Model save
Browse files- README.md +59 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May21_01-07-02_gpu4-119-5/events.out.tfevents.1716217780.gpu4-119-5.1156251.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1794 -0
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-i0
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-irepo-chatml-v11-i1
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# phi-2-irepo-chatml-v11-i1
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-i0](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-i0) 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: 6
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 24
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
### Framework versions
|
| 54 |
+
|
| 55 |
+
- PEFT 0.7.1
|
| 56 |
+
- Transformers 4.36.2
|
| 57 |
+
- Pytorch 2.1.2+cu121
|
| 58 |
+
- Datasets 2.14.6
|
| 59 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335579632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:735ed2764243ca4b61806622077c78da4686c681f2cd460b310e08f5d9d5ac63
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1874461171746254,
|
| 4 |
+
"train_runtime": 12039.6342,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 2.492,
|
| 7 |
+
"train_steps_per_second": 0.104
|
| 8 |
+
}
|
runs/May21_01-07-02_gpu4-119-5/events.out.tfevents.1716217780.gpu4-119-5.1156251.0
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 sha256:6cf39f9577f1a983ee54498491648a13299e4dd533950a537492181920d9a745
|
| 3 |
+
size 85008
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1874461171746254,
|
| 4 |
+
"train_runtime": 12039.6342,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 2.492,
|
| 7 |
+
"train_steps_per_second": 0.104
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1794 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 4e-08,
|
| 14 |
+
"logits/chosen": 0.17149439454078674,
|
| 15 |
+
"logits/rejected": -0.16577354073524475,
|
| 16 |
+
"logps/chosen": -424.0601806640625,
|
| 17 |
+
"logps/rejected": -451.33026123046875,
|
| 18 |
+
"loss": 0.21,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 28 |
+
"logits/chosen": 0.21744126081466675,
|
| 29 |
+
"logits/rejected": 0.10579843074083328,
|
| 30 |
+
"logps/chosen": -382.20452880859375,
|
| 31 |
+
"logps/rejected": -405.85113525390625,
|
| 32 |
+
"loss": 0.1999,
|
| 33 |
+
"rewards/accuracies": 0.3194444477558136,
|
| 34 |
+
"rewards/chosen": -0.000663464015815407,
|
| 35 |
+
"rewards/margins": 2.6586050807964057e-05,
|
| 36 |
+
"rewards/rejected": -0.0006900500156916678,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 8.000000000000001e-07,
|
| 42 |
+
"logits/chosen": 0.09920214116573334,
|
| 43 |
+
"logits/rejected": 0.17896269261837006,
|
| 44 |
+
"logps/chosen": -424.150390625,
|
| 45 |
+
"logps/rejected": -425.36322021484375,
|
| 46 |
+
"loss": 0.2149,
|
| 47 |
+
"rewards/accuracies": 0.3291666805744171,
|
| 48 |
+
"rewards/chosen": -0.001120259752497077,
|
| 49 |
+
"rewards/margins": -2.1472937078215182e-05,
|
| 50 |
+
"rewards/rejected": -0.0010987869463860989,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 56 |
+
"logits/chosen": 0.10742081701755524,
|
| 57 |
+
"logits/rejected": 0.17089782655239105,
|
| 58 |
+
"logps/chosen": -428.20599365234375,
|
| 59 |
+
"logps/rejected": -377.82623291015625,
|
| 60 |
+
"loss": 0.2248,
|
| 61 |
+
"rewards/accuracies": 0.32083335518836975,
|
| 62 |
+
"rewards/chosen": -0.0012378226965665817,
|
| 63 |
+
"rewards/margins": -4.129592707613483e-05,
|
| 64 |
+
"rewards/rejected": -0.001196526805870235,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 70 |
+
"logits/chosen": 0.06296560913324356,
|
| 71 |
+
"logits/rejected": 0.1074155792593956,
|
| 72 |
+
"logps/chosen": -383.998291015625,
|
| 73 |
+
"logps/rejected": -394.5549621582031,
|
| 74 |
+
"loss": 0.2149,
|
| 75 |
+
"rewards/accuracies": 0.3583333492279053,
|
| 76 |
+
"rewards/chosen": -0.0029038754291832447,
|
| 77 |
+
"rewards/margins": 4.263871960574761e-05,
|
| 78 |
+
"rewards/rejected": -0.002946514170616865,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 84 |
+
"logits/chosen": 0.14813974499702454,
|
| 85 |
+
"logits/rejected": 0.09698332846164703,
|
| 86 |
+
"logps/chosen": -429.5348205566406,
|
| 87 |
+
"logps/rejected": -416.16082763671875,
|
| 88 |
+
"loss": 0.2107,
|
| 89 |
+
"rewards/accuracies": 0.3916666507720947,
|
| 90 |
+
"rewards/chosen": -0.003114475170150399,
|
| 91 |
+
"rewards/margins": 0.00012498181604314595,
|
| 92 |
+
"rewards/rejected": -0.003239457029849291,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 98 |
+
"logits/chosen": 0.07653869688510895,
|
| 99 |
+
"logits/rejected": 0.21269424259662628,
|
| 100 |
+
"logps/chosen": -426.544189453125,
|
| 101 |
+
"logps/rejected": -410.603271484375,
|
| 102 |
+
"loss": 0.2157,
|
| 103 |
+
"rewards/accuracies": 0.3916667103767395,
|
| 104 |
+
"rewards/chosen": -0.003012719564139843,
|
| 105 |
+
"rewards/margins": 4.8593028623145074e-05,
|
| 106 |
+
"rewards/rejected": -0.003061312483623624,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 112 |
+
"logits/chosen": 0.01920640841126442,
|
| 113 |
+
"logits/rejected": 0.16419027745723724,
|
| 114 |
+
"logps/chosen": -390.6888122558594,
|
| 115 |
+
"logps/rejected": -365.8466796875,
|
| 116 |
+
"loss": 0.204,
|
| 117 |
+
"rewards/accuracies": 0.38333332538604736,
|
| 118 |
+
"rewards/chosen": -0.003003176301717758,
|
| 119 |
+
"rewards/margins": 0.00020479671366047114,
|
| 120 |
+
"rewards/rejected": -0.00320797273889184,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06,
|
| 125 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 126 |
+
"logits/chosen": 0.10941372811794281,
|
| 127 |
+
"logits/rejected": 0.16332782804965973,
|
| 128 |
+
"logps/chosen": -412.390625,
|
| 129 |
+
"logps/rejected": -417.4317321777344,
|
| 130 |
+
"loss": 0.2145,
|
| 131 |
+
"rewards/accuracies": 0.4375,
|
| 132 |
+
"rewards/chosen": -0.0038808684330433607,
|
| 133 |
+
"rewards/margins": 0.0004434056463651359,
|
| 134 |
+
"rewards/rejected": -0.004324274603277445,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 140 |
+
"logits/chosen": 0.18084049224853516,
|
| 141 |
+
"logits/rejected": 0.13003312051296234,
|
| 142 |
+
"logps/chosen": -419.4568786621094,
|
| 143 |
+
"logps/rejected": -383.35205078125,
|
| 144 |
+
"loss": 0.2071,
|
| 145 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 146 |
+
"rewards/chosen": -0.003477463498711586,
|
| 147 |
+
"rewards/margins": 0.0005018340307287872,
|
| 148 |
+
"rewards/rejected": -0.003979298286139965,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08,
|
| 153 |
+
"learning_rate": 4.000000000000001e-06,
|
| 154 |
+
"logits/chosen": 0.13773226737976074,
|
| 155 |
+
"logits/rejected": 0.136666402220726,
|
| 156 |
+
"logps/chosen": -423.04364013671875,
|
| 157 |
+
"logps/rejected": -416.84002685546875,
|
| 158 |
+
"loss": 0.199,
|
| 159 |
+
"rewards/accuracies": 0.4333333373069763,
|
| 160 |
+
"rewards/chosen": -0.0012789195170626044,
|
| 161 |
+
"rewards/margins": 0.00046353376819752157,
|
| 162 |
+
"rewards/rejected": -0.0017424530815333128,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09,
|
| 167 |
+
"learning_rate": 4.4e-06,
|
| 168 |
+
"logits/chosen": 0.07242347300052643,
|
| 169 |
+
"logits/rejected": 0.10395532846450806,
|
| 170 |
+
"logps/chosen": -410.901611328125,
|
| 171 |
+
"logps/rejected": -425.29461669921875,
|
| 172 |
+
"loss": 0.2097,
|
| 173 |
+
"rewards/accuracies": 0.5,
|
| 174 |
+
"rewards/chosen": -0.0012211017310619354,
|
| 175 |
+
"rewards/margins": 0.0012917147250846028,
|
| 176 |
+
"rewards/rejected": -0.0025128168053925037,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 4.800000000000001e-06,
|
| 182 |
+
"logits/chosen": 0.16134211421012878,
|
| 183 |
+
"logits/rejected": -0.009699034504592419,
|
| 184 |
+
"logps/chosen": -399.96441650390625,
|
| 185 |
+
"logps/rejected": -396.57672119140625,
|
| 186 |
+
"loss": 0.2075,
|
| 187 |
+
"rewards/accuracies": 0.4958333373069763,
|
| 188 |
+
"rewards/chosen": -0.0006208900013007224,
|
| 189 |
+
"rewards/margins": 0.0016982462257146835,
|
| 190 |
+
"rewards/rejected": -0.002319136168807745,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1,
|
| 195 |
+
"learning_rate": 4.999756310023261e-06,
|
| 196 |
+
"logits/chosen": 0.07792703807353973,
|
| 197 |
+
"logits/rejected": 0.0053740618750452995,
|
| 198 |
+
"logps/chosen": -407.54522705078125,
|
| 199 |
+
"logps/rejected": -386.1396179199219,
|
| 200 |
+
"loss": 0.2103,
|
| 201 |
+
"rewards/accuracies": 0.49166664481163025,
|
| 202 |
+
"rewards/chosen": 0.0015033172676339746,
|
| 203 |
+
"rewards/margins": 0.0024497557897120714,
|
| 204 |
+
"rewards/rejected": -0.0009464388713240623,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.11,
|
| 209 |
+
"learning_rate": 4.997807075247147e-06,
|
| 210 |
+
"logits/chosen": 0.17738033831119537,
|
| 211 |
+
"logits/rejected": 0.11884935200214386,
|
| 212 |
+
"logps/chosen": -432.95916748046875,
|
| 213 |
+
"logps/rejected": -437.46685791015625,
|
| 214 |
+
"loss": 0.2088,
|
| 215 |
+
"rewards/accuracies": 0.5041666626930237,
|
| 216 |
+
"rewards/chosen": 0.008168506436049938,
|
| 217 |
+
"rewards/margins": 0.0032126710284501314,
|
| 218 |
+
"rewards/rejected": 0.0049558356404304504,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 4.993910125649561e-06,
|
| 224 |
+
"logits/chosen": 0.09095987677574158,
|
| 225 |
+
"logits/rejected": 0.21810762584209442,
|
| 226 |
+
"logps/chosen": -403.97509765625,
|
| 227 |
+
"logps/rejected": -398.00567626953125,
|
| 228 |
+
"loss": 0.214,
|
| 229 |
+
"rewards/accuracies": 0.4833332896232605,
|
| 230 |
+
"rewards/chosen": 0.012083831243216991,
|
| 231 |
+
"rewards/margins": 0.002966669388115406,
|
| 232 |
+
"rewards/rejected": 0.009117161855101585,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13,
|
| 237 |
+
"learning_rate": 4.988068499954578e-06,
|
| 238 |
+
"logits/chosen": 0.11167311668395996,
|
| 239 |
+
"logits/rejected": -0.01715979352593422,
|
| 240 |
+
"logps/chosen": -395.1109924316406,
|
| 241 |
+
"logps/rejected": -386.7571105957031,
|
| 242 |
+
"loss": 0.2005,
|
| 243 |
+
"rewards/accuracies": 0.4791666567325592,
|
| 244 |
+
"rewards/chosen": 0.01772935874760151,
|
| 245 |
+
"rewards/margins": 0.005436168517917395,
|
| 246 |
+
"rewards/rejected": 0.012293190695345402,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"learning_rate": 4.980286753286196e-06,
|
| 252 |
+
"logits/chosen": 0.07135671377182007,
|
| 253 |
+
"logits/rejected": 0.004518161062151194,
|
| 254 |
+
"logps/chosen": -381.22509765625,
|
| 255 |
+
"logps/rejected": -369.58880615234375,
|
| 256 |
+
"loss": 0.2085,
|
| 257 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 258 |
+
"rewards/chosen": 0.027819514274597168,
|
| 259 |
+
"rewards/margins": 0.006179440300911665,
|
| 260 |
+
"rewards/rejected": 0.021640075370669365,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14,
|
| 265 |
+
"learning_rate": 4.970570953616383e-06,
|
| 266 |
+
"logits/chosen": 0.03489253669977188,
|
| 267 |
+
"logits/rejected": 0.12006882578134537,
|
| 268 |
+
"logps/chosen": -377.1296081542969,
|
| 269 |
+
"logps/rejected": -362.04364013671875,
|
| 270 |
+
"loss": 0.2018,
|
| 271 |
+
"rewards/accuracies": 0.5166667103767395,
|
| 272 |
+
"rewards/chosen": 0.029645437374711037,
|
| 273 |
+
"rewards/margins": 0.008070086129009724,
|
| 274 |
+
"rewards/rejected": 0.02157535031437874,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15,
|
| 279 |
+
"learning_rate": 4.958928677033465e-06,
|
| 280 |
+
"logits/chosen": 0.01938822492957115,
|
| 281 |
+
"logits/rejected": 0.04349769651889801,
|
| 282 |
+
"logps/chosen": -394.98101806640625,
|
| 283 |
+
"logps/rejected": -428.86248779296875,
|
| 284 |
+
"loss": 0.208,
|
| 285 |
+
"rewards/accuracies": 0.5,
|
| 286 |
+
"rewards/chosen": 0.020193781703710556,
|
| 287 |
+
"rewards/margins": 0.008541513234376907,
|
| 288 |
+
"rewards/rejected": 0.011652267538011074,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16,
|
| 293 |
+
"learning_rate": 4.9453690018345144e-06,
|
| 294 |
+
"logits/chosen": -0.11528314650058746,
|
| 295 |
+
"logits/rejected": 0.08821746706962585,
|
| 296 |
+
"logps/chosen": -394.2080078125,
|
| 297 |
+
"logps/rejected": -403.65496826171875,
|
| 298 |
+
"loss": 0.1946,
|
| 299 |
+
"rewards/accuracies": 0.5250000357627869,
|
| 300 |
+
"rewards/chosen": 0.020861472934484482,
|
| 301 |
+
"rewards/margins": 0.01827095076441765,
|
| 302 |
+
"rewards/rejected": 0.0025905228685587645,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 4.9299025014463665e-06,
|
| 308 |
+
"logits/chosen": -0.08552906662225723,
|
| 309 |
+
"logits/rejected": 0.031030725687742233,
|
| 310 |
+
"logps/chosen": -383.574462890625,
|
| 311 |
+
"logps/rejected": -404.0837707519531,
|
| 312 |
+
"loss": 0.1909,
|
| 313 |
+
"rewards/accuracies": 0.47083336114883423,
|
| 314 |
+
"rewards/chosen": 0.01809662953019142,
|
| 315 |
+
"rewards/margins": 0.014171933755278587,
|
| 316 |
+
"rewards/rejected": 0.0039246962405741215,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"learning_rate": 4.912541236180779e-06,
|
| 322 |
+
"logits/chosen": -0.13254012167453766,
|
| 323 |
+
"logits/rejected": -0.06545063108205795,
|
| 324 |
+
"logps/chosen": -332.7752380371094,
|
| 325 |
+
"logps/rejected": -348.6072082519531,
|
| 326 |
+
"loss": 0.1975,
|
| 327 |
+
"rewards/accuracies": 0.44583338499069214,
|
| 328 |
+
"rewards/chosen": 0.0345706008374691,
|
| 329 |
+
"rewards/margins": 0.018852438777685165,
|
| 330 |
+
"rewards/rejected": 0.015718165785074234,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.18,
|
| 335 |
+
"learning_rate": 4.893298743830168e-06,
|
| 336 |
+
"logits/chosen": -0.09530626982450485,
|
| 337 |
+
"logits/rejected": -0.10254266113042831,
|
| 338 |
+
"logps/chosen": -398.1355895996094,
|
| 339 |
+
"logps/rejected": -425.45172119140625,
|
| 340 |
+
"loss": 0.1885,
|
| 341 |
+
"rewards/accuracies": 0.47083336114883423,
|
| 342 |
+
"rewards/chosen": 0.012728950008749962,
|
| 343 |
+
"rewards/margins": 0.029127534478902817,
|
| 344 |
+
"rewards/rejected": -0.016398586332798004,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.19,
|
| 349 |
+
"learning_rate": 4.8721900291112415e-06,
|
| 350 |
+
"logits/chosen": -0.13877639174461365,
|
| 351 |
+
"logits/rejected": 0.013827897608280182,
|
| 352 |
+
"logps/chosen": -396.7447204589844,
|
| 353 |
+
"logps/rejected": -418.518798828125,
|
| 354 |
+
"loss": 0.1898,
|
| 355 |
+
"rewards/accuracies": 0.5333333611488342,
|
| 356 |
+
"rewards/chosen": -0.002779316157102585,
|
| 357 |
+
"rewards/margins": 0.028926661238074303,
|
| 358 |
+
"rewards/rejected": -0.03170597925782204,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2,
|
| 363 |
+
"learning_rate": 4.849231551964771e-06,
|
| 364 |
+
"logits/chosen": -0.09128137677907944,
|
| 365 |
+
"logits/rejected": -0.05126717686653137,
|
| 366 |
+
"logps/chosen": -404.491943359375,
|
| 367 |
+
"logps/rejected": -454.119873046875,
|
| 368 |
+
"loss": 0.1884,
|
| 369 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 370 |
+
"rewards/chosen": -0.019060546532273293,
|
| 371 |
+
"rewards/margins": 0.036740098148584366,
|
| 372 |
+
"rewards/rejected": -0.05580064654350281,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21,
|
| 377 |
+
"learning_rate": 4.824441214720629e-06,
|
| 378 |
+
"logits/chosen": -0.11080489307641983,
|
| 379 |
+
"logits/rejected": -0.14405983686447144,
|
| 380 |
+
"logps/chosen": -494.0188903808594,
|
| 381 |
+
"logps/rejected": -519.1729736328125,
|
| 382 |
+
"loss": 0.2014,
|
| 383 |
+
"rewards/accuracies": 0.5250000357627869,
|
| 384 |
+
"rewards/chosen": -0.0692259818315506,
|
| 385 |
+
"rewards/margins": 0.04139824956655502,
|
| 386 |
+
"rewards/rejected": -0.11062423884868622,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 4.7978383481380865e-06,
|
| 392 |
+
"logits/chosen": -0.12256069481372833,
|
| 393 |
+
"logits/rejected": -0.13387584686279297,
|
| 394 |
+
"logps/chosen": -487.1686096191406,
|
| 395 |
+
"logps/rejected": -525.7955322265625,
|
| 396 |
+
"loss": 0.2103,
|
| 397 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 398 |
+
"rewards/chosen": -0.09114581346511841,
|
| 399 |
+
"rewards/margins": 0.04267682135105133,
|
| 400 |
+
"rewards/rejected": -0.13382264971733093,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.22,
|
| 405 |
+
"learning_rate": 4.769443696332272e-06,
|
| 406 |
+
"logits/chosen": -0.049383699893951416,
|
| 407 |
+
"logits/rejected": -0.16224342584609985,
|
| 408 |
+
"logps/chosen": -455.2054748535156,
|
| 409 |
+
"logps/rejected": -494.6611328125,
|
| 410 |
+
"loss": 0.1946,
|
| 411 |
+
"rewards/accuracies": 0.429166704416275,
|
| 412 |
+
"rewards/chosen": -0.08516400307416916,
|
| 413 |
+
"rewards/margins": 0.03522291034460068,
|
| 414 |
+
"rewards/rejected": -0.12038691341876984,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.23,
|
| 419 |
+
"learning_rate": 4.7392794005985324e-06,
|
| 420 |
+
"logits/chosen": -0.08826161921024323,
|
| 421 |
+
"logits/rejected": -0.05565328150987625,
|
| 422 |
+
"logps/chosen": -510.9239196777344,
|
| 423 |
+
"logps/rejected": -519.4769897460938,
|
| 424 |
+
"loss": 0.202,
|
| 425 |
+
"rewards/accuracies": 0.4750000536441803,
|
| 426 |
+
"rewards/chosen": -0.10056551545858383,
|
| 427 |
+
"rewards/margins": 0.028566282242536545,
|
| 428 |
+
"rewards/rejected": -0.12913179397583008,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24,
|
| 433 |
+
"learning_rate": 4.707368982147318e-06,
|
| 434 |
+
"logits/chosen": 0.010274168103933334,
|
| 435 |
+
"logits/rejected": -0.10608565807342529,
|
| 436 |
+
"logps/chosen": -440.32464599609375,
|
| 437 |
+
"logps/rejected": -487.58209228515625,
|
| 438 |
+
"loss": 0.1839,
|
| 439 |
+
"rewards/accuracies": 0.4750000536441803,
|
| 440 |
+
"rewards/chosen": -0.052764929831027985,
|
| 441 |
+
"rewards/margins": 0.04310880973935127,
|
| 442 |
+
"rewards/rejected": -0.09587373584508896,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.25,
|
| 447 |
+
"learning_rate": 4.673737323763048e-06,
|
| 448 |
+
"logits/chosen": -0.016120150685310364,
|
| 449 |
+
"logits/rejected": 0.003306228667497635,
|
| 450 |
+
"logps/chosen": -387.26629638671875,
|
| 451 |
+
"logps/rejected": -432.75018310546875,
|
| 452 |
+
"loss": 0.1978,
|
| 453 |
+
"rewards/accuracies": 0.44166669249534607,
|
| 454 |
+
"rewards/chosen": -0.039925262331962585,
|
| 455 |
+
"rewards/margins": 0.03133027255535126,
|
| 456 |
+
"rewards/rejected": -0.07125553488731384,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.26,
|
| 461 |
+
"learning_rate": 4.638410650401267e-06,
|
| 462 |
+
"logits/chosen": -0.036097295582294464,
|
| 463 |
+
"logits/rejected": -0.040274590253829956,
|
| 464 |
+
"logps/chosen": -436.0054626464844,
|
| 465 |
+
"logps/rejected": -477.3866271972656,
|
| 466 |
+
"loss": 0.1853,
|
| 467 |
+
"rewards/accuracies": 0.49166664481163025,
|
| 468 |
+
"rewards/chosen": -0.04764013737440109,
|
| 469 |
+
"rewards/margins": 0.02985115721821785,
|
| 470 |
+
"rewards/rejected": -0.07749129831790924,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.26,
|
| 475 |
+
"learning_rate": 4.601416508739211e-06,
|
| 476 |
+
"logits/chosen": -0.0325358584523201,
|
| 477 |
+
"logits/rejected": -0.036110930144786835,
|
| 478 |
+
"logps/chosen": -475.7208557128906,
|
| 479 |
+
"logps/rejected": -515.5665283203125,
|
| 480 |
+
"loss": 0.1944,
|
| 481 |
+
"rewards/accuracies": 0.5208333730697632,
|
| 482 |
+
"rewards/chosen": -0.04646621271967888,
|
| 483 |
+
"rewards/margins": 0.04523799195885658,
|
| 484 |
+
"rewards/rejected": -0.09170420467853546,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.27,
|
| 489 |
+
"learning_rate": 4.562783745695738e-06,
|
| 490 |
+
"logits/chosen": -0.04594831541180611,
|
| 491 |
+
"logits/rejected": -0.03698522225022316,
|
| 492 |
+
"logps/chosen": -496.4822692871094,
|
| 493 |
+
"logps/rejected": -489.32391357421875,
|
| 494 |
+
"loss": 0.2003,
|
| 495 |
+
"rewards/accuracies": 0.47083336114883423,
|
| 496 |
+
"rewards/chosen": -0.05407736450433731,
|
| 497 |
+
"rewards/margins": 0.03637322038412094,
|
| 498 |
+
"rewards/rejected": -0.09045058488845825,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.28,
|
| 503 |
+
"learning_rate": 4.522542485937369e-06,
|
| 504 |
+
"logits/chosen": -0.1583801805973053,
|
| 505 |
+
"logits/rejected": -0.03529781848192215,
|
| 506 |
+
"logps/chosen": -460.81793212890625,
|
| 507 |
+
"logps/rejected": -519.77587890625,
|
| 508 |
+
"loss": 0.1752,
|
| 509 |
+
"rewards/accuracies": 0.5291666984558105,
|
| 510 |
+
"rewards/chosen": -0.03841938078403473,
|
| 511 |
+
"rewards/margins": 0.0512566938996315,
|
| 512 |
+
"rewards/rejected": -0.08967608213424683,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.29,
|
| 517 |
+
"learning_rate": 4.4807241083879774e-06,
|
| 518 |
+
"logits/chosen": -0.20257849991321564,
|
| 519 |
+
"logits/rejected": -0.1146155446767807,
|
| 520 |
+
"logps/chosen": -442.28594970703125,
|
| 521 |
+
"logps/rejected": -458.53173828125,
|
| 522 |
+
"loss": 0.1895,
|
| 523 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 524 |
+
"rewards/chosen": -0.04586230590939522,
|
| 525 |
+
"rewards/margins": 0.03675750643014908,
|
| 526 |
+
"rewards/rejected": -0.0826198160648346,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3,
|
| 531 |
+
"learning_rate": 4.437361221760449e-06,
|
| 532 |
+
"logits/chosen": -0.11894889175891876,
|
| 533 |
+
"logits/rejected": -0.08775348216295242,
|
| 534 |
+
"logps/chosen": -456.0023498535156,
|
| 535 |
+
"logps/rejected": -466.5443420410156,
|
| 536 |
+
"loss": 0.1868,
|
| 537 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 538 |
+
"rewards/chosen": -0.050740133970975876,
|
| 539 |
+
"rewards/margins": 0.039192140102386475,
|
| 540 |
+
"rewards/rejected": -0.08993227034807205,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3,
|
| 545 |
+
"learning_rate": 4.3924876391293915e-06,
|
| 546 |
+
"logits/chosen": -0.18518304824829102,
|
| 547 |
+
"logits/rejected": -0.1563677340745926,
|
| 548 |
+
"logps/chosen": -445.9903259277344,
|
| 549 |
+
"logps/rejected": -468.9036560058594,
|
| 550 |
+
"loss": 0.1779,
|
| 551 |
+
"rewards/accuracies": 0.5000000596046448,
|
| 552 |
+
"rewards/chosen": -0.047802653163671494,
|
| 553 |
+
"rewards/margins": 0.03556705266237259,
|
| 554 |
+
"rewards/rejected": -0.08336970955133438,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.31,
|
| 559 |
+
"learning_rate": 4.346138351564711e-06,
|
| 560 |
+
"logits/chosen": -0.17687319219112396,
|
| 561 |
+
"logits/rejected": -0.16852393746376038,
|
| 562 |
+
"logps/chosen": -413.527587890625,
|
| 563 |
+
"logps/rejected": -469.2893981933594,
|
| 564 |
+
"loss": 0.1849,
|
| 565 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 566 |
+
"rewards/chosen": -0.047930918633937836,
|
| 567 |
+
"rewards/margins": 0.05219081789255142,
|
| 568 |
+
"rewards/rejected": -0.10012175142765045,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.32,
|
| 573 |
+
"learning_rate": 4.2983495008466285e-06,
|
| 574 |
+
"logits/chosen": -0.20533815026283264,
|
| 575 |
+
"logits/rejected": -0.20098014175891876,
|
| 576 |
+
"logps/chosen": -412.97698974609375,
|
| 577 |
+
"logps/rejected": -473.263671875,
|
| 578 |
+
"loss": 0.1845,
|
| 579 |
+
"rewards/accuracies": 0.4958333373069763,
|
| 580 |
+
"rewards/chosen": -0.04717981815338135,
|
| 581 |
+
"rewards/margins": 0.05400770157575607,
|
| 582 |
+
"rewards/rejected": -0.10118752717971802,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.33,
|
| 587 |
+
"learning_rate": 4.249158351283414e-06,
|
| 588 |
+
"logits/chosen": -0.20028965175151825,
|
| 589 |
+
"logits/rejected": -0.11055328696966171,
|
| 590 |
+
"logps/chosen": -464.6874084472656,
|
| 591 |
+
"logps/rejected": -541.6143798828125,
|
| 592 |
+
"loss": 0.1788,
|
| 593 |
+
"rewards/accuracies": 0.512499988079071,
|
| 594 |
+
"rewards/chosen": -0.05910419300198555,
|
| 595 |
+
"rewards/margins": 0.060402512550354004,
|
| 596 |
+
"rewards/rejected": -0.11950669437646866,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34,
|
| 601 |
+
"learning_rate": 4.198603260653792e-06,
|
| 602 |
+
"logits/chosen": -0.23082371056079865,
|
| 603 |
+
"logits/rejected": -0.12578482925891876,
|
| 604 |
+
"logps/chosen": -482.4796447753906,
|
| 605 |
+
"logps/rejected": -553.0191650390625,
|
| 606 |
+
"loss": 0.1709,
|
| 607 |
+
"rewards/accuracies": 0.5166667103767395,
|
| 608 |
+
"rewards/chosen": -0.058818310499191284,
|
| 609 |
+
"rewards/margins": 0.06956759095191956,
|
| 610 |
+
"rewards/rejected": -0.12838590145111084,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.34,
|
| 615 |
+
"learning_rate": 4.146723650296701e-06,
|
| 616 |
+
"logits/chosen": -0.1750180423259735,
|
| 617 |
+
"logits/rejected": -0.11045924574136734,
|
| 618 |
+
"logps/chosen": -482.70904541015625,
|
| 619 |
+
"logps/rejected": -499.7896423339844,
|
| 620 |
+
"loss": 0.187,
|
| 621 |
+
"rewards/accuracies": 0.46666663885116577,
|
| 622 |
+
"rewards/chosen": -0.0458199642598629,
|
| 623 |
+
"rewards/margins": 0.04604263976216316,
|
| 624 |
+
"rewards/rejected": -0.09186260402202606,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.35,
|
| 629 |
+
"learning_rate": 4.093559974371725e-06,
|
| 630 |
+
"logits/chosen": -0.2370443344116211,
|
| 631 |
+
"logits/rejected": -0.14606305956840515,
|
| 632 |
+
"logps/chosen": -397.68548583984375,
|
| 633 |
+
"logps/rejected": -440.5757751464844,
|
| 634 |
+
"loss": 0.1907,
|
| 635 |
+
"rewards/accuracies": 0.47083336114883423,
|
| 636 |
+
"rewards/chosen": -0.02382233552634716,
|
| 637 |
+
"rewards/margins": 0.04170426353812218,
|
| 638 |
+
"rewards/rejected": -0.06552660465240479,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.36,
|
| 643 |
+
"learning_rate": 4.039153688314146e-06,
|
| 644 |
+
"logits/chosen": -0.19962234795093536,
|
| 645 |
+
"logits/rejected": -0.18455585837364197,
|
| 646 |
+
"logps/chosen": -433.9319763183594,
|
| 647 |
+
"logps/rejected": -486.72247314453125,
|
| 648 |
+
"loss": 0.1899,
|
| 649 |
+
"rewards/accuracies": 0.5333333611488342,
|
| 650 |
+
"rewards/chosen": -0.005404153373092413,
|
| 651 |
+
"rewards/margins": 0.050141505897045135,
|
| 652 |
+
"rewards/rejected": -0.05554566532373428,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.37,
|
| 657 |
+
"learning_rate": 3.983547216509254e-06,
|
| 658 |
+
"logits/chosen": -0.23652057349681854,
|
| 659 |
+
"logits/rejected": -0.13747069239616394,
|
| 660 |
+
"logps/chosen": -385.99859619140625,
|
| 661 |
+
"logps/rejected": -418.61859130859375,
|
| 662 |
+
"loss": 0.1786,
|
| 663 |
+
"rewards/accuracies": 0.47083336114883423,
|
| 664 |
+
"rewards/chosen": -0.011283977888524532,
|
| 665 |
+
"rewards/margins": 0.043274398893117905,
|
| 666 |
+
"rewards/rejected": -0.05455837398767471,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38,
|
| 671 |
+
"learning_rate": 3.92678391921108e-06,
|
| 672 |
+
"logits/chosen": -0.1722879260778427,
|
| 673 |
+
"logits/rejected": -0.2078588902950287,
|
| 674 |
+
"logps/chosen": -425.4927673339844,
|
| 675 |
+
"logps/rejected": -452.87347412109375,
|
| 676 |
+
"loss": 0.1813,
|
| 677 |
+
"rewards/accuracies": 0.5041666626930237,
|
| 678 |
+
"rewards/chosen": -0.0162376556545496,
|
| 679 |
+
"rewards/margins": 0.04304374381899834,
|
| 680 |
+
"rewards/rejected": -0.059281397610902786,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.38,
|
| 685 |
+
"learning_rate": 3.868908058731376e-06,
|
| 686 |
+
"logits/chosen": -0.21139149367809296,
|
| 687 |
+
"logits/rejected": -0.17750591039657593,
|
| 688 |
+
"logps/chosen": -478.3169860839844,
|
| 689 |
+
"logps/rejected": -513.8565063476562,
|
| 690 |
+
"loss": 0.1842,
|
| 691 |
+
"rewards/accuracies": 0.5333333611488342,
|
| 692 |
+
"rewards/chosen": -0.023320624604821205,
|
| 693 |
+
"rewards/margins": 0.044868770986795425,
|
| 694 |
+
"rewards/rejected": -0.06818939745426178,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.39,
|
| 699 |
+
"learning_rate": 3.8099647649251984e-06,
|
| 700 |
+
"logits/chosen": -0.2609555125236511,
|
| 701 |
+
"logits/rejected": -0.17367315292358398,
|
| 702 |
+
"logps/chosen": -418.36279296875,
|
| 703 |
+
"logps/rejected": -473.0401306152344,
|
| 704 |
+
"loss": 0.1892,
|
| 705 |
+
"rewards/accuracies": 0.4958333373069763,
|
| 706 |
+
"rewards/chosen": -0.032408542931079865,
|
| 707 |
+
"rewards/margins": 0.04911263287067413,
|
| 708 |
+
"rewards/rejected": -0.0815211683511734,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4,
|
| 713 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 714 |
+
"logits/chosen": -0.2730502486228943,
|
| 715 |
+
"logits/rejected": -0.2116207778453827,
|
| 716 |
+
"logps/chosen": -475.0166015625,
|
| 717 |
+
"logps/rejected": -491.03948974609375,
|
| 718 |
+
"loss": 0.1987,
|
| 719 |
+
"rewards/accuracies": 0.4791666567325592,
|
| 720 |
+
"rewards/chosen": -0.04057503864169121,
|
| 721 |
+
"rewards/margins": 0.039973508566617966,
|
| 722 |
+
"rewards/rejected": -0.08054854720830917,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.41,
|
| 727 |
+
"learning_rate": 3.689060522675689e-06,
|
| 728 |
+
"logits/chosen": -0.2958037555217743,
|
| 729 |
+
"logits/rejected": -0.16685570776462555,
|
| 730 |
+
"logps/chosen": -446.9232482910156,
|
| 731 |
+
"logps/rejected": -492.4410095214844,
|
| 732 |
+
"loss": 0.182,
|
| 733 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 734 |
+
"rewards/chosen": -0.04383234679698944,
|
| 735 |
+
"rewards/margins": 0.04704504832625389,
|
| 736 |
+
"rewards/rejected": -0.09087739884853363,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.42,
|
| 741 |
+
"learning_rate": 3.627193851723577e-06,
|
| 742 |
+
"logits/chosen": -0.21801650524139404,
|
| 743 |
+
"logits/rejected": -0.23087890446186066,
|
| 744 |
+
"logps/chosen": -416.719482421875,
|
| 745 |
+
"logps/rejected": -477.15155029296875,
|
| 746 |
+
"loss": 0.1968,
|
| 747 |
+
"rewards/accuracies": 0.4791666567325592,
|
| 748 |
+
"rewards/chosen": -0.041071660816669464,
|
| 749 |
+
"rewards/margins": 0.04972352460026741,
|
| 750 |
+
"rewards/rejected": -0.09079518169164658,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.42,
|
| 755 |
+
"learning_rate": 3.564448228912682e-06,
|
| 756 |
+
"logits/chosen": -0.22313952445983887,
|
| 757 |
+
"logits/rejected": -0.2395196259021759,
|
| 758 |
+
"logps/chosen": -435.31829833984375,
|
| 759 |
+
"logps/rejected": -500.8714294433594,
|
| 760 |
+
"loss": 0.1991,
|
| 761 |
+
"rewards/accuracies": 0.5083333253860474,
|
| 762 |
+
"rewards/chosen": -0.050644002854824066,
|
| 763 |
+
"rewards/margins": 0.04440879076719284,
|
| 764 |
+
"rewards/rejected": -0.0950528010725975,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.43,
|
| 769 |
+
"learning_rate": 3.5008725813922383e-06,
|
| 770 |
+
"logits/chosen": -0.29003390669822693,
|
| 771 |
+
"logits/rejected": -0.15861546993255615,
|
| 772 |
+
"logps/chosen": -495.62060546875,
|
| 773 |
+
"logps/rejected": -535.9207763671875,
|
| 774 |
+
"loss": 0.1652,
|
| 775 |
+
"rewards/accuracies": 0.5666667222976685,
|
| 776 |
+
"rewards/chosen": -0.047018229961395264,
|
| 777 |
+
"rewards/margins": 0.04982719197869301,
|
| 778 |
+
"rewards/rejected": -0.09684541821479797,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.44,
|
| 783 |
+
"learning_rate": 3.436516483539781e-06,
|
| 784 |
+
"logits/chosen": -0.28255754709243774,
|
| 785 |
+
"logits/rejected": -0.2905382513999939,
|
| 786 |
+
"logps/chosen": -474.9947204589844,
|
| 787 |
+
"logps/rejected": -492.84130859375,
|
| 788 |
+
"loss": 0.1953,
|
| 789 |
+
"rewards/accuracies": 0.48750004172325134,
|
| 790 |
+
"rewards/chosen": -0.06080613657832146,
|
| 791 |
+
"rewards/margins": 0.035242706537246704,
|
| 792 |
+
"rewards/rejected": -0.09604884684085846,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.45,
|
| 797 |
+
"learning_rate": 3.3714301183045382e-06,
|
| 798 |
+
"logits/chosen": -0.2140432894229889,
|
| 799 |
+
"logits/rejected": -0.30546998977661133,
|
| 800 |
+
"logps/chosen": -459.7528381347656,
|
| 801 |
+
"logps/rejected": -547.1843872070312,
|
| 802 |
+
"loss": 0.1525,
|
| 803 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 804 |
+
"rewards/chosen": -0.058339886367321014,
|
| 805 |
+
"rewards/margins": 0.07008499652147293,
|
| 806 |
+
"rewards/rejected": -0.12842489778995514,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.46,
|
| 811 |
+
"learning_rate": 3.3056642380762783e-06,
|
| 812 |
+
"logits/chosen": -0.20786988735198975,
|
| 813 |
+
"logits/rejected": -0.30285245180130005,
|
| 814 |
+
"logps/chosen": -435.9219665527344,
|
| 815 |
+
"logps/rejected": -506.14996337890625,
|
| 816 |
+
"loss": 0.1704,
|
| 817 |
+
"rewards/accuracies": 0.49583330750465393,
|
| 818 |
+
"rewards/chosen": -0.06140541285276413,
|
| 819 |
+
"rewards/margins": 0.0633297935128212,
|
| 820 |
+
"rewards/rejected": -0.12473521381616592,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.46,
|
| 825 |
+
"learning_rate": 3.2392701251101172e-06,
|
| 826 |
+
"logits/chosen": -0.2695538401603699,
|
| 827 |
+
"logits/rejected": -0.2578602135181427,
|
| 828 |
+
"logps/chosen": -507.4090881347656,
|
| 829 |
+
"logps/rejected": -573.2657470703125,
|
| 830 |
+
"loss": 0.1713,
|
| 831 |
+
"rewards/accuracies": 0.5583332777023315,
|
| 832 |
+
"rewards/chosen": -0.07743930071592331,
|
| 833 |
+
"rewards/margins": 0.0685843974351883,
|
| 834 |
+
"rewards/rejected": -0.1460237056016922,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.47,
|
| 839 |
+
"learning_rate": 3.1722995515381644e-06,
|
| 840 |
+
"logits/chosen": -0.2915573716163635,
|
| 841 |
+
"logits/rejected": -0.2425670623779297,
|
| 842 |
+
"logps/chosen": -462.32220458984375,
|
| 843 |
+
"logps/rejected": -534.523193359375,
|
| 844 |
+
"loss": 0.1851,
|
| 845 |
+
"rewards/accuracies": 0.5041666626930237,
|
| 846 |
+
"rewards/chosen": -0.07182817161083221,
|
| 847 |
+
"rewards/margins": 0.06546822935342789,
|
| 848 |
+
"rewards/rejected": -0.1372964084148407,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.48,
|
| 853 |
+
"learning_rate": 3.1048047389991693e-06,
|
| 854 |
+
"logits/chosen": -0.2364952117204666,
|
| 855 |
+
"logits/rejected": -0.29197296500205994,
|
| 856 |
+
"logps/chosen": -456.0204162597656,
|
| 857 |
+
"logps/rejected": -503.23822021484375,
|
| 858 |
+
"loss": 0.1863,
|
| 859 |
+
"rewards/accuracies": 0.48750004172325134,
|
| 860 |
+
"rewards/chosen": -0.06296292692422867,
|
| 861 |
+
"rewards/margins": 0.05075465515255928,
|
| 862 |
+
"rewards/rejected": -0.11371759325265884,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.49,
|
| 867 |
+
"learning_rate": 3.0368383179176584e-06,
|
| 868 |
+
"logits/chosen": -0.3178825378417969,
|
| 869 |
+
"logits/rejected": -0.17681264877319336,
|
| 870 |
+
"logps/chosen": -445.4483947753906,
|
| 871 |
+
"logps/rejected": -500.03387451171875,
|
| 872 |
+
"loss": 0.1853,
|
| 873 |
+
"rewards/accuracies": 0.4791666567325592,
|
| 874 |
+
"rewards/chosen": -0.05490962415933609,
|
| 875 |
+
"rewards/margins": 0.047073423862457275,
|
| 876 |
+
"rewards/rejected": -0.10198304802179337,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5,
|
| 881 |
+
"learning_rate": 2.9684532864643123e-06,
|
| 882 |
+
"logits/chosen": -0.3539500832557678,
|
| 883 |
+
"logits/rejected": -0.20667648315429688,
|
| 884 |
+
"logps/chosen": -466.39764404296875,
|
| 885 |
+
"logps/rejected": -501.822021484375,
|
| 886 |
+
"loss": 0.1844,
|
| 887 |
+
"rewards/accuracies": 0.4833333492279053,
|
| 888 |
+
"rewards/chosen": -0.05339791625738144,
|
| 889 |
+
"rewards/margins": 0.053281139582395554,
|
| 890 |
+
"rewards/rejected": -0.1066790446639061,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5,
|
| 895 |
+
"learning_rate": 2.8997029692295875e-06,
|
| 896 |
+
"logits/chosen": -0.3101775050163269,
|
| 897 |
+
"logits/rejected": -0.2914181053638458,
|
| 898 |
+
"logps/chosen": -427.52032470703125,
|
| 899 |
+
"logps/rejected": -466.09197998046875,
|
| 900 |
+
"loss": 0.1837,
|
| 901 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 902 |
+
"rewards/chosen": -0.048539165407419205,
|
| 903 |
+
"rewards/margins": 0.052506644278764725,
|
| 904 |
+
"rewards/rejected": -0.10104580223560333,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.51,
|
| 909 |
+
"learning_rate": 2.8306409756428067e-06,
|
| 910 |
+
"logits/chosen": -0.317528635263443,
|
| 911 |
+
"logits/rejected": -0.18300285935401917,
|
| 912 |
+
"logps/chosen": -482.93939208984375,
|
| 913 |
+
"logps/rejected": -531.2368774414062,
|
| 914 |
+
"loss": 0.1641,
|
| 915 |
+
"rewards/accuracies": 0.550000011920929,
|
| 916 |
+
"rewards/chosen": -0.041467417031526566,
|
| 917 |
+
"rewards/margins": 0.07688767462968826,
|
| 918 |
+
"rewards/rejected": -0.11835509538650513,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.52,
|
| 923 |
+
"learning_rate": 2.761321158169134e-06,
|
| 924 |
+
"logits/chosen": -0.23212091624736786,
|
| 925 |
+
"logits/rejected": -0.28510648012161255,
|
| 926 |
+
"logps/chosen": -484.9613342285156,
|
| 927 |
+
"logps/rejected": -542.4539184570312,
|
| 928 |
+
"loss": 0.1745,
|
| 929 |
+
"rewards/accuracies": 0.5250000357627869,
|
| 930 |
+
"rewards/chosen": -0.039610255509614944,
|
| 931 |
+
"rewards/margins": 0.061538826674222946,
|
| 932 |
+
"rewards/rejected": -0.10114908218383789,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.53,
|
| 937 |
+
"learning_rate": 2.6917975703170466e-06,
|
| 938 |
+
"logits/chosen": -0.27057233452796936,
|
| 939 |
+
"logits/rejected": -0.24964137375354767,
|
| 940 |
+
"logps/chosen": -427.0650329589844,
|
| 941 |
+
"logps/rejected": -500.9590759277344,
|
| 942 |
+
"loss": 0.1835,
|
| 943 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 944 |
+
"rewards/chosen": -0.0389983169734478,
|
| 945 |
+
"rewards/margins": 0.07033900916576385,
|
| 946 |
+
"rewards/rejected": -0.10933732986450195,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.54,
|
| 951 |
+
"learning_rate": 2.6221244244890336e-06,
|
| 952 |
+
"logits/chosen": -0.2637156546115875,
|
| 953 |
+
"logits/rejected": -0.2788185477256775,
|
| 954 |
+
"logps/chosen": -450.2159118652344,
|
| 955 |
+
"logps/rejected": -507.42962646484375,
|
| 956 |
+
"loss": 0.1696,
|
| 957 |
+
"rewards/accuracies": 0.4958333969116211,
|
| 958 |
+
"rewards/chosen": -0.0435161329805851,
|
| 959 |
+
"rewards/margins": 0.0677158460021019,
|
| 960 |
+
"rewards/rejected": -0.1112319827079773,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.54,
|
| 965 |
+
"learning_rate": 2.5523560497083927e-06,
|
| 966 |
+
"logits/chosen": -0.23590517044067383,
|
| 967 |
+
"logits/rejected": -0.30847400426864624,
|
| 968 |
+
"logps/chosen": -388.68463134765625,
|
| 969 |
+
"logps/rejected": -449.8109436035156,
|
| 970 |
+
"loss": 0.1846,
|
| 971 |
+
"rewards/accuracies": 0.4958333373069763,
|
| 972 |
+
"rewards/chosen": -0.033804431557655334,
|
| 973 |
+
"rewards/margins": 0.06065298244357109,
|
| 974 |
+
"rewards/rejected": -0.09445741027593613,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.55,
|
| 979 |
+
"learning_rate": 2.482546849255096e-06,
|
| 980 |
+
"logits/chosen": -0.310326486825943,
|
| 981 |
+
"logits/rejected": -0.2718106508255005,
|
| 982 |
+
"logps/chosen": -451.0816345214844,
|
| 983 |
+
"logps/rejected": -527.0636596679688,
|
| 984 |
+
"loss": 0.18,
|
| 985 |
+
"rewards/accuracies": 0.5125000476837158,
|
| 986 |
+
"rewards/chosen": -0.04315061867237091,
|
| 987 |
+
"rewards/margins": 0.06889710575342178,
|
| 988 |
+
"rewards/rejected": -0.1120477169752121,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.56,
|
| 993 |
+
"learning_rate": 2.4127512582437486e-06,
|
| 994 |
+
"logits/chosen": -0.2296207696199417,
|
| 995 |
+
"logits/rejected": -0.2563227415084839,
|
| 996 |
+
"logps/chosen": -489.15380859375,
|
| 997 |
+
"logps/rejected": -535.2841186523438,
|
| 998 |
+
"loss": 0.1847,
|
| 999 |
+
"rewards/accuracies": 0.5333333611488342,
|
| 1000 |
+
"rewards/chosen": -0.04005949944257736,
|
| 1001 |
+
"rewards/margins": 0.063002809882164,
|
| 1002 |
+
"rewards/rejected": -0.10306230932474136,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.57,
|
| 1007 |
+
"learning_rate": 2.3430237011767166e-06,
|
| 1008 |
+
"logits/chosen": -0.28292739391326904,
|
| 1009 |
+
"logits/rejected": -0.22382238507270813,
|
| 1010 |
+
"logps/chosen": -402.1965637207031,
|
| 1011 |
+
"logps/rejected": -477.5860900878906,
|
| 1012 |
+
"loss": 0.1755,
|
| 1013 |
+
"rewards/accuracies": 0.5041667222976685,
|
| 1014 |
+
"rewards/chosen": -0.018582064658403397,
|
| 1015 |
+
"rewards/margins": 0.07370585948228836,
|
| 1016 |
+
"rewards/rejected": -0.09228792786598206,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.58,
|
| 1021 |
+
"learning_rate": 2.2734185495055503e-06,
|
| 1022 |
+
"logits/chosen": -0.286498486995697,
|
| 1023 |
+
"logits/rejected": -0.22381773591041565,
|
| 1024 |
+
"logps/chosen": -419.038330078125,
|
| 1025 |
+
"logps/rejected": -441.9375915527344,
|
| 1026 |
+
"loss": 0.1932,
|
| 1027 |
+
"rewards/accuracies": 0.44583335518836975,
|
| 1028 |
+
"rewards/chosen": -0.022441592067480087,
|
| 1029 |
+
"rewards/margins": 0.03786554932594299,
|
| 1030 |
+
"rewards/rejected": -0.06030714511871338,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.58,
|
| 1035 |
+
"learning_rate": 2.2039900792337477e-06,
|
| 1036 |
+
"logits/chosen": -0.22549033164978027,
|
| 1037 |
+
"logits/rejected": -0.2243853360414505,
|
| 1038 |
+
"logps/chosen": -447.57635498046875,
|
| 1039 |
+
"logps/rejected": -464.91082763671875,
|
| 1040 |
+
"loss": 0.1868,
|
| 1041 |
+
"rewards/accuracies": 0.5291666388511658,
|
| 1042 |
+
"rewards/chosen": -0.014703089371323586,
|
| 1043 |
+
"rewards/margins": 0.04347188025712967,
|
| 1044 |
+
"rewards/rejected": -0.058174967765808105,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.59,
|
| 1049 |
+
"learning_rate": 2.134792428593971e-06,
|
| 1050 |
+
"logits/chosen": -0.26262083649635315,
|
| 1051 |
+
"logits/rejected": -0.23271727561950684,
|
| 1052 |
+
"logps/chosen": -452.77880859375,
|
| 1053 |
+
"logps/rejected": -475.3125915527344,
|
| 1054 |
+
"loss": 0.1925,
|
| 1055 |
+
"rewards/accuracies": 0.5,
|
| 1056 |
+
"rewards/chosen": -0.025184612721204758,
|
| 1057 |
+
"rewards/margins": 0.04363705962896347,
|
| 1058 |
+
"rewards/rejected": -0.06882167607545853,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6,
|
| 1063 |
+
"learning_rate": 2.0658795558326745e-06,
|
| 1064 |
+
"logits/chosen": -0.2798984944820404,
|
| 1065 |
+
"logits/rejected": -0.1053474098443985,
|
| 1066 |
+
"logps/chosen": -432.2371520996094,
|
| 1067 |
+
"logps/rejected": -437.374755859375,
|
| 1068 |
+
"loss": 0.183,
|
| 1069 |
+
"rewards/accuracies": 0.4833333492279053,
|
| 1070 |
+
"rewards/chosen": -0.0092130983248353,
|
| 1071 |
+
"rewards/margins": 0.04416029527783394,
|
| 1072 |
+
"rewards/rejected": -0.053373388946056366,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.61,
|
| 1077 |
+
"learning_rate": 1.997305197135089e-06,
|
| 1078 |
+
"logits/chosen": -0.24332702159881592,
|
| 1079 |
+
"logits/rejected": -0.24699708819389343,
|
| 1080 |
+
"logps/chosen": -413.81317138671875,
|
| 1081 |
+
"logps/rejected": -436.09185791015625,
|
| 1082 |
+
"loss": 0.1861,
|
| 1083 |
+
"rewards/accuracies": 0.4833333492279053,
|
| 1084 |
+
"rewards/chosen": -0.018954753875732422,
|
| 1085 |
+
"rewards/margins": 0.046722229570150375,
|
| 1086 |
+
"rewards/rejected": -0.0656769797205925,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.62,
|
| 1091 |
+
"learning_rate": 1.9291228247233607e-06,
|
| 1092 |
+
"logits/chosen": -0.19670598208904266,
|
| 1093 |
+
"logits/rejected": -0.14346536993980408,
|
| 1094 |
+
"logps/chosen": -426.93316650390625,
|
| 1095 |
+
"logps/rejected": -422.44830322265625,
|
| 1096 |
+
"loss": 0.1813,
|
| 1097 |
+
"rewards/accuracies": 0.4833332896232605,
|
| 1098 |
+
"rewards/chosen": -0.01260639913380146,
|
| 1099 |
+
"rewards/margins": 0.04483729228377342,
|
| 1100 |
+
"rewards/rejected": -0.05744368955492973,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.62,
|
| 1105 |
+
"learning_rate": 1.8613856051605242e-06,
|
| 1106 |
+
"logits/chosen": -0.19106583297252655,
|
| 1107 |
+
"logits/rejected": -0.2591181695461273,
|
| 1108 |
+
"logps/chosen": -396.3172912597656,
|
| 1109 |
+
"logps/rejected": -458.3994140625,
|
| 1110 |
+
"loss": 0.1657,
|
| 1111 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1112 |
+
"rewards/chosen": -0.011414697393774986,
|
| 1113 |
+
"rewards/margins": 0.06354735046625137,
|
| 1114 |
+
"rewards/rejected": -0.07496203482151031,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.63,
|
| 1119 |
+
"learning_rate": 1.7941463578928088e-06,
|
| 1120 |
+
"logits/chosen": -0.20239433646202087,
|
| 1121 |
+
"logits/rejected": -0.18643388152122498,
|
| 1122 |
+
"logps/chosen": -386.0264587402344,
|
| 1123 |
+
"logps/rejected": -415.656494140625,
|
| 1124 |
+
"loss": 0.1868,
|
| 1125 |
+
"rewards/accuracies": 0.44583335518836975,
|
| 1126 |
+
"rewards/chosen": -0.01508850883692503,
|
| 1127 |
+
"rewards/margins": 0.044246602803468704,
|
| 1128 |
+
"rewards/rejected": -0.05933511257171631,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.64,
|
| 1133 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 1134 |
+
"logits/chosen": -0.2549183666706085,
|
| 1135 |
+
"logits/rejected": -0.13016203045845032,
|
| 1136 |
+
"logps/chosen": -463.55816650390625,
|
| 1137 |
+
"logps/rejected": -502.923828125,
|
| 1138 |
+
"loss": 0.1769,
|
| 1139 |
+
"rewards/accuracies": 0.5583332777023315,
|
| 1140 |
+
"rewards/chosen": -0.025710273534059525,
|
| 1141 |
+
"rewards/margins": 0.05553792044520378,
|
| 1142 |
+
"rewards/rejected": -0.0812481939792633,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.65,
|
| 1147 |
+
"learning_rate": 1.661371075624363e-06,
|
| 1148 |
+
"logits/chosen": -0.2786555886268616,
|
| 1149 |
+
"logits/rejected": -0.19162516295909882,
|
| 1150 |
+
"logps/chosen": -460.2269592285156,
|
| 1151 |
+
"logps/rejected": -480.3688049316406,
|
| 1152 |
+
"loss": 0.1761,
|
| 1153 |
+
"rewards/accuracies": 0.5166667103767395,
|
| 1154 |
+
"rewards/chosen": -0.025559108704328537,
|
| 1155 |
+
"rewards/margins": 0.051572393625974655,
|
| 1156 |
+
"rewards/rejected": -0.0771314948797226,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.66,
|
| 1161 |
+
"learning_rate": 1.5959385747947697e-06,
|
| 1162 |
+
"logits/chosen": -0.16187801957130432,
|
| 1163 |
+
"logits/rejected": -0.15380509197711945,
|
| 1164 |
+
"logps/chosen": -437.10205078125,
|
| 1165 |
+
"logps/rejected": -482.42718505859375,
|
| 1166 |
+
"loss": 0.1891,
|
| 1167 |
+
"rewards/accuracies": 0.4958333969116211,
|
| 1168 |
+
"rewards/chosen": -0.02434079721570015,
|
| 1169 |
+
"rewards/margins": 0.04448997974395752,
|
| 1170 |
+
"rewards/rejected": -0.06883077323436737,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.66,
|
| 1175 |
+
"learning_rate": 1.5312110338697427e-06,
|
| 1176 |
+
"logits/chosen": -0.12476430833339691,
|
| 1177 |
+
"logits/rejected": -0.2756340801715851,
|
| 1178 |
+
"logps/chosen": -413.1475524902344,
|
| 1179 |
+
"logps/rejected": -469.5107421875,
|
| 1180 |
+
"loss": 0.1796,
|
| 1181 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1182 |
+
"rewards/chosen": -0.024911707267165184,
|
| 1183 |
+
"rewards/margins": 0.06037444993853569,
|
| 1184 |
+
"rewards/rejected": -0.08528616279363632,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.67,
|
| 1189 |
+
"learning_rate": 1.467238925438646e-06,
|
| 1190 |
+
"logits/chosen": -0.2615768313407898,
|
| 1191 |
+
"logits/rejected": -0.20825617015361786,
|
| 1192 |
+
"logps/chosen": -413.496826171875,
|
| 1193 |
+
"logps/rejected": -466.8892517089844,
|
| 1194 |
+
"loss": 0.1772,
|
| 1195 |
+
"rewards/accuracies": 0.5166667103767395,
|
| 1196 |
+
"rewards/chosen": -0.015650052577257156,
|
| 1197 |
+
"rewards/margins": 0.05704290792346001,
|
| 1198 |
+
"rewards/rejected": -0.07269296050071716,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.68,
|
| 1203 |
+
"learning_rate": 1.4040721330273063e-06,
|
| 1204 |
+
"logits/chosen": -0.23080775141716003,
|
| 1205 |
+
"logits/rejected": -0.07844565808773041,
|
| 1206 |
+
"logps/chosen": -432.4065856933594,
|
| 1207 |
+
"logps/rejected": -493.73876953125,
|
| 1208 |
+
"loss": 0.1733,
|
| 1209 |
+
"rewards/accuracies": 0.5208333134651184,
|
| 1210 |
+
"rewards/chosen": -0.02299593947827816,
|
| 1211 |
+
"rewards/margins": 0.06412651389837265,
|
| 1212 |
+
"rewards/rejected": -0.08712244778871536,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.69,
|
| 1217 |
+
"learning_rate": 1.3417599122003464e-06,
|
| 1218 |
+
"logits/chosen": -0.18598750233650208,
|
| 1219 |
+
"logits/rejected": -0.20719997584819794,
|
| 1220 |
+
"logps/chosen": -423.7872619628906,
|
| 1221 |
+
"logps/rejected": -479.3990173339844,
|
| 1222 |
+
"loss": 0.1958,
|
| 1223 |
+
"rewards/accuracies": 0.4791666567325592,
|
| 1224 |
+
"rewards/chosen": -0.027820762246847153,
|
| 1225 |
+
"rewards/margins": 0.05425436049699783,
|
| 1226 |
+
"rewards/rejected": -0.08207512646913528,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7,
|
| 1231 |
+
"learning_rate": 1.280350852153168e-06,
|
| 1232 |
+
"logits/chosen": -0.2046211063861847,
|
| 1233 |
+
"logits/rejected": -0.23867718875408173,
|
| 1234 |
+
"logps/chosen": -432.0369567871094,
|
| 1235 |
+
"logps/rejected": -490.05548095703125,
|
| 1236 |
+
"loss": 0.1985,
|
| 1237 |
+
"rewards/accuracies": 0.4833333492279053,
|
| 1238 |
+
"rewards/chosen": -0.0314149484038353,
|
| 1239 |
+
"rewards/margins": 0.05088344216346741,
|
| 1240 |
+
"rewards/rejected": -0.0822983831167221,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7,
|
| 1245 |
+
"learning_rate": 1.2198928378235717e-06,
|
| 1246 |
+
"logits/chosen": -0.2688402533531189,
|
| 1247 |
+
"logits/rejected": -0.20974984765052795,
|
| 1248 |
+
"logps/chosen": -416.24322509765625,
|
| 1249 |
+
"logps/rejected": -463.6009216308594,
|
| 1250 |
+
"loss": 0.1971,
|
| 1251 |
+
"rewards/accuracies": 0.46250003576278687,
|
| 1252 |
+
"rewards/chosen": -0.029970809817314148,
|
| 1253 |
+
"rewards/margins": 0.04484293609857559,
|
| 1254 |
+
"rewards/rejected": -0.07481373846530914,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.71,
|
| 1259 |
+
"learning_rate": 1.160433012552508e-06,
|
| 1260 |
+
"logits/chosen": -0.2599441409111023,
|
| 1261 |
+
"logits/rejected": -0.23637132346630096,
|
| 1262 |
+
"logps/chosen": -417.55908203125,
|
| 1263 |
+
"logps/rejected": -505.0204162597656,
|
| 1264 |
+
"loss": 0.1608,
|
| 1265 |
+
"rewards/accuracies": 0.5333333611488342,
|
| 1266 |
+
"rewards/chosen": -0.008947738446295261,
|
| 1267 |
+
"rewards/margins": 0.07473009079694748,
|
| 1268 |
+
"rewards/rejected": -0.08367783576250076,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.72,
|
| 1273 |
+
"learning_rate": 1.1020177413231334e-06,
|
| 1274 |
+
"logits/chosen": -0.2652960419654846,
|
| 1275 |
+
"logits/rejected": -0.25931379199028015,
|
| 1276 |
+
"logps/chosen": -435.1573791503906,
|
| 1277 |
+
"logps/rejected": -473.2171325683594,
|
| 1278 |
+
"loss": 0.1658,
|
| 1279 |
+
"rewards/accuracies": 0.5333333015441895,
|
| 1280 |
+
"rewards/chosen": -0.011026141233742237,
|
| 1281 |
+
"rewards/margins": 0.06725867092609406,
|
| 1282 |
+
"rewards/rejected": -0.07828481495380402,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.73,
|
| 1287 |
+
"learning_rate": 1.0446925746067768e-06,
|
| 1288 |
+
"logits/chosen": -0.28469547629356384,
|
| 1289 |
+
"logits/rejected": -0.21729762852191925,
|
| 1290 |
+
"logps/chosen": -415.32012939453125,
|
| 1291 |
+
"logps/rejected": -454.0088806152344,
|
| 1292 |
+
"loss": 0.1959,
|
| 1293 |
+
"rewards/accuracies": 0.49166664481163025,
|
| 1294 |
+
"rewards/chosen": -0.01757933758199215,
|
| 1295 |
+
"rewards/margins": 0.04614214226603508,
|
| 1296 |
+
"rewards/rejected": -0.06372148543596268,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.74,
|
| 1301 |
+
"learning_rate": 9.88502212844063e-07,
|
| 1302 |
+
"logits/chosen": -0.18305090069770813,
|
| 1303 |
+
"logits/rejected": -0.28139248490333557,
|
| 1304 |
+
"logps/chosen": -462.94598388671875,
|
| 1305 |
+
"logps/rejected": -518.9043579101562,
|
| 1306 |
+
"loss": 0.1791,
|
| 1307 |
+
"rewards/accuracies": 0.5416666865348816,
|
| 1308 |
+
"rewards/chosen": -0.022413870319724083,
|
| 1309 |
+
"rewards/margins": 0.06975697726011276,
|
| 1310 |
+
"rewards/rejected": -0.092170849442482,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.74,
|
| 1315 |
+
"learning_rate": 9.334904715888496e-07,
|
| 1316 |
+
"logits/chosen": -0.2571960687637329,
|
| 1317 |
+
"logits/rejected": -0.1717800498008728,
|
| 1318 |
+
"logps/chosen": -448.0375061035156,
|
| 1319 |
+
"logps/rejected": -492.38494873046875,
|
| 1320 |
+
"loss": 0.1906,
|
| 1321 |
+
"rewards/accuracies": 0.48333340883255005,
|
| 1322 |
+
"rewards/chosen": -0.01861201599240303,
|
| 1323 |
+
"rewards/margins": 0.05696520954370499,
|
| 1324 |
+
"rewards/rejected": -0.07557722926139832,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.75,
|
| 1329 |
+
"learning_rate": 8.797002473421729e-07,
|
| 1330 |
+
"logits/chosen": -0.24043762683868408,
|
| 1331 |
+
"logits/rejected": -0.22050480544567108,
|
| 1332 |
+
"logps/chosen": -460.51629638671875,
|
| 1333 |
+
"logps/rejected": -494.3642578125,
|
| 1334 |
+
"loss": 0.1907,
|
| 1335 |
+
"rewards/accuracies": 0.5333333611488342,
|
| 1336 |
+
"rewards/chosen": -0.024757737293839455,
|
| 1337 |
+
"rewards/margins": 0.05093444511294365,
|
| 1338 |
+
"rewards/rejected": -0.07569219172000885,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.76,
|
| 1343 |
+
"learning_rate": 8.271734841028553e-07,
|
| 1344 |
+
"logits/chosen": -0.2750247120857239,
|
| 1345 |
+
"logits/rejected": -0.1990630328655243,
|
| 1346 |
+
"logps/chosen": -414.51177978515625,
|
| 1347 |
+
"logps/rejected": -439.66583251953125,
|
| 1348 |
+
"loss": 0.1875,
|
| 1349 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1350 |
+
"rewards/chosen": -0.030453836545348167,
|
| 1351 |
+
"rewards/margins": 0.041512638330459595,
|
| 1352 |
+
"rewards/rejected": -0.07196646928787231,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.77,
|
| 1357 |
+
"learning_rate": 7.759511406608255e-07,
|
| 1358 |
+
"logits/chosen": -0.10888031870126724,
|
| 1359 |
+
"logits/rejected": -0.2525996267795563,
|
| 1360 |
+
"logps/chosen": -417.1622009277344,
|
| 1361 |
+
"logps/rejected": -480.26812744140625,
|
| 1362 |
+
"loss": 0.1814,
|
| 1363 |
+
"rewards/accuracies": 0.5291666984558105,
|
| 1364 |
+
"rewards/chosen": -0.019586481153964996,
|
| 1365 |
+
"rewards/margins": 0.0609549880027771,
|
| 1366 |
+
"rewards/rejected": -0.08054147660732269,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.78,
|
| 1371 |
+
"learning_rate": 7.260731586586983e-07,
|
| 1372 |
+
"logits/chosen": -0.28881603479385376,
|
| 1373 |
+
"logits/rejected": -0.22749415040016174,
|
| 1374 |
+
"logps/chosen": -418.9693298339844,
|
| 1375 |
+
"logps/rejected": -488.30487060546875,
|
| 1376 |
+
"loss": 0.1695,
|
| 1377 |
+
"rewards/accuracies": 0.5458333492279053,
|
| 1378 |
+
"rewards/chosen": -0.025732625275850296,
|
| 1379 |
+
"rewards/margins": 0.06428026407957077,
|
| 1380 |
+
"rewards/rejected": -0.09001289308071136,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.78,
|
| 1385 |
+
"learning_rate": 6.775784314464717e-07,
|
| 1386 |
+
"logits/chosen": -0.2233542948961258,
|
| 1387 |
+
"logits/rejected": -0.21398404240608215,
|
| 1388 |
+
"logps/chosen": -427.0870056152344,
|
| 1389 |
+
"logps/rejected": -473.38299560546875,
|
| 1390 |
+
"loss": 0.1746,
|
| 1391 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 1392 |
+
"rewards/chosen": -0.015530099160969257,
|
| 1393 |
+
"rewards/margins": 0.059838373214006424,
|
| 1394 |
+
"rewards/rejected": -0.0753684714436531,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.79,
|
| 1399 |
+
"learning_rate": 6.305047737536707e-07,
|
| 1400 |
+
"logits/chosen": -0.2794179916381836,
|
| 1401 |
+
"logits/rejected": -0.1606103777885437,
|
| 1402 |
+
"logps/chosen": -443.2103576660156,
|
| 1403 |
+
"logps/rejected": -475.12835693359375,
|
| 1404 |
+
"loss": 0.1745,
|
| 1405 |
+
"rewards/accuracies": 0.5083333253860474,
|
| 1406 |
+
"rewards/chosen": -0.02874937281012535,
|
| 1407 |
+
"rewards/margins": 0.04828978329896927,
|
| 1408 |
+
"rewards/rejected": -0.07703914493322372,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8,
|
| 1413 |
+
"learning_rate": 5.848888922025553e-07,
|
| 1414 |
+
"logits/chosen": -0.2493915855884552,
|
| 1415 |
+
"logits/rejected": -0.24869143962860107,
|
| 1416 |
+
"logps/chosen": -401.45263671875,
|
| 1417 |
+
"logps/rejected": -445.24774169921875,
|
| 1418 |
+
"loss": 0.1821,
|
| 1419 |
+
"rewards/accuracies": 0.4791666865348816,
|
| 1420 |
+
"rewards/chosen": -0.0232832133769989,
|
| 1421 |
+
"rewards/margins": 0.05199895054101944,
|
| 1422 |
+
"rewards/rejected": -0.07528215646743774,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.81,
|
| 1427 |
+
"learning_rate": 5.407663566854008e-07,
|
| 1428 |
+
"logits/chosen": -0.2700728476047516,
|
| 1429 |
+
"logits/rejected": -0.2861558794975281,
|
| 1430 |
+
"logps/chosen": -420.72088623046875,
|
| 1431 |
+
"logps/rejected": -501.34991455078125,
|
| 1432 |
+
"loss": 0.1614,
|
| 1433 |
+
"rewards/accuracies": 0.5541666746139526,
|
| 1434 |
+
"rewards/chosen": -0.029055217280983925,
|
| 1435 |
+
"rewards/margins": 0.06994070112705231,
|
| 1436 |
+
"rewards/rejected": -0.09899591654539108,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.82,
|
| 1441 |
+
"learning_rate": 4.981715726281666e-07,
|
| 1442 |
+
"logits/chosen": -0.17120757699012756,
|
| 1443 |
+
"logits/rejected": -0.2849826216697693,
|
| 1444 |
+
"logps/chosen": -431.4073181152344,
|
| 1445 |
+
"logps/rejected": -485.0538024902344,
|
| 1446 |
+
"loss": 0.1867,
|
| 1447 |
+
"rewards/accuracies": 0.5208333730697632,
|
| 1448 |
+
"rewards/chosen": -0.028083154931664467,
|
| 1449 |
+
"rewards/margins": 0.050588030368089676,
|
| 1450 |
+
"rewards/rejected": -0.0786711797118187,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.82,
|
| 1455 |
+
"learning_rate": 4.5713775416217884e-07,
|
| 1456 |
+
"logits/chosen": -0.3271382451057434,
|
| 1457 |
+
"logits/rejected": -0.24611802399158478,
|
| 1458 |
+
"logps/chosen": -447.4208068847656,
|
| 1459 |
+
"logps/rejected": -512.2904052734375,
|
| 1460 |
+
"loss": 0.1849,
|
| 1461 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1462 |
+
"rewards/chosen": -0.02718830667436123,
|
| 1463 |
+
"rewards/margins": 0.05544273182749748,
|
| 1464 |
+
"rewards/rejected": -0.08263102918863297,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.83,
|
| 1469 |
+
"learning_rate": 4.1769689822475147e-07,
|
| 1470 |
+
"logits/chosen": -0.24327817559242249,
|
| 1471 |
+
"logits/rejected": -0.24398300051689148,
|
| 1472 |
+
"logps/chosen": -418.857177734375,
|
| 1473 |
+
"logps/rejected": -455.48052978515625,
|
| 1474 |
+
"loss": 0.1898,
|
| 1475 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1476 |
+
"rewards/chosen": -0.026202013716101646,
|
| 1477 |
+
"rewards/margins": 0.04488568380475044,
|
| 1478 |
+
"rewards/rejected": -0.07108769565820694,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.84,
|
| 1483 |
+
"learning_rate": 3.798797596089351e-07,
|
| 1484 |
+
"logits/chosen": -0.22220292687416077,
|
| 1485 |
+
"logits/rejected": -0.1325482428073883,
|
| 1486 |
+
"logps/chosen": -440.03704833984375,
|
| 1487 |
+
"logps/rejected": -495.2511291503906,
|
| 1488 |
+
"loss": 0.1807,
|
| 1489 |
+
"rewards/accuracies": 0.5041666626930237,
|
| 1490 |
+
"rewards/chosen": -0.028768355026841164,
|
| 1491 |
+
"rewards/margins": 0.05239064618945122,
|
| 1492 |
+
"rewards/rejected": -0.08115899562835693,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.85,
|
| 1497 |
+
"learning_rate": 3.4371582698185636e-07,
|
| 1498 |
+
"logits/chosen": -0.2665029764175415,
|
| 1499 |
+
"logits/rejected": -0.26157745718955994,
|
| 1500 |
+
"logps/chosen": -386.71441650390625,
|
| 1501 |
+
"logps/rejected": -432.8797302246094,
|
| 1502 |
+
"loss": 0.1877,
|
| 1503 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1504 |
+
"rewards/chosen": -0.021984888240695,
|
| 1505 |
+
"rewards/margins": 0.048461947590112686,
|
| 1506 |
+
"rewards/rejected": -0.07044683396816254,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.86,
|
| 1511 |
+
"learning_rate": 3.092332998903416e-07,
|
| 1512 |
+
"logits/chosen": -0.25679802894592285,
|
| 1513 |
+
"logits/rejected": -0.22036735713481903,
|
| 1514 |
+
"logps/chosen": -460.5780334472656,
|
| 1515 |
+
"logps/rejected": -521.6238403320312,
|
| 1516 |
+
"loss": 0.177,
|
| 1517 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1518 |
+
"rewards/chosen": -0.020292013883590698,
|
| 1519 |
+
"rewards/margins": 0.06953073292970657,
|
| 1520 |
+
"rewards/rejected": -0.08982274681329727,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.86,
|
| 1525 |
+
"learning_rate": 2.764590667717562e-07,
|
| 1526 |
+
"logits/chosen": -0.20977798104286194,
|
| 1527 |
+
"logits/rejected": -0.25232791900634766,
|
| 1528 |
+
"logps/chosen": -441.75091552734375,
|
| 1529 |
+
"logps/rejected": -503.1982421875,
|
| 1530 |
+
"loss": 0.1922,
|
| 1531 |
+
"rewards/accuracies": 0.5041667222976685,
|
| 1532 |
+
"rewards/chosen": -0.026740949600934982,
|
| 1533 |
+
"rewards/margins": 0.05636667460203171,
|
| 1534 |
+
"rewards/rejected": -0.08310762792825699,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.87,
|
| 1539 |
+
"learning_rate": 2.454186839872158e-07,
|
| 1540 |
+
"logits/chosen": -0.22725868225097656,
|
| 1541 |
+
"logits/rejected": -0.2418319284915924,
|
| 1542 |
+
"logps/chosen": -385.9988098144531,
|
| 1543 |
+
"logps/rejected": -447.5536193847656,
|
| 1544 |
+
"loss": 0.1749,
|
| 1545 |
+
"rewards/accuracies": 0.4583333134651184,
|
| 1546 |
+
"rewards/chosen": -0.014233797788619995,
|
| 1547 |
+
"rewards/margins": 0.05856531113386154,
|
| 1548 |
+
"rewards/rejected": -0.07279910892248154,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.88,
|
| 1553 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 1554 |
+
"logits/chosen": -0.23666933178901672,
|
| 1555 |
+
"logits/rejected": -0.2799440324306488,
|
| 1556 |
+
"logps/chosen": -413.6375427246094,
|
| 1557 |
+
"logps/rejected": -459.60101318359375,
|
| 1558 |
+
"loss": 0.1858,
|
| 1559 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1560 |
+
"rewards/chosen": -0.019571740180253983,
|
| 1561 |
+
"rewards/margins": 0.051161814481019974,
|
| 1562 |
+
"rewards/rejected": -0.07073356211185455,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.89,
|
| 1567 |
+
"learning_rate": 1.8863491596921745e-07,
|
| 1568 |
+
"logits/chosen": -0.25514012575149536,
|
| 1569 |
+
"logits/rejected": -0.26672855019569397,
|
| 1570 |
+
"logps/chosen": -429.20318603515625,
|
| 1571 |
+
"logps/rejected": -485.3815002441406,
|
| 1572 |
+
"loss": 0.1865,
|
| 1573 |
+
"rewards/accuracies": 0.5083333253860474,
|
| 1574 |
+
"rewards/chosen": -0.02379278652369976,
|
| 1575 |
+
"rewards/margins": 0.0564563162624836,
|
| 1576 |
+
"rewards/rejected": -0.08024909347295761,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9,
|
| 1581 |
+
"learning_rate": 1.629358090099639e-07,
|
| 1582 |
+
"logits/chosen": -0.2413201630115509,
|
| 1583 |
+
"logits/rejected": -0.30872708559036255,
|
| 1584 |
+
"logps/chosen": -447.03985595703125,
|
| 1585 |
+
"logps/rejected": -493.2216796875,
|
| 1586 |
+
"loss": 0.189,
|
| 1587 |
+
"rewards/accuracies": 0.4791666567325592,
|
| 1588 |
+
"rewards/chosen": -0.030030418187379837,
|
| 1589 |
+
"rewards/margins": 0.05704699829220772,
|
| 1590 |
+
"rewards/rejected": -0.08707742393016815,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9,
|
| 1595 |
+
"learning_rate": 1.3905907440629752e-07,
|
| 1596 |
+
"logits/chosen": -0.23792843520641327,
|
| 1597 |
+
"logits/rejected": -0.28303149342536926,
|
| 1598 |
+
"logps/chosen": -416.78448486328125,
|
| 1599 |
+
"logps/rejected": -434.672119140625,
|
| 1600 |
+
"loss": 0.1939,
|
| 1601 |
+
"rewards/accuracies": 0.4791666865348816,
|
| 1602 |
+
"rewards/chosen": -0.018583226948976517,
|
| 1603 |
+
"rewards/margins": 0.041258666664361954,
|
| 1604 |
+
"rewards/rejected": -0.05984188988804817,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.91,
|
| 1609 |
+
"learning_rate": 1.1702333051763271e-07,
|
| 1610 |
+
"logits/chosen": -0.22025823593139648,
|
| 1611 |
+
"logits/rejected": -0.23834295570850372,
|
| 1612 |
+
"logps/chosen": -389.4822692871094,
|
| 1613 |
+
"logps/rejected": -454.0912170410156,
|
| 1614 |
+
"loss": 0.1826,
|
| 1615 |
+
"rewards/accuracies": 0.4791666865348816,
|
| 1616 |
+
"rewards/chosen": -0.019084876403212547,
|
| 1617 |
+
"rewards/margins": 0.052420567721128464,
|
| 1618 |
+
"rewards/rejected": -0.07150544971227646,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.92,
|
| 1623 |
+
"learning_rate": 9.684576015420277e-08,
|
| 1624 |
+
"logits/chosen": -0.2792247235774994,
|
| 1625 |
+
"logits/rejected": -0.1931079924106598,
|
| 1626 |
+
"logps/chosen": -450.61297607421875,
|
| 1627 |
+
"logps/rejected": -475.45947265625,
|
| 1628 |
+
"loss": 0.1857,
|
| 1629 |
+
"rewards/accuracies": 0.46666669845581055,
|
| 1630 |
+
"rewards/chosen": -0.018364811316132545,
|
| 1631 |
+
"rewards/margins": 0.049478866159915924,
|
| 1632 |
+
"rewards/rejected": -0.06784368306398392,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.93,
|
| 1637 |
+
"learning_rate": 7.854209717842231e-08,
|
| 1638 |
+
"logits/chosen": -0.2361956536769867,
|
| 1639 |
+
"logits/rejected": -0.16988393664360046,
|
| 1640 |
+
"logps/chosen": -463.72625732421875,
|
| 1641 |
+
"logps/rejected": -532.1114501953125,
|
| 1642 |
+
"loss": 0.1735,
|
| 1643 |
+
"rewards/accuracies": 0.5750000476837158,
|
| 1644 |
+
"rewards/chosen": -0.01867097057402134,
|
| 1645 |
+
"rewards/margins": 0.07356119900941849,
|
| 1646 |
+
"rewards/rejected": -0.09223215281963348,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.94,
|
| 1651 |
+
"learning_rate": 6.212661423609184e-08,
|
| 1652 |
+
"logits/chosen": -0.2650465965270996,
|
| 1653 |
+
"logits/rejected": -0.22043271362781525,
|
| 1654 |
+
"logps/chosen": -476.1746520996094,
|
| 1655 |
+
"logps/rejected": -500.8211364746094,
|
| 1656 |
+
"loss": 0.1848,
|
| 1657 |
+
"rewards/accuracies": 0.491666704416275,
|
| 1658 |
+
"rewards/chosen": -0.02679665945470333,
|
| 1659 |
+
"rewards/margins": 0.05153702571988106,
|
| 1660 |
+
"rewards/rejected": -0.07833368331193924,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.94,
|
| 1665 |
+
"learning_rate": 4.761211162702117e-08,
|
| 1666 |
+
"logits/chosen": -0.2697955369949341,
|
| 1667 |
+
"logits/rejected": -0.2639797329902649,
|
| 1668 |
+
"logps/chosen": -401.6107177734375,
|
| 1669 |
+
"logps/rejected": -457.95703125,
|
| 1670 |
+
"loss": 0.1775,
|
| 1671 |
+
"rewards/accuracies": 0.4833333492279053,
|
| 1672 |
+
"rewards/chosen": -0.02222241833806038,
|
| 1673 |
+
"rewards/margins": 0.05034973472356796,
|
| 1674 |
+
"rewards/rejected": -0.07257215678691864,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.95,
|
| 1679 |
+
"learning_rate": 3.5009907323737826e-08,
|
| 1680 |
+
"logits/chosen": -0.2754846215248108,
|
| 1681 |
+
"logits/rejected": -0.3097229599952698,
|
| 1682 |
+
"logps/chosen": -415.70867919921875,
|
| 1683 |
+
"logps/rejected": -478.73663330078125,
|
| 1684 |
+
"loss": 0.1718,
|
| 1685 |
+
"rewards/accuracies": 0.5291666984558105,
|
| 1686 |
+
"rewards/chosen": -0.013669279403984547,
|
| 1687 |
+
"rewards/margins": 0.07036744058132172,
|
| 1688 |
+
"rewards/rejected": -0.08403672277927399,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.96,
|
| 1693 |
+
"learning_rate": 2.4329828146074096e-08,
|
| 1694 |
+
"logits/chosen": -0.2891579866409302,
|
| 1695 |
+
"logits/rejected": -0.19230952858924866,
|
| 1696 |
+
"logps/chosen": -454.9552307128906,
|
| 1697 |
+
"logps/rejected": -495.06488037109375,
|
| 1698 |
+
"loss": 0.1764,
|
| 1699 |
+
"rewards/accuracies": 0.5708333849906921,
|
| 1700 |
+
"rewards/chosen": -0.016126099973917007,
|
| 1701 |
+
"rewards/margins": 0.06828036159276962,
|
| 1702 |
+
"rewards/rejected": -0.08440648019313812,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.97,
|
| 1707 |
+
"learning_rate": 1.5580202098509078e-08,
|
| 1708 |
+
"logits/chosen": -0.29824376106262207,
|
| 1709 |
+
"logits/rejected": -0.22227320075035095,
|
| 1710 |
+
"logps/chosen": -399.3383483886719,
|
| 1711 |
+
"logps/rejected": -465.268310546875,
|
| 1712 |
+
"loss": 0.1686,
|
| 1713 |
+
"rewards/accuracies": 0.5041666626930237,
|
| 1714 |
+
"rewards/chosen": -0.010598058812320232,
|
| 1715 |
+
"rewards/margins": 0.06828632950782776,
|
| 1716 |
+
"rewards/rejected": -0.07888438552618027,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.98,
|
| 1721 |
+
"learning_rate": 8.767851876239075e-09,
|
| 1722 |
+
"logits/chosen": -0.25601503252983093,
|
| 1723 |
+
"logits/rejected": -0.28030115365982056,
|
| 1724 |
+
"logps/chosen": -452.5179138183594,
|
| 1725 |
+
"logps/rejected": -499.35125732421875,
|
| 1726 |
+
"loss": 0.1759,
|
| 1727 |
+
"rewards/accuracies": 0.5500000715255737,
|
| 1728 |
+
"rewards/chosen": -0.017482977360486984,
|
| 1729 |
+
"rewards/margins": 0.05968954414129257,
|
| 1730 |
+
"rewards/rejected": -0.07717252522706985,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.98,
|
| 1735 |
+
"learning_rate": 3.8980895450474455e-09,
|
| 1736 |
+
"logits/chosen": -0.24264974892139435,
|
| 1737 |
+
"logits/rejected": -0.2742842137813568,
|
| 1738 |
+
"logps/chosen": -439.875244140625,
|
| 1739 |
+
"logps/rejected": -479.13873291015625,
|
| 1740 |
+
"loss": 0.1792,
|
| 1741 |
+
"rewards/accuracies": 0.5333333015441895,
|
| 1742 |
+
"rewards/chosen": -0.020408231765031815,
|
| 1743 |
+
"rewards/margins": 0.05712126940488815,
|
| 1744 |
+
"rewards/rejected": -0.07752950489521027,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.99,
|
| 1749 |
+
"learning_rate": 9.747123991141193e-10,
|
| 1750 |
+
"logits/chosen": -0.25368720293045044,
|
| 1751 |
+
"logits/rejected": -0.23606958985328674,
|
| 1752 |
+
"logps/chosen": -377.1168212890625,
|
| 1753 |
+
"logps/rejected": -435.25732421875,
|
| 1754 |
+
"loss": 0.1724,
|
| 1755 |
+
"rewards/accuracies": 0.4916667342185974,
|
| 1756 |
+
"rewards/chosen": -0.018287640064954758,
|
| 1757 |
+
"rewards/margins": 0.055953748524188995,
|
| 1758 |
+
"rewards/rejected": -0.07424138486385345,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.0,
|
| 1763 |
+
"learning_rate": 0.0,
|
| 1764 |
+
"logits/chosen": -0.2323763072490692,
|
| 1765 |
+
"logits/rejected": -0.3323909640312195,
|
| 1766 |
+
"logps/chosen": -420.1419372558594,
|
| 1767 |
+
"logps/rejected": -468.536376953125,
|
| 1768 |
+
"loss": 0.1831,
|
| 1769 |
+
"rewards/accuracies": 0.4541666507720947,
|
| 1770 |
+
"rewards/chosen": -0.01915622688829899,
|
| 1771 |
+
"rewards/margins": 0.05424219369888306,
|
| 1772 |
+
"rewards/rejected": -0.07339842617511749,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.0,
|
| 1777 |
+
"step": 1250,
|
| 1778 |
+
"total_flos": 0.0,
|
| 1779 |
+
"train_loss": 0.1874461171746254,
|
| 1780 |
+
"train_runtime": 12039.6342,
|
| 1781 |
+
"train_samples_per_second": 2.492,
|
| 1782 |
+
"train_steps_per_second": 0.104
|
| 1783 |
+
}
|
| 1784 |
+
],
|
| 1785 |
+
"logging_steps": 10,
|
| 1786 |
+
"max_steps": 1250,
|
| 1787 |
+
"num_input_tokens_seen": 0,
|
| 1788 |
+
"num_train_epochs": 1,
|
| 1789 |
+
"save_steps": 100,
|
| 1790 |
+
"total_flos": 0.0,
|
| 1791 |
+
"train_batch_size": 6,
|
| 1792 |
+
"trial_name": null,
|
| 1793 |
+
"trial_params": null
|
| 1794 |
+
}
|