Model save
Browse files- README.md +59 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May21_19-10-01_gpu4-119-5/events.out.tfevents.1716282770.gpu4-119-5.1848158.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -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-v20-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-v20-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: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
### Framework versions
|
| 54 |
+
|
| 55 |
+
- PEFT 0.7.1
|
| 56 |
+
- Transformers 4.36.2
|
| 57 |
+
- Pytorch 2.1.2+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 167807296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1a150483b53c0527c48da864fe4d4dc1beb8c02521eee7b13a997a109a09479
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.016774978733062745,
|
| 4 |
+
"train_runtime": 1063.735,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 28.203,
|
| 7 |
+
"train_steps_per_second": 1.763
|
| 8 |
+
}
|
runs/May21_19-10-01_gpu4-119-5/events.out.tfevents.1716282770.gpu4-119-5.1848158.0
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:b507d3759f1ad71c4926cf42574d3b8706a3ee6fc549d993f6674d1220ea9dac
|
| 3 |
+
size 16045
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.016774978733062745,
|
| 4 |
+
"train_runtime": 1063.735,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 28.203,
|
| 7 |
+
"train_steps_per_second": 1.763
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2662 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1875,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2.6595744680851065e-08,
|
| 14 |
+
"logits/chosen": 0.4583740830421448,
|
| 15 |
+
"logits/rejected": 0.45381295680999756,
|
| 16 |
+
"logps/chosen": -403.16717529296875,
|
| 17 |
+
"logps/rejected": -354.3865051269531,
|
| 18 |
+
"loss": 0.1853,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 2.6595744680851066e-07,
|
| 28 |
+
"logits/chosen": 0.18831893801689148,
|
| 29 |
+
"logits/rejected": 0.16829822957515717,
|
| 30 |
+
"logps/chosen": -401.88055419921875,
|
| 31 |
+
"logps/rejected": -396.11865234375,
|
| 32 |
+
"loss": 0.2155,
|
| 33 |
+
"rewards/accuracies": 0.2638888955116272,
|
| 34 |
+
"rewards/chosen": -0.000744127610232681,
|
| 35 |
+
"rewards/margins": -8.914418140193447e-05,
|
| 36 |
+
"rewards/rejected": -0.0006549834506586194,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": 0.1669415831565857,
|
| 43 |
+
"logits/rejected": 0.27017873525619507,
|
| 44 |
+
"logps/chosen": -453.92071533203125,
|
| 45 |
+
"logps/rejected": -443.1700744628906,
|
| 46 |
+
"loss": 0.2137,
|
| 47 |
+
"rewards/accuracies": 0.3812499940395355,
|
| 48 |
+
"rewards/chosen": -0.0007682474097236991,
|
| 49 |
+
"rewards/margins": -1.9114029782940634e-05,
|
| 50 |
+
"rewards/rejected": -0.0007491334108635783,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": 0.1750134825706482,
|
| 57 |
+
"logits/rejected": 0.2582840919494629,
|
| 58 |
+
"logps/chosen": -361.32965087890625,
|
| 59 |
+
"logps/rejected": -338.42205810546875,
|
| 60 |
+
"loss": 0.2148,
|
| 61 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 62 |
+
"rewards/chosen": -0.0005828866851516068,
|
| 63 |
+
"rewards/margins": 4.7791574615985155e-05,
|
| 64 |
+
"rewards/rejected": -0.000630678201559931,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": 0.1780398190021515,
|
| 71 |
+
"logits/rejected": 0.23933863639831543,
|
| 72 |
+
"logps/chosen": -418.8761291503906,
|
| 73 |
+
"logps/rejected": -419.4820251464844,
|
| 74 |
+
"loss": 0.205,
|
| 75 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 76 |
+
"rewards/chosen": -0.0007866934174671769,
|
| 77 |
+
"rewards/margins": -4.094879113836214e-05,
|
| 78 |
+
"rewards/rejected": -0.0007457446190528572,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": 0.21062365174293518,
|
| 85 |
+
"logits/rejected": 0.3023103177547455,
|
| 86 |
+
"logps/chosen": -369.01318359375,
|
| 87 |
+
"logps/rejected": -368.9207458496094,
|
| 88 |
+
"loss": 0.2261,
|
| 89 |
+
"rewards/accuracies": 0.33125001192092896,
|
| 90 |
+
"rewards/chosen": -0.0007744937902316451,
|
| 91 |
+
"rewards/margins": -3.84082886739634e-05,
|
| 92 |
+
"rewards/rejected": -0.0007360855233855546,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": 0.21257944405078888,
|
| 99 |
+
"logits/rejected": 0.23676128685474396,
|
| 100 |
+
"logps/chosen": -401.72259521484375,
|
| 101 |
+
"logps/rejected": -401.12982177734375,
|
| 102 |
+
"loss": 0.21,
|
| 103 |
+
"rewards/accuracies": 0.32499998807907104,
|
| 104 |
+
"rewards/chosen": -0.0010942494263872504,
|
| 105 |
+
"rewards/margins": 2.2952935978537425e-05,
|
| 106 |
+
"rewards/rejected": -0.0011172023368999362,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": 0.22530443966388702,
|
| 113 |
+
"logits/rejected": 0.24157127737998962,
|
| 114 |
+
"logps/chosen": -421.9361877441406,
|
| 115 |
+
"logps/rejected": -450.1436462402344,
|
| 116 |
+
"loss": 0.2112,
|
| 117 |
+
"rewards/accuracies": 0.375,
|
| 118 |
+
"rewards/chosen": -0.0015197412576526403,
|
| 119 |
+
"rewards/margins": 2.4099141228361987e-05,
|
| 120 |
+
"rewards/rejected": -0.0015438406262546778,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": 0.23238015174865723,
|
| 127 |
+
"logits/rejected": 0.2601611614227295,
|
| 128 |
+
"logps/chosen": -418.73187255859375,
|
| 129 |
+
"logps/rejected": -398.03265380859375,
|
| 130 |
+
"loss": 0.205,
|
| 131 |
+
"rewards/accuracies": 0.34375,
|
| 132 |
+
"rewards/chosen": -0.0016283972654491663,
|
| 133 |
+
"rewards/margins": -1.6413705452578142e-05,
|
| 134 |
+
"rewards/rejected": -0.0016119834035634995,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": 0.17837639153003693,
|
| 141 |
+
"logits/rejected": 0.24620842933654785,
|
| 142 |
+
"logps/chosen": -392.7635192871094,
|
| 143 |
+
"logps/rejected": -385.9835205078125,
|
| 144 |
+
"loss": 0.2062,
|
| 145 |
+
"rewards/accuracies": 0.3687500059604645,
|
| 146 |
+
"rewards/chosen": -0.0008109696209430695,
|
| 147 |
+
"rewards/margins": 8.667097426950932e-05,
|
| 148 |
+
"rewards/rejected": -0.0008976406534202397,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": 0.22456176578998566,
|
| 155 |
+
"logits/rejected": 0.2180750072002411,
|
| 156 |
+
"logps/chosen": -411.5848693847656,
|
| 157 |
+
"logps/rejected": -392.6322326660156,
|
| 158 |
+
"loss": 0.2234,
|
| 159 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 160 |
+
"rewards/chosen": -0.00039298724732361734,
|
| 161 |
+
"rewards/margins": 0.00011892013571923599,
|
| 162 |
+
"rewards/rejected": -0.0005119073903188109,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": 0.19836413860321045,
|
| 169 |
+
"logits/rejected": 0.3192578852176666,
|
| 170 |
+
"logps/chosen": -410.68499755859375,
|
| 171 |
+
"logps/rejected": -386.6772155761719,
|
| 172 |
+
"loss": 0.2086,
|
| 173 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 174 |
+
"rewards/chosen": -0.0007202932611107826,
|
| 175 |
+
"rewards/margins": 0.00010950298747047782,
|
| 176 |
+
"rewards/rejected": -0.0008297963067889214,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": 0.1606016904115677,
|
| 183 |
+
"logits/rejected": 0.28400760889053345,
|
| 184 |
+
"logps/chosen": -401.4821472167969,
|
| 185 |
+
"logps/rejected": -373.6825256347656,
|
| 186 |
+
"loss": 0.2184,
|
| 187 |
+
"rewards/accuracies": 0.40625,
|
| 188 |
+
"rewards/chosen": -0.0019728371407836676,
|
| 189 |
+
"rewards/margins": 0.0002594580873847008,
|
| 190 |
+
"rewards/rejected": -0.0022322952281683683,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": 0.22675403952598572,
|
| 197 |
+
"logits/rejected": 0.2259739637374878,
|
| 198 |
+
"logps/chosen": -432.01788330078125,
|
| 199 |
+
"logps/rejected": -415.99237060546875,
|
| 200 |
+
"loss": 0.2144,
|
| 201 |
+
"rewards/accuracies": 0.5,
|
| 202 |
+
"rewards/chosen": -0.0032550902105867863,
|
| 203 |
+
"rewards/margins": 0.000516787578817457,
|
| 204 |
+
"rewards/rejected": -0.0037718776147812605,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": 0.13569238781929016,
|
| 211 |
+
"logits/rejected": 0.23111942410469055,
|
| 212 |
+
"logps/chosen": -416.4497985839844,
|
| 213 |
+
"logps/rejected": -402.7656555175781,
|
| 214 |
+
"loss": 0.202,
|
| 215 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 216 |
+
"rewards/chosen": -0.006250211503356695,
|
| 217 |
+
"rewards/margins": 0.0006005663308314979,
|
| 218 |
+
"rewards/rejected": -0.006850778125226498,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": 0.15672233700752258,
|
| 225 |
+
"logits/rejected": 0.2764233350753784,
|
| 226 |
+
"logps/chosen": -441.35137939453125,
|
| 227 |
+
"logps/rejected": -409.206787109375,
|
| 228 |
+
"loss": 0.2094,
|
| 229 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 230 |
+
"rewards/chosen": -0.008352077566087246,
|
| 231 |
+
"rewards/margins": 0.000567329756449908,
|
| 232 |
+
"rewards/rejected": -0.008919407613575459,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": 0.17575426399707794,
|
| 239 |
+
"logits/rejected": 0.3381495475769043,
|
| 240 |
+
"logps/chosen": -468.0437927246094,
|
| 241 |
+
"logps/rejected": -437.7367248535156,
|
| 242 |
+
"loss": 0.2069,
|
| 243 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 244 |
+
"rewards/chosen": -0.011829295195639133,
|
| 245 |
+
"rewards/margins": 0.0006891209632158279,
|
| 246 |
+
"rewards/rejected": -0.012518415227532387,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": 0.2566456198692322,
|
| 253 |
+
"logits/rejected": 0.21506217122077942,
|
| 254 |
+
"logps/chosen": -443.35540771484375,
|
| 255 |
+
"logps/rejected": -438.29876708984375,
|
| 256 |
+
"loss": 0.224,
|
| 257 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 258 |
+
"rewards/chosen": -0.013920286670327187,
|
| 259 |
+
"rewards/margins": 0.0008589512435719371,
|
| 260 |
+
"rewards/rejected": -0.014779238030314445,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": 0.1587153822183609,
|
| 267 |
+
"logits/rejected": 0.346591055393219,
|
| 268 |
+
"logps/chosen": -423.898681640625,
|
| 269 |
+
"logps/rejected": -416.0426330566406,
|
| 270 |
+
"loss": 0.2208,
|
| 271 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 272 |
+
"rewards/chosen": -0.01828654855489731,
|
| 273 |
+
"rewards/margins": 0.0014178925193846226,
|
| 274 |
+
"rewards/rejected": -0.019704440608620644,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": 0.19637706875801086,
|
| 281 |
+
"logits/rejected": 0.13249197602272034,
|
| 282 |
+
"logps/chosen": -401.75360107421875,
|
| 283 |
+
"logps/rejected": -391.2793884277344,
|
| 284 |
+
"loss": 0.2078,
|
| 285 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 286 |
+
"rewards/chosen": -0.023105399683117867,
|
| 287 |
+
"rewards/margins": 0.0009698948706500232,
|
| 288 |
+
"rewards/rejected": -0.02407529577612877,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": 0.12021654844284058,
|
| 295 |
+
"logits/rejected": 0.22755944728851318,
|
| 296 |
+
"logps/chosen": -438.9696350097656,
|
| 297 |
+
"logps/rejected": -436.67559814453125,
|
| 298 |
+
"loss": 0.212,
|
| 299 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 300 |
+
"rewards/chosen": -0.0280294306576252,
|
| 301 |
+
"rewards/margins": 0.001816231175325811,
|
| 302 |
+
"rewards/rejected": -0.02984566055238247,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": 0.17782853543758392,
|
| 309 |
+
"logits/rejected": 0.1260356307029724,
|
| 310 |
+
"logps/chosen": -428.07281494140625,
|
| 311 |
+
"logps/rejected": -423.8680725097656,
|
| 312 |
+
"loss": 0.2116,
|
| 313 |
+
"rewards/accuracies": 0.550000011920929,
|
| 314 |
+
"rewards/chosen": -0.03266894817352295,
|
| 315 |
+
"rewards/margins": 0.0038566484581679106,
|
| 316 |
+
"rewards/rejected": -0.03652559593319893,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": 0.15141043066978455,
|
| 323 |
+
"logits/rejected": 0.21045760810375214,
|
| 324 |
+
"logps/chosen": -441.1923828125,
|
| 325 |
+
"logps/rejected": -440.4317321777344,
|
| 326 |
+
"loss": 0.2056,
|
| 327 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 328 |
+
"rewards/chosen": -0.03683360293507576,
|
| 329 |
+
"rewards/margins": 0.00403643399477005,
|
| 330 |
+
"rewards/rejected": -0.04087003692984581,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": 0.1319437474012375,
|
| 337 |
+
"logits/rejected": 0.16590853035449982,
|
| 338 |
+
"logps/chosen": -463.49951171875,
|
| 339 |
+
"logps/rejected": -463.0955505371094,
|
| 340 |
+
"loss": 0.2099,
|
| 341 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 342 |
+
"rewards/chosen": -0.04471432790160179,
|
| 343 |
+
"rewards/margins": 0.004302737768739462,
|
| 344 |
+
"rewards/rejected": -0.04901706799864769,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": 0.10973749309778214,
|
| 351 |
+
"logits/rejected": 0.14370934665203094,
|
| 352 |
+
"logps/chosen": -432.8614807128906,
|
| 353 |
+
"logps/rejected": -412.8258361816406,
|
| 354 |
+
"loss": 0.2081,
|
| 355 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 356 |
+
"rewards/chosen": -0.048478107899427414,
|
| 357 |
+
"rewards/margins": 0.0035480097867548466,
|
| 358 |
+
"rewards/rejected": -0.052026115357875824,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": 0.14486494660377502,
|
| 365 |
+
"logits/rejected": 0.13507609069347382,
|
| 366 |
+
"logps/chosen": -425.30743408203125,
|
| 367 |
+
"logps/rejected": -446.130615234375,
|
| 368 |
+
"loss": 0.1997,
|
| 369 |
+
"rewards/accuracies": 0.46875,
|
| 370 |
+
"rewards/chosen": -0.05807062238454819,
|
| 371 |
+
"rewards/margins": 0.0065963054075837135,
|
| 372 |
+
"rewards/rejected": -0.06466692686080933,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": 0.18454475700855255,
|
| 379 |
+
"logits/rejected": 0.16011472046375275,
|
| 380 |
+
"logps/chosen": -497.3888244628906,
|
| 381 |
+
"logps/rejected": -488.9383850097656,
|
| 382 |
+
"loss": 0.1955,
|
| 383 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 384 |
+
"rewards/chosen": -0.07542432844638824,
|
| 385 |
+
"rewards/margins": 0.005581502337008715,
|
| 386 |
+
"rewards/rejected": -0.08100582659244537,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": 0.04981505125761032,
|
| 393 |
+
"logits/rejected": 0.11929504573345184,
|
| 394 |
+
"logps/chosen": -475.73687744140625,
|
| 395 |
+
"logps/rejected": -471.32421875,
|
| 396 |
+
"loss": 0.2008,
|
| 397 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 398 |
+
"rewards/chosen": -0.07895161211490631,
|
| 399 |
+
"rewards/margins": 0.011724306270480156,
|
| 400 |
+
"rewards/rejected": -0.09067590534687042,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": 0.09068510681390762,
|
| 407 |
+
"logits/rejected": 0.17252135276794434,
|
| 408 |
+
"logps/chosen": -545.042724609375,
|
| 409 |
+
"logps/rejected": -578.0839233398438,
|
| 410 |
+
"loss": 0.189,
|
| 411 |
+
"rewards/accuracies": 0.5625,
|
| 412 |
+
"rewards/chosen": -0.10266657918691635,
|
| 413 |
+
"rewards/margins": 0.02503531612455845,
|
| 414 |
+
"rewards/rejected": -0.12770189344882965,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": -0.0076313503086566925,
|
| 421 |
+
"logits/rejected": 0.0826013833284378,
|
| 422 |
+
"logps/chosen": -509.309326171875,
|
| 423 |
+
"logps/rejected": -542.4077758789062,
|
| 424 |
+
"loss": 0.1898,
|
| 425 |
+
"rewards/accuracies": 0.518750011920929,
|
| 426 |
+
"rewards/chosen": -0.12836064398288727,
|
| 427 |
+
"rewards/margins": 0.03418760746717453,
|
| 428 |
+
"rewards/rejected": -0.1625482589006424,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": -0.011387845501303673,
|
| 435 |
+
"logits/rejected": 0.058963656425476074,
|
| 436 |
+
"logps/chosen": -550.4841918945312,
|
| 437 |
+
"logps/rejected": -566.2930297851562,
|
| 438 |
+
"loss": 0.1994,
|
| 439 |
+
"rewards/accuracies": 0.5,
|
| 440 |
+
"rewards/chosen": -0.1419098824262619,
|
| 441 |
+
"rewards/margins": 0.03765057772397995,
|
| 442 |
+
"rewards/rejected": -0.17956045269966125,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": 0.030229881405830383,
|
| 449 |
+
"logits/rejected": 0.00785739440470934,
|
| 450 |
+
"logps/chosen": -546.796875,
|
| 451 |
+
"logps/rejected": -585.1295776367188,
|
| 452 |
+
"loss": 0.1988,
|
| 453 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 454 |
+
"rewards/chosen": -0.15364839136600494,
|
| 455 |
+
"rewards/margins": 0.04681529477238655,
|
| 456 |
+
"rewards/rejected": -0.2004636526107788,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": 0.09916579723358154,
|
| 463 |
+
"logits/rejected": 0.03708130493760109,
|
| 464 |
+
"logps/chosen": -534.3087158203125,
|
| 465 |
+
"logps/rejected": -577.957275390625,
|
| 466 |
+
"loss": 0.176,
|
| 467 |
+
"rewards/accuracies": 0.543749988079071,
|
| 468 |
+
"rewards/chosen": -0.13466373085975647,
|
| 469 |
+
"rewards/margins": 0.046590112149715424,
|
| 470 |
+
"rewards/rejected": -0.1812538504600525,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": 0.09245137125253677,
|
| 477 |
+
"logits/rejected": -0.01894455775618553,
|
| 478 |
+
"logps/chosen": -570.8424682617188,
|
| 479 |
+
"logps/rejected": -633.2811279296875,
|
| 480 |
+
"loss": 0.1982,
|
| 481 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 482 |
+
"rewards/chosen": -0.1720808893442154,
|
| 483 |
+
"rewards/margins": 0.05095798522233963,
|
| 484 |
+
"rewards/rejected": -0.22303888201713562,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": 0.06517922878265381,
|
| 491 |
+
"logits/rejected": 0.05662886053323746,
|
| 492 |
+
"logps/chosen": -556.5380859375,
|
| 493 |
+
"logps/rejected": -572.91943359375,
|
| 494 |
+
"loss": 0.1967,
|
| 495 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 496 |
+
"rewards/chosen": -0.1459980458021164,
|
| 497 |
+
"rewards/margins": 0.031131967902183533,
|
| 498 |
+
"rewards/rejected": -0.17713001370429993,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": 0.053707320243120193,
|
| 505 |
+
"logits/rejected": 0.12972167134284973,
|
| 506 |
+
"logps/chosen": -587.4563598632812,
|
| 507 |
+
"logps/rejected": -619.8084716796875,
|
| 508 |
+
"loss": 0.1789,
|
| 509 |
+
"rewards/accuracies": 0.512499988079071,
|
| 510 |
+
"rewards/chosen": -0.14950796961784363,
|
| 511 |
+
"rewards/margins": 0.027994930744171143,
|
| 512 |
+
"rewards/rejected": -0.17750290036201477,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": 0.05275138095021248,
|
| 519 |
+
"logits/rejected": 0.13531816005706787,
|
| 520 |
+
"logps/chosen": -553.1101684570312,
|
| 521 |
+
"logps/rejected": -604.1668701171875,
|
| 522 |
+
"loss": 0.1926,
|
| 523 |
+
"rewards/accuracies": 0.53125,
|
| 524 |
+
"rewards/chosen": -0.13555410504341125,
|
| 525 |
+
"rewards/margins": 0.0414896085858345,
|
| 526 |
+
"rewards/rejected": -0.17704370617866516,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": 0.10553497076034546,
|
| 533 |
+
"logits/rejected": 0.027261802926659584,
|
| 534 |
+
"logps/chosen": -506.9090881347656,
|
| 535 |
+
"logps/rejected": -567.632568359375,
|
| 536 |
+
"loss": 0.1952,
|
| 537 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 538 |
+
"rewards/chosen": -0.12961818277835846,
|
| 539 |
+
"rewards/margins": 0.0423763282597065,
|
| 540 |
+
"rewards/rejected": -0.17199452221393585,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": -0.021337047219276428,
|
| 547 |
+
"logits/rejected": 0.10264651477336884,
|
| 548 |
+
"logps/chosen": -569.1201171875,
|
| 549 |
+
"logps/rejected": -573.4818115234375,
|
| 550 |
+
"loss": 0.1775,
|
| 551 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 552 |
+
"rewards/chosen": -0.15105991065502167,
|
| 553 |
+
"rewards/margins": 0.04063944146037102,
|
| 554 |
+
"rewards/rejected": -0.19169935584068298,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": -0.007825059816241264,
|
| 561 |
+
"logits/rejected": -0.015095917508006096,
|
| 562 |
+
"logps/chosen": -517.6556396484375,
|
| 563 |
+
"logps/rejected": -564.65673828125,
|
| 564 |
+
"loss": 0.1934,
|
| 565 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 566 |
+
"rewards/chosen": -0.15630927681922913,
|
| 567 |
+
"rewards/margins": 0.03676559031009674,
|
| 568 |
+
"rewards/rejected": -0.19307485222816467,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": 0.03950309008359909,
|
| 575 |
+
"logits/rejected": 0.025178443640470505,
|
| 576 |
+
"logps/chosen": -613.1845703125,
|
| 577 |
+
"logps/rejected": -667.6192016601562,
|
| 578 |
+
"loss": 0.1839,
|
| 579 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 580 |
+
"rewards/chosen": -0.16962917149066925,
|
| 581 |
+
"rewards/margins": 0.061695653945207596,
|
| 582 |
+
"rewards/rejected": -0.23132482171058655,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": -0.019574914127588272,
|
| 589 |
+
"logits/rejected": 0.10981860011816025,
|
| 590 |
+
"logps/chosen": -587.1323852539062,
|
| 591 |
+
"logps/rejected": -607.53955078125,
|
| 592 |
+
"loss": 0.1968,
|
| 593 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 594 |
+
"rewards/chosen": -0.1764066517353058,
|
| 595 |
+
"rewards/margins": 0.03810610622167587,
|
| 596 |
+
"rewards/rejected": -0.21451278030872345,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": -0.016084378585219383,
|
| 603 |
+
"logits/rejected": 0.11264481395483017,
|
| 604 |
+
"logps/chosen": -570.8071899414062,
|
| 605 |
+
"logps/rejected": -621.8716430664062,
|
| 606 |
+
"loss": 0.2007,
|
| 607 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 608 |
+
"rewards/chosen": -0.16467757523059845,
|
| 609 |
+
"rewards/margins": 0.039321959018707275,
|
| 610 |
+
"rewards/rejected": -0.20399951934814453,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": 0.05447696894407272,
|
| 617 |
+
"logits/rejected": 0.03223523125052452,
|
| 618 |
+
"logps/chosen": -529.8160400390625,
|
| 619 |
+
"logps/rejected": -550.2005004882812,
|
| 620 |
+
"loss": 0.1846,
|
| 621 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 622 |
+
"rewards/chosen": -0.13065846264362335,
|
| 623 |
+
"rewards/margins": 0.04571721702814102,
|
| 624 |
+
"rewards/rejected": -0.17637568712234497,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": -0.021515950560569763,
|
| 631 |
+
"logits/rejected": 0.03140898048877716,
|
| 632 |
+
"logps/chosen": -578.0147094726562,
|
| 633 |
+
"logps/rejected": -585.7742919921875,
|
| 634 |
+
"loss": 0.1984,
|
| 635 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 636 |
+
"rewards/chosen": -0.15668722987174988,
|
| 637 |
+
"rewards/margins": 0.035644322633743286,
|
| 638 |
+
"rewards/rejected": -0.19233153760433197,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": -0.012143002822995186,
|
| 645 |
+
"logits/rejected": -0.0082742003723979,
|
| 646 |
+
"logps/chosen": -486.759521484375,
|
| 647 |
+
"logps/rejected": -521.0432739257812,
|
| 648 |
+
"loss": 0.199,
|
| 649 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 650 |
+
"rewards/chosen": -0.127678781747818,
|
| 651 |
+
"rewards/margins": 0.03519933670759201,
|
| 652 |
+
"rewards/rejected": -0.1628781259059906,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": -0.023242251947522163,
|
| 659 |
+
"logits/rejected": 0.003186366055160761,
|
| 660 |
+
"logps/chosen": -485.2528381347656,
|
| 661 |
+
"logps/rejected": -513.8176879882812,
|
| 662 |
+
"loss": 0.1925,
|
| 663 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 664 |
+
"rewards/chosen": -0.11917861551046371,
|
| 665 |
+
"rewards/margins": 0.047842614352703094,
|
| 666 |
+
"rewards/rejected": -0.167021244764328,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": 0.01416336465626955,
|
| 673 |
+
"logits/rejected": -0.06039174646139145,
|
| 674 |
+
"logps/chosen": -549.2015380859375,
|
| 675 |
+
"logps/rejected": -583.758544921875,
|
| 676 |
+
"loss": 0.1822,
|
| 677 |
+
"rewards/accuracies": 0.5,
|
| 678 |
+
"rewards/chosen": -0.14279165863990784,
|
| 679 |
+
"rewards/margins": 0.038277558982372284,
|
| 680 |
+
"rewards/rejected": -0.18106922507286072,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": 0.01400854904204607,
|
| 687 |
+
"logits/rejected": 0.10263659805059433,
|
| 688 |
+
"logps/chosen": -515.437255859375,
|
| 689 |
+
"logps/rejected": -564.8402099609375,
|
| 690 |
+
"loss": 0.1976,
|
| 691 |
+
"rewards/accuracies": 0.5,
|
| 692 |
+
"rewards/chosen": -0.13872714340686798,
|
| 693 |
+
"rewards/margins": 0.03997962549328804,
|
| 694 |
+
"rewards/rejected": -0.17870678007602692,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": -0.06926377862691879,
|
| 701 |
+
"logits/rejected": 0.03542783483862877,
|
| 702 |
+
"logps/chosen": -540.4765625,
|
| 703 |
+
"logps/rejected": -549.0443115234375,
|
| 704 |
+
"loss": 0.1897,
|
| 705 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 706 |
+
"rewards/chosen": -0.13047516345977783,
|
| 707 |
+
"rewards/margins": 0.03688601404428482,
|
| 708 |
+
"rewards/rejected": -0.16736117005348206,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": -0.055144570767879486,
|
| 715 |
+
"logits/rejected": 0.00845063291490078,
|
| 716 |
+
"logps/chosen": -540.0427856445312,
|
| 717 |
+
"logps/rejected": -555.8956298828125,
|
| 718 |
+
"loss": 0.1863,
|
| 719 |
+
"rewards/accuracies": 0.512499988079071,
|
| 720 |
+
"rewards/chosen": -0.14786241948604584,
|
| 721 |
+
"rewards/margins": 0.03734371438622475,
|
| 722 |
+
"rewards/rejected": -0.18520613014698029,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": -0.06796270608901978,
|
| 729 |
+
"logits/rejected": -0.021189894527196884,
|
| 730 |
+
"logps/chosen": -538.6000366210938,
|
| 731 |
+
"logps/rejected": -609.37353515625,
|
| 732 |
+
"loss": 0.1812,
|
| 733 |
+
"rewards/accuracies": 0.53125,
|
| 734 |
+
"rewards/chosen": -0.14661245048046112,
|
| 735 |
+
"rewards/margins": 0.0674336701631546,
|
| 736 |
+
"rewards/rejected": -0.2140461504459381,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": -0.13910801708698273,
|
| 743 |
+
"logits/rejected": 0.04259239882230759,
|
| 744 |
+
"logps/chosen": -555.0911865234375,
|
| 745 |
+
"logps/rejected": -552.6492919921875,
|
| 746 |
+
"loss": 0.1901,
|
| 747 |
+
"rewards/accuracies": 0.46875,
|
| 748 |
+
"rewards/chosen": -0.15548577904701233,
|
| 749 |
+
"rewards/margins": 0.03300771862268448,
|
| 750 |
+
"rewards/rejected": -0.18849347531795502,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": -0.047577690333127975,
|
| 757 |
+
"logits/rejected": 0.034965887665748596,
|
| 758 |
+
"logps/chosen": -664.0265502929688,
|
| 759 |
+
"logps/rejected": -692.3294677734375,
|
| 760 |
+
"loss": 0.1941,
|
| 761 |
+
"rewards/accuracies": 0.518750011920929,
|
| 762 |
+
"rewards/chosen": -0.1734737604856491,
|
| 763 |
+
"rewards/margins": 0.04430503025650978,
|
| 764 |
+
"rewards/rejected": -0.21777880191802979,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": -0.013295474462211132,
|
| 771 |
+
"logits/rejected": -0.07179677486419678,
|
| 772 |
+
"logps/chosen": -540.1502685546875,
|
| 773 |
+
"logps/rejected": -567.1649169921875,
|
| 774 |
+
"loss": 0.1972,
|
| 775 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 776 |
+
"rewards/chosen": -0.1351390928030014,
|
| 777 |
+
"rewards/margins": 0.03879848122596741,
|
| 778 |
+
"rewards/rejected": -0.1739375740289688,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": -0.10417531430721283,
|
| 785 |
+
"logits/rejected": 0.025454232469201088,
|
| 786 |
+
"logps/chosen": -571.4408569335938,
|
| 787 |
+
"logps/rejected": -581.1018676757812,
|
| 788 |
+
"loss": 0.1785,
|
| 789 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 790 |
+
"rewards/chosen": -0.13031336665153503,
|
| 791 |
+
"rewards/margins": 0.04332467168569565,
|
| 792 |
+
"rewards/rejected": -0.17363804578781128,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": -0.09106893092393875,
|
| 799 |
+
"logits/rejected": 0.05246344953775406,
|
| 800 |
+
"logps/chosen": -590.4605712890625,
|
| 801 |
+
"logps/rejected": -646.8682861328125,
|
| 802 |
+
"loss": 0.1797,
|
| 803 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 804 |
+
"rewards/chosen": -0.16008590161800385,
|
| 805 |
+
"rewards/margins": 0.03608149290084839,
|
| 806 |
+
"rewards/rejected": -0.19616740942001343,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": -0.00037176310434006155,
|
| 813 |
+
"logits/rejected": -0.05788201093673706,
|
| 814 |
+
"logps/chosen": -603.2279663085938,
|
| 815 |
+
"logps/rejected": -637.8117065429688,
|
| 816 |
+
"loss": 0.2042,
|
| 817 |
+
"rewards/accuracies": 0.518750011920929,
|
| 818 |
+
"rewards/chosen": -0.15948781371116638,
|
| 819 |
+
"rewards/margins": 0.039536003023386,
|
| 820 |
+
"rewards/rejected": -0.19902381300926208,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": -0.06197139620780945,
|
| 827 |
+
"logits/rejected": -0.04511360824108124,
|
| 828 |
+
"logps/chosen": -502.40704345703125,
|
| 829 |
+
"logps/rejected": -549.5247802734375,
|
| 830 |
+
"loss": 0.1904,
|
| 831 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 832 |
+
"rewards/chosen": -0.1260320395231247,
|
| 833 |
+
"rewards/margins": 0.04073121398687363,
|
| 834 |
+
"rewards/rejected": -0.1667632758617401,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": -0.03825578838586807,
|
| 841 |
+
"logits/rejected": 0.00044789613457396626,
|
| 842 |
+
"logps/chosen": -474.03973388671875,
|
| 843 |
+
"logps/rejected": -531.3597412109375,
|
| 844 |
+
"loss": 0.1772,
|
| 845 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 846 |
+
"rewards/chosen": -0.11952260881662369,
|
| 847 |
+
"rewards/margins": 0.05453835800290108,
|
| 848 |
+
"rewards/rejected": -0.17406097054481506,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": -0.06856271624565125,
|
| 855 |
+
"logits/rejected": -0.03950439766049385,
|
| 856 |
+
"logps/chosen": -530.919189453125,
|
| 857 |
+
"logps/rejected": -575.9044189453125,
|
| 858 |
+
"loss": 0.1848,
|
| 859 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 860 |
+
"rewards/chosen": -0.1305655688047409,
|
| 861 |
+
"rewards/margins": 0.04401278868317604,
|
| 862 |
+
"rewards/rejected": -0.17457836866378784,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": -0.008585452102124691,
|
| 869 |
+
"logits/rejected": -0.08859982341527939,
|
| 870 |
+
"logps/chosen": -561.964599609375,
|
| 871 |
+
"logps/rejected": -607.6642456054688,
|
| 872 |
+
"loss": 0.1815,
|
| 873 |
+
"rewards/accuracies": 0.512499988079071,
|
| 874 |
+
"rewards/chosen": -0.13443836569786072,
|
| 875 |
+
"rewards/margins": 0.061653982847929,
|
| 876 |
+
"rewards/rejected": -0.19609235227108002,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": -0.11785644292831421,
|
| 883 |
+
"logits/rejected": 0.07683457434177399,
|
| 884 |
+
"logps/chosen": -580.4694213867188,
|
| 885 |
+
"logps/rejected": -604.2586669921875,
|
| 886 |
+
"loss": 0.1988,
|
| 887 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 888 |
+
"rewards/chosen": -0.14866627752780914,
|
| 889 |
+
"rewards/margins": 0.03873666003346443,
|
| 890 |
+
"rewards/rejected": -0.18740293383598328,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": -0.08321277797222137,
|
| 897 |
+
"logits/rejected": -0.059583961963653564,
|
| 898 |
+
"logps/chosen": -520.8612060546875,
|
| 899 |
+
"logps/rejected": -594.0638427734375,
|
| 900 |
+
"loss": 0.1774,
|
| 901 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 902 |
+
"rewards/chosen": -0.1341467797756195,
|
| 903 |
+
"rewards/margins": 0.05918589234352112,
|
| 904 |
+
"rewards/rejected": -0.19333268702030182,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": -0.09531132876873016,
|
| 911 |
+
"logits/rejected": -0.0270084198564291,
|
| 912 |
+
"logps/chosen": -528.1355590820312,
|
| 913 |
+
"logps/rejected": -581.7833251953125,
|
| 914 |
+
"loss": 0.1745,
|
| 915 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 916 |
+
"rewards/chosen": -0.13981810212135315,
|
| 917 |
+
"rewards/margins": 0.07118718326091766,
|
| 918 |
+
"rewards/rejected": -0.211005300283432,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": -0.10320959240198135,
|
| 925 |
+
"logits/rejected": -0.019093522801995277,
|
| 926 |
+
"logps/chosen": -571.685791015625,
|
| 927 |
+
"logps/rejected": -591.3698120117188,
|
| 928 |
+
"loss": 0.2015,
|
| 929 |
+
"rewards/accuracies": 0.46875,
|
| 930 |
+
"rewards/chosen": -0.16250738501548767,
|
| 931 |
+
"rewards/margins": 0.04821362346410751,
|
| 932 |
+
"rewards/rejected": -0.21072101593017578,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": -0.11241753399372101,
|
| 939 |
+
"logits/rejected": -0.032273612916469574,
|
| 940 |
+
"logps/chosen": -624.3687133789062,
|
| 941 |
+
"logps/rejected": -671.1177368164062,
|
| 942 |
+
"loss": 0.1973,
|
| 943 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 944 |
+
"rewards/chosen": -0.17460055649280548,
|
| 945 |
+
"rewards/margins": 0.044025253504514694,
|
| 946 |
+
"rewards/rejected": -0.21862581372261047,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": -0.029143745079636574,
|
| 953 |
+
"logits/rejected": -0.060622453689575195,
|
| 954 |
+
"logps/chosen": -519.5960083007812,
|
| 955 |
+
"logps/rejected": -589.2883911132812,
|
| 956 |
+
"loss": 0.1632,
|
| 957 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 958 |
+
"rewards/chosen": -0.1383863389492035,
|
| 959 |
+
"rewards/margins": 0.062351007014513016,
|
| 960 |
+
"rewards/rejected": -0.2007373571395874,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": -0.06448385864496231,
|
| 967 |
+
"logits/rejected": -0.04329472780227661,
|
| 968 |
+
"logps/chosen": -536.9004516601562,
|
| 969 |
+
"logps/rejected": -563.5870361328125,
|
| 970 |
+
"loss": 0.1866,
|
| 971 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 972 |
+
"rewards/chosen": -0.14495059847831726,
|
| 973 |
+
"rewards/margins": 0.03540947288274765,
|
| 974 |
+
"rewards/rejected": -0.1803600788116455,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": -0.004617185331881046,
|
| 981 |
+
"logits/rejected": -0.01678011380136013,
|
| 982 |
+
"logps/chosen": -555.3660278320312,
|
| 983 |
+
"logps/rejected": -594.7876586914062,
|
| 984 |
+
"loss": 0.182,
|
| 985 |
+
"rewards/accuracies": 0.5,
|
| 986 |
+
"rewards/chosen": -0.13744883239269257,
|
| 987 |
+
"rewards/margins": 0.038119856268167496,
|
| 988 |
+
"rewards/rejected": -0.17556868493556976,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": -0.11041183769702911,
|
| 995 |
+
"logits/rejected": -0.09442894160747528,
|
| 996 |
+
"logps/chosen": -475.54583740234375,
|
| 997 |
+
"logps/rejected": -500.1151428222656,
|
| 998 |
+
"loss": 0.1817,
|
| 999 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1000 |
+
"rewards/chosen": -0.11575014889240265,
|
| 1001 |
+
"rewards/margins": 0.033661358058452606,
|
| 1002 |
+
"rewards/rejected": -0.14941151440143585,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": -0.10789042711257935,
|
| 1009 |
+
"logits/rejected": -0.014411434531211853,
|
| 1010 |
+
"logps/chosen": -543.808837890625,
|
| 1011 |
+
"logps/rejected": -581.8538818359375,
|
| 1012 |
+
"loss": 0.1886,
|
| 1013 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1014 |
+
"rewards/chosen": -0.1326008141040802,
|
| 1015 |
+
"rewards/margins": 0.03887839615345001,
|
| 1016 |
+
"rewards/rejected": -0.17147919535636902,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": -0.10680530220270157,
|
| 1023 |
+
"logits/rejected": -0.07425309717655182,
|
| 1024 |
+
"logps/chosen": -522.1688842773438,
|
| 1025 |
+
"logps/rejected": -554.4418334960938,
|
| 1026 |
+
"loss": 0.1864,
|
| 1027 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1028 |
+
"rewards/chosen": -0.12628528475761414,
|
| 1029 |
+
"rewards/margins": 0.04535987228155136,
|
| 1030 |
+
"rewards/rejected": -0.1716451495885849,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": -0.10503558814525604,
|
| 1037 |
+
"logits/rejected": -0.013972464017570019,
|
| 1038 |
+
"logps/chosen": -550.2520751953125,
|
| 1039 |
+
"logps/rejected": -571.8939208984375,
|
| 1040 |
+
"loss": 0.1934,
|
| 1041 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1042 |
+
"rewards/chosen": -0.14120154082775116,
|
| 1043 |
+
"rewards/margins": 0.0461118221282959,
|
| 1044 |
+
"rewards/rejected": -0.18731336295604706,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": -0.05753170698881149,
|
| 1051 |
+
"logits/rejected": -0.05392669886350632,
|
| 1052 |
+
"logps/chosen": -513.2532348632812,
|
| 1053 |
+
"logps/rejected": -580.1729736328125,
|
| 1054 |
+
"loss": 0.186,
|
| 1055 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1056 |
+
"rewards/chosen": -0.13195370137691498,
|
| 1057 |
+
"rewards/margins": 0.04442184790968895,
|
| 1058 |
+
"rewards/rejected": -0.17637556791305542,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": -0.03736535459756851,
|
| 1065 |
+
"logits/rejected": -0.001959963236004114,
|
| 1066 |
+
"logps/chosen": -531.0137939453125,
|
| 1067 |
+
"logps/rejected": -591.2086181640625,
|
| 1068 |
+
"loss": 0.1881,
|
| 1069 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1070 |
+
"rewards/chosen": -0.1330515593290329,
|
| 1071 |
+
"rewards/margins": 0.05102803185582161,
|
| 1072 |
+
"rewards/rejected": -0.1840795874595642,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": -0.10402516275644302,
|
| 1079 |
+
"logits/rejected": -0.04912823066115379,
|
| 1080 |
+
"logps/chosen": -558.085205078125,
|
| 1081 |
+
"logps/rejected": -588.9461669921875,
|
| 1082 |
+
"loss": 0.2009,
|
| 1083 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1084 |
+
"rewards/chosen": -0.13824841380119324,
|
| 1085 |
+
"rewards/margins": 0.03640920668840408,
|
| 1086 |
+
"rewards/rejected": -0.17465761303901672,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": -0.06400999426841736,
|
| 1093 |
+
"logits/rejected": -0.06958254426717758,
|
| 1094 |
+
"logps/chosen": -541.27099609375,
|
| 1095 |
+
"logps/rejected": -621.9313354492188,
|
| 1096 |
+
"loss": 0.1797,
|
| 1097 |
+
"rewards/accuracies": 0.5625,
|
| 1098 |
+
"rewards/chosen": -0.12520474195480347,
|
| 1099 |
+
"rewards/margins": 0.06592214107513428,
|
| 1100 |
+
"rewards/rejected": -0.19112688302993774,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": -0.13884581625461578,
|
| 1107 |
+
"logits/rejected": -0.11223921924829483,
|
| 1108 |
+
"logps/chosen": -552.3884887695312,
|
| 1109 |
+
"logps/rejected": -589.5878295898438,
|
| 1110 |
+
"loss": 0.1734,
|
| 1111 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1112 |
+
"rewards/chosen": -0.14118912816047668,
|
| 1113 |
+
"rewards/margins": 0.051578063517808914,
|
| 1114 |
+
"rewards/rejected": -0.1927671879529953,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": -0.07228229939937592,
|
| 1121 |
+
"logits/rejected": 0.038021642714738846,
|
| 1122 |
+
"logps/chosen": -565.1091918945312,
|
| 1123 |
+
"logps/rejected": -591.867431640625,
|
| 1124 |
+
"loss": 0.2045,
|
| 1125 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 1126 |
+
"rewards/chosen": -0.1505979746580124,
|
| 1127 |
+
"rewards/margins": 0.04035702347755432,
|
| 1128 |
+
"rewards/rejected": -0.1909550130367279,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": -0.04605743661522865,
|
| 1135 |
+
"logits/rejected": 0.011277568526566029,
|
| 1136 |
+
"logps/chosen": -562.3070678710938,
|
| 1137 |
+
"logps/rejected": -597.06201171875,
|
| 1138 |
+
"loss": 0.1925,
|
| 1139 |
+
"rewards/accuracies": 0.46875,
|
| 1140 |
+
"rewards/chosen": -0.14476799964904785,
|
| 1141 |
+
"rewards/margins": 0.04444306343793869,
|
| 1142 |
+
"rewards/rejected": -0.18921108543872833,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": -0.06661860644817352,
|
| 1149 |
+
"logits/rejected": -0.13232673704624176,
|
| 1150 |
+
"logps/chosen": -506.79315185546875,
|
| 1151 |
+
"logps/rejected": -562.1184692382812,
|
| 1152 |
+
"loss": 0.1726,
|
| 1153 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1154 |
+
"rewards/chosen": -0.12148015201091766,
|
| 1155 |
+
"rewards/margins": 0.05448601767420769,
|
| 1156 |
+
"rewards/rejected": -0.17596617341041565,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": -0.13019916415214539,
|
| 1163 |
+
"logits/rejected": -0.08353747427463531,
|
| 1164 |
+
"logps/chosen": -481.433837890625,
|
| 1165 |
+
"logps/rejected": -490.4483947753906,
|
| 1166 |
+
"loss": 0.1862,
|
| 1167 |
+
"rewards/accuracies": 0.4375,
|
| 1168 |
+
"rewards/chosen": -0.11900192499160767,
|
| 1169 |
+
"rewards/margins": 0.037384189665317535,
|
| 1170 |
+
"rewards/rejected": -0.1563861072063446,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": -0.0683845803141594,
|
| 1177 |
+
"logits/rejected": -0.03088710829615593,
|
| 1178 |
+
"logps/chosen": -492.447021484375,
|
| 1179 |
+
"logps/rejected": -564.9397583007812,
|
| 1180 |
+
"loss": 0.1862,
|
| 1181 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1182 |
+
"rewards/chosen": -0.13119229674339294,
|
| 1183 |
+
"rewards/margins": 0.05578438565135002,
|
| 1184 |
+
"rewards/rejected": -0.18697668612003326,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": -0.09018312394618988,
|
| 1191 |
+
"logits/rejected": -0.10359557718038559,
|
| 1192 |
+
"logps/chosen": -537.9823608398438,
|
| 1193 |
+
"logps/rejected": -594.79443359375,
|
| 1194 |
+
"loss": 0.1849,
|
| 1195 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1196 |
+
"rewards/chosen": -0.13429854810237885,
|
| 1197 |
+
"rewards/margins": 0.06120805814862251,
|
| 1198 |
+
"rewards/rejected": -0.19550660252571106,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": -0.18850287795066833,
|
| 1205 |
+
"logits/rejected": -0.04869599640369415,
|
| 1206 |
+
"logps/chosen": -496.01007080078125,
|
| 1207 |
+
"logps/rejected": -560.2242431640625,
|
| 1208 |
+
"loss": 0.1825,
|
| 1209 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1210 |
+
"rewards/chosen": -0.12265129387378693,
|
| 1211 |
+
"rewards/margins": 0.05625399202108383,
|
| 1212 |
+
"rewards/rejected": -0.17890527844429016,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": -0.19866463541984558,
|
| 1219 |
+
"logits/rejected": -0.004881598986685276,
|
| 1220 |
+
"logps/chosen": -532.1676635742188,
|
| 1221 |
+
"logps/rejected": -571.507568359375,
|
| 1222 |
+
"loss": 0.1791,
|
| 1223 |
+
"rewards/accuracies": 0.5,
|
| 1224 |
+
"rewards/chosen": -0.12184770405292511,
|
| 1225 |
+
"rewards/margins": 0.05913316085934639,
|
| 1226 |
+
"rewards/rejected": -0.18098084628582,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": -0.2018626630306244,
|
| 1233 |
+
"logits/rejected": -0.10594689846038818,
|
| 1234 |
+
"logps/chosen": -488.4137268066406,
|
| 1235 |
+
"logps/rejected": -556.1409912109375,
|
| 1236 |
+
"loss": 0.1846,
|
| 1237 |
+
"rewards/accuracies": 0.46875,
|
| 1238 |
+
"rewards/chosen": -0.12942823767662048,
|
| 1239 |
+
"rewards/margins": 0.05433051660656929,
|
| 1240 |
+
"rewards/rejected": -0.18375876545906067,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": -0.16193589568138123,
|
| 1247 |
+
"logits/rejected": -0.2137628048658371,
|
| 1248 |
+
"logps/chosen": -484.3509826660156,
|
| 1249 |
+
"logps/rejected": -553.5465698242188,
|
| 1250 |
+
"loss": 0.1964,
|
| 1251 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 1252 |
+
"rewards/chosen": -0.12599757313728333,
|
| 1253 |
+
"rewards/margins": 0.049567125737667084,
|
| 1254 |
+
"rewards/rejected": -0.1755646914243698,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": -0.01477061491459608,
|
| 1261 |
+
"logits/rejected": -0.20513947308063507,
|
| 1262 |
+
"logps/chosen": -559.4446411132812,
|
| 1263 |
+
"logps/rejected": -626.2364501953125,
|
| 1264 |
+
"loss": 0.171,
|
| 1265 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 1266 |
+
"rewards/chosen": -0.13351976871490479,
|
| 1267 |
+
"rewards/margins": 0.07253735512495041,
|
| 1268 |
+
"rewards/rejected": -0.2060571163892746,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": -0.23158374428749084,
|
| 1275 |
+
"logits/rejected": -0.15197685360908508,
|
| 1276 |
+
"logps/chosen": -511.8590393066406,
|
| 1277 |
+
"logps/rejected": -550.5593872070312,
|
| 1278 |
+
"loss": 0.2039,
|
| 1279 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 1280 |
+
"rewards/chosen": -0.11726844310760498,
|
| 1281 |
+
"rewards/margins": 0.04829251766204834,
|
| 1282 |
+
"rewards/rejected": -0.16556094586849213,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": -0.17909975349903107,
|
| 1289 |
+
"logits/rejected": -0.11886115372180939,
|
| 1290 |
+
"logps/chosen": -516.4205932617188,
|
| 1291 |
+
"logps/rejected": -559.4550170898438,
|
| 1292 |
+
"loss": 0.1824,
|
| 1293 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1294 |
+
"rewards/chosen": -0.1072378158569336,
|
| 1295 |
+
"rewards/margins": 0.04554293677210808,
|
| 1296 |
+
"rewards/rejected": -0.15278074145317078,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": -0.14633020758628845,
|
| 1303 |
+
"logits/rejected": -0.08009175956249237,
|
| 1304 |
+
"logps/chosen": -497.86724853515625,
|
| 1305 |
+
"logps/rejected": -534.5050659179688,
|
| 1306 |
+
"loss": 0.1581,
|
| 1307 |
+
"rewards/accuracies": 0.53125,
|
| 1308 |
+
"rewards/chosen": -0.09393012523651123,
|
| 1309 |
+
"rewards/margins": 0.05776657536625862,
|
| 1310 |
+
"rewards/rejected": -0.15169671177864075,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": -0.17566119134426117,
|
| 1317 |
+
"logits/rejected": -0.08242344111204147,
|
| 1318 |
+
"logps/chosen": -552.6607055664062,
|
| 1319 |
+
"logps/rejected": -587.2052612304688,
|
| 1320 |
+
"loss": 0.1719,
|
| 1321 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1322 |
+
"rewards/chosen": -0.09468172490596771,
|
| 1323 |
+
"rewards/margins": 0.05334918573498726,
|
| 1324 |
+
"rewards/rejected": -0.14803092181682587,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": -0.05346371978521347,
|
| 1331 |
+
"logits/rejected": -0.1932278424501419,
|
| 1332 |
+
"logps/chosen": -535.7907104492188,
|
| 1333 |
+
"logps/rejected": -599.4446411132812,
|
| 1334 |
+
"loss": 0.1681,
|
| 1335 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1336 |
+
"rewards/chosen": -0.09776908159255981,
|
| 1337 |
+
"rewards/margins": 0.05439938232302666,
|
| 1338 |
+
"rewards/rejected": -0.15216846764087677,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": -0.17646734416484833,
|
| 1345 |
+
"logits/rejected": -0.10943827778100967,
|
| 1346 |
+
"logps/chosen": -508.94232177734375,
|
| 1347 |
+
"logps/rejected": -568.2824096679688,
|
| 1348 |
+
"loss": 0.1889,
|
| 1349 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1350 |
+
"rewards/chosen": -0.10447195917367935,
|
| 1351 |
+
"rewards/margins": 0.05140892416238785,
|
| 1352 |
+
"rewards/rejected": -0.1558808833360672,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": -0.08494242280721664,
|
| 1359 |
+
"logits/rejected": -0.18166685104370117,
|
| 1360 |
+
"logps/chosen": -509.8265686035156,
|
| 1361 |
+
"logps/rejected": -575.4097900390625,
|
| 1362 |
+
"loss": 0.1796,
|
| 1363 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1364 |
+
"rewards/chosen": -0.09938603639602661,
|
| 1365 |
+
"rewards/margins": 0.06175467371940613,
|
| 1366 |
+
"rewards/rejected": -0.16114071011543274,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": -0.11445019394159317,
|
| 1373 |
+
"logits/rejected": -0.12723931670188904,
|
| 1374 |
+
"logps/chosen": -484.7312927246094,
|
| 1375 |
+
"logps/rejected": -564.54345703125,
|
| 1376 |
+
"loss": 0.1861,
|
| 1377 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1378 |
+
"rewards/chosen": -0.10803971439599991,
|
| 1379 |
+
"rewards/margins": 0.055267833173274994,
|
| 1380 |
+
"rewards/rejected": -0.1633075475692749,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": -0.14208866655826569,
|
| 1387 |
+
"logits/rejected": -0.020831745117902756,
|
| 1388 |
+
"logps/chosen": -528.3738403320312,
|
| 1389 |
+
"logps/rejected": -538.9185180664062,
|
| 1390 |
+
"loss": 0.1867,
|
| 1391 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1392 |
+
"rewards/chosen": -0.11705558001995087,
|
| 1393 |
+
"rewards/margins": 0.04653087258338928,
|
| 1394 |
+
"rewards/rejected": -0.16358645260334015,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": -0.21168622374534607,
|
| 1401 |
+
"logits/rejected": -0.10795080661773682,
|
| 1402 |
+
"logps/chosen": -551.8548583984375,
|
| 1403 |
+
"logps/rejected": -576.697998046875,
|
| 1404 |
+
"loss": 0.1936,
|
| 1405 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1406 |
+
"rewards/chosen": -0.12270279228687286,
|
| 1407 |
+
"rewards/margins": 0.041682593524456024,
|
| 1408 |
+
"rewards/rejected": -0.1643853634595871,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": -0.08504590392112732,
|
| 1415 |
+
"logits/rejected": -0.11864916980266571,
|
| 1416 |
+
"logps/chosen": -531.6979370117188,
|
| 1417 |
+
"logps/rejected": -553.0827026367188,
|
| 1418 |
+
"loss": 0.1765,
|
| 1419 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1420 |
+
"rewards/chosen": -0.107094407081604,
|
| 1421 |
+
"rewards/margins": 0.04743362218141556,
|
| 1422 |
+
"rewards/rejected": -0.15452802181243896,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": -0.08871813118457794,
|
| 1429 |
+
"logits/rejected": -0.20158669352531433,
|
| 1430 |
+
"logps/chosen": -532.0164794921875,
|
| 1431 |
+
"logps/rejected": -609.779052734375,
|
| 1432 |
+
"loss": 0.1869,
|
| 1433 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 1434 |
+
"rewards/chosen": -0.10916718095541,
|
| 1435 |
+
"rewards/margins": 0.06110434979200363,
|
| 1436 |
+
"rewards/rejected": -0.17027154564857483,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": -0.13045457005500793,
|
| 1443 |
+
"logits/rejected": -0.15182146430015564,
|
| 1444 |
+
"logps/chosen": -511.3404846191406,
|
| 1445 |
+
"logps/rejected": -542.553466796875,
|
| 1446 |
+
"loss": 0.1791,
|
| 1447 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1448 |
+
"rewards/chosen": -0.10936908423900604,
|
| 1449 |
+
"rewards/margins": 0.04454661160707474,
|
| 1450 |
+
"rewards/rejected": -0.15391568839550018,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": -0.10655238479375839,
|
| 1457 |
+
"logits/rejected": -0.07288862764835358,
|
| 1458 |
+
"logps/chosen": -545.8250732421875,
|
| 1459 |
+
"logps/rejected": -581.5811767578125,
|
| 1460 |
+
"loss": 0.1716,
|
| 1461 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1462 |
+
"rewards/chosen": -0.11866410076618195,
|
| 1463 |
+
"rewards/margins": 0.06786342710256577,
|
| 1464 |
+
"rewards/rejected": -0.18652752041816711,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": -0.18012507259845734,
|
| 1471 |
+
"logits/rejected": -0.11784622818231583,
|
| 1472 |
+
"logps/chosen": -466.735107421875,
|
| 1473 |
+
"logps/rejected": -501.16302490234375,
|
| 1474 |
+
"loss": 0.1912,
|
| 1475 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1476 |
+
"rewards/chosen": -0.10379817336797714,
|
| 1477 |
+
"rewards/margins": 0.051670271903276443,
|
| 1478 |
+
"rewards/rejected": -0.15546846389770508,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": -0.20981307327747345,
|
| 1485 |
+
"logits/rejected": -0.1565089374780655,
|
| 1486 |
+
"logps/chosen": -503.9241638183594,
|
| 1487 |
+
"logps/rejected": -531.1654052734375,
|
| 1488 |
+
"loss": 0.2048,
|
| 1489 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 1490 |
+
"rewards/chosen": -0.11265435069799423,
|
| 1491 |
+
"rewards/margins": 0.036974333226680756,
|
| 1492 |
+
"rewards/rejected": -0.14962869882583618,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": -0.17128372192382812,
|
| 1499 |
+
"logits/rejected": -0.1380850225687027,
|
| 1500 |
+
"logps/chosen": -493.03936767578125,
|
| 1501 |
+
"logps/rejected": -539.0289306640625,
|
| 1502 |
+
"loss": 0.194,
|
| 1503 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 1504 |
+
"rewards/chosen": -0.10857043415307999,
|
| 1505 |
+
"rewards/margins": 0.04022621735930443,
|
| 1506 |
+
"rewards/rejected": -0.14879664778709412,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": -0.14254216849803925,
|
| 1513 |
+
"logits/rejected": -0.13331882655620575,
|
| 1514 |
+
"logps/chosen": -505.95428466796875,
|
| 1515 |
+
"logps/rejected": -575.7135009765625,
|
| 1516 |
+
"loss": 0.1834,
|
| 1517 |
+
"rewards/accuracies": 0.5,
|
| 1518 |
+
"rewards/chosen": -0.11139512062072754,
|
| 1519 |
+
"rewards/margins": 0.05586816743016243,
|
| 1520 |
+
"rewards/rejected": -0.16726329922676086,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": -0.1611151099205017,
|
| 1527 |
+
"logits/rejected": -0.06889496743679047,
|
| 1528 |
+
"logps/chosen": -582.8988037109375,
|
| 1529 |
+
"logps/rejected": -629.1710205078125,
|
| 1530 |
+
"loss": 0.1726,
|
| 1531 |
+
"rewards/accuracies": 0.5625,
|
| 1532 |
+
"rewards/chosen": -0.11593208461999893,
|
| 1533 |
+
"rewards/margins": 0.06972763687372208,
|
| 1534 |
+
"rewards/rejected": -0.1856597363948822,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": -0.22832027077674866,
|
| 1541 |
+
"logits/rejected": -0.03726217523217201,
|
| 1542 |
+
"logps/chosen": -508.06768798828125,
|
| 1543 |
+
"logps/rejected": -514.2000732421875,
|
| 1544 |
+
"loss": 0.1795,
|
| 1545 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 1546 |
+
"rewards/chosen": -0.10370014607906342,
|
| 1547 |
+
"rewards/margins": 0.04398902878165245,
|
| 1548 |
+
"rewards/rejected": -0.14768919348716736,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": -0.20967726409435272,
|
| 1555 |
+
"logits/rejected": -0.1568584442138672,
|
| 1556 |
+
"logps/chosen": -568.8887329101562,
|
| 1557 |
+
"logps/rejected": -614.3547973632812,
|
| 1558 |
+
"loss": 0.1752,
|
| 1559 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1560 |
+
"rewards/chosen": -0.10962442308664322,
|
| 1561 |
+
"rewards/margins": 0.060089100152254105,
|
| 1562 |
+
"rewards/rejected": -0.16971352696418762,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": -0.23702092468738556,
|
| 1569 |
+
"logits/rejected": -0.054711341857910156,
|
| 1570 |
+
"logps/chosen": -569.4314575195312,
|
| 1571 |
+
"logps/rejected": -610.4983520507812,
|
| 1572 |
+
"loss": 0.1861,
|
| 1573 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1574 |
+
"rewards/chosen": -0.13101813197135925,
|
| 1575 |
+
"rewards/margins": 0.043327562510967255,
|
| 1576 |
+
"rewards/rejected": -0.1743457019329071,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": -0.13204485177993774,
|
| 1583 |
+
"logits/rejected": -0.18103663623332977,
|
| 1584 |
+
"logps/chosen": -501.7928771972656,
|
| 1585 |
+
"logps/rejected": -548.9622192382812,
|
| 1586 |
+
"loss": 0.1908,
|
| 1587 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1588 |
+
"rewards/chosen": -0.10908225923776627,
|
| 1589 |
+
"rewards/margins": 0.034237340092659,
|
| 1590 |
+
"rewards/rejected": -0.14331960678100586,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": -0.178396537899971,
|
| 1597 |
+
"logits/rejected": -0.2268516570329666,
|
| 1598 |
+
"logps/chosen": -512.7816772460938,
|
| 1599 |
+
"logps/rejected": -568.0106811523438,
|
| 1600 |
+
"loss": 0.1771,
|
| 1601 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1602 |
+
"rewards/chosen": -0.11387573182582855,
|
| 1603 |
+
"rewards/margins": 0.05218449980020523,
|
| 1604 |
+
"rewards/rejected": -0.16606023907661438,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": -0.18940022587776184,
|
| 1611 |
+
"logits/rejected": -0.2560541033744812,
|
| 1612 |
+
"logps/chosen": -531.294677734375,
|
| 1613 |
+
"logps/rejected": -585.197509765625,
|
| 1614 |
+
"loss": 0.1857,
|
| 1615 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1616 |
+
"rewards/chosen": -0.10909552872180939,
|
| 1617 |
+
"rewards/margins": 0.05390959978103638,
|
| 1618 |
+
"rewards/rejected": -0.16300514340400696,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": -0.17567074298858643,
|
| 1625 |
+
"logits/rejected": -0.08641554415225983,
|
| 1626 |
+
"logps/chosen": -553.5035400390625,
|
| 1627 |
+
"logps/rejected": -660.8178100585938,
|
| 1628 |
+
"loss": 0.1567,
|
| 1629 |
+
"rewards/accuracies": 0.612500011920929,
|
| 1630 |
+
"rewards/chosen": -0.10895760357379913,
|
| 1631 |
+
"rewards/margins": 0.08049053698778152,
|
| 1632 |
+
"rewards/rejected": -0.18944814801216125,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": -0.23474335670471191,
|
| 1639 |
+
"logits/rejected": -0.10942939668893814,
|
| 1640 |
+
"logps/chosen": -514.3484497070312,
|
| 1641 |
+
"logps/rejected": -560.9384765625,
|
| 1642 |
+
"loss": 0.1795,
|
| 1643 |
+
"rewards/accuracies": 0.46875,
|
| 1644 |
+
"rewards/chosen": -0.10143520683050156,
|
| 1645 |
+
"rewards/margins": 0.06253394484519958,
|
| 1646 |
+
"rewards/rejected": -0.16396915912628174,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": -0.20588059723377228,
|
| 1653 |
+
"logits/rejected": -0.11454887688159943,
|
| 1654 |
+
"logps/chosen": -492.59356689453125,
|
| 1655 |
+
"logps/rejected": -502.0108947753906,
|
| 1656 |
+
"loss": 0.1959,
|
| 1657 |
+
"rewards/accuracies": 0.4375,
|
| 1658 |
+
"rewards/chosen": -0.11700236797332764,
|
| 1659 |
+
"rewards/margins": 0.039218030869960785,
|
| 1660 |
+
"rewards/rejected": -0.15622040629386902,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": -0.1135745421051979,
|
| 1667 |
+
"logits/rejected": -0.21998748183250427,
|
| 1668 |
+
"logps/chosen": -511.43975830078125,
|
| 1669 |
+
"logps/rejected": -591.8009033203125,
|
| 1670 |
+
"loss": 0.1752,
|
| 1671 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1672 |
+
"rewards/chosen": -0.11385758221149445,
|
| 1673 |
+
"rewards/margins": 0.062401823699474335,
|
| 1674 |
+
"rewards/rejected": -0.17625939846038818,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": -0.1687012016773224,
|
| 1681 |
+
"logits/rejected": -0.09966389834880829,
|
| 1682 |
+
"logps/chosen": -462.24664306640625,
|
| 1683 |
+
"logps/rejected": -541.049072265625,
|
| 1684 |
+
"loss": 0.1691,
|
| 1685 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1686 |
+
"rewards/chosen": -0.11714209616184235,
|
| 1687 |
+
"rewards/margins": 0.0646623969078064,
|
| 1688 |
+
"rewards/rejected": -0.18180450797080994,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": -0.246677964925766,
|
| 1695 |
+
"logits/rejected": -0.1048688292503357,
|
| 1696 |
+
"logps/chosen": -603.5682983398438,
|
| 1697 |
+
"logps/rejected": -627.1761474609375,
|
| 1698 |
+
"loss": 0.1809,
|
| 1699 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 1700 |
+
"rewards/chosen": -0.14629192650318146,
|
| 1701 |
+
"rewards/margins": 0.04966907575726509,
|
| 1702 |
+
"rewards/rejected": -0.19596099853515625,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": -0.19738665223121643,
|
| 1709 |
+
"logits/rejected": -0.19479918479919434,
|
| 1710 |
+
"logps/chosen": -532.4442138671875,
|
| 1711 |
+
"logps/rejected": -585.4338989257812,
|
| 1712 |
+
"loss": 0.182,
|
| 1713 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1714 |
+
"rewards/chosen": -0.12195596843957901,
|
| 1715 |
+
"rewards/margins": 0.06082000583410263,
|
| 1716 |
+
"rewards/rejected": -0.18277597427368164,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": -0.25693798065185547,
|
| 1723 |
+
"logits/rejected": -0.07481320202350616,
|
| 1724 |
+
"logps/chosen": -533.8644409179688,
|
| 1725 |
+
"logps/rejected": -563.401123046875,
|
| 1726 |
+
"loss": 0.197,
|
| 1727 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1728 |
+
"rewards/chosen": -0.12102751433849335,
|
| 1729 |
+
"rewards/margins": 0.05077686160802841,
|
| 1730 |
+
"rewards/rejected": -0.17180435359477997,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": -0.2309873402118683,
|
| 1737 |
+
"logits/rejected": -0.10137152671813965,
|
| 1738 |
+
"logps/chosen": -551.7896728515625,
|
| 1739 |
+
"logps/rejected": -624.3748779296875,
|
| 1740 |
+
"loss": 0.19,
|
| 1741 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1742 |
+
"rewards/chosen": -0.11541406065225601,
|
| 1743 |
+
"rewards/margins": 0.06133885309100151,
|
| 1744 |
+
"rewards/rejected": -0.17675292491912842,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": -0.2246209681034088,
|
| 1751 |
+
"logits/rejected": -0.13239261507987976,
|
| 1752 |
+
"logps/chosen": -519.9109497070312,
|
| 1753 |
+
"logps/rejected": -560.1650390625,
|
| 1754 |
+
"loss": 0.1923,
|
| 1755 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1756 |
+
"rewards/chosen": -0.1011136993765831,
|
| 1757 |
+
"rewards/margins": 0.05040975660085678,
|
| 1758 |
+
"rewards/rejected": -0.15152345597743988,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": -0.16264840960502625,
|
| 1765 |
+
"logits/rejected": -0.17924869060516357,
|
| 1766 |
+
"logps/chosen": -568.4891967773438,
|
| 1767 |
+
"logps/rejected": -606.84375,
|
| 1768 |
+
"loss": 0.1893,
|
| 1769 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1770 |
+
"rewards/chosen": -0.11496226489543915,
|
| 1771 |
+
"rewards/margins": 0.05937162786722183,
|
| 1772 |
+
"rewards/rejected": -0.17433388531208038,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": -0.23676082491874695,
|
| 1779 |
+
"logits/rejected": -0.10287532955408096,
|
| 1780 |
+
"logps/chosen": -539.798095703125,
|
| 1781 |
+
"logps/rejected": -559.6898193359375,
|
| 1782 |
+
"loss": 0.1844,
|
| 1783 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1784 |
+
"rewards/chosen": -0.103573277592659,
|
| 1785 |
+
"rewards/margins": 0.044529445469379425,
|
| 1786 |
+
"rewards/rejected": -0.14810271561145782,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": -0.16643217206001282,
|
| 1793 |
+
"logits/rejected": -0.20663738250732422,
|
| 1794 |
+
"logps/chosen": -477.3910217285156,
|
| 1795 |
+
"logps/rejected": -546.283203125,
|
| 1796 |
+
"loss": 0.1722,
|
| 1797 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1798 |
+
"rewards/chosen": -0.09414063394069672,
|
| 1799 |
+
"rewards/margins": 0.0609886460006237,
|
| 1800 |
+
"rewards/rejected": -0.15512928366661072,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": -0.2298511266708374,
|
| 1807 |
+
"logits/rejected": -0.11243085563182831,
|
| 1808 |
+
"logps/chosen": -501.55517578125,
|
| 1809 |
+
"logps/rejected": -560.3333740234375,
|
| 1810 |
+
"loss": 0.2001,
|
| 1811 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1812 |
+
"rewards/chosen": -0.10863594710826874,
|
| 1813 |
+
"rewards/margins": 0.04755181074142456,
|
| 1814 |
+
"rewards/rejected": -0.1561877578496933,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": -0.24995306134223938,
|
| 1821 |
+
"logits/rejected": -0.09091716259717941,
|
| 1822 |
+
"logps/chosen": -546.91455078125,
|
| 1823 |
+
"logps/rejected": -573.63134765625,
|
| 1824 |
+
"loss": 0.1758,
|
| 1825 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1826 |
+
"rewards/chosen": -0.09987141191959381,
|
| 1827 |
+
"rewards/margins": 0.051563430577516556,
|
| 1828 |
+
"rewards/rejected": -0.15143482387065887,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": -0.20659741759300232,
|
| 1835 |
+
"logits/rejected": -0.1793586015701294,
|
| 1836 |
+
"logps/chosen": -461.78741455078125,
|
| 1837 |
+
"logps/rejected": -546.7547607421875,
|
| 1838 |
+
"loss": 0.1772,
|
| 1839 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1840 |
+
"rewards/chosen": -0.09007732570171356,
|
| 1841 |
+
"rewards/margins": 0.06504637002944946,
|
| 1842 |
+
"rewards/rejected": -0.15512368083000183,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": -0.16400612890720367,
|
| 1849 |
+
"logits/rejected": -0.10733946412801743,
|
| 1850 |
+
"logps/chosen": -477.58673095703125,
|
| 1851 |
+
"logps/rejected": -483.0821838378906,
|
| 1852 |
+
"loss": 0.1908,
|
| 1853 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 1854 |
+
"rewards/chosen": -0.09252551943063736,
|
| 1855 |
+
"rewards/margins": 0.03763090446591377,
|
| 1856 |
+
"rewards/rejected": -0.13015642762184143,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": -0.23552432656288147,
|
| 1863 |
+
"logits/rejected": -0.05100318789482117,
|
| 1864 |
+
"logps/chosen": -508.714111328125,
|
| 1865 |
+
"logps/rejected": -520.7734375,
|
| 1866 |
+
"loss": 0.1903,
|
| 1867 |
+
"rewards/accuracies": 0.40625,
|
| 1868 |
+
"rewards/chosen": -0.10599436610937119,
|
| 1869 |
+
"rewards/margins": 0.04144153743982315,
|
| 1870 |
+
"rewards/rejected": -0.14743590354919434,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": -0.23125293850898743,
|
| 1877 |
+
"logits/rejected": -0.17557989060878754,
|
| 1878 |
+
"logps/chosen": -544.9722900390625,
|
| 1879 |
+
"logps/rejected": -586.7325439453125,
|
| 1880 |
+
"loss": 0.1788,
|
| 1881 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1882 |
+
"rewards/chosen": -0.10128601640462875,
|
| 1883 |
+
"rewards/margins": 0.07126955687999725,
|
| 1884 |
+
"rewards/rejected": -0.1725555956363678,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": -0.23312774300575256,
|
| 1891 |
+
"logits/rejected": -0.14277367293834686,
|
| 1892 |
+
"logps/chosen": -485.92535400390625,
|
| 1893 |
+
"logps/rejected": -506.35205078125,
|
| 1894 |
+
"loss": 0.194,
|
| 1895 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1896 |
+
"rewards/chosen": -0.09930580854415894,
|
| 1897 |
+
"rewards/margins": 0.03314018249511719,
|
| 1898 |
+
"rewards/rejected": -0.13244597613811493,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": -0.18930380046367645,
|
| 1905 |
+
"logits/rejected": -0.14925286173820496,
|
| 1906 |
+
"logps/chosen": -466.244140625,
|
| 1907 |
+
"logps/rejected": -539.2670288085938,
|
| 1908 |
+
"loss": 0.1836,
|
| 1909 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1910 |
+
"rewards/chosen": -0.09682577848434448,
|
| 1911 |
+
"rewards/margins": 0.0532786026597023,
|
| 1912 |
+
"rewards/rejected": -0.1501043736934662,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": -0.19082944095134735,
|
| 1919 |
+
"logits/rejected": -0.18094971776008606,
|
| 1920 |
+
"logps/chosen": -499.90362548828125,
|
| 1921 |
+
"logps/rejected": -542.33251953125,
|
| 1922 |
+
"loss": 0.1693,
|
| 1923 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1924 |
+
"rewards/chosen": -0.09551337361335754,
|
| 1925 |
+
"rewards/margins": 0.051950085908174515,
|
| 1926 |
+
"rewards/rejected": -0.14746347069740295,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": -0.19364750385284424,
|
| 1933 |
+
"logits/rejected": -0.22844457626342773,
|
| 1934 |
+
"logps/chosen": -481.7339782714844,
|
| 1935 |
+
"logps/rejected": -537.8257446289062,
|
| 1936 |
+
"loss": 0.173,
|
| 1937 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1938 |
+
"rewards/chosen": -0.10904572159051895,
|
| 1939 |
+
"rewards/margins": 0.05478460714221001,
|
| 1940 |
+
"rewards/rejected": -0.16383032500743866,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": -0.1437099277973175,
|
| 1947 |
+
"logits/rejected": -0.1075567975640297,
|
| 1948 |
+
"logps/chosen": -463.90985107421875,
|
| 1949 |
+
"logps/rejected": -566.3432006835938,
|
| 1950 |
+
"loss": 0.1896,
|
| 1951 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1952 |
+
"rewards/chosen": -0.09277530014514923,
|
| 1953 |
+
"rewards/margins": 0.0687888115644455,
|
| 1954 |
+
"rewards/rejected": -0.16156412661075592,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": -0.242875337600708,
|
| 1961 |
+
"logits/rejected": -0.16699561476707458,
|
| 1962 |
+
"logps/chosen": -552.685302734375,
|
| 1963 |
+
"logps/rejected": -590.0584106445312,
|
| 1964 |
+
"loss": 0.1848,
|
| 1965 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1966 |
+
"rewards/chosen": -0.11167445033788681,
|
| 1967 |
+
"rewards/margins": 0.04991639405488968,
|
| 1968 |
+
"rewards/rejected": -0.1615908443927765,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": -0.11828355491161346,
|
| 1975 |
+
"logits/rejected": -0.20383377373218536,
|
| 1976 |
+
"logps/chosen": -546.3382568359375,
|
| 1977 |
+
"logps/rejected": -630.2655029296875,
|
| 1978 |
+
"loss": 0.1791,
|
| 1979 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1980 |
+
"rewards/chosen": -0.10707902908325195,
|
| 1981 |
+
"rewards/margins": 0.07424376159906387,
|
| 1982 |
+
"rewards/rejected": -0.18132279813289642,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": -0.14532892405986786,
|
| 1989 |
+
"logits/rejected": -0.23003335297107697,
|
| 1990 |
+
"logps/chosen": -478.4186096191406,
|
| 1991 |
+
"logps/rejected": -552.7274169921875,
|
| 1992 |
+
"loss": 0.1775,
|
| 1993 |
+
"rewards/accuracies": 0.53125,
|
| 1994 |
+
"rewards/chosen": -0.09584512561559677,
|
| 1995 |
+
"rewards/margins": 0.06631821393966675,
|
| 1996 |
+
"rewards/rejected": -0.16216334700584412,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": -0.20046038925647736,
|
| 2003 |
+
"logits/rejected": -0.15967608988285065,
|
| 2004 |
+
"logps/chosen": -544.1749267578125,
|
| 2005 |
+
"logps/rejected": -586.116943359375,
|
| 2006 |
+
"loss": 0.1792,
|
| 2007 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 2008 |
+
"rewards/chosen": -0.11548880487680435,
|
| 2009 |
+
"rewards/margins": 0.05985084921121597,
|
| 2010 |
+
"rewards/rejected": -0.17533965408802032,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": -0.19410791993141174,
|
| 2017 |
+
"logits/rejected": -0.23477724194526672,
|
| 2018 |
+
"logps/chosen": -451.70941162109375,
|
| 2019 |
+
"logps/rejected": -480.71881103515625,
|
| 2020 |
+
"loss": 0.1821,
|
| 2021 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 2022 |
+
"rewards/chosen": -0.09721177071332932,
|
| 2023 |
+
"rewards/margins": 0.04050077125430107,
|
| 2024 |
+
"rewards/rejected": -0.1377125382423401,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": -0.1642087996006012,
|
| 2031 |
+
"logits/rejected": -0.230143740773201,
|
| 2032 |
+
"logps/chosen": -522.2006225585938,
|
| 2033 |
+
"logps/rejected": -582.2677612304688,
|
| 2034 |
+
"loss": 0.1954,
|
| 2035 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 2036 |
+
"rewards/chosen": -0.11323000490665436,
|
| 2037 |
+
"rewards/margins": 0.06264480203390121,
|
| 2038 |
+
"rewards/rejected": -0.17587482929229736,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": -0.2773049473762512,
|
| 2045 |
+
"logits/rejected": -0.1615469753742218,
|
| 2046 |
+
"logps/chosen": -547.8629760742188,
|
| 2047 |
+
"logps/rejected": -587.5028076171875,
|
| 2048 |
+
"loss": 0.1817,
|
| 2049 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 2050 |
+
"rewards/chosen": -0.11454708874225616,
|
| 2051 |
+
"rewards/margins": 0.0604601725935936,
|
| 2052 |
+
"rewards/rejected": -0.17500726878643036,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": -0.16052532196044922,
|
| 2059 |
+
"logits/rejected": -0.25322675704956055,
|
| 2060 |
+
"logps/chosen": -515.0181884765625,
|
| 2061 |
+
"logps/rejected": -600.516357421875,
|
| 2062 |
+
"loss": 0.1766,
|
| 2063 |
+
"rewards/accuracies": 0.574999988079071,
|
| 2064 |
+
"rewards/chosen": -0.12128403037786484,
|
| 2065 |
+
"rewards/margins": 0.06581829488277435,
|
| 2066 |
+
"rewards/rejected": -0.1871023178100586,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": -0.2754663825035095,
|
| 2073 |
+
"logits/rejected": -0.19558298587799072,
|
| 2074 |
+
"logps/chosen": -479.9947204589844,
|
| 2075 |
+
"logps/rejected": -522.5654296875,
|
| 2076 |
+
"loss": 0.1816,
|
| 2077 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 2078 |
+
"rewards/chosen": -0.10307195037603378,
|
| 2079 |
+
"rewards/margins": 0.05991575866937637,
|
| 2080 |
+
"rewards/rejected": -0.16298770904541016,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": -0.3147231340408325,
|
| 2087 |
+
"logits/rejected": -0.12713433802127838,
|
| 2088 |
+
"logps/chosen": -576.8265380859375,
|
| 2089 |
+
"logps/rejected": -582.334716796875,
|
| 2090 |
+
"loss": 0.2017,
|
| 2091 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 2092 |
+
"rewards/chosen": -0.13038143515586853,
|
| 2093 |
+
"rewards/margins": 0.05221244692802429,
|
| 2094 |
+
"rewards/rejected": -0.18259385228157043,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": -0.20450320839881897,
|
| 2101 |
+
"logits/rejected": -0.2868250906467438,
|
| 2102 |
+
"logps/chosen": -535.9012451171875,
|
| 2103 |
+
"logps/rejected": -593.1867065429688,
|
| 2104 |
+
"loss": 0.1831,
|
| 2105 |
+
"rewards/accuracies": 0.5,
|
| 2106 |
+
"rewards/chosen": -0.11613848060369492,
|
| 2107 |
+
"rewards/margins": 0.05925974249839783,
|
| 2108 |
+
"rewards/rejected": -0.17539823055267334,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": -0.20174920558929443,
|
| 2115 |
+
"logits/rejected": -0.17505855858325958,
|
| 2116 |
+
"logps/chosen": -544.5908813476562,
|
| 2117 |
+
"logps/rejected": -570.7057495117188,
|
| 2118 |
+
"loss": 0.1812,
|
| 2119 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 2120 |
+
"rewards/chosen": -0.12965530157089233,
|
| 2121 |
+
"rewards/margins": 0.03963715583086014,
|
| 2122 |
+
"rewards/rejected": -0.16929244995117188,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": -0.17067115008831024,
|
| 2129 |
+
"logits/rejected": -0.23377446830272675,
|
| 2130 |
+
"logps/chosen": -544.231201171875,
|
| 2131 |
+
"logps/rejected": -599.497802734375,
|
| 2132 |
+
"loss": 0.1781,
|
| 2133 |
+
"rewards/accuracies": 0.543749988079071,
|
| 2134 |
+
"rewards/chosen": -0.11236411333084106,
|
| 2135 |
+
"rewards/margins": 0.05633332207798958,
|
| 2136 |
+
"rewards/rejected": -0.16869743168354034,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": -0.2045322209596634,
|
| 2143 |
+
"logits/rejected": -0.19451120495796204,
|
| 2144 |
+
"logps/chosen": -543.3025512695312,
|
| 2145 |
+
"logps/rejected": -558.47119140625,
|
| 2146 |
+
"loss": 0.1912,
|
| 2147 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 2148 |
+
"rewards/chosen": -0.12296583503484726,
|
| 2149 |
+
"rewards/margins": 0.03358592838048935,
|
| 2150 |
+
"rewards/rejected": -0.1565517634153366,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": -0.23366038501262665,
|
| 2157 |
+
"logits/rejected": -0.2533060610294342,
|
| 2158 |
+
"logps/chosen": -494.28082275390625,
|
| 2159 |
+
"logps/rejected": -536.08251953125,
|
| 2160 |
+
"loss": 0.1975,
|
| 2161 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 2162 |
+
"rewards/chosen": -0.11815425008535385,
|
| 2163 |
+
"rewards/margins": 0.03765954449772835,
|
| 2164 |
+
"rewards/rejected": -0.1558137983083725,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": -0.25420263409614563,
|
| 2171 |
+
"logits/rejected": -0.10746750980615616,
|
| 2172 |
+
"logps/chosen": -496.64349365234375,
|
| 2173 |
+
"logps/rejected": -555.2488403320312,
|
| 2174 |
+
"loss": 0.1853,
|
| 2175 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 2176 |
+
"rewards/chosen": -0.10732255131006241,
|
| 2177 |
+
"rewards/margins": 0.05255774408578873,
|
| 2178 |
+
"rewards/rejected": -0.15988029539585114,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": -0.230036661028862,
|
| 2185 |
+
"logits/rejected": -0.16146495938301086,
|
| 2186 |
+
"logps/chosen": -498.93365478515625,
|
| 2187 |
+
"logps/rejected": -519.977783203125,
|
| 2188 |
+
"loss": 0.179,
|
| 2189 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 2190 |
+
"rewards/chosen": -0.09960173070430756,
|
| 2191 |
+
"rewards/margins": 0.04401581361889839,
|
| 2192 |
+
"rewards/rejected": -0.14361754059791565,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": -0.14786578714847565,
|
| 2199 |
+
"logits/rejected": -0.1643018275499344,
|
| 2200 |
+
"logps/chosen": -516.0054931640625,
|
| 2201 |
+
"logps/rejected": -543.8809814453125,
|
| 2202 |
+
"loss": 0.1974,
|
| 2203 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 2204 |
+
"rewards/chosen": -0.10642917454242706,
|
| 2205 |
+
"rewards/margins": 0.05054362863302231,
|
| 2206 |
+
"rewards/rejected": -0.15697282552719116,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": -0.26063111424446106,
|
| 2213 |
+
"logits/rejected": -0.20259733498096466,
|
| 2214 |
+
"logps/chosen": -477.3902893066406,
|
| 2215 |
+
"logps/rejected": -544.326416015625,
|
| 2216 |
+
"loss": 0.1805,
|
| 2217 |
+
"rewards/accuracies": 0.5,
|
| 2218 |
+
"rewards/chosen": -0.11126448959112167,
|
| 2219 |
+
"rewards/margins": 0.053704213351011276,
|
| 2220 |
+
"rewards/rejected": -0.16496869921684265,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": -0.19165876507759094,
|
| 2227 |
+
"logits/rejected": -0.2015565186738968,
|
| 2228 |
+
"logps/chosen": -514.6396484375,
|
| 2229 |
+
"logps/rejected": -582.6300659179688,
|
| 2230 |
+
"loss": 0.1798,
|
| 2231 |
+
"rewards/accuracies": 0.5,
|
| 2232 |
+
"rewards/chosen": -0.11115659773349762,
|
| 2233 |
+
"rewards/margins": 0.05640328675508499,
|
| 2234 |
+
"rewards/rejected": -0.1675598919391632,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": -0.24871298670768738,
|
| 2241 |
+
"logits/rejected": -0.2329408824443817,
|
| 2242 |
+
"logps/chosen": -527.1490478515625,
|
| 2243 |
+
"logps/rejected": -558.3999633789062,
|
| 2244 |
+
"loss": 0.1913,
|
| 2245 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 2246 |
+
"rewards/chosen": -0.10850969702005386,
|
| 2247 |
+
"rewards/margins": 0.04025677964091301,
|
| 2248 |
+
"rewards/rejected": -0.14876648783683777,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": -0.1298540085554123,
|
| 2255 |
+
"logits/rejected": -0.22532661259174347,
|
| 2256 |
+
"logps/chosen": -549.50390625,
|
| 2257 |
+
"logps/rejected": -626.0857543945312,
|
| 2258 |
+
"loss": 0.1837,
|
| 2259 |
+
"rewards/accuracies": 0.5,
|
| 2260 |
+
"rewards/chosen": -0.13459596037864685,
|
| 2261 |
+
"rewards/margins": 0.053374581038951874,
|
| 2262 |
+
"rewards/rejected": -0.18797054886817932,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": -0.1630309522151947,
|
| 2269 |
+
"logits/rejected": -0.2934538722038269,
|
| 2270 |
+
"logps/chosen": -513.16943359375,
|
| 2271 |
+
"logps/rejected": -542.3517456054688,
|
| 2272 |
+
"loss": 0.1856,
|
| 2273 |
+
"rewards/accuracies": 0.5,
|
| 2274 |
+
"rewards/chosen": -0.1167718768119812,
|
| 2275 |
+
"rewards/margins": 0.04849160462617874,
|
| 2276 |
+
"rewards/rejected": -0.16526347398757935,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": -0.24708867073059082,
|
| 2283 |
+
"logits/rejected": -0.21414759755134583,
|
| 2284 |
+
"logps/chosen": -569.2642822265625,
|
| 2285 |
+
"logps/rejected": -592.0335693359375,
|
| 2286 |
+
"loss": 0.1832,
|
| 2287 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 2288 |
+
"rewards/chosen": -0.1170465499162674,
|
| 2289 |
+
"rewards/margins": 0.04982801154255867,
|
| 2290 |
+
"rewards/rejected": -0.16687455773353577,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": -0.2323312759399414,
|
| 2297 |
+
"logits/rejected": -0.0636955201625824,
|
| 2298 |
+
"logps/chosen": -530.3974609375,
|
| 2299 |
+
"logps/rejected": -546.2402954101562,
|
| 2300 |
+
"loss": 0.196,
|
| 2301 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2302 |
+
"rewards/chosen": -0.10811781883239746,
|
| 2303 |
+
"rewards/margins": 0.05536898970603943,
|
| 2304 |
+
"rewards/rejected": -0.1634868085384369,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": -0.2858187258243561,
|
| 2311 |
+
"logits/rejected": -0.16766619682312012,
|
| 2312 |
+
"logps/chosen": -497.91876220703125,
|
| 2313 |
+
"logps/rejected": -530.9742431640625,
|
| 2314 |
+
"loss": 0.1815,
|
| 2315 |
+
"rewards/accuracies": 0.543749988079071,
|
| 2316 |
+
"rewards/chosen": -0.09212108701467514,
|
| 2317 |
+
"rewards/margins": 0.06050460413098335,
|
| 2318 |
+
"rewards/rejected": -0.1526256948709488,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": -0.18948575854301453,
|
| 2325 |
+
"logits/rejected": -0.2522360682487488,
|
| 2326 |
+
"logps/chosen": -498.93951416015625,
|
| 2327 |
+
"logps/rejected": -548.31787109375,
|
| 2328 |
+
"loss": 0.1875,
|
| 2329 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 2330 |
+
"rewards/chosen": -0.10647443681955338,
|
| 2331 |
+
"rewards/margins": 0.06186903268098831,
|
| 2332 |
+
"rewards/rejected": -0.1683434695005417,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": -0.20894873142242432,
|
| 2339 |
+
"logits/rejected": -0.07307926565408707,
|
| 2340 |
+
"logps/chosen": -496.451416015625,
|
| 2341 |
+
"logps/rejected": -536.22119140625,
|
| 2342 |
+
"loss": 0.1744,
|
| 2343 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 2344 |
+
"rewards/chosen": -0.10921342670917511,
|
| 2345 |
+
"rewards/margins": 0.05700286105275154,
|
| 2346 |
+
"rewards/rejected": -0.16621626913547516,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": -0.2548653483390808,
|
| 2353 |
+
"logits/rejected": -0.2179504930973053,
|
| 2354 |
+
"logps/chosen": -520.787841796875,
|
| 2355 |
+
"logps/rejected": -576.6990966796875,
|
| 2356 |
+
"loss": 0.1716,
|
| 2357 |
+
"rewards/accuracies": 0.5,
|
| 2358 |
+
"rewards/chosen": -0.10316022485494614,
|
| 2359 |
+
"rewards/margins": 0.06640519946813583,
|
| 2360 |
+
"rewards/rejected": -0.16956540942192078,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": -0.14907491207122803,
|
| 2367 |
+
"logits/rejected": -0.18132783472537994,
|
| 2368 |
+
"logps/chosen": -493.564697265625,
|
| 2369 |
+
"logps/rejected": -568.8427734375,
|
| 2370 |
+
"loss": 0.1922,
|
| 2371 |
+
"rewards/accuracies": 0.512499988079071,
|
| 2372 |
+
"rewards/chosen": -0.11788590997457504,
|
| 2373 |
+
"rewards/margins": 0.05090482905507088,
|
| 2374 |
+
"rewards/rejected": -0.16879074275493622,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": -0.2242707461118698,
|
| 2381 |
+
"logits/rejected": -0.16642411053180695,
|
| 2382 |
+
"logps/chosen": -527.6796875,
|
| 2383 |
+
"logps/rejected": -568.4700927734375,
|
| 2384 |
+
"loss": 0.1721,
|
| 2385 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 2386 |
+
"rewards/chosen": -0.10909800231456757,
|
| 2387 |
+
"rewards/margins": 0.05576147884130478,
|
| 2388 |
+
"rewards/rejected": -0.16485948860645294,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": -0.1916467398405075,
|
| 2395 |
+
"logits/rejected": -0.21406717598438263,
|
| 2396 |
+
"logps/chosen": -564.77880859375,
|
| 2397 |
+
"logps/rejected": -602.3505859375,
|
| 2398 |
+
"loss": 0.1906,
|
| 2399 |
+
"rewards/accuracies": 0.5,
|
| 2400 |
+
"rewards/chosen": -0.12277360260486603,
|
| 2401 |
+
"rewards/margins": 0.04569784551858902,
|
| 2402 |
+
"rewards/rejected": -0.16847144067287445,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": -0.20755720138549805,
|
| 2409 |
+
"logits/rejected": -0.1797691434621811,
|
| 2410 |
+
"logps/chosen": -478.31634521484375,
|
| 2411 |
+
"logps/rejected": -570.5222778320312,
|
| 2412 |
+
"loss": 0.1803,
|
| 2413 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2414 |
+
"rewards/chosen": -0.10136885941028595,
|
| 2415 |
+
"rewards/margins": 0.07469947636127472,
|
| 2416 |
+
"rewards/rejected": -0.17606833577156067,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": -0.15231382846832275,
|
| 2423 |
+
"logits/rejected": -0.20254746079444885,
|
| 2424 |
+
"logps/chosen": -493.1875915527344,
|
| 2425 |
+
"logps/rejected": -561.9268188476562,
|
| 2426 |
+
"loss": 0.1827,
|
| 2427 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 2428 |
+
"rewards/chosen": -0.10837433487176895,
|
| 2429 |
+
"rewards/margins": 0.05267762392759323,
|
| 2430 |
+
"rewards/rejected": -0.16105195879936218,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": -0.33545562624931335,
|
| 2437 |
+
"logits/rejected": -0.14177361130714417,
|
| 2438 |
+
"logps/chosen": -489.1234436035156,
|
| 2439 |
+
"logps/rejected": -541.3236694335938,
|
| 2440 |
+
"loss": 0.1817,
|
| 2441 |
+
"rewards/accuracies": 0.46875,
|
| 2442 |
+
"rewards/chosen": -0.10399062931537628,
|
| 2443 |
+
"rewards/margins": 0.052609704434871674,
|
| 2444 |
+
"rewards/rejected": -0.15660032629966736,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": -0.18932399153709412,
|
| 2451 |
+
"logits/rejected": -0.16892239451408386,
|
| 2452 |
+
"logps/chosen": -535.3873291015625,
|
| 2453 |
+
"logps/rejected": -541.3253173828125,
|
| 2454 |
+
"loss": 0.1843,
|
| 2455 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2456 |
+
"rewards/chosen": -0.11377620697021484,
|
| 2457 |
+
"rewards/margins": 0.04663427174091339,
|
| 2458 |
+
"rewards/rejected": -0.16041049361228943,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": -0.171333447098732,
|
| 2465 |
+
"logits/rejected": -0.1328922063112259,
|
| 2466 |
+
"logps/chosen": -491.8202209472656,
|
| 2467 |
+
"logps/rejected": -543.0697021484375,
|
| 2468 |
+
"loss": 0.1924,
|
| 2469 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 2470 |
+
"rewards/chosen": -0.1006278246641159,
|
| 2471 |
+
"rewards/margins": 0.05380718782544136,
|
| 2472 |
+
"rewards/rejected": -0.15443500876426697,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": -0.24088236689567566,
|
| 2479 |
+
"logits/rejected": -0.15874245762825012,
|
| 2480 |
+
"logps/chosen": -508.15496826171875,
|
| 2481 |
+
"logps/rejected": -554.2071533203125,
|
| 2482 |
+
"loss": 0.1761,
|
| 2483 |
+
"rewards/accuracies": 0.518750011920929,
|
| 2484 |
+
"rewards/chosen": -0.10783319175243378,
|
| 2485 |
+
"rewards/margins": 0.05231726914644241,
|
| 2486 |
+
"rewards/rejected": -0.1601504534482956,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": -0.35891515016555786,
|
| 2493 |
+
"logits/rejected": -0.10517171770334244,
|
| 2494 |
+
"logps/chosen": -558.290771484375,
|
| 2495 |
+
"logps/rejected": -577.0843505859375,
|
| 2496 |
+
"loss": 0.1852,
|
| 2497 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2498 |
+
"rewards/chosen": -0.1132727861404419,
|
| 2499 |
+
"rewards/margins": 0.04631791263818741,
|
| 2500 |
+
"rewards/rejected": -0.1595907062292099,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": -0.25900477170944214,
|
| 2507 |
+
"logits/rejected": -0.2353241741657257,
|
| 2508 |
+
"logps/chosen": -511.06231689453125,
|
| 2509 |
+
"logps/rejected": -571.1373291015625,
|
| 2510 |
+
"loss": 0.181,
|
| 2511 |
+
"rewards/accuracies": 0.5,
|
| 2512 |
+
"rewards/chosen": -0.1033167615532875,
|
| 2513 |
+
"rewards/margins": 0.05643168091773987,
|
| 2514 |
+
"rewards/rejected": -0.15974844992160797,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": -0.25551778078079224,
|
| 2521 |
+
"logits/rejected": -0.1563359797000885,
|
| 2522 |
+
"logps/chosen": -518.1477661132812,
|
| 2523 |
+
"logps/rejected": -544.9768676757812,
|
| 2524 |
+
"loss": 0.1796,
|
| 2525 |
+
"rewards/accuracies": 0.518750011920929,
|
| 2526 |
+
"rewards/chosen": -0.1060783639550209,
|
| 2527 |
+
"rewards/margins": 0.061492882668972015,
|
| 2528 |
+
"rewards/rejected": -0.16757124662399292,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": -0.306395947933197,
|
| 2535 |
+
"logits/rejected": -0.20862647891044617,
|
| 2536 |
+
"logps/chosen": -527.55908203125,
|
| 2537 |
+
"logps/rejected": -568.0324096679688,
|
| 2538 |
+
"loss": 0.1903,
|
| 2539 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2540 |
+
"rewards/chosen": -0.11323089897632599,
|
| 2541 |
+
"rewards/margins": 0.051735300570726395,
|
| 2542 |
+
"rewards/rejected": -0.16496619582176208,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": -0.2206902951002121,
|
| 2549 |
+
"logits/rejected": -0.22108717262744904,
|
| 2550 |
+
"logps/chosen": -513.4564208984375,
|
| 2551 |
+
"logps/rejected": -591.93701171875,
|
| 2552 |
+
"loss": 0.1774,
|
| 2553 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 2554 |
+
"rewards/chosen": -0.10885292291641235,
|
| 2555 |
+
"rewards/margins": 0.06501305848360062,
|
| 2556 |
+
"rewards/rejected": -0.17386598885059357,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": -0.11251676082611084,
|
| 2563 |
+
"logits/rejected": -0.19971203804016113,
|
| 2564 |
+
"logps/chosen": -483.9027404785156,
|
| 2565 |
+
"logps/rejected": -568.6507568359375,
|
| 2566 |
+
"loss": 0.1638,
|
| 2567 |
+
"rewards/accuracies": 0.550000011920929,
|
| 2568 |
+
"rewards/chosen": -0.0930183082818985,
|
| 2569 |
+
"rewards/margins": 0.07240499556064606,
|
| 2570 |
+
"rewards/rejected": -0.16542330384254456,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": -0.10743804275989532,
|
| 2577 |
+
"logits/rejected": -0.14361344277858734,
|
| 2578 |
+
"logps/chosen": -578.63671875,
|
| 2579 |
+
"logps/rejected": -649.34423828125,
|
| 2580 |
+
"loss": 0.1712,
|
| 2581 |
+
"rewards/accuracies": 0.59375,
|
| 2582 |
+
"rewards/chosen": -0.12350692600011826,
|
| 2583 |
+
"rewards/margins": 0.06949726492166519,
|
| 2584 |
+
"rewards/rejected": -0.19300420582294464,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": -0.2110254317522049,
|
| 2591 |
+
"logits/rejected": -0.14409136772155762,
|
| 2592 |
+
"logps/chosen": -484.0826110839844,
|
| 2593 |
+
"logps/rejected": -534.74755859375,
|
| 2594 |
+
"loss": 0.1695,
|
| 2595 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 2596 |
+
"rewards/chosen": -0.09997762739658356,
|
| 2597 |
+
"rewards/margins": 0.05725119262933731,
|
| 2598 |
+
"rewards/rejected": -0.15722879767417908,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": -0.2690781056880951,
|
| 2605 |
+
"logits/rejected": -0.10777749866247177,
|
| 2606 |
+
"logps/chosen": -531.328125,
|
| 2607 |
+
"logps/rejected": -558.0218505859375,
|
| 2608 |
+
"loss": 0.192,
|
| 2609 |
+
"rewards/accuracies": 0.4375,
|
| 2610 |
+
"rewards/chosen": -0.11898232996463776,
|
| 2611 |
+
"rewards/margins": 0.04323791339993477,
|
| 2612 |
+
"rewards/rejected": -0.16222023963928223,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": -0.2458486258983612,
|
| 2619 |
+
"logits/rejected": -0.14588430523872375,
|
| 2620 |
+
"logps/chosen": -481.7171936035156,
|
| 2621 |
+
"logps/rejected": -523.7376708984375,
|
| 2622 |
+
"loss": 0.1744,
|
| 2623 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 2624 |
+
"rewards/chosen": -0.10408926010131836,
|
| 2625 |
+
"rewards/margins": 0.047747764736413956,
|
| 2626 |
+
"rewards/rejected": -0.15183702111244202,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": -0.2206140011548996,
|
| 2633 |
+
"logits/rejected": -0.13354091346263885,
|
| 2634 |
+
"logps/chosen": -543.6251220703125,
|
| 2635 |
+
"logps/rejected": -563.88330078125,
|
| 2636 |
+
"loss": 0.1818,
|
| 2637 |
+
"rewards/accuracies": 0.5,
|
| 2638 |
+
"rewards/chosen": -0.11700856685638428,
|
| 2639 |
+
"rewards/margins": 0.05272556096315384,
|
| 2640 |
+
"rewards/rejected": -0.1697341352701187,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 0.016774978733062745,
|
| 2648 |
+
"train_runtime": 1063.735,
|
| 2649 |
+
"train_samples_per_second": 28.203,
|
| 2650 |
+
"train_steps_per_second": 1.763
|
| 2651 |
+
}
|
| 2652 |
+
],
|
| 2653 |
+
"logging_steps": 10,
|
| 2654 |
+
"max_steps": 1875,
|
| 2655 |
+
"num_input_tokens_seen": 0,
|
| 2656 |
+
"num_train_epochs": 1,
|
| 2657 |
+
"save_steps": 100,
|
| 2658 |
+
"total_flos": 0.0,
|
| 2659 |
+
"train_batch_size": 4,
|
| 2660 |
+
"trial_name": null,
|
| 2661 |
+
"trial_params": null
|
| 2662 |
+
}
|