/margins": 0.09772337228059769,
|
| 1534 |
+
"rewards/rejected": -0.576115608215332,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.87,
|
| 1539 |
+
"learning_rate": 2.454186839872158e-07,
|
| 1540 |
+
"logits/chosen": 0.12992113828659058,
|
| 1541 |
+
"logits/rejected": 0.17095732688903809,
|
| 1542 |
+
"logps/chosen": -741.812744140625,
|
| 1543 |
+
"logps/rejected": -800.1990356445312,
|
| 1544 |
+
"loss": 199043.9375,
|
| 1545 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1546 |
+
"rewards/chosen": -0.457599937915802,
|
| 1547 |
+
"rewards/margins": 0.08316919207572937,
|
| 1548 |
+
"rewards/rejected": -0.5407691597938538,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.88,
|
| 1553 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 1554 |
+
"logits/chosen": 0.13861994445323944,
|
| 1555 |
+
"logits/rejected": 0.1576179414987564,
|
| 1556 |
+
"logps/chosen": -768.8173828125,
|
| 1557 |
+
"logps/rejected": -865.2081298828125,
|
| 1558 |
+
"loss": 204553.75,
|
| 1559 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 1560 |
+
"rewards/chosen": -0.47151508927345276,
|
| 1561 |
+
"rewards/margins": 0.08232859522104263,
|
| 1562 |
+
"rewards/rejected": -0.5538436770439148,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.89,
|
| 1567 |
+
"learning_rate": 1.8863491596921745e-07,
|
| 1568 |
+
"logits/chosen": 0.14720812439918518,
|
| 1569 |
+
"logits/rejected": 0.1831195056438446,
|
| 1570 |
+
"logps/chosen": -797.4757080078125,
|
| 1571 |
+
"logps/rejected": -875.4158325195312,
|
| 1572 |
+
"loss": 196172.15,
|
| 1573 |
+
"rewards/accuracies": 0.637499988079071,
|
| 1574 |
+
"rewards/chosen": -0.4769609570503235,
|
| 1575 |
+
"rewards/margins": 0.09553588926792145,
|
| 1576 |
+
"rewards/rejected": -0.5724968314170837,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9,
|
| 1581 |
+
"learning_rate": 1.629358090099639e-07,
|
| 1582 |
+
"logits/chosen": 0.15089096128940582,
|
| 1583 |
+
"logits/rejected": 0.19758984446525574,
|
| 1584 |
+
"logps/chosen": -764.42138671875,
|
| 1585 |
+
"logps/rejected": -824.7005615234375,
|
| 1586 |
+
"loss": 196494.8125,
|
| 1587 |
+
"rewards/accuracies": 0.625,
|
| 1588 |
+
"rewards/chosen": -0.47583532333374023,
|
| 1589 |
+
"rewards/margins": 0.09009422361850739,
|
| 1590 |
+
"rewards/rejected": -0.5659295320510864,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9,
|
| 1595 |
+
"learning_rate": 1.3905907440629752e-07,
|
| 1596 |
+
"logits/chosen": 0.08568934351205826,
|
| 1597 |
+
"logits/rejected": 0.2077227085828781,
|
| 1598 |
+
"logps/chosen": -822.9054565429688,
|
| 1599 |
+
"logps/rejected": -849.7650146484375,
|
| 1600 |
+
"loss": 206632.825,
|
| 1601 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1602 |
+
"rewards/chosen": -0.4819079339504242,
|
| 1603 |
+
"rewards/margins": 0.07615750283002853,
|
| 1604 |
+
"rewards/rejected": -0.5580654144287109,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.91,
|
| 1609 |
+
"learning_rate": 1.1702333051763271e-07,
|
| 1610 |
+
"logits/chosen": 0.10578087717294693,
|
| 1611 |
+
"logits/rejected": 0.20318789780139923,
|
| 1612 |
+
"logps/chosen": -779.73876953125,
|
| 1613 |
+
"logps/rejected": -802.28125,
|
| 1614 |
+
"loss": 215590.5,
|
| 1615 |
+
"rewards/accuracies": 0.606249988079071,
|
| 1616 |
+
"rewards/chosen": -0.4948987364768982,
|
| 1617 |
+
"rewards/margins": 0.06325242668390274,
|
| 1618 |
+
"rewards/rejected": -0.558151125907898,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.92,
|
| 1623 |
+
"learning_rate": 9.684576015420277e-08,
|
| 1624 |
+
"logits/chosen": 0.12398680299520493,
|
| 1625 |
+
"logits/rejected": 0.18018838763237,
|
| 1626 |
+
"logps/chosen": -837.7791748046875,
|
| 1627 |
+
"logps/rejected": -894.8541259765625,
|
| 1628 |
+
"loss": 209903.075,
|
| 1629 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 1630 |
+
"rewards/chosen": -0.5204319953918457,
|
| 1631 |
+
"rewards/margins": 0.07653878629207611,
|
| 1632 |
+
"rewards/rejected": -0.596970796585083,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.93,
|
| 1637 |
+
"learning_rate": 7.854209717842231e-08,
|
| 1638 |
+
"logits/chosen": 0.1505010426044464,
|
| 1639 |
+
"logits/rejected": 0.15430773794651031,
|
| 1640 |
+
"logps/chosen": -726.85888671875,
|
| 1641 |
+
"logps/rejected": -761.1307983398438,
|
| 1642 |
+
"loss": 221966.15,
|
| 1643 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1644 |
+
"rewards/chosen": -0.44809263944625854,
|
| 1645 |
+
"rewards/margins": 0.05523185059428215,
|
| 1646 |
+
"rewards/rejected": -0.5033245086669922,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.94,
|
| 1651 |
+
"learning_rate": 6.212661423609184e-08,
|
| 1652 |
+
"logits/chosen": 0.16363343596458435,
|
| 1653 |
+
"logits/rejected": 0.20976746082305908,
|
| 1654 |
+
"logps/chosen": -806.9349365234375,
|
| 1655 |
+
"logps/rejected": -863.7510986328125,
|
| 1656 |
+
"loss": 190806.0375,
|
| 1657 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1658 |
+
"rewards/chosen": -0.4746907353401184,
|
| 1659 |
+
"rewards/margins": 0.09740374982357025,
|
| 1660 |
+
"rewards/rejected": -0.5720945000648499,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.94,
|
| 1665 |
+
"learning_rate": 4.761211162702117e-08,
|
| 1666 |
+
"logits/chosen": 0.18693126738071442,
|
| 1667 |
+
"logits/rejected": 0.17179496586322784,
|
| 1668 |
+
"logps/chosen": -774.9769897460938,
|
| 1669 |
+
"logps/rejected": -854.8970947265625,
|
| 1670 |
+
"loss": 202477.175,
|
| 1671 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1672 |
+
"rewards/chosen": -0.4908948838710785,
|
| 1673 |
+
"rewards/margins": 0.08085609972476959,
|
| 1674 |
+
"rewards/rejected": -0.5717509984970093,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.95,
|
| 1679 |
+
"learning_rate": 3.5009907323737826e-08,
|
| 1680 |
+
"logits/chosen": 0.16129986941814423,
|
| 1681 |
+
"logits/rejected": 0.19500942528247833,
|
| 1682 |
+
"logps/chosen": -792.909912109375,
|
| 1683 |
+
"logps/rejected": -888.8028564453125,
|
| 1684 |
+
"loss": 184403.25,
|
| 1685 |
+
"rewards/accuracies": 0.6875,
|
| 1686 |
+
"rewards/chosen": -0.5034135580062866,
|
| 1687 |
+
"rewards/margins": 0.10005589574575424,
|
| 1688 |
+
"rewards/rejected": -0.6034694910049438,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.96,
|
| 1693 |
+
"learning_rate": 2.4329828146074096e-08,
|
| 1694 |
+
"logits/chosen": 0.18494980037212372,
|
| 1695 |
+
"logits/rejected": 0.17617648839950562,
|
| 1696 |
+
"logps/chosen": -800.6261596679688,
|
| 1697 |
+
"logps/rejected": -876.5882568359375,
|
| 1698 |
+
"loss": 196898.3625,
|
| 1699 |
+
"rewards/accuracies": 0.625,
|
| 1700 |
+
"rewards/chosen": -0.47020062804222107,
|
| 1701 |
+
"rewards/margins": 0.08556860685348511,
|
| 1702 |
+
"rewards/rejected": -0.555769145488739,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.97,
|
| 1707 |
+
"learning_rate": 1.5580202098509078e-08,
|
| 1708 |
+
"logits/chosen": 0.14691737294197083,
|
| 1709 |
+
"logits/rejected": 0.14955729246139526,
|
| 1710 |
+
"logps/chosen": -776.9261474609375,
|
| 1711 |
+
"logps/rejected": -835.3674926757812,
|
| 1712 |
+
"loss": 190650.5875,
|
| 1713 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1714 |
+
"rewards/chosen": -0.4579540193080902,
|
| 1715 |
+
"rewards/margins": 0.09634914249181747,
|
| 1716 |
+
"rewards/rejected": -0.5543031692504883,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.98,
|
| 1721 |
+
"learning_rate": 8.767851876239075e-09,
|
| 1722 |
+
"logits/chosen": 0.16913214325904846,
|
| 1723 |
+
"logits/rejected": 0.2180750072002411,
|
| 1724 |
+
"logps/chosen": -779.931640625,
|
| 1725 |
+
"logps/rejected": -836.6170043945312,
|
| 1726 |
+
"loss": 202766.325,
|
| 1727 |
+
"rewards/accuracies": 0.606249988079071,
|
| 1728 |
+
"rewards/chosen": -0.47672662138938904,
|
| 1729 |
+
"rewards/margins": 0.09171019494533539,
|
| 1730 |
+
"rewards/rejected": -0.5684367418289185,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.98,
|
| 1735 |
+
"learning_rate": 3.8980895450474455e-09,
|
| 1736 |
+
"logits/chosen": 0.10289184749126434,
|
| 1737 |
+
"logits/rejected": 0.1398571878671646,
|
| 1738 |
+
"logps/chosen": -763.5850219726562,
|
| 1739 |
+
"logps/rejected": -839.4816284179688,
|
| 1740 |
+
"loss": 208227.95,
|
| 1741 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1742 |
+
"rewards/chosen": -0.47743678092956543,
|
| 1743 |
+
"rewards/margins": 0.07457558810710907,
|
| 1744 |
+
"rewards/rejected": -0.5520124435424805,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.99,
|
| 1749 |
+
"learning_rate": 9.747123991141193e-10,
|
| 1750 |
+
"logits/chosen": 0.142451211810112,
|
| 1751 |
+
"logits/rejected": 0.16754242777824402,
|
| 1752 |
+
"logps/chosen": -774.1744384765625,
|
| 1753 |
+
"logps/rejected": -825.1458740234375,
|
| 1754 |
+
"loss": 226408.775,
|
| 1755 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 1756 |
+
"rewards/chosen": -0.47371751070022583,
|
| 1757 |
+
"rewards/margins": 0.05325751751661301,
|
| 1758 |
+
"rewards/rejected": -0.5269749760627747,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.0,
|
| 1763 |
+
"learning_rate": 0.0,
|
| 1764 |
+
"logits/chosen": 0.17251411080360413,
|
| 1765 |
+
"logits/rejected": 0.23562026023864746,
|
| 1766 |
+
"logps/chosen": -756.9190673828125,
|
| 1767 |
+
"logps/rejected": -808.0845947265625,
|
| 1768 |
+
"loss": 202083.5,
|
| 1769 |
+
"rewards/accuracies": 0.606249988079071,
|
| 1770 |
+
"rewards/chosen": -0.4673381447792053,
|
| 1771 |
+
"rewards/margins": 0.0791386216878891,
|
| 1772 |
+
"rewards/rejected": -0.5464767217636108,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.0,
|
| 1777 |
+
"step": 1250,
|
| 1778 |
+
"total_flos": 0.0,
|
| 1779 |
+
"train_loss": 214327.7246,
|
| 1780 |
+
"train_runtime": 12057.8081,
|
| 1781 |
+
"train_samples_per_second": 1.659,
|
| 1782 |
+
"train_steps_per_second": 0.104
|
| 1783 |
+
}
|
| 1784 |
+
],
|
| 1785 |
+
"logging_steps": 10,
|
| 1786 |
+
"max_steps": 1250,
|
| 1787 |
+
"num_input_tokens_seen": 0,
|
| 1788 |
+
"num_train_epochs": 1,
|
| 1789 |
+
"save_steps": 100,
|
| 1790 |
+
"total_flos": 0.0,
|
| 1791 |
+
"train_batch_size": 4,
|
| 1792 |
+
"trial_name": null,
|
| 1793 |
+
"trial_params": null
|
| 1794 |
+
}
|