Commit
•
1711bb1
1
Parent(s):
ad901b2
Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- emissions.csv +2 -0
- runs/Sep19_19-27-21_gpu4-119-5/events.out.tfevents.1726738147.gpu4-119-5.385328.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1794 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged
|
| 8 |
+
model-index:
|
| 9 |
+
- name: zephyr-7b-dpo-0k-15k-0.001-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 |
+
# zephyr-7b-dpo-0k-15k-0.001-i1
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged](https://huggingface.co/DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged) 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: 3
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 12
|
| 45 |
+
- total_eval_batch_size: 6
|
| 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
|
| 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 sha256:389fe6efb785f67577d5b77be77e128c333bac374632a988320e6b427c10594d
|
| 3 |
size 671150064
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.6113488140106201,
|
| 4 |
+
"train_runtime": 13063.964,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 1.148,
|
| 7 |
+
"train_steps_per_second": 0.096
|
| 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 |
+
2024-09-19T23:06:51,codecarbon,7c914d07-c4ea-4a84-bf6c-02a4e62087ad,13063.968004226685,0.006697428912915107,5.126642158606204e-07,42.5,574.926,188.74309015274048,0.15422212819026557,1.9818767648647813,0.6812393140365398,2.817338207091581,Canada,CAN,quebec,,,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,-71.2,46.8,503.3149070739746,machine,N,1.0
|
runs/Sep19_19-27-21_gpu4-119-5/events.out.tfevents.1726738147.gpu4-119-5.385328.0
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 sha256:029cb288ea4ef330810fddb044642a6cdb6c562a2a1eaef33da992e59f0d717e
|
| 3 |
+
size 84725
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.6113488140106201,
|
| 4 |
+
"train_runtime": 13063.964,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 1.148,
|
| 7 |
+
"train_steps_per_second": 0.096
|
| 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": -2.6577353477478027,
|
| 15 |
+
"logits/rejected": -2.043900489807129,
|
| 16 |
+
"logps/chosen": -505.98724365234375,
|
| 17 |
+
"logps/rejected": -319.40179443359375,
|
| 18 |
+
"loss": 0.6931,
|
| 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": -2.477782726287842,
|
| 29 |
+
"logits/rejected": -2.1347055435180664,
|
| 30 |
+
"logps/chosen": -285.4302978515625,
|
| 31 |
+
"logps/rejected": -191.6398468017578,
|
| 32 |
+
"loss": 0.6932,
|
| 33 |
+
"rewards/accuracies": 0.3611111044883728,
|
| 34 |
+
"rewards/chosen": -7.325204205699265e-05,
|
| 35 |
+
"rewards/margins": -3.685199044412002e-05,
|
| 36 |
+
"rewards/rejected": -3.6400058888830245e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 8.000000000000001e-07,
|
| 42 |
+
"logits/chosen": -2.361138343811035,
|
| 43 |
+
"logits/rejected": -2.1276116371154785,
|
| 44 |
+
"logps/chosen": -271.57037353515625,
|
| 45 |
+
"logps/rejected": -208.7891387939453,
|
| 46 |
+
"loss": 0.6932,
|
| 47 |
+
"rewards/accuracies": 0.375,
|
| 48 |
+
"rewards/chosen": -4.8331461584893987e-05,
|
| 49 |
+
"rewards/margins": -0.00016093224985525012,
|
| 50 |
+
"rewards/rejected": 0.00011260081373620778,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 56 |
+
"logits/chosen": -2.2788968086242676,
|
| 57 |
+
"logits/rejected": -2.2496988773345947,
|
| 58 |
+
"logps/chosen": -269.85345458984375,
|
| 59 |
+
"logps/rejected": -288.97467041015625,
|
| 60 |
+
"loss": 0.6931,
|
| 61 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 62 |
+
"rewards/chosen": 0.00023421745572704822,
|
| 63 |
+
"rewards/margins": 0.00014686177019029856,
|
| 64 |
+
"rewards/rejected": 8.735566370887682e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 70 |
+
"logits/chosen": -2.508540153503418,
|
| 71 |
+
"logits/rejected": -2.340709924697876,
|
| 72 |
+
"logps/chosen": -210.4788055419922,
|
| 73 |
+
"logps/rejected": -181.59371948242188,
|
| 74 |
+
"loss": 0.6931,
|
| 75 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 76 |
+
"rewards/chosen": 0.0002574770478531718,
|
| 77 |
+
"rewards/margins": 0.000190830382052809,
|
| 78 |
+
"rewards/rejected": 6.664668035227805e-05,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 84 |
+
"logits/chosen": -2.3627312183380127,
|
| 85 |
+
"logits/rejected": -2.338744640350342,
|
| 86 |
+
"logps/chosen": -195.59091186523438,
|
| 87 |
+
"logps/rejected": -211.3479461669922,
|
| 88 |
+
"loss": 0.6931,
|
| 89 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 90 |
+
"rewards/chosen": 0.0001339252630714327,
|
| 91 |
+
"rewards/margins": 0.00029316064319573343,
|
| 92 |
+
"rewards/rejected": -0.00015923538012430072,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 98 |
+
"logits/chosen": -2.495098829269409,
|
| 99 |
+
"logits/rejected": -2.304222583770752,
|
| 100 |
+
"logps/chosen": -244.5299530029297,
|
| 101 |
+
"logps/rejected": -277.59429931640625,
|
| 102 |
+
"loss": 0.6931,
|
| 103 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 104 |
+
"rewards/chosen": -0.0008799650822766125,
|
| 105 |
+
"rewards/margins": -0.0001361109607387334,
|
| 106 |
+
"rewards/rejected": -0.0007438541506417096,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 112 |
+
"logits/chosen": -2.249950885772705,
|
| 113 |
+
"logits/rejected": -2.266622543334961,
|
| 114 |
+
"logps/chosen": -229.8421173095703,
|
| 115 |
+
"logps/rejected": -216.9417266845703,
|
| 116 |
+
"loss": 0.6928,
|
| 117 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 118 |
+
"rewards/chosen": -0.001011955551803112,
|
| 119 |
+
"rewards/margins": 0.0009981539333239198,
|
| 120 |
+
"rewards/rejected": -0.00201010936871171,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06,
|
| 125 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 126 |
+
"logits/chosen": -2.4004368782043457,
|
| 127 |
+
"logits/rejected": -2.394763708114624,
|
| 128 |
+
"logps/chosen": -265.89312744140625,
|
| 129 |
+
"logps/rejected": -262.71856689453125,
|
| 130 |
+
"loss": 0.6925,
|
| 131 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 132 |
+
"rewards/chosen": -0.0012450494104996324,
|
| 133 |
+
"rewards/margins": 0.0020160204730927944,
|
| 134 |
+
"rewards/rejected": -0.0032610702328383923,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 140 |
+
"logits/chosen": -2.3297479152679443,
|
| 141 |
+
"logits/rejected": -1.9925298690795898,
|
| 142 |
+
"logps/chosen": -268.21148681640625,
|
| 143 |
+
"logps/rejected": -179.89309692382812,
|
| 144 |
+
"loss": 0.6924,
|
| 145 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 146 |
+
"rewards/chosen": -0.002822208683937788,
|
| 147 |
+
"rewards/margins": 0.002088978886604309,
|
| 148 |
+
"rewards/rejected": -0.004911187570542097,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08,
|
| 153 |
+
"learning_rate": 4.000000000000001e-06,
|
| 154 |
+
"logits/chosen": -2.3094894886016846,
|
| 155 |
+
"logits/rejected": -2.3130946159362793,
|
| 156 |
+
"logps/chosen": -275.2729187011719,
|
| 157 |
+
"logps/rejected": -251.2887420654297,
|
| 158 |
+
"loss": 0.6928,
|
| 159 |
+
"rewards/accuracies": 0.625,
|
| 160 |
+
"rewards/chosen": -0.003516852855682373,
|
| 161 |
+
"rewards/margins": 0.0011107095051556826,
|
| 162 |
+
"rewards/rejected": -0.004627562593668699,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09,
|
| 167 |
+
"learning_rate": 4.4e-06,
|
| 168 |
+
"logits/chosen": -2.2586567401885986,
|
| 169 |
+
"logits/rejected": -2.1448559761047363,
|
| 170 |
+
"logps/chosen": -211.8444366455078,
|
| 171 |
+
"logps/rejected": -180.26292419433594,
|
| 172 |
+
"loss": 0.6919,
|
| 173 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 174 |
+
"rewards/chosen": 0.00023485408746637404,
|
| 175 |
+
"rewards/margins": 0.00365343876183033,
|
| 176 |
+
"rewards/rejected": -0.003418584819883108,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 4.800000000000001e-06,
|
| 182 |
+
"logits/chosen": -2.1576130390167236,
|
| 183 |
+
"logits/rejected": -2.168747663497925,
|
| 184 |
+
"logps/chosen": -238.6951141357422,
|
| 185 |
+
"logps/rejected": -270.9164123535156,
|
| 186 |
+
"loss": 0.6905,
|
| 187 |
+
"rewards/accuracies": 0.625,
|
| 188 |
+
"rewards/chosen": -0.0023627025075256824,
|
| 189 |
+
"rewards/margins": 0.005031881853938103,
|
| 190 |
+
"rewards/rejected": -0.0073945834301412106,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1,
|
| 195 |
+
"learning_rate": 4.999756310023261e-06,
|
| 196 |
+
"logits/chosen": -2.439880132675171,
|
| 197 |
+
"logits/rejected": -2.3125338554382324,
|
| 198 |
+
"logps/chosen": -240.32211303710938,
|
| 199 |
+
"logps/rejected": -199.84616088867188,
|
| 200 |
+
"loss": 0.691,
|
| 201 |
+
"rewards/accuracies": 0.574999988079071,
|
| 202 |
+
"rewards/chosen": -0.006134279537945986,
|
| 203 |
+
"rewards/margins": 0.007197326980531216,
|
| 204 |
+
"rewards/rejected": -0.013331606984138489,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.11,
|
| 209 |
+
"learning_rate": 4.997807075247147e-06,
|
| 210 |
+
"logits/chosen": -2.3178114891052246,
|
| 211 |
+
"logits/rejected": -2.017031192779541,
|
| 212 |
+
"logps/chosen": -214.5780792236328,
|
| 213 |
+
"logps/rejected": -194.8052215576172,
|
| 214 |
+
"loss": 0.6907,
|
| 215 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 216 |
+
"rewards/chosen": -0.023361103609204292,
|
| 217 |
+
"rewards/margins": 0.004234091378748417,
|
| 218 |
+
"rewards/rejected": -0.027595192193984985,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 4.993910125649561e-06,
|
| 224 |
+
"logits/chosen": -2.2956302165985107,
|
| 225 |
+
"logits/rejected": -2.1826136112213135,
|
| 226 |
+
"logps/chosen": -245.3561248779297,
|
| 227 |
+
"logps/rejected": -219.53140258789062,
|
| 228 |
+
"loss": 0.687,
|
| 229 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 230 |
+
"rewards/chosen": -0.01726583205163479,
|
| 231 |
+
"rewards/margins": 0.01438895333558321,
|
| 232 |
+
"rewards/rejected": -0.031654782593250275,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13,
|
| 237 |
+
"learning_rate": 4.988068499954578e-06,
|
| 238 |
+
"logits/chosen": -2.1682140827178955,
|
| 239 |
+
"logits/rejected": -2.240255117416382,
|
| 240 |
+
"logps/chosen": -334.9776306152344,
|
| 241 |
+
"logps/rejected": -354.7172546386719,
|
| 242 |
+
"loss": 0.6901,
|
| 243 |
+
"rewards/accuracies": 0.5,
|
| 244 |
+
"rewards/chosen": -0.08232413232326508,
|
| 245 |
+
"rewards/margins": 0.013598999008536339,
|
| 246 |
+
"rewards/rejected": -0.09592311829328537,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"learning_rate": 4.980286753286196e-06,
|
| 252 |
+
"logits/chosen": -2.3772664070129395,
|
| 253 |
+
"logits/rejected": -1.992201566696167,
|
| 254 |
+
"logps/chosen": -375.8896789550781,
|
| 255 |
+
"logps/rejected": -332.3999938964844,
|
| 256 |
+
"loss": 0.6815,
|
| 257 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 258 |
+
"rewards/chosen": -0.10898187011480331,
|
| 259 |
+
"rewards/margins": -0.0016051859129220247,
|
| 260 |
+
"rewards/rejected": -0.10737669467926025,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14,
|
| 265 |
+
"learning_rate": 4.970570953616383e-06,
|
| 266 |
+
"logits/chosen": -2.130321979522705,
|
| 267 |
+
"logits/rejected": -2.113255739212036,
|
| 268 |
+
"logps/chosen": -351.16204833984375,
|
| 269 |
+
"logps/rejected": -367.5383605957031,
|
| 270 |
+
"loss": 0.6796,
|
| 271 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 272 |
+
"rewards/chosen": -0.12460009753704071,
|
| 273 |
+
"rewards/margins": 0.016373703256249428,
|
| 274 |
+
"rewards/rejected": -0.1409737914800644,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15,
|
| 279 |
+
"learning_rate": 4.958928677033465e-06,
|
| 280 |
+
"logits/chosen": -1.8712676763534546,
|
| 281 |
+
"logits/rejected": -1.8069908618927002,
|
| 282 |
+
"logps/chosen": -588.4874877929688,
|
| 283 |
+
"logps/rejected": -609.7493286132812,
|
| 284 |
+
"loss": 0.6845,
|
| 285 |
+
"rewards/accuracies": 0.5,
|
| 286 |
+
"rewards/chosen": -0.3521875739097595,
|
| 287 |
+
"rewards/margins": 0.048989322036504745,
|
| 288 |
+
"rewards/rejected": -0.40117692947387695,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16,
|
| 293 |
+
"learning_rate": 4.9453690018345144e-06,
|
| 294 |
+
"logits/chosen": -2.2647531032562256,
|
| 295 |
+
"logits/rejected": -2.1226019859313965,
|
| 296 |
+
"logps/chosen": -324.08404541015625,
|
| 297 |
+
"logps/rejected": -342.01953125,
|
| 298 |
+
"loss": 0.6819,
|
| 299 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 300 |
+
"rewards/chosen": -0.0697219967842102,
|
| 301 |
+
"rewards/margins": 0.010161248967051506,
|
| 302 |
+
"rewards/rejected": -0.07988324016332626,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 4.9299025014463665e-06,
|
| 308 |
+
"logits/chosen": -2.41994047164917,
|
| 309 |
+
"logits/rejected": -2.061509132385254,
|
| 310 |
+
"logps/chosen": -352.439453125,
|
| 311 |
+
"logps/rejected": -327.6614685058594,
|
| 312 |
+
"loss": 0.6733,
|
| 313 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 314 |
+
"rewards/chosen": -0.0789322555065155,
|
| 315 |
+
"rewards/margins": 0.058253444731235504,
|
| 316 |
+
"rewards/rejected": -0.1371857076883316,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"learning_rate": 4.912541236180779e-06,
|
| 322 |
+
"logits/chosen": -2.14202618598938,
|
| 323 |
+
"logits/rejected": -1.7346794605255127,
|
| 324 |
+
"logps/chosen": -420.63775634765625,
|
| 325 |
+
"logps/rejected": -467.1897888183594,
|
| 326 |
+
"loss": 0.6749,
|
| 327 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 328 |
+
"rewards/chosen": -0.1840709000825882,
|
| 329 |
+
"rewards/margins": 0.0854046419262886,
|
| 330 |
+
"rewards/rejected": -0.2694755494594574,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.18,
|
| 335 |
+
"learning_rate": 4.893298743830168e-06,
|
| 336 |
+
"logits/chosen": -2.003080129623413,
|
| 337 |
+
"logits/rejected": -2.0397982597351074,
|
| 338 |
+
"logps/chosen": -470.3719787597656,
|
| 339 |
+
"logps/rejected": -551.4140625,
|
| 340 |
+
"loss": 0.676,
|
| 341 |
+
"rewards/accuracies": 0.5,
|
| 342 |
+
"rewards/chosen": -0.27153176069259644,
|
| 343 |
+
"rewards/margins": 0.054350595921278,
|
| 344 |
+
"rewards/rejected": -0.3258823752403259,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.19,
|
| 349 |
+
"learning_rate": 4.8721900291112415e-06,
|
| 350 |
+
"logits/chosen": -1.852705717086792,
|
| 351 |
+
"logits/rejected": -1.6845359802246094,
|
| 352 |
+
"logps/chosen": -642.0089111328125,
|
| 353 |
+
"logps/rejected": -671.2232055664062,
|
| 354 |
+
"loss": 0.6746,
|
| 355 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 356 |
+
"rewards/chosen": -0.4353899359703064,
|
| 357 |
+
"rewards/margins": 0.041978295892477036,
|
| 358 |
+
"rewards/rejected": -0.4773682653903961,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2,
|
| 363 |
+
"learning_rate": 4.849231551964771e-06,
|
| 364 |
+
"logits/chosen": -1.8547617197036743,
|
| 365 |
+
"logits/rejected": -1.7584753036499023,
|
| 366 |
+
"logps/chosen": -806.89208984375,
|
| 367 |
+
"logps/rejected": -791.40869140625,
|
| 368 |
+
"loss": 0.6877,
|
| 369 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 370 |
+
"rewards/chosen": -0.6369258165359497,
|
| 371 |
+
"rewards/margins": -0.01818418875336647,
|
| 372 |
+
"rewards/rejected": -0.6187416315078735,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21,
|
| 377 |
+
"learning_rate": 4.824441214720629e-06,
|
| 378 |
+
"logits/chosen": -1.795576810836792,
|
| 379 |
+
"logits/rejected": -1.5512839555740356,
|
| 380 |
+
"logps/chosen": -1120.3328857421875,
|
| 381 |
+
"logps/rejected": -1224.4669189453125,
|
| 382 |
+
"loss": 0.6485,
|
| 383 |
+
"rewards/accuracies": 0.574999988079071,
|
| 384 |
+
"rewards/chosen": -0.8469240069389343,
|
| 385 |
+
"rewards/margins": 0.12044433504343033,
|
| 386 |
+
"rewards/rejected": -0.9673683047294617,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 4.7978383481380865e-06,
|
| 392 |
+
"logits/chosen": -1.3707473278045654,
|
| 393 |
+
"logits/rejected": -1.1816232204437256,
|
| 394 |
+
"logps/chosen": -1378.314697265625,
|
| 395 |
+
"logps/rejected": -1494.1234130859375,
|
| 396 |
+
"loss": 0.6689,
|
| 397 |
+
"rewards/accuracies": 0.550000011920929,
|
| 398 |
+
"rewards/chosen": -1.1299686431884766,
|
| 399 |
+
"rewards/margins": 0.15295067429542542,
|
| 400 |
+
"rewards/rejected": -1.2829192876815796,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.22,
|
| 405 |
+
"learning_rate": 4.769443696332272e-06,
|
| 406 |
+
"logits/chosen": -1.5147939920425415,
|
| 407 |
+
"logits/rejected": -1.5684055089950562,
|
| 408 |
+
"logps/chosen": -509.37579345703125,
|
| 409 |
+
"logps/rejected": -719.7078247070312,
|
| 410 |
+
"loss": 0.6556,
|
| 411 |
+
"rewards/accuracies": 0.699999988079071,
|
| 412 |
+
"rewards/chosen": -0.3430081605911255,
|
| 413 |
+
"rewards/margins": 0.17507921159267426,
|
| 414 |
+
"rewards/rejected": -0.5180873274803162,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.23,
|
| 419 |
+
"learning_rate": 4.7392794005985324e-06,
|
| 420 |
+
"logits/chosen": -1.9780447483062744,
|
| 421 |
+
"logits/rejected": -1.7068169116973877,
|
| 422 |
+
"logps/chosen": -503.57684326171875,
|
| 423 |
+
"logps/rejected": -538.3973388671875,
|
| 424 |
+
"loss": 0.6529,
|
| 425 |
+
"rewards/accuracies": 0.574999988079071,
|
| 426 |
+
"rewards/chosen": -0.2268252670764923,
|
| 427 |
+
"rewards/margins": 0.09029386937618256,
|
| 428 |
+
"rewards/rejected": -0.31711912155151367,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24,
|
| 433 |
+
"learning_rate": 4.707368982147318e-06,
|
| 434 |
+
"logits/chosen": -1.725359320640564,
|
| 435 |
+
"logits/rejected": -1.6483027935028076,
|
| 436 |
+
"logps/chosen": -612.9721069335938,
|
| 437 |
+
"logps/rejected": -744.4105224609375,
|
| 438 |
+
"loss": 0.6381,
|
| 439 |
+
"rewards/accuracies": 0.699999988079071,
|
| 440 |
+
"rewards/chosen": -0.32202452421188354,
|
| 441 |
+
"rewards/margins": 0.21170559525489807,
|
| 442 |
+
"rewards/rejected": -0.533730149269104,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.25,
|
| 447 |
+
"learning_rate": 4.673737323763048e-06,
|
| 448 |
+
"logits/chosen": -1.478655457496643,
|
| 449 |
+
"logits/rejected": -1.5181188583374023,
|
| 450 |
+
"logps/chosen": -718.6035766601562,
|
| 451 |
+
"logps/rejected": -861.0172119140625,
|
| 452 |
+
"loss": 0.6412,
|
| 453 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 454 |
+
"rewards/chosen": -0.5259624719619751,
|
| 455 |
+
"rewards/margins": 0.10101442039012909,
|
| 456 |
+
"rewards/rejected": -0.6269768476486206,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.26,
|
| 461 |
+
"learning_rate": 4.638410650401267e-06,
|
| 462 |
+
"logits/chosen": -1.3320460319519043,
|
| 463 |
+
"logits/rejected": -1.0306655168533325,
|
| 464 |
+
"logps/chosen": -665.1239013671875,
|
| 465 |
+
"logps/rejected": -827.1819458007812,
|
| 466 |
+
"loss": 0.6595,
|
| 467 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 468 |
+
"rewards/chosen": -0.4110494554042816,
|
| 469 |
+
"rewards/margins": 0.24086549878120422,
|
| 470 |
+
"rewards/rejected": -0.6519149541854858,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.26,
|
| 475 |
+
"learning_rate": 4.601416508739211e-06,
|
| 476 |
+
"logits/chosen": -1.3477035760879517,
|
| 477 |
+
"logits/rejected": -1.3697832822799683,
|
| 478 |
+
"logps/chosen": -867.5467529296875,
|
| 479 |
+
"logps/rejected": -948.0695190429688,
|
| 480 |
+
"loss": 0.621,
|
| 481 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 482 |
+
"rewards/chosen": -0.5947723388671875,
|
| 483 |
+
"rewards/margins": 0.1193898469209671,
|
| 484 |
+
"rewards/rejected": -0.7141622304916382,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.27,
|
| 489 |
+
"learning_rate": 4.562783745695738e-06,
|
| 490 |
+
"logits/chosen": -1.3015021085739136,
|
| 491 |
+
"logits/rejected": -1.025702714920044,
|
| 492 |
+
"logps/chosen": -1093.9085693359375,
|
| 493 |
+
"logps/rejected": -1216.8255615234375,
|
| 494 |
+
"loss": 0.6451,
|
| 495 |
+
"rewards/accuracies": 0.550000011920929,
|
| 496 |
+
"rewards/chosen": -0.9000682830810547,
|
| 497 |
+
"rewards/margins": 0.1583687961101532,
|
| 498 |
+
"rewards/rejected": -1.0584371089935303,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.28,
|
| 503 |
+
"learning_rate": 4.522542485937369e-06,
|
| 504 |
+
"logits/chosen": -1.5709688663482666,
|
| 505 |
+
"logits/rejected": -1.283427119255066,
|
| 506 |
+
"logps/chosen": -1376.850341796875,
|
| 507 |
+
"logps/rejected": -1516.5667724609375,
|
| 508 |
+
"loss": 0.6395,
|
| 509 |
+
"rewards/accuracies": 0.5,
|
| 510 |
+
"rewards/chosen": -1.1210005283355713,
|
| 511 |
+
"rewards/margins": 0.1694861352443695,
|
| 512 |
+
"rewards/rejected": -1.2904865741729736,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.29,
|
| 517 |
+
"learning_rate": 4.4807241083879774e-06,
|
| 518 |
+
"logits/chosen": -1.6043704748153687,
|
| 519 |
+
"logits/rejected": -1.3832875490188599,
|
| 520 |
+
"logps/chosen": -1154.26220703125,
|
| 521 |
+
"logps/rejected": -1336.6424560546875,
|
| 522 |
+
"loss": 0.6427,
|
| 523 |
+
"rewards/accuracies": 0.675000011920929,
|
| 524 |
+
"rewards/chosen": -0.896734356880188,
|
| 525 |
+
"rewards/margins": 0.21884091198444366,
|
| 526 |
+
"rewards/rejected": -1.1155753135681152,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3,
|
| 531 |
+
"learning_rate": 4.437361221760449e-06,
|
| 532 |
+
"logits/chosen": -1.3710479736328125,
|
| 533 |
+
"logits/rejected": -1.3098589181900024,
|
| 534 |
+
"logps/chosen": -1009.2317504882812,
|
| 535 |
+
"logps/rejected": -1062.556640625,
|
| 536 |
+
"loss": 0.6655,
|
| 537 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 538 |
+
"rewards/chosen": -0.821437656879425,
|
| 539 |
+
"rewards/margins": 0.057194460183382034,
|
| 540 |
+
"rewards/rejected": -0.8786321878433228,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3,
|
| 545 |
+
"learning_rate": 4.3924876391293915e-06,
|
| 546 |
+
"logits/chosen": -0.8956707119941711,
|
| 547 |
+
"logits/rejected": -0.8277013897895813,
|
| 548 |
+
"logps/chosen": -1106.165283203125,
|
| 549 |
+
"logps/rejected": -1343.876708984375,
|
| 550 |
+
"loss": 0.6192,
|
| 551 |
+
"rewards/accuracies": 0.5,
|
| 552 |
+
"rewards/chosen": -0.9171901941299438,
|
| 553 |
+
"rewards/margins": 0.2286480963230133,
|
| 554 |
+
"rewards/rejected": -1.1458381414413452,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.31,
|
| 559 |
+
"learning_rate": 4.346138351564711e-06,
|
| 560 |
+
"logits/chosen": -0.6417841911315918,
|
| 561 |
+
"logits/rejected": -0.44266366958618164,
|
| 562 |
+
"logps/chosen": -836.3943481445312,
|
| 563 |
+
"logps/rejected": -1194.9322509765625,
|
| 564 |
+
"loss": 0.6001,
|
| 565 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 566 |
+
"rewards/chosen": -0.644795298576355,
|
| 567 |
+
"rewards/margins": 0.4003651738166809,
|
| 568 |
+
"rewards/rejected": -1.0451605319976807,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.32,
|
| 573 |
+
"learning_rate": 4.2983495008466285e-06,
|
| 574 |
+
"logits/chosen": -0.8112918734550476,
|
| 575 |
+
"logits/rejected": -0.7515584230422974,
|
| 576 |
+
"logps/chosen": -834.2249755859375,
|
| 577 |
+
"logps/rejected": -1054.40087890625,
|
| 578 |
+
"loss": 0.6716,
|
| 579 |
+
"rewards/accuracies": 0.550000011920929,
|
| 580 |
+
"rewards/chosen": -0.6205351948738098,
|
| 581 |
+
"rewards/margins": 0.20678479969501495,
|
| 582 |
+
"rewards/rejected": -0.8273199796676636,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.33,
|
| 587 |
+
"learning_rate": 4.249158351283414e-06,
|
| 588 |
+
"logits/chosen": -1.344972848892212,
|
| 589 |
+
"logits/rejected": -1.1616101264953613,
|
| 590 |
+
"logps/chosen": -608.2757568359375,
|
| 591 |
+
"logps/rejected": -736.3763427734375,
|
| 592 |
+
"loss": 0.6591,
|
| 593 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 594 |
+
"rewards/chosen": -0.3484669029712677,
|
| 595 |
+
"rewards/margins": 0.12206283956766129,
|
| 596 |
+
"rewards/rejected": -0.4705297350883484,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34,
|
| 601 |
+
"learning_rate": 4.198603260653792e-06,
|
| 602 |
+
"logits/chosen": -1.5138790607452393,
|
| 603 |
+
"logits/rejected": -1.3168789148330688,
|
| 604 |
+
"logps/chosen": -660.6969604492188,
|
| 605 |
+
"logps/rejected": -721.4447631835938,
|
| 606 |
+
"loss": 0.6268,
|
| 607 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 608 |
+
"rewards/chosen": -0.39333969354629517,
|
| 609 |
+
"rewards/margins": 0.0856555625796318,
|
| 610 |
+
"rewards/rejected": -0.4789952337741852,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.34,
|
| 615 |
+
"learning_rate": 4.146723650296701e-06,
|
| 616 |
+
"logits/chosen": -0.835279643535614,
|
| 617 |
+
"logits/rejected": -0.7461940050125122,
|
| 618 |
+
"logps/chosen": -1367.2841796875,
|
| 619 |
+
"logps/rejected": -1730.0777587890625,
|
| 620 |
+
"loss": 0.6363,
|
| 621 |
+
"rewards/accuracies": 0.75,
|
| 622 |
+
"rewards/chosen": -1.0674763917922974,
|
| 623 |
+
"rewards/margins": 0.35012298822402954,
|
| 624 |
+
"rewards/rejected": -1.4175993204116821,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.35,
|
| 629 |
+
"learning_rate": 4.093559974371725e-06,
|
| 630 |
+
"logits/chosen": 0.03398115560412407,
|
| 631 |
+
"logits/rejected": 0.2700420320034027,
|
| 632 |
+
"logps/chosen": -1314.656005859375,
|
| 633 |
+
"logps/rejected": -1531.143798828125,
|
| 634 |
+
"loss": 0.5735,
|
| 635 |
+
"rewards/accuracies": 0.550000011920929,
|
| 636 |
+
"rewards/chosen": -1.1307179927825928,
|
| 637 |
+
"rewards/margins": 0.2540770173072815,
|
| 638 |
+
"rewards/rejected": -1.3847953081130981,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.36,
|
| 643 |
+
"learning_rate": 4.039153688314146e-06,
|
| 644 |
+
"logits/chosen": -1.2114994525909424,
|
| 645 |
+
"logits/rejected": -0.9774553179740906,
|
| 646 |
+
"logps/chosen": -639.7308959960938,
|
| 647 |
+
"logps/rejected": -1037.600830078125,
|
| 648 |
+
"loss": 0.6237,
|
| 649 |
+
"rewards/accuracies": 0.699999988079071,
|
| 650 |
+
"rewards/chosen": -0.37664055824279785,
|
| 651 |
+
"rewards/margins": 0.4325637221336365,
|
| 652 |
+
"rewards/rejected": -0.8092042803764343,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.37,
|
| 657 |
+
"learning_rate": 3.983547216509254e-06,
|
| 658 |
+
"logits/chosen": -1.3054085969924927,
|
| 659 |
+
"logits/rejected": -1.221360683441162,
|
| 660 |
+
"logps/chosen": -556.9669799804688,
|
| 661 |
+
"logps/rejected": -634.5089111328125,
|
| 662 |
+
"loss": 0.6412,
|
| 663 |
+
"rewards/accuracies": 0.550000011920929,
|
| 664 |
+
"rewards/chosen": -0.32842499017715454,
|
| 665 |
+
"rewards/margins": 0.10787343978881836,
|
| 666 |
+
"rewards/rejected": -0.4362984299659729,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38,
|
| 671 |
+
"learning_rate": 3.92678391921108e-06,
|
| 672 |
+
"logits/chosen": -1.2041904926300049,
|
| 673 |
+
"logits/rejected": -1.1369637250900269,
|
| 674 |
+
"logps/chosen": -508.9098205566406,
|
| 675 |
+
"logps/rejected": -549.3627319335938,
|
| 676 |
+
"loss": 0.6646,
|
| 677 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 678 |
+
"rewards/chosen": -0.34369945526123047,
|
| 679 |
+
"rewards/margins": 0.057983528822660446,
|
| 680 |
+
"rewards/rejected": -0.4016830027103424,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.38,
|
| 685 |
+
"learning_rate": 3.868908058731376e-06,
|
| 686 |
+
"logits/chosen": -1.0662200450897217,
|
| 687 |
+
"logits/rejected": -0.960114598274231,
|
| 688 |
+
"logps/chosen": -994.2325439453125,
|
| 689 |
+
"logps/rejected": -1141.496337890625,
|
| 690 |
+
"loss": 0.6428,
|
| 691 |
+
"rewards/accuracies": 0.574999988079071,
|
| 692 |
+
"rewards/chosen": -0.8284689784049988,
|
| 693 |
+
"rewards/margins": 0.12653744220733643,
|
| 694 |
+
"rewards/rejected": -0.95500648021698,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.39,
|
| 699 |
+
"learning_rate": 3.8099647649251984e-06,
|
| 700 |
+
"logits/chosen": -1.110414743423462,
|
| 701 |
+
"logits/rejected": -0.8326665759086609,
|
| 702 |
+
"logps/chosen": -1098.611572265625,
|
| 703 |
+
"logps/rejected": -1337.651123046875,
|
| 704 |
+
"loss": 0.5994,
|
| 705 |
+
"rewards/accuracies": 0.699999988079071,
|
| 706 |
+
"rewards/chosen": -0.8522143363952637,
|
| 707 |
+
"rewards/margins": 0.2896762788295746,
|
| 708 |
+
"rewards/rejected": -1.141890525817871,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4,
|
| 713 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 714 |
+
"logits/chosen": -1.0082452297210693,
|
| 715 |
+
"logits/rejected": -0.8550570607185364,
|
| 716 |
+
"logps/chosen": -1118.4150390625,
|
| 717 |
+
"logps/rejected": -1403.4140625,
|
| 718 |
+
"loss": 0.6138,
|
| 719 |
+
"rewards/accuracies": 0.550000011920929,
|
| 720 |
+
"rewards/chosen": -0.9241348505020142,
|
| 721 |
+
"rewards/margins": 0.283856064081192,
|
| 722 |
+
"rewards/rejected": -1.2079908847808838,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.41,
|
| 727 |
+
"learning_rate": 3.689060522675689e-06,
|
| 728 |
+
"logits/chosen": -1.1805860996246338,
|
| 729 |
+
"logits/rejected": -1.0648720264434814,
|
| 730 |
+
"logps/chosen": -968.7009887695312,
|
| 731 |
+
"logps/rejected": -1127.3431396484375,
|
| 732 |
+
"loss": 0.5993,
|
| 733 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 734 |
+
"rewards/chosen": -0.7270181775093079,
|
| 735 |
+
"rewards/margins": 0.19340118765830994,
|
| 736 |
+
"rewards/rejected": -0.9204193949699402,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.42,
|
| 741 |
+
"learning_rate": 3.627193851723577e-06,
|
| 742 |
+
"logits/chosen": -1.0413739681243896,
|
| 743 |
+
"logits/rejected": -0.9251521825790405,
|
| 744 |
+
"logps/chosen": -962.42919921875,
|
| 745 |
+
"logps/rejected": -1037.397705078125,
|
| 746 |
+
"loss": 0.6336,
|
| 747 |
+
"rewards/accuracies": 0.550000011920929,
|
| 748 |
+
"rewards/chosen": -0.7336166501045227,
|
| 749 |
+
"rewards/margins": 0.10032469034194946,
|
| 750 |
+
"rewards/rejected": -0.8339413404464722,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.42,
|
| 755 |
+
"learning_rate": 3.564448228912682e-06,
|
| 756 |
+
"logits/chosen": -1.196645975112915,
|
| 757 |
+
"logits/rejected": -1.1510522365570068,
|
| 758 |
+
"logps/chosen": -906.9932861328125,
|
| 759 |
+
"logps/rejected": -1005.1427612304688,
|
| 760 |
+
"loss": 0.6233,
|
| 761 |
+
"rewards/accuracies": 0.574999988079071,
|
| 762 |
+
"rewards/chosen": -0.6604412794113159,
|
| 763 |
+
"rewards/margins": 0.08722977340221405,
|
| 764 |
+
"rewards/rejected": -0.7476710081100464,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.43,
|
| 769 |
+
"learning_rate": 3.5008725813922383e-06,
|
| 770 |
+
"logits/chosen": -1.0590436458587646,
|
| 771 |
+
"logits/rejected": -0.7820866703987122,
|
| 772 |
+
"logps/chosen": -1043.649169921875,
|
| 773 |
+
"logps/rejected": -1336.0374755859375,
|
| 774 |
+
"loss": 0.5875,
|
| 775 |
+
"rewards/accuracies": 0.550000011920929,
|
| 776 |
+
"rewards/chosen": -0.7807156443595886,
|
| 777 |
+
"rewards/margins": 0.3648682236671448,
|
| 778 |
+
"rewards/rejected": -1.1455838680267334,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.44,
|
| 783 |
+
"learning_rate": 3.436516483539781e-06,
|
| 784 |
+
"logits/chosen": -0.8871183395385742,
|
| 785 |
+
"logits/rejected": -0.6445604562759399,
|
| 786 |
+
"logps/chosen": -974.1388549804688,
|
| 787 |
+
"logps/rejected": -1435.357666015625,
|
| 788 |
+
"loss": 0.5548,
|
| 789 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 790 |
+
"rewards/chosen": -0.7723373770713806,
|
| 791 |
+
"rewards/margins": 0.4823000431060791,
|
| 792 |
+
"rewards/rejected": -1.2546374797821045,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.45,
|
| 797 |
+
"learning_rate": 3.3714301183045382e-06,
|
| 798 |
+
"logits/chosen": -1.1284804344177246,
|
| 799 |
+
"logits/rejected": -1.0746089220046997,
|
| 800 |
+
"logps/chosen": -1098.0726318359375,
|
| 801 |
+
"logps/rejected": -1571.875732421875,
|
| 802 |
+
"loss": 0.5809,
|
| 803 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 804 |
+
"rewards/chosen": -0.8001961708068848,
|
| 805 |
+
"rewards/margins": 0.49779874086380005,
|
| 806 |
+
"rewards/rejected": -1.29799485206604,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.46,
|
| 811 |
+
"learning_rate": 3.3056642380762783e-06,
|
| 812 |
+
"logits/chosen": -1.0926157236099243,
|
| 813 |
+
"logits/rejected": -0.9620027542114258,
|
| 814 |
+
"logps/chosen": -909.43896484375,
|
| 815 |
+
"logps/rejected": -1261.0572509765625,
|
| 816 |
+
"loss": 0.5876,
|
| 817 |
+
"rewards/accuracies": 0.574999988079071,
|
| 818 |
+
"rewards/chosen": -0.6548485159873962,
|
| 819 |
+
"rewards/margins": 0.3792751133441925,
|
| 820 |
+
"rewards/rejected": -1.0341236591339111,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.46,
|
| 825 |
+
"learning_rate": 3.2392701251101172e-06,
|
| 826 |
+
"logits/chosen": -1.1053316593170166,
|
| 827 |
+
"logits/rejected": -0.9159544706344604,
|
| 828 |
+
"logps/chosen": -904.6321411132812,
|
| 829 |
+
"logps/rejected": -1194.8170166015625,
|
| 830 |
+
"loss": 0.5921,
|
| 831 |
+
"rewards/accuracies": 0.550000011920929,
|
| 832 |
+
"rewards/chosen": -0.6870709657669067,
|
| 833 |
+
"rewards/margins": 0.3379691243171692,
|
| 834 |
+
"rewards/rejected": -1.0250400304794312,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.47,
|
| 839 |
+
"learning_rate": 3.1722995515381644e-06,
|
| 840 |
+
"logits/chosen": -0.5783677101135254,
|
| 841 |
+
"logits/rejected": -0.381605327129364,
|
| 842 |
+
"logps/chosen": -1375.947265625,
|
| 843 |
+
"logps/rejected": -1693.8013916015625,
|
| 844 |
+
"loss": 0.5704,
|
| 845 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 846 |
+
"rewards/chosen": -1.1249635219573975,
|
| 847 |
+
"rewards/margins": 0.3614503741264343,
|
| 848 |
+
"rewards/rejected": -1.486413836479187,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.48,
|
| 853 |
+
"learning_rate": 3.1048047389991693e-06,
|
| 854 |
+
"logits/chosen": -0.6121073365211487,
|
| 855 |
+
"logits/rejected": -0.4031047224998474,
|
| 856 |
+
"logps/chosen": -1350.5516357421875,
|
| 857 |
+
"logps/rejected": -1793.6240234375,
|
| 858 |
+
"loss": 0.6244,
|
| 859 |
+
"rewards/accuracies": 0.550000011920929,
|
| 860 |
+
"rewards/chosen": -1.1342486143112183,
|
| 861 |
+
"rewards/margins": 0.43501371145248413,
|
| 862 |
+
"rewards/rejected": -1.5692622661590576,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.49,
|
| 867 |
+
"learning_rate": 3.0368383179176584e-06,
|
| 868 |
+
"logits/chosen": -0.8454495668411255,
|
| 869 |
+
"logits/rejected": -0.6569667458534241,
|
| 870 |
+
"logps/chosen": -890.9841918945312,
|
| 871 |
+
"logps/rejected": -1315.620849609375,
|
| 872 |
+
"loss": 0.5818,
|
| 873 |
+
"rewards/accuracies": 0.699999988079071,
|
| 874 |
+
"rewards/chosen": -0.6493796110153198,
|
| 875 |
+
"rewards/margins": 0.46156787872314453,
|
| 876 |
+
"rewards/rejected": -1.1109474897384644,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5,
|
| 881 |
+
"learning_rate": 2.9684532864643123e-06,
|
| 882 |
+
"logits/chosen": -0.8009635210037231,
|
| 883 |
+
"logits/rejected": -0.6670125126838684,
|
| 884 |
+
"logps/chosen": -1004.8250122070312,
|
| 885 |
+
"logps/rejected": -1155.979736328125,
|
| 886 |
+
"loss": 0.6091,
|
| 887 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 888 |
+
"rewards/chosen": -0.7524474263191223,
|
| 889 |
+
"rewards/margins": 0.18189628422260284,
|
| 890 |
+
"rewards/rejected": -0.934343695640564,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5,
|
| 895 |
+
"learning_rate": 2.8997029692295875e-06,
|
| 896 |
+
"logits/chosen": -0.9459114074707031,
|
| 897 |
+
"logits/rejected": -0.6500396728515625,
|
| 898 |
+
"logps/chosen": -1066.767333984375,
|
| 899 |
+
"logps/rejected": -1516.01953125,
|
| 900 |
+
"loss": 0.5912,
|
| 901 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 902 |
+
"rewards/chosen": -0.7964303493499756,
|
| 903 |
+
"rewards/margins": 0.4783499240875244,
|
| 904 |
+
"rewards/rejected": -1.274780511856079,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.51,
|
| 909 |
+
"learning_rate": 2.8306409756428067e-06,
|
| 910 |
+
"logits/chosen": -0.7831882238388062,
|
| 911 |
+
"logits/rejected": -0.3093162477016449,
|
| 912 |
+
"logps/chosen": -1089.9415283203125,
|
| 913 |
+
"logps/rejected": -1740.2158203125,
|
| 914 |
+
"loss": 0.5638,
|
| 915 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 916 |
+
"rewards/chosen": -0.7907674908638,
|
| 917 |
+
"rewards/margins": 0.7186497449874878,
|
| 918 |
+
"rewards/rejected": -1.509417176246643,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.52,
|
| 923 |
+
"learning_rate": 2.761321158169134e-06,
|
| 924 |
+
"logits/chosen": -0.5406681299209595,
|
| 925 |
+
"logits/rejected": -0.27648812532424927,
|
| 926 |
+
"logps/chosen": -1686.183349609375,
|
| 927 |
+
"logps/rejected": -1993.3765869140625,
|
| 928 |
+
"loss": 0.5719,
|
| 929 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 930 |
+
"rewards/chosen": -1.4113540649414062,
|
| 931 |
+
"rewards/margins": 0.37404680252075195,
|
| 932 |
+
"rewards/rejected": -1.7854007482528687,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.53,
|
| 937 |
+
"learning_rate": 2.6917975703170466e-06,
|
| 938 |
+
"logits/chosen": -0.5704952478408813,
|
| 939 |
+
"logits/rejected": -0.023378795012831688,
|
| 940 |
+
"logps/chosen": -1294.9827880859375,
|
| 941 |
+
"logps/rejected": -2076.658447265625,
|
| 942 |
+
"loss": 0.5743,
|
| 943 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 944 |
+
"rewards/chosen": -1.0449953079223633,
|
| 945 |
+
"rewards/margins": 0.7736978530883789,
|
| 946 |
+
"rewards/rejected": -1.8186931610107422,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.54,
|
| 951 |
+
"learning_rate": 2.6221244244890336e-06,
|
| 952 |
+
"logits/chosen": -0.5983051061630249,
|
| 953 |
+
"logits/rejected": -0.35873037576675415,
|
| 954 |
+
"logps/chosen": -1279.24072265625,
|
| 955 |
+
"logps/rejected": -1712.7236328125,
|
| 956 |
+
"loss": 0.5588,
|
| 957 |
+
"rewards/accuracies": 0.699999988079071,
|
| 958 |
+
"rewards/chosen": -1.0362498760223389,
|
| 959 |
+
"rewards/margins": 0.4681357741355896,
|
| 960 |
+
"rewards/rejected": -1.5043857097625732,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.54,
|
| 965 |
+
"learning_rate": 2.5523560497083927e-06,
|
| 966 |
+
"logits/chosen": -0.7439953088760376,
|
| 967 |
+
"logits/rejected": -0.5419555306434631,
|
| 968 |
+
"logps/chosen": -986.34765625,
|
| 969 |
+
"logps/rejected": -1177.267333984375,
|
| 970 |
+
"loss": 0.6399,
|
| 971 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 972 |
+
"rewards/chosen": -0.7895917296409607,
|
| 973 |
+
"rewards/margins": 0.20669332146644592,
|
| 974 |
+
"rewards/rejected": -0.996285080909729,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.55,
|
| 979 |
+
"learning_rate": 2.482546849255096e-06,
|
| 980 |
+
"logits/chosen": -0.9641045331954956,
|
| 981 |
+
"logits/rejected": -0.6751854419708252,
|
| 982 |
+
"logps/chosen": -834.6181640625,
|
| 983 |
+
"logps/rejected": -1149.5087890625,
|
| 984 |
+
"loss": 0.5592,
|
| 985 |
+
"rewards/accuracies": 0.625,
|
| 986 |
+
"rewards/chosen": -0.6201135516166687,
|
| 987 |
+
"rewards/margins": 0.3461000919342041,
|
| 988 |
+
"rewards/rejected": -0.966213583946228,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.56,
|
| 993 |
+
"learning_rate": 2.4127512582437486e-06,
|
| 994 |
+
"logits/chosen": -0.9225761294364929,
|
| 995 |
+
"logits/rejected": -0.772851824760437,
|
| 996 |
+
"logps/chosen": -925.7664184570312,
|
| 997 |
+
"logps/rejected": -1246.7874755859375,
|
| 998 |
+
"loss": 0.5751,
|
| 999 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1000 |
+
"rewards/chosen": -0.6425189971923828,
|
| 1001 |
+
"rewards/margins": 0.3423493504524231,
|
| 1002 |
+
"rewards/rejected": -0.9848684072494507,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.57,
|
| 1007 |
+
"learning_rate": 2.3430237011767166e-06,
|
| 1008 |
+
"logits/chosen": -0.45442017912864685,
|
| 1009 |
+
"logits/rejected": -0.23890094459056854,
|
| 1010 |
+
"logps/chosen": -1335.2960205078125,
|
| 1011 |
+
"logps/rejected": -1824.8148193359375,
|
| 1012 |
+
"loss": 0.5562,
|
| 1013 |
+
"rewards/accuracies": 0.625,
|
| 1014 |
+
"rewards/chosen": -1.1126158237457275,
|
| 1015 |
+
"rewards/margins": 0.5235506296157837,
|
| 1016 |
+
"rewards/rejected": -1.6361665725708008,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.58,
|
| 1021 |
+
"learning_rate": 2.2734185495055503e-06,
|
| 1022 |
+
"logits/chosen": 0.43471193313598633,
|
| 1023 |
+
"logits/rejected": 0.7335575222969055,
|
| 1024 |
+
"logps/chosen": -1717.737060546875,
|
| 1025 |
+
"logps/rejected": -2255.147705078125,
|
| 1026 |
+
"loss": 0.5663,
|
| 1027 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1028 |
+
"rewards/chosen": -1.4929530620574951,
|
| 1029 |
+
"rewards/margins": 0.5923892259597778,
|
| 1030 |
+
"rewards/rejected": -2.0853421688079834,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.58,
|
| 1035 |
+
"learning_rate": 2.2039900792337477e-06,
|
| 1036 |
+
"logits/chosen": -0.5602989792823792,
|
| 1037 |
+
"logits/rejected": -0.28851318359375,
|
| 1038 |
+
"logps/chosen": -1234.8255615234375,
|
| 1039 |
+
"logps/rejected": -1552.613037109375,
|
| 1040 |
+
"loss": 0.5947,
|
| 1041 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1042 |
+
"rewards/chosen": -0.978289783000946,
|
| 1043 |
+
"rewards/margins": 0.3596613109111786,
|
| 1044 |
+
"rewards/rejected": -1.3379510641098022,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.59,
|
| 1049 |
+
"learning_rate": 2.134792428593971e-06,
|
| 1050 |
+
"logits/chosen": -0.9215381741523743,
|
| 1051 |
+
"logits/rejected": -0.6034310460090637,
|
| 1052 |
+
"logps/chosen": -918.3829345703125,
|
| 1053 |
+
"logps/rejected": -1260.914794921875,
|
| 1054 |
+
"loss": 0.5731,
|
| 1055 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1056 |
+
"rewards/chosen": -0.6723597645759583,
|
| 1057 |
+
"rewards/margins": 0.3877628743648529,
|
| 1058 |
+
"rewards/rejected": -1.0601227283477783,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6,
|
| 1063 |
+
"learning_rate": 2.0658795558326745e-06,
|
| 1064 |
+
"logits/chosen": -0.75888991355896,
|
| 1065 |
+
"logits/rejected": -0.8145910501480103,
|
| 1066 |
+
"logps/chosen": -942.7371215820312,
|
| 1067 |
+
"logps/rejected": -1151.885986328125,
|
| 1068 |
+
"loss": 0.6138,
|
| 1069 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1070 |
+
"rewards/chosen": -0.7426967620849609,
|
| 1071 |
+
"rewards/margins": 0.20792725682258606,
|
| 1072 |
+
"rewards/rejected": -0.9506238698959351,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.61,
|
| 1077 |
+
"learning_rate": 1.997305197135089e-06,
|
| 1078 |
+
"logits/chosen": -0.5050958395004272,
|
| 1079 |
+
"logits/rejected": -0.3710903823375702,
|
| 1080 |
+
"logps/chosen": -1115.988525390625,
|
| 1081 |
+
"logps/rejected": -1241.006103515625,
|
| 1082 |
+
"loss": 0.6371,
|
| 1083 |
+
"rewards/accuracies": 0.5,
|
| 1084 |
+
"rewards/chosen": -0.9049081802368164,
|
| 1085 |
+
"rewards/margins": 0.14062346518039703,
|
| 1086 |
+
"rewards/rejected": -1.0455316305160522,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.62,
|
| 1091 |
+
"learning_rate": 1.9291228247233607e-06,
|
| 1092 |
+
"logits/chosen": -1.0052917003631592,
|
| 1093 |
+
"logits/rejected": -0.7385827302932739,
|
| 1094 |
+
"logps/chosen": -1185.632568359375,
|
| 1095 |
+
"logps/rejected": -1218.97412109375,
|
| 1096 |
+
"loss": 0.602,
|
| 1097 |
+
"rewards/accuracies": 0.625,
|
| 1098 |
+
"rewards/chosen": -0.8952628970146179,
|
| 1099 |
+
"rewards/margins": 0.1188296228647232,
|
| 1100 |
+
"rewards/rejected": -1.0140926837921143,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.62,
|
| 1105 |
+
"learning_rate": 1.8613856051605242e-06,
|
| 1106 |
+
"logits/chosen": -0.7601789236068726,
|
| 1107 |
+
"logits/rejected": -0.4364476203918457,
|
| 1108 |
+
"logps/chosen": -1060.472412109375,
|
| 1109 |
+
"logps/rejected": -1608.5179443359375,
|
| 1110 |
+
"loss": 0.5912,
|
| 1111 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1112 |
+
"rewards/chosen": -0.8007382154464722,
|
| 1113 |
+
"rewards/margins": 0.5700600743293762,
|
| 1114 |
+
"rewards/rejected": -1.3707983493804932,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.63,
|
| 1119 |
+
"learning_rate": 1.7941463578928088e-06,
|
| 1120 |
+
"logits/chosen": -0.8455929756164551,
|
| 1121 |
+
"logits/rejected": -0.7644866704940796,
|
| 1122 |
+
"logps/chosen": -1184.275634765625,
|
| 1123 |
+
"logps/rejected": -1357.3797607421875,
|
| 1124 |
+
"loss": 0.6282,
|
| 1125 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1126 |
+
"rewards/chosen": -0.9668749570846558,
|
| 1127 |
+
"rewards/margins": 0.18699315190315247,
|
| 1128 |
+
"rewards/rejected": -1.1538680791854858,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.64,
|
| 1133 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 1134 |
+
"logits/chosen": -0.6272526979446411,
|
| 1135 |
+
"logits/rejected": -0.6869767904281616,
|
| 1136 |
+
"logps/chosen": -1237.728759765625,
|
| 1137 |
+
"logps/rejected": -1527.4461669921875,
|
| 1138 |
+
"loss": 0.5405,
|
| 1139 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1140 |
+
"rewards/chosen": -0.9917057156562805,
|
| 1141 |
+
"rewards/margins": 0.2875545024871826,
|
| 1142 |
+
"rewards/rejected": -1.2792601585388184,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.65,
|
| 1147 |
+
"learning_rate": 1.661371075624363e-06,
|
| 1148 |
+
"logits/chosen": -0.38267868757247925,
|
| 1149 |
+
"logits/rejected": -0.11700303852558136,
|
| 1150 |
+
"logps/chosen": -1500.436767578125,
|
| 1151 |
+
"logps/rejected": -1794.047119140625,
|
| 1152 |
+
"loss": 0.5961,
|
| 1153 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1154 |
+
"rewards/chosen": -1.308133840560913,
|
| 1155 |
+
"rewards/margins": 0.3339870274066925,
|
| 1156 |
+
"rewards/rejected": -1.6421207189559937,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.66,
|
| 1161 |
+
"learning_rate": 1.5959385747947697e-06,
|
| 1162 |
+
"logits/chosen": -0.5077565908432007,
|
| 1163 |
+
"logits/rejected": -0.36555030941963196,
|
| 1164 |
+
"logps/chosen": -1464.396240234375,
|
| 1165 |
+
"logps/rejected": -2057.291259765625,
|
| 1166 |
+
"loss": 0.5732,
|
| 1167 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1168 |
+
"rewards/chosen": -1.2214739322662354,
|
| 1169 |
+
"rewards/margins": 0.5794647336006165,
|
| 1170 |
+
"rewards/rejected": -1.800938606262207,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.66,
|
| 1175 |
+
"learning_rate": 1.5312110338697427e-06,
|
| 1176 |
+
"logits/chosen": -0.8566253781318665,
|
| 1177 |
+
"logits/rejected": -0.703198254108429,
|
| 1178 |
+
"logps/chosen": -1135.494873046875,
|
| 1179 |
+
"logps/rejected": -1410.838134765625,
|
| 1180 |
+
"loss": 0.5885,
|
| 1181 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1182 |
+
"rewards/chosen": -0.9456474184989929,
|
| 1183 |
+
"rewards/margins": 0.2893359661102295,
|
| 1184 |
+
"rewards/rejected": -1.2349833250045776,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.67,
|
| 1189 |
+
"learning_rate": 1.467238925438646e-06,
|
| 1190 |
+
"logits/chosen": -0.9742065668106079,
|
| 1191 |
+
"logits/rejected": -0.7325109839439392,
|
| 1192 |
+
"logps/chosen": -1128.455078125,
|
| 1193 |
+
"logps/rejected": -1652.849609375,
|
| 1194 |
+
"loss": 0.5826,
|
| 1195 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1196 |
+
"rewards/chosen": -0.8605993986129761,
|
| 1197 |
+
"rewards/margins": 0.5381206274032593,
|
| 1198 |
+
"rewards/rejected": -1.3987200260162354,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.68,
|
| 1203 |
+
"learning_rate": 1.4040721330273063e-06,
|
| 1204 |
+
"logits/chosen": -0.6383851766586304,
|
| 1205 |
+
"logits/rejected": -0.30349114537239075,
|
| 1206 |
+
"logps/chosen": -1556.1243896484375,
|
| 1207 |
+
"logps/rejected": -2115.495361328125,
|
| 1208 |
+
"loss": 0.5752,
|
| 1209 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1210 |
+
"rewards/chosen": -1.2599270343780518,
|
| 1211 |
+
"rewards/margins": 0.6025987863540649,
|
| 1212 |
+
"rewards/rejected": -1.8625257015228271,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.69,
|
| 1217 |
+
"learning_rate": 1.3417599122003464e-06,
|
| 1218 |
+
"logits/chosen": -0.945850670337677,
|
| 1219 |
+
"logits/rejected": -0.4593322277069092,
|
| 1220 |
+
"logps/chosen": -1373.3946533203125,
|
| 1221 |
+
"logps/rejected": -2057.10498046875,
|
| 1222 |
+
"loss": 0.5475,
|
| 1223 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1224 |
+
"rewards/chosen": -1.1107696294784546,
|
| 1225 |
+
"rewards/margins": 0.7481247782707214,
|
| 1226 |
+
"rewards/rejected": -1.8588945865631104,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7,
|
| 1231 |
+
"learning_rate": 1.280350852153168e-06,
|
| 1232 |
+
"logits/chosen": -0.587804913520813,
|
| 1233 |
+
"logits/rejected": -0.4838123917579651,
|
| 1234 |
+
"logps/chosen": -1164.4200439453125,
|
| 1235 |
+
"logps/rejected": -1821.4710693359375,
|
| 1236 |
+
"loss": 0.522,
|
| 1237 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1238 |
+
"rewards/chosen": -0.9738459587097168,
|
| 1239 |
+
"rewards/margins": 0.613839328289032,
|
| 1240 |
+
"rewards/rejected": -1.5876853466033936,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7,
|
| 1245 |
+
"learning_rate": 1.2198928378235717e-06,
|
| 1246 |
+
"logits/chosen": -0.6612527966499329,
|
| 1247 |
+
"logits/rejected": -0.5115641355514526,
|
| 1248 |
+
"logps/chosen": -1650.718505859375,
|
| 1249 |
+
"logps/rejected": -2091.0732421875,
|
| 1250 |
+
"loss": 0.6349,
|
| 1251 |
+
"rewards/accuracies": 0.625,
|
| 1252 |
+
"rewards/chosen": -1.4022929668426514,
|
| 1253 |
+
"rewards/margins": 0.423071950674057,
|
| 1254 |
+
"rewards/rejected": -1.8253650665283203,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.71,
|
| 1259 |
+
"learning_rate": 1.160433012552508e-06,
|
| 1260 |
+
"logits/chosen": -1.0209529399871826,
|
| 1261 |
+
"logits/rejected": -0.7942039966583252,
|
| 1262 |
+
"logps/chosen": -967.7880859375,
|
| 1263 |
+
"logps/rejected": -1502.6470947265625,
|
| 1264 |
+
"loss": 0.5917,
|
| 1265 |
+
"rewards/accuracies": 0.625,
|
| 1266 |
+
"rewards/chosen": -0.7300990223884583,
|
| 1267 |
+
"rewards/margins": 0.5862218141555786,
|
| 1268 |
+
"rewards/rejected": -1.316320776939392,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.72,
|
| 1273 |
+
"learning_rate": 1.1020177413231334e-06,
|
| 1274 |
+
"logits/chosen": -0.9528091549873352,
|
| 1275 |
+
"logits/rejected": -0.6705907583236694,
|
| 1276 |
+
"logps/chosen": -1106.0501708984375,
|
| 1277 |
+
"logps/rejected": -1562.62939453125,
|
| 1278 |
+
"loss": 0.5511,
|
| 1279 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1280 |
+
"rewards/chosen": -0.8729621767997742,
|
| 1281 |
+
"rewards/margins": 0.4861548840999603,
|
| 1282 |
+
"rewards/rejected": -1.359117031097412,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.73,
|
| 1287 |
+
"learning_rate": 1.0446925746067768e-06,
|
| 1288 |
+
"logits/chosen": -0.6244916915893555,
|
| 1289 |
+
"logits/rejected": -0.30852293968200684,
|
| 1290 |
+
"logps/chosen": -1030.0357666015625,
|
| 1291 |
+
"logps/rejected": -1489.8277587890625,
|
| 1292 |
+
"loss": 0.5651,
|
| 1293 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1294 |
+
"rewards/chosen": -0.8064696192741394,
|
| 1295 |
+
"rewards/margins": 0.5191851258277893,
|
| 1296 |
+
"rewards/rejected": -1.3256547451019287,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.74,
|
| 1301 |
+
"learning_rate": 9.88502212844063e-07,
|
| 1302 |
+
"logits/chosen": -0.8371726870536804,
|
| 1303 |
+
"logits/rejected": -0.5608356595039368,
|
| 1304 |
+
"logps/chosen": -1306.61181640625,
|
| 1305 |
+
"logps/rejected": -1983.6080322265625,
|
| 1306 |
+
"loss": 0.6032,
|
| 1307 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1308 |
+
"rewards/chosen": -1.0330902338027954,
|
| 1309 |
+
"rewards/margins": 0.6798037886619568,
|
| 1310 |
+
"rewards/rejected": -1.712894082069397,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.74,
|
| 1315 |
+
"learning_rate": 9.334904715888496e-07,
|
| 1316 |
+
"logits/chosen": -0.6907060146331787,
|
| 1317 |
+
"logits/rejected": -0.3094312250614166,
|
| 1318 |
+
"logps/chosen": -1471.054443359375,
|
| 1319 |
+
"logps/rejected": -2111.68701171875,
|
| 1320 |
+
"loss": 0.6023,
|
| 1321 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1322 |
+
"rewards/chosen": -1.1933256387710571,
|
| 1323 |
+
"rewards/margins": 0.6424576044082642,
|
| 1324 |
+
"rewards/rejected": -1.8357832431793213,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.75,
|
| 1329 |
+
"learning_rate": 8.797002473421729e-07,
|
| 1330 |
+
"logits/chosen": -0.6967111825942993,
|
| 1331 |
+
"logits/rejected": -0.7114680409431458,
|
| 1332 |
+
"logps/chosen": -1068.6622314453125,
|
| 1333 |
+
"logps/rejected": -1549.4698486328125,
|
| 1334 |
+
"loss": 0.5634,
|
| 1335 |
+
"rewards/accuracies": 0.625,
|
| 1336 |
+
"rewards/chosen": -0.8170648813247681,
|
| 1337 |
+
"rewards/margins": 0.4820033013820648,
|
| 1338 |
+
"rewards/rejected": -1.2990682125091553,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.76,
|
| 1343 |
+
"learning_rate": 8.271734841028553e-07,
|
| 1344 |
+
"logits/chosen": -0.6052312850952148,
|
| 1345 |
+
"logits/rejected": -0.38424620032310486,
|
| 1346 |
+
"logps/chosen": -1452.5819091796875,
|
| 1347 |
+
"logps/rejected": -1862.074462890625,
|
| 1348 |
+
"loss": 0.5435,
|
| 1349 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1350 |
+
"rewards/chosen": -1.1982152462005615,
|
| 1351 |
+
"rewards/margins": 0.44351309537887573,
|
| 1352 |
+
"rewards/rejected": -1.641728162765503,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.77,
|
| 1357 |
+
"learning_rate": 7.759511406608255e-07,
|
| 1358 |
+
"logits/chosen": -0.8322499990463257,
|
| 1359 |
+
"logits/rejected": -0.7050498723983765,
|
| 1360 |
+
"logps/chosen": -1228.91650390625,
|
| 1361 |
+
"logps/rejected": -1504.3065185546875,
|
| 1362 |
+
"loss": 0.5831,
|
| 1363 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1364 |
+
"rewards/chosen": -0.9939497709274292,
|
| 1365 |
+
"rewards/margins": 0.2843117415904999,
|
| 1366 |
+
"rewards/rejected": -1.2782615423202515,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.78,
|
| 1371 |
+
"learning_rate": 7.260731586586983e-07,
|
| 1372 |
+
"logits/chosen": -0.6231692433357239,
|
| 1373 |
+
"logits/rejected": -0.5812069773674011,
|
| 1374 |
+
"logps/chosen": -907.5172729492188,
|
| 1375 |
+
"logps/rejected": -1289.426513671875,
|
| 1376 |
+
"loss": 0.5797,
|
| 1377 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1378 |
+
"rewards/chosen": -0.7803674936294556,
|
| 1379 |
+
"rewards/margins": 0.38126420974731445,
|
| 1380 |
+
"rewards/rejected": -1.1616315841674805,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.78,
|
| 1385 |
+
"learning_rate": 6.775784314464717e-07,
|
| 1386 |
+
"logits/chosen": -0.9975751638412476,
|
| 1387 |
+
"logits/rejected": -0.5946329236030579,
|
| 1388 |
+
"logps/chosen": -1023.9324340820312,
|
| 1389 |
+
"logps/rejected": -1547.0753173828125,
|
| 1390 |
+
"loss": 0.5251,
|
| 1391 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1392 |
+
"rewards/chosen": -0.7850741147994995,
|
| 1393 |
+
"rewards/margins": 0.5707739591598511,
|
| 1394 |
+
"rewards/rejected": -1.355847954750061,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.79,
|
| 1399 |
+
"learning_rate": 6.305047737536707e-07,
|
| 1400 |
+
"logits/chosen": -0.577874481678009,
|
| 1401 |
+
"logits/rejected": -0.44077569246292114,
|
| 1402 |
+
"logps/chosen": -1363.0498046875,
|
| 1403 |
+
"logps/rejected": -2003.899658203125,
|
| 1404 |
+
"loss": 0.5644,
|
| 1405 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1406 |
+
"rewards/chosen": -1.1625807285308838,
|
| 1407 |
+
"rewards/margins": 0.6248854398727417,
|
| 1408 |
+
"rewards/rejected": -1.787466287612915,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8,
|
| 1413 |
+
"learning_rate": 5.848888922025553e-07,
|
| 1414 |
+
"logits/chosen": -0.8105753064155579,
|
| 1415 |
+
"logits/rejected": -0.919611930847168,
|
| 1416 |
+
"logps/chosen": -1336.093994140625,
|
| 1417 |
+
"logps/rejected": -1582.025146484375,
|
| 1418 |
+
"loss": 0.5633,
|
| 1419 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1420 |
+
"rewards/chosen": -1.0712718963623047,
|
| 1421 |
+
"rewards/margins": 0.27774709463119507,
|
| 1422 |
+
"rewards/rejected": -1.3490190505981445,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.81,
|
| 1427 |
+
"learning_rate": 5.407663566854008e-07,
|
| 1428 |
+
"logits/chosen": -1.1405055522918701,
|
| 1429 |
+
"logits/rejected": -0.8410784006118774,
|
| 1430 |
+
"logps/chosen": -1108.752197265625,
|
| 1431 |
+
"logps/rejected": -1712.4912109375,
|
| 1432 |
+
"loss": 0.5699,
|
| 1433 |
+
"rewards/accuracies": 0.625,
|
| 1434 |
+
"rewards/chosen": -0.8489648103713989,
|
| 1435 |
+
"rewards/margins": 0.6527272462844849,
|
| 1436 |
+
"rewards/rejected": -1.5016920566558838,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.82,
|
| 1441 |
+
"learning_rate": 4.981715726281666e-07,
|
| 1442 |
+
"logits/chosen": -0.8187993764877319,
|
| 1443 |
+
"logits/rejected": -0.6521504521369934,
|
| 1444 |
+
"logps/chosen": -1444.044189453125,
|
| 1445 |
+
"logps/rejected": -2250.241943359375,
|
| 1446 |
+
"loss": 0.5623,
|
| 1447 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1448 |
+
"rewards/chosen": -1.1614019870758057,
|
| 1449 |
+
"rewards/margins": 0.798125147819519,
|
| 1450 |
+
"rewards/rejected": -1.9595272541046143,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.82,
|
| 1455 |
+
"learning_rate": 4.5713775416217884e-07,
|
| 1456 |
+
"logits/chosen": -0.44266295433044434,
|
| 1457 |
+
"logits/rejected": -0.33986443281173706,
|
| 1458 |
+
"logps/chosen": -1182.5404052734375,
|
| 1459 |
+
"logps/rejected": -1922.5198974609375,
|
| 1460 |
+
"loss": 0.5714,
|
| 1461 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1462 |
+
"rewards/chosen": -0.9850846529006958,
|
| 1463 |
+
"rewards/margins": 0.7335339188575745,
|
| 1464 |
+
"rewards/rejected": -1.718618631362915,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.83,
|
| 1469 |
+
"learning_rate": 4.1769689822475147e-07,
|
| 1470 |
+
"logits/chosen": -0.5250821709632874,
|
| 1471 |
+
"logits/rejected": -0.5564389228820801,
|
| 1472 |
+
"logps/chosen": -1238.247802734375,
|
| 1473 |
+
"logps/rejected": -1787.1693115234375,
|
| 1474 |
+
"loss": 0.5653,
|
| 1475 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1476 |
+
"rewards/chosen": -1.0797133445739746,
|
| 1477 |
+
"rewards/margins": 0.4955691695213318,
|
| 1478 |
+
"rewards/rejected": -1.5752824544906616,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.84,
|
| 1483 |
+
"learning_rate": 3.798797596089351e-07,
|
| 1484 |
+
"logits/chosen": -0.7688647508621216,
|
| 1485 |
+
"logits/rejected": -0.4375014901161194,
|
| 1486 |
+
"logps/chosen": -1243.4844970703125,
|
| 1487 |
+
"logps/rejected": -1739.737548828125,
|
| 1488 |
+
"loss": 0.5426,
|
| 1489 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1490 |
+
"rewards/chosen": -1.010633111000061,
|
| 1491 |
+
"rewards/margins": 0.519820511341095,
|
| 1492 |
+
"rewards/rejected": -1.5304534435272217,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.85,
|
| 1497 |
+
"learning_rate": 3.4371582698185636e-07,
|
| 1498 |
+
"logits/chosen": -0.8014335632324219,
|
| 1499 |
+
"logits/rejected": -0.5965282917022705,
|
| 1500 |
+
"logps/chosen": -1543.572021484375,
|
| 1501 |
+
"logps/rejected": -2121.01611328125,
|
| 1502 |
+
"loss": 0.5224,
|
| 1503 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1504 |
+
"rewards/chosen": -1.2631282806396484,
|
| 1505 |
+
"rewards/margins": 0.5626910924911499,
|
| 1506 |
+
"rewards/rejected": -1.8258193731307983,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.86,
|
| 1511 |
+
"learning_rate": 3.092332998903416e-07,
|
| 1512 |
+
"logits/chosen": -0.7670878171920776,
|
| 1513 |
+
"logits/rejected": -0.6641474366188049,
|
| 1514 |
+
"logps/chosen": -1278.5185546875,
|
| 1515 |
+
"logps/rejected": -1890.5849609375,
|
| 1516 |
+
"loss": 0.5691,
|
| 1517 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1518 |
+
"rewards/chosen": -1.028751015663147,
|
| 1519 |
+
"rewards/margins": 0.6037184000015259,
|
| 1520 |
+
"rewards/rejected": -1.6324694156646729,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.86,
|
| 1525 |
+
"learning_rate": 2.764590667717562e-07,
|
| 1526 |
+
"logits/chosen": -0.5815708637237549,
|
| 1527 |
+
"logits/rejected": -0.41486841440200806,
|
| 1528 |
+
"logps/chosen": -1293.8211669921875,
|
| 1529 |
+
"logps/rejected": -1344.2347412109375,
|
| 1530 |
+
"loss": 0.6088,
|
| 1531 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1532 |
+
"rewards/chosen": -1.1181930303573608,
|
| 1533 |
+
"rewards/margins": 0.08898428082466125,
|
| 1534 |
+
"rewards/rejected": -1.2071774005889893,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.87,
|
| 1539 |
+
"learning_rate": 2.454186839872158e-07,
|
| 1540 |
+
"logits/chosen": -0.5545269250869751,
|
| 1541 |
+
"logits/rejected": -0.26859965920448303,
|
| 1542 |
+
"logps/chosen": -1244.134033203125,
|
| 1543 |
+
"logps/rejected": -2037.753173828125,
|
| 1544 |
+
"loss": 0.5342,
|
| 1545 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1546 |
+
"rewards/chosen": -1.0435465574264526,
|
| 1547 |
+
"rewards/margins": 0.803005039691925,
|
| 1548 |
+
"rewards/rejected": -1.846551537513733,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.88,
|
| 1553 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 1554 |
+
"logits/chosen": -0.7278003096580505,
|
| 1555 |
+
"logits/rejected": -0.48944416642189026,
|
| 1556 |
+
"logps/chosen": -1177.9012451171875,
|
| 1557 |
+
"logps/rejected": -1511.353271484375,
|
| 1558 |
+
"loss": 0.5785,
|
| 1559 |
+
"rewards/accuracies": 0.5,
|
| 1560 |
+
"rewards/chosen": -0.9513974189758301,
|
| 1561 |
+
"rewards/margins": 0.3561546504497528,
|
| 1562 |
+
"rewards/rejected": -1.3075522184371948,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.89,
|
| 1567 |
+
"learning_rate": 1.8863491596921745e-07,
|
| 1568 |
+
"logits/chosen": -0.6377410888671875,
|
| 1569 |
+
"logits/rejected": -0.3075203001499176,
|
| 1570 |
+
"logps/chosen": -1318.663330078125,
|
| 1571 |
+
"logps/rejected": -1740.0550537109375,
|
| 1572 |
+
"loss": 0.5713,
|
| 1573 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1574 |
+
"rewards/chosen": -1.0838841199874878,
|
| 1575 |
+
"rewards/margins": 0.48200005292892456,
|
| 1576 |
+
"rewards/rejected": -1.5658843517303467,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9,
|
| 1581 |
+
"learning_rate": 1.629358090099639e-07,
|
| 1582 |
+
"logits/chosen": -0.6629775166511536,
|
| 1583 |
+
"logits/rejected": -0.4597536623477936,
|
| 1584 |
+
"logps/chosen": -1286.1126708984375,
|
| 1585 |
+
"logps/rejected": -1661.913818359375,
|
| 1586 |
+
"loss": 0.5857,
|
| 1587 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1588 |
+
"rewards/chosen": -1.0760018825531006,
|
| 1589 |
+
"rewards/margins": 0.4137555658817291,
|
| 1590 |
+
"rewards/rejected": -1.4897575378417969,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9,
|
| 1595 |
+
"learning_rate": 1.3905907440629752e-07,
|
| 1596 |
+
"logits/chosen": -0.6975369453430176,
|
| 1597 |
+
"logits/rejected": -0.37434595823287964,
|
| 1598 |
+
"logps/chosen": -1213.16357421875,
|
| 1599 |
+
"logps/rejected": -1767.626953125,
|
| 1600 |
+
"loss": 0.5456,
|
| 1601 |
+
"rewards/accuracies": 0.625,
|
| 1602 |
+
"rewards/chosen": -1.0053523778915405,
|
| 1603 |
+
"rewards/margins": 0.5850921869277954,
|
| 1604 |
+
"rewards/rejected": -1.590444564819336,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.91,
|
| 1609 |
+
"learning_rate": 1.1702333051763271e-07,
|
| 1610 |
+
"logits/chosen": -0.5941771268844604,
|
| 1611 |
+
"logits/rejected": -0.2517922520637512,
|
| 1612 |
+
"logps/chosen": -1322.6558837890625,
|
| 1613 |
+
"logps/rejected": -2049.239990234375,
|
| 1614 |
+
"loss": 0.5619,
|
| 1615 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1616 |
+
"rewards/chosen": -1.0624778270721436,
|
| 1617 |
+
"rewards/margins": 0.7733040452003479,
|
| 1618 |
+
"rewards/rejected": -1.8357816934585571,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.92,
|
| 1623 |
+
"learning_rate": 9.684576015420277e-08,
|
| 1624 |
+
"logits/chosen": -0.5614938139915466,
|
| 1625 |
+
"logits/rejected": -0.23553869128227234,
|
| 1626 |
+
"logps/chosen": -1208.92578125,
|
| 1627 |
+
"logps/rejected": -1956.3076171875,
|
| 1628 |
+
"loss": 0.5312,
|
| 1629 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1630 |
+
"rewards/chosen": -0.964518666267395,
|
| 1631 |
+
"rewards/margins": 0.7551183700561523,
|
| 1632 |
+
"rewards/rejected": -1.7196366786956787,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.93,
|
| 1637 |
+
"learning_rate": 7.854209717842231e-08,
|
| 1638 |
+
"logits/chosen": -0.47661489248275757,
|
| 1639 |
+
"logits/rejected": -0.4136199951171875,
|
| 1640 |
+
"logps/chosen": -1535.53125,
|
| 1641 |
+
"logps/rejected": -1556.564208984375,
|
| 1642 |
+
"loss": 0.5937,
|
| 1643 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1644 |
+
"rewards/chosen": -1.3042292594909668,
|
| 1645 |
+
"rewards/margins": 0.05206754058599472,
|
| 1646 |
+
"rewards/rejected": -1.3562968969345093,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.94,
|
| 1651 |
+
"learning_rate": 6.212661423609184e-08,
|
| 1652 |
+
"logits/chosen": -0.2740413248538971,
|
| 1653 |
+
"logits/rejected": -0.08171738684177399,
|
| 1654 |
+
"logps/chosen": -1799.115966796875,
|
| 1655 |
+
"logps/rejected": -2178.206298828125,
|
| 1656 |
+
"loss": 0.6457,
|
| 1657 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1658 |
+
"rewards/chosen": -1.5849744081497192,
|
| 1659 |
+
"rewards/margins": 0.36505863070487976,
|
| 1660 |
+
"rewards/rejected": -1.950033187866211,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.94,
|
| 1665 |
+
"learning_rate": 4.761211162702117e-08,
|
| 1666 |
+
"logits/chosen": -0.6067721247673035,
|
| 1667 |
+
"logits/rejected": -0.4642402231693268,
|
| 1668 |
+
"logps/chosen": -1221.586181640625,
|
| 1669 |
+
"logps/rejected": -1701.192138671875,
|
| 1670 |
+
"loss": 0.5565,
|
| 1671 |
+
"rewards/accuracies": 0.625,
|
| 1672 |
+
"rewards/chosen": -0.9978384971618652,
|
| 1673 |
+
"rewards/margins": 0.4972690939903259,
|
| 1674 |
+
"rewards/rejected": -1.495107650756836,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.95,
|
| 1679 |
+
"learning_rate": 3.5009907323737826e-08,
|
| 1680 |
+
"logits/chosen": -0.49088191986083984,
|
| 1681 |
+
"logits/rejected": -0.08736220747232437,
|
| 1682 |
+
"logps/chosen": -1518.2652587890625,
|
| 1683 |
+
"logps/rejected": -2224.583251953125,
|
| 1684 |
+
"loss": 0.5343,
|
| 1685 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1686 |
+
"rewards/chosen": -1.2854472398757935,
|
| 1687 |
+
"rewards/margins": 0.7208049893379211,
|
| 1688 |
+
"rewards/rejected": -2.0062522888183594,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.96,
|
| 1693 |
+
"learning_rate": 2.4329828146074096e-08,
|
| 1694 |
+
"logits/chosen": -0.8410149812698364,
|
| 1695 |
+
"logits/rejected": -0.44159603118896484,
|
| 1696 |
+
"logps/chosen": -1532.341064453125,
|
| 1697 |
+
"logps/rejected": -2004.224609375,
|
| 1698 |
+
"loss": 0.5429,
|
| 1699 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1700 |
+
"rewards/chosen": -1.2669811248779297,
|
| 1701 |
+
"rewards/margins": 0.5341062545776367,
|
| 1702 |
+
"rewards/rejected": -1.8010873794555664,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.97,
|
| 1707 |
+
"learning_rate": 1.5580202098509078e-08,
|
| 1708 |
+
"logits/chosen": -0.7756412625312805,
|
| 1709 |
+
"logits/rejected": -0.6899667382240295,
|
| 1710 |
+
"logps/chosen": -1571.1226806640625,
|
| 1711 |
+
"logps/rejected": -1902.881103515625,
|
| 1712 |
+
"loss": 0.6078,
|
| 1713 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1714 |
+
"rewards/chosen": -1.2325947284698486,
|
| 1715 |
+
"rewards/margins": 0.39045584201812744,
|
| 1716 |
+
"rewards/rejected": -1.6230506896972656,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.98,
|
| 1721 |
+
"learning_rate": 8.767851876239075e-09,
|
| 1722 |
+
"logits/chosen": -0.46918898820877075,
|
| 1723 |
+
"logits/rejected": -0.3102288246154785,
|
| 1724 |
+
"logps/chosen": -1344.245849609375,
|
| 1725 |
+
"logps/rejected": -2028.437744140625,
|
| 1726 |
+
"loss": 0.5657,
|
| 1727 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1728 |
+
"rewards/chosen": -1.1186540126800537,
|
| 1729 |
+
"rewards/margins": 0.6764768362045288,
|
| 1730 |
+
"rewards/rejected": -1.795130729675293,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.98,
|
| 1735 |
+
"learning_rate": 3.8980895450474455e-09,
|
| 1736 |
+
"logits/chosen": -0.711412787437439,
|
| 1737 |
+
"logits/rejected": -0.4764884412288666,
|
| 1738 |
+
"logps/chosen": -1259.3299560546875,
|
| 1739 |
+
"logps/rejected": -1813.244140625,
|
| 1740 |
+
"loss": 0.6144,
|
| 1741 |
+
"rewards/accuracies": 0.625,
|
| 1742 |
+
"rewards/chosen": -1.0406744480133057,
|
| 1743 |
+
"rewards/margins": 0.5738798379898071,
|
| 1744 |
+
"rewards/rejected": -1.6145541667938232,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.99,
|
| 1749 |
+
"learning_rate": 9.747123991141193e-10,
|
| 1750 |
+
"logits/chosen": -0.8476069569587708,
|
| 1751 |
+
"logits/rejected": -0.6075129508972168,
|
| 1752 |
+
"logps/chosen": -1082.3035888671875,
|
| 1753 |
+
"logps/rejected": -1693.7867431640625,
|
| 1754 |
+
"loss": 0.5187,
|
| 1755 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1756 |
+
"rewards/chosen": -0.8576550483703613,
|
| 1757 |
+
"rewards/margins": 0.6194905042648315,
|
| 1758 |
+
"rewards/rejected": -1.4771454334259033,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.0,
|
| 1763 |
+
"learning_rate": 0.0,
|
| 1764 |
+
"logits/chosen": -0.6977601051330566,
|
| 1765 |
+
"logits/rejected": -0.5082852244377136,
|
| 1766 |
+
"logps/chosen": -1377.8076171875,
|
| 1767 |
+
"logps/rejected": -1863.675048828125,
|
| 1768 |
+
"loss": 0.5461,
|
| 1769 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1770 |
+
"rewards/chosen": -1.1340118646621704,
|
| 1771 |
+
"rewards/margins": 0.5046813488006592,
|
| 1772 |
+
"rewards/rejected": -1.6386932134628296,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.0,
|
| 1777 |
+
"step": 1250,
|
| 1778 |
+
"total_flos": 0.0,
|
| 1779 |
+
"train_loss": 0.6113488140106201,
|
| 1780 |
+
"train_runtime": 13063.964,
|
| 1781 |
+
"train_samples_per_second": 1.148,
|
| 1782 |
+
"train_steps_per_second": 0.096
|
| 1783 |
+
}
|
| 1784 |
+
],
|
| 1785 |
+
"logging_steps": 10,
|
| 1786 |
+
"max_steps": 1250,
|
| 1787 |
+
"num_input_tokens_seen": 0,
|
| 1788 |
+
"num_train_epochs": 1,
|
| 1789 |
+
"save_steps": 20,
|
| 1790 |
+
"total_flos": 0.0,
|
| 1791 |
+
"train_batch_size": 2,
|
| 1792 |
+
"trial_name": null,
|
| 1793 |
+
"trial_params": null
|
| 1794 |
+
}
|