Commit
•
4cbd7b3
1
Parent(s):
fd2f7d0
Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May12_03-16-12_gpu4-119-5/events.out.tfevents.1715447867.gpu4-119-5.1635540.0 +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-newSFT-b0.001-15k-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-newSFT-b0.001-15k-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
|
| 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 sha256:04bd7811e39cdf74d4d86fd4c6a4be4cdd840c33cf7ccfcefa091bbccec38ff0
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2409534176996449,
|
| 4 |
+
"train_runtime": 8445.1148,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 1.776,
|
| 7 |
+
"train_steps_per_second": 0.111
|
| 8 |
+
}
|
runs/May12_03-16-12_gpu4-119-5/events.out.tfevents.1715447867.gpu4-119-5.1635540.0
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 sha256:9115c52186472389cb1a4c5a30f7efa0545b665da1c7bcec376620fc434a1a72
|
| 3 |
+
size 64690
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2409534176996449,
|
| 4 |
+
"train_runtime": 8445.1148,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 1.776,
|
| 7 |
+
"train_steps_per_second": 0.111
|
| 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": 0.06159799173474312,
|
| 15 |
+
"logits/rejected": 0.2503473162651062,
|
| 16 |
+
"logps/chosen": -348.4295349121094,
|
| 17 |
+
"logps/rejected": -269.23321533203125,
|
| 18 |
+
"loss": 0.4013,
|
| 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": 0.050236668437719345,
|
| 29 |
+
"logits/rejected": 0.23283202946186066,
|
| 30 |
+
"logps/chosen": -357.2872314453125,
|
| 31 |
+
"logps/rejected": -284.6590270996094,
|
| 32 |
+
"loss": 0.3533,
|
| 33 |
+
"rewards/accuracies": 0.3958333432674408,
|
| 34 |
+
"rewards/chosen": -9.200325621350203e-06,
|
| 35 |
+
"rewards/margins": -3.7092313505127095e-06,
|
| 36 |
+
"rewards/rejected": -5.491095635079546e-06,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.07863714545965195,
|
| 43 |
+
"logits/rejected": 0.17622847855091095,
|
| 44 |
+
"logps/chosen": -305.1004638671875,
|
| 45 |
+
"logps/rejected": -284.56573486328125,
|
| 46 |
+
"loss": 0.3668,
|
| 47 |
+
"rewards/accuracies": 0.46875,
|
| 48 |
+
"rewards/chosen": -3.269618537160568e-05,
|
| 49 |
+
"rewards/margins": -7.148426084313542e-05,
|
| 50 |
+
"rewards/rejected": 3.878808274748735e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.10170497745275497,
|
| 57 |
+
"logits/rejected": 0.2674924433231354,
|
| 58 |
+
"logps/chosen": -318.61309814453125,
|
| 59 |
+
"logps/rejected": -289.11529541015625,
|
| 60 |
+
"loss": 0.3582,
|
| 61 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 62 |
+
"rewards/chosen": -2.7896196570509346e-06,
|
| 63 |
+
"rewards/margins": -0.00010077792830998078,
|
| 64 |
+
"rewards/rejected": 9.798832616070285e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.09615897387266159,
|
| 71 |
+
"logits/rejected": 0.2696045935153961,
|
| 72 |
+
"logps/chosen": -371.0738220214844,
|
| 73 |
+
"logps/rejected": -285.8421325683594,
|
| 74 |
+
"loss": 0.3338,
|
| 75 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 76 |
+
"rewards/chosen": 4.211660780129023e-05,
|
| 77 |
+
"rewards/margins": 0.0002511069178581238,
|
| 78 |
+
"rewards/rejected": -0.00020899029914289713,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.1058117151260376,
|
| 85 |
+
"logits/rejected": 0.2665451169013977,
|
| 86 |
+
"logps/chosen": -365.52001953125,
|
| 87 |
+
"logps/rejected": -291.03778076171875,
|
| 88 |
+
"loss": 0.3245,
|
| 89 |
+
"rewards/accuracies": 0.625,
|
| 90 |
+
"rewards/chosen": 0.0004745240439660847,
|
| 91 |
+
"rewards/margins": 0.0008677773294039071,
|
| 92 |
+
"rewards/rejected": -0.00039325328543782234,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.07869451493024826,
|
| 99 |
+
"logits/rejected": 0.2602466642856598,
|
| 100 |
+
"logps/chosen": -347.3607482910156,
|
| 101 |
+
"logps/rejected": -290.67364501953125,
|
| 102 |
+
"loss": 0.3335,
|
| 103 |
+
"rewards/accuracies": 0.731249988079071,
|
| 104 |
+
"rewards/chosen": 0.0010413106065243483,
|
| 105 |
+
"rewards/margins": 0.0015250012511387467,
|
| 106 |
+
"rewards/rejected": -0.00048369058640673757,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.12400275468826294,
|
| 113 |
+
"logits/rejected": 0.26277071237564087,
|
| 114 |
+
"logps/chosen": -336.801025390625,
|
| 115 |
+
"logps/rejected": -295.81439208984375,
|
| 116 |
+
"loss": 0.3541,
|
| 117 |
+
"rewards/accuracies": 0.668749988079071,
|
| 118 |
+
"rewards/chosen": 0.0017572289798408747,
|
| 119 |
+
"rewards/margins": 0.002515274565666914,
|
| 120 |
+
"rewards/rejected": -0.0007580459350720048,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.06505224108695984,
|
| 127 |
+
"logits/rejected": 0.18910573422908783,
|
| 128 |
+
"logps/chosen": -312.43511962890625,
|
| 129 |
+
"logps/rejected": -274.01617431640625,
|
| 130 |
+
"loss": 0.3528,
|
| 131 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 132 |
+
"rewards/chosen": 0.003332150634378195,
|
| 133 |
+
"rewards/margins": 0.004707558546215296,
|
| 134 |
+
"rewards/rejected": -0.0013754077954217792,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.09570185840129852,
|
| 141 |
+
"logits/rejected": 0.292137086391449,
|
| 142 |
+
"logps/chosen": -320.4757080078125,
|
| 143 |
+
"logps/rejected": -282.39453125,
|
| 144 |
+
"loss": 0.3233,
|
| 145 |
+
"rewards/accuracies": 0.706250011920929,
|
| 146 |
+
"rewards/chosen": 0.005724198184907436,
|
| 147 |
+
"rewards/margins": 0.00849069096148014,
|
| 148 |
+
"rewards/rejected": -0.002766493707895279,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.11051477491855621,
|
| 155 |
+
"logits/rejected": 0.2542819380760193,
|
| 156 |
+
"logps/chosen": -341.4449768066406,
|
| 157 |
+
"logps/rejected": -303.7613220214844,
|
| 158 |
+
"loss": 0.2954,
|
| 159 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 160 |
+
"rewards/chosen": 0.006659829057753086,
|
| 161 |
+
"rewards/margins": 0.017101887613534927,
|
| 162 |
+
"rewards/rejected": -0.010442061349749565,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.09644671529531479,
|
| 169 |
+
"logits/rejected": 0.26117372512817383,
|
| 170 |
+
"logps/chosen": -347.67059326171875,
|
| 171 |
+
"logps/rejected": -339.35205078125,
|
| 172 |
+
"loss": 0.3068,
|
| 173 |
+
"rewards/accuracies": 0.737500011920929,
|
| 174 |
+
"rewards/chosen": -0.005562308244407177,
|
| 175 |
+
"rewards/margins": 0.025120720267295837,
|
| 176 |
+
"rewards/rejected": -0.03068302944302559,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.1643160879611969,
|
| 183 |
+
"logits/rejected": 0.33352339267730713,
|
| 184 |
+
"logps/chosen": -393.2250061035156,
|
| 185 |
+
"logps/rejected": -346.75457763671875,
|
| 186 |
+
"loss": 0.3154,
|
| 187 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 188 |
+
"rewards/chosen": -0.026022305712103844,
|
| 189 |
+
"rewards/margins": 0.04141021519899368,
|
| 190 |
+
"rewards/rejected": -0.06743250787258148,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.14933325350284576,
|
| 197 |
+
"logits/rejected": 0.36655381321907043,
|
| 198 |
+
"logps/chosen": -425.4112243652344,
|
| 199 |
+
"logps/rejected": -428.3099670410156,
|
| 200 |
+
"loss": 0.2788,
|
| 201 |
+
"rewards/accuracies": 0.6875,
|
| 202 |
+
"rewards/chosen": -0.07423840463161469,
|
| 203 |
+
"rewards/margins": 0.06771700084209442,
|
| 204 |
+
"rewards/rejected": -0.1419553905725479,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.20979711413383484,
|
| 211 |
+
"logits/rejected": 0.2947987914085388,
|
| 212 |
+
"logps/chosen": -455.8238830566406,
|
| 213 |
+
"logps/rejected": -478.470703125,
|
| 214 |
+
"loss": 0.2889,
|
| 215 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 216 |
+
"rewards/chosen": -0.11944756656885147,
|
| 217 |
+
"rewards/margins": 0.08143159002065659,
|
| 218 |
+
"rewards/rejected": -0.20087914168834686,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.22968748211860657,
|
| 225 |
+
"logits/rejected": 0.3435000777244568,
|
| 226 |
+
"logps/chosen": -494.1380920410156,
|
| 227 |
+
"logps/rejected": -557.603271484375,
|
| 228 |
+
"loss": 0.2274,
|
| 229 |
+
"rewards/accuracies": 0.78125,
|
| 230 |
+
"rewards/chosen": -0.15503188967704773,
|
| 231 |
+
"rewards/margins": 0.12964466214179993,
|
| 232 |
+
"rewards/rejected": -0.28467655181884766,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.2052285373210907,
|
| 239 |
+
"logits/rejected": 0.3779992461204529,
|
| 240 |
+
"logps/chosen": -555.717529296875,
|
| 241 |
+
"logps/rejected": -618.7412719726562,
|
| 242 |
+
"loss": 0.2945,
|
| 243 |
+
"rewards/accuracies": 0.668749988079071,
|
| 244 |
+
"rewards/chosen": -0.22048434615135193,
|
| 245 |
+
"rewards/margins": 0.12210027873516083,
|
| 246 |
+
"rewards/rejected": -0.34258466958999634,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.19485141336917877,
|
| 253 |
+
"logits/rejected": 0.35038071870803833,
|
| 254 |
+
"logps/chosen": -564.8143310546875,
|
| 255 |
+
"logps/rejected": -614.8881225585938,
|
| 256 |
+
"loss": 0.2459,
|
| 257 |
+
"rewards/accuracies": 0.71875,
|
| 258 |
+
"rewards/chosen": -0.19514423608779907,
|
| 259 |
+
"rewards/margins": 0.13954147696495056,
|
| 260 |
+
"rewards/rejected": -0.33468568325042725,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.26888132095336914,
|
| 267 |
+
"logits/rejected": 0.38210389018058777,
|
| 268 |
+
"logps/chosen": -542.71875,
|
| 269 |
+
"logps/rejected": -610.9818115234375,
|
| 270 |
+
"loss": 0.2668,
|
| 271 |
+
"rewards/accuracies": 0.699999988079071,
|
| 272 |
+
"rewards/chosen": -0.20494337379932404,
|
| 273 |
+
"rewards/margins": 0.13571330904960632,
|
| 274 |
+
"rewards/rejected": -0.34065669775009155,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.27069562673568726,
|
| 281 |
+
"logits/rejected": 0.3432765603065491,
|
| 282 |
+
"logps/chosen": -552.3577270507812,
|
| 283 |
+
"logps/rejected": -633.7227783203125,
|
| 284 |
+
"loss": 0.2295,
|
| 285 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 286 |
+
"rewards/chosen": -0.20474235713481903,
|
| 287 |
+
"rewards/margins": 0.14836545288562775,
|
| 288 |
+
"rewards/rejected": -0.35310783982276917,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.2959613800048828,
|
| 295 |
+
"logits/rejected": 0.4290657639503479,
|
| 296 |
+
"logps/chosen": -607.9371337890625,
|
| 297 |
+
"logps/rejected": -658.5770263671875,
|
| 298 |
+
"loss": 0.2489,
|
| 299 |
+
"rewards/accuracies": 0.762499988079071,
|
| 300 |
+
"rewards/chosen": -0.22546908259391785,
|
| 301 |
+
"rewards/margins": 0.14855849742889404,
|
| 302 |
+
"rewards/rejected": -0.3740275502204895,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.315132200717926,
|
| 309 |
+
"logits/rejected": 0.43885716795921326,
|
| 310 |
+
"logps/chosen": -636.2320556640625,
|
| 311 |
+
"logps/rejected": -777.607421875,
|
| 312 |
+
"loss": 0.2412,
|
| 313 |
+
"rewards/accuracies": 0.737500011920929,
|
| 314 |
+
"rewards/chosen": -0.28788623213768005,
|
| 315 |
+
"rewards/margins": 0.1952207386493683,
|
| 316 |
+
"rewards/rejected": -0.4831070005893707,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.27698999643325806,
|
| 323 |
+
"logits/rejected": 0.468730628490448,
|
| 324 |
+
"logps/chosen": -641.8867797851562,
|
| 325 |
+
"logps/rejected": -759.454833984375,
|
| 326 |
+
"loss": 0.2575,
|
| 327 |
+
"rewards/accuracies": 0.737500011920929,
|
| 328 |
+
"rewards/chosen": -0.26833561062812805,
|
| 329 |
+
"rewards/margins": 0.1899726390838623,
|
| 330 |
+
"rewards/rejected": -0.45830821990966797,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": 0.2822573781013489,
|
| 337 |
+
"logits/rejected": 0.42682987451553345,
|
| 338 |
+
"logps/chosen": -578.1446533203125,
|
| 339 |
+
"logps/rejected": -648.0927734375,
|
| 340 |
+
"loss": 0.2443,
|
| 341 |
+
"rewards/accuracies": 0.78125,
|
| 342 |
+
"rewards/chosen": -0.19278240203857422,
|
| 343 |
+
"rewards/margins": 0.18077878654003143,
|
| 344 |
+
"rewards/rejected": -0.37356117367744446,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": 0.3316207230091095,
|
| 351 |
+
"logits/rejected": 0.42460235953330994,
|
| 352 |
+
"logps/chosen": -508.28924560546875,
|
| 353 |
+
"logps/rejected": -627.9178466796875,
|
| 354 |
+
"loss": 0.2394,
|
| 355 |
+
"rewards/accuracies": 0.75,
|
| 356 |
+
"rewards/chosen": -0.18461547791957855,
|
| 357 |
+
"rewards/margins": 0.17850570380687714,
|
| 358 |
+
"rewards/rejected": -0.3631211817264557,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": 0.34463202953338623,
|
| 365 |
+
"logits/rejected": 0.4213656485080719,
|
| 366 |
+
"logps/chosen": -602.0831909179688,
|
| 367 |
+
"logps/rejected": -723.1624145507812,
|
| 368 |
+
"loss": 0.2229,
|
| 369 |
+
"rewards/accuracies": 0.768750011920929,
|
| 370 |
+
"rewards/chosen": -0.22979848086833954,
|
| 371 |
+
"rewards/margins": 0.1861880123615265,
|
| 372 |
+
"rewards/rejected": -0.41598647832870483,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": 0.2841508984565735,
|
| 379 |
+
"logits/rejected": 0.4096981883049011,
|
| 380 |
+
"logps/chosen": -649.3954467773438,
|
| 381 |
+
"logps/rejected": -714.6544189453125,
|
| 382 |
+
"loss": 0.263,
|
| 383 |
+
"rewards/accuracies": 0.706250011920929,
|
| 384 |
+
"rewards/chosen": -0.26575830578804016,
|
| 385 |
+
"rewards/margins": 0.15293100476264954,
|
| 386 |
+
"rewards/rejected": -0.4186893105506897,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": 0.33302605152130127,
|
| 393 |
+
"logits/rejected": 0.4252694249153137,
|
| 394 |
+
"logps/chosen": -652.48828125,
|
| 395 |
+
"logps/rejected": -734.8269653320312,
|
| 396 |
+
"loss": 0.2375,
|
| 397 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 398 |
+
"rewards/chosen": -0.2703024744987488,
|
| 399 |
+
"rewards/margins": 0.16575393080711365,
|
| 400 |
+
"rewards/rejected": -0.43605637550354004,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": 0.2720186710357666,
|
| 407 |
+
"logits/rejected": 0.4189075827598572,
|
| 408 |
+
"logps/chosen": -606.5438232421875,
|
| 409 |
+
"logps/rejected": -711.4382934570312,
|
| 410 |
+
"loss": 0.234,
|
| 411 |
+
"rewards/accuracies": 0.78125,
|
| 412 |
+
"rewards/chosen": -0.2561277151107788,
|
| 413 |
+
"rewards/margins": 0.1838252693414688,
|
| 414 |
+
"rewards/rejected": -0.4399529993534088,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": 0.2856540381908417,
|
| 421 |
+
"logits/rejected": 0.46640047430992126,
|
| 422 |
+
"logps/chosen": -581.0446166992188,
|
| 423 |
+
"logps/rejected": -699.5716552734375,
|
| 424 |
+
"loss": 0.2034,
|
| 425 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 426 |
+
"rewards/chosen": -0.22450003027915955,
|
| 427 |
+
"rewards/margins": 0.187502920627594,
|
| 428 |
+
"rewards/rejected": -0.41200295090675354,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": 0.30591830611228943,
|
| 435 |
+
"logits/rejected": 0.4262414574623108,
|
| 436 |
+
"logps/chosen": -547.7359619140625,
|
| 437 |
+
"logps/rejected": -688.0494995117188,
|
| 438 |
+
"loss": 0.2329,
|
| 439 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 440 |
+
"rewards/chosen": -0.2417764961719513,
|
| 441 |
+
"rewards/margins": 0.18638503551483154,
|
| 442 |
+
"rewards/rejected": -0.42816153168678284,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": 0.2821730375289917,
|
| 449 |
+
"logits/rejected": 0.4414825439453125,
|
| 450 |
+
"logps/chosen": -625.08984375,
|
| 451 |
+
"logps/rejected": -736.9857177734375,
|
| 452 |
+
"loss": 0.2392,
|
| 453 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 454 |
+
"rewards/chosen": -0.29913753271102905,
|
| 455 |
+
"rewards/margins": 0.1723407357931137,
|
| 456 |
+
"rewards/rejected": -0.4714782238006592,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": 0.3146980404853821,
|
| 463 |
+
"logits/rejected": 0.5349381566047668,
|
| 464 |
+
"logps/chosen": -667.1527099609375,
|
| 465 |
+
"logps/rejected": -809.9267578125,
|
| 466 |
+
"loss": 0.2347,
|
| 467 |
+
"rewards/accuracies": 0.737500011920929,
|
| 468 |
+
"rewards/chosen": -0.3215456008911133,
|
| 469 |
+
"rewards/margins": 0.2190614491701126,
|
| 470 |
+
"rewards/rejected": -0.5406070947647095,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": 0.3459940552711487,
|
| 477 |
+
"logits/rejected": 0.5182437300682068,
|
| 478 |
+
"logps/chosen": -632.4589233398438,
|
| 479 |
+
"logps/rejected": -797.7081298828125,
|
| 480 |
+
"loss": 0.1764,
|
| 481 |
+
"rewards/accuracies": 0.862500011920929,
|
| 482 |
+
"rewards/chosen": -0.2630694508552551,
|
| 483 |
+
"rewards/margins": 0.2305426150560379,
|
| 484 |
+
"rewards/rejected": -0.49361199140548706,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": 0.3081711232662201,
|
| 491 |
+
"logits/rejected": 0.3925454020500183,
|
| 492 |
+
"logps/chosen": -592.3121948242188,
|
| 493 |
+
"logps/rejected": -695.0133666992188,
|
| 494 |
+
"loss": 0.2528,
|
| 495 |
+
"rewards/accuracies": 0.706250011920929,
|
| 496 |
+
"rewards/chosen": -0.2648671865463257,
|
| 497 |
+
"rewards/margins": 0.17098167538642883,
|
| 498 |
+
"rewards/rejected": -0.4358488619327545,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.3076136112213135,
|
| 505 |
+
"logits/rejected": 0.38813453912734985,
|
| 506 |
+
"logps/chosen": -642.5826416015625,
|
| 507 |
+
"logps/rejected": -815.0631103515625,
|
| 508 |
+
"loss": 0.1942,
|
| 509 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 510 |
+
"rewards/chosen": -0.31470799446105957,
|
| 511 |
+
"rewards/margins": 0.20841769874095917,
|
| 512 |
+
"rewards/rejected": -0.5231257677078247,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": 0.2800385057926178,
|
| 519 |
+
"logits/rejected": 0.45763272047042847,
|
| 520 |
+
"logps/chosen": -611.0481567382812,
|
| 521 |
+
"logps/rejected": -790.9743041992188,
|
| 522 |
+
"loss": 0.1966,
|
| 523 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 524 |
+
"rewards/chosen": -0.275074303150177,
|
| 525 |
+
"rewards/margins": 0.22857530415058136,
|
| 526 |
+
"rewards/rejected": -0.5036496520042419,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": 0.2838382422924042,
|
| 533 |
+
"logits/rejected": 0.4253064692020416,
|
| 534 |
+
"logps/chosen": -663.5225830078125,
|
| 535 |
+
"logps/rejected": -790.7160034179688,
|
| 536 |
+
"loss": 0.2077,
|
| 537 |
+
"rewards/accuracies": 0.737500011920929,
|
| 538 |
+
"rewards/chosen": -0.28215542435646057,
|
| 539 |
+
"rewards/margins": 0.2109585702419281,
|
| 540 |
+
"rewards/rejected": -0.49311399459838867,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": 0.32005783915519714,
|
| 547 |
+
"logits/rejected": 0.42395836114883423,
|
| 548 |
+
"logps/chosen": -589.5636596679688,
|
| 549 |
+
"logps/rejected": -722.5950317382812,
|
| 550 |
+
"loss": 0.2375,
|
| 551 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 552 |
+
"rewards/chosen": -0.24356071650981903,
|
| 553 |
+
"rewards/margins": 0.18706892430782318,
|
| 554 |
+
"rewards/rejected": -0.4306296408176422,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": 0.318645715713501,
|
| 561 |
+
"logits/rejected": 0.4325946271419525,
|
| 562 |
+
"logps/chosen": -611.2227783203125,
|
| 563 |
+
"logps/rejected": -759.0226440429688,
|
| 564 |
+
"loss": 0.2232,
|
| 565 |
+
"rewards/accuracies": 0.737500011920929,
|
| 566 |
+
"rewards/chosen": -0.25262197852134705,
|
| 567 |
+
"rewards/margins": 0.19418981671333313,
|
| 568 |
+
"rewards/rejected": -0.44681182503700256,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": 0.27690261602401733,
|
| 575 |
+
"logits/rejected": 0.4690285325050354,
|
| 576 |
+
"logps/chosen": -600.1328125,
|
| 577 |
+
"logps/rejected": -722.5906982421875,
|
| 578 |
+
"loss": 0.2403,
|
| 579 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 580 |
+
"rewards/chosen": -0.2763115167617798,
|
| 581 |
+
"rewards/margins": 0.16976875066757202,
|
| 582 |
+
"rewards/rejected": -0.4460802674293518,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": 0.2978890836238861,
|
| 589 |
+
"logits/rejected": 0.5168454647064209,
|
| 590 |
+
"logps/chosen": -631.8878173828125,
|
| 591 |
+
"logps/rejected": -754.962646484375,
|
| 592 |
+
"loss": 0.2448,
|
| 593 |
+
"rewards/accuracies": 0.737500011920929,
|
| 594 |
+
"rewards/chosen": -0.3049059808254242,
|
| 595 |
+
"rewards/margins": 0.16670657694339752,
|
| 596 |
+
"rewards/rejected": -0.4716125428676605,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": 0.31090012192726135,
|
| 603 |
+
"logits/rejected": 0.4086151123046875,
|
| 604 |
+
"logps/chosen": -639.5802612304688,
|
| 605 |
+
"logps/rejected": -715.4155883789062,
|
| 606 |
+
"loss": 0.2345,
|
| 607 |
+
"rewards/accuracies": 0.699999988079071,
|
| 608 |
+
"rewards/chosen": -0.29435452818870544,
|
| 609 |
+
"rewards/margins": 0.1740979552268982,
|
| 610 |
+
"rewards/rejected": -0.46845245361328125,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": 0.29356813430786133,
|
| 617 |
+
"logits/rejected": 0.45901551842689514,
|
| 618 |
+
"logps/chosen": -648.76806640625,
|
| 619 |
+
"logps/rejected": -793.9247436523438,
|
| 620 |
+
"loss": 0.195,
|
| 621 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 622 |
+
"rewards/chosen": -0.30719709396362305,
|
| 623 |
+
"rewards/margins": 0.2049371302127838,
|
| 624 |
+
"rewards/rejected": -0.5121342539787292,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": 0.35314708948135376,
|
| 631 |
+
"logits/rejected": 0.4861513078212738,
|
| 632 |
+
"logps/chosen": -669.8665771484375,
|
| 633 |
+
"logps/rejected": -808.8753051757812,
|
| 634 |
+
"loss": 0.2386,
|
| 635 |
+
"rewards/accuracies": 0.75,
|
| 636 |
+
"rewards/chosen": -0.34487032890319824,
|
| 637 |
+
"rewards/margins": 0.20408621430397034,
|
| 638 |
+
"rewards/rejected": -0.548956573009491,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": 0.3531484007835388,
|
| 645 |
+
"logits/rejected": 0.5174172520637512,
|
| 646 |
+
"logps/chosen": -657.7909545898438,
|
| 647 |
+
"logps/rejected": -806.8094482421875,
|
| 648 |
+
"loss": 0.2039,
|
| 649 |
+
"rewards/accuracies": 0.78125,
|
| 650 |
+
"rewards/chosen": -0.3043491244316101,
|
| 651 |
+
"rewards/margins": 0.21579626202583313,
|
| 652 |
+
"rewards/rejected": -0.5201453566551208,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": 0.29440468549728394,
|
| 659 |
+
"logits/rejected": 0.4629596769809723,
|
| 660 |
+
"logps/chosen": -613.6539916992188,
|
| 661 |
+
"logps/rejected": -718.9657592773438,
|
| 662 |
+
"loss": 0.2514,
|
| 663 |
+
"rewards/accuracies": 0.699999988079071,
|
| 664 |
+
"rewards/chosen": -0.28395384550094604,
|
| 665 |
+
"rewards/margins": 0.17435352504253387,
|
| 666 |
+
"rewards/rejected": -0.4583073556423187,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": 0.26766303181648254,
|
| 673 |
+
"logits/rejected": 0.4210576117038727,
|
| 674 |
+
"logps/chosen": -611.0421142578125,
|
| 675 |
+
"logps/rejected": -752.10546875,
|
| 676 |
+
"loss": 0.2478,
|
| 677 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 678 |
+
"rewards/chosen": -0.2685486972332001,
|
| 679 |
+
"rewards/margins": 0.20156879723072052,
|
| 680 |
+
"rewards/rejected": -0.4701175093650818,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": 0.3156279921531677,
|
| 687 |
+
"logits/rejected": 0.4234594702720642,
|
| 688 |
+
"logps/chosen": -583.9177856445312,
|
| 689 |
+
"logps/rejected": -695.6286010742188,
|
| 690 |
+
"loss": 0.2687,
|
| 691 |
+
"rewards/accuracies": 0.731249988079071,
|
| 692 |
+
"rewards/chosen": -0.2727667987346649,
|
| 693 |
+
"rewards/margins": 0.16848285496234894,
|
| 694 |
+
"rewards/rejected": -0.44124966859817505,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": 0.2484460324048996,
|
| 701 |
+
"logits/rejected": 0.3799341320991516,
|
| 702 |
+
"logps/chosen": -582.5774536132812,
|
| 703 |
+
"logps/rejected": -692.3199462890625,
|
| 704 |
+
"loss": 0.2314,
|
| 705 |
+
"rewards/accuracies": 0.731249988079071,
|
| 706 |
+
"rewards/chosen": -0.23775920271873474,
|
| 707 |
+
"rewards/margins": 0.1904359757900238,
|
| 708 |
+
"rewards/rejected": -0.42819517850875854,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": 0.31521672010421753,
|
| 715 |
+
"logits/rejected": 0.4720017910003662,
|
| 716 |
+
"logps/chosen": -617.0424194335938,
|
| 717 |
+
"logps/rejected": -763.6742553710938,
|
| 718 |
+
"loss": 0.2106,
|
| 719 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 720 |
+
"rewards/chosen": -0.2587849795818329,
|
| 721 |
+
"rewards/margins": 0.21287491917610168,
|
| 722 |
+
"rewards/rejected": -0.4716598391532898,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": 0.23266558349132538,
|
| 729 |
+
"logits/rejected": 0.4128551483154297,
|
| 730 |
+
"logps/chosen": -645.7574462890625,
|
| 731 |
+
"logps/rejected": -775.3682861328125,
|
| 732 |
+
"loss": 0.2031,
|
| 733 |
+
"rewards/accuracies": 0.737500011920929,
|
| 734 |
+
"rewards/chosen": -0.26859793066978455,
|
| 735 |
+
"rewards/margins": 0.21920350193977356,
|
| 736 |
+
"rewards/rejected": -0.4878014624118805,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": 0.2809138298034668,
|
| 743 |
+
"logits/rejected": 0.36528998613357544,
|
| 744 |
+
"logps/chosen": -635.5758666992188,
|
| 745 |
+
"logps/rejected": -790.5833129882812,
|
| 746 |
+
"loss": 0.2095,
|
| 747 |
+
"rewards/accuracies": 0.768750011920929,
|
| 748 |
+
"rewards/chosen": -0.29754263162612915,
|
| 749 |
+
"rewards/margins": 0.1984301209449768,
|
| 750 |
+
"rewards/rejected": -0.49597278237342834,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": 0.27885499596595764,
|
| 757 |
+
"logits/rejected": 0.4202384352684021,
|
| 758 |
+
"logps/chosen": -633.392333984375,
|
| 759 |
+
"logps/rejected": -738.7381591796875,
|
| 760 |
+
"loss": 0.2417,
|
| 761 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 762 |
+
"rewards/chosen": -0.296310693025589,
|
| 763 |
+
"rewards/margins": 0.18409204483032227,
|
| 764 |
+
"rewards/rejected": -0.48040276765823364,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": 0.2572694420814514,
|
| 771 |
+
"logits/rejected": 0.3829544484615326,
|
| 772 |
+
"logps/chosen": -661.2225341796875,
|
| 773 |
+
"logps/rejected": -775.2647094726562,
|
| 774 |
+
"loss": 0.2215,
|
| 775 |
+
"rewards/accuracies": 0.71875,
|
| 776 |
+
"rewards/chosen": -0.3194531500339508,
|
| 777 |
+
"rewards/margins": 0.1850832998752594,
|
| 778 |
+
"rewards/rejected": -0.5045364499092102,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": 0.22785460948944092,
|
| 785 |
+
"logits/rejected": 0.39559316635131836,
|
| 786 |
+
"logps/chosen": -616.7025146484375,
|
| 787 |
+
"logps/rejected": -784.1016235351562,
|
| 788 |
+
"loss": 0.2179,
|
| 789 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 790 |
+
"rewards/chosen": -0.28892993927001953,
|
| 791 |
+
"rewards/margins": 0.21685433387756348,
|
| 792 |
+
"rewards/rejected": -0.505784273147583,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": 0.24686650931835175,
|
| 799 |
+
"logits/rejected": 0.39195549488067627,
|
| 800 |
+
"logps/chosen": -679.55859375,
|
| 801 |
+
"logps/rejected": -784.8621215820312,
|
| 802 |
+
"loss": 0.2101,
|
| 803 |
+
"rewards/accuracies": 0.768750011920929,
|
| 804 |
+
"rewards/chosen": -0.3024412989616394,
|
| 805 |
+
"rewards/margins": 0.1977556049823761,
|
| 806 |
+
"rewards/rejected": -0.5001968741416931,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": 0.2292439192533493,
|
| 813 |
+
"logits/rejected": 0.4420854151248932,
|
| 814 |
+
"logps/chosen": -635.6842041015625,
|
| 815 |
+
"logps/rejected": -802.7564697265625,
|
| 816 |
+
"loss": 0.2054,
|
| 817 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 818 |
+
"rewards/chosen": -0.2987775206565857,
|
| 819 |
+
"rewards/margins": 0.22222964465618134,
|
| 820 |
+
"rewards/rejected": -0.5210071206092834,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": 0.24736735224723816,
|
| 827 |
+
"logits/rejected": 0.4444567561149597,
|
| 828 |
+
"logps/chosen": -658.0628662109375,
|
| 829 |
+
"logps/rejected": -821.857421875,
|
| 830 |
+
"loss": 0.2104,
|
| 831 |
+
"rewards/accuracies": 0.768750011920929,
|
| 832 |
+
"rewards/chosen": -0.3125050663948059,
|
| 833 |
+
"rewards/margins": 0.21667668223381042,
|
| 834 |
+
"rewards/rejected": -0.5291817784309387,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": 0.18406185507774353,
|
| 841 |
+
"logits/rejected": 0.3239056468009949,
|
| 842 |
+
"logps/chosen": -618.2083129882812,
|
| 843 |
+
"logps/rejected": -770.7822875976562,
|
| 844 |
+
"loss": 0.2304,
|
| 845 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 846 |
+
"rewards/chosen": -0.2990264892578125,
|
| 847 |
+
"rewards/margins": 0.19497379660606384,
|
| 848 |
+
"rewards/rejected": -0.49400028586387634,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": 0.23465320467948914,
|
| 855 |
+
"logits/rejected": 0.41701340675354004,
|
| 856 |
+
"logps/chosen": -603.99609375,
|
| 857 |
+
"logps/rejected": -717.4134521484375,
|
| 858 |
+
"loss": 0.2277,
|
| 859 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 860 |
+
"rewards/chosen": -0.274019718170166,
|
| 861 |
+
"rewards/margins": 0.18845617771148682,
|
| 862 |
+
"rewards/rejected": -0.4624759256839752,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": 0.2198990285396576,
|
| 869 |
+
"logits/rejected": 0.3981742560863495,
|
| 870 |
+
"logps/chosen": -660.04931640625,
|
| 871 |
+
"logps/rejected": -776.05322265625,
|
| 872 |
+
"loss": 0.2166,
|
| 873 |
+
"rewards/accuracies": 0.75,
|
| 874 |
+
"rewards/chosen": -0.275198370218277,
|
| 875 |
+
"rewards/margins": 0.21421167254447937,
|
| 876 |
+
"rewards/rejected": -0.4894101023674011,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": 0.21209344267845154,
|
| 883 |
+
"logits/rejected": 0.35057374835014343,
|
| 884 |
+
"logps/chosen": -608.8699951171875,
|
| 885 |
+
"logps/rejected": -748.3526611328125,
|
| 886 |
+
"loss": 0.2356,
|
| 887 |
+
"rewards/accuracies": 0.706250011920929,
|
| 888 |
+
"rewards/chosen": -0.30509600043296814,
|
| 889 |
+
"rewards/margins": 0.183022603392601,
|
| 890 |
+
"rewards/rejected": -0.48811858892440796,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": 0.1554277241230011,
|
| 897 |
+
"logits/rejected": 0.38564786314964294,
|
| 898 |
+
"logps/chosen": -655.8323974609375,
|
| 899 |
+
"logps/rejected": -804.4343872070312,
|
| 900 |
+
"loss": 0.2157,
|
| 901 |
+
"rewards/accuracies": 0.762499988079071,
|
| 902 |
+
"rewards/chosen": -0.29179584980010986,
|
| 903 |
+
"rewards/margins": 0.22734172642230988,
|
| 904 |
+
"rewards/rejected": -0.5191375613212585,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": 0.21835489571094513,
|
| 911 |
+
"logits/rejected": 0.365634948015213,
|
| 912 |
+
"logps/chosen": -661.9124145507812,
|
| 913 |
+
"logps/rejected": -783.0175170898438,
|
| 914 |
+
"loss": 0.1961,
|
| 915 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 916 |
+
"rewards/chosen": -0.3171085715293884,
|
| 917 |
+
"rewards/margins": 0.20071883499622345,
|
| 918 |
+
"rewards/rejected": -0.5178273916244507,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": 0.23657183349132538,
|
| 925 |
+
"logits/rejected": 0.3743918836116791,
|
| 926 |
+
"logps/chosen": -680.4862670898438,
|
| 927 |
+
"logps/rejected": -835.0526123046875,
|
| 928 |
+
"loss": 0.2212,
|
| 929 |
+
"rewards/accuracies": 0.762499988079071,
|
| 930 |
+
"rewards/chosen": -0.3263990879058838,
|
| 931 |
+
"rewards/margins": 0.22416400909423828,
|
| 932 |
+
"rewards/rejected": -0.5505631566047668,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": 0.2182171642780304,
|
| 939 |
+
"logits/rejected": 0.32706716656684875,
|
| 940 |
+
"logps/chosen": -675.8248901367188,
|
| 941 |
+
"logps/rejected": -836.1906127929688,
|
| 942 |
+
"loss": 0.2204,
|
| 943 |
+
"rewards/accuracies": 0.75,
|
| 944 |
+
"rewards/chosen": -0.3406047821044922,
|
| 945 |
+
"rewards/margins": 0.20144791901111603,
|
| 946 |
+
"rewards/rejected": -0.5420526266098022,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": 0.21965551376342773,
|
| 953 |
+
"logits/rejected": 0.377861887216568,
|
| 954 |
+
"logps/chosen": -645.6212158203125,
|
| 955 |
+
"logps/rejected": -850.5048828125,
|
| 956 |
+
"loss": 0.2011,
|
| 957 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 958 |
+
"rewards/chosen": -0.32531431317329407,
|
| 959 |
+
"rewards/margins": 0.23981444537639618,
|
| 960 |
+
"rewards/rejected": -0.565128743648529,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": 0.23912313580513,
|
| 967 |
+
"logits/rejected": 0.33457493782043457,
|
| 968 |
+
"logps/chosen": -652.5158081054688,
|
| 969 |
+
"logps/rejected": -804.5699462890625,
|
| 970 |
+
"loss": 0.2,
|
| 971 |
+
"rewards/accuracies": 0.71875,
|
| 972 |
+
"rewards/chosen": -0.3123088479042053,
|
| 973 |
+
"rewards/margins": 0.22432692348957062,
|
| 974 |
+
"rewards/rejected": -0.5366358160972595,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": 0.22238676249980927,
|
| 981 |
+
"logits/rejected": 0.4501045346260071,
|
| 982 |
+
"logps/chosen": -702.1354370117188,
|
| 983 |
+
"logps/rejected": -854.2493896484375,
|
| 984 |
+
"loss": 0.2429,
|
| 985 |
+
"rewards/accuracies": 0.737500011920929,
|
| 986 |
+
"rewards/chosen": -0.3496148884296417,
|
| 987 |
+
"rewards/margins": 0.21850232779979706,
|
| 988 |
+
"rewards/rejected": -0.5681171417236328,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": 0.21312983334064484,
|
| 995 |
+
"logits/rejected": 0.3885112702846527,
|
| 996 |
+
"logps/chosen": -668.33447265625,
|
| 997 |
+
"logps/rejected": -807.5436401367188,
|
| 998 |
+
"loss": 0.236,
|
| 999 |
+
"rewards/accuracies": 0.6875,
|
| 1000 |
+
"rewards/chosen": -0.3556881546974182,
|
| 1001 |
+
"rewards/margins": 0.1771022081375122,
|
| 1002 |
+
"rewards/rejected": -0.5327903628349304,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": 0.17015187442302704,
|
| 1009 |
+
"logits/rejected": 0.3787848949432373,
|
| 1010 |
+
"logps/chosen": -694.0350341796875,
|
| 1011 |
+
"logps/rejected": -877.3869018554688,
|
| 1012 |
+
"loss": 0.1718,
|
| 1013 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1014 |
+
"rewards/chosen": -0.32832252979278564,
|
| 1015 |
+
"rewards/margins": 0.2480977475643158,
|
| 1016 |
+
"rewards/rejected": -0.5764203071594238,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": 0.18861600756645203,
|
| 1023 |
+
"logits/rejected": 0.3507705330848694,
|
| 1024 |
+
"logps/chosen": -677.43701171875,
|
| 1025 |
+
"logps/rejected": -824.4730224609375,
|
| 1026 |
+
"loss": 0.1952,
|
| 1027 |
+
"rewards/accuracies": 0.8125,
|
| 1028 |
+
"rewards/chosen": -0.3222949504852295,
|
| 1029 |
+
"rewards/margins": 0.23219437897205353,
|
| 1030 |
+
"rewards/rejected": -0.5544893145561218,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": 0.22210793197155,
|
| 1037 |
+
"logits/rejected": 0.3462095856666565,
|
| 1038 |
+
"logps/chosen": -642.8484497070312,
|
| 1039 |
+
"logps/rejected": -801.2487182617188,
|
| 1040 |
+
"loss": 0.2144,
|
| 1041 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1042 |
+
"rewards/chosen": -0.2975847125053406,
|
| 1043 |
+
"rewards/margins": 0.23604163527488708,
|
| 1044 |
+
"rewards/rejected": -0.53362637758255,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": 0.18037883937358856,
|
| 1051 |
+
"logits/rejected": 0.32701772451400757,
|
| 1052 |
+
"logps/chosen": -619.3107299804688,
|
| 1053 |
+
"logps/rejected": -796.5120849609375,
|
| 1054 |
+
"loss": 0.2121,
|
| 1055 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1056 |
+
"rewards/chosen": -0.2894679307937622,
|
| 1057 |
+
"rewards/margins": 0.22074396908283234,
|
| 1058 |
+
"rewards/rejected": -0.5102118849754333,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": 0.21488244831562042,
|
| 1065 |
+
"logits/rejected": 0.3539666533470154,
|
| 1066 |
+
"logps/chosen": -646.1163330078125,
|
| 1067 |
+
"logps/rejected": -821.9992065429688,
|
| 1068 |
+
"loss": 0.1931,
|
| 1069 |
+
"rewards/accuracies": 0.78125,
|
| 1070 |
+
"rewards/chosen": -0.30917179584503174,
|
| 1071 |
+
"rewards/margins": 0.22842054069042206,
|
| 1072 |
+
"rewards/rejected": -0.537592351436615,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": 0.2123112678527832,
|
| 1079 |
+
"logits/rejected": 0.38105306029319763,
|
| 1080 |
+
"logps/chosen": -718.8529663085938,
|
| 1081 |
+
"logps/rejected": -841.3015747070312,
|
| 1082 |
+
"loss": 0.2265,
|
| 1083 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1084 |
+
"rewards/chosen": -0.3423205316066742,
|
| 1085 |
+
"rewards/margins": 0.21526296436786652,
|
| 1086 |
+
"rewards/rejected": -0.5575835108757019,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": 0.2072085589170456,
|
| 1093 |
+
"logits/rejected": 0.33443737030029297,
|
| 1094 |
+
"logps/chosen": -687.7586669921875,
|
| 1095 |
+
"logps/rejected": -815.7947998046875,
|
| 1096 |
+
"loss": 0.2148,
|
| 1097 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1098 |
+
"rewards/chosen": -0.3153381943702698,
|
| 1099 |
+
"rewards/margins": 0.20979492366313934,
|
| 1100 |
+
"rewards/rejected": -0.5251331329345703,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": 0.22315290570259094,
|
| 1107 |
+
"logits/rejected": 0.39601173996925354,
|
| 1108 |
+
"logps/chosen": -641.2395629882812,
|
| 1109 |
+
"logps/rejected": -768.5919799804688,
|
| 1110 |
+
"loss": 0.2332,
|
| 1111 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1112 |
+
"rewards/chosen": -0.2931545674800873,
|
| 1113 |
+
"rewards/margins": 0.20355018973350525,
|
| 1114 |
+
"rewards/rejected": -0.49670475721359253,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": 0.23425737023353577,
|
| 1121 |
+
"logits/rejected": 0.3700588047504425,
|
| 1122 |
+
"logps/chosen": -647.1505737304688,
|
| 1123 |
+
"logps/rejected": -796.8721313476562,
|
| 1124 |
+
"loss": 0.2232,
|
| 1125 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1126 |
+
"rewards/chosen": -0.3021949827671051,
|
| 1127 |
+
"rewards/margins": 0.2227589339017868,
|
| 1128 |
+
"rewards/rejected": -0.5249539017677307,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": 0.21941573917865753,
|
| 1135 |
+
"logits/rejected": 0.38576945662498474,
|
| 1136 |
+
"logps/chosen": -681.2139282226562,
|
| 1137 |
+
"logps/rejected": -785.1143188476562,
|
| 1138 |
+
"loss": 0.2456,
|
| 1139 |
+
"rewards/accuracies": 0.65625,
|
| 1140 |
+
"rewards/chosen": -0.3359334468841553,
|
| 1141 |
+
"rewards/margins": 0.15878985822200775,
|
| 1142 |
+
"rewards/rejected": -0.4947233200073242,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": 0.21103620529174805,
|
| 1149 |
+
"logits/rejected": 0.37812119722366333,
|
| 1150 |
+
"logps/chosen": -675.7420654296875,
|
| 1151 |
+
"logps/rejected": -835.7942504882812,
|
| 1152 |
+
"loss": 0.2342,
|
| 1153 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1154 |
+
"rewards/chosen": -0.3283590078353882,
|
| 1155 |
+
"rewards/margins": 0.1955871880054474,
|
| 1156 |
+
"rewards/rejected": -0.5239461660385132,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": 0.18820640444755554,
|
| 1163 |
+
"logits/rejected": 0.3453311324119568,
|
| 1164 |
+
"logps/chosen": -699.3671264648438,
|
| 1165 |
+
"logps/rejected": -808.0126342773438,
|
| 1166 |
+
"loss": 0.2185,
|
| 1167 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1168 |
+
"rewards/chosen": -0.32744988799095154,
|
| 1169 |
+
"rewards/margins": 0.19639787077903748,
|
| 1170 |
+
"rewards/rejected": -0.523847758769989,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": 0.1902572214603424,
|
| 1177 |
+
"logits/rejected": 0.3874988257884979,
|
| 1178 |
+
"logps/chosen": -704.2755737304688,
|
| 1179 |
+
"logps/rejected": -798.5086669921875,
|
| 1180 |
+
"loss": 0.2272,
|
| 1181 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1182 |
+
"rewards/chosen": -0.3353065848350525,
|
| 1183 |
+
"rewards/margins": 0.1846623420715332,
|
| 1184 |
+
"rewards/rejected": -0.5199689269065857,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": 0.2346924990415573,
|
| 1191 |
+
"logits/rejected": 0.35877925157546997,
|
| 1192 |
+
"logps/chosen": -631.2687377929688,
|
| 1193 |
+
"logps/rejected": -800.9693603515625,
|
| 1194 |
+
"loss": 0.2343,
|
| 1195 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1196 |
+
"rewards/chosen": -0.31699609756469727,
|
| 1197 |
+
"rewards/margins": 0.20049229264259338,
|
| 1198 |
+
"rewards/rejected": -0.517488420009613,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": 0.22632627189159393,
|
| 1205 |
+
"logits/rejected": 0.4042627811431885,
|
| 1206 |
+
"logps/chosen": -647.9192504882812,
|
| 1207 |
+
"logps/rejected": -805.1476440429688,
|
| 1208 |
+
"loss": 0.1767,
|
| 1209 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1210 |
+
"rewards/chosen": -0.29563456773757935,
|
| 1211 |
+
"rewards/margins": 0.23449036478996277,
|
| 1212 |
+
"rewards/rejected": -0.5301249623298645,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": 0.18376657366752625,
|
| 1219 |
+
"logits/rejected": 0.2582804560661316,
|
| 1220 |
+
"logps/chosen": -614.8178100585938,
|
| 1221 |
+
"logps/rejected": -754.7501220703125,
|
| 1222 |
+
"loss": 0.2084,
|
| 1223 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1224 |
+
"rewards/chosen": -0.27827420830726624,
|
| 1225 |
+
"rewards/margins": 0.21241740882396698,
|
| 1226 |
+
"rewards/rejected": -0.49069157242774963,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": 0.2309151142835617,
|
| 1233 |
+
"logits/rejected": 0.32766053080558777,
|
| 1234 |
+
"logps/chosen": -618.4566650390625,
|
| 1235 |
+
"logps/rejected": -769.9896850585938,
|
| 1236 |
+
"loss": 0.2188,
|
| 1237 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1238 |
+
"rewards/chosen": -0.2959611415863037,
|
| 1239 |
+
"rewards/margins": 0.19887039065361023,
|
| 1240 |
+
"rewards/rejected": -0.49483156204223633,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": 0.24140353500843048,
|
| 1247 |
+
"logits/rejected": 0.29053181409835815,
|
| 1248 |
+
"logps/chosen": -647.7692260742188,
|
| 1249 |
+
"logps/rejected": -806.162109375,
|
| 1250 |
+
"loss": 0.2179,
|
| 1251 |
+
"rewards/accuracies": 0.75,
|
| 1252 |
+
"rewards/chosen": -0.31588608026504517,
|
| 1253 |
+
"rewards/margins": 0.21005694568157196,
|
| 1254 |
+
"rewards/rejected": -0.5259430408477783,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": 0.21158334612846375,
|
| 1261 |
+
"logits/rejected": 0.31529536843299866,
|
| 1262 |
+
"logps/chosen": -656.6387939453125,
|
| 1263 |
+
"logps/rejected": -829.8762817382812,
|
| 1264 |
+
"loss": 0.2066,
|
| 1265 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1266 |
+
"rewards/chosen": -0.31754207611083984,
|
| 1267 |
+
"rewards/margins": 0.2269022911787033,
|
| 1268 |
+
"rewards/rejected": -0.5444443821907043,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": 0.18535788357257843,
|
| 1275 |
+
"logits/rejected": 0.3380703330039978,
|
| 1276 |
+
"logps/chosen": -669.4324340820312,
|
| 1277 |
+
"logps/rejected": -809.5096435546875,
|
| 1278 |
+
"loss": 0.2213,
|
| 1279 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1280 |
+
"rewards/chosen": -0.33157414197921753,
|
| 1281 |
+
"rewards/margins": 0.20540854334831238,
|
| 1282 |
+
"rewards/rejected": -0.5369827151298523,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": 0.21935626864433289,
|
| 1289 |
+
"logits/rejected": 0.3299446702003479,
|
| 1290 |
+
"logps/chosen": -643.43310546875,
|
| 1291 |
+
"logps/rejected": -753.556884765625,
|
| 1292 |
+
"loss": 0.2527,
|
| 1293 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1294 |
+
"rewards/chosen": -0.3096220791339874,
|
| 1295 |
+
"rewards/margins": 0.17697684466838837,
|
| 1296 |
+
"rewards/rejected": -0.4865988790988922,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": 0.20347245037555695,
|
| 1303 |
+
"logits/rejected": 0.37708914279937744,
|
| 1304 |
+
"logps/chosen": -650.4703979492188,
|
| 1305 |
+
"logps/rejected": -769.6436767578125,
|
| 1306 |
+
"loss": 0.2711,
|
| 1307 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1308 |
+
"rewards/chosen": -0.3225279450416565,
|
| 1309 |
+
"rewards/margins": 0.16174957156181335,
|
| 1310 |
+
"rewards/rejected": -0.48427754640579224,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": 0.22470831871032715,
|
| 1317 |
+
"logits/rejected": 0.3196450173854828,
|
| 1318 |
+
"logps/chosen": -647.2747192382812,
|
| 1319 |
+
"logps/rejected": -821.5018310546875,
|
| 1320 |
+
"loss": 0.2047,
|
| 1321 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1322 |
+
"rewards/chosen": -0.3270157277584076,
|
| 1323 |
+
"rewards/margins": 0.21042361855506897,
|
| 1324 |
+
"rewards/rejected": -0.5374393463134766,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.2409534176996449,
|
| 1332 |
+
"train_runtime": 8445.1148,
|
| 1333 |
+
"train_samples_per_second": 1.776,
|
| 1334 |
+
"train_steps_per_second": 0.111
|
| 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 |
+
}
|