Commit
•
7051ffb
1
Parent(s):
b572b6e
Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May11_17-21-22_gpu4-119-5/events.out.tfevents.1715412193.gpu4-119-5.850833.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1794 -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-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-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:feee75508094650bed5f2001b3c57e8b80b6b072fe814ad8685631f584e87a83
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.23378739290237427,
|
| 4 |
+
"train_runtime": 11502.4567,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 1.739,
|
| 7 |
+
"train_steps_per_second": 0.109
|
| 8 |
+
}
|
runs/May11_17-21-22_gpu4-119-5/events.out.tfevents.1715412193.gpu4-119-5.850833.0
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:f66181c562adacbeb4de671c970ad6f40f8e2a37bf73f817e29e01d18b6f7093
|
| 3 |
+
size 84962
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.23378739290237427,
|
| 4 |
+
"train_runtime": 11502.4567,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 1.739,
|
| 7 |
+
"train_steps_per_second": 0.109
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1794 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 4e-08,
|
| 14 |
+
"logits/chosen": 0.0844864472746849,
|
| 15 |
+
"logits/rejected": 0.33310458064079285,
|
| 16 |
+
"logps/chosen": -353.5397644042969,
|
| 17 |
+
"logps/rejected": -288.2696533203125,
|
| 18 |
+
"loss": 0.3643,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 28 |
+
"logits/chosen": 0.13158750534057617,
|
| 29 |
+
"logits/rejected": 0.30511173605918884,
|
| 30 |
+
"logps/chosen": -367.65313720703125,
|
| 31 |
+
"logps/rejected": -325.7276306152344,
|
| 32 |
+
"loss": 0.3313,
|
| 33 |
+
"rewards/accuracies": 0.4444444477558136,
|
| 34 |
+
"rewards/chosen": 8.732380229048431e-05,
|
| 35 |
+
"rewards/margins": 4.071068178745918e-05,
|
| 36 |
+
"rewards/rejected": 4.661310958908871e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 8.000000000000001e-07,
|
| 42 |
+
"logits/chosen": 0.05526388809084892,
|
| 43 |
+
"logits/rejected": 0.26700764894485474,
|
| 44 |
+
"logps/chosen": -373.4114685058594,
|
| 45 |
+
"logps/rejected": -284.48565673828125,
|
| 46 |
+
"loss": 0.3266,
|
| 47 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 48 |
+
"rewards/chosen": 1.75450313690817e-05,
|
| 49 |
+
"rewards/margins": -2.7303020033286884e-05,
|
| 50 |
+
"rewards/rejected": 4.484804958337918e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 56 |
+
"logits/chosen": 0.11817634105682373,
|
| 57 |
+
"logits/rejected": 0.26461678743362427,
|
| 58 |
+
"logps/chosen": -332.13763427734375,
|
| 59 |
+
"logps/rejected": -277.1170349121094,
|
| 60 |
+
"loss": 0.3326,
|
| 61 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 62 |
+
"rewards/chosen": 3.170762283843942e-05,
|
| 63 |
+
"rewards/margins": 0.00019424580386839807,
|
| 64 |
+
"rewards/rejected": -0.00016253818466793746,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 70 |
+
"logits/chosen": 0.13425800204277039,
|
| 71 |
+
"logits/rejected": 0.27743664383888245,
|
| 72 |
+
"logps/chosen": -360.2136535644531,
|
| 73 |
+
"logps/rejected": -288.0032043457031,
|
| 74 |
+
"loss": 0.3294,
|
| 75 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 76 |
+
"rewards/chosen": 0.00029172180802561343,
|
| 77 |
+
"rewards/margins": 0.0002648543450050056,
|
| 78 |
+
"rewards/rejected": 2.686746302060783e-05,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 84 |
+
"logits/chosen": 0.10267142951488495,
|
| 85 |
+
"logits/rejected": 0.2553173899650574,
|
| 86 |
+
"logps/chosen": -367.2956237792969,
|
| 87 |
+
"logps/rejected": -284.4521179199219,
|
| 88 |
+
"loss": 0.3632,
|
| 89 |
+
"rewards/accuracies": 0.59375,
|
| 90 |
+
"rewards/chosen": 0.00040079615428112447,
|
| 91 |
+
"rewards/margins": 0.00044054677709937096,
|
| 92 |
+
"rewards/rejected": -3.9750571886543185e-05,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 98 |
+
"logits/chosen": 0.10230157524347305,
|
| 99 |
+
"logits/rejected": 0.3024536967277527,
|
| 100 |
+
"logps/chosen": -380.87152099609375,
|
| 101 |
+
"logps/rejected": -280.0581970214844,
|
| 102 |
+
"loss": 0.3291,
|
| 103 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 104 |
+
"rewards/chosen": 0.001117692911066115,
|
| 105 |
+
"rewards/margins": 0.0011034052586182952,
|
| 106 |
+
"rewards/rejected": 1.4287617887021042e-05,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 112 |
+
"logits/chosen": 0.06087830662727356,
|
| 113 |
+
"logits/rejected": 0.2554122507572174,
|
| 114 |
+
"logps/chosen": -337.41510009765625,
|
| 115 |
+
"logps/rejected": -270.31951904296875,
|
| 116 |
+
"loss": 0.3419,
|
| 117 |
+
"rewards/accuracies": 0.675000011920929,
|
| 118 |
+
"rewards/chosen": 0.00204535317607224,
|
| 119 |
+
"rewards/margins": 0.0012875745305791497,
|
| 120 |
+
"rewards/rejected": 0.0007577788201160729,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06,
|
| 125 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 126 |
+
"logits/chosen": 0.13091996312141418,
|
| 127 |
+
"logits/rejected": 0.28141072392463684,
|
| 128 |
+
"logps/chosen": -298.9620056152344,
|
| 129 |
+
"logps/rejected": -288.3242492675781,
|
| 130 |
+
"loss": 0.3368,
|
| 131 |
+
"rewards/accuracies": 0.668749988079071,
|
| 132 |
+
"rewards/chosen": 0.0036297098267823458,
|
| 133 |
+
"rewards/margins": 0.0019692983478307724,
|
| 134 |
+
"rewards/rejected": 0.0016604112461209297,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 140 |
+
"logits/chosen": 0.10048405081033707,
|
| 141 |
+
"logits/rejected": 0.3519255816936493,
|
| 142 |
+
"logps/chosen": -341.4709777832031,
|
| 143 |
+
"logps/rejected": -273.7690734863281,
|
| 144 |
+
"loss": 0.3499,
|
| 145 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 146 |
+
"rewards/chosen": 0.005201340653002262,
|
| 147 |
+
"rewards/margins": 0.003749363124370575,
|
| 148 |
+
"rewards/rejected": 0.0014519785763695836,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08,
|
| 153 |
+
"learning_rate": 4.000000000000001e-06,
|
| 154 |
+
"logits/chosen": 0.1552368402481079,
|
| 155 |
+
"logits/rejected": 0.2774108052253723,
|
| 156 |
+
"logps/chosen": -379.28582763671875,
|
| 157 |
+
"logps/rejected": -269.00274658203125,
|
| 158 |
+
"loss": 0.3645,
|
| 159 |
+
"rewards/accuracies": 0.6875,
|
| 160 |
+
"rewards/chosen": 0.008240935392677784,
|
| 161 |
+
"rewards/margins": 0.005792171694338322,
|
| 162 |
+
"rewards/rejected": 0.0024487627670168877,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09,
|
| 167 |
+
"learning_rate": 4.4e-06,
|
| 168 |
+
"logits/chosen": 0.11597893387079239,
|
| 169 |
+
"logits/rejected": 0.27429717779159546,
|
| 170 |
+
"logps/chosen": -308.16546630859375,
|
| 171 |
+
"logps/rejected": -280.6103515625,
|
| 172 |
+
"loss": 0.3184,
|
| 173 |
+
"rewards/accuracies": 0.706250011920929,
|
| 174 |
+
"rewards/chosen": 0.012317601591348648,
|
| 175 |
+
"rewards/margins": 0.010150535963475704,
|
| 176 |
+
"rewards/rejected": 0.0021670644637197256,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 4.800000000000001e-06,
|
| 182 |
+
"logits/chosen": 0.12486454099416733,
|
| 183 |
+
"logits/rejected": 0.24381475150585175,
|
| 184 |
+
"logps/chosen": -331.5213928222656,
|
| 185 |
+
"logps/rejected": -280.4713439941406,
|
| 186 |
+
"loss": 0.3277,
|
| 187 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 188 |
+
"rewards/chosen": 0.014500940218567848,
|
| 189 |
+
"rewards/margins": 0.015465673990547657,
|
| 190 |
+
"rewards/rejected": -0.0009647362167015672,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1,
|
| 195 |
+
"learning_rate": 4.999756310023261e-06,
|
| 196 |
+
"logits/chosen": 0.15956248342990875,
|
| 197 |
+
"logits/rejected": 0.26742810010910034,
|
| 198 |
+
"logps/chosen": -335.33087158203125,
|
| 199 |
+
"logps/rejected": -297.67108154296875,
|
| 200 |
+
"loss": 0.3306,
|
| 201 |
+
"rewards/accuracies": 0.71875,
|
| 202 |
+
"rewards/chosen": 0.007238332182168961,
|
| 203 |
+
"rewards/margins": 0.022594567388296127,
|
| 204 |
+
"rewards/rejected": -0.01535623800009489,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.11,
|
| 209 |
+
"learning_rate": 4.997807075247147e-06,
|
| 210 |
+
"logits/chosen": 0.17396698892116547,
|
| 211 |
+
"logits/rejected": 0.23725232481956482,
|
| 212 |
+
"logps/chosen": -327.118896484375,
|
| 213 |
+
"logps/rejected": -327.3667907714844,
|
| 214 |
+
"loss": 0.2977,
|
| 215 |
+
"rewards/accuracies": 0.675000011920929,
|
| 216 |
+
"rewards/chosen": -0.013849464245140553,
|
| 217 |
+
"rewards/margins": 0.03406212851405144,
|
| 218 |
+
"rewards/rejected": -0.047911591827869415,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 4.993910125649561e-06,
|
| 224 |
+
"logits/chosen": 0.12554484605789185,
|
| 225 |
+
"logits/rejected": 0.29098716378211975,
|
| 226 |
+
"logps/chosen": -424.14111328125,
|
| 227 |
+
"logps/rejected": -483.7743225097656,
|
| 228 |
+
"loss": 0.2796,
|
| 229 |
+
"rewards/accuracies": 0.762499988079071,
|
| 230 |
+
"rewards/chosen": -0.09817798435688019,
|
| 231 |
+
"rewards/margins": 0.09961286187171936,
|
| 232 |
+
"rewards/rejected": -0.19779083132743835,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13,
|
| 237 |
+
"learning_rate": 4.988068499954578e-06,
|
| 238 |
+
"logits/chosen": 0.13350623846054077,
|
| 239 |
+
"logits/rejected": 0.2567678689956665,
|
| 240 |
+
"logps/chosen": -515.5465087890625,
|
| 241 |
+
"logps/rejected": -636.443115234375,
|
| 242 |
+
"loss": 0.2543,
|
| 243 |
+
"rewards/accuracies": 0.668749988079071,
|
| 244 |
+
"rewards/chosen": -0.22427871823310852,
|
| 245 |
+
"rewards/margins": 0.14295950531959534,
|
| 246 |
+
"rewards/rejected": -0.36723819375038147,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"learning_rate": 4.980286753286196e-06,
|
| 252 |
+
"logits/chosen": 0.16326992213726044,
|
| 253 |
+
"logits/rejected": 0.3378574252128601,
|
| 254 |
+
"logps/chosen": -609.2169189453125,
|
| 255 |
+
"logps/rejected": -717.1610107421875,
|
| 256 |
+
"loss": 0.2543,
|
| 257 |
+
"rewards/accuracies": 0.768750011920929,
|
| 258 |
+
"rewards/chosen": -0.253111332654953,
|
| 259 |
+
"rewards/margins": 0.16249707341194153,
|
| 260 |
+
"rewards/rejected": -0.41560840606689453,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14,
|
| 265 |
+
"learning_rate": 4.970570953616383e-06,
|
| 266 |
+
"logits/chosen": 0.2185734510421753,
|
| 267 |
+
"logits/rejected": 0.33415085077285767,
|
| 268 |
+
"logps/chosen": -549.37841796875,
|
| 269 |
+
"logps/rejected": -652.755126953125,
|
| 270 |
+
"loss": 0.2807,
|
| 271 |
+
"rewards/accuracies": 0.731249988079071,
|
| 272 |
+
"rewards/chosen": -0.20153920352458954,
|
| 273 |
+
"rewards/margins": 0.16085070371627808,
|
| 274 |
+
"rewards/rejected": -0.3623898923397064,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15,
|
| 279 |
+
"learning_rate": 4.958928677033465e-06,
|
| 280 |
+
"logits/chosen": 0.18986164033412933,
|
| 281 |
+
"logits/rejected": 0.27733010053634644,
|
| 282 |
+
"logps/chosen": -517.0262451171875,
|
| 283 |
+
"logps/rejected": -574.3702392578125,
|
| 284 |
+
"loss": 0.2593,
|
| 285 |
+
"rewards/accuracies": 0.6875,
|
| 286 |
+
"rewards/chosen": -0.17016564309597015,
|
| 287 |
+
"rewards/margins": 0.12780186533927917,
|
| 288 |
+
"rewards/rejected": -0.2979675233364105,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16,
|
| 293 |
+
"learning_rate": 4.9453690018345144e-06,
|
| 294 |
+
"logits/chosen": 0.16576513648033142,
|
| 295 |
+
"logits/rejected": 0.2792220711708069,
|
| 296 |
+
"logps/chosen": -486.26055908203125,
|
| 297 |
+
"logps/rejected": -568.0484619140625,
|
| 298 |
+
"loss": 0.2607,
|
| 299 |
+
"rewards/accuracies": 0.75,
|
| 300 |
+
"rewards/chosen": -0.14735093712806702,
|
| 301 |
+
"rewards/margins": 0.1370319128036499,
|
| 302 |
+
"rewards/rejected": -0.2843828499317169,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 4.9299025014463665e-06,
|
| 308 |
+
"logits/chosen": 0.2451048195362091,
|
| 309 |
+
"logits/rejected": 0.3201284408569336,
|
| 310 |
+
"logps/chosen": -545.4906616210938,
|
| 311 |
+
"logps/rejected": -641.3413696289062,
|
| 312 |
+
"loss": 0.2498,
|
| 313 |
+
"rewards/accuracies": 0.71875,
|
| 314 |
+
"rewards/chosen": -0.20472323894500732,
|
| 315 |
+
"rewards/margins": 0.1518576443195343,
|
| 316 |
+
"rewards/rejected": -0.3565808832645416,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"learning_rate": 4.912541236180779e-06,
|
| 322 |
+
"logits/chosen": 0.24414494633674622,
|
| 323 |
+
"logits/rejected": 0.34964054822921753,
|
| 324 |
+
"logps/chosen": -543.0393676757812,
|
| 325 |
+
"logps/rejected": -640.4935302734375,
|
| 326 |
+
"loss": 0.2441,
|
| 327 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 328 |
+
"rewards/chosen": -0.2151704579591751,
|
| 329 |
+
"rewards/margins": 0.14475873112678528,
|
| 330 |
+
"rewards/rejected": -0.35992923378944397,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.18,
|
| 335 |
+
"learning_rate": 4.893298743830168e-06,
|
| 336 |
+
"logits/chosen": 0.21800033748149872,
|
| 337 |
+
"logits/rejected": 0.3654104471206665,
|
| 338 |
+
"logps/chosen": -565.3587646484375,
|
| 339 |
+
"logps/rejected": -664.7565307617188,
|
| 340 |
+
"loss": 0.263,
|
| 341 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 342 |
+
"rewards/chosen": -0.2173396795988083,
|
| 343 |
+
"rewards/margins": 0.14265912771224976,
|
| 344 |
+
"rewards/rejected": -0.35999882221221924,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.19,
|
| 349 |
+
"learning_rate": 4.8721900291112415e-06,
|
| 350 |
+
"logits/chosen": 0.23501598834991455,
|
| 351 |
+
"logits/rejected": 0.3829185962677002,
|
| 352 |
+
"logps/chosen": -552.0388793945312,
|
| 353 |
+
"logps/rejected": -684.6451416015625,
|
| 354 |
+
"loss": 0.2185,
|
| 355 |
+
"rewards/accuracies": 0.78125,
|
| 356 |
+
"rewards/chosen": -0.21107693016529083,
|
| 357 |
+
"rewards/margins": 0.17598167061805725,
|
| 358 |
+
"rewards/rejected": -0.3870585560798645,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2,
|
| 363 |
+
"learning_rate": 4.849231551964771e-06,
|
| 364 |
+
"logits/chosen": 0.19817332923412323,
|
| 365 |
+
"logits/rejected": 0.405841588973999,
|
| 366 |
+
"logps/chosen": -584.6502685546875,
|
| 367 |
+
"logps/rejected": -727.7828369140625,
|
| 368 |
+
"loss": 0.2008,
|
| 369 |
+
"rewards/accuracies": 0.71875,
|
| 370 |
+
"rewards/chosen": -0.24216294288635254,
|
| 371 |
+
"rewards/margins": 0.19921335577964783,
|
| 372 |
+
"rewards/rejected": -0.44137629866600037,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21,
|
| 377 |
+
"learning_rate": 4.824441214720629e-06,
|
| 378 |
+
"logits/chosen": 0.25659921765327454,
|
| 379 |
+
"logits/rejected": 0.5147486925125122,
|
| 380 |
+
"logps/chosen": -669.7100830078125,
|
| 381 |
+
"logps/rejected": -784.080078125,
|
| 382 |
+
"loss": 0.2293,
|
| 383 |
+
"rewards/accuracies": 0.699999988079071,
|
| 384 |
+
"rewards/chosen": -0.305190771818161,
|
| 385 |
+
"rewards/margins": 0.198633074760437,
|
| 386 |
+
"rewards/rejected": -0.5038238763809204,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 4.7978383481380865e-06,
|
| 392 |
+
"logits/chosen": 0.25666308403015137,
|
| 393 |
+
"logits/rejected": 0.39037442207336426,
|
| 394 |
+
"logps/chosen": -600.1813354492188,
|
| 395 |
+
"logps/rejected": -742.1792602539062,
|
| 396 |
+
"loss": 0.2295,
|
| 397 |
+
"rewards/accuracies": 0.78125,
|
| 398 |
+
"rewards/chosen": -0.22432246804237366,
|
| 399 |
+
"rewards/margins": 0.22660879790782928,
|
| 400 |
+
"rewards/rejected": -0.45093125104904175,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.22,
|
| 405 |
+
"learning_rate": 4.769443696332272e-06,
|
| 406 |
+
"logits/chosen": 0.1597982496023178,
|
| 407 |
+
"logits/rejected": 0.4019368588924408,
|
| 408 |
+
"logps/chosen": -622.7044677734375,
|
| 409 |
+
"logps/rejected": -739.5430908203125,
|
| 410 |
+
"loss": 0.1935,
|
| 411 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 412 |
+
"rewards/chosen": -0.260140985250473,
|
| 413 |
+
"rewards/margins": 0.20764973759651184,
|
| 414 |
+
"rewards/rejected": -0.4677906930446625,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.23,
|
| 419 |
+
"learning_rate": 4.7392794005985324e-06,
|
| 420 |
+
"logits/chosen": 0.17551542818546295,
|
| 421 |
+
"logits/rejected": 0.299673855304718,
|
| 422 |
+
"logps/chosen": -612.8324584960938,
|
| 423 |
+
"logps/rejected": -739.7828369140625,
|
| 424 |
+
"loss": 0.2569,
|
| 425 |
+
"rewards/accuracies": 0.737500011920929,
|
| 426 |
+
"rewards/chosen": -0.2785190939903259,
|
| 427 |
+
"rewards/margins": 0.1762886345386505,
|
| 428 |
+
"rewards/rejected": -0.45480766892433167,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24,
|
| 433 |
+
"learning_rate": 4.707368982147318e-06,
|
| 434 |
+
"logits/chosen": 0.16563180088996887,
|
| 435 |
+
"logits/rejected": 0.3696051239967346,
|
| 436 |
+
"logps/chosen": -628.3892211914062,
|
| 437 |
+
"logps/rejected": -711.805908203125,
|
| 438 |
+
"loss": 0.2439,
|
| 439 |
+
"rewards/accuracies": 0.699999988079071,
|
| 440 |
+
"rewards/chosen": -0.26610690355300903,
|
| 441 |
+
"rewards/margins": 0.16744135320186615,
|
| 442 |
+
"rewards/rejected": -0.4335482716560364,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.25,
|
| 447 |
+
"learning_rate": 4.673737323763048e-06,
|
| 448 |
+
"logits/chosen": 0.154313862323761,
|
| 449 |
+
"logits/rejected": 0.2695145905017853,
|
| 450 |
+
"logps/chosen": -626.7857055664062,
|
| 451 |
+
"logps/rejected": -733.1358642578125,
|
| 452 |
+
"loss": 0.2429,
|
| 453 |
+
"rewards/accuracies": 0.699999988079071,
|
| 454 |
+
"rewards/chosen": -0.3073986768722534,
|
| 455 |
+
"rewards/margins": 0.14215336740016937,
|
| 456 |
+
"rewards/rejected": -0.4495519995689392,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.26,
|
| 461 |
+
"learning_rate": 4.638410650401267e-06,
|
| 462 |
+
"logits/chosen": 0.17420662939548492,
|
| 463 |
+
"logits/rejected": 0.2810192406177521,
|
| 464 |
+
"logps/chosen": -659.523193359375,
|
| 465 |
+
"logps/rejected": -739.6040649414062,
|
| 466 |
+
"loss": 0.2339,
|
| 467 |
+
"rewards/accuracies": 0.706250011920929,
|
| 468 |
+
"rewards/chosen": -0.2910728454589844,
|
| 469 |
+
"rewards/margins": 0.16638004779815674,
|
| 470 |
+
"rewards/rejected": -0.4574528634548187,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.26,
|
| 475 |
+
"learning_rate": 4.601416508739211e-06,
|
| 476 |
+
"logits/chosen": 0.12969666719436646,
|
| 477 |
+
"logits/rejected": 0.27314314246177673,
|
| 478 |
+
"logps/chosen": -605.5972290039062,
|
| 479 |
+
"logps/rejected": -687.2078857421875,
|
| 480 |
+
"loss": 0.2538,
|
| 481 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 482 |
+
"rewards/chosen": -0.25853052735328674,
|
| 483 |
+
"rewards/margins": 0.15462937951087952,
|
| 484 |
+
"rewards/rejected": -0.41315993666648865,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.27,
|
| 489 |
+
"learning_rate": 4.562783745695738e-06,
|
| 490 |
+
"logits/chosen": 0.17410126328468323,
|
| 491 |
+
"logits/rejected": 0.3125883936882019,
|
| 492 |
+
"logps/chosen": -633.088134765625,
|
| 493 |
+
"logps/rejected": -710.6566162109375,
|
| 494 |
+
"loss": 0.2351,
|
| 495 |
+
"rewards/accuracies": 0.71875,
|
| 496 |
+
"rewards/chosen": -0.26320981979370117,
|
| 497 |
+
"rewards/margins": 0.17223307490348816,
|
| 498 |
+
"rewards/rejected": -0.4354429244995117,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.28,
|
| 503 |
+
"learning_rate": 4.522542485937369e-06,
|
| 504 |
+
"logits/chosen": 0.19418665766716003,
|
| 505 |
+
"logits/rejected": 0.32736459374427795,
|
| 506 |
+
"logps/chosen": -600.09521484375,
|
| 507 |
+
"logps/rejected": -744.0341796875,
|
| 508 |
+
"loss": 0.2474,
|
| 509 |
+
"rewards/accuracies": 0.71875,
|
| 510 |
+
"rewards/chosen": -0.2684987485408783,
|
| 511 |
+
"rewards/margins": 0.19482778012752533,
|
| 512 |
+
"rewards/rejected": -0.4633265435695648,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.29,
|
| 517 |
+
"learning_rate": 4.4807241083879774e-06,
|
| 518 |
+
"logits/chosen": 0.17102095484733582,
|
| 519 |
+
"logits/rejected": 0.3697226047515869,
|
| 520 |
+
"logps/chosen": -643.48388671875,
|
| 521 |
+
"logps/rejected": -785.5322265625,
|
| 522 |
+
"loss": 0.2028,
|
| 523 |
+
"rewards/accuracies": 0.78125,
|
| 524 |
+
"rewards/chosen": -0.2777577042579651,
|
| 525 |
+
"rewards/margins": 0.21700581908226013,
|
| 526 |
+
"rewards/rejected": -0.4947635531425476,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3,
|
| 531 |
+
"learning_rate": 4.437361221760449e-06,
|
| 532 |
+
"logits/chosen": 0.16235628724098206,
|
| 533 |
+
"logits/rejected": 0.3275222182273865,
|
| 534 |
+
"logps/chosen": -632.9365234375,
|
| 535 |
+
"logps/rejected": -711.3013916015625,
|
| 536 |
+
"loss": 0.2672,
|
| 537 |
+
"rewards/accuracies": 0.71875,
|
| 538 |
+
"rewards/chosen": -0.2944018244743347,
|
| 539 |
+
"rewards/margins": 0.14519986510276794,
|
| 540 |
+
"rewards/rejected": -0.43960171937942505,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3,
|
| 545 |
+
"learning_rate": 4.3924876391293915e-06,
|
| 546 |
+
"logits/chosen": 0.16521404683589935,
|
| 547 |
+
"logits/rejected": 0.2474815845489502,
|
| 548 |
+
"logps/chosen": -574.040283203125,
|
| 549 |
+
"logps/rejected": -666.442626953125,
|
| 550 |
+
"loss": 0.2099,
|
| 551 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 552 |
+
"rewards/chosen": -0.20964479446411133,
|
| 553 |
+
"rewards/margins": 0.17186279594898224,
|
| 554 |
+
"rewards/rejected": -0.3815075755119324,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.31,
|
| 559 |
+
"learning_rate": 4.346138351564711e-06,
|
| 560 |
+
"logits/chosen": 0.22545070946216583,
|
| 561 |
+
"logits/rejected": 0.3371376395225525,
|
| 562 |
+
"logps/chosen": -628.6351928710938,
|
| 563 |
+
"logps/rejected": -679.3721313476562,
|
| 564 |
+
"loss": 0.2481,
|
| 565 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 566 |
+
"rewards/chosen": -0.23831382393836975,
|
| 567 |
+
"rewards/margins": 0.1526465266942978,
|
| 568 |
+
"rewards/rejected": -0.39096030592918396,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.32,
|
| 573 |
+
"learning_rate": 4.2983495008466285e-06,
|
| 574 |
+
"logits/chosen": 0.19101233780384064,
|
| 575 |
+
"logits/rejected": 0.28732946515083313,
|
| 576 |
+
"logps/chosen": -540.628173828125,
|
| 577 |
+
"logps/rejected": -661.4655151367188,
|
| 578 |
+
"loss": 0.2303,
|
| 579 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 580 |
+
"rewards/chosen": -0.23400673270225525,
|
| 581 |
+
"rewards/margins": 0.1693030148744583,
|
| 582 |
+
"rewards/rejected": -0.40330973267555237,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.33,
|
| 587 |
+
"learning_rate": 4.249158351283414e-06,
|
| 588 |
+
"logits/chosen": 0.18795284628868103,
|
| 589 |
+
"logits/rejected": 0.34203091263771057,
|
| 590 |
+
"logps/chosen": -611.86181640625,
|
| 591 |
+
"logps/rejected": -750.4905395507812,
|
| 592 |
+
"loss": 0.2459,
|
| 593 |
+
"rewards/accuracies": 0.75,
|
| 594 |
+
"rewards/chosen": -0.2899382412433624,
|
| 595 |
+
"rewards/margins": 0.18975083529949188,
|
| 596 |
+
"rewards/rejected": -0.4796890616416931,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34,
|
| 601 |
+
"learning_rate": 4.198603260653792e-06,
|
| 602 |
+
"logits/chosen": 0.20498259365558624,
|
| 603 |
+
"logits/rejected": 0.361739844083786,
|
| 604 |
+
"logps/chosen": -652.5081787109375,
|
| 605 |
+
"logps/rejected": -800.6769409179688,
|
| 606 |
+
"loss": 0.2531,
|
| 607 |
+
"rewards/accuracies": 0.75,
|
| 608 |
+
"rewards/chosen": -0.31163305044174194,
|
| 609 |
+
"rewards/margins": 0.21305236220359802,
|
| 610 |
+
"rewards/rejected": -0.5246853828430176,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.34,
|
| 615 |
+
"learning_rate": 4.146723650296701e-06,
|
| 616 |
+
"logits/chosen": 0.15172120928764343,
|
| 617 |
+
"logits/rejected": 0.29123345017433167,
|
| 618 |
+
"logps/chosen": -632.1334228515625,
|
| 619 |
+
"logps/rejected": -758.0350952148438,
|
| 620 |
+
"loss": 0.2519,
|
| 621 |
+
"rewards/accuracies": 0.706250011920929,
|
| 622 |
+
"rewards/chosen": -0.3022623658180237,
|
| 623 |
+
"rewards/margins": 0.19012293219566345,
|
| 624 |
+
"rewards/rejected": -0.49238529801368713,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.35,
|
| 629 |
+
"learning_rate": 4.093559974371725e-06,
|
| 630 |
+
"logits/chosen": 0.14015085995197296,
|
| 631 |
+
"logits/rejected": 0.2808334529399872,
|
| 632 |
+
"logps/chosen": -616.999267578125,
|
| 633 |
+
"logps/rejected": -718.7491455078125,
|
| 634 |
+
"loss": 0.2204,
|
| 635 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 636 |
+
"rewards/chosen": -0.2764546275138855,
|
| 637 |
+
"rewards/margins": 0.15102453529834747,
|
| 638 |
+
"rewards/rejected": -0.42747917771339417,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.36,
|
| 643 |
+
"learning_rate": 4.039153688314146e-06,
|
| 644 |
+
"logits/chosen": 0.18793924152851105,
|
| 645 |
+
"logits/rejected": 0.32496175169944763,
|
| 646 |
+
"logps/chosen": -640.4262084960938,
|
| 647 |
+
"logps/rejected": -751.7564697265625,
|
| 648 |
+
"loss": 0.2309,
|
| 649 |
+
"rewards/accuracies": 0.737500011920929,
|
| 650 |
+
"rewards/chosen": -0.28454405069351196,
|
| 651 |
+
"rewards/margins": 0.17815975844860077,
|
| 652 |
+
"rewards/rejected": -0.46270379424095154,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.37,
|
| 657 |
+
"learning_rate": 3.983547216509254e-06,
|
| 658 |
+
"logits/chosen": 0.18021197617053986,
|
| 659 |
+
"logits/rejected": 0.38667747378349304,
|
| 660 |
+
"logps/chosen": -659.7672729492188,
|
| 661 |
+
"logps/rejected": -808.3829956054688,
|
| 662 |
+
"loss": 0.1852,
|
| 663 |
+
"rewards/accuracies": 0.8125,
|
| 664 |
+
"rewards/chosen": -0.29309019446372986,
|
| 665 |
+
"rewards/margins": 0.21565881371498108,
|
| 666 |
+
"rewards/rejected": -0.5087490081787109,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38,
|
| 671 |
+
"learning_rate": 3.92678391921108e-06,
|
| 672 |
+
"logits/chosen": 0.2365349531173706,
|
| 673 |
+
"logits/rejected": 0.42279887199401855,
|
| 674 |
+
"logps/chosen": -671.0607299804688,
|
| 675 |
+
"logps/rejected": -815.6022338867188,
|
| 676 |
+
"loss": 0.1932,
|
| 677 |
+
"rewards/accuracies": 0.737500011920929,
|
| 678 |
+
"rewards/chosen": -0.32014933228492737,
|
| 679 |
+
"rewards/margins": 0.22637374699115753,
|
| 680 |
+
"rewards/rejected": -0.5465230345726013,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.38,
|
| 685 |
+
"learning_rate": 3.868908058731376e-06,
|
| 686 |
+
"logits/chosen": 0.19958177208900452,
|
| 687 |
+
"logits/rejected": 0.3300831913948059,
|
| 688 |
+
"logps/chosen": -628.7908935546875,
|
| 689 |
+
"logps/rejected": -836.0079345703125,
|
| 690 |
+
"loss": 0.1918,
|
| 691 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 692 |
+
"rewards/chosen": -0.3073442578315735,
|
| 693 |
+
"rewards/margins": 0.248644158244133,
|
| 694 |
+
"rewards/rejected": -0.5559884309768677,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.39,
|
| 699 |
+
"learning_rate": 3.8099647649251984e-06,
|
| 700 |
+
"logits/chosen": 0.24684026837348938,
|
| 701 |
+
"logits/rejected": 0.40296274423599243,
|
| 702 |
+
"logps/chosen": -703.308837890625,
|
| 703 |
+
"logps/rejected": -823.93115234375,
|
| 704 |
+
"loss": 0.2178,
|
| 705 |
+
"rewards/accuracies": 0.75,
|
| 706 |
+
"rewards/chosen": -0.35310739278793335,
|
| 707 |
+
"rewards/margins": 0.19319894909858704,
|
| 708 |
+
"rewards/rejected": -0.5463063716888428,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4,
|
| 713 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 714 |
+
"logits/chosen": 0.23402579128742218,
|
| 715 |
+
"logits/rejected": 0.3793715238571167,
|
| 716 |
+
"logps/chosen": -686.2119140625,
|
| 717 |
+
"logps/rejected": -793.6251220703125,
|
| 718 |
+
"loss": 0.2244,
|
| 719 |
+
"rewards/accuracies": 0.762499988079071,
|
| 720 |
+
"rewards/chosen": -0.3346458077430725,
|
| 721 |
+
"rewards/margins": 0.20509561896324158,
|
| 722 |
+
"rewards/rejected": -0.5397413969039917,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.41,
|
| 727 |
+
"learning_rate": 3.689060522675689e-06,
|
| 728 |
+
"logits/chosen": 0.22621877491474152,
|
| 729 |
+
"logits/rejected": 0.3817893862724304,
|
| 730 |
+
"logps/chosen": -635.5712890625,
|
| 731 |
+
"logps/rejected": -857.2591552734375,
|
| 732 |
+
"loss": 0.1884,
|
| 733 |
+
"rewards/accuracies": 0.768750011920929,
|
| 734 |
+
"rewards/chosen": -0.3070182800292969,
|
| 735 |
+
"rewards/margins": 0.2568911015987396,
|
| 736 |
+
"rewards/rejected": -0.5639094114303589,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.42,
|
| 741 |
+
"learning_rate": 3.627193851723577e-06,
|
| 742 |
+
"logits/chosen": 0.27324920892715454,
|
| 743 |
+
"logits/rejected": 0.33206120133399963,
|
| 744 |
+
"logps/chosen": -610.9793701171875,
|
| 745 |
+
"logps/rejected": -760.0927124023438,
|
| 746 |
+
"loss": 0.2509,
|
| 747 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 748 |
+
"rewards/chosen": -0.29021549224853516,
|
| 749 |
+
"rewards/margins": 0.19801415503025055,
|
| 750 |
+
"rewards/rejected": -0.4882296621799469,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.42,
|
| 755 |
+
"learning_rate": 3.564448228912682e-06,
|
| 756 |
+
"logits/chosen": 0.21176056563854218,
|
| 757 |
+
"logits/rejected": 0.3238454759120941,
|
| 758 |
+
"logps/chosen": -701.1263427734375,
|
| 759 |
+
"logps/rejected": -854.8087158203125,
|
| 760 |
+
"loss": 0.2231,
|
| 761 |
+
"rewards/accuracies": 0.768750011920929,
|
| 762 |
+
"rewards/chosen": -0.335193008184433,
|
| 763 |
+
"rewards/margins": 0.2088688313961029,
|
| 764 |
+
"rewards/rejected": -0.5440617799758911,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.43,
|
| 769 |
+
"learning_rate": 3.5008725813922383e-06,
|
| 770 |
+
"logits/chosen": 0.16880548000335693,
|
| 771 |
+
"logits/rejected": 0.3071228861808777,
|
| 772 |
+
"logps/chosen": -649.8262939453125,
|
| 773 |
+
"logps/rejected": -850.3421630859375,
|
| 774 |
+
"loss": 0.2157,
|
| 775 |
+
"rewards/accuracies": 0.75,
|
| 776 |
+
"rewards/chosen": -0.32233431935310364,
|
| 777 |
+
"rewards/margins": 0.23912398517131805,
|
| 778 |
+
"rewards/rejected": -0.5614583492279053,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.44,
|
| 783 |
+
"learning_rate": 3.436516483539781e-06,
|
| 784 |
+
"logits/chosen": 0.19489061832427979,
|
| 785 |
+
"logits/rejected": 0.3110398054122925,
|
| 786 |
+
"logps/chosen": -714.0751953125,
|
| 787 |
+
"logps/rejected": -858.6014404296875,
|
| 788 |
+
"loss": 0.2142,
|
| 789 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 790 |
+
"rewards/chosen": -0.3476428985595703,
|
| 791 |
+
"rewards/margins": 0.22875848412513733,
|
| 792 |
+
"rewards/rejected": -0.5764013528823853,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.45,
|
| 797 |
+
"learning_rate": 3.3714301183045382e-06,
|
| 798 |
+
"logits/chosen": 0.24650970101356506,
|
| 799 |
+
"logits/rejected": 0.32072556018829346,
|
| 800 |
+
"logps/chosen": -695.4619140625,
|
| 801 |
+
"logps/rejected": -859.4768676757812,
|
| 802 |
+
"loss": 0.2535,
|
| 803 |
+
"rewards/accuracies": 0.71875,
|
| 804 |
+
"rewards/chosen": -0.3652021288871765,
|
| 805 |
+
"rewards/margins": 0.19063223898410797,
|
| 806 |
+
"rewards/rejected": -0.5558344125747681,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.46,
|
| 811 |
+
"learning_rate": 3.3056642380762783e-06,
|
| 812 |
+
"logits/chosen": 0.18784189224243164,
|
| 813 |
+
"logits/rejected": 0.2975664734840393,
|
| 814 |
+
"logps/chosen": -696.1307373046875,
|
| 815 |
+
"logps/rejected": -840.21533203125,
|
| 816 |
+
"loss": 0.188,
|
| 817 |
+
"rewards/accuracies": 0.78125,
|
| 818 |
+
"rewards/chosen": -0.3386804461479187,
|
| 819 |
+
"rewards/margins": 0.21644003689289093,
|
| 820 |
+
"rewards/rejected": -0.5551204085350037,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.46,
|
| 825 |
+
"learning_rate": 3.2392701251101172e-06,
|
| 826 |
+
"logits/chosen": 0.14956721663475037,
|
| 827 |
+
"logits/rejected": 0.3091835081577301,
|
| 828 |
+
"logps/chosen": -672.9777221679688,
|
| 829 |
+
"logps/rejected": -797.7686767578125,
|
| 830 |
+
"loss": 0.2119,
|
| 831 |
+
"rewards/accuracies": 0.75,
|
| 832 |
+
"rewards/chosen": -0.3007811903953552,
|
| 833 |
+
"rewards/margins": 0.22610263526439667,
|
| 834 |
+
"rewards/rejected": -0.5268837809562683,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.47,
|
| 839 |
+
"learning_rate": 3.1722995515381644e-06,
|
| 840 |
+
"logits/chosen": 0.16815881431102753,
|
| 841 |
+
"logits/rejected": 0.29664796590805054,
|
| 842 |
+
"logps/chosen": -731.1002807617188,
|
| 843 |
+
"logps/rejected": -859.3917236328125,
|
| 844 |
+
"loss": 0.2439,
|
| 845 |
+
"rewards/accuracies": 0.737500011920929,
|
| 846 |
+
"rewards/chosen": -0.3603288531303406,
|
| 847 |
+
"rewards/margins": 0.2046092301607132,
|
| 848 |
+
"rewards/rejected": -0.5649380683898926,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.48,
|
| 853 |
+
"learning_rate": 3.1048047389991693e-06,
|
| 854 |
+
"logits/chosen": 0.1886782944202423,
|
| 855 |
+
"logits/rejected": 0.28089115023612976,
|
| 856 |
+
"logps/chosen": -742.2792358398438,
|
| 857 |
+
"logps/rejected": -894.4122924804688,
|
| 858 |
+
"loss": 0.2057,
|
| 859 |
+
"rewards/accuracies": 0.768750011920929,
|
| 860 |
+
"rewards/chosen": -0.3729311227798462,
|
| 861 |
+
"rewards/margins": 0.23213550448417664,
|
| 862 |
+
"rewards/rejected": -0.6050665974617004,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.49,
|
| 867 |
+
"learning_rate": 3.0368383179176584e-06,
|
| 868 |
+
"logits/chosen": 0.17394626140594482,
|
| 869 |
+
"logits/rejected": 0.2982519865036011,
|
| 870 |
+
"logps/chosen": -674.7700805664062,
|
| 871 |
+
"logps/rejected": -813.771728515625,
|
| 872 |
+
"loss": 0.2239,
|
| 873 |
+
"rewards/accuracies": 0.762499988079071,
|
| 874 |
+
"rewards/chosen": -0.34023207426071167,
|
| 875 |
+
"rewards/margins": 0.1940125972032547,
|
| 876 |
+
"rewards/rejected": -0.5342446565628052,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5,
|
| 881 |
+
"learning_rate": 2.9684532864643123e-06,
|
| 882 |
+
"logits/chosen": 0.18182912468910217,
|
| 883 |
+
"logits/rejected": 0.24953170120716095,
|
| 884 |
+
"logps/chosen": -655.6112060546875,
|
| 885 |
+
"logps/rejected": -810.8953247070312,
|
| 886 |
+
"loss": 0.2287,
|
| 887 |
+
"rewards/accuracies": 0.75,
|
| 888 |
+
"rewards/chosen": -0.31626206636428833,
|
| 889 |
+
"rewards/margins": 0.1988387405872345,
|
| 890 |
+
"rewards/rejected": -0.5151007771492004,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5,
|
| 895 |
+
"learning_rate": 2.8997029692295875e-06,
|
| 896 |
+
"logits/chosen": 0.15592697262763977,
|
| 897 |
+
"logits/rejected": 0.28623780608177185,
|
| 898 |
+
"logps/chosen": -652.3097534179688,
|
| 899 |
+
"logps/rejected": -798.4329833984375,
|
| 900 |
+
"loss": 0.1837,
|
| 901 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 902 |
+
"rewards/chosen": -0.30768585205078125,
|
| 903 |
+
"rewards/margins": 0.20968368649482727,
|
| 904 |
+
"rewards/rejected": -0.5173695683479309,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.51,
|
| 909 |
+
"learning_rate": 2.8306409756428067e-06,
|
| 910 |
+
"logits/chosen": 0.17375251650810242,
|
| 911 |
+
"logits/rejected": 0.3520289361476898,
|
| 912 |
+
"logps/chosen": -688.189697265625,
|
| 913 |
+
"logps/rejected": -851.2540283203125,
|
| 914 |
+
"loss": 0.2075,
|
| 915 |
+
"rewards/accuracies": 0.737500011920929,
|
| 916 |
+
"rewards/chosen": -0.34062907099723816,
|
| 917 |
+
"rewards/margins": 0.21998348832130432,
|
| 918 |
+
"rewards/rejected": -0.5606126189231873,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.52,
|
| 923 |
+
"learning_rate": 2.761321158169134e-06,
|
| 924 |
+
"logits/chosen": 0.18335016071796417,
|
| 925 |
+
"logits/rejected": 0.35726577043533325,
|
| 926 |
+
"logps/chosen": -694.2769775390625,
|
| 927 |
+
"logps/rejected": -852.6566162109375,
|
| 928 |
+
"loss": 0.2004,
|
| 929 |
+
"rewards/accuracies": 0.768750011920929,
|
| 930 |
+
"rewards/chosen": -0.3523062467575073,
|
| 931 |
+
"rewards/margins": 0.22832950949668884,
|
| 932 |
+
"rewards/rejected": -0.5806357860565186,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.53,
|
| 937 |
+
"learning_rate": 2.6917975703170466e-06,
|
| 938 |
+
"logits/chosen": 0.1765713393688202,
|
| 939 |
+
"logits/rejected": 0.3084057867527008,
|
| 940 |
+
"logps/chosen": -696.19921875,
|
| 941 |
+
"logps/rejected": -840.1595458984375,
|
| 942 |
+
"loss": 0.2349,
|
| 943 |
+
"rewards/accuracies": 0.706250011920929,
|
| 944 |
+
"rewards/chosen": -0.3651433289051056,
|
| 945 |
+
"rewards/margins": 0.20626911520957947,
|
| 946 |
+
"rewards/rejected": -0.5714124441146851,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.54,
|
| 951 |
+
"learning_rate": 2.6221244244890336e-06,
|
| 952 |
+
"logits/chosen": 0.17487014830112457,
|
| 953 |
+
"logits/rejected": 0.3306402862071991,
|
| 954 |
+
"logps/chosen": -604.9376220703125,
|
| 955 |
+
"logps/rejected": -776.1007080078125,
|
| 956 |
+
"loss": 0.1945,
|
| 957 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 958 |
+
"rewards/chosen": -0.2879158854484558,
|
| 959 |
+
"rewards/margins": 0.2369171380996704,
|
| 960 |
+
"rewards/rejected": -0.5248330235481262,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.54,
|
| 965 |
+
"learning_rate": 2.5523560497083927e-06,
|
| 966 |
+
"logits/chosen": 0.16831302642822266,
|
| 967 |
+
"logits/rejected": 0.27101099491119385,
|
| 968 |
+
"logps/chosen": -597.2200317382812,
|
| 969 |
+
"logps/rejected": -789.1015014648438,
|
| 970 |
+
"loss": 0.2018,
|
| 971 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 972 |
+
"rewards/chosen": -0.2811848819255829,
|
| 973 |
+
"rewards/margins": 0.22648608684539795,
|
| 974 |
+
"rewards/rejected": -0.5076709985733032,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.55,
|
| 979 |
+
"learning_rate": 2.482546849255096e-06,
|
| 980 |
+
"logits/chosen": 0.21936634182929993,
|
| 981 |
+
"logits/rejected": 0.28759822249412537,
|
| 982 |
+
"logps/chosen": -643.5916748046875,
|
| 983 |
+
"logps/rejected": -810.319091796875,
|
| 984 |
+
"loss": 0.2443,
|
| 985 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 986 |
+
"rewards/chosen": -0.3228510022163391,
|
| 987 |
+
"rewards/margins": 0.20574745535850525,
|
| 988 |
+
"rewards/rejected": -0.528598427772522,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.56,
|
| 993 |
+
"learning_rate": 2.4127512582437486e-06,
|
| 994 |
+
"logits/chosen": 0.19976723194122314,
|
| 995 |
+
"logits/rejected": 0.31451618671417236,
|
| 996 |
+
"logps/chosen": -684.4381103515625,
|
| 997 |
+
"logps/rejected": -806.4821166992188,
|
| 998 |
+
"loss": 0.2494,
|
| 999 |
+
"rewards/accuracies": 0.6875,
|
| 1000 |
+
"rewards/chosen": -0.3466591238975525,
|
| 1001 |
+
"rewards/margins": 0.19899781048297882,
|
| 1002 |
+
"rewards/rejected": -0.5456569194793701,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.57,
|
| 1007 |
+
"learning_rate": 2.3430237011767166e-06,
|
| 1008 |
+
"logits/chosen": 0.20017175376415253,
|
| 1009 |
+
"logits/rejected": 0.35698938369750977,
|
| 1010 |
+
"logps/chosen": -647.2357177734375,
|
| 1011 |
+
"logps/rejected": -793.7425537109375,
|
| 1012 |
+
"loss": 0.2248,
|
| 1013 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1014 |
+
"rewards/chosen": -0.3104330003261566,
|
| 1015 |
+
"rewards/margins": 0.21013958752155304,
|
| 1016 |
+
"rewards/rejected": -0.5205725431442261,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.58,
|
| 1021 |
+
"learning_rate": 2.2734185495055503e-06,
|
| 1022 |
+
"logits/chosen": 0.15426483750343323,
|
| 1023 |
+
"logits/rejected": 0.34104445576667786,
|
| 1024 |
+
"logps/chosen": -680.1815795898438,
|
| 1025 |
+
"logps/rejected": -807.5281982421875,
|
| 1026 |
+
"loss": 0.2194,
|
| 1027 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1028 |
+
"rewards/chosen": -0.3009037375450134,
|
| 1029 |
+
"rewards/margins": 0.21621103584766388,
|
| 1030 |
+
"rewards/rejected": -0.5171148180961609,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.58,
|
| 1035 |
+
"learning_rate": 2.2039900792337477e-06,
|
| 1036 |
+
"logits/chosen": 0.15546688437461853,
|
| 1037 |
+
"logits/rejected": 0.30181190371513367,
|
| 1038 |
+
"logps/chosen": -634.5504150390625,
|
| 1039 |
+
"logps/rejected": -799.9237060546875,
|
| 1040 |
+
"loss": 0.2099,
|
| 1041 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1042 |
+
"rewards/chosen": -0.30252155661582947,
|
| 1043 |
+
"rewards/margins": 0.21298882365226746,
|
| 1044 |
+
"rewards/rejected": -0.5155104398727417,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.59,
|
| 1049 |
+
"learning_rate": 2.134792428593971e-06,
|
| 1050 |
+
"logits/chosen": 0.18524444103240967,
|
| 1051 |
+
"logits/rejected": 0.3257278800010681,
|
| 1052 |
+
"logps/chosen": -634.2327270507812,
|
| 1053 |
+
"logps/rejected": -799.712890625,
|
| 1054 |
+
"loss": 0.2234,
|
| 1055 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1056 |
+
"rewards/chosen": -0.31897279620170593,
|
| 1057 |
+
"rewards/margins": 0.1969139128923416,
|
| 1058 |
+
"rewards/rejected": -0.5158867239952087,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6,
|
| 1063 |
+
"learning_rate": 2.0658795558326745e-06,
|
| 1064 |
+
"logits/chosen": 0.19903485476970673,
|
| 1065 |
+
"logits/rejected": 0.3221394121646881,
|
| 1066 |
+
"logps/chosen": -691.9305419921875,
|
| 1067 |
+
"logps/rejected": -832.52490234375,
|
| 1068 |
+
"loss": 0.2076,
|
| 1069 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1070 |
+
"rewards/chosen": -0.32866790890693665,
|
| 1071 |
+
"rewards/margins": 0.20474858582019806,
|
| 1072 |
+
"rewards/rejected": -0.5334164500236511,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.61,
|
| 1077 |
+
"learning_rate": 1.997305197135089e-06,
|
| 1078 |
+
"logits/chosen": 0.13654232025146484,
|
| 1079 |
+
"logits/rejected": 0.34442517161369324,
|
| 1080 |
+
"logps/chosen": -730.4304809570312,
|
| 1081 |
+
"logps/rejected": -885.47509765625,
|
| 1082 |
+
"loss": 0.2367,
|
| 1083 |
+
"rewards/accuracies": 0.75,
|
| 1084 |
+
"rewards/chosen": -0.3690676987171173,
|
| 1085 |
+
"rewards/margins": 0.21865062415599823,
|
| 1086 |
+
"rewards/rejected": -0.5877183675765991,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.62,
|
| 1091 |
+
"learning_rate": 1.9291228247233607e-06,
|
| 1092 |
+
"logits/chosen": 0.1613738089799881,
|
| 1093 |
+
"logits/rejected": 0.3314889371395111,
|
| 1094 |
+
"logps/chosen": -709.2805786132812,
|
| 1095 |
+
"logps/rejected": -836.31103515625,
|
| 1096 |
+
"loss": 0.2369,
|
| 1097 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1098 |
+
"rewards/chosen": -0.3563346862792969,
|
| 1099 |
+
"rewards/margins": 0.20591847598552704,
|
| 1100 |
+
"rewards/rejected": -0.5622531771659851,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.62,
|
| 1105 |
+
"learning_rate": 1.8613856051605242e-06,
|
| 1106 |
+
"logits/chosen": 0.11923319101333618,
|
| 1107 |
+
"logits/rejected": 0.285444974899292,
|
| 1108 |
+
"logps/chosen": -645.7232055664062,
|
| 1109 |
+
"logps/rejected": -823.2490234375,
|
| 1110 |
+
"loss": 0.1769,
|
| 1111 |
+
"rewards/accuracies": 0.78125,
|
| 1112 |
+
"rewards/chosen": -0.33025866746902466,
|
| 1113 |
+
"rewards/margins": 0.20709960162639618,
|
| 1114 |
+
"rewards/rejected": -0.5373582243919373,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.63,
|
| 1119 |
+
"learning_rate": 1.7941463578928088e-06,
|
| 1120 |
+
"logits/chosen": 0.1610349863767624,
|
| 1121 |
+
"logits/rejected": 0.2602684795856476,
|
| 1122 |
+
"logps/chosen": -620.0457763671875,
|
| 1123 |
+
"logps/rejected": -792.6785888671875,
|
| 1124 |
+
"loss": 0.1843,
|
| 1125 |
+
"rewards/accuracies": 0.75,
|
| 1126 |
+
"rewards/chosen": -0.3178996443748474,
|
| 1127 |
+
"rewards/margins": 0.20034177601337433,
|
| 1128 |
+
"rewards/rejected": -0.5182414650917053,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.64,
|
| 1133 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 1134 |
+
"logits/chosen": 0.1608382761478424,
|
| 1135 |
+
"logits/rejected": 0.33513420820236206,
|
| 1136 |
+
"logps/chosen": -701.2503662109375,
|
| 1137 |
+
"logps/rejected": -831.8974609375,
|
| 1138 |
+
"loss": 0.2322,
|
| 1139 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1140 |
+
"rewards/chosen": -0.3356068432331085,
|
| 1141 |
+
"rewards/margins": 0.20932845771312714,
|
| 1142 |
+
"rewards/rejected": -0.5449352860450745,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.65,
|
| 1147 |
+
"learning_rate": 1.661371075624363e-06,
|
| 1148 |
+
"logits/chosen": 0.15488770604133606,
|
| 1149 |
+
"logits/rejected": 0.3019334077835083,
|
| 1150 |
+
"logps/chosen": -671.2911987304688,
|
| 1151 |
+
"logps/rejected": -839.7340698242188,
|
| 1152 |
+
"loss": 0.2192,
|
| 1153 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1154 |
+
"rewards/chosen": -0.3298002779483795,
|
| 1155 |
+
"rewards/margins": 0.23614534735679626,
|
| 1156 |
+
"rewards/rejected": -0.565945565700531,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.66,
|
| 1161 |
+
"learning_rate": 1.5959385747947697e-06,
|
| 1162 |
+
"logits/chosen": 0.13863755762577057,
|
| 1163 |
+
"logits/rejected": 0.2941049039363861,
|
| 1164 |
+
"logps/chosen": -673.3838500976562,
|
| 1165 |
+
"logps/rejected": -800.2962646484375,
|
| 1166 |
+
"loss": 0.238,
|
| 1167 |
+
"rewards/accuracies": 0.75,
|
| 1168 |
+
"rewards/chosen": -0.32969725131988525,
|
| 1169 |
+
"rewards/margins": 0.19401879608631134,
|
| 1170 |
+
"rewards/rejected": -0.5237160921096802,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.66,
|
| 1175 |
+
"learning_rate": 1.5312110338697427e-06,
|
| 1176 |
+
"logits/chosen": 0.17822691798210144,
|
| 1177 |
+
"logits/rejected": 0.3630051612854004,
|
| 1178 |
+
"logps/chosen": -677.8616943359375,
|
| 1179 |
+
"logps/rejected": -796.6567993164062,
|
| 1180 |
+
"loss": 0.2204,
|
| 1181 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1182 |
+
"rewards/chosen": -0.3189065754413605,
|
| 1183 |
+
"rewards/margins": 0.20444388687610626,
|
| 1184 |
+
"rewards/rejected": -0.5233504772186279,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.67,
|
| 1189 |
+
"learning_rate": 1.467238925438646e-06,
|
| 1190 |
+
"logits/chosen": 0.15325886011123657,
|
| 1191 |
+
"logits/rejected": 0.35390084981918335,
|
| 1192 |
+
"logps/chosen": -688.0020751953125,
|
| 1193 |
+
"logps/rejected": -839.5821533203125,
|
| 1194 |
+
"loss": 0.211,
|
| 1195 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1196 |
+
"rewards/chosen": -0.3258528709411621,
|
| 1197 |
+
"rewards/margins": 0.20627765357494354,
|
| 1198 |
+
"rewards/rejected": -0.5321305394172668,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.68,
|
| 1203 |
+
"learning_rate": 1.4040721330273063e-06,
|
| 1204 |
+
"logits/chosen": 0.16561973094940186,
|
| 1205 |
+
"logits/rejected": 0.3361406922340393,
|
| 1206 |
+
"logps/chosen": -680.9835815429688,
|
| 1207 |
+
"logps/rejected": -798.2662963867188,
|
| 1208 |
+
"loss": 0.2393,
|
| 1209 |
+
"rewards/accuracies": 0.75,
|
| 1210 |
+
"rewards/chosen": -0.31890079379081726,
|
| 1211 |
+
"rewards/margins": 0.19797927141189575,
|
| 1212 |
+
"rewards/rejected": -0.5168800950050354,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.69,
|
| 1217 |
+
"learning_rate": 1.3417599122003464e-06,
|
| 1218 |
+
"logits/chosen": 0.12001974880695343,
|
| 1219 |
+
"logits/rejected": 0.3118813633918762,
|
| 1220 |
+
"logps/chosen": -642.9356689453125,
|
| 1221 |
+
"logps/rejected": -756.2481689453125,
|
| 1222 |
+
"loss": 0.2139,
|
| 1223 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1224 |
+
"rewards/chosen": -0.2910546660423279,
|
| 1225 |
+
"rewards/margins": 0.20218122005462646,
|
| 1226 |
+
"rewards/rejected": -0.49323591589927673,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7,
|
| 1231 |
+
"learning_rate": 1.280350852153168e-06,
|
| 1232 |
+
"logits/chosen": 0.17175157368183136,
|
| 1233 |
+
"logits/rejected": 0.3029019832611084,
|
| 1234 |
+
"logps/chosen": -641.348876953125,
|
| 1235 |
+
"logps/rejected": -797.3103637695312,
|
| 1236 |
+
"loss": 0.2066,
|
| 1237 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1238 |
+
"rewards/chosen": -0.2968835234642029,
|
| 1239 |
+
"rewards/margins": 0.2184431552886963,
|
| 1240 |
+
"rewards/rejected": -0.5153266787528992,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7,
|
| 1245 |
+
"learning_rate": 1.2198928378235717e-06,
|
| 1246 |
+
"logits/chosen": 0.1690296232700348,
|
| 1247 |
+
"logits/rejected": 0.3570968508720398,
|
| 1248 |
+
"logps/chosen": -618.2169799804688,
|
| 1249 |
+
"logps/rejected": -749.9168090820312,
|
| 1250 |
+
"loss": 0.2216,
|
| 1251 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1252 |
+
"rewards/chosen": -0.30495065450668335,
|
| 1253 |
+
"rewards/margins": 0.19468514621257782,
|
| 1254 |
+
"rewards/rejected": -0.4996357858181,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.71,
|
| 1259 |
+
"learning_rate": 1.160433012552508e-06,
|
| 1260 |
+
"logits/chosen": 0.2119169682264328,
|
| 1261 |
+
"logits/rejected": 0.30031877756118774,
|
| 1262 |
+
"logps/chosen": -656.6976318359375,
|
| 1263 |
+
"logps/rejected": -787.128173828125,
|
| 1264 |
+
"loss": 0.2286,
|
| 1265 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1266 |
+
"rewards/chosen": -0.2992306053638458,
|
| 1267 |
+
"rewards/margins": 0.22145242989063263,
|
| 1268 |
+
"rewards/rejected": -0.5206829905509949,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.72,
|
| 1273 |
+
"learning_rate": 1.1020177413231334e-06,
|
| 1274 |
+
"logits/chosen": 0.13341255486011505,
|
| 1275 |
+
"logits/rejected": 0.3082992434501648,
|
| 1276 |
+
"logps/chosen": -662.7161865234375,
|
| 1277 |
+
"logps/rejected": -828.9288330078125,
|
| 1278 |
+
"loss": 0.2239,
|
| 1279 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1280 |
+
"rewards/chosen": -0.34333524107933044,
|
| 1281 |
+
"rewards/margins": 0.19684186577796936,
|
| 1282 |
+
"rewards/rejected": -0.5401771664619446,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.73,
|
| 1287 |
+
"learning_rate": 1.0446925746067768e-06,
|
| 1288 |
+
"logits/chosen": 0.19903436303138733,
|
| 1289 |
+
"logits/rejected": 0.3391624391078949,
|
| 1290 |
+
"logps/chosen": -676.8585815429688,
|
| 1291 |
+
"logps/rejected": -858.0517578125,
|
| 1292 |
+
"loss": 0.1919,
|
| 1293 |
+
"rewards/accuracies": 0.78125,
|
| 1294 |
+
"rewards/chosen": -0.3304493725299835,
|
| 1295 |
+
"rewards/margins": 0.23948295414447784,
|
| 1296 |
+
"rewards/rejected": -0.5699323415756226,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.74,
|
| 1301 |
+
"learning_rate": 9.88502212844063e-07,
|
| 1302 |
+
"logits/chosen": 0.17577281594276428,
|
| 1303 |
+
"logits/rejected": 0.3430553376674652,
|
| 1304 |
+
"logps/chosen": -685.7710571289062,
|
| 1305 |
+
"logps/rejected": -849.7398681640625,
|
| 1306 |
+
"loss": 0.209,
|
| 1307 |
+
"rewards/accuracies": 0.78125,
|
| 1308 |
+
"rewards/chosen": -0.3442957103252411,
|
| 1309 |
+
"rewards/margins": 0.22943301498889923,
|
| 1310 |
+
"rewards/rejected": -0.5737287402153015,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.74,
|
| 1315 |
+
"learning_rate": 9.334904715888496e-07,
|
| 1316 |
+
"logits/chosen": 0.1338399201631546,
|
| 1317 |
+
"logits/rejected": 0.3034221827983856,
|
| 1318 |
+
"logps/chosen": -700.2951049804688,
|
| 1319 |
+
"logps/rejected": -862.9910278320312,
|
| 1320 |
+
"loss": 0.222,
|
| 1321 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1322 |
+
"rewards/chosen": -0.35036206245422363,
|
| 1323 |
+
"rewards/margins": 0.20818236470222473,
|
| 1324 |
+
"rewards/rejected": -0.558544397354126,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.75,
|
| 1329 |
+
"learning_rate": 8.797002473421729e-07,
|
| 1330 |
+
"logits/chosen": 0.17294977605342865,
|
| 1331 |
+
"logits/rejected": 0.2793739140033722,
|
| 1332 |
+
"logps/chosen": -675.140380859375,
|
| 1333 |
+
"logps/rejected": -871.4267578125,
|
| 1334 |
+
"loss": 0.2172,
|
| 1335 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1336 |
+
"rewards/chosen": -0.36102813482284546,
|
| 1337 |
+
"rewards/margins": 0.23649725317955017,
|
| 1338 |
+
"rewards/rejected": -0.5975253582000732,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.76,
|
| 1343 |
+
"learning_rate": 8.271734841028553e-07,
|
| 1344 |
+
"logits/chosen": 0.17170271277427673,
|
| 1345 |
+
"logits/rejected": 0.3552166521549225,
|
| 1346 |
+
"logps/chosen": -712.1497192382812,
|
| 1347 |
+
"logps/rejected": -911.623046875,
|
| 1348 |
+
"loss": 0.1657,
|
| 1349 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 1350 |
+
"rewards/chosen": -0.33436793088912964,
|
| 1351 |
+
"rewards/margins": 0.2865039110183716,
|
| 1352 |
+
"rewards/rejected": -0.6208718419075012,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.77,
|
| 1357 |
+
"learning_rate": 7.759511406608255e-07,
|
| 1358 |
+
"logits/chosen": 0.2097000628709793,
|
| 1359 |
+
"logits/rejected": 0.38318851590156555,
|
| 1360 |
+
"logps/chosen": -696.2910766601562,
|
| 1361 |
+
"logps/rejected": -820.8037109375,
|
| 1362 |
+
"loss": 0.2308,
|
| 1363 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1364 |
+
"rewards/chosen": -0.34062105417251587,
|
| 1365 |
+
"rewards/margins": 0.20582206547260284,
|
| 1366 |
+
"rewards/rejected": -0.5464431047439575,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.78,
|
| 1371 |
+
"learning_rate": 7.260731586586983e-07,
|
| 1372 |
+
"logits/chosen": 0.14738574624061584,
|
| 1373 |
+
"logits/rejected": 0.3880694508552551,
|
| 1374 |
+
"logps/chosen": -718.88720703125,
|
| 1375 |
+
"logps/rejected": -898.0353393554688,
|
| 1376 |
+
"loss": 0.1708,
|
| 1377 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1378 |
+
"rewards/chosen": -0.35463714599609375,
|
| 1379 |
+
"rewards/margins": 0.24733135104179382,
|
| 1380 |
+
"rewards/rejected": -0.6019684672355652,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.78,
|
| 1385 |
+
"learning_rate": 6.775784314464717e-07,
|
| 1386 |
+
"logits/chosen": 0.16683539748191833,
|
| 1387 |
+
"logits/rejected": 0.3655339777469635,
|
| 1388 |
+
"logps/chosen": -702.0345458984375,
|
| 1389 |
+
"logps/rejected": -867.12841796875,
|
| 1390 |
+
"loss": 0.1899,
|
| 1391 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1392 |
+
"rewards/chosen": -0.3350572884082794,
|
| 1393 |
+
"rewards/margins": 0.23009845614433289,
|
| 1394 |
+
"rewards/rejected": -0.5651557445526123,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.79,
|
| 1399 |
+
"learning_rate": 6.305047737536707e-07,
|
| 1400 |
+
"logits/chosen": 0.1536882221698761,
|
| 1401 |
+
"logits/rejected": 0.3550207018852234,
|
| 1402 |
+
"logps/chosen": -675.9546508789062,
|
| 1403 |
+
"logps/rejected": -849.9825439453125,
|
| 1404 |
+
"loss": 0.1885,
|
| 1405 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1406 |
+
"rewards/chosen": -0.32899874448776245,
|
| 1407 |
+
"rewards/margins": 0.24229104816913605,
|
| 1408 |
+
"rewards/rejected": -0.5712897777557373,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8,
|
| 1413 |
+
"learning_rate": 5.848888922025553e-07,
|
| 1414 |
+
"logits/chosen": 0.11290659010410309,
|
| 1415 |
+
"logits/rejected": 0.36724716424942017,
|
| 1416 |
+
"logps/chosen": -704.583984375,
|
| 1417 |
+
"logps/rejected": -828.1179809570312,
|
| 1418 |
+
"loss": 0.2066,
|
| 1419 |
+
"rewards/accuracies": 0.75,
|
| 1420 |
+
"rewards/chosen": -0.3340883255004883,
|
| 1421 |
+
"rewards/margins": 0.22779309749603271,
|
| 1422 |
+
"rewards/rejected": -0.561881422996521,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.81,
|
| 1427 |
+
"learning_rate": 5.407663566854008e-07,
|
| 1428 |
+
"logits/chosen": 0.1633438766002655,
|
| 1429 |
+
"logits/rejected": 0.3375682234764099,
|
| 1430 |
+
"logps/chosen": -702.7527465820312,
|
| 1431 |
+
"logps/rejected": -863.3948364257812,
|
| 1432 |
+
"loss": 0.2006,
|
| 1433 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1434 |
+
"rewards/chosen": -0.35370200872421265,
|
| 1435 |
+
"rewards/margins": 0.22583265602588654,
|
| 1436 |
+
"rewards/rejected": -0.579534649848938,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.82,
|
| 1441 |
+
"learning_rate": 4.981715726281666e-07,
|
| 1442 |
+
"logits/chosen": 0.1937498301267624,
|
| 1443 |
+
"logits/rejected": 0.340679407119751,
|
| 1444 |
+
"logps/chosen": -691.4595947265625,
|
| 1445 |
+
"logps/rejected": -839.4888916015625,
|
| 1446 |
+
"loss": 0.2208,
|
| 1447 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1448 |
+
"rewards/chosen": -0.35861554741859436,
|
| 1449 |
+
"rewards/margins": 0.20035746693611145,
|
| 1450 |
+
"rewards/rejected": -0.5589730143547058,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.82,
|
| 1455 |
+
"learning_rate": 4.5713775416217884e-07,
|
| 1456 |
+
"logits/chosen": 0.12361009418964386,
|
| 1457 |
+
"logits/rejected": 0.34942418336868286,
|
| 1458 |
+
"logps/chosen": -680.8634033203125,
|
| 1459 |
+
"logps/rejected": -882.5494995117188,
|
| 1460 |
+
"loss": 0.1692,
|
| 1461 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 1462 |
+
"rewards/chosen": -0.3480374217033386,
|
| 1463 |
+
"rewards/margins": 0.26189786195755005,
|
| 1464 |
+
"rewards/rejected": -0.6099352836608887,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.83,
|
| 1469 |
+
"learning_rate": 4.1769689822475147e-07,
|
| 1470 |
+
"logits/chosen": 0.19276142120361328,
|
| 1471 |
+
"logits/rejected": 0.29219889640808105,
|
| 1472 |
+
"logps/chosen": -703.4930419921875,
|
| 1473 |
+
"logps/rejected": -866.1170654296875,
|
| 1474 |
+
"loss": 0.1982,
|
| 1475 |
+
"rewards/accuracies": 0.75,
|
| 1476 |
+
"rewards/chosen": -0.3588348627090454,
|
| 1477 |
+
"rewards/margins": 0.22297649085521698,
|
| 1478 |
+
"rewards/rejected": -0.5818113088607788,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.84,
|
| 1483 |
+
"learning_rate": 3.798797596089351e-07,
|
| 1484 |
+
"logits/chosen": 0.19400565326213837,
|
| 1485 |
+
"logits/rejected": 0.32384955883026123,
|
| 1486 |
+
"logps/chosen": -673.8597412109375,
|
| 1487 |
+
"logps/rejected": -835.2975463867188,
|
| 1488 |
+
"loss": 0.2252,
|
| 1489 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1490 |
+
"rewards/chosen": -0.34572821855545044,
|
| 1491 |
+
"rewards/margins": 0.21857137978076935,
|
| 1492 |
+
"rewards/rejected": -0.5642995834350586,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.85,
|
| 1497 |
+
"learning_rate": 3.4371582698185636e-07,
|
| 1498 |
+
"logits/chosen": 0.17536142468452454,
|
| 1499 |
+
"logits/rejected": 0.29948705434799194,
|
| 1500 |
+
"logps/chosen": -675.4208374023438,
|
| 1501 |
+
"logps/rejected": -875.52587890625,
|
| 1502 |
+
"loss": 0.2243,
|
| 1503 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1504 |
+
"rewards/chosen": -0.34358900785446167,
|
| 1505 |
+
"rewards/margins": 0.23982660472393036,
|
| 1506 |
+
"rewards/rejected": -0.5834155678749084,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.86,
|
| 1511 |
+
"learning_rate": 3.092332998903416e-07,
|
| 1512 |
+
"logits/chosen": 0.19849039614200592,
|
| 1513 |
+
"logits/rejected": 0.3707537055015564,
|
| 1514 |
+
"logps/chosen": -705.3458862304688,
|
| 1515 |
+
"logps/rejected": -847.8703002929688,
|
| 1516 |
+
"loss": 0.1904,
|
| 1517 |
+
"rewards/accuracies": 0.78125,
|
| 1518 |
+
"rewards/chosen": -0.3420145809650421,
|
| 1519 |
+
"rewards/margins": 0.220182865858078,
|
| 1520 |
+
"rewards/rejected": -0.5621975064277649,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.86,
|
| 1525 |
+
"learning_rate": 2.764590667717562e-07,
|
| 1526 |
+
"logits/chosen": 0.1871638298034668,
|
| 1527 |
+
"logits/rejected": 0.2827778458595276,
|
| 1528 |
+
"logps/chosen": -680.1304931640625,
|
| 1529 |
+
"logps/rejected": -818.0643310546875,
|
| 1530 |
+
"loss": 0.2392,
|
| 1531 |
+
"rewards/accuracies": 0.71875,
|
| 1532 |
+
"rewards/chosen": -0.3372667133808136,
|
| 1533 |
+
"rewards/margins": 0.20627236366271973,
|
| 1534 |
+
"rewards/rejected": -0.5435390472412109,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.87,
|
| 1539 |
+
"learning_rate": 2.454186839872158e-07,
|
| 1540 |
+
"logits/chosen": 0.16120100021362305,
|
| 1541 |
+
"logits/rejected": 0.32251447439193726,
|
| 1542 |
+
"logps/chosen": -686.634765625,
|
| 1543 |
+
"logps/rejected": -866.3630981445312,
|
| 1544 |
+
"loss": 0.216,
|
| 1545 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1546 |
+
"rewards/chosen": -0.32807648181915283,
|
| 1547 |
+
"rewards/margins": 0.24755918979644775,
|
| 1548 |
+
"rewards/rejected": -0.5756356716156006,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.88,
|
| 1553 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 1554 |
+
"logits/chosen": 0.1712665855884552,
|
| 1555 |
+
"logits/rejected": 0.3769349753856659,
|
| 1556 |
+
"logps/chosen": -679.5457153320312,
|
| 1557 |
+
"logps/rejected": -809.4376220703125,
|
| 1558 |
+
"loss": 0.2088,
|
| 1559 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1560 |
+
"rewards/chosen": -0.3401484489440918,
|
| 1561 |
+
"rewards/margins": 0.19833040237426758,
|
| 1562 |
+
"rewards/rejected": -0.5384788513183594,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.89,
|
| 1567 |
+
"learning_rate": 1.8863491596921745e-07,
|
| 1568 |
+
"logits/chosen": 0.1486029326915741,
|
| 1569 |
+
"logits/rejected": 0.28596794605255127,
|
| 1570 |
+
"logps/chosen": -646.8463134765625,
|
| 1571 |
+
"logps/rejected": -788.2711181640625,
|
| 1572 |
+
"loss": 0.2536,
|
| 1573 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1574 |
+
"rewards/chosen": -0.3294883668422699,
|
| 1575 |
+
"rewards/margins": 0.18572267889976501,
|
| 1576 |
+
"rewards/rejected": -0.5152110457420349,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9,
|
| 1581 |
+
"learning_rate": 1.629358090099639e-07,
|
| 1582 |
+
"logits/chosen": 0.17368651926517487,
|
| 1583 |
+
"logits/rejected": 0.3338169455528259,
|
| 1584 |
+
"logps/chosen": -634.6134643554688,
|
| 1585 |
+
"logps/rejected": -778.5861206054688,
|
| 1586 |
+
"loss": 0.1982,
|
| 1587 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1588 |
+
"rewards/chosen": -0.2928779125213623,
|
| 1589 |
+
"rewards/margins": 0.2151258885860443,
|
| 1590 |
+
"rewards/rejected": -0.508003830909729,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9,
|
| 1595 |
+
"learning_rate": 1.3905907440629752e-07,
|
| 1596 |
+
"logits/chosen": 0.15766136348247528,
|
| 1597 |
+
"logits/rejected": 0.3557658791542053,
|
| 1598 |
+
"logps/chosen": -662.1260986328125,
|
| 1599 |
+
"logps/rejected": -839.3025512695312,
|
| 1600 |
+
"loss": 0.1941,
|
| 1601 |
+
"rewards/accuracies": 0.8125,
|
| 1602 |
+
"rewards/chosen": -0.31253698468208313,
|
| 1603 |
+
"rewards/margins": 0.24924030900001526,
|
| 1604 |
+
"rewards/rejected": -0.5617772340774536,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.91,
|
| 1609 |
+
"learning_rate": 1.1702333051763271e-07,
|
| 1610 |
+
"logits/chosen": 0.15091878175735474,
|
| 1611 |
+
"logits/rejected": 0.30173712968826294,
|
| 1612 |
+
"logps/chosen": -701.94970703125,
|
| 1613 |
+
"logps/rejected": -801.0489501953125,
|
| 1614 |
+
"loss": 0.2352,
|
| 1615 |
+
"rewards/accuracies": 0.75,
|
| 1616 |
+
"rewards/chosen": -0.3308618664741516,
|
| 1617 |
+
"rewards/margins": 0.19058778882026672,
|
| 1618 |
+
"rewards/rejected": -0.5214496850967407,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.92,
|
| 1623 |
+
"learning_rate": 9.684576015420277e-08,
|
| 1624 |
+
"logits/chosen": 0.1685861349105835,
|
| 1625 |
+
"logits/rejected": 0.3190310597419739,
|
| 1626 |
+
"logps/chosen": -623.9698486328125,
|
| 1627 |
+
"logps/rejected": -801.55126953125,
|
| 1628 |
+
"loss": 0.2013,
|
| 1629 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1630 |
+
"rewards/chosen": -0.2987983226776123,
|
| 1631 |
+
"rewards/margins": 0.22366292774677277,
|
| 1632 |
+
"rewards/rejected": -0.5224612951278687,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.93,
|
| 1637 |
+
"learning_rate": 7.854209717842231e-08,
|
| 1638 |
+
"logits/chosen": 0.22428612411022186,
|
| 1639 |
+
"logits/rejected": 0.32517939805984497,
|
| 1640 |
+
"logps/chosen": -670.4127807617188,
|
| 1641 |
+
"logps/rejected": -846.4913330078125,
|
| 1642 |
+
"loss": 0.2279,
|
| 1643 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1644 |
+
"rewards/chosen": -0.31652674078941345,
|
| 1645 |
+
"rewards/margins": 0.24327680468559265,
|
| 1646 |
+
"rewards/rejected": -0.5598036050796509,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.94,
|
| 1651 |
+
"learning_rate": 6.212661423609184e-08,
|
| 1652 |
+
"logits/chosen": 0.20708954334259033,
|
| 1653 |
+
"logits/rejected": 0.2972474992275238,
|
| 1654 |
+
"logps/chosen": -662.8619995117188,
|
| 1655 |
+
"logps/rejected": -839.24169921875,
|
| 1656 |
+
"loss": 0.2332,
|
| 1657 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1658 |
+
"rewards/chosen": -0.3305516839027405,
|
| 1659 |
+
"rewards/margins": 0.2120494544506073,
|
| 1660 |
+
"rewards/rejected": -0.5426011085510254,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.94,
|
| 1665 |
+
"learning_rate": 4.761211162702117e-08,
|
| 1666 |
+
"logits/chosen": 0.16905297338962555,
|
| 1667 |
+
"logits/rejected": 0.33523765206336975,
|
| 1668 |
+
"logps/chosen": -740.4127197265625,
|
| 1669 |
+
"logps/rejected": -869.7010498046875,
|
| 1670 |
+
"loss": 0.2049,
|
| 1671 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1672 |
+
"rewards/chosen": -0.32125991582870483,
|
| 1673 |
+
"rewards/margins": 0.23766210675239563,
|
| 1674 |
+
"rewards/rejected": -0.5589220523834229,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.95,
|
| 1679 |
+
"learning_rate": 3.5009907323737826e-08,
|
| 1680 |
+
"logits/chosen": 0.17241886258125305,
|
| 1681 |
+
"logits/rejected": 0.27635636925697327,
|
| 1682 |
+
"logps/chosen": -646.537109375,
|
| 1683 |
+
"logps/rejected": -793.7910766601562,
|
| 1684 |
+
"loss": 0.2084,
|
| 1685 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1686 |
+
"rewards/chosen": -0.3147274851799011,
|
| 1687 |
+
"rewards/margins": 0.20939941704273224,
|
| 1688 |
+
"rewards/rejected": -0.5241268873214722,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.96,
|
| 1693 |
+
"learning_rate": 2.4329828146074096e-08,
|
| 1694 |
+
"logits/chosen": 0.1950569897890091,
|
| 1695 |
+
"logits/rejected": 0.27444005012512207,
|
| 1696 |
+
"logps/chosen": -603.3720703125,
|
| 1697 |
+
"logps/rejected": -796.5051879882812,
|
| 1698 |
+
"loss": 0.2438,
|
| 1699 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1700 |
+
"rewards/chosen": -0.31794172525405884,
|
| 1701 |
+
"rewards/margins": 0.20714089274406433,
|
| 1702 |
+
"rewards/rejected": -0.5250825881958008,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.97,
|
| 1707 |
+
"learning_rate": 1.5580202098509078e-08,
|
| 1708 |
+
"logits/chosen": 0.19672410190105438,
|
| 1709 |
+
"logits/rejected": 0.2793806791305542,
|
| 1710 |
+
"logps/chosen": -667.3795166015625,
|
| 1711 |
+
"logps/rejected": -806.3576049804688,
|
| 1712 |
+
"loss": 0.2217,
|
| 1713 |
+
"rewards/accuracies": 0.71875,
|
| 1714 |
+
"rewards/chosen": -0.32957980036735535,
|
| 1715 |
+
"rewards/margins": 0.19165340065956116,
|
| 1716 |
+
"rewards/rejected": -0.5212332010269165,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.98,
|
| 1721 |
+
"learning_rate": 8.767851876239075e-09,
|
| 1722 |
+
"logits/chosen": 0.14809760451316833,
|
| 1723 |
+
"logits/rejected": 0.33844250440597534,
|
| 1724 |
+
"logps/chosen": -681.6161499023438,
|
| 1725 |
+
"logps/rejected": -838.42578125,
|
| 1726 |
+
"loss": 0.2059,
|
| 1727 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1728 |
+
"rewards/chosen": -0.32918164134025574,
|
| 1729 |
+
"rewards/margins": 0.22278150916099548,
|
| 1730 |
+
"rewards/rejected": -0.5519631505012512,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.98,
|
| 1735 |
+
"learning_rate": 3.8980895450474455e-09,
|
| 1736 |
+
"logits/chosen": 0.21805985271930695,
|
| 1737 |
+
"logits/rejected": 0.3143409788608551,
|
| 1738 |
+
"logps/chosen": -660.1900634765625,
|
| 1739 |
+
"logps/rejected": -861.4285888671875,
|
| 1740 |
+
"loss": 0.1828,
|
| 1741 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1742 |
+
"rewards/chosen": -0.3263797163963318,
|
| 1743 |
+
"rewards/margins": 0.2446649968624115,
|
| 1744 |
+
"rewards/rejected": -0.5710447430610657,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.99,
|
| 1749 |
+
"learning_rate": 9.747123991141193e-10,
|
| 1750 |
+
"logits/chosen": 0.13117751479148865,
|
| 1751 |
+
"logits/rejected": 0.3310020864009857,
|
| 1752 |
+
"logps/chosen": -721.1244506835938,
|
| 1753 |
+
"logps/rejected": -845.4733276367188,
|
| 1754 |
+
"loss": 0.221,
|
| 1755 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1756 |
+
"rewards/chosen": -0.3326810896396637,
|
| 1757 |
+
"rewards/margins": 0.22099986672401428,
|
| 1758 |
+
"rewards/rejected": -0.5536808967590332,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.0,
|
| 1763 |
+
"learning_rate": 0.0,
|
| 1764 |
+
"logits/chosen": 0.14761529862880707,
|
| 1765 |
+
"logits/rejected": 0.3856538236141205,
|
| 1766 |
+
"logps/chosen": -645.8055419921875,
|
| 1767 |
+
"logps/rejected": -837.1917724609375,
|
| 1768 |
+
"loss": 0.1805,
|
| 1769 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1770 |
+
"rewards/chosen": -0.3032386898994446,
|
| 1771 |
+
"rewards/margins": 0.2420150488615036,
|
| 1772 |
+
"rewards/rejected": -0.5452538132667542,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.0,
|
| 1777 |
+
"step": 1250,
|
| 1778 |
+
"total_flos": 0.0,
|
| 1779 |
+
"train_loss": 0.23378739290237427,
|
| 1780 |
+
"train_runtime": 11502.4567,
|
| 1781 |
+
"train_samples_per_second": 1.739,
|
| 1782 |
+
"train_steps_per_second": 0.109
|
| 1783 |
+
}
|
| 1784 |
+
],
|
| 1785 |
+
"logging_steps": 10,
|
| 1786 |
+
"max_steps": 1250,
|
| 1787 |
+
"num_input_tokens_seen": 0,
|
| 1788 |
+
"num_train_epochs": 1,
|
| 1789 |
+
"save_steps": 100,
|
| 1790 |
+
"total_flos": 0.0,
|
| 1791 |
+
"train_batch_size": 4,
|
| 1792 |
+
"trial_name": null,
|
| 1793 |
+
"trial_params": null
|
| 1794 |
+
}
|