Model save
Browse files- README.md +62 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May22_11-35-09_gpu4-119-5/events.out.tfevents.1716341869.gpu4-119-5.2727811.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1346 -0
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-i1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: phi-2-irepo-chatml-v5-i2
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# phi-2-irepo-chatml-v5-i2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-i1](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-i1) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 2
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- total_eval_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- PEFT 0.7.1
|
| 59 |
+
- Transformers 4.36.2
|
| 60 |
+
- Pytorch 2.1.2+cu121
|
| 61 |
+
- Datasets 2.14.6
|
| 62 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335579632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af7afaf16cef59c811f9058d17c3ffcd3b9fbf58649f65b8fc7c6aaf939843d1
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.19473119514220044,
|
| 4 |
+
"train_runtime": 7963.8235,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.767,
|
| 7 |
+
"train_steps_per_second": 0.118
|
| 8 |
+
}
|
runs/May22_11-35-09_gpu4-119-5/events.out.tfevents.1716341869.gpu4-119-5.2727811.0
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:a4a9c6f91559b86b4aa523e91c4f385f112115b201f93271e1367657ac29938b
|
| 3 |
+
size 64716
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.19473119514220044,
|
| 4 |
+
"train_runtime": 7963.8235,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.767,
|
| 7 |
+
"train_steps_per_second": 0.118
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9994666666666666,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 937,
|
| 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": 5.319148936170213e-08,
|
| 14 |
+
"logits/chosen": -0.1885092854499817,
|
| 15 |
+
"logits/rejected": -0.3158565163612366,
|
| 16 |
+
"logps/chosen": -579.0175170898438,
|
| 17 |
+
"logps/rejected": -485.2366638183594,
|
| 18 |
+
"loss": 0.2285,
|
| 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": 5.319148936170213e-07,
|
| 28 |
+
"logits/chosen": -0.14487330615520477,
|
| 29 |
+
"logits/rejected": -0.07772153615951538,
|
| 30 |
+
"logps/chosen": -490.6266174316406,
|
| 31 |
+
"logps/rejected": -480.7708740234375,
|
| 32 |
+
"loss": 0.21,
|
| 33 |
+
"rewards/accuracies": 0.3263888955116272,
|
| 34 |
+
"rewards/chosen": -0.00022973844897933304,
|
| 35 |
+
"rewards/margins": -7.616530638188124e-05,
|
| 36 |
+
"rewards/rejected": -0.0001535731425974518,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": -0.17436349391937256,
|
| 43 |
+
"logits/rejected": -0.20474335551261902,
|
| 44 |
+
"logps/chosen": -491.7076721191406,
|
| 45 |
+
"logps/rejected": -509.813232421875,
|
| 46 |
+
"loss": 0.2025,
|
| 47 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 48 |
+
"rewards/chosen": -9.073010733118281e-05,
|
| 49 |
+
"rewards/margins": 9.670343570178375e-05,
|
| 50 |
+
"rewards/rejected": -0.00018743352848105133,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": -0.13612958788871765,
|
| 57 |
+
"logits/rejected": -0.13220253586769104,
|
| 58 |
+
"logps/chosen": -529.9112548828125,
|
| 59 |
+
"logps/rejected": -542.8663940429688,
|
| 60 |
+
"loss": 0.2153,
|
| 61 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 62 |
+
"rewards/chosen": -0.0004884627414867282,
|
| 63 |
+
"rewards/margins": 0.00024191811098717153,
|
| 64 |
+
"rewards/rejected": -0.0007303808815777302,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": -0.10267192125320435,
|
| 71 |
+
"logits/rejected": -0.09803201258182526,
|
| 72 |
+
"logps/chosen": -578.48291015625,
|
| 73 |
+
"logps/rejected": -594.6197509765625,
|
| 74 |
+
"loss": 0.2087,
|
| 75 |
+
"rewards/accuracies": 0.512499988079071,
|
| 76 |
+
"rewards/chosen": -0.0006708616274408996,
|
| 77 |
+
"rewards/margins": 0.0006775633082725108,
|
| 78 |
+
"rewards/rejected": -0.0013484249357134104,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": -0.10303981602191925,
|
| 85 |
+
"logits/rejected": -0.133346289396286,
|
| 86 |
+
"logps/chosen": -511.7806091308594,
|
| 87 |
+
"logps/rejected": -534.8740234375,
|
| 88 |
+
"loss": 0.21,
|
| 89 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 90 |
+
"rewards/chosen": -0.0018150504911318421,
|
| 91 |
+
"rewards/margins": 0.0009007491171360016,
|
| 92 |
+
"rewards/rejected": -0.0027157997246831656,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": -0.22180834412574768,
|
| 99 |
+
"logits/rejected": -0.08587469905614853,
|
| 100 |
+
"logps/chosen": -550.4360961914062,
|
| 101 |
+
"logps/rejected": -563.314697265625,
|
| 102 |
+
"loss": 0.212,
|
| 103 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 104 |
+
"rewards/chosen": -0.005344606935977936,
|
| 105 |
+
"rewards/margins": 0.0011552043724805117,
|
| 106 |
+
"rewards/rejected": -0.006499811075627804,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": -0.1192946806550026,
|
| 113 |
+
"logits/rejected": -0.10370689630508423,
|
| 114 |
+
"logps/chosen": -537.7994384765625,
|
| 115 |
+
"logps/rejected": -544.24951171875,
|
| 116 |
+
"loss": 0.2132,
|
| 117 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 118 |
+
"rewards/chosen": -0.010287364944815636,
|
| 119 |
+
"rewards/margins": 0.003959923516958952,
|
| 120 |
+
"rewards/rejected": -0.0142472879961133,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": -0.12416684627532959,
|
| 127 |
+
"logits/rejected": -0.1819939911365509,
|
| 128 |
+
"logps/chosen": -515.0903930664062,
|
| 129 |
+
"logps/rejected": -531.8945922851562,
|
| 130 |
+
"loss": 0.21,
|
| 131 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 132 |
+
"rewards/chosen": -0.015505559742450714,
|
| 133 |
+
"rewards/margins": 0.003083501709625125,
|
| 134 |
+
"rewards/rejected": -0.018589060753583908,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": -0.2256217896938324,
|
| 141 |
+
"logits/rejected": -0.21886661648750305,
|
| 142 |
+
"logps/chosen": -503.46875,
|
| 143 |
+
"logps/rejected": -517.8480224609375,
|
| 144 |
+
"loss": 0.2086,
|
| 145 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 146 |
+
"rewards/chosen": -0.02677309513092041,
|
| 147 |
+
"rewards/margins": 0.004604019224643707,
|
| 148 |
+
"rewards/rejected": -0.03137711435556412,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": -0.14829424023628235,
|
| 155 |
+
"logits/rejected": -0.23846416175365448,
|
| 156 |
+
"logps/chosen": -551.840087890625,
|
| 157 |
+
"logps/rejected": -553.8361206054688,
|
| 158 |
+
"loss": 0.1984,
|
| 159 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 160 |
+
"rewards/chosen": -0.04528447985649109,
|
| 161 |
+
"rewards/margins": 0.004657699726521969,
|
| 162 |
+
"rewards/rejected": -0.04994218051433563,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": -0.25657883286476135,
|
| 169 |
+
"logits/rejected": -0.28871434926986694,
|
| 170 |
+
"logps/chosen": -600.0863647460938,
|
| 171 |
+
"logps/rejected": -634.4995727539062,
|
| 172 |
+
"loss": 0.1992,
|
| 173 |
+
"rewards/accuracies": 0.46875,
|
| 174 |
+
"rewards/chosen": -0.0750977173447609,
|
| 175 |
+
"rewards/margins": 0.020321359857916832,
|
| 176 |
+
"rewards/rejected": -0.09541907161474228,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": -0.2847597897052765,
|
| 183 |
+
"logits/rejected": -0.2475430965423584,
|
| 184 |
+
"logps/chosen": -621.210693359375,
|
| 185 |
+
"logps/rejected": -635.7638549804688,
|
| 186 |
+
"loss": 0.2029,
|
| 187 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 188 |
+
"rewards/chosen": -0.08808945119380951,
|
| 189 |
+
"rewards/margins": 0.016084905713796616,
|
| 190 |
+
"rewards/rejected": -0.10417436063289642,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": -0.19638505578041077,
|
| 197 |
+
"logits/rejected": -0.2249457836151123,
|
| 198 |
+
"logps/chosen": -586.533203125,
|
| 199 |
+
"logps/rejected": -623.6920166015625,
|
| 200 |
+
"loss": 0.1987,
|
| 201 |
+
"rewards/accuracies": 0.46875,
|
| 202 |
+
"rewards/chosen": -0.09554356336593628,
|
| 203 |
+
"rewards/margins": 0.026452088728547096,
|
| 204 |
+
"rewards/rejected": -0.12199564278125763,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": -0.2038092166185379,
|
| 211 |
+
"logits/rejected": -0.2346273958683014,
|
| 212 |
+
"logps/chosen": -569.3733520507812,
|
| 213 |
+
"logps/rejected": -591.7291259765625,
|
| 214 |
+
"loss": 0.1968,
|
| 215 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 216 |
+
"rewards/chosen": -0.08128508180379868,
|
| 217 |
+
"rewards/margins": 0.024774957448244095,
|
| 218 |
+
"rewards/rejected": -0.10606005042791367,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": -0.26792481541633606,
|
| 225 |
+
"logits/rejected": -0.16466854512691498,
|
| 226 |
+
"logps/chosen": -599.0369262695312,
|
| 227 |
+
"logps/rejected": -654.7034912109375,
|
| 228 |
+
"loss": 0.2017,
|
| 229 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 230 |
+
"rewards/chosen": -0.08535520732402802,
|
| 231 |
+
"rewards/margins": 0.025586510077118874,
|
| 232 |
+
"rewards/rejected": -0.11094172298908234,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": -0.1864621341228485,
|
| 239 |
+
"logits/rejected": -0.2081078737974167,
|
| 240 |
+
"logps/chosen": -529.7960205078125,
|
| 241 |
+
"logps/rejected": -589.953857421875,
|
| 242 |
+
"loss": 0.199,
|
| 243 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 244 |
+
"rewards/chosen": -0.06579065322875977,
|
| 245 |
+
"rewards/margins": 0.027334023267030716,
|
| 246 |
+
"rewards/rejected": -0.09312467277050018,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": -0.26899057626724243,
|
| 253 |
+
"logits/rejected": -0.22697623074054718,
|
| 254 |
+
"logps/chosen": -629.7769165039062,
|
| 255 |
+
"logps/rejected": -715.6519775390625,
|
| 256 |
+
"loss": 0.1984,
|
| 257 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 258 |
+
"rewards/chosen": -0.08880215883255005,
|
| 259 |
+
"rewards/margins": 0.038344450294971466,
|
| 260 |
+
"rewards/rejected": -0.1271466165781021,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": -0.2153758555650711,
|
| 267 |
+
"logits/rejected": -0.09847669303417206,
|
| 268 |
+
"logps/chosen": -593.626953125,
|
| 269 |
+
"logps/rejected": -643.131591796875,
|
| 270 |
+
"loss": 0.2048,
|
| 271 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 272 |
+
"rewards/chosen": -0.08825898915529251,
|
| 273 |
+
"rewards/margins": 0.031147807836532593,
|
| 274 |
+
"rewards/rejected": -0.1194067969918251,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": -0.12460646778345108,
|
| 281 |
+
"logits/rejected": -0.21595044434070587,
|
| 282 |
+
"logps/chosen": -633.2433471679688,
|
| 283 |
+
"logps/rejected": -660.8668212890625,
|
| 284 |
+
"loss": 0.2002,
|
| 285 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 286 |
+
"rewards/chosen": -0.09575756639242172,
|
| 287 |
+
"rewards/margins": 0.027992555871605873,
|
| 288 |
+
"rewards/rejected": -0.12375012785196304,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": -0.14323315024375916,
|
| 295 |
+
"logits/rejected": -0.2139279544353485,
|
| 296 |
+
"logps/chosen": -578.2418212890625,
|
| 297 |
+
"logps/rejected": -605.6033325195312,
|
| 298 |
+
"loss": 0.2023,
|
| 299 |
+
"rewards/accuracies": 0.3812499940395355,
|
| 300 |
+
"rewards/chosen": -0.08724905550479889,
|
| 301 |
+
"rewards/margins": 0.01588294841349125,
|
| 302 |
+
"rewards/rejected": -0.1031319871544838,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": -0.15528282523155212,
|
| 309 |
+
"logits/rejected": -0.15554766356945038,
|
| 310 |
+
"logps/chosen": -628.6737060546875,
|
| 311 |
+
"logps/rejected": -688.3468017578125,
|
| 312 |
+
"loss": 0.1956,
|
| 313 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 314 |
+
"rewards/chosen": -0.08062631636857986,
|
| 315 |
+
"rewards/margins": 0.026851017028093338,
|
| 316 |
+
"rewards/rejected": -0.1074773296713829,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": -0.18030421435832977,
|
| 323 |
+
"logits/rejected": -0.06279157847166061,
|
| 324 |
+
"logps/chosen": -651.3761596679688,
|
| 325 |
+
"logps/rejected": -689.3553466796875,
|
| 326 |
+
"loss": 0.1887,
|
| 327 |
+
"rewards/accuracies": 0.512499988079071,
|
| 328 |
+
"rewards/chosen": -0.09219054132699966,
|
| 329 |
+
"rewards/margins": 0.028040152043104172,
|
| 330 |
+
"rewards/rejected": -0.12023069709539413,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": -0.16874362528324127,
|
| 337 |
+
"logits/rejected": -0.1639997959136963,
|
| 338 |
+
"logps/chosen": -555.4114990234375,
|
| 339 |
+
"logps/rejected": -628.8604736328125,
|
| 340 |
+
"loss": 0.1989,
|
| 341 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 342 |
+
"rewards/chosen": -0.1045011430978775,
|
| 343 |
+
"rewards/margins": 0.02383086457848549,
|
| 344 |
+
"rewards/rejected": -0.1283320039510727,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": -0.12631872296333313,
|
| 351 |
+
"logits/rejected": -0.13256661593914032,
|
| 352 |
+
"logps/chosen": -553.3485717773438,
|
| 353 |
+
"logps/rejected": -603.0968627929688,
|
| 354 |
+
"loss": 0.1915,
|
| 355 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 356 |
+
"rewards/chosen": -0.08940593898296356,
|
| 357 |
+
"rewards/margins": 0.04212746024131775,
|
| 358 |
+
"rewards/rejected": -0.1315334141254425,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": -0.1083054393529892,
|
| 365 |
+
"logits/rejected": -0.0742143839597702,
|
| 366 |
+
"logps/chosen": -599.7116088867188,
|
| 367 |
+
"logps/rejected": -652.4061279296875,
|
| 368 |
+
"loss": 0.1884,
|
| 369 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 370 |
+
"rewards/chosen": -0.09931150823831558,
|
| 371 |
+
"rewards/margins": 0.03657541796565056,
|
| 372 |
+
"rewards/rejected": -0.13588692247867584,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": -0.11171998083591461,
|
| 379 |
+
"logits/rejected": -0.16903842985630035,
|
| 380 |
+
"logps/chosen": -593.5734252929688,
|
| 381 |
+
"logps/rejected": -672.16552734375,
|
| 382 |
+
"loss": 0.1929,
|
| 383 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 384 |
+
"rewards/chosen": -0.09612639248371124,
|
| 385 |
+
"rewards/margins": 0.05510964244604111,
|
| 386 |
+
"rewards/rejected": -0.15123602747917175,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": -0.09803778678178787,
|
| 393 |
+
"logits/rejected": -0.08885441720485687,
|
| 394 |
+
"logps/chosen": -665.0200805664062,
|
| 395 |
+
"logps/rejected": -690.63818359375,
|
| 396 |
+
"loss": 0.2074,
|
| 397 |
+
"rewards/accuracies": 0.40625,
|
| 398 |
+
"rewards/chosen": -0.08989432454109192,
|
| 399 |
+
"rewards/margins": 0.02165227010846138,
|
| 400 |
+
"rewards/rejected": -0.111546590924263,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": -0.005570247769355774,
|
| 407 |
+
"logits/rejected": -0.13455268740653992,
|
| 408 |
+
"logps/chosen": -609.916748046875,
|
| 409 |
+
"logps/rejected": -643.1370849609375,
|
| 410 |
+
"loss": 0.1925,
|
| 411 |
+
"rewards/accuracies": 0.512499988079071,
|
| 412 |
+
"rewards/chosen": -0.06449146568775177,
|
| 413 |
+
"rewards/margins": 0.022723758593201637,
|
| 414 |
+
"rewards/rejected": -0.08721521496772766,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": -0.027301525697112083,
|
| 421 |
+
"logits/rejected": -0.0810176208615303,
|
| 422 |
+
"logps/chosen": -541.7484130859375,
|
| 423 |
+
"logps/rejected": -617.4515380859375,
|
| 424 |
+
"loss": 0.1958,
|
| 425 |
+
"rewards/accuracies": 0.53125,
|
| 426 |
+
"rewards/chosen": -0.062103599309921265,
|
| 427 |
+
"rewards/margins": 0.0201987586915493,
|
| 428 |
+
"rewards/rejected": -0.08230235427618027,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": 0.005954580847173929,
|
| 435 |
+
"logits/rejected": -0.03331022337079048,
|
| 436 |
+
"logps/chosen": -575.2536010742188,
|
| 437 |
+
"logps/rejected": -629.2679443359375,
|
| 438 |
+
"loss": 0.1965,
|
| 439 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 440 |
+
"rewards/chosen": -0.07110811769962311,
|
| 441 |
+
"rewards/margins": 0.021345119923353195,
|
| 442 |
+
"rewards/rejected": -0.0924532413482666,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": -0.05120337754487991,
|
| 449 |
+
"logits/rejected": -0.07742851972579956,
|
| 450 |
+
"logps/chosen": -555.53662109375,
|
| 451 |
+
"logps/rejected": -598.7825927734375,
|
| 452 |
+
"loss": 0.1928,
|
| 453 |
+
"rewards/accuracies": 0.512499988079071,
|
| 454 |
+
"rewards/chosen": -0.07844728976488113,
|
| 455 |
+
"rewards/margins": 0.03324751555919647,
|
| 456 |
+
"rewards/rejected": -0.11169479787349701,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": -0.10243277251720428,
|
| 463 |
+
"logits/rejected": -0.03584013134241104,
|
| 464 |
+
"logps/chosen": -573.73046875,
|
| 465 |
+
"logps/rejected": -552.7764892578125,
|
| 466 |
+
"loss": 0.206,
|
| 467 |
+
"rewards/accuracies": 0.40625,
|
| 468 |
+
"rewards/chosen": -0.06825848668813705,
|
| 469 |
+
"rewards/margins": 0.009243585169315338,
|
| 470 |
+
"rewards/rejected": -0.0775020569562912,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": -0.028592532500624657,
|
| 477 |
+
"logits/rejected": 0.022961582988500595,
|
| 478 |
+
"logps/chosen": -559.4745483398438,
|
| 479 |
+
"logps/rejected": -626.19482421875,
|
| 480 |
+
"loss": 0.1891,
|
| 481 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 482 |
+
"rewards/chosen": -0.05221911519765854,
|
| 483 |
+
"rewards/margins": 0.037141233682632446,
|
| 484 |
+
"rewards/rejected": -0.08936034888029099,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": 0.02807508036494255,
|
| 491 |
+
"logits/rejected": -0.025245526805520058,
|
| 492 |
+
"logps/chosen": -576.9495239257812,
|
| 493 |
+
"logps/rejected": -612.4227905273438,
|
| 494 |
+
"loss": 0.1949,
|
| 495 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 496 |
+
"rewards/chosen": -0.04981788620352745,
|
| 497 |
+
"rewards/margins": 0.029762808233499527,
|
| 498 |
+
"rewards/rejected": -0.07958068698644638,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.014679011888802052,
|
| 505 |
+
"logits/rejected": 0.05258216708898544,
|
| 506 |
+
"logps/chosen": -537.677978515625,
|
| 507 |
+
"logps/rejected": -593.5046997070312,
|
| 508 |
+
"loss": 0.1982,
|
| 509 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 510 |
+
"rewards/chosen": -0.063970185816288,
|
| 511 |
+
"rewards/margins": 0.030909085646271706,
|
| 512 |
+
"rewards/rejected": -0.09487926214933395,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": -0.10759621858596802,
|
| 519 |
+
"logits/rejected": -0.07801146060228348,
|
| 520 |
+
"logps/chosen": -577.882568359375,
|
| 521 |
+
"logps/rejected": -652.2096557617188,
|
| 522 |
+
"loss": 0.1919,
|
| 523 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 524 |
+
"rewards/chosen": -0.07402776181697845,
|
| 525 |
+
"rewards/margins": 0.038211267441511154,
|
| 526 |
+
"rewards/rejected": -0.1122390404343605,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": -0.02245343290269375,
|
| 533 |
+
"logits/rejected": 0.03868962079286575,
|
| 534 |
+
"logps/chosen": -616.5308837890625,
|
| 535 |
+
"logps/rejected": -642.6898193359375,
|
| 536 |
+
"loss": 0.1978,
|
| 537 |
+
"rewards/accuracies": 0.46875,
|
| 538 |
+
"rewards/chosen": -0.08398912847042084,
|
| 539 |
+
"rewards/margins": 0.02132398448884487,
|
| 540 |
+
"rewards/rejected": -0.10531310737133026,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": -0.07354136556386948,
|
| 547 |
+
"logits/rejected": -0.04209035634994507,
|
| 548 |
+
"logps/chosen": -616.562744140625,
|
| 549 |
+
"logps/rejected": -685.1181030273438,
|
| 550 |
+
"loss": 0.2001,
|
| 551 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 552 |
+
"rewards/chosen": -0.0954984650015831,
|
| 553 |
+
"rewards/margins": 0.04605044052004814,
|
| 554 |
+
"rewards/rejected": -0.14154890179634094,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": -0.11906121671199799,
|
| 561 |
+
"logits/rejected": -0.056663453578948975,
|
| 562 |
+
"logps/chosen": -596.8269653320312,
|
| 563 |
+
"logps/rejected": -644.7449340820312,
|
| 564 |
+
"loss": 0.1951,
|
| 565 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 566 |
+
"rewards/chosen": -0.08853301405906677,
|
| 567 |
+
"rewards/margins": 0.0294196717441082,
|
| 568 |
+
"rewards/rejected": -0.11795268207788467,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": 0.013636293821036816,
|
| 575 |
+
"logits/rejected": -0.04586212337017059,
|
| 576 |
+
"logps/chosen": -599.9013671875,
|
| 577 |
+
"logps/rejected": -657.8106079101562,
|
| 578 |
+
"loss": 0.2035,
|
| 579 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 580 |
+
"rewards/chosen": -0.09106438606977463,
|
| 581 |
+
"rewards/margins": 0.04611728712916374,
|
| 582 |
+
"rewards/rejected": -0.13718166947364807,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": 0.08837394416332245,
|
| 589 |
+
"logits/rejected": -0.07880507409572601,
|
| 590 |
+
"logps/chosen": -598.9387817382812,
|
| 591 |
+
"logps/rejected": -617.7493286132812,
|
| 592 |
+
"loss": 0.2047,
|
| 593 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 594 |
+
"rewards/chosen": -0.07388485968112946,
|
| 595 |
+
"rewards/margins": 0.019855108112096786,
|
| 596 |
+
"rewards/rejected": -0.09373997151851654,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": -0.005928731057792902,
|
| 603 |
+
"logits/rejected": -0.030420657247304916,
|
| 604 |
+
"logps/chosen": -558.4488525390625,
|
| 605 |
+
"logps/rejected": -602.2744750976562,
|
| 606 |
+
"loss": 0.2045,
|
| 607 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 608 |
+
"rewards/chosen": -0.06963202357292175,
|
| 609 |
+
"rewards/margins": 0.03080623783171177,
|
| 610 |
+
"rewards/rejected": -0.10043825954198837,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": -0.06051339581608772,
|
| 617 |
+
"logits/rejected": 0.0010267883772030473,
|
| 618 |
+
"logps/chosen": -594.7051391601562,
|
| 619 |
+
"logps/rejected": -662.65625,
|
| 620 |
+
"loss": 0.1935,
|
| 621 |
+
"rewards/accuracies": 0.512499988079071,
|
| 622 |
+
"rewards/chosen": -0.07640456408262253,
|
| 623 |
+
"rewards/margins": 0.04043372720479965,
|
| 624 |
+
"rewards/rejected": -0.11683829128742218,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": -0.07280877977609634,
|
| 631 |
+
"logits/rejected": -0.03391597419977188,
|
| 632 |
+
"logps/chosen": -590.2994384765625,
|
| 633 |
+
"logps/rejected": -659.5791015625,
|
| 634 |
+
"loss": 0.1965,
|
| 635 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 636 |
+
"rewards/chosen": -0.068049356341362,
|
| 637 |
+
"rewards/margins": 0.03281210735440254,
|
| 638 |
+
"rewards/rejected": -0.10086147487163544,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": -0.00242437282577157,
|
| 645 |
+
"logits/rejected": -0.059494733810424805,
|
| 646 |
+
"logps/chosen": -576.4191284179688,
|
| 647 |
+
"logps/rejected": -637.6677856445312,
|
| 648 |
+
"loss": 0.189,
|
| 649 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 650 |
+
"rewards/chosen": -0.06889624148607254,
|
| 651 |
+
"rewards/margins": 0.041952721774578094,
|
| 652 |
+
"rewards/rejected": -0.11084897816181183,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": 0.023568499833345413,
|
| 659 |
+
"logits/rejected": -0.002035862300544977,
|
| 660 |
+
"logps/chosen": -549.110107421875,
|
| 661 |
+
"logps/rejected": -576.5599365234375,
|
| 662 |
+
"loss": 0.1978,
|
| 663 |
+
"rewards/accuracies": 0.4375,
|
| 664 |
+
"rewards/chosen": -0.06544467061758041,
|
| 665 |
+
"rewards/margins": 0.02002917230129242,
|
| 666 |
+
"rewards/rejected": -0.08547384291887283,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": -0.07891889661550522,
|
| 673 |
+
"logits/rejected": 0.012334518134593964,
|
| 674 |
+
"logps/chosen": -603.6246337890625,
|
| 675 |
+
"logps/rejected": -670.80615234375,
|
| 676 |
+
"loss": 0.1957,
|
| 677 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 678 |
+
"rewards/chosen": -0.07147827744483948,
|
| 679 |
+
"rewards/margins": 0.032703179866075516,
|
| 680 |
+
"rewards/rejected": -0.10418146848678589,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": 0.04133855551481247,
|
| 687 |
+
"logits/rejected": -0.06480925530195236,
|
| 688 |
+
"logps/chosen": -609.1380004882812,
|
| 689 |
+
"logps/rejected": -640.5394287109375,
|
| 690 |
+
"loss": 0.1896,
|
| 691 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 692 |
+
"rewards/chosen": -0.07929681241512299,
|
| 693 |
+
"rewards/margins": 0.025448182597756386,
|
| 694 |
+
"rewards/rejected": -0.10474499315023422,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": 0.053513627499341965,
|
| 701 |
+
"logits/rejected": -0.0014798849588260055,
|
| 702 |
+
"logps/chosen": -560.655517578125,
|
| 703 |
+
"logps/rejected": -680.7060546875,
|
| 704 |
+
"loss": 0.1833,
|
| 705 |
+
"rewards/accuracies": 0.59375,
|
| 706 |
+
"rewards/chosen": -0.06273628771305084,
|
| 707 |
+
"rewards/margins": 0.05317532271146774,
|
| 708 |
+
"rewards/rejected": -0.11591160297393799,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": -0.02448629029095173,
|
| 715 |
+
"logits/rejected": 0.0629236251115799,
|
| 716 |
+
"logps/chosen": -592.8604125976562,
|
| 717 |
+
"logps/rejected": -623.6454467773438,
|
| 718 |
+
"loss": 0.188,
|
| 719 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 720 |
+
"rewards/chosen": -0.07425443828105927,
|
| 721 |
+
"rewards/margins": 0.044731441885232925,
|
| 722 |
+
"rewards/rejected": -0.1189858689904213,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": -0.08944495767354965,
|
| 729 |
+
"logits/rejected": 0.10957720130681992,
|
| 730 |
+
"logps/chosen": -582.0028076171875,
|
| 731 |
+
"logps/rejected": -623.3414306640625,
|
| 732 |
+
"loss": 0.1852,
|
| 733 |
+
"rewards/accuracies": 0.518750011920929,
|
| 734 |
+
"rewards/chosen": -0.08551887422800064,
|
| 735 |
+
"rewards/margins": 0.04520031064748764,
|
| 736 |
+
"rewards/rejected": -0.1307191699743271,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": -0.06701700389385223,
|
| 743 |
+
"logits/rejected": -0.07697690278291702,
|
| 744 |
+
"logps/chosen": -553.2176513671875,
|
| 745 |
+
"logps/rejected": -593.4279174804688,
|
| 746 |
+
"loss": 0.199,
|
| 747 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 748 |
+
"rewards/chosen": -0.09521619975566864,
|
| 749 |
+
"rewards/margins": 0.033401116728782654,
|
| 750 |
+
"rewards/rejected": -0.1286173164844513,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": -0.0331454835832119,
|
| 757 |
+
"logits/rejected": -0.10423725843429565,
|
| 758 |
+
"logps/chosen": -543.7550048828125,
|
| 759 |
+
"logps/rejected": -637.5558471679688,
|
| 760 |
+
"loss": 0.1833,
|
| 761 |
+
"rewards/accuracies": 0.518750011920929,
|
| 762 |
+
"rewards/chosen": -0.07857955992221832,
|
| 763 |
+
"rewards/margins": 0.043745510280132294,
|
| 764 |
+
"rewards/rejected": -0.12232507765293121,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.04820919781923294,
|
| 771 |
+
"logits/rejected": -0.08856736123561859,
|
| 772 |
+
"logps/chosen": -550.280517578125,
|
| 773 |
+
"logps/rejected": -695.6846313476562,
|
| 774 |
+
"loss": 0.182,
|
| 775 |
+
"rewards/accuracies": 0.53125,
|
| 776 |
+
"rewards/chosen": -0.0971294417977333,
|
| 777 |
+
"rewards/margins": 0.06545992940664291,
|
| 778 |
+
"rewards/rejected": -0.16258935630321503,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": -0.06888549029827118,
|
| 785 |
+
"logits/rejected": -0.019281355664134026,
|
| 786 |
+
"logps/chosen": -631.0794067382812,
|
| 787 |
+
"logps/rejected": -681.6578369140625,
|
| 788 |
+
"loss": 0.1999,
|
| 789 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 790 |
+
"rewards/chosen": -0.0913894921541214,
|
| 791 |
+
"rewards/margins": 0.034925952553749084,
|
| 792 |
+
"rewards/rejected": -0.12631544470787048,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": 0.05780111625790596,
|
| 799 |
+
"logits/rejected": -0.08857734501361847,
|
| 800 |
+
"logps/chosen": -554.0203857421875,
|
| 801 |
+
"logps/rejected": -672.1288452148438,
|
| 802 |
+
"loss": 0.1885,
|
| 803 |
+
"rewards/accuracies": 0.5,
|
| 804 |
+
"rewards/chosen": -0.08766164630651474,
|
| 805 |
+
"rewards/margins": 0.05516546964645386,
|
| 806 |
+
"rewards/rejected": -0.1428271234035492,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": -0.07425542920827866,
|
| 813 |
+
"logits/rejected": -0.14232522249221802,
|
| 814 |
+
"logps/chosen": -590.5303955078125,
|
| 815 |
+
"logps/rejected": -634.2200317382812,
|
| 816 |
+
"loss": 0.1922,
|
| 817 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 818 |
+
"rewards/chosen": -0.08620771020650864,
|
| 819 |
+
"rewards/margins": 0.02542172744870186,
|
| 820 |
+
"rewards/rejected": -0.1116294413805008,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": -0.04322206228971481,
|
| 827 |
+
"logits/rejected": 0.028172429651021957,
|
| 828 |
+
"logps/chosen": -600.7364501953125,
|
| 829 |
+
"logps/rejected": -676.2041625976562,
|
| 830 |
+
"loss": 0.1917,
|
| 831 |
+
"rewards/accuracies": 0.574999988079071,
|
| 832 |
+
"rewards/chosen": -0.07297880947589874,
|
| 833 |
+
"rewards/margins": 0.03739452734589577,
|
| 834 |
+
"rewards/rejected": -0.11037333309650421,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": 0.03321009874343872,
|
| 841 |
+
"logits/rejected": -0.012934012338519096,
|
| 842 |
+
"logps/chosen": -562.2665405273438,
|
| 843 |
+
"logps/rejected": -677.3361206054688,
|
| 844 |
+
"loss": 0.1969,
|
| 845 |
+
"rewards/accuracies": 0.53125,
|
| 846 |
+
"rewards/chosen": -0.06490649282932281,
|
| 847 |
+
"rewards/margins": 0.03305616229772568,
|
| 848 |
+
"rewards/rejected": -0.09796266257762909,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": -0.0036629363894462585,
|
| 855 |
+
"logits/rejected": 0.04252059385180473,
|
| 856 |
+
"logps/chosen": -574.91064453125,
|
| 857 |
+
"logps/rejected": -599.8869018554688,
|
| 858 |
+
"loss": 0.1941,
|
| 859 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 860 |
+
"rewards/chosen": -0.06440480798482895,
|
| 861 |
+
"rewards/margins": 0.02049572765827179,
|
| 862 |
+
"rewards/rejected": -0.08490053564310074,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": -0.028811585158109665,
|
| 869 |
+
"logits/rejected": -0.0507902130484581,
|
| 870 |
+
"logps/chosen": -614.2153930664062,
|
| 871 |
+
"logps/rejected": -697.7538452148438,
|
| 872 |
+
"loss": 0.1922,
|
| 873 |
+
"rewards/accuracies": 0.512499988079071,
|
| 874 |
+
"rewards/chosen": -0.07627642154693604,
|
| 875 |
+
"rewards/margins": 0.028858337551355362,
|
| 876 |
+
"rewards/rejected": -0.1051347628235817,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": -0.06321687996387482,
|
| 883 |
+
"logits/rejected": 0.04666703939437866,
|
| 884 |
+
"logps/chosen": -562.6372680664062,
|
| 885 |
+
"logps/rejected": -623.3756713867188,
|
| 886 |
+
"loss": 0.1964,
|
| 887 |
+
"rewards/accuracies": 0.543749988079071,
|
| 888 |
+
"rewards/chosen": -0.07641318440437317,
|
| 889 |
+
"rewards/margins": 0.02390345185995102,
|
| 890 |
+
"rewards/rejected": -0.10031662881374359,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": -0.03132300823926926,
|
| 897 |
+
"logits/rejected": 0.05715359374880791,
|
| 898 |
+
"logps/chosen": -556.3076171875,
|
| 899 |
+
"logps/rejected": -603.981689453125,
|
| 900 |
+
"loss": 0.188,
|
| 901 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 902 |
+
"rewards/chosen": -0.0778612419962883,
|
| 903 |
+
"rewards/margins": 0.032999925315380096,
|
| 904 |
+
"rewards/rejected": -0.1108611598610878,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": -0.0160093754529953,
|
| 911 |
+
"logits/rejected": -0.033678505569696426,
|
| 912 |
+
"logps/chosen": -561.7026977539062,
|
| 913 |
+
"logps/rejected": -632.2767333984375,
|
| 914 |
+
"loss": 0.1998,
|
| 915 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 916 |
+
"rewards/chosen": -0.08461053669452667,
|
| 917 |
+
"rewards/margins": 0.027624454349279404,
|
| 918 |
+
"rewards/rejected": -0.11223499476909637,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": 0.033716317266225815,
|
| 925 |
+
"logits/rejected": -0.05850861221551895,
|
| 926 |
+
"logps/chosen": -576.638916015625,
|
| 927 |
+
"logps/rejected": -658.7437133789062,
|
| 928 |
+
"loss": 0.1877,
|
| 929 |
+
"rewards/accuracies": 0.543749988079071,
|
| 930 |
+
"rewards/chosen": -0.07561091333627701,
|
| 931 |
+
"rewards/margins": 0.035250525921583176,
|
| 932 |
+
"rewards/rejected": -0.11086144298315048,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": -0.0035046476405113935,
|
| 939 |
+
"logits/rejected": -0.01969769224524498,
|
| 940 |
+
"logps/chosen": -594.3090209960938,
|
| 941 |
+
"logps/rejected": -659.2559814453125,
|
| 942 |
+
"loss": 0.1831,
|
| 943 |
+
"rewards/accuracies": 0.5625,
|
| 944 |
+
"rewards/chosen": -0.07316828519105911,
|
| 945 |
+
"rewards/margins": 0.05110269784927368,
|
| 946 |
+
"rewards/rejected": -0.12427099049091339,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": 0.015228897333145142,
|
| 953 |
+
"logits/rejected": -0.07918987423181534,
|
| 954 |
+
"logps/chosen": -573.0462646484375,
|
| 955 |
+
"logps/rejected": -665.521728515625,
|
| 956 |
+
"loss": 0.1846,
|
| 957 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 958 |
+
"rewards/chosen": -0.060265183448791504,
|
| 959 |
+
"rewards/margins": 0.053003955632448196,
|
| 960 |
+
"rewards/rejected": -0.1132691353559494,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": 0.04909176006913185,
|
| 967 |
+
"logits/rejected": 0.0019339825958013535,
|
| 968 |
+
"logps/chosen": -591.9546508789062,
|
| 969 |
+
"logps/rejected": -646.3989868164062,
|
| 970 |
+
"loss": 0.1872,
|
| 971 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 972 |
+
"rewards/chosen": -0.07109365612268448,
|
| 973 |
+
"rewards/margins": 0.050017982721328735,
|
| 974 |
+
"rewards/rejected": -0.12111164629459381,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": -0.06201664358377457,
|
| 981 |
+
"logits/rejected": 0.021130381152033806,
|
| 982 |
+
"logps/chosen": -599.9959716796875,
|
| 983 |
+
"logps/rejected": -649.0542602539062,
|
| 984 |
+
"loss": 0.1803,
|
| 985 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 986 |
+
"rewards/chosen": -0.07730476558208466,
|
| 987 |
+
"rewards/margins": 0.035370949655771255,
|
| 988 |
+
"rewards/rejected": -0.11267571151256561,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": -0.060487646609544754,
|
| 995 |
+
"logits/rejected": -0.031666141003370285,
|
| 996 |
+
"logps/chosen": -546.1062622070312,
|
| 997 |
+
"logps/rejected": -622.996337890625,
|
| 998 |
+
"loss": 0.1898,
|
| 999 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1000 |
+
"rewards/chosen": -0.07208921015262604,
|
| 1001 |
+
"rewards/margins": 0.048208087682724,
|
| 1002 |
+
"rewards/rejected": -0.12029729783535004,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": -0.043236102908849716,
|
| 1009 |
+
"logits/rejected": 0.010083493776619434,
|
| 1010 |
+
"logps/chosen": -565.9916381835938,
|
| 1011 |
+
"logps/rejected": -666.7619018554688,
|
| 1012 |
+
"loss": 0.1877,
|
| 1013 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1014 |
+
"rewards/chosen": -0.07324135303497314,
|
| 1015 |
+
"rewards/margins": 0.0542600154876709,
|
| 1016 |
+
"rewards/rejected": -0.12750136852264404,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": -0.03003951907157898,
|
| 1023 |
+
"logits/rejected": -0.023655174300074577,
|
| 1024 |
+
"logps/chosen": -593.333740234375,
|
| 1025 |
+
"logps/rejected": -679.3707275390625,
|
| 1026 |
+
"loss": 0.1821,
|
| 1027 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1028 |
+
"rewards/chosen": -0.07741405069828033,
|
| 1029 |
+
"rewards/margins": 0.040637485682964325,
|
| 1030 |
+
"rewards/rejected": -0.11805154383182526,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": -0.10231657326221466,
|
| 1037 |
+
"logits/rejected": -0.00636244285851717,
|
| 1038 |
+
"logps/chosen": -564.58154296875,
|
| 1039 |
+
"logps/rejected": -615.8031005859375,
|
| 1040 |
+
"loss": 0.1959,
|
| 1041 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1042 |
+
"rewards/chosen": -0.07730068266391754,
|
| 1043 |
+
"rewards/margins": 0.038891423493623734,
|
| 1044 |
+
"rewards/rejected": -0.11619208753108978,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": -0.12688763439655304,
|
| 1051 |
+
"logits/rejected": 0.07261992990970612,
|
| 1052 |
+
"logps/chosen": -589.0942993164062,
|
| 1053 |
+
"logps/rejected": -604.7650756835938,
|
| 1054 |
+
"loss": 0.193,
|
| 1055 |
+
"rewards/accuracies": 0.5,
|
| 1056 |
+
"rewards/chosen": -0.09481467306613922,
|
| 1057 |
+
"rewards/margins": 0.03096696175634861,
|
| 1058 |
+
"rewards/rejected": -0.12578162550926208,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": -0.0817611813545227,
|
| 1065 |
+
"logits/rejected": -0.010524662211537361,
|
| 1066 |
+
"logps/chosen": -537.4359130859375,
|
| 1067 |
+
"logps/rejected": -617.6580810546875,
|
| 1068 |
+
"loss": 0.1898,
|
| 1069 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1070 |
+
"rewards/chosen": -0.08204906433820724,
|
| 1071 |
+
"rewards/margins": 0.05059989541769028,
|
| 1072 |
+
"rewards/rejected": -0.13264895975589752,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": -0.08540595322847366,
|
| 1079 |
+
"logits/rejected": -0.019884133711457253,
|
| 1080 |
+
"logps/chosen": -569.3452758789062,
|
| 1081 |
+
"logps/rejected": -623.3587646484375,
|
| 1082 |
+
"loss": 0.1916,
|
| 1083 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1084 |
+
"rewards/chosen": -0.07342539727687836,
|
| 1085 |
+
"rewards/margins": 0.03685514256358147,
|
| 1086 |
+
"rewards/rejected": -0.11028053611516953,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": -0.0825069323182106,
|
| 1093 |
+
"logits/rejected": 0.03379444032907486,
|
| 1094 |
+
"logps/chosen": -560.5318603515625,
|
| 1095 |
+
"logps/rejected": -629.8617553710938,
|
| 1096 |
+
"loss": 0.1859,
|
| 1097 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1098 |
+
"rewards/chosen": -0.07376088947057724,
|
| 1099 |
+
"rewards/margins": 0.036222193390131,
|
| 1100 |
+
"rewards/rejected": -0.10998308658599854,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": 0.015585740096867085,
|
| 1107 |
+
"logits/rejected": -0.09954878687858582,
|
| 1108 |
+
"logps/chosen": -536.1882934570312,
|
| 1109 |
+
"logps/rejected": -646.0011596679688,
|
| 1110 |
+
"loss": 0.1864,
|
| 1111 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1112 |
+
"rewards/chosen": -0.08902934193611145,
|
| 1113 |
+
"rewards/margins": 0.054770153015851974,
|
| 1114 |
+
"rewards/rejected": -0.14379946887493134,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": -0.0846419557929039,
|
| 1121 |
+
"logits/rejected": -0.027601266279816628,
|
| 1122 |
+
"logps/chosen": -524.1680297851562,
|
| 1123 |
+
"logps/rejected": -655.0399169921875,
|
| 1124 |
+
"loss": 0.1905,
|
| 1125 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1126 |
+
"rewards/chosen": -0.06788254529237747,
|
| 1127 |
+
"rewards/margins": 0.07369416952133179,
|
| 1128 |
+
"rewards/rejected": -0.14157672226428986,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": -0.04564080387353897,
|
| 1135 |
+
"logits/rejected": -0.056423623114824295,
|
| 1136 |
+
"logps/chosen": -556.4688720703125,
|
| 1137 |
+
"logps/rejected": -622.6414794921875,
|
| 1138 |
+
"loss": 0.1852,
|
| 1139 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1140 |
+
"rewards/chosen": -0.0697588101029396,
|
| 1141 |
+
"rewards/margins": 0.047328755259513855,
|
| 1142 |
+
"rewards/rejected": -0.11708758026361465,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": -0.00408951798453927,
|
| 1149 |
+
"logits/rejected": -0.05295505374670029,
|
| 1150 |
+
"logps/chosen": -588.3592529296875,
|
| 1151 |
+
"logps/rejected": -639.141845703125,
|
| 1152 |
+
"loss": 0.1884,
|
| 1153 |
+
"rewards/accuracies": 0.5,
|
| 1154 |
+
"rewards/chosen": -0.08244818449020386,
|
| 1155 |
+
"rewards/margins": 0.04398036748170853,
|
| 1156 |
+
"rewards/rejected": -0.1264285445213318,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": -0.023698529228568077,
|
| 1163 |
+
"logits/rejected": -0.033614348620176315,
|
| 1164 |
+
"logps/chosen": -550.3116455078125,
|
| 1165 |
+
"logps/rejected": -649.8366088867188,
|
| 1166 |
+
"loss": 0.1813,
|
| 1167 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1168 |
+
"rewards/chosen": -0.06834039092063904,
|
| 1169 |
+
"rewards/margins": 0.056421488523483276,
|
| 1170 |
+
"rewards/rejected": -0.12476189434528351,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": -0.020034242421388626,
|
| 1177 |
+
"logits/rejected": -0.053077150136232376,
|
| 1178 |
+
"logps/chosen": -530.62744140625,
|
| 1179 |
+
"logps/rejected": -573.3870239257812,
|
| 1180 |
+
"loss": 0.1829,
|
| 1181 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 1182 |
+
"rewards/chosen": -0.07050155103206635,
|
| 1183 |
+
"rewards/margins": 0.03381948173046112,
|
| 1184 |
+
"rewards/rejected": -0.10432104766368866,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": -0.03530939295887947,
|
| 1191 |
+
"logits/rejected": -0.05062105506658554,
|
| 1192 |
+
"logps/chosen": -612.7421875,
|
| 1193 |
+
"logps/rejected": -640.69580078125,
|
| 1194 |
+
"loss": 0.1912,
|
| 1195 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1196 |
+
"rewards/chosen": -0.08575752377510071,
|
| 1197 |
+
"rewards/margins": 0.034512124955654144,
|
| 1198 |
+
"rewards/rejected": -0.12026965618133545,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": -0.02685430273413658,
|
| 1205 |
+
"logits/rejected": -0.050860174000263214,
|
| 1206 |
+
"logps/chosen": -561.8297119140625,
|
| 1207 |
+
"logps/rejected": -601.8411865234375,
|
| 1208 |
+
"loss": 0.1938,
|
| 1209 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 1210 |
+
"rewards/chosen": -0.07358418405056,
|
| 1211 |
+
"rewards/margins": 0.03662911430001259,
|
| 1212 |
+
"rewards/rejected": -0.11021329462528229,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": -0.0493302047252655,
|
| 1219 |
+
"logits/rejected": 0.006892223842442036,
|
| 1220 |
+
"logps/chosen": -599.8060913085938,
|
| 1221 |
+
"logps/rejected": -692.0012817382812,
|
| 1222 |
+
"loss": 0.1973,
|
| 1223 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 1224 |
+
"rewards/chosen": -0.07736798375844955,
|
| 1225 |
+
"rewards/margins": 0.050996191799640656,
|
| 1226 |
+
"rewards/rejected": -0.1283641755580902,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": -0.02599761262536049,
|
| 1233 |
+
"logits/rejected": -0.013713346794247627,
|
| 1234 |
+
"logps/chosen": -580.1739501953125,
|
| 1235 |
+
"logps/rejected": -671.7718505859375,
|
| 1236 |
+
"loss": 0.1925,
|
| 1237 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1238 |
+
"rewards/chosen": -0.07879254966974258,
|
| 1239 |
+
"rewards/margins": 0.05689109489321709,
|
| 1240 |
+
"rewards/rejected": -0.13568365573883057,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": 0.02115291729569435,
|
| 1247 |
+
"logits/rejected": -0.052051056176424026,
|
| 1248 |
+
"logps/chosen": -584.3345336914062,
|
| 1249 |
+
"logps/rejected": -611.1611328125,
|
| 1250 |
+
"loss": 0.1831,
|
| 1251 |
+
"rewards/accuracies": 0.46875,
|
| 1252 |
+
"rewards/chosen": -0.0652504563331604,
|
| 1253 |
+
"rewards/margins": 0.03656047582626343,
|
| 1254 |
+
"rewards/rejected": -0.10181091725826263,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": 0.001644585281610489,
|
| 1261 |
+
"logits/rejected": -0.010257053188979626,
|
| 1262 |
+
"logps/chosen": -632.9583740234375,
|
| 1263 |
+
"logps/rejected": -683.1160888671875,
|
| 1264 |
+
"loss": 0.204,
|
| 1265 |
+
"rewards/accuracies": 0.53125,
|
| 1266 |
+
"rewards/chosen": -0.08045943081378937,
|
| 1267 |
+
"rewards/margins": 0.047462526708841324,
|
| 1268 |
+
"rewards/rejected": -0.1279219686985016,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": -0.13961699604988098,
|
| 1275 |
+
"logits/rejected": -0.039934299886226654,
|
| 1276 |
+
"logps/chosen": -542.2841186523438,
|
| 1277 |
+
"logps/rejected": -602.2158813476562,
|
| 1278 |
+
"loss": 0.1903,
|
| 1279 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 1280 |
+
"rewards/chosen": -0.08329685032367706,
|
| 1281 |
+
"rewards/margins": 0.034699175506830215,
|
| 1282 |
+
"rewards/rejected": -0.11799603700637817,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": -0.06002987176179886,
|
| 1289 |
+
"logits/rejected": -0.00015243441157508641,
|
| 1290 |
+
"logps/chosen": -576.7723388671875,
|
| 1291 |
+
"logps/rejected": -622.7515869140625,
|
| 1292 |
+
"loss": 0.1949,
|
| 1293 |
+
"rewards/accuracies": 0.5,
|
| 1294 |
+
"rewards/chosen": -0.0770721584558487,
|
| 1295 |
+
"rewards/margins": 0.03859367594122887,
|
| 1296 |
+
"rewards/rejected": -0.11566583812236786,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": 0.030324691906571388,
|
| 1303 |
+
"logits/rejected": -0.10050855576992035,
|
| 1304 |
+
"logps/chosen": -561.7693481445312,
|
| 1305 |
+
"logps/rejected": -647.3151245117188,
|
| 1306 |
+
"loss": 0.1875,
|
| 1307 |
+
"rewards/accuracies": 0.5,
|
| 1308 |
+
"rewards/chosen": -0.07844243943691254,
|
| 1309 |
+
"rewards/margins": 0.04898718744516373,
|
| 1310 |
+
"rewards/rejected": -0.12742963433265686,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": 0.004024127032607794,
|
| 1317 |
+
"logits/rejected": -0.07468675822019577,
|
| 1318 |
+
"logps/chosen": -574.8939208984375,
|
| 1319 |
+
"logps/rejected": -618.0397338867188,
|
| 1320 |
+
"loss": 0.1861,
|
| 1321 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1322 |
+
"rewards/chosen": -0.08176033198833466,
|
| 1323 |
+
"rewards/margins": 0.037909943610429764,
|
| 1324 |
+
"rewards/rejected": -0.11967027187347412,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.19473119514220044,
|
| 1332 |
+
"train_runtime": 7963.8235,
|
| 1333 |
+
"train_samples_per_second": 3.767,
|
| 1334 |
+
"train_steps_per_second": 0.118
|
| 1335 |
+
}
|
| 1336 |
+
],
|
| 1337 |
+
"logging_steps": 10,
|
| 1338 |
+
"max_steps": 937,
|
| 1339 |
+
"num_input_tokens_seen": 0,
|
| 1340 |
+
"num_train_epochs": 1,
|
| 1341 |
+
"save_steps": 100,
|
| 1342 |
+
"total_flos": 0.0,
|
| 1343 |
+
"train_batch_size": 4,
|
| 1344 |
+
"trial_name": null,
|
| 1345 |
+
"trial_params": null
|
| 1346 |
+
}
|