Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May13_03-37-55_gpu4-119-5/events.out.tfevents.1715535575.gpu4-119-5.3533961.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1346 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: DUAL-GPO/phi-2-gpo-new-i0
|
| 9 |
+
model-index:
|
| 10 |
+
- name: phi-2-gpo-v10-i1
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# phi-2-gpo-v10-i1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- PEFT 0.7.1
|
| 57 |
+
- Transformers 4.36.2
|
| 58 |
+
- Pytorch 2.1.2+cu121
|
| 59 |
+
- Datasets 2.14.6
|
| 60 |
+
- 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 sha256:045f6cfd928301440a361bd8abb50e037dd55bb9b7c07fdef7e9ad3dfd6d3cc7
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2460615715387664,
|
| 4 |
+
"train_runtime": 8500.6415,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 1.765,
|
| 7 |
+
"train_steps_per_second": 0.11
|
| 8 |
+
}
|
runs/May13_03-37-55_gpu4-119-5/events.out.tfevents.1715535575.gpu4-119-5.3533961.0
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:a45ab9680c755c3bd0f4a41ebbb4f782381dd32941e35407fa700a2ecbd12c80
|
| 3 |
+
size 64634
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2460615715387664,
|
| 4 |
+
"train_runtime": 8500.6415,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 1.765,
|
| 7 |
+
"train_steps_per_second": 0.11
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9994666666666666,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 937,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5.319148936170213e-08,
|
| 14 |
+
"logits/chosen": 0.14563202857971191,
|
| 15 |
+
"logits/rejected": 0.3874575197696686,
|
| 16 |
+
"logps/chosen": -454.742919921875,
|
| 17 |
+
"logps/rejected": -268.25054931640625,
|
| 18 |
+
"loss": 0.3396,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 5.319148936170213e-07,
|
| 28 |
+
"logits/chosen": 0.07718739658594131,
|
| 29 |
+
"logits/rejected": 0.26869574189186096,
|
| 30 |
+
"logps/chosen": -350.5389709472656,
|
| 31 |
+
"logps/rejected": -281.45709228515625,
|
| 32 |
+
"loss": 0.315,
|
| 33 |
+
"rewards/accuracies": 0.375,
|
| 34 |
+
"rewards/chosen": 2.5761094093468273e-06,
|
| 35 |
+
"rewards/margins": -5.979803609079681e-05,
|
| 36 |
+
"rewards/rejected": 6.237414345378056e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.051278989762067795,
|
| 43 |
+
"logits/rejected": 0.2582473158836365,
|
| 44 |
+
"logps/chosen": -354.6767578125,
|
| 45 |
+
"logps/rejected": -278.68255615234375,
|
| 46 |
+
"loss": 0.3562,
|
| 47 |
+
"rewards/accuracies": 0.518750011920929,
|
| 48 |
+
"rewards/chosen": 0.00019174082262907177,
|
| 49 |
+
"rewards/margins": 5.2712995966430753e-05,
|
| 50 |
+
"rewards/rejected": 0.00013902783393859863,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.087407685816288,
|
| 57 |
+
"logits/rejected": 0.23584076762199402,
|
| 58 |
+
"logps/chosen": -341.74859619140625,
|
| 59 |
+
"logps/rejected": -292.8842468261719,
|
| 60 |
+
"loss": 0.3276,
|
| 61 |
+
"rewards/accuracies": 0.53125,
|
| 62 |
+
"rewards/chosen": 0.00011408107820898294,
|
| 63 |
+
"rewards/margins": 0.00017452315660193563,
|
| 64 |
+
"rewards/rejected": -6.044206747901626e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.07952137291431427,
|
| 71 |
+
"logits/rejected": 0.18448325991630554,
|
| 72 |
+
"logps/chosen": -345.06378173828125,
|
| 73 |
+
"logps/rejected": -308.3074951171875,
|
| 74 |
+
"loss": 0.3338,
|
| 75 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 76 |
+
"rewards/chosen": 6.922694592503831e-05,
|
| 77 |
+
"rewards/margins": 0.0002068312169285491,
|
| 78 |
+
"rewards/rejected": -0.0001376042637275532,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.1114521399140358,
|
| 85 |
+
"logits/rejected": 0.2774251103401184,
|
| 86 |
+
"logps/chosen": -326.83441162109375,
|
| 87 |
+
"logps/rejected": -293.80291748046875,
|
| 88 |
+
"loss": 0.3451,
|
| 89 |
+
"rewards/accuracies": 0.643750011920929,
|
| 90 |
+
"rewards/chosen": 0.00041769607923924923,
|
| 91 |
+
"rewards/margins": 0.0006514322012662888,
|
| 92 |
+
"rewards/rejected": -0.00023373604926746339,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.09482766687870026,
|
| 99 |
+
"logits/rejected": 0.27632468938827515,
|
| 100 |
+
"logps/chosen": -351.2109680175781,
|
| 101 |
+
"logps/rejected": -277.0458068847656,
|
| 102 |
+
"loss": 0.339,
|
| 103 |
+
"rewards/accuracies": 0.6875,
|
| 104 |
+
"rewards/chosen": 0.0010114657925441861,
|
| 105 |
+
"rewards/margins": 0.0016303223092108965,
|
| 106 |
+
"rewards/rejected": -0.0006188566330820322,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.02542046643793583,
|
| 113 |
+
"logits/rejected": 0.19503046572208405,
|
| 114 |
+
"logps/chosen": -325.17486572265625,
|
| 115 |
+
"logps/rejected": -285.79205322265625,
|
| 116 |
+
"loss": 0.3265,
|
| 117 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 118 |
+
"rewards/chosen": 0.001514864037744701,
|
| 119 |
+
"rewards/margins": 0.002718320582062006,
|
| 120 |
+
"rewards/rejected": -0.0012034563114866614,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.13358162343502045,
|
| 127 |
+
"logits/rejected": 0.31503233313560486,
|
| 128 |
+
"logps/chosen": -368.6209716796875,
|
| 129 |
+
"logps/rejected": -295.80133056640625,
|
| 130 |
+
"loss": 0.3393,
|
| 131 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 132 |
+
"rewards/chosen": 0.002275743056088686,
|
| 133 |
+
"rewards/margins": 0.005096759647130966,
|
| 134 |
+
"rewards/rejected": -0.0028210170567035675,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.08928992599248886,
|
| 141 |
+
"logits/rejected": 0.24500127136707306,
|
| 142 |
+
"logps/chosen": -346.7084045410156,
|
| 143 |
+
"logps/rejected": -290.81646728515625,
|
| 144 |
+
"loss": 0.3163,
|
| 145 |
+
"rewards/accuracies": 0.706250011920929,
|
| 146 |
+
"rewards/chosen": 0.004672099836170673,
|
| 147 |
+
"rewards/margins": 0.009218016639351845,
|
| 148 |
+
"rewards/rejected": -0.004545916803181171,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.17046232521533966,
|
| 155 |
+
"logits/rejected": 0.22814074158668518,
|
| 156 |
+
"logps/chosen": -332.4991760253906,
|
| 157 |
+
"logps/rejected": -293.03314208984375,
|
| 158 |
+
"loss": 0.3288,
|
| 159 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 160 |
+
"rewards/chosen": 0.0032020125072449446,
|
| 161 |
+
"rewards/margins": 0.01331277471035719,
|
| 162 |
+
"rewards/rejected": -0.010110762901604176,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.13835321366786957,
|
| 169 |
+
"logits/rejected": 0.2707987427711487,
|
| 170 |
+
"logps/chosen": -353.07904052734375,
|
| 171 |
+
"logps/rejected": -316.55377197265625,
|
| 172 |
+
"loss": 0.3145,
|
| 173 |
+
"rewards/accuracies": 0.71875,
|
| 174 |
+
"rewards/chosen": -0.0036005068104714155,
|
| 175 |
+
"rewards/margins": 0.02047211304306984,
|
| 176 |
+
"rewards/rejected": -0.024072617292404175,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.14788897335529327,
|
| 183 |
+
"logits/rejected": 0.2877771258354187,
|
| 184 |
+
"logps/chosen": -368.3328857421875,
|
| 185 |
+
"logps/rejected": -326.0980224609375,
|
| 186 |
+
"loss": 0.3211,
|
| 187 |
+
"rewards/accuracies": 0.668749988079071,
|
| 188 |
+
"rewards/chosen": -0.009556634351611137,
|
| 189 |
+
"rewards/margins": 0.031165510416030884,
|
| 190 |
+
"rewards/rejected": -0.04072214290499687,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.09604962915182114,
|
| 197 |
+
"logits/rejected": 0.29759398102760315,
|
| 198 |
+
"logps/chosen": -394.56146240234375,
|
| 199 |
+
"logps/rejected": -389.3465270996094,
|
| 200 |
+
"loss": 0.2595,
|
| 201 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 202 |
+
"rewards/chosen": -0.04469118267297745,
|
| 203 |
+
"rewards/margins": 0.059812031686306,
|
| 204 |
+
"rewards/rejected": -0.10450321435928345,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.09464170038700104,
|
| 211 |
+
"logits/rejected": 0.23635534942150116,
|
| 212 |
+
"logps/chosen": -411.34344482421875,
|
| 213 |
+
"logps/rejected": -472.7259216308594,
|
| 214 |
+
"loss": 0.2809,
|
| 215 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 216 |
+
"rewards/chosen": -0.09930221736431122,
|
| 217 |
+
"rewards/margins": 0.08144193887710571,
|
| 218 |
+
"rewards/rejected": -0.18074414134025574,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.15742775797843933,
|
| 225 |
+
"logits/rejected": 0.2725524306297302,
|
| 226 |
+
"logps/chosen": -477.2586975097656,
|
| 227 |
+
"logps/rejected": -517.0968627929688,
|
| 228 |
+
"loss": 0.2592,
|
| 229 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 230 |
+
"rewards/chosen": -0.13660530745983124,
|
| 231 |
+
"rewards/margins": 0.11236293613910675,
|
| 232 |
+
"rewards/rejected": -0.2489682137966156,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.19448170065879822,
|
| 239 |
+
"logits/rejected": 0.25956863164901733,
|
| 240 |
+
"logps/chosen": -487.07196044921875,
|
| 241 |
+
"logps/rejected": -597.939208984375,
|
| 242 |
+
"loss": 0.2663,
|
| 243 |
+
"rewards/accuracies": 0.699999988079071,
|
| 244 |
+
"rewards/chosen": -0.15577515959739685,
|
| 245 |
+
"rewards/margins": 0.15100589394569397,
|
| 246 |
+
"rewards/rejected": -0.3067810833454132,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.18750979006290436,
|
| 253 |
+
"logits/rejected": 0.326152503490448,
|
| 254 |
+
"logps/chosen": -559.5252685546875,
|
| 255 |
+
"logps/rejected": -645.9837036132812,
|
| 256 |
+
"loss": 0.2719,
|
| 257 |
+
"rewards/accuracies": 0.71875,
|
| 258 |
+
"rewards/chosen": -0.22856616973876953,
|
| 259 |
+
"rewards/margins": 0.12326528877019882,
|
| 260 |
+
"rewards/rejected": -0.35183146595954895,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.16625967621803284,
|
| 267 |
+
"logits/rejected": 0.29693764448165894,
|
| 268 |
+
"logps/chosen": -530.322021484375,
|
| 269 |
+
"logps/rejected": -600.0885009765625,
|
| 270 |
+
"loss": 0.2955,
|
| 271 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 272 |
+
"rewards/chosen": -0.18995243310928345,
|
| 273 |
+
"rewards/margins": 0.14340588450431824,
|
| 274 |
+
"rewards/rejected": -0.3333582878112793,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.135554239153862,
|
| 281 |
+
"logits/rejected": 0.26710349321365356,
|
| 282 |
+
"logps/chosen": -582.8619384765625,
|
| 283 |
+
"logps/rejected": -616.3886108398438,
|
| 284 |
+
"loss": 0.2737,
|
| 285 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 286 |
+
"rewards/chosen": -0.21700850129127502,
|
| 287 |
+
"rewards/margins": 0.12937961518764496,
|
| 288 |
+
"rewards/rejected": -0.3463881015777588,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.10434029996395111,
|
| 295 |
+
"logits/rejected": 0.28046977519989014,
|
| 296 |
+
"logps/chosen": -585.6417236328125,
|
| 297 |
+
"logps/rejected": -614.5296630859375,
|
| 298 |
+
"loss": 0.2886,
|
| 299 |
+
"rewards/accuracies": 0.71875,
|
| 300 |
+
"rewards/chosen": -0.2205405980348587,
|
| 301 |
+
"rewards/margins": 0.12526755034923553,
|
| 302 |
+
"rewards/rejected": -0.34580811858177185,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.1413886696100235,
|
| 309 |
+
"logits/rejected": 0.27238231897354126,
|
| 310 |
+
"logps/chosen": -519.6276245117188,
|
| 311 |
+
"logps/rejected": -587.7799072265625,
|
| 312 |
+
"loss": 0.2557,
|
| 313 |
+
"rewards/accuracies": 0.675000011920929,
|
| 314 |
+
"rewards/chosen": -0.16974905133247375,
|
| 315 |
+
"rewards/margins": 0.1322554051876068,
|
| 316 |
+
"rewards/rejected": -0.30200448632240295,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.1467094123363495,
|
| 323 |
+
"logits/rejected": 0.2754250466823578,
|
| 324 |
+
"logps/chosen": -554.9280395507812,
|
| 325 |
+
"logps/rejected": -615.7232666015625,
|
| 326 |
+
"loss": 0.2471,
|
| 327 |
+
"rewards/accuracies": 0.731249988079071,
|
| 328 |
+
"rewards/chosen": -0.21137747168540955,
|
| 329 |
+
"rewards/margins": 0.1308281123638153,
|
| 330 |
+
"rewards/rejected": -0.34220558404922485,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": 0.1171431764960289,
|
| 337 |
+
"logits/rejected": 0.2890062928199768,
|
| 338 |
+
"logps/chosen": -575.1917724609375,
|
| 339 |
+
"logps/rejected": -651.8801879882812,
|
| 340 |
+
"loss": 0.244,
|
| 341 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 342 |
+
"rewards/chosen": -0.24391531944274902,
|
| 343 |
+
"rewards/margins": 0.15722794830799103,
|
| 344 |
+
"rewards/rejected": -0.40114325284957886,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": 0.10296036303043365,
|
| 351 |
+
"logits/rejected": 0.28510022163391113,
|
| 352 |
+
"logps/chosen": -640.1365966796875,
|
| 353 |
+
"logps/rejected": -720.7387084960938,
|
| 354 |
+
"loss": 0.2331,
|
| 355 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 356 |
+
"rewards/chosen": -0.2727048397064209,
|
| 357 |
+
"rewards/margins": 0.1723267138004303,
|
| 358 |
+
"rewards/rejected": -0.4450315833091736,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": 0.15176770091056824,
|
| 365 |
+
"logits/rejected": 0.22689513862133026,
|
| 366 |
+
"logps/chosen": -542.8187255859375,
|
| 367 |
+
"logps/rejected": -679.3350830078125,
|
| 368 |
+
"loss": 0.2444,
|
| 369 |
+
"rewards/accuracies": 0.699999988079071,
|
| 370 |
+
"rewards/chosen": -0.23740482330322266,
|
| 371 |
+
"rewards/margins": 0.16511742770671844,
|
| 372 |
+
"rewards/rejected": -0.4025222659111023,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": 0.1848079115152359,
|
| 379 |
+
"logits/rejected": 0.28918254375457764,
|
| 380 |
+
"logps/chosen": -591.1017456054688,
|
| 381 |
+
"logps/rejected": -719.2144775390625,
|
| 382 |
+
"loss": 0.2388,
|
| 383 |
+
"rewards/accuracies": 0.762499988079071,
|
| 384 |
+
"rewards/chosen": -0.23014459013938904,
|
| 385 |
+
"rewards/margins": 0.18921832740306854,
|
| 386 |
+
"rewards/rejected": -0.4193629324436188,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": 0.16476555168628693,
|
| 393 |
+
"logits/rejected": 0.23265871405601501,
|
| 394 |
+
"logps/chosen": -612.1968383789062,
|
| 395 |
+
"logps/rejected": -663.5397338867188,
|
| 396 |
+
"loss": 0.2918,
|
| 397 |
+
"rewards/accuracies": 0.65625,
|
| 398 |
+
"rewards/chosen": -0.24918679893016815,
|
| 399 |
+
"rewards/margins": 0.11979563534259796,
|
| 400 |
+
"rewards/rejected": -0.3689824044704437,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": 0.180597186088562,
|
| 407 |
+
"logits/rejected": 0.3083464503288269,
|
| 408 |
+
"logps/chosen": -560.151123046875,
|
| 409 |
+
"logps/rejected": -635.0821533203125,
|
| 410 |
+
"loss": 0.2582,
|
| 411 |
+
"rewards/accuracies": 0.71875,
|
| 412 |
+
"rewards/chosen": -0.2051992118358612,
|
| 413 |
+
"rewards/margins": 0.14893193542957306,
|
| 414 |
+
"rewards/rejected": -0.35413113236427307,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": 0.22149360179901123,
|
| 421 |
+
"logits/rejected": 0.3726951479911804,
|
| 422 |
+
"logps/chosen": -628.3652954101562,
|
| 423 |
+
"logps/rejected": -711.3004150390625,
|
| 424 |
+
"loss": 0.2145,
|
| 425 |
+
"rewards/accuracies": 0.768750011920929,
|
| 426 |
+
"rewards/chosen": -0.24089030921459198,
|
| 427 |
+
"rewards/margins": 0.16530363261699677,
|
| 428 |
+
"rewards/rejected": -0.40619391202926636,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": 0.17435990273952484,
|
| 435 |
+
"logits/rejected": 0.3360474705696106,
|
| 436 |
+
"logps/chosen": -610.1092529296875,
|
| 437 |
+
"logps/rejected": -695.5682983398438,
|
| 438 |
+
"loss": 0.2356,
|
| 439 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 440 |
+
"rewards/chosen": -0.26700595021247864,
|
| 441 |
+
"rewards/margins": 0.1659780740737915,
|
| 442 |
+
"rewards/rejected": -0.43298402428627014,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": 0.177028626203537,
|
| 449 |
+
"logits/rejected": 0.2775452136993408,
|
| 450 |
+
"logps/chosen": -601.6631469726562,
|
| 451 |
+
"logps/rejected": -679.7595825195312,
|
| 452 |
+
"loss": 0.2454,
|
| 453 |
+
"rewards/accuracies": 0.71875,
|
| 454 |
+
"rewards/chosen": -0.2515362799167633,
|
| 455 |
+
"rewards/margins": 0.15310627222061157,
|
| 456 |
+
"rewards/rejected": -0.4046425223350525,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": 0.17227385938167572,
|
| 463 |
+
"logits/rejected": 0.2626027464866638,
|
| 464 |
+
"logps/chosen": -565.1954956054688,
|
| 465 |
+
"logps/rejected": -653.8951416015625,
|
| 466 |
+
"loss": 0.2601,
|
| 467 |
+
"rewards/accuracies": 0.668749988079071,
|
| 468 |
+
"rewards/chosen": -0.22992494702339172,
|
| 469 |
+
"rewards/margins": 0.14292170107364655,
|
| 470 |
+
"rewards/rejected": -0.3728466331958771,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": 0.17768487334251404,
|
| 477 |
+
"logits/rejected": 0.33285486698150635,
|
| 478 |
+
"logps/chosen": -610.06201171875,
|
| 479 |
+
"logps/rejected": -670.5873413085938,
|
| 480 |
+
"loss": 0.238,
|
| 481 |
+
"rewards/accuracies": 0.75,
|
| 482 |
+
"rewards/chosen": -0.23991577327251434,
|
| 483 |
+
"rewards/margins": 0.15924175083637238,
|
| 484 |
+
"rewards/rejected": -0.39915746450424194,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": 0.12916894257068634,
|
| 491 |
+
"logits/rejected": 0.2785950303077698,
|
| 492 |
+
"logps/chosen": -571.642578125,
|
| 493 |
+
"logps/rejected": -680.286865234375,
|
| 494 |
+
"loss": 0.2314,
|
| 495 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 496 |
+
"rewards/chosen": -0.2410048544406891,
|
| 497 |
+
"rewards/margins": 0.15611061453819275,
|
| 498 |
+
"rewards/rejected": -0.39711546897888184,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.1318448781967163,
|
| 505 |
+
"logits/rejected": 0.2396216094493866,
|
| 506 |
+
"logps/chosen": -577.1714477539062,
|
| 507 |
+
"logps/rejected": -694.001220703125,
|
| 508 |
+
"loss": 0.23,
|
| 509 |
+
"rewards/accuracies": 0.71875,
|
| 510 |
+
"rewards/chosen": -0.25458115339279175,
|
| 511 |
+
"rewards/margins": 0.16680863499641418,
|
| 512 |
+
"rewards/rejected": -0.42138975858688354,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": 0.1819082796573639,
|
| 519 |
+
"logits/rejected": 0.30339935421943665,
|
| 520 |
+
"logps/chosen": -620.7168579101562,
|
| 521 |
+
"logps/rejected": -733.3218994140625,
|
| 522 |
+
"loss": 0.2306,
|
| 523 |
+
"rewards/accuracies": 0.737500011920929,
|
| 524 |
+
"rewards/chosen": -0.24643263220787048,
|
| 525 |
+
"rewards/margins": 0.19664740562438965,
|
| 526 |
+
"rewards/rejected": -0.4430800974369049,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": 0.1591918021440506,
|
| 533 |
+
"logits/rejected": 0.24382638931274414,
|
| 534 |
+
"logps/chosen": -650.5294189453125,
|
| 535 |
+
"logps/rejected": -757.6646118164062,
|
| 536 |
+
"loss": 0.2606,
|
| 537 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 538 |
+
"rewards/chosen": -0.29114747047424316,
|
| 539 |
+
"rewards/margins": 0.1727633774280548,
|
| 540 |
+
"rewards/rejected": -0.46391087770462036,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": 0.15119919180870056,
|
| 547 |
+
"logits/rejected": 0.24405035376548767,
|
| 548 |
+
"logps/chosen": -622.4024658203125,
|
| 549 |
+
"logps/rejected": -731.4509887695312,
|
| 550 |
+
"loss": 0.2127,
|
| 551 |
+
"rewards/accuracies": 0.793749988079071,
|
| 552 |
+
"rewards/chosen": -0.2556970715522766,
|
| 553 |
+
"rewards/margins": 0.20232219994068146,
|
| 554 |
+
"rewards/rejected": -0.4580192565917969,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": 0.16059614717960358,
|
| 561 |
+
"logits/rejected": 0.26955538988113403,
|
| 562 |
+
"logps/chosen": -620.3678588867188,
|
| 563 |
+
"logps/rejected": -734.6710205078125,
|
| 564 |
+
"loss": 0.2319,
|
| 565 |
+
"rewards/accuracies": 0.731249988079071,
|
| 566 |
+
"rewards/chosen": -0.26077157258987427,
|
| 567 |
+
"rewards/margins": 0.18923643231391907,
|
| 568 |
+
"rewards/rejected": -0.4500080645084381,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": 0.15299072861671448,
|
| 575 |
+
"logits/rejected": 0.27529269456863403,
|
| 576 |
+
"logps/chosen": -626.7930908203125,
|
| 577 |
+
"logps/rejected": -771.9212646484375,
|
| 578 |
+
"loss": 0.1765,
|
| 579 |
+
"rewards/accuracies": 0.824999988079071,
|
| 580 |
+
"rewards/chosen": -0.25388702750205994,
|
| 581 |
+
"rewards/margins": 0.23886942863464355,
|
| 582 |
+
"rewards/rejected": -0.49275651574134827,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": 0.10297727584838867,
|
| 589 |
+
"logits/rejected": 0.2494010478258133,
|
| 590 |
+
"logps/chosen": -701.2484130859375,
|
| 591 |
+
"logps/rejected": -797.5471801757812,
|
| 592 |
+
"loss": 0.2255,
|
| 593 |
+
"rewards/accuracies": 0.762499988079071,
|
| 594 |
+
"rewards/chosen": -0.3326496481895447,
|
| 595 |
+
"rewards/margins": 0.19009152054786682,
|
| 596 |
+
"rewards/rejected": -0.5227411985397339,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": 0.0838174819946289,
|
| 603 |
+
"logits/rejected": 0.24609944224357605,
|
| 604 |
+
"logps/chosen": -691.7960205078125,
|
| 605 |
+
"logps/rejected": -792.8016357421875,
|
| 606 |
+
"loss": 0.2473,
|
| 607 |
+
"rewards/accuracies": 0.6875,
|
| 608 |
+
"rewards/chosen": -0.3393723964691162,
|
| 609 |
+
"rewards/margins": 0.17680588364601135,
|
| 610 |
+
"rewards/rejected": -0.5161782503128052,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": 0.13857319951057434,
|
| 617 |
+
"logits/rejected": 0.25091537833213806,
|
| 618 |
+
"logps/chosen": -635.0294189453125,
|
| 619 |
+
"logps/rejected": -770.2885131835938,
|
| 620 |
+
"loss": 0.2029,
|
| 621 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 622 |
+
"rewards/chosen": -0.28675633668899536,
|
| 623 |
+
"rewards/margins": 0.20502133667469025,
|
| 624 |
+
"rewards/rejected": -0.4917777180671692,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": 0.09761005640029907,
|
| 631 |
+
"logits/rejected": 0.21226266026496887,
|
| 632 |
+
"logps/chosen": -669.2428588867188,
|
| 633 |
+
"logps/rejected": -749.3931884765625,
|
| 634 |
+
"loss": 0.242,
|
| 635 |
+
"rewards/accuracies": 0.706250011920929,
|
| 636 |
+
"rewards/chosen": -0.3128831088542938,
|
| 637 |
+
"rewards/margins": 0.17808611690998077,
|
| 638 |
+
"rewards/rejected": -0.4909692406654358,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": 0.1553424596786499,
|
| 645 |
+
"logits/rejected": 0.25895553827285767,
|
| 646 |
+
"logps/chosen": -694.4083862304688,
|
| 647 |
+
"logps/rejected": -792.1837158203125,
|
| 648 |
+
"loss": 0.2174,
|
| 649 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 650 |
+
"rewards/chosen": -0.3040028214454651,
|
| 651 |
+
"rewards/margins": 0.2048918753862381,
|
| 652 |
+
"rewards/rejected": -0.508894681930542,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": 0.1065811887383461,
|
| 659 |
+
"logits/rejected": 0.25707563757896423,
|
| 660 |
+
"logps/chosen": -613.1231689453125,
|
| 661 |
+
"logps/rejected": -758.7059326171875,
|
| 662 |
+
"loss": 0.2107,
|
| 663 |
+
"rewards/accuracies": 0.800000011920929,
|
| 664 |
+
"rewards/chosen": -0.26900747418403625,
|
| 665 |
+
"rewards/margins": 0.21452918648719788,
|
| 666 |
+
"rewards/rejected": -0.48353663086891174,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": 0.16053031384944916,
|
| 673 |
+
"logits/rejected": 0.2852506935596466,
|
| 674 |
+
"logps/chosen": -637.3067626953125,
|
| 675 |
+
"logps/rejected": -732.3541259765625,
|
| 676 |
+
"loss": 0.2118,
|
| 677 |
+
"rewards/accuracies": 0.75,
|
| 678 |
+
"rewards/chosen": -0.2603939175605774,
|
| 679 |
+
"rewards/margins": 0.18671852350234985,
|
| 680 |
+
"rewards/rejected": -0.44711247086524963,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": 0.1389404833316803,
|
| 687 |
+
"logits/rejected": 0.2467120885848999,
|
| 688 |
+
"logps/chosen": -638.651123046875,
|
| 689 |
+
"logps/rejected": -754.9122314453125,
|
| 690 |
+
"loss": 0.2233,
|
| 691 |
+
"rewards/accuracies": 0.737500011920929,
|
| 692 |
+
"rewards/chosen": -0.26695486903190613,
|
| 693 |
+
"rewards/margins": 0.20951655507087708,
|
| 694 |
+
"rewards/rejected": -0.476471483707428,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": 0.11784114688634872,
|
| 701 |
+
"logits/rejected": 0.18245339393615723,
|
| 702 |
+
"logps/chosen": -603.6224365234375,
|
| 703 |
+
"logps/rejected": -770.082275390625,
|
| 704 |
+
"loss": 0.2182,
|
| 705 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 706 |
+
"rewards/chosen": -0.28938090801239014,
|
| 707 |
+
"rewards/margins": 0.2138332575559616,
|
| 708 |
+
"rewards/rejected": -0.5032141804695129,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": 0.11818281561136246,
|
| 715 |
+
"logits/rejected": 0.26330405473709106,
|
| 716 |
+
"logps/chosen": -623.1153564453125,
|
| 717 |
+
"logps/rejected": -809.2369384765625,
|
| 718 |
+
"loss": 0.2143,
|
| 719 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 720 |
+
"rewards/chosen": -0.3059650957584381,
|
| 721 |
+
"rewards/margins": 0.23646679520606995,
|
| 722 |
+
"rewards/rejected": -0.5424319505691528,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": 0.16755148768424988,
|
| 729 |
+
"logits/rejected": 0.28101032972335815,
|
| 730 |
+
"logps/chosen": -677.8587646484375,
|
| 731 |
+
"logps/rejected": -864.1910400390625,
|
| 732 |
+
"loss": 0.2025,
|
| 733 |
+
"rewards/accuracies": 0.768750011920929,
|
| 734 |
+
"rewards/chosen": -0.32487982511520386,
|
| 735 |
+
"rewards/margins": 0.2524875998497009,
|
| 736 |
+
"rewards/rejected": -0.5773674249649048,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": 0.08524368703365326,
|
| 743 |
+
"logits/rejected": 0.21973176300525665,
|
| 744 |
+
"logps/chosen": -697.4478759765625,
|
| 745 |
+
"logps/rejected": -855.9630737304688,
|
| 746 |
+
"loss": 0.22,
|
| 747 |
+
"rewards/accuracies": 0.737500011920929,
|
| 748 |
+
"rewards/chosen": -0.33033424615859985,
|
| 749 |
+
"rewards/margins": 0.21664047241210938,
|
| 750 |
+
"rewards/rejected": -0.5469747185707092,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": 0.1285276859998703,
|
| 757 |
+
"logits/rejected": 0.2174634039402008,
|
| 758 |
+
"logps/chosen": -610.0903930664062,
|
| 759 |
+
"logps/rejected": -795.0265502929688,
|
| 760 |
+
"loss": 0.1928,
|
| 761 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 762 |
+
"rewards/chosen": -0.293308824300766,
|
| 763 |
+
"rewards/margins": 0.21643824875354767,
|
| 764 |
+
"rewards/rejected": -0.5097470879554749,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": 0.14484889805316925,
|
| 771 |
+
"logits/rejected": 0.20977553725242615,
|
| 772 |
+
"logps/chosen": -650.8162231445312,
|
| 773 |
+
"logps/rejected": -814.1326293945312,
|
| 774 |
+
"loss": 0.2019,
|
| 775 |
+
"rewards/accuracies": 0.737500011920929,
|
| 776 |
+
"rewards/chosen": -0.2902231812477112,
|
| 777 |
+
"rewards/margins": 0.24104826152324677,
|
| 778 |
+
"rewards/rejected": -0.5312714576721191,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": 0.11247887462377548,
|
| 785 |
+
"logits/rejected": 0.22003412246704102,
|
| 786 |
+
"logps/chosen": -649.1162719726562,
|
| 787 |
+
"logps/rejected": -767.150634765625,
|
| 788 |
+
"loss": 0.2465,
|
| 789 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 790 |
+
"rewards/chosen": -0.3138406574726105,
|
| 791 |
+
"rewards/margins": 0.182392418384552,
|
| 792 |
+
"rewards/rejected": -0.49623313546180725,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": 0.057500071823596954,
|
| 799 |
+
"logits/rejected": 0.19665978848934174,
|
| 800 |
+
"logps/chosen": -651.9990844726562,
|
| 801 |
+
"logps/rejected": -783.0087890625,
|
| 802 |
+
"loss": 0.2255,
|
| 803 |
+
"rewards/accuracies": 0.706250011920929,
|
| 804 |
+
"rewards/chosen": -0.3106940984725952,
|
| 805 |
+
"rewards/margins": 0.20310230553150177,
|
| 806 |
+
"rewards/rejected": -0.5137964487075806,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": 0.11110985279083252,
|
| 813 |
+
"logits/rejected": 0.2312009632587433,
|
| 814 |
+
"logps/chosen": -621.1902465820312,
|
| 815 |
+
"logps/rejected": -777.6902465820312,
|
| 816 |
+
"loss": 0.1934,
|
| 817 |
+
"rewards/accuracies": 0.768750011920929,
|
| 818 |
+
"rewards/chosen": -0.25909268856048584,
|
| 819 |
+
"rewards/margins": 0.2260764092206955,
|
| 820 |
+
"rewards/rejected": -0.48516911268234253,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": 0.14112098515033722,
|
| 827 |
+
"logits/rejected": 0.2636359930038452,
|
| 828 |
+
"logps/chosen": -635.9463500976562,
|
| 829 |
+
"logps/rejected": -735.6661376953125,
|
| 830 |
+
"loss": 0.2452,
|
| 831 |
+
"rewards/accuracies": 0.737500011920929,
|
| 832 |
+
"rewards/chosen": -0.266891747713089,
|
| 833 |
+
"rewards/margins": 0.19298222661018372,
|
| 834 |
+
"rewards/rejected": -0.4598739743232727,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": 0.11148792505264282,
|
| 841 |
+
"logits/rejected": 0.25395482778549194,
|
| 842 |
+
"logps/chosen": -586.4432373046875,
|
| 843 |
+
"logps/rejected": -725.523193359375,
|
| 844 |
+
"loss": 0.224,
|
| 845 |
+
"rewards/accuracies": 0.75,
|
| 846 |
+
"rewards/chosen": -0.2619563043117523,
|
| 847 |
+
"rewards/margins": 0.19483323395252228,
|
| 848 |
+
"rewards/rejected": -0.4567895531654358,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": 0.09673704952001572,
|
| 855 |
+
"logits/rejected": 0.20130054652690887,
|
| 856 |
+
"logps/chosen": -615.4747314453125,
|
| 857 |
+
"logps/rejected": -788.6925659179688,
|
| 858 |
+
"loss": 0.2763,
|
| 859 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 860 |
+
"rewards/chosen": -0.27522048354148865,
|
| 861 |
+
"rewards/margins": 0.21255996823310852,
|
| 862 |
+
"rewards/rejected": -0.48778048157691956,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": 0.07239886373281479,
|
| 869 |
+
"logits/rejected": 0.18439838290214539,
|
| 870 |
+
"logps/chosen": -564.4202880859375,
|
| 871 |
+
"logps/rejected": -704.7264404296875,
|
| 872 |
+
"loss": 0.2415,
|
| 873 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 874 |
+
"rewards/chosen": -0.25343528389930725,
|
| 875 |
+
"rewards/margins": 0.1700516790151596,
|
| 876 |
+
"rewards/rejected": -0.42348694801330566,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": 0.10070653259754181,
|
| 883 |
+
"logits/rejected": 0.19296300411224365,
|
| 884 |
+
"logps/chosen": -595.9661865234375,
|
| 885 |
+
"logps/rejected": -724.99658203125,
|
| 886 |
+
"loss": 0.2326,
|
| 887 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 888 |
+
"rewards/chosen": -0.23254573345184326,
|
| 889 |
+
"rewards/margins": 0.19659695029258728,
|
| 890 |
+
"rewards/rejected": -0.42914265394210815,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": 0.08602897822856903,
|
| 897 |
+
"logits/rejected": 0.1648799628019333,
|
| 898 |
+
"logps/chosen": -553.3023681640625,
|
| 899 |
+
"logps/rejected": -709.7655639648438,
|
| 900 |
+
"loss": 0.2185,
|
| 901 |
+
"rewards/accuracies": 0.737500011920929,
|
| 902 |
+
"rewards/chosen": -0.2514170706272125,
|
| 903 |
+
"rewards/margins": 0.1915900856256485,
|
| 904 |
+
"rewards/rejected": -0.4430071711540222,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": 0.0444771870970726,
|
| 911 |
+
"logits/rejected": 0.16466517746448517,
|
| 912 |
+
"logps/chosen": -611.7086181640625,
|
| 913 |
+
"logps/rejected": -756.202392578125,
|
| 914 |
+
"loss": 0.2093,
|
| 915 |
+
"rewards/accuracies": 0.71875,
|
| 916 |
+
"rewards/chosen": -0.27020856738090515,
|
| 917 |
+
"rewards/margins": 0.20864149928092957,
|
| 918 |
+
"rewards/rejected": -0.4788500666618347,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": 0.08262890577316284,
|
| 925 |
+
"logits/rejected": 0.21953897178173065,
|
| 926 |
+
"logps/chosen": -657.6599731445312,
|
| 927 |
+
"logps/rejected": -753.6175537109375,
|
| 928 |
+
"loss": 0.2635,
|
| 929 |
+
"rewards/accuracies": 0.675000011920929,
|
| 930 |
+
"rewards/chosen": -0.30637097358703613,
|
| 931 |
+
"rewards/margins": 0.1610550731420517,
|
| 932 |
+
"rewards/rejected": -0.46742600202560425,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": 0.08547943085432053,
|
| 939 |
+
"logits/rejected": 0.22080206871032715,
|
| 940 |
+
"logps/chosen": -639.3602905273438,
|
| 941 |
+
"logps/rejected": -765.0423583984375,
|
| 942 |
+
"loss": 0.2281,
|
| 943 |
+
"rewards/accuracies": 0.8125,
|
| 944 |
+
"rewards/chosen": -0.2679855227470398,
|
| 945 |
+
"rewards/margins": 0.2209259271621704,
|
| 946 |
+
"rewards/rejected": -0.4889114797115326,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": 0.10255439579486847,
|
| 953 |
+
"logits/rejected": 0.17642661929130554,
|
| 954 |
+
"logps/chosen": -590.3636474609375,
|
| 955 |
+
"logps/rejected": -765.87890625,
|
| 956 |
+
"loss": 0.2285,
|
| 957 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 958 |
+
"rewards/chosen": -0.2688559293746948,
|
| 959 |
+
"rewards/margins": 0.2031112015247345,
|
| 960 |
+
"rewards/rejected": -0.47196707129478455,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": 0.09613371640443802,
|
| 967 |
+
"logits/rejected": 0.20681801438331604,
|
| 968 |
+
"logps/chosen": -639.8070678710938,
|
| 969 |
+
"logps/rejected": -783.1290283203125,
|
| 970 |
+
"loss": 0.2284,
|
| 971 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 972 |
+
"rewards/chosen": -0.28017768263816833,
|
| 973 |
+
"rewards/margins": 0.2119220495223999,
|
| 974 |
+
"rewards/rejected": -0.4920997619628906,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": 0.10619207471609116,
|
| 981 |
+
"logits/rejected": 0.19468547403812408,
|
| 982 |
+
"logps/chosen": -697.66162109375,
|
| 983 |
+
"logps/rejected": -777.8093872070312,
|
| 984 |
+
"loss": 0.2456,
|
| 985 |
+
"rewards/accuracies": 0.731249988079071,
|
| 986 |
+
"rewards/chosen": -0.31186243891716003,
|
| 987 |
+
"rewards/margins": 0.1904953420162201,
|
| 988 |
+
"rewards/rejected": -0.5023577809333801,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": 0.12791021168231964,
|
| 995 |
+
"logits/rejected": 0.18563024699687958,
|
| 996 |
+
"logps/chosen": -692.7999267578125,
|
| 997 |
+
"logps/rejected": -838.0908203125,
|
| 998 |
+
"loss": 0.2424,
|
| 999 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1000 |
+
"rewards/chosen": -0.30099743604660034,
|
| 1001 |
+
"rewards/margins": 0.24136948585510254,
|
| 1002 |
+
"rewards/rejected": -0.5423668622970581,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": 0.10475460439920425,
|
| 1009 |
+
"logits/rejected": 0.17532803118228912,
|
| 1010 |
+
"logps/chosen": -574.7904663085938,
|
| 1011 |
+
"logps/rejected": -732.5684814453125,
|
| 1012 |
+
"loss": 0.2116,
|
| 1013 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1014 |
+
"rewards/chosen": -0.27657538652420044,
|
| 1015 |
+
"rewards/margins": 0.19332227110862732,
|
| 1016 |
+
"rewards/rejected": -0.46989765763282776,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": 0.11339239031076431,
|
| 1023 |
+
"logits/rejected": 0.23391477763652802,
|
| 1024 |
+
"logps/chosen": -614.44384765625,
|
| 1025 |
+
"logps/rejected": -739.0775756835938,
|
| 1026 |
+
"loss": 0.2129,
|
| 1027 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1028 |
+
"rewards/chosen": -0.26443395018577576,
|
| 1029 |
+
"rewards/margins": 0.20620107650756836,
|
| 1030 |
+
"rewards/rejected": -0.47063499689102173,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": 0.11114220321178436,
|
| 1037 |
+
"logits/rejected": 0.1741330623626709,
|
| 1038 |
+
"logps/chosen": -649.84423828125,
|
| 1039 |
+
"logps/rejected": -796.5662841796875,
|
| 1040 |
+
"loss": 0.249,
|
| 1041 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1042 |
+
"rewards/chosen": -0.30554836988449097,
|
| 1043 |
+
"rewards/margins": 0.18621903657913208,
|
| 1044 |
+
"rewards/rejected": -0.49176740646362305,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": 0.05583947151899338,
|
| 1051 |
+
"logits/rejected": 0.208854079246521,
|
| 1052 |
+
"logps/chosen": -677.1410522460938,
|
| 1053 |
+
"logps/rejected": -806.2962646484375,
|
| 1054 |
+
"loss": 0.2157,
|
| 1055 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1056 |
+
"rewards/chosen": -0.3019706606864929,
|
| 1057 |
+
"rewards/margins": 0.21764162182807922,
|
| 1058 |
+
"rewards/rejected": -0.5196123123168945,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": 0.11103875935077667,
|
| 1065 |
+
"logits/rejected": 0.23960928618907928,
|
| 1066 |
+
"logps/chosen": -651.9210205078125,
|
| 1067 |
+
"logps/rejected": -767.1956176757812,
|
| 1068 |
+
"loss": 0.2196,
|
| 1069 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1070 |
+
"rewards/chosen": -0.28146857023239136,
|
| 1071 |
+
"rewards/margins": 0.21090731024742126,
|
| 1072 |
+
"rewards/rejected": -0.492375910282135,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": 0.08522719889879227,
|
| 1079 |
+
"logits/rejected": 0.18019166588783264,
|
| 1080 |
+
"logps/chosen": -693.9295043945312,
|
| 1081 |
+
"logps/rejected": -834.8268432617188,
|
| 1082 |
+
"loss": 0.2044,
|
| 1083 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1084 |
+
"rewards/chosen": -0.3021830916404724,
|
| 1085 |
+
"rewards/margins": 0.22599780559539795,
|
| 1086 |
+
"rewards/rejected": -0.5281809568405151,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": 0.10727125406265259,
|
| 1093 |
+
"logits/rejected": 0.2462559938430786,
|
| 1094 |
+
"logps/chosen": -690.4157104492188,
|
| 1095 |
+
"logps/rejected": -837.8204956054688,
|
| 1096 |
+
"loss": 0.2228,
|
| 1097 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1098 |
+
"rewards/chosen": -0.3111000657081604,
|
| 1099 |
+
"rewards/margins": 0.22689378261566162,
|
| 1100 |
+
"rewards/rejected": -0.5379937887191772,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": 0.10468622297048569,
|
| 1107 |
+
"logits/rejected": 0.21340981125831604,
|
| 1108 |
+
"logps/chosen": -664.1920166015625,
|
| 1109 |
+
"logps/rejected": -791.6151123046875,
|
| 1110 |
+
"loss": 0.2025,
|
| 1111 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1112 |
+
"rewards/chosen": -0.28642627596855164,
|
| 1113 |
+
"rewards/margins": 0.2306082546710968,
|
| 1114 |
+
"rewards/rejected": -0.5170345306396484,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": 0.11628569662570953,
|
| 1121 |
+
"logits/rejected": 0.23161634802818298,
|
| 1122 |
+
"logps/chosen": -672.2249755859375,
|
| 1123 |
+
"logps/rejected": -801.2711181640625,
|
| 1124 |
+
"loss": 0.2464,
|
| 1125 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1126 |
+
"rewards/chosen": -0.3202977776527405,
|
| 1127 |
+
"rewards/margins": 0.2009088099002838,
|
| 1128 |
+
"rewards/rejected": -0.5212065577507019,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": 0.06959172338247299,
|
| 1135 |
+
"logits/rejected": 0.2281877100467682,
|
| 1136 |
+
"logps/chosen": -652.8377685546875,
|
| 1137 |
+
"logps/rejected": -795.1046752929688,
|
| 1138 |
+
"loss": 0.2284,
|
| 1139 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1140 |
+
"rewards/chosen": -0.2909380793571472,
|
| 1141 |
+
"rewards/margins": 0.22871951758861542,
|
| 1142 |
+
"rewards/rejected": -0.5196576714515686,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": 0.11237098276615143,
|
| 1149 |
+
"logits/rejected": 0.21487274765968323,
|
| 1150 |
+
"logps/chosen": -660.4642944335938,
|
| 1151 |
+
"logps/rejected": -802.35009765625,
|
| 1152 |
+
"loss": 0.196,
|
| 1153 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1154 |
+
"rewards/chosen": -0.31749480962753296,
|
| 1155 |
+
"rewards/margins": 0.21312642097473145,
|
| 1156 |
+
"rewards/rejected": -0.5306212306022644,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": 0.04496614262461662,
|
| 1163 |
+
"logits/rejected": 0.25041455030441284,
|
| 1164 |
+
"logps/chosen": -633.7536010742188,
|
| 1165 |
+
"logps/rejected": -752.9474487304688,
|
| 1166 |
+
"loss": 0.2326,
|
| 1167 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1168 |
+
"rewards/chosen": -0.303285151720047,
|
| 1169 |
+
"rewards/margins": 0.18882021307945251,
|
| 1170 |
+
"rewards/rejected": -0.4921053349971771,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": 0.07390692830085754,
|
| 1177 |
+
"logits/rejected": 0.17046715319156647,
|
| 1178 |
+
"logps/chosen": -650.1712646484375,
|
| 1179 |
+
"logps/rejected": -773.189697265625,
|
| 1180 |
+
"loss": 0.2534,
|
| 1181 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1182 |
+
"rewards/chosen": -0.32713738083839417,
|
| 1183 |
+
"rewards/margins": 0.16583597660064697,
|
| 1184 |
+
"rewards/rejected": -0.4929733872413635,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": 0.08455213159322739,
|
| 1191 |
+
"logits/rejected": 0.2394600361585617,
|
| 1192 |
+
"logps/chosen": -624.288818359375,
|
| 1193 |
+
"logps/rejected": -786.5145263671875,
|
| 1194 |
+
"loss": 0.2184,
|
| 1195 |
+
"rewards/accuracies": 0.78125,
|
| 1196 |
+
"rewards/chosen": -0.28965824842453003,
|
| 1197 |
+
"rewards/margins": 0.20828434824943542,
|
| 1198 |
+
"rewards/rejected": -0.49794262647628784,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": 0.08053167164325714,
|
| 1205 |
+
"logits/rejected": 0.1703474223613739,
|
| 1206 |
+
"logps/chosen": -638.90966796875,
|
| 1207 |
+
"logps/rejected": -760.4950561523438,
|
| 1208 |
+
"loss": 0.2568,
|
| 1209 |
+
"rewards/accuracies": 0.6875,
|
| 1210 |
+
"rewards/chosen": -0.29267439246177673,
|
| 1211 |
+
"rewards/margins": 0.18851785361766815,
|
| 1212 |
+
"rewards/rejected": -0.48119229078292847,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": 0.08862993866205215,
|
| 1219 |
+
"logits/rejected": 0.2355298101902008,
|
| 1220 |
+
"logps/chosen": -659.1481323242188,
|
| 1221 |
+
"logps/rejected": -788.7034912109375,
|
| 1222 |
+
"loss": 0.2149,
|
| 1223 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1224 |
+
"rewards/chosen": -0.28642982244491577,
|
| 1225 |
+
"rewards/margins": 0.22406980395317078,
|
| 1226 |
+
"rewards/rejected": -0.5104995965957642,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": 0.09468914568424225,
|
| 1233 |
+
"logits/rejected": 0.17423442006111145,
|
| 1234 |
+
"logps/chosen": -628.0216064453125,
|
| 1235 |
+
"logps/rejected": -736.0591430664062,
|
| 1236 |
+
"loss": 0.2635,
|
| 1237 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1238 |
+
"rewards/chosen": -0.29823777079582214,
|
| 1239 |
+
"rewards/margins": 0.16002070903778076,
|
| 1240 |
+
"rewards/rejected": -0.4582585394382477,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": 0.1822114735841751,
|
| 1247 |
+
"logits/rejected": 0.25673800706863403,
|
| 1248 |
+
"logps/chosen": -647.0616455078125,
|
| 1249 |
+
"logps/rejected": -785.24853515625,
|
| 1250 |
+
"loss": 0.2055,
|
| 1251 |
+
"rewards/accuracies": 0.71875,
|
| 1252 |
+
"rewards/chosen": -0.2835825979709625,
|
| 1253 |
+
"rewards/margins": 0.21645894646644592,
|
| 1254 |
+
"rewards/rejected": -0.5000415444374084,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": 0.08051988482475281,
|
| 1261 |
+
"logits/rejected": 0.22623100876808167,
|
| 1262 |
+
"logps/chosen": -661.945068359375,
|
| 1263 |
+
"logps/rejected": -801.7554321289062,
|
| 1264 |
+
"loss": 0.279,
|
| 1265 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1266 |
+
"rewards/chosen": -0.3187974691390991,
|
| 1267 |
+
"rewards/margins": 0.20359888672828674,
|
| 1268 |
+
"rewards/rejected": -0.5223963260650635,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": 0.09252520650625229,
|
| 1275 |
+
"logits/rejected": 0.2231016904115677,
|
| 1276 |
+
"logps/chosen": -594.2275390625,
|
| 1277 |
+
"logps/rejected": -788.0599975585938,
|
| 1278 |
+
"loss": 0.2146,
|
| 1279 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1280 |
+
"rewards/chosen": -0.2893867492675781,
|
| 1281 |
+
"rewards/margins": 0.22611062228679657,
|
| 1282 |
+
"rewards/rejected": -0.5154973864555359,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": 0.06350111961364746,
|
| 1289 |
+
"logits/rejected": 0.20778074860572815,
|
| 1290 |
+
"logps/chosen": -707.4957275390625,
|
| 1291 |
+
"logps/rejected": -834.1343994140625,
|
| 1292 |
+
"loss": 0.2248,
|
| 1293 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1294 |
+
"rewards/chosen": -0.3360898196697235,
|
| 1295 |
+
"rewards/margins": 0.18199169635772705,
|
| 1296 |
+
"rewards/rejected": -0.518081545829773,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": 0.08399736881256104,
|
| 1303 |
+
"logits/rejected": 0.18887805938720703,
|
| 1304 |
+
"logps/chosen": -649.8248291015625,
|
| 1305 |
+
"logps/rejected": -780.5101318359375,
|
| 1306 |
+
"loss": 0.212,
|
| 1307 |
+
"rewards/accuracies": 0.78125,
|
| 1308 |
+
"rewards/chosen": -0.2871829569339752,
|
| 1309 |
+
"rewards/margins": 0.21405375003814697,
|
| 1310 |
+
"rewards/rejected": -0.5012367367744446,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": 0.10902540385723114,
|
| 1317 |
+
"logits/rejected": 0.24318072199821472,
|
| 1318 |
+
"logps/chosen": -606.8221435546875,
|
| 1319 |
+
"logps/rejected": -784.5928955078125,
|
| 1320 |
+
"loss": 0.2001,
|
| 1321 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1322 |
+
"rewards/chosen": -0.284158855676651,
|
| 1323 |
+
"rewards/margins": 0.23260316252708435,
|
| 1324 |
+
"rewards/rejected": -0.5167620778083801,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.2460615715387664,
|
| 1332 |
+
"train_runtime": 8500.6415,
|
| 1333 |
+
"train_samples_per_second": 1.765,
|
| 1334 |
+
"train_steps_per_second": 0.11
|
| 1335 |
+
}
|
| 1336 |
+
],
|
| 1337 |
+
"logging_steps": 10,
|
| 1338 |
+
"max_steps": 937,
|
| 1339 |
+
"num_input_tokens_seen": 0,
|
| 1340 |
+
"num_train_epochs": 1,
|
| 1341 |
+
"save_steps": 100,
|
| 1342 |
+
"total_flos": 0.0,
|
| 1343 |
+
"train_batch_size": 4,
|
| 1344 |
+
"trial_name": null,
|
| 1345 |
+
"trial_params": null
|
| 1346 |
+
}
|