Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May21_02-50-47_gpu4-119-5/events.out.tfevents.1716224008.gpu4-119-5.1224963.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1346 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-i0
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-irepo-chatml-v12-i1
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# phi-2-irepo-chatml-v12-i1
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-i0](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-i0) on the None dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 2
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- total_eval_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.7.1
|
| 58 |
+
- Transformers 4.36.2
|
| 59 |
+
- Pytorch 2.1.2+cu121
|
| 60 |
+
- Datasets 2.14.6
|
| 61 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335579632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65ffeecb360e1d6ca4df09840309227cf8b939667bca09179ab07502707dcbe7
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.275421927202982,
|
| 4 |
+
"train_runtime": 7850.8319,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.821,
|
| 7 |
+
"train_steps_per_second": 0.119
|
| 8 |
+
}
|
runs/May21_02-50-47_gpu4-119-5/events.out.tfevents.1716224008.gpu4-119-5.1224963.0
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:bfae93cc43fb7a11be44a827b8db1ce4cc0fc0f051dd91e21c4ff9048ecf4365
|
| 3 |
+
size 64720
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.275421927202982,
|
| 4 |
+
"train_runtime": 7850.8319,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.821,
|
| 7 |
+
"train_steps_per_second": 0.119
|
| 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": 0.06642268598079681,
|
| 15 |
+
"logits/rejected": 0.23397813737392426,
|
| 16 |
+
"logps/chosen": -587.28369140625,
|
| 17 |
+
"logps/rejected": -568.082763671875,
|
| 18 |
+
"loss": 0.279,
|
| 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": 0.16077889502048492,
|
| 29 |
+
"logits/rejected": 0.28465068340301514,
|
| 30 |
+
"logps/chosen": -462.99114990234375,
|
| 31 |
+
"logps/rejected": -441.3485107421875,
|
| 32 |
+
"loss": 0.303,
|
| 33 |
+
"rewards/accuracies": 0.4236111044883728,
|
| 34 |
+
"rewards/chosen": -0.0005749252159148455,
|
| 35 |
+
"rewards/margins": 0.0002628265065141022,
|
| 36 |
+
"rewards/rejected": -0.0008377517224289477,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.2244517058134079,
|
| 43 |
+
"logits/rejected": 0.2146037071943283,
|
| 44 |
+
"logps/chosen": -456.9951171875,
|
| 45 |
+
"logps/rejected": -442.496826171875,
|
| 46 |
+
"loss": 0.3007,
|
| 47 |
+
"rewards/accuracies": 0.33125001192092896,
|
| 48 |
+
"rewards/chosen": -0.0011023276019841433,
|
| 49 |
+
"rewards/margins": -6.420163117581978e-05,
|
| 50 |
+
"rewards/rejected": -0.0010381259489804506,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.34518542885780334,
|
| 57 |
+
"logits/rejected": 0.15579931437969208,
|
| 58 |
+
"logps/chosen": -414.3968200683594,
|
| 59 |
+
"logps/rejected": -407.1432800292969,
|
| 60 |
+
"loss": 0.3064,
|
| 61 |
+
"rewards/accuracies": 0.3812499940395355,
|
| 62 |
+
"rewards/chosen": -0.0004762631724588573,
|
| 63 |
+
"rewards/margins": 6.935702549526468e-05,
|
| 64 |
+
"rewards/rejected": -0.0005456201615743339,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.19979876279830933,
|
| 71 |
+
"logits/rejected": 0.1475386917591095,
|
| 72 |
+
"logps/chosen": -387.1222839355469,
|
| 73 |
+
"logps/rejected": -380.3912048339844,
|
| 74 |
+
"loss": 0.3173,
|
| 75 |
+
"rewards/accuracies": 0.36250001192092896,
|
| 76 |
+
"rewards/chosen": 8.398960198974237e-05,
|
| 77 |
+
"rewards/margins": 0.0001377248700009659,
|
| 78 |
+
"rewards/rejected": -5.3735253459308296e-05,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.20050282776355743,
|
| 85 |
+
"logits/rejected": 0.2853023409843445,
|
| 86 |
+
"logps/chosen": -405.1722717285156,
|
| 87 |
+
"logps/rejected": -433.797119140625,
|
| 88 |
+
"loss": 0.2969,
|
| 89 |
+
"rewards/accuracies": 0.38749998807907104,
|
| 90 |
+
"rewards/chosen": -0.00031604920513927937,
|
| 91 |
+
"rewards/margins": 9.358949318993837e-05,
|
| 92 |
+
"rewards/rejected": -0.0004096386837773025,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.22685687243938446,
|
| 99 |
+
"logits/rejected": 0.2761882245540619,
|
| 100 |
+
"logps/chosen": -418.8284606933594,
|
| 101 |
+
"logps/rejected": -444.300537109375,
|
| 102 |
+
"loss": 0.2916,
|
| 103 |
+
"rewards/accuracies": 0.5,
|
| 104 |
+
"rewards/chosen": -0.0013369970256462693,
|
| 105 |
+
"rewards/margins": 0.00045625813072547317,
|
| 106 |
+
"rewards/rejected": -0.0017932550981640816,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.1869155615568161,
|
| 113 |
+
"logits/rejected": 0.2700553834438324,
|
| 114 |
+
"logps/chosen": -443.9104919433594,
|
| 115 |
+
"logps/rejected": -423.21075439453125,
|
| 116 |
+
"loss": 0.2976,
|
| 117 |
+
"rewards/accuracies": 0.46875,
|
| 118 |
+
"rewards/chosen": -0.003828343003988266,
|
| 119 |
+
"rewards/margins": 0.0006897930870763958,
|
| 120 |
+
"rewards/rejected": -0.004518135450780392,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.23689034581184387,
|
| 127 |
+
"logits/rejected": 0.21069273352622986,
|
| 128 |
+
"logps/chosen": -386.25067138671875,
|
| 129 |
+
"logps/rejected": -387.7801818847656,
|
| 130 |
+
"loss": 0.3143,
|
| 131 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 132 |
+
"rewards/chosen": -0.003951665014028549,
|
| 133 |
+
"rewards/margins": 0.0011586709879338741,
|
| 134 |
+
"rewards/rejected": -0.005110335536301136,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.24118606746196747,
|
| 141 |
+
"logits/rejected": 0.25480058789253235,
|
| 142 |
+
"logps/chosen": -412.43499755859375,
|
| 143 |
+
"logps/rejected": -408.15802001953125,
|
| 144 |
+
"loss": 0.3065,
|
| 145 |
+
"rewards/accuracies": 0.5,
|
| 146 |
+
"rewards/chosen": -0.010140495374798775,
|
| 147 |
+
"rewards/margins": 0.001615689368918538,
|
| 148 |
+
"rewards/rejected": -0.01175618451088667,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.1671404391527176,
|
| 155 |
+
"logits/rejected": 0.2540619969367981,
|
| 156 |
+
"logps/chosen": -389.2574157714844,
|
| 157 |
+
"logps/rejected": -388.87408447265625,
|
| 158 |
+
"loss": 0.3053,
|
| 159 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 160 |
+
"rewards/chosen": -0.022764097899198532,
|
| 161 |
+
"rewards/margins": 0.0024351924657821655,
|
| 162 |
+
"rewards/rejected": -0.02519928850233555,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.23305337131023407,
|
| 169 |
+
"logits/rejected": 0.22437167167663574,
|
| 170 |
+
"logps/chosen": -441.59771728515625,
|
| 171 |
+
"logps/rejected": -446.51971435546875,
|
| 172 |
+
"loss": 0.3081,
|
| 173 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 174 |
+
"rewards/chosen": -0.04231434687972069,
|
| 175 |
+
"rewards/margins": 0.003846729639917612,
|
| 176 |
+
"rewards/rejected": -0.04616107791662216,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.17237094044685364,
|
| 183 |
+
"logits/rejected": 0.20950445532798767,
|
| 184 |
+
"logps/chosen": -497.03741455078125,
|
| 185 |
+
"logps/rejected": -493.6482849121094,
|
| 186 |
+
"loss": 0.3001,
|
| 187 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 188 |
+
"rewards/chosen": -0.06084052473306656,
|
| 189 |
+
"rewards/margins": 0.009210348129272461,
|
| 190 |
+
"rewards/rejected": -0.07005088031291962,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.12596510350704193,
|
| 197 |
+
"logits/rejected": 0.18595007061958313,
|
| 198 |
+
"logps/chosen": -534.695556640625,
|
| 199 |
+
"logps/rejected": -506.4364318847656,
|
| 200 |
+
"loss": 0.285,
|
| 201 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 202 |
+
"rewards/chosen": -0.09366725385189056,
|
| 203 |
+
"rewards/margins": 0.009929810650646687,
|
| 204 |
+
"rewards/rejected": -0.10359706729650497,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.12804082036018372,
|
| 211 |
+
"logits/rejected": 0.10300163924694061,
|
| 212 |
+
"logps/chosen": -515.469970703125,
|
| 213 |
+
"logps/rejected": -508.8036193847656,
|
| 214 |
+
"loss": 0.3043,
|
| 215 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 216 |
+
"rewards/chosen": -0.11144615709781647,
|
| 217 |
+
"rewards/margins": 0.012134796939790249,
|
| 218 |
+
"rewards/rejected": -0.1235809326171875,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.16220004856586456,
|
| 225 |
+
"logits/rejected": 0.08028533309698105,
|
| 226 |
+
"logps/chosen": -479.33184814453125,
|
| 227 |
+
"logps/rejected": -524.7337646484375,
|
| 228 |
+
"loss": 0.2802,
|
| 229 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 230 |
+
"rewards/chosen": -0.1306999772787094,
|
| 231 |
+
"rewards/margins": 0.03233319893479347,
|
| 232 |
+
"rewards/rejected": -0.16303318738937378,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.18928228318691254,
|
| 239 |
+
"logits/rejected": 0.14869533479213715,
|
| 240 |
+
"logps/chosen": -573.3798828125,
|
| 241 |
+
"logps/rejected": -610.5779418945312,
|
| 242 |
+
"loss": 0.2894,
|
| 243 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 244 |
+
"rewards/chosen": -0.168126180768013,
|
| 245 |
+
"rewards/margins": 0.04517129063606262,
|
| 246 |
+
"rewards/rejected": -0.21329745650291443,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.062172818928956985,
|
| 253 |
+
"logits/rejected": 0.019718164578080177,
|
| 254 |
+
"logps/chosen": -475.08551025390625,
|
| 255 |
+
"logps/rejected": -561.6641845703125,
|
| 256 |
+
"loss": 0.2631,
|
| 257 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 258 |
+
"rewards/chosen": -0.1646568328142166,
|
| 259 |
+
"rewards/margins": 0.06741134822368622,
|
| 260 |
+
"rewards/rejected": -0.23206815123558044,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": -0.0011120836716145277,
|
| 267 |
+
"logits/rejected": 0.13960300385951996,
|
| 268 |
+
"logps/chosen": -525.2228393554688,
|
| 269 |
+
"logps/rejected": -511.014404296875,
|
| 270 |
+
"loss": 0.2908,
|
| 271 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 272 |
+
"rewards/chosen": -0.14511564373970032,
|
| 273 |
+
"rewards/margins": 0.03634321317076683,
|
| 274 |
+
"rewards/rejected": -0.18145884573459625,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.11656410992145538,
|
| 281 |
+
"logits/rejected": 0.08704119175672531,
|
| 282 |
+
"logps/chosen": -514.813720703125,
|
| 283 |
+
"logps/rejected": -595.0880126953125,
|
| 284 |
+
"loss": 0.2617,
|
| 285 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 286 |
+
"rewards/chosen": -0.14817455410957336,
|
| 287 |
+
"rewards/margins": 0.04434273764491081,
|
| 288 |
+
"rewards/rejected": -0.19251729547977448,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.06601261347532272,
|
| 295 |
+
"logits/rejected": 0.12538839876651764,
|
| 296 |
+
"logps/chosen": -538.46142578125,
|
| 297 |
+
"logps/rejected": -592.1277465820312,
|
| 298 |
+
"loss": 0.2739,
|
| 299 |
+
"rewards/accuracies": 0.5,
|
| 300 |
+
"rewards/chosen": -0.15786947309970856,
|
| 301 |
+
"rewards/margins": 0.04001317173242569,
|
| 302 |
+
"rewards/rejected": -0.19788263738155365,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.04595109820365906,
|
| 309 |
+
"logits/rejected": 0.05397043749690056,
|
| 310 |
+
"logps/chosen": -542.3662109375,
|
| 311 |
+
"logps/rejected": -587.703125,
|
| 312 |
+
"loss": 0.2803,
|
| 313 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 314 |
+
"rewards/chosen": -0.15854400396347046,
|
| 315 |
+
"rewards/margins": 0.037279583513736725,
|
| 316 |
+
"rewards/rejected": -0.19582359492778778,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.06908506900072098,
|
| 323 |
+
"logits/rejected": 0.0783570259809494,
|
| 324 |
+
"logps/chosen": -543.8673095703125,
|
| 325 |
+
"logps/rejected": -552.3768920898438,
|
| 326 |
+
"loss": 0.273,
|
| 327 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 328 |
+
"rewards/chosen": -0.14275754988193512,
|
| 329 |
+
"rewards/margins": 0.04143111780285835,
|
| 330 |
+
"rewards/rejected": -0.18418867886066437,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": 0.07219888269901276,
|
| 337 |
+
"logits/rejected": 0.0497373566031456,
|
| 338 |
+
"logps/chosen": -572.8856201171875,
|
| 339 |
+
"logps/rejected": -622.0572509765625,
|
| 340 |
+
"loss": 0.2833,
|
| 341 |
+
"rewards/accuracies": 0.543749988079071,
|
| 342 |
+
"rewards/chosen": -0.14573441445827484,
|
| 343 |
+
"rewards/margins": 0.06495748460292816,
|
| 344 |
+
"rewards/rejected": -0.210691899061203,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": -0.10666439682245255,
|
| 351 |
+
"logits/rejected": 0.05354728549718857,
|
| 352 |
+
"logps/chosen": -541.7586059570312,
|
| 353 |
+
"logps/rejected": -586.1435546875,
|
| 354 |
+
"loss": 0.2883,
|
| 355 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 356 |
+
"rewards/chosen": -0.14508689939975739,
|
| 357 |
+
"rewards/margins": 0.048395391553640366,
|
| 358 |
+
"rewards/rejected": -0.19348229467868805,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": 0.07505561411380768,
|
| 365 |
+
"logits/rejected": -0.051252782344818115,
|
| 366 |
+
"logps/chosen": -555.9990844726562,
|
| 367 |
+
"logps/rejected": -585.9085083007812,
|
| 368 |
+
"loss": 0.2815,
|
| 369 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 370 |
+
"rewards/chosen": -0.14657357335090637,
|
| 371 |
+
"rewards/margins": 0.04433682560920715,
|
| 372 |
+
"rewards/rejected": -0.19091038405895233,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": -0.020656492561101913,
|
| 379 |
+
"logits/rejected": 0.007626605220139027,
|
| 380 |
+
"logps/chosen": -612.7149658203125,
|
| 381 |
+
"logps/rejected": -613.846435546875,
|
| 382 |
+
"loss": 0.2945,
|
| 383 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 384 |
+
"rewards/chosen": -0.1504904180765152,
|
| 385 |
+
"rewards/margins": 0.03951232135295868,
|
| 386 |
+
"rewards/rejected": -0.19000275433063507,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": 0.06314031779766083,
|
| 393 |
+
"logits/rejected": 0.05012714862823486,
|
| 394 |
+
"logps/chosen": -572.8782958984375,
|
| 395 |
+
"logps/rejected": -599.4718627929688,
|
| 396 |
+
"loss": 0.286,
|
| 397 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 398 |
+
"rewards/chosen": -0.11262224614620209,
|
| 399 |
+
"rewards/margins": 0.0400107316672802,
|
| 400 |
+
"rewards/rejected": -0.15263298153877258,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": 4.419684410095215e-05,
|
| 407 |
+
"logits/rejected": 0.1705075055360794,
|
| 408 |
+
"logps/chosen": -478.0445251464844,
|
| 409 |
+
"logps/rejected": -514.4085693359375,
|
| 410 |
+
"loss": 0.2574,
|
| 411 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 412 |
+
"rewards/chosen": -0.08713702112436295,
|
| 413 |
+
"rewards/margins": 0.0530150942504406,
|
| 414 |
+
"rewards/rejected": -0.14015211164951324,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": -0.05049672722816467,
|
| 421 |
+
"logits/rejected": 0.10665085166692734,
|
| 422 |
+
"logps/chosen": -562.5294799804688,
|
| 423 |
+
"logps/rejected": -583.0447998046875,
|
| 424 |
+
"loss": 0.2866,
|
| 425 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 426 |
+
"rewards/chosen": -0.12877288460731506,
|
| 427 |
+
"rewards/margins": 0.0415426567196846,
|
| 428 |
+
"rewards/rejected": -0.17031553387641907,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": -0.13402745127677917,
|
| 435 |
+
"logits/rejected": 0.04227043688297272,
|
| 436 |
+
"logps/chosen": -570.83935546875,
|
| 437 |
+
"logps/rejected": -597.737060546875,
|
| 438 |
+
"loss": 0.2749,
|
| 439 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 440 |
+
"rewards/chosen": -0.14190678298473358,
|
| 441 |
+
"rewards/margins": 0.054900676012039185,
|
| 442 |
+
"rewards/rejected": -0.19680745899677277,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": -0.07339149713516235,
|
| 449 |
+
"logits/rejected": -0.040264565497636795,
|
| 450 |
+
"logps/chosen": -619.7767333984375,
|
| 451 |
+
"logps/rejected": -682.0263061523438,
|
| 452 |
+
"loss": 0.2589,
|
| 453 |
+
"rewards/accuracies": 0.581250011920929,
|
| 454 |
+
"rewards/chosen": -0.16093352437019348,
|
| 455 |
+
"rewards/margins": 0.07607638835906982,
|
| 456 |
+
"rewards/rejected": -0.2370099127292633,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": -0.028974998742341995,
|
| 463 |
+
"logits/rejected": -0.06319359689950943,
|
| 464 |
+
"logps/chosen": -549.9708862304688,
|
| 465 |
+
"logps/rejected": -637.650390625,
|
| 466 |
+
"loss": 0.264,
|
| 467 |
+
"rewards/accuracies": 0.5,
|
| 468 |
+
"rewards/chosen": -0.13445612788200378,
|
| 469 |
+
"rewards/margins": 0.07859645038843155,
|
| 470 |
+
"rewards/rejected": -0.21305255591869354,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": -0.11449748277664185,
|
| 477 |
+
"logits/rejected": -0.03637564182281494,
|
| 478 |
+
"logps/chosen": -601.0888671875,
|
| 479 |
+
"logps/rejected": -669.8153076171875,
|
| 480 |
+
"loss": 0.2698,
|
| 481 |
+
"rewards/accuracies": 0.543749988079071,
|
| 482 |
+
"rewards/chosen": -0.1675841063261032,
|
| 483 |
+
"rewards/margins": 0.0730680450797081,
|
| 484 |
+
"rewards/rejected": -0.2406521737575531,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": -0.08815717697143555,
|
| 491 |
+
"logits/rejected": 0.015436625108122826,
|
| 492 |
+
"logps/chosen": -504.43658447265625,
|
| 493 |
+
"logps/rejected": -530.493408203125,
|
| 494 |
+
"loss": 0.2631,
|
| 495 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 496 |
+
"rewards/chosen": -0.11692949384450912,
|
| 497 |
+
"rewards/margins": 0.04244539141654968,
|
| 498 |
+
"rewards/rejected": -0.1593748927116394,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": -0.061802517622709274,
|
| 505 |
+
"logits/rejected": 0.09361619502305984,
|
| 506 |
+
"logps/chosen": -579.513671875,
|
| 507 |
+
"logps/rejected": -639.0809936523438,
|
| 508 |
+
"loss": 0.2755,
|
| 509 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 510 |
+
"rewards/chosen": -0.16077642142772675,
|
| 511 |
+
"rewards/margins": 0.05602121353149414,
|
| 512 |
+
"rewards/rejected": -0.2167976200580597,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": -0.10564370453357697,
|
| 519 |
+
"logits/rejected": 0.02583186700940132,
|
| 520 |
+
"logps/chosen": -590.0396728515625,
|
| 521 |
+
"logps/rejected": -647.909423828125,
|
| 522 |
+
"loss": 0.2786,
|
| 523 |
+
"rewards/accuracies": 0.53125,
|
| 524 |
+
"rewards/chosen": -0.15724439918994904,
|
| 525 |
+
"rewards/margins": 0.0704963356256485,
|
| 526 |
+
"rewards/rejected": -0.22774071991443634,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": -0.10458900034427643,
|
| 533 |
+
"logits/rejected": -0.004534685518592596,
|
| 534 |
+
"logps/chosen": -542.1465454101562,
|
| 535 |
+
"logps/rejected": -573.3040771484375,
|
| 536 |
+
"loss": 0.2668,
|
| 537 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 538 |
+
"rewards/chosen": -0.1385766863822937,
|
| 539 |
+
"rewards/margins": 0.05575231835246086,
|
| 540 |
+
"rewards/rejected": -0.19432899355888367,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": -0.06990720331668854,
|
| 547 |
+
"logits/rejected": 0.01404495257884264,
|
| 548 |
+
"logps/chosen": -505.4917907714844,
|
| 549 |
+
"logps/rejected": -572.2424926757812,
|
| 550 |
+
"loss": 0.2636,
|
| 551 |
+
"rewards/accuracies": 0.46875,
|
| 552 |
+
"rewards/chosen": -0.14204895496368408,
|
| 553 |
+
"rewards/margins": 0.050913404673337936,
|
| 554 |
+
"rewards/rejected": -0.19296236336231232,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": -0.040005024522542953,
|
| 561 |
+
"logits/rejected": 0.017743710428476334,
|
| 562 |
+
"logps/chosen": -548.9078369140625,
|
| 563 |
+
"logps/rejected": -573.68408203125,
|
| 564 |
+
"loss": 0.2815,
|
| 565 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 566 |
+
"rewards/chosen": -0.1460207998752594,
|
| 567 |
+
"rewards/margins": 0.041480742394924164,
|
| 568 |
+
"rewards/rejected": -0.18750153481960297,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": -0.13051895797252655,
|
| 575 |
+
"logits/rejected": 0.012003961019217968,
|
| 576 |
+
"logps/chosen": -543.142578125,
|
| 577 |
+
"logps/rejected": -594.59326171875,
|
| 578 |
+
"loss": 0.2753,
|
| 579 |
+
"rewards/accuracies": 0.512499988079071,
|
| 580 |
+
"rewards/chosen": -0.13953322172164917,
|
| 581 |
+
"rewards/margins": 0.0578032024204731,
|
| 582 |
+
"rewards/rejected": -0.19733640551567078,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": -0.03122936561703682,
|
| 589 |
+
"logits/rejected": 0.010242189280688763,
|
| 590 |
+
"logps/chosen": -564.1265869140625,
|
| 591 |
+
"logps/rejected": -600.2008666992188,
|
| 592 |
+
"loss": 0.2742,
|
| 593 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 594 |
+
"rewards/chosen": -0.14681796729564667,
|
| 595 |
+
"rewards/margins": 0.06189022213220596,
|
| 596 |
+
"rewards/rejected": -0.20870819687843323,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": -0.010301386937499046,
|
| 603 |
+
"logits/rejected": -0.039281733334064484,
|
| 604 |
+
"logps/chosen": -603.3815307617188,
|
| 605 |
+
"logps/rejected": -645.9063110351562,
|
| 606 |
+
"loss": 0.2761,
|
| 607 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 608 |
+
"rewards/chosen": -0.15229162573814392,
|
| 609 |
+
"rewards/margins": 0.06186581775546074,
|
| 610 |
+
"rewards/rejected": -0.21415743231773376,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": -0.08892063051462173,
|
| 617 |
+
"logits/rejected": -0.0773845762014389,
|
| 618 |
+
"logps/chosen": -537.9869995117188,
|
| 619 |
+
"logps/rejected": -586.5262451171875,
|
| 620 |
+
"loss": 0.2721,
|
| 621 |
+
"rewards/accuracies": 0.53125,
|
| 622 |
+
"rewards/chosen": -0.13618162274360657,
|
| 623 |
+
"rewards/margins": 0.06536873430013657,
|
| 624 |
+
"rewards/rejected": -0.20155039429664612,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": -0.03688632696866989,
|
| 631 |
+
"logits/rejected": -0.00927029736340046,
|
| 632 |
+
"logps/chosen": -540.3975219726562,
|
| 633 |
+
"logps/rejected": -622.5618896484375,
|
| 634 |
+
"loss": 0.2622,
|
| 635 |
+
"rewards/accuracies": 0.53125,
|
| 636 |
+
"rewards/chosen": -0.12767064571380615,
|
| 637 |
+
"rewards/margins": 0.07470119744539261,
|
| 638 |
+
"rewards/rejected": -0.20237183570861816,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": -0.05976264923810959,
|
| 645 |
+
"logits/rejected": -0.16253043711185455,
|
| 646 |
+
"logps/chosen": -514.6741943359375,
|
| 647 |
+
"logps/rejected": -578.7728271484375,
|
| 648 |
+
"loss": 0.2588,
|
| 649 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 650 |
+
"rewards/chosen": -0.13386496901512146,
|
| 651 |
+
"rewards/margins": 0.05132218077778816,
|
| 652 |
+
"rewards/rejected": -0.18518713116645813,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": -0.15890637040138245,
|
| 659 |
+
"logits/rejected": -0.05094796419143677,
|
| 660 |
+
"logps/chosen": -516.9619750976562,
|
| 661 |
+
"logps/rejected": -604.88525390625,
|
| 662 |
+
"loss": 0.2671,
|
| 663 |
+
"rewards/accuracies": 0.543749988079071,
|
| 664 |
+
"rewards/chosen": -0.11203358322381973,
|
| 665 |
+
"rewards/margins": 0.08909189701080322,
|
| 666 |
+
"rewards/rejected": -0.20112547278404236,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": -0.17138849198818207,
|
| 673 |
+
"logits/rejected": -0.08313537389039993,
|
| 674 |
+
"logps/chosen": -573.4813232421875,
|
| 675 |
+
"logps/rejected": -608.16552734375,
|
| 676 |
+
"loss": 0.2695,
|
| 677 |
+
"rewards/accuracies": 0.518750011920929,
|
| 678 |
+
"rewards/chosen": -0.13088415563106537,
|
| 679 |
+
"rewards/margins": 0.047856587916612625,
|
| 680 |
+
"rewards/rejected": -0.1787407547235489,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": -0.12412846088409424,
|
| 687 |
+
"logits/rejected": -0.11923656612634659,
|
| 688 |
+
"logps/chosen": -472.38726806640625,
|
| 689 |
+
"logps/rejected": -527.9046020507812,
|
| 690 |
+
"loss": 0.2658,
|
| 691 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 692 |
+
"rewards/chosen": -0.09405693411827087,
|
| 693 |
+
"rewards/margins": 0.057601846754550934,
|
| 694 |
+
"rewards/rejected": -0.1516587734222412,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": -0.11355652660131454,
|
| 701 |
+
"logits/rejected": -0.06184381991624832,
|
| 702 |
+
"logps/chosen": -522.3283081054688,
|
| 703 |
+
"logps/rejected": -575.9847412109375,
|
| 704 |
+
"loss": 0.2596,
|
| 705 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 706 |
+
"rewards/chosen": -0.11173069477081299,
|
| 707 |
+
"rewards/margins": 0.06776181608438492,
|
| 708 |
+
"rewards/rejected": -0.1794925034046173,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": -0.1486915647983551,
|
| 715 |
+
"logits/rejected": -0.1126946210861206,
|
| 716 |
+
"logps/chosen": -472.10009765625,
|
| 717 |
+
"logps/rejected": -565.5072021484375,
|
| 718 |
+
"loss": 0.2578,
|
| 719 |
+
"rewards/accuracies": 0.512499988079071,
|
| 720 |
+
"rewards/chosen": -0.10586412250995636,
|
| 721 |
+
"rewards/margins": 0.08054044097661972,
|
| 722 |
+
"rewards/rejected": -0.1864045411348343,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": -0.07071704417467117,
|
| 729 |
+
"logits/rejected": -0.06895752251148224,
|
| 730 |
+
"logps/chosen": -553.7777709960938,
|
| 731 |
+
"logps/rejected": -641.0071411132812,
|
| 732 |
+
"loss": 0.2755,
|
| 733 |
+
"rewards/accuracies": 0.543749988079071,
|
| 734 |
+
"rewards/chosen": -0.12443629652261734,
|
| 735 |
+
"rewards/margins": 0.08012167364358902,
|
| 736 |
+
"rewards/rejected": -0.20455794036388397,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": -0.07696928828954697,
|
| 743 |
+
"logits/rejected": 0.0007179826498031616,
|
| 744 |
+
"logps/chosen": -548.6107788085938,
|
| 745 |
+
"logps/rejected": -587.250732421875,
|
| 746 |
+
"loss": 0.2776,
|
| 747 |
+
"rewards/accuracies": 0.46875,
|
| 748 |
+
"rewards/chosen": -0.14552563428878784,
|
| 749 |
+
"rewards/margins": 0.04918716475367546,
|
| 750 |
+
"rewards/rejected": -0.1947127878665924,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": -0.07807435840368271,
|
| 757 |
+
"logits/rejected": 0.01831636391580105,
|
| 758 |
+
"logps/chosen": -556.7833251953125,
|
| 759 |
+
"logps/rejected": -576.1497192382812,
|
| 760 |
+
"loss": 0.2592,
|
| 761 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 762 |
+
"rewards/chosen": -0.13193278014659882,
|
| 763 |
+
"rewards/margins": 0.05105576664209366,
|
| 764 |
+
"rewards/rejected": -0.18298853933811188,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.014492440037429333,
|
| 771 |
+
"logits/rejected": -0.10470409691333771,
|
| 772 |
+
"logps/chosen": -520.7554931640625,
|
| 773 |
+
"logps/rejected": -621.583251953125,
|
| 774 |
+
"loss": 0.2589,
|
| 775 |
+
"rewards/accuracies": 0.518750011920929,
|
| 776 |
+
"rewards/chosen": -0.1109011173248291,
|
| 777 |
+
"rewards/margins": 0.08521705865859985,
|
| 778 |
+
"rewards/rejected": -0.19611816108226776,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": -0.09592770040035248,
|
| 785 |
+
"logits/rejected": 0.03173860162496567,
|
| 786 |
+
"logps/chosen": -527.00537109375,
|
| 787 |
+
"logps/rejected": -587.9857177734375,
|
| 788 |
+
"loss": 0.2698,
|
| 789 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 790 |
+
"rewards/chosen": -0.13213616609573364,
|
| 791 |
+
"rewards/margins": 0.07161318510770798,
|
| 792 |
+
"rewards/rejected": -0.2037493735551834,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": -0.08211179822683334,
|
| 799 |
+
"logits/rejected": -0.07464434206485748,
|
| 800 |
+
"logps/chosen": -526.9556884765625,
|
| 801 |
+
"logps/rejected": -597.501708984375,
|
| 802 |
+
"loss": 0.263,
|
| 803 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 804 |
+
"rewards/chosen": -0.12764397263526917,
|
| 805 |
+
"rewards/margins": 0.07685311138629913,
|
| 806 |
+
"rewards/rejected": -0.2044970691204071,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": -0.17138975858688354,
|
| 813 |
+
"logits/rejected": 0.06973910331726074,
|
| 814 |
+
"logps/chosen": -606.2980346679688,
|
| 815 |
+
"logps/rejected": -656.0491943359375,
|
| 816 |
+
"loss": 0.2673,
|
| 817 |
+
"rewards/accuracies": 0.53125,
|
| 818 |
+
"rewards/chosen": -0.13349631428718567,
|
| 819 |
+
"rewards/margins": 0.08181539922952652,
|
| 820 |
+
"rewards/rejected": -0.2153116911649704,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": -0.12237439304590225,
|
| 827 |
+
"logits/rejected": 0.0009635284659452736,
|
| 828 |
+
"logps/chosen": -486.32818603515625,
|
| 829 |
+
"logps/rejected": -522.0555419921875,
|
| 830 |
+
"loss": 0.2611,
|
| 831 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 832 |
+
"rewards/chosen": -0.09265846014022827,
|
| 833 |
+
"rewards/margins": 0.06704847514629364,
|
| 834 |
+
"rewards/rejected": -0.15970692038536072,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": -0.0846022367477417,
|
| 841 |
+
"logits/rejected": 0.020748872309923172,
|
| 842 |
+
"logps/chosen": -515.6177368164062,
|
| 843 |
+
"logps/rejected": -512.121337890625,
|
| 844 |
+
"loss": 0.288,
|
| 845 |
+
"rewards/accuracies": 0.4375,
|
| 846 |
+
"rewards/chosen": -0.10487208515405655,
|
| 847 |
+
"rewards/margins": 0.0322984978556633,
|
| 848 |
+
"rewards/rejected": -0.13717058300971985,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": -0.1460862159729004,
|
| 855 |
+
"logits/rejected": -0.06654468178749084,
|
| 856 |
+
"logps/chosen": -464.4956970214844,
|
| 857 |
+
"logps/rejected": -489.59161376953125,
|
| 858 |
+
"loss": 0.2786,
|
| 859 |
+
"rewards/accuracies": 0.40625,
|
| 860 |
+
"rewards/chosen": -0.09209474176168442,
|
| 861 |
+
"rewards/margins": 0.04379875212907791,
|
| 862 |
+
"rewards/rejected": -0.13589349389076233,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": -0.1410539448261261,
|
| 869 |
+
"logits/rejected": -0.08074741810560226,
|
| 870 |
+
"logps/chosen": -483.46893310546875,
|
| 871 |
+
"logps/rejected": -526.5164794921875,
|
| 872 |
+
"loss": 0.2829,
|
| 873 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 874 |
+
"rewards/chosen": -0.09680439531803131,
|
| 875 |
+
"rewards/margins": 0.06490226835012436,
|
| 876 |
+
"rewards/rejected": -0.16170665621757507,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": -0.09655305743217468,
|
| 883 |
+
"logits/rejected": -0.0762481540441513,
|
| 884 |
+
"logps/chosen": -468.4337463378906,
|
| 885 |
+
"logps/rejected": -525.4623413085938,
|
| 886 |
+
"loss": 0.2619,
|
| 887 |
+
"rewards/accuracies": 0.5,
|
| 888 |
+
"rewards/chosen": -0.08364450931549072,
|
| 889 |
+
"rewards/margins": 0.0691133439540863,
|
| 890 |
+
"rewards/rejected": -0.15275785326957703,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": -0.03865772485733032,
|
| 897 |
+
"logits/rejected": -0.10341192781925201,
|
| 898 |
+
"logps/chosen": -468.88763427734375,
|
| 899 |
+
"logps/rejected": -524.7953491210938,
|
| 900 |
+
"loss": 0.2589,
|
| 901 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 902 |
+
"rewards/chosen": -0.08644279092550278,
|
| 903 |
+
"rewards/margins": 0.0591856949031353,
|
| 904 |
+
"rewards/rejected": -0.14562849700450897,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": -0.08597133308649063,
|
| 911 |
+
"logits/rejected": 0.0006229489808902144,
|
| 912 |
+
"logps/chosen": -556.832275390625,
|
| 913 |
+
"logps/rejected": -577.3524780273438,
|
| 914 |
+
"loss": 0.2942,
|
| 915 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 916 |
+
"rewards/chosen": -0.1141686886548996,
|
| 917 |
+
"rewards/margins": 0.03842983394861221,
|
| 918 |
+
"rewards/rejected": -0.1525985300540924,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": -0.09541022032499313,
|
| 925 |
+
"logits/rejected": -0.05003209039568901,
|
| 926 |
+
"logps/chosen": -469.9234313964844,
|
| 927 |
+
"logps/rejected": -529.8631591796875,
|
| 928 |
+
"loss": 0.2683,
|
| 929 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 930 |
+
"rewards/chosen": -0.09767267853021622,
|
| 931 |
+
"rewards/margins": 0.054049454629421234,
|
| 932 |
+
"rewards/rejected": -0.15172213315963745,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": -0.2083953619003296,
|
| 939 |
+
"logits/rejected": 0.05156536027789116,
|
| 940 |
+
"logps/chosen": -587.299560546875,
|
| 941 |
+
"logps/rejected": -581.7611694335938,
|
| 942 |
+
"loss": 0.2608,
|
| 943 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 944 |
+
"rewards/chosen": -0.10773968696594238,
|
| 945 |
+
"rewards/margins": 0.06141304969787598,
|
| 946 |
+
"rewards/rejected": -0.16915276646614075,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": -0.09526301920413971,
|
| 953 |
+
"logits/rejected": -0.06854981184005737,
|
| 954 |
+
"logps/chosen": -553.5062255859375,
|
| 955 |
+
"logps/rejected": -567.5850219726562,
|
| 956 |
+
"loss": 0.2713,
|
| 957 |
+
"rewards/accuracies": 0.518750011920929,
|
| 958 |
+
"rewards/chosen": -0.10804013162851334,
|
| 959 |
+
"rewards/margins": 0.06674468517303467,
|
| 960 |
+
"rewards/rejected": -0.1747848242521286,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": -0.15921640396118164,
|
| 967 |
+
"logits/rejected": -0.22180967032909393,
|
| 968 |
+
"logps/chosen": -464.23480224609375,
|
| 969 |
+
"logps/rejected": -517.2071533203125,
|
| 970 |
+
"loss": 0.2618,
|
| 971 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 972 |
+
"rewards/chosen": -0.1085701733827591,
|
| 973 |
+
"rewards/margins": 0.06596361845731735,
|
| 974 |
+
"rewards/rejected": -0.17453376948833466,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": -0.2035103738307953,
|
| 981 |
+
"logits/rejected": -0.13756130635738373,
|
| 982 |
+
"logps/chosen": -533.3971557617188,
|
| 983 |
+
"logps/rejected": -562.695068359375,
|
| 984 |
+
"loss": 0.2758,
|
| 985 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 986 |
+
"rewards/chosen": -0.12624426186084747,
|
| 987 |
+
"rewards/margins": 0.05400489643216133,
|
| 988 |
+
"rewards/rejected": -0.1802491694688797,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": -0.19000104069709778,
|
| 995 |
+
"logits/rejected": -0.17901551723480225,
|
| 996 |
+
"logps/chosen": -564.2060546875,
|
| 997 |
+
"logps/rejected": -620.484619140625,
|
| 998 |
+
"loss": 0.2765,
|
| 999 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1000 |
+
"rewards/chosen": -0.12581291794776917,
|
| 1001 |
+
"rewards/margins": 0.06180128455162048,
|
| 1002 |
+
"rewards/rejected": -0.18761418759822845,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": -0.1307680755853653,
|
| 1009 |
+
"logits/rejected": -0.10078835487365723,
|
| 1010 |
+
"logps/chosen": -524.8638916015625,
|
| 1011 |
+
"logps/rejected": -553.104736328125,
|
| 1012 |
+
"loss": 0.2792,
|
| 1013 |
+
"rewards/accuracies": 0.4375,
|
| 1014 |
+
"rewards/chosen": -0.13305291533470154,
|
| 1015 |
+
"rewards/margins": 0.040464796125888824,
|
| 1016 |
+
"rewards/rejected": -0.17351767420768738,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": -0.11268335580825806,
|
| 1023 |
+
"logits/rejected": -0.05942006781697273,
|
| 1024 |
+
"logps/chosen": -497.02325439453125,
|
| 1025 |
+
"logps/rejected": -589.494384765625,
|
| 1026 |
+
"loss": 0.267,
|
| 1027 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1028 |
+
"rewards/chosen": -0.11972874402999878,
|
| 1029 |
+
"rewards/margins": 0.0718456357717514,
|
| 1030 |
+
"rewards/rejected": -0.19157439470291138,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": -0.14758452773094177,
|
| 1037 |
+
"logits/rejected": -0.0012020498979836702,
|
| 1038 |
+
"logps/chosen": -520.2757568359375,
|
| 1039 |
+
"logps/rejected": -585.8750610351562,
|
| 1040 |
+
"loss": 0.2769,
|
| 1041 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 1042 |
+
"rewards/chosen": -0.11923079192638397,
|
| 1043 |
+
"rewards/margins": 0.06183774396777153,
|
| 1044 |
+
"rewards/rejected": -0.1810685396194458,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": -0.1631493866443634,
|
| 1051 |
+
"logits/rejected": -0.14262652397155762,
|
| 1052 |
+
"logps/chosen": -531.8765869140625,
|
| 1053 |
+
"logps/rejected": -570.99365234375,
|
| 1054 |
+
"loss": 0.2753,
|
| 1055 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1056 |
+
"rewards/chosen": -0.11439726501703262,
|
| 1057 |
+
"rewards/margins": 0.05860968679189682,
|
| 1058 |
+
"rewards/rejected": -0.17300695180892944,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": -0.13462567329406738,
|
| 1065 |
+
"logits/rejected": -0.10775252431631088,
|
| 1066 |
+
"logps/chosen": -528.6737060546875,
|
| 1067 |
+
"logps/rejected": -559.4716796875,
|
| 1068 |
+
"loss": 0.2773,
|
| 1069 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1070 |
+
"rewards/chosen": -0.11941119283437729,
|
| 1071 |
+
"rewards/margins": 0.06873499602079391,
|
| 1072 |
+
"rewards/rejected": -0.1881461888551712,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": -0.10648471117019653,
|
| 1079 |
+
"logits/rejected": -0.12774226069450378,
|
| 1080 |
+
"logps/chosen": -540.2073974609375,
|
| 1081 |
+
"logps/rejected": -609.1519165039062,
|
| 1082 |
+
"loss": 0.2717,
|
| 1083 |
+
"rewards/accuracies": 0.53125,
|
| 1084 |
+
"rewards/chosen": -0.1273835450410843,
|
| 1085 |
+
"rewards/margins": 0.07286655902862549,
|
| 1086 |
+
"rewards/rejected": -0.2002500742673874,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": -0.2068806141614914,
|
| 1093 |
+
"logits/rejected": -0.1860518753528595,
|
| 1094 |
+
"logps/chosen": -510.51983642578125,
|
| 1095 |
+
"logps/rejected": -575.1392822265625,
|
| 1096 |
+
"loss": 0.2802,
|
| 1097 |
+
"rewards/accuracies": 0.46875,
|
| 1098 |
+
"rewards/chosen": -0.1164456382393837,
|
| 1099 |
+
"rewards/margins": 0.06441595405340195,
|
| 1100 |
+
"rewards/rejected": -0.18086162209510803,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": -0.23118607699871063,
|
| 1107 |
+
"logits/rejected": 0.012592856772243977,
|
| 1108 |
+
"logps/chosen": -493.88201904296875,
|
| 1109 |
+
"logps/rejected": -535.3624267578125,
|
| 1110 |
+
"loss": 0.2541,
|
| 1111 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1112 |
+
"rewards/chosen": -0.10904928296804428,
|
| 1113 |
+
"rewards/margins": 0.06981517374515533,
|
| 1114 |
+
"rewards/rejected": -0.17886444926261902,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": -0.13056764006614685,
|
| 1121 |
+
"logits/rejected": -0.06715533137321472,
|
| 1122 |
+
"logps/chosen": -526.5809326171875,
|
| 1123 |
+
"logps/rejected": -599.15771484375,
|
| 1124 |
+
"loss": 0.2635,
|
| 1125 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1126 |
+
"rewards/chosen": -0.12021216005086899,
|
| 1127 |
+
"rewards/margins": 0.07990214973688126,
|
| 1128 |
+
"rewards/rejected": -0.20011429488658905,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": -0.2064342051744461,
|
| 1135 |
+
"logits/rejected": -0.1310141682624817,
|
| 1136 |
+
"logps/chosen": -503.92022705078125,
|
| 1137 |
+
"logps/rejected": -535.3073120117188,
|
| 1138 |
+
"loss": 0.2788,
|
| 1139 |
+
"rewards/accuracies": 0.4375,
|
| 1140 |
+
"rewards/chosen": -0.1168203130364418,
|
| 1141 |
+
"rewards/margins": 0.04998582974076271,
|
| 1142 |
+
"rewards/rejected": -0.1668061465024948,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": -0.15658999979496002,
|
| 1149 |
+
"logits/rejected": -0.05465535447001457,
|
| 1150 |
+
"logps/chosen": -493.89666748046875,
|
| 1151 |
+
"logps/rejected": -565.4508056640625,
|
| 1152 |
+
"loss": 0.2593,
|
| 1153 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1154 |
+
"rewards/chosen": -0.11054392158985138,
|
| 1155 |
+
"rewards/margins": 0.062444061040878296,
|
| 1156 |
+
"rewards/rejected": -0.17298798263072968,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": -0.12076146900653839,
|
| 1163 |
+
"logits/rejected": -0.07717995345592499,
|
| 1164 |
+
"logps/chosen": -557.0513305664062,
|
| 1165 |
+
"logps/rejected": -630.1217041015625,
|
| 1166 |
+
"loss": 0.26,
|
| 1167 |
+
"rewards/accuracies": 0.53125,
|
| 1168 |
+
"rewards/chosen": -0.12639924883842468,
|
| 1169 |
+
"rewards/margins": 0.06895993649959564,
|
| 1170 |
+
"rewards/rejected": -0.19535920023918152,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": -0.18750372529029846,
|
| 1177 |
+
"logits/rejected": -0.20195484161376953,
|
| 1178 |
+
"logps/chosen": -431.05615234375,
|
| 1179 |
+
"logps/rejected": -488.2513732910156,
|
| 1180 |
+
"loss": 0.2672,
|
| 1181 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 1182 |
+
"rewards/chosen": -0.0998988226056099,
|
| 1183 |
+
"rewards/margins": 0.054485417902469635,
|
| 1184 |
+
"rewards/rejected": -0.15438422560691833,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": -0.17934174835681915,
|
| 1191 |
+
"logits/rejected": -0.13482218980789185,
|
| 1192 |
+
"logps/chosen": -465.31268310546875,
|
| 1193 |
+
"logps/rejected": -541.5718994140625,
|
| 1194 |
+
"loss": 0.2379,
|
| 1195 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1196 |
+
"rewards/chosen": -0.11106850951910019,
|
| 1197 |
+
"rewards/margins": 0.07404305785894394,
|
| 1198 |
+
"rewards/rejected": -0.18511156737804413,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": -0.16116994619369507,
|
| 1205 |
+
"logits/rejected": -0.06133908033370972,
|
| 1206 |
+
"logps/chosen": -567.8401489257812,
|
| 1207 |
+
"logps/rejected": -617.7798461914062,
|
| 1208 |
+
"loss": 0.2591,
|
| 1209 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 1210 |
+
"rewards/chosen": -0.12380583584308624,
|
| 1211 |
+
"rewards/margins": 0.07460357248783112,
|
| 1212 |
+
"rewards/rejected": -0.19840940833091736,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": -0.09671641886234283,
|
| 1219 |
+
"logits/rejected": -0.10632093995809555,
|
| 1220 |
+
"logps/chosen": -526.3566284179688,
|
| 1221 |
+
"logps/rejected": -554.2623291015625,
|
| 1222 |
+
"loss": 0.271,
|
| 1223 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 1224 |
+
"rewards/chosen": -0.1161075010895729,
|
| 1225 |
+
"rewards/margins": 0.05733795836567879,
|
| 1226 |
+
"rewards/rejected": -0.1734454333782196,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": -0.15584774315357208,
|
| 1233 |
+
"logits/rejected": -0.18242886662483215,
|
| 1234 |
+
"logps/chosen": -535.07373046875,
|
| 1235 |
+
"logps/rejected": -580.4075927734375,
|
| 1236 |
+
"loss": 0.2676,
|
| 1237 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1238 |
+
"rewards/chosen": -0.12142983824014664,
|
| 1239 |
+
"rewards/margins": 0.06167648360133171,
|
| 1240 |
+
"rewards/rejected": -0.18310633301734924,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": -0.09849689900875092,
|
| 1247 |
+
"logits/rejected": -0.10616960376501083,
|
| 1248 |
+
"logps/chosen": -480.7345275878906,
|
| 1249 |
+
"logps/rejected": -568.6452026367188,
|
| 1250 |
+
"loss": 0.2573,
|
| 1251 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1252 |
+
"rewards/chosen": -0.12242833524942398,
|
| 1253 |
+
"rewards/margins": 0.07691850513219833,
|
| 1254 |
+
"rewards/rejected": -0.19934681057929993,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": -0.1931258887052536,
|
| 1261 |
+
"logits/rejected": -0.14527785778045654,
|
| 1262 |
+
"logps/chosen": -525.9476318359375,
|
| 1263 |
+
"logps/rejected": -556.6074829101562,
|
| 1264 |
+
"loss": 0.2718,
|
| 1265 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1266 |
+
"rewards/chosen": -0.1265556812286377,
|
| 1267 |
+
"rewards/margins": 0.05168802663683891,
|
| 1268 |
+
"rewards/rejected": -0.1782437115907669,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": -0.1395512819290161,
|
| 1275 |
+
"logits/rejected": -0.15351735055446625,
|
| 1276 |
+
"logps/chosen": -519.0070190429688,
|
| 1277 |
+
"logps/rejected": -630.4365234375,
|
| 1278 |
+
"loss": 0.25,
|
| 1279 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1280 |
+
"rewards/chosen": -0.12783722579479218,
|
| 1281 |
+
"rewards/margins": 0.08357492834329605,
|
| 1282 |
+
"rewards/rejected": -0.21141216158866882,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": -0.1655835509300232,
|
| 1289 |
+
"logits/rejected": -0.06148504465818405,
|
| 1290 |
+
"logps/chosen": -530.4078979492188,
|
| 1291 |
+
"logps/rejected": -588.1494140625,
|
| 1292 |
+
"loss": 0.2773,
|
| 1293 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1294 |
+
"rewards/chosen": -0.13116273283958435,
|
| 1295 |
+
"rewards/margins": 0.060104191303253174,
|
| 1296 |
+
"rewards/rejected": -0.19126692414283752,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": -0.13306137919425964,
|
| 1303 |
+
"logits/rejected": -0.1015244722366333,
|
| 1304 |
+
"logps/chosen": -540.9669189453125,
|
| 1305 |
+
"logps/rejected": -633.6178588867188,
|
| 1306 |
+
"loss": 0.2619,
|
| 1307 |
+
"rewards/accuracies": 0.53125,
|
| 1308 |
+
"rewards/chosen": -0.13009101152420044,
|
| 1309 |
+
"rewards/margins": 0.07983705401420593,
|
| 1310 |
+
"rewards/rejected": -0.20992806553840637,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": -0.16086629033088684,
|
| 1317 |
+
"logits/rejected": -0.07110301405191422,
|
| 1318 |
+
"logps/chosen": -540.5888061523438,
|
| 1319 |
+
"logps/rejected": -531.308349609375,
|
| 1320 |
+
"loss": 0.2795,
|
| 1321 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 1322 |
+
"rewards/chosen": -0.11827180534601212,
|
| 1323 |
+
"rewards/margins": 0.032559461891651154,
|
| 1324 |
+
"rewards/rejected": -0.15083125233650208,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.275421927202982,
|
| 1332 |
+
"train_runtime": 7850.8319,
|
| 1333 |
+
"train_samples_per_second": 3.821,
|
| 1334 |
+
"train_steps_per_second": 0.119
|
| 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 |
+
}
|