Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May21_12-09-31_gpu4-119-5/events.out.tfevents.1716257541.gpu4-119-5.1638634.0 +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-v17-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-v17-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:ad5f06c5017c16353e1aeb5f0f8830d1cae3c32720768547c14e871260342cae
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1752831537352046,
|
| 4 |
+
"train_runtime": 7846.1192,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.824,
|
| 7 |
+
"train_steps_per_second": 0.119
|
| 8 |
+
}
|
runs/May21_12-09-31_gpu4-119-5/events.out.tfevents.1716257541.gpu4-119-5.1638634.0
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:e9ea42d3069b011125c79b449163caff7260b2c536d56b5b5be710f7971f5df0
|
| 3 |
+
size 64719
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1752831537352046,
|
| 4 |
+
"train_runtime": 7846.1192,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.824,
|
| 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": 0.4053989052772522,
|
| 15 |
+
"logits/rejected": 0.1312936246395111,
|
| 16 |
+
"logps/chosen": -434.00537109375,
|
| 17 |
+
"logps/rejected": -516.5983276367188,
|
| 18 |
+
"loss": 0.1853,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 5.319148936170213e-07,
|
| 28 |
+
"logits/chosen": 0.15346182882785797,
|
| 29 |
+
"logits/rejected": 0.2922114133834839,
|
| 30 |
+
"logps/chosen": -365.6877746582031,
|
| 31 |
+
"logps/rejected": -353.01446533203125,
|
| 32 |
+
"loss": 0.2092,
|
| 33 |
+
"rewards/accuracies": 0.2847222089767456,
|
| 34 |
+
"rewards/chosen": -0.005939984694123268,
|
| 35 |
+
"rewards/margins": -0.0001524988911114633,
|
| 36 |
+
"rewards/rejected": -0.005787486210465431,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.1189204677939415,
|
| 43 |
+
"logits/rejected": 0.20350512862205505,
|
| 44 |
+
"logps/chosen": -340.10516357421875,
|
| 45 |
+
"logps/rejected": -348.26995849609375,
|
| 46 |
+
"loss": 0.2104,
|
| 47 |
+
"rewards/accuracies": 0.28125,
|
| 48 |
+
"rewards/chosen": -0.006609903182834387,
|
| 49 |
+
"rewards/margins": -0.0014991617063060403,
|
| 50 |
+
"rewards/rejected": -0.005110741592943668,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.2546407878398895,
|
| 57 |
+
"logits/rejected": 0.2511681616306305,
|
| 58 |
+
"logps/chosen": -383.5899353027344,
|
| 59 |
+
"logps/rejected": -364.458251953125,
|
| 60 |
+
"loss": 0.2,
|
| 61 |
+
"rewards/accuracies": 0.3687500059604645,
|
| 62 |
+
"rewards/chosen": -0.010028360411524773,
|
| 63 |
+
"rewards/margins": 0.000567590759601444,
|
| 64 |
+
"rewards/rejected": -0.010595952160656452,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.15378129482269287,
|
| 71 |
+
"logits/rejected": 0.27011898159980774,
|
| 72 |
+
"logps/chosen": -402.9029846191406,
|
| 73 |
+
"logps/rejected": -387.1457214355469,
|
| 74 |
+
"loss": 0.2097,
|
| 75 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 76 |
+
"rewards/chosen": -0.018913280218839645,
|
| 77 |
+
"rewards/margins": -0.0008677333826199174,
|
| 78 |
+
"rewards/rejected": -0.018045546486973763,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.23259440064430237,
|
| 85 |
+
"logits/rejected": 0.27333545684814453,
|
| 86 |
+
"logps/chosen": -444.83447265625,
|
| 87 |
+
"logps/rejected": -435.3008728027344,
|
| 88 |
+
"loss": 0.2034,
|
| 89 |
+
"rewards/accuracies": 0.4375,
|
| 90 |
+
"rewards/chosen": -0.039250001311302185,
|
| 91 |
+
"rewards/margins": 0.002604855690151453,
|
| 92 |
+
"rewards/rejected": -0.0418548583984375,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.1691911518573761,
|
| 99 |
+
"logits/rejected": 0.3174379765987396,
|
| 100 |
+
"logps/chosen": -413.50665283203125,
|
| 101 |
+
"logps/rejected": -417.56591796875,
|
| 102 |
+
"loss": 0.2144,
|
| 103 |
+
"rewards/accuracies": 0.40625,
|
| 104 |
+
"rewards/chosen": -0.04588966816663742,
|
| 105 |
+
"rewards/margins": 0.002726958366110921,
|
| 106 |
+
"rewards/rejected": -0.04861662536859512,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.12422730773687363,
|
| 113 |
+
"logits/rejected": 0.2234603464603424,
|
| 114 |
+
"logps/chosen": -361.4434814453125,
|
| 115 |
+
"logps/rejected": -363.685302734375,
|
| 116 |
+
"loss": 0.2037,
|
| 117 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 118 |
+
"rewards/chosen": -0.06797133386135101,
|
| 119 |
+
"rewards/margins": 0.009325895458459854,
|
| 120 |
+
"rewards/rejected": -0.07729722559452057,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.14516139030456543,
|
| 127 |
+
"logits/rejected": 0.25278085470199585,
|
| 128 |
+
"logps/chosen": -403.75347900390625,
|
| 129 |
+
"logps/rejected": -391.7194519042969,
|
| 130 |
+
"loss": 0.2017,
|
| 131 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 132 |
+
"rewards/chosen": -0.10898496210575104,
|
| 133 |
+
"rewards/margins": 0.009633904322981834,
|
| 134 |
+
"rewards/rejected": -0.11861886829137802,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.23768356442451477,
|
| 141 |
+
"logits/rejected": 0.17344684898853302,
|
| 142 |
+
"logps/chosen": -408.779052734375,
|
| 143 |
+
"logps/rejected": -431.6903381347656,
|
| 144 |
+
"loss": 0.1899,
|
| 145 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 146 |
+
"rewards/chosen": -0.15845593810081482,
|
| 147 |
+
"rewards/margins": 0.01751708984375,
|
| 148 |
+
"rewards/rejected": -0.17597301304340363,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.15429627895355225,
|
| 155 |
+
"logits/rejected": 0.1605452001094818,
|
| 156 |
+
"logps/chosen": -438.6952209472656,
|
| 157 |
+
"logps/rejected": -433.0787048339844,
|
| 158 |
+
"loss": 0.1962,
|
| 159 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 160 |
+
"rewards/chosen": -0.2150062620639801,
|
| 161 |
+
"rewards/margins": 0.019437283277511597,
|
| 162 |
+
"rewards/rejected": -0.2344435453414917,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.23242899775505066,
|
| 169 |
+
"logits/rejected": 0.15503418445587158,
|
| 170 |
+
"logps/chosen": -424.6685485839844,
|
| 171 |
+
"logps/rejected": -408.0357666015625,
|
| 172 |
+
"loss": 0.1863,
|
| 173 |
+
"rewards/accuracies": 0.512499988079071,
|
| 174 |
+
"rewards/chosen": -0.055656641721725464,
|
| 175 |
+
"rewards/margins": 0.023944241926074028,
|
| 176 |
+
"rewards/rejected": -0.07960088551044464,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.09133955091238022,
|
| 183 |
+
"logits/rejected": 0.2611747682094574,
|
| 184 |
+
"logps/chosen": -403.81085205078125,
|
| 185 |
+
"logps/rejected": -435.2984924316406,
|
| 186 |
+
"loss": 0.1903,
|
| 187 |
+
"rewards/accuracies": 0.5625,
|
| 188 |
+
"rewards/chosen": 0.10940422862768173,
|
| 189 |
+
"rewards/margins": 0.041554711759090424,
|
| 190 |
+
"rewards/rejected": 0.06784951686859131,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.16850045323371887,
|
| 197 |
+
"logits/rejected": 0.2994873821735382,
|
| 198 |
+
"logps/chosen": -397.17254638671875,
|
| 199 |
+
"logps/rejected": -387.06561279296875,
|
| 200 |
+
"loss": 0.1881,
|
| 201 |
+
"rewards/accuracies": 0.512499988079071,
|
| 202 |
+
"rewards/chosen": 0.15394046902656555,
|
| 203 |
+
"rewards/margins": 0.0355982705950737,
|
| 204 |
+
"rewards/rejected": 0.11834220588207245,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.1726590096950531,
|
| 211 |
+
"logits/rejected": 0.2367965281009674,
|
| 212 |
+
"logps/chosen": -373.75689697265625,
|
| 213 |
+
"logps/rejected": -357.42108154296875,
|
| 214 |
+
"loss": 0.1843,
|
| 215 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 216 |
+
"rewards/chosen": 0.10395370423793793,
|
| 217 |
+
"rewards/margins": 0.031282939016819,
|
| 218 |
+
"rewards/rejected": 0.07267077267169952,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.04663983732461929,
|
| 225 |
+
"logits/rejected": 0.09915662556886673,
|
| 226 |
+
"logps/chosen": -379.2816162109375,
|
| 227 |
+
"logps/rejected": -385.98834228515625,
|
| 228 |
+
"loss": 0.1811,
|
| 229 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 230 |
+
"rewards/chosen": 0.03478062525391579,
|
| 231 |
+
"rewards/margins": 0.03926830738782883,
|
| 232 |
+
"rewards/rejected": -0.004487680736929178,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.1232941746711731,
|
| 239 |
+
"logits/rejected": 0.20809748768806458,
|
| 240 |
+
"logps/chosen": -426.62841796875,
|
| 241 |
+
"logps/rejected": -422.14910888671875,
|
| 242 |
+
"loss": 0.1715,
|
| 243 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 244 |
+
"rewards/chosen": -0.03437420353293419,
|
| 245 |
+
"rewards/margins": 0.0738130509853363,
|
| 246 |
+
"rewards/rejected": -0.1081872433423996,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.07926517724990845,
|
| 253 |
+
"logits/rejected": 0.25820231437683105,
|
| 254 |
+
"logps/chosen": -460.07012939453125,
|
| 255 |
+
"logps/rejected": -439.01495361328125,
|
| 256 |
+
"loss": 0.2022,
|
| 257 |
+
"rewards/accuracies": 0.53125,
|
| 258 |
+
"rewards/chosen": -0.19370847940444946,
|
| 259 |
+
"rewards/margins": 0.05930668115615845,
|
| 260 |
+
"rewards/rejected": -0.2530151605606079,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.19027003645896912,
|
| 267 |
+
"logits/rejected": 0.20081575214862823,
|
| 268 |
+
"logps/chosen": -411.0907287597656,
|
| 269 |
+
"logps/rejected": -418.31689453125,
|
| 270 |
+
"loss": 0.168,
|
| 271 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 272 |
+
"rewards/chosen": -0.30076223611831665,
|
| 273 |
+
"rewards/margins": 0.07709387689828873,
|
| 274 |
+
"rewards/rejected": -0.3778560757637024,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.1264984905719757,
|
| 281 |
+
"logits/rejected": 0.21260645985603333,
|
| 282 |
+
"logps/chosen": -527.2296752929688,
|
| 283 |
+
"logps/rejected": -502.3099670410156,
|
| 284 |
+
"loss": 0.1784,
|
| 285 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 286 |
+
"rewards/chosen": -0.43060359358787537,
|
| 287 |
+
"rewards/margins": 0.06492508202791214,
|
| 288 |
+
"rewards/rejected": -0.4955286979675293,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.061636537313461304,
|
| 295 |
+
"logits/rejected": 0.19780707359313965,
|
| 296 |
+
"logps/chosen": -453.3473205566406,
|
| 297 |
+
"logps/rejected": -477.33819580078125,
|
| 298 |
+
"loss": 0.1818,
|
| 299 |
+
"rewards/accuracies": 0.543749988079071,
|
| 300 |
+
"rewards/chosen": -0.4919506013393402,
|
| 301 |
+
"rewards/margins": 0.06804502010345459,
|
| 302 |
+
"rewards/rejected": -0.559995710849762,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.12850946187973022,
|
| 309 |
+
"logits/rejected": 0.12981989979743958,
|
| 310 |
+
"logps/chosen": -447.4049377441406,
|
| 311 |
+
"logps/rejected": -458.405029296875,
|
| 312 |
+
"loss": 0.1796,
|
| 313 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 314 |
+
"rewards/chosen": -0.4579945504665375,
|
| 315 |
+
"rewards/margins": 0.07319770753383636,
|
| 316 |
+
"rewards/rejected": -0.5311923027038574,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.12648232281208038,
|
| 323 |
+
"logits/rejected": 0.10291828960180283,
|
| 324 |
+
"logps/chosen": -447.4896545410156,
|
| 325 |
+
"logps/rejected": -447.23248291015625,
|
| 326 |
+
"loss": 0.1804,
|
| 327 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 328 |
+
"rewards/chosen": -0.4558301568031311,
|
| 329 |
+
"rewards/margins": 0.051274996250867844,
|
| 330 |
+
"rewards/rejected": -0.5071052312850952,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": 0.11354929208755493,
|
| 337 |
+
"logits/rejected": 0.13758793473243713,
|
| 338 |
+
"logps/chosen": -435.9432678222656,
|
| 339 |
+
"logps/rejected": -443.25250244140625,
|
| 340 |
+
"loss": 0.1821,
|
| 341 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 342 |
+
"rewards/chosen": -0.36004215478897095,
|
| 343 |
+
"rewards/margins": 0.06442644447088242,
|
| 344 |
+
"rewards/rejected": -0.42446860671043396,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": -0.01750967465341091,
|
| 351 |
+
"logits/rejected": 0.15084341168403625,
|
| 352 |
+
"logps/chosen": -406.10284423828125,
|
| 353 |
+
"logps/rejected": -415.41131591796875,
|
| 354 |
+
"loss": 0.173,
|
| 355 |
+
"rewards/accuracies": 0.518750011920929,
|
| 356 |
+
"rewards/chosen": -0.2852724492549896,
|
| 357 |
+
"rewards/margins": 0.060403019189834595,
|
| 358 |
+
"rewards/rejected": -0.3456754982471466,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": 0.08206398785114288,
|
| 365 |
+
"logits/rejected": 0.1491158902645111,
|
| 366 |
+
"logps/chosen": -441.6056213378906,
|
| 367 |
+
"logps/rejected": -435.2107849121094,
|
| 368 |
+
"loss": 0.1863,
|
| 369 |
+
"rewards/accuracies": 0.5,
|
| 370 |
+
"rewards/chosen": -0.2744644582271576,
|
| 371 |
+
"rewards/margins": 0.07761115580797195,
|
| 372 |
+
"rewards/rejected": -0.35207563638687134,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": 0.07012276351451874,
|
| 379 |
+
"logits/rejected": 0.11525042355060577,
|
| 380 |
+
"logps/chosen": -459.88323974609375,
|
| 381 |
+
"logps/rejected": -479.2359313964844,
|
| 382 |
+
"loss": 0.17,
|
| 383 |
+
"rewards/accuracies": 0.543749988079071,
|
| 384 |
+
"rewards/chosen": -0.2863777279853821,
|
| 385 |
+
"rewards/margins": 0.06567540019750595,
|
| 386 |
+
"rewards/rejected": -0.35205310583114624,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": 0.03542683273553848,
|
| 393 |
+
"logits/rejected": 0.08359168469905853,
|
| 394 |
+
"logps/chosen": -459.03814697265625,
|
| 395 |
+
"logps/rejected": -487.94781494140625,
|
| 396 |
+
"loss": 0.1683,
|
| 397 |
+
"rewards/accuracies": 0.574999988079071,
|
| 398 |
+
"rewards/chosen": -0.25155481696128845,
|
| 399 |
+
"rewards/margins": 0.09583600610494614,
|
| 400 |
+
"rewards/rejected": -0.3473908305168152,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": 0.03823712840676308,
|
| 407 |
+
"logits/rejected": 0.12090680748224258,
|
| 408 |
+
"logps/chosen": -434.3282165527344,
|
| 409 |
+
"logps/rejected": -428.10675048828125,
|
| 410 |
+
"loss": 0.1758,
|
| 411 |
+
"rewards/accuracies": 0.518750011920929,
|
| 412 |
+
"rewards/chosen": -0.2617419362068176,
|
| 413 |
+
"rewards/margins": 0.07895456254482269,
|
| 414 |
+
"rewards/rejected": -0.3406964838504791,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": 0.04959043115377426,
|
| 421 |
+
"logits/rejected": 0.1204204112291336,
|
| 422 |
+
"logps/chosen": -440.5345764160156,
|
| 423 |
+
"logps/rejected": -477.7173767089844,
|
| 424 |
+
"loss": 0.184,
|
| 425 |
+
"rewards/accuracies": 0.53125,
|
| 426 |
+
"rewards/chosen": -0.37586796283721924,
|
| 427 |
+
"rewards/margins": 0.07159671187400818,
|
| 428 |
+
"rewards/rejected": -0.44746464490890503,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": 0.09089604020118713,
|
| 435 |
+
"logits/rejected": 0.0841570645570755,
|
| 436 |
+
"logps/chosen": -469.25775146484375,
|
| 437 |
+
"logps/rejected": -441.3363342285156,
|
| 438 |
+
"loss": 0.1693,
|
| 439 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 440 |
+
"rewards/chosen": -0.4600369930267334,
|
| 441 |
+
"rewards/margins": 0.07286399602890015,
|
| 442 |
+
"rewards/rejected": -0.5329009294509888,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": -0.010215234942734241,
|
| 449 |
+
"logits/rejected": 0.14281333982944489,
|
| 450 |
+
"logps/chosen": -418.6227111816406,
|
| 451 |
+
"logps/rejected": -425.4488830566406,
|
| 452 |
+
"loss": 0.1808,
|
| 453 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 454 |
+
"rewards/chosen": -0.39024704694747925,
|
| 455 |
+
"rewards/margins": 0.07213394343852997,
|
| 456 |
+
"rewards/rejected": -0.462380975484848,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": 0.05900254100561142,
|
| 463 |
+
"logits/rejected": 0.11304068565368652,
|
| 464 |
+
"logps/chosen": -415.36883544921875,
|
| 465 |
+
"logps/rejected": -410.0850524902344,
|
| 466 |
+
"loss": 0.1688,
|
| 467 |
+
"rewards/accuracies": 0.543749988079071,
|
| 468 |
+
"rewards/chosen": -0.3306947648525238,
|
| 469 |
+
"rewards/margins": 0.06759382784366608,
|
| 470 |
+
"rewards/rejected": -0.3982886075973511,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": 0.09281224012374878,
|
| 477 |
+
"logits/rejected": 0.10557293891906738,
|
| 478 |
+
"logps/chosen": -458.1168518066406,
|
| 479 |
+
"logps/rejected": -433.6602478027344,
|
| 480 |
+
"loss": 0.1818,
|
| 481 |
+
"rewards/accuracies": 0.518750011920929,
|
| 482 |
+
"rewards/chosen": -0.2099827080965042,
|
| 483 |
+
"rewards/margins": 0.07166289538145065,
|
| 484 |
+
"rewards/rejected": -0.28164559602737427,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": 0.1274840533733368,
|
| 491 |
+
"logits/rejected": 0.1528143584728241,
|
| 492 |
+
"logps/chosen": -436.2671813964844,
|
| 493 |
+
"logps/rejected": -449.423095703125,
|
| 494 |
+
"loss": 0.1728,
|
| 495 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 496 |
+
"rewards/chosen": -0.16712762415409088,
|
| 497 |
+
"rewards/margins": 0.0913640707731247,
|
| 498 |
+
"rewards/rejected": -0.2584916949272156,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.03427785634994507,
|
| 505 |
+
"logits/rejected": 0.1746084988117218,
|
| 506 |
+
"logps/chosen": -448.252197265625,
|
| 507 |
+
"logps/rejected": -450.52459716796875,
|
| 508 |
+
"loss": 0.1746,
|
| 509 |
+
"rewards/accuracies": 0.518750011920929,
|
| 510 |
+
"rewards/chosen": -0.1110633835196495,
|
| 511 |
+
"rewards/margins": 0.07623620331287384,
|
| 512 |
+
"rewards/rejected": -0.18729960918426514,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": -0.044000182300806046,
|
| 519 |
+
"logits/rejected": 0.06577601283788681,
|
| 520 |
+
"logps/chosen": -455.25042724609375,
|
| 521 |
+
"logps/rejected": -427.7881774902344,
|
| 522 |
+
"loss": 0.1644,
|
| 523 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 524 |
+
"rewards/chosen": -0.048846274614334106,
|
| 525 |
+
"rewards/margins": 0.08700191974639893,
|
| 526 |
+
"rewards/rejected": -0.13584819436073303,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": 0.07364512979984283,
|
| 533 |
+
"logits/rejected": 0.08710888028144836,
|
| 534 |
+
"logps/chosen": -406.98309326171875,
|
| 535 |
+
"logps/rejected": -417.3194274902344,
|
| 536 |
+
"loss": 0.1731,
|
| 537 |
+
"rewards/accuracies": 0.5,
|
| 538 |
+
"rewards/chosen": -0.07288642972707748,
|
| 539 |
+
"rewards/margins": 0.06538988649845123,
|
| 540 |
+
"rewards/rejected": -0.13827630877494812,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": -0.05436893552541733,
|
| 547 |
+
"logits/rejected": 0.11040735244750977,
|
| 548 |
+
"logps/chosen": -409.92462158203125,
|
| 549 |
+
"logps/rejected": -393.9139404296875,
|
| 550 |
+
"loss": 0.1577,
|
| 551 |
+
"rewards/accuracies": 0.512499988079071,
|
| 552 |
+
"rewards/chosen": -0.05880141258239746,
|
| 553 |
+
"rewards/margins": 0.08271567523479462,
|
| 554 |
+
"rewards/rejected": -0.14151708781719208,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": -0.007267399691045284,
|
| 561 |
+
"logits/rejected": 0.06522424519062042,
|
| 562 |
+
"logps/chosen": -431.5768127441406,
|
| 563 |
+
"logps/rejected": -446.33001708984375,
|
| 564 |
+
"loss": 0.1801,
|
| 565 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 566 |
+
"rewards/chosen": -0.10045109689235687,
|
| 567 |
+
"rewards/margins": 0.06214982271194458,
|
| 568 |
+
"rewards/rejected": -0.16260093450546265,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": 0.07450960576534271,
|
| 575 |
+
"logits/rejected": 0.09937725961208344,
|
| 576 |
+
"logps/chosen": -435.92291259765625,
|
| 577 |
+
"logps/rejected": -440.31182861328125,
|
| 578 |
+
"loss": 0.1738,
|
| 579 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 580 |
+
"rewards/chosen": -0.1277085244655609,
|
| 581 |
+
"rewards/margins": 0.07721880823373795,
|
| 582 |
+
"rewards/rejected": -0.20492735505104065,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": 0.03635771945118904,
|
| 589 |
+
"logits/rejected": 0.04270925745368004,
|
| 590 |
+
"logps/chosen": -437.2557067871094,
|
| 591 |
+
"logps/rejected": -465.94915771484375,
|
| 592 |
+
"loss": 0.1651,
|
| 593 |
+
"rewards/accuracies": 0.5625,
|
| 594 |
+
"rewards/chosen": -0.15446950495243073,
|
| 595 |
+
"rewards/margins": 0.09225080162286758,
|
| 596 |
+
"rewards/rejected": -0.24672028422355652,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": 0.0480308011174202,
|
| 603 |
+
"logits/rejected": 0.09423025697469711,
|
| 604 |
+
"logps/chosen": -461.2041931152344,
|
| 605 |
+
"logps/rejected": -467.91644287109375,
|
| 606 |
+
"loss": 0.1701,
|
| 607 |
+
"rewards/accuracies": 0.543749988079071,
|
| 608 |
+
"rewards/chosen": -0.14544199407100677,
|
| 609 |
+
"rewards/margins": 0.09961853921413422,
|
| 610 |
+
"rewards/rejected": -0.245060533285141,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": 0.0305793434381485,
|
| 617 |
+
"logits/rejected": 0.033555738627910614,
|
| 618 |
+
"logps/chosen": -377.18719482421875,
|
| 619 |
+
"logps/rejected": -382.844970703125,
|
| 620 |
+
"loss": 0.1698,
|
| 621 |
+
"rewards/accuracies": 0.53125,
|
| 622 |
+
"rewards/chosen": -0.09203015267848969,
|
| 623 |
+
"rewards/margins": 0.07604523003101349,
|
| 624 |
+
"rewards/rejected": -0.16807539761066437,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": 0.046750448644161224,
|
| 631 |
+
"logits/rejected": 0.07448974251747131,
|
| 632 |
+
"logps/chosen": -459.547607421875,
|
| 633 |
+
"logps/rejected": -455.531005859375,
|
| 634 |
+
"loss": 0.175,
|
| 635 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 636 |
+
"rewards/chosen": -0.08039159327745438,
|
| 637 |
+
"rewards/margins": 0.0626746192574501,
|
| 638 |
+
"rewards/rejected": -0.14306621253490448,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": 0.03396008908748627,
|
| 645 |
+
"logits/rejected": 0.09014374762773514,
|
| 646 |
+
"logps/chosen": -429.5635681152344,
|
| 647 |
+
"logps/rejected": -421.2688903808594,
|
| 648 |
+
"loss": 0.1802,
|
| 649 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 650 |
+
"rewards/chosen": -0.039100803434848785,
|
| 651 |
+
"rewards/margins": 0.08359581232070923,
|
| 652 |
+
"rewards/rejected": -0.12269661575555801,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": 0.04828561842441559,
|
| 659 |
+
"logits/rejected": 0.11091510206460953,
|
| 660 |
+
"logps/chosen": -445.12713623046875,
|
| 661 |
+
"logps/rejected": -433.92047119140625,
|
| 662 |
+
"loss": 0.1619,
|
| 663 |
+
"rewards/accuracies": 0.5625,
|
| 664 |
+
"rewards/chosen": -0.06680645048618317,
|
| 665 |
+
"rewards/margins": 0.0745815858244896,
|
| 666 |
+
"rewards/rejected": -0.14138804376125336,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": 0.04593321308493614,
|
| 673 |
+
"logits/rejected": 0.07564611732959747,
|
| 674 |
+
"logps/chosen": -422.21954345703125,
|
| 675 |
+
"logps/rejected": -430.91802978515625,
|
| 676 |
+
"loss": 0.1732,
|
| 677 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 678 |
+
"rewards/chosen": -0.07942485064268112,
|
| 679 |
+
"rewards/margins": 0.09848260879516602,
|
| 680 |
+
"rewards/rejected": -0.17790746688842773,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": -0.00015009715571068227,
|
| 687 |
+
"logits/rejected": 0.11992751061916351,
|
| 688 |
+
"logps/chosen": -397.8226318359375,
|
| 689 |
+
"logps/rejected": -412.5755920410156,
|
| 690 |
+
"loss": 0.1662,
|
| 691 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 692 |
+
"rewards/chosen": -0.09762930124998093,
|
| 693 |
+
"rewards/margins": 0.10028882324695587,
|
| 694 |
+
"rewards/rejected": -0.1979181170463562,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": 0.08348871767520905,
|
| 701 |
+
"logits/rejected": 0.09916739165782928,
|
| 702 |
+
"logps/chosen": -390.0538330078125,
|
| 703 |
+
"logps/rejected": -407.1832275390625,
|
| 704 |
+
"loss": 0.1732,
|
| 705 |
+
"rewards/accuracies": 0.5,
|
| 706 |
+
"rewards/chosen": -0.12354443222284317,
|
| 707 |
+
"rewards/margins": 0.10041115432977676,
|
| 708 |
+
"rewards/rejected": -0.22395558655261993,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": 0.0067026736214756966,
|
| 715 |
+
"logits/rejected": -0.01416114903986454,
|
| 716 |
+
"logps/chosen": -386.2361755371094,
|
| 717 |
+
"logps/rejected": -397.430908203125,
|
| 718 |
+
"loss": 0.1684,
|
| 719 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 720 |
+
"rewards/chosen": -0.16371376812458038,
|
| 721 |
+
"rewards/margins": 0.06288306415081024,
|
| 722 |
+
"rewards/rejected": -0.22659683227539062,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": 0.03226105123758316,
|
| 729 |
+
"logits/rejected": 0.08519762009382248,
|
| 730 |
+
"logps/chosen": -463.94879150390625,
|
| 731 |
+
"logps/rejected": -457.156982421875,
|
| 732 |
+
"loss": 0.1738,
|
| 733 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 734 |
+
"rewards/chosen": -0.1887294501066208,
|
| 735 |
+
"rewards/margins": 0.07099872827529907,
|
| 736 |
+
"rewards/rejected": -0.25972819328308105,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": -0.030474770814180374,
|
| 743 |
+
"logits/rejected": 0.06743954867124557,
|
| 744 |
+
"logps/chosen": -430.6739196777344,
|
| 745 |
+
"logps/rejected": -406.80535888671875,
|
| 746 |
+
"loss": 0.1712,
|
| 747 |
+
"rewards/accuracies": 0.5,
|
| 748 |
+
"rewards/chosen": -0.1928265392780304,
|
| 749 |
+
"rewards/margins": 0.08770117908716202,
|
| 750 |
+
"rewards/rejected": -0.2805277109146118,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": 0.1015111431479454,
|
| 757 |
+
"logits/rejected": 0.06599382311105728,
|
| 758 |
+
"logps/chosen": -437.9898986816406,
|
| 759 |
+
"logps/rejected": -436.36004638671875,
|
| 760 |
+
"loss": 0.179,
|
| 761 |
+
"rewards/accuracies": 0.53125,
|
| 762 |
+
"rewards/chosen": -0.2587732672691345,
|
| 763 |
+
"rewards/margins": 0.0716363936662674,
|
| 764 |
+
"rewards/rejected": -0.3304096758365631,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.04144694283604622,
|
| 771 |
+
"logits/rejected": 0.055634863674640656,
|
| 772 |
+
"logps/chosen": -430.6463317871094,
|
| 773 |
+
"logps/rejected": -424.1119079589844,
|
| 774 |
+
"loss": 0.1712,
|
| 775 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 776 |
+
"rewards/chosen": -0.26249006390571594,
|
| 777 |
+
"rewards/margins": 0.08809027820825577,
|
| 778 |
+
"rewards/rejected": -0.3505803048610687,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": -0.03823351487517357,
|
| 785 |
+
"logits/rejected": 0.08283025026321411,
|
| 786 |
+
"logps/chosen": -450.2481384277344,
|
| 787 |
+
"logps/rejected": -451.69097900390625,
|
| 788 |
+
"loss": 0.1741,
|
| 789 |
+
"rewards/accuracies": 0.518750011920929,
|
| 790 |
+
"rewards/chosen": -0.31970635056495667,
|
| 791 |
+
"rewards/margins": 0.07840566337108612,
|
| 792 |
+
"rewards/rejected": -0.3981119990348816,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": 0.04782441258430481,
|
| 799 |
+
"logits/rejected": 0.0727071687579155,
|
| 800 |
+
"logps/chosen": -412.89306640625,
|
| 801 |
+
"logps/rejected": -450.1448669433594,
|
| 802 |
+
"loss": 0.1816,
|
| 803 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 804 |
+
"rewards/chosen": -0.3479355573654175,
|
| 805 |
+
"rewards/margins": 0.07213512808084488,
|
| 806 |
+
"rewards/rejected": -0.42007070779800415,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": -0.041085027158260345,
|
| 813 |
+
"logits/rejected": -0.010372793301939964,
|
| 814 |
+
"logps/chosen": -402.28997802734375,
|
| 815 |
+
"logps/rejected": -407.7055969238281,
|
| 816 |
+
"loss": 0.1809,
|
| 817 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 818 |
+
"rewards/chosen": -0.3540458381175995,
|
| 819 |
+
"rewards/margins": 0.060313619673252106,
|
| 820 |
+
"rewards/rejected": -0.4143594801425934,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": 0.023486686870455742,
|
| 827 |
+
"logits/rejected": 0.07347628474235535,
|
| 828 |
+
"logps/chosen": -444.597412109375,
|
| 829 |
+
"logps/rejected": -440.24407958984375,
|
| 830 |
+
"loss": 0.1686,
|
| 831 |
+
"rewards/accuracies": 0.53125,
|
| 832 |
+
"rewards/chosen": -0.34095701575279236,
|
| 833 |
+
"rewards/margins": 0.08776627480983734,
|
| 834 |
+
"rewards/rejected": -0.4287233352661133,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": 0.0032510061282664537,
|
| 841 |
+
"logits/rejected": 0.12992344796657562,
|
| 842 |
+
"logps/chosen": -465.0745544433594,
|
| 843 |
+
"logps/rejected": -462.6073303222656,
|
| 844 |
+
"loss": 0.1583,
|
| 845 |
+
"rewards/accuracies": 0.59375,
|
| 846 |
+
"rewards/chosen": -0.3434141278266907,
|
| 847 |
+
"rewards/margins": 0.08694170415401459,
|
| 848 |
+
"rewards/rejected": -0.43035584688186646,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": -0.010292215272784233,
|
| 855 |
+
"logits/rejected": 0.03650585561990738,
|
| 856 |
+
"logps/chosen": -390.76690673828125,
|
| 857 |
+
"logps/rejected": -422.77105712890625,
|
| 858 |
+
"loss": 0.1712,
|
| 859 |
+
"rewards/accuracies": 0.518750011920929,
|
| 860 |
+
"rewards/chosen": -0.3311789929866791,
|
| 861 |
+
"rewards/margins": 0.07950376719236374,
|
| 862 |
+
"rewards/rejected": -0.410682737827301,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": -0.03925107792019844,
|
| 869 |
+
"logits/rejected": -0.04231791943311691,
|
| 870 |
+
"logps/chosen": -445.1822204589844,
|
| 871 |
+
"logps/rejected": -434.329833984375,
|
| 872 |
+
"loss": 0.1719,
|
| 873 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 874 |
+
"rewards/chosen": -0.3707120418548584,
|
| 875 |
+
"rewards/margins": 0.09252772480249405,
|
| 876 |
+
"rewards/rejected": -0.46323972940444946,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": 0.06463605910539627,
|
| 883 |
+
"logits/rejected": -0.027300477027893066,
|
| 884 |
+
"logps/chosen": -431.5687561035156,
|
| 885 |
+
"logps/rejected": -470.56072998046875,
|
| 886 |
+
"loss": 0.1793,
|
| 887 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 888 |
+
"rewards/chosen": -0.37444019317626953,
|
| 889 |
+
"rewards/margins": 0.07550361007452011,
|
| 890 |
+
"rewards/rejected": -0.44994378089904785,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": -0.04705502465367317,
|
| 897 |
+
"logits/rejected": -0.02023206278681755,
|
| 898 |
+
"logps/chosen": -402.87274169921875,
|
| 899 |
+
"logps/rejected": -393.464599609375,
|
| 900 |
+
"loss": 0.1722,
|
| 901 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 902 |
+
"rewards/chosen": -0.3044665455818176,
|
| 903 |
+
"rewards/margins": 0.08127270638942719,
|
| 904 |
+
"rewards/rejected": -0.385739266872406,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": -0.03925855830311775,
|
| 911 |
+
"logits/rejected": 0.015137474052608013,
|
| 912 |
+
"logps/chosen": -417.5736389160156,
|
| 913 |
+
"logps/rejected": -411.40386962890625,
|
| 914 |
+
"loss": 0.1753,
|
| 915 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 916 |
+
"rewards/chosen": -0.2832847535610199,
|
| 917 |
+
"rewards/margins": 0.10071472823619843,
|
| 918 |
+
"rewards/rejected": -0.38399946689605713,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": -0.03505668044090271,
|
| 925 |
+
"logits/rejected": 0.16136914491653442,
|
| 926 |
+
"logps/chosen": -457.20556640625,
|
| 927 |
+
"logps/rejected": -451.82073974609375,
|
| 928 |
+
"loss": 0.166,
|
| 929 |
+
"rewards/accuracies": 0.59375,
|
| 930 |
+
"rewards/chosen": -0.3379427492618561,
|
| 931 |
+
"rewards/margins": 0.10498092323541641,
|
| 932 |
+
"rewards/rejected": -0.4429236948490143,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": -0.060994476079940796,
|
| 939 |
+
"logits/rejected": 0.0816785916686058,
|
| 940 |
+
"logps/chosen": -460.37445068359375,
|
| 941 |
+
"logps/rejected": -450.03155517578125,
|
| 942 |
+
"loss": 0.174,
|
| 943 |
+
"rewards/accuracies": 0.550000011920929,
|
| 944 |
+
"rewards/chosen": -0.3193809986114502,
|
| 945 |
+
"rewards/margins": 0.07850383222103119,
|
| 946 |
+
"rewards/rejected": -0.3978848159313202,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": 0.09993238747119904,
|
| 953 |
+
"logits/rejected": 0.04898153617978096,
|
| 954 |
+
"logps/chosen": -418.4270935058594,
|
| 955 |
+
"logps/rejected": -422.74822998046875,
|
| 956 |
+
"loss": 0.1796,
|
| 957 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 958 |
+
"rewards/chosen": -0.29177647829055786,
|
| 959 |
+
"rewards/margins": 0.07586276531219482,
|
| 960 |
+
"rewards/rejected": -0.3676392436027527,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": 0.04208558052778244,
|
| 967 |
+
"logits/rejected": 0.044306449592113495,
|
| 968 |
+
"logps/chosen": -393.4234924316406,
|
| 969 |
+
"logps/rejected": -386.6611633300781,
|
| 970 |
+
"loss": 0.1715,
|
| 971 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 972 |
+
"rewards/chosen": -0.23296888172626495,
|
| 973 |
+
"rewards/margins": 0.06498309224843979,
|
| 974 |
+
"rewards/rejected": -0.29795199632644653,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": -0.03271818161010742,
|
| 981 |
+
"logits/rejected": 0.07850229740142822,
|
| 982 |
+
"logps/chosen": -422.83489990234375,
|
| 983 |
+
"logps/rejected": -424.16876220703125,
|
| 984 |
+
"loss": 0.1734,
|
| 985 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 986 |
+
"rewards/chosen": -0.26918911933898926,
|
| 987 |
+
"rewards/margins": 0.06875598430633545,
|
| 988 |
+
"rewards/rejected": -0.3379451334476471,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": -0.053741514682769775,
|
| 995 |
+
"logits/rejected": 0.01618141494691372,
|
| 996 |
+
"logps/chosen": -423.0733947753906,
|
| 997 |
+
"logps/rejected": -434.5904235839844,
|
| 998 |
+
"loss": 0.1454,
|
| 999 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 1000 |
+
"rewards/chosen": -0.2766970098018646,
|
| 1001 |
+
"rewards/margins": 0.07641127705574036,
|
| 1002 |
+
"rewards/rejected": -0.353108286857605,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": -0.0247728880494833,
|
| 1009 |
+
"logits/rejected": 0.08638174831867218,
|
| 1010 |
+
"logps/chosen": -435.94366455078125,
|
| 1011 |
+
"logps/rejected": -447.54522705078125,
|
| 1012 |
+
"loss": 0.1705,
|
| 1013 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 1014 |
+
"rewards/chosen": -0.26050230860710144,
|
| 1015 |
+
"rewards/margins": 0.10260170698165894,
|
| 1016 |
+
"rewards/rejected": -0.3631040155887604,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": 0.014270253479480743,
|
| 1023 |
+
"logits/rejected": 0.035499878227710724,
|
| 1024 |
+
"logps/chosen": -450.578369140625,
|
| 1025 |
+
"logps/rejected": -448.53533935546875,
|
| 1026 |
+
"loss": 0.1607,
|
| 1027 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 1028 |
+
"rewards/chosen": -0.3028029799461365,
|
| 1029 |
+
"rewards/margins": 0.088174968957901,
|
| 1030 |
+
"rewards/rejected": -0.3909779191017151,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": 0.037296146154403687,
|
| 1037 |
+
"logits/rejected": 0.01444760151207447,
|
| 1038 |
+
"logps/chosen": -452.60845947265625,
|
| 1039 |
+
"logps/rejected": -439.6041564941406,
|
| 1040 |
+
"loss": 0.1698,
|
| 1041 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1042 |
+
"rewards/chosen": -0.2787321209907532,
|
| 1043 |
+
"rewards/margins": 0.08983801305294037,
|
| 1044 |
+
"rewards/rejected": -0.36857014894485474,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": -0.01685388572514057,
|
| 1051 |
+
"logits/rejected": 0.08555487543344498,
|
| 1052 |
+
"logps/chosen": -405.7493591308594,
|
| 1053 |
+
"logps/rejected": -383.0268859863281,
|
| 1054 |
+
"loss": 0.1631,
|
| 1055 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1056 |
+
"rewards/chosen": -0.2447400987148285,
|
| 1057 |
+
"rewards/margins": 0.08146357536315918,
|
| 1058 |
+
"rewards/rejected": -0.32620367407798767,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": 4.3596326577244326e-05,
|
| 1065 |
+
"logits/rejected": 0.07585635036230087,
|
| 1066 |
+
"logps/chosen": -454.00299072265625,
|
| 1067 |
+
"logps/rejected": -468.2713317871094,
|
| 1068 |
+
"loss": 0.1772,
|
| 1069 |
+
"rewards/accuracies": 0.53125,
|
| 1070 |
+
"rewards/chosen": -0.3086394667625427,
|
| 1071 |
+
"rewards/margins": 0.08122680336236954,
|
| 1072 |
+
"rewards/rejected": -0.38986626267433167,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": -0.05567328259348869,
|
| 1079 |
+
"logits/rejected": 0.16029450297355652,
|
| 1080 |
+
"logps/chosen": -415.29608154296875,
|
| 1081 |
+
"logps/rejected": -398.7294921875,
|
| 1082 |
+
"loss": 0.153,
|
| 1083 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1084 |
+
"rewards/chosen": -0.2835378050804138,
|
| 1085 |
+
"rewards/margins": 0.09213887155056,
|
| 1086 |
+
"rewards/rejected": -0.375676691532135,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": -0.08789820969104767,
|
| 1093 |
+
"logits/rejected": -0.000363718718290329,
|
| 1094 |
+
"logps/chosen": -463.2998962402344,
|
| 1095 |
+
"logps/rejected": -440.36328125,
|
| 1096 |
+
"loss": 0.1584,
|
| 1097 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 1098 |
+
"rewards/chosen": -0.29543575644493103,
|
| 1099 |
+
"rewards/margins": 0.09579849988222122,
|
| 1100 |
+
"rewards/rejected": -0.39123424887657166,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": -0.030699348077178,
|
| 1107 |
+
"logits/rejected": 0.08616991341114044,
|
| 1108 |
+
"logps/chosen": -469.35833740234375,
|
| 1109 |
+
"logps/rejected": -482.96337890625,
|
| 1110 |
+
"loss": 0.1671,
|
| 1111 |
+
"rewards/accuracies": 0.59375,
|
| 1112 |
+
"rewards/chosen": -0.3277556598186493,
|
| 1113 |
+
"rewards/margins": 0.0916672796010971,
|
| 1114 |
+
"rewards/rejected": -0.4194229543209076,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": 0.04981686919927597,
|
| 1121 |
+
"logits/rejected": 0.08207514882087708,
|
| 1122 |
+
"logps/chosen": -433.3348693847656,
|
| 1123 |
+
"logps/rejected": -440.70953369140625,
|
| 1124 |
+
"loss": 0.1727,
|
| 1125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1126 |
+
"rewards/chosen": -0.31288522481918335,
|
| 1127 |
+
"rewards/margins": 0.08250272274017334,
|
| 1128 |
+
"rewards/rejected": -0.3953879475593567,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": -0.040587715804576874,
|
| 1135 |
+
"logits/rejected": 0.07621972262859344,
|
| 1136 |
+
"logps/chosen": -451.85345458984375,
|
| 1137 |
+
"logps/rejected": -429.25634765625,
|
| 1138 |
+
"loss": 0.1697,
|
| 1139 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 1140 |
+
"rewards/chosen": -0.3361504375934601,
|
| 1141 |
+
"rewards/margins": 0.09061960875988007,
|
| 1142 |
+
"rewards/rejected": -0.42677006125450134,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": 0.033268146216869354,
|
| 1149 |
+
"logits/rejected": -0.0012865017633885145,
|
| 1150 |
+
"logps/chosen": -478.40673828125,
|
| 1151 |
+
"logps/rejected": -487.28680419921875,
|
| 1152 |
+
"loss": 0.1613,
|
| 1153 |
+
"rewards/accuracies": 0.612500011920929,
|
| 1154 |
+
"rewards/chosen": -0.3244819939136505,
|
| 1155 |
+
"rewards/margins": 0.10256977379322052,
|
| 1156 |
+
"rewards/rejected": -0.42705172300338745,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": -0.06332585215568542,
|
| 1163 |
+
"logits/rejected": 0.13626988232135773,
|
| 1164 |
+
"logps/chosen": -468.19378662109375,
|
| 1165 |
+
"logps/rejected": -437.52227783203125,
|
| 1166 |
+
"loss": 0.1594,
|
| 1167 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1168 |
+
"rewards/chosen": -0.2964176535606384,
|
| 1169 |
+
"rewards/margins": 0.11590894311666489,
|
| 1170 |
+
"rewards/rejected": -0.4123266339302063,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": 0.07440580427646637,
|
| 1177 |
+
"logits/rejected": 0.08452493697404861,
|
| 1178 |
+
"logps/chosen": -448.39862060546875,
|
| 1179 |
+
"logps/rejected": -437.47235107421875,
|
| 1180 |
+
"loss": 0.1661,
|
| 1181 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1182 |
+
"rewards/chosen": -0.29594478011131287,
|
| 1183 |
+
"rewards/margins": 0.09329672157764435,
|
| 1184 |
+
"rewards/rejected": -0.3892415463924408,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": -0.06233375146985054,
|
| 1191 |
+
"logits/rejected": 0.027787405997514725,
|
| 1192 |
+
"logps/chosen": -398.1230773925781,
|
| 1193 |
+
"logps/rejected": -390.20489501953125,
|
| 1194 |
+
"loss": 0.1742,
|
| 1195 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1196 |
+
"rewards/chosen": -0.2930799126625061,
|
| 1197 |
+
"rewards/margins": 0.09176953136920929,
|
| 1198 |
+
"rewards/rejected": -0.3848494589328766,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": -0.025651434436440468,
|
| 1205 |
+
"logits/rejected": 0.04196717590093613,
|
| 1206 |
+
"logps/chosen": -450.2112731933594,
|
| 1207 |
+
"logps/rejected": -449.22393798828125,
|
| 1208 |
+
"loss": 0.1564,
|
| 1209 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1210 |
+
"rewards/chosen": -0.31000474095344543,
|
| 1211 |
+
"rewards/margins": 0.09261561930179596,
|
| 1212 |
+
"rewards/rejected": -0.4026203751564026,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": 0.1431967318058014,
|
| 1219 |
+
"logits/rejected": 0.003605568315833807,
|
| 1220 |
+
"logps/chosen": -432.6329650878906,
|
| 1221 |
+
"logps/rejected": -449.58282470703125,
|
| 1222 |
+
"loss": 0.1597,
|
| 1223 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1224 |
+
"rewards/chosen": -0.3245397210121155,
|
| 1225 |
+
"rewards/margins": 0.0643848329782486,
|
| 1226 |
+
"rewards/rejected": -0.3889245390892029,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": 0.059076208621263504,
|
| 1233 |
+
"logits/rejected": -0.0008928939932957292,
|
| 1234 |
+
"logps/chosen": -480.4388732910156,
|
| 1235 |
+
"logps/rejected": -463.54522705078125,
|
| 1236 |
+
"loss": 0.1676,
|
| 1237 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1238 |
+
"rewards/chosen": -0.31118619441986084,
|
| 1239 |
+
"rewards/margins": 0.08092699944972992,
|
| 1240 |
+
"rewards/rejected": -0.3921131491661072,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": -0.019091134890913963,
|
| 1247 |
+
"logits/rejected": 0.034938834607601166,
|
| 1248 |
+
"logps/chosen": -435.51953125,
|
| 1249 |
+
"logps/rejected": -441.9061584472656,
|
| 1250 |
+
"loss": 0.1645,
|
| 1251 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 1252 |
+
"rewards/chosen": -0.3230697214603424,
|
| 1253 |
+
"rewards/margins": 0.09634076803922653,
|
| 1254 |
+
"rewards/rejected": -0.41941046714782715,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": -0.056211818009614944,
|
| 1261 |
+
"logits/rejected": 0.04693780839443207,
|
| 1262 |
+
"logps/chosen": -446.30224609375,
|
| 1263 |
+
"logps/rejected": -438.859375,
|
| 1264 |
+
"loss": 0.1766,
|
| 1265 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1266 |
+
"rewards/chosen": -0.30564260482788086,
|
| 1267 |
+
"rewards/margins": 0.0854407250881195,
|
| 1268 |
+
"rewards/rejected": -0.39108332991600037,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": 0.026849299669265747,
|
| 1275 |
+
"logits/rejected": -0.015656864270567894,
|
| 1276 |
+
"logps/chosen": -413.23876953125,
|
| 1277 |
+
"logps/rejected": -446.19219970703125,
|
| 1278 |
+
"loss": 0.1638,
|
| 1279 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 1280 |
+
"rewards/chosen": -0.30960044264793396,
|
| 1281 |
+
"rewards/margins": 0.08425579965114594,
|
| 1282 |
+
"rewards/rejected": -0.3938562273979187,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": 0.02639024890959263,
|
| 1289 |
+
"logits/rejected": 0.017060106620192528,
|
| 1290 |
+
"logps/chosen": -459.57318115234375,
|
| 1291 |
+
"logps/rejected": -468.657958984375,
|
| 1292 |
+
"loss": 0.1567,
|
| 1293 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 1294 |
+
"rewards/chosen": -0.2922886312007904,
|
| 1295 |
+
"rewards/margins": 0.1054367646574974,
|
| 1296 |
+
"rewards/rejected": -0.3977254033088684,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": -0.023000415414571762,
|
| 1303 |
+
"logits/rejected": -0.024313045665621758,
|
| 1304 |
+
"logps/chosen": -414.48370361328125,
|
| 1305 |
+
"logps/rejected": -406.40069580078125,
|
| 1306 |
+
"loss": 0.1696,
|
| 1307 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1308 |
+
"rewards/chosen": -0.308437705039978,
|
| 1309 |
+
"rewards/margins": 0.0932714194059372,
|
| 1310 |
+
"rewards/rejected": -0.40170907974243164,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": 0.016056960448622704,
|
| 1317 |
+
"logits/rejected": 0.02258588932454586,
|
| 1318 |
+
"logps/chosen": -415.54803466796875,
|
| 1319 |
+
"logps/rejected": -428.69775390625,
|
| 1320 |
+
"loss": 0.1713,
|
| 1321 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1322 |
+
"rewards/chosen": -0.31125369668006897,
|
| 1323 |
+
"rewards/margins": 0.08610902726650238,
|
| 1324 |
+
"rewards/rejected": -0.39736273884773254,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.1752831537352046,
|
| 1332 |
+
"train_runtime": 7846.1192,
|
| 1333 |
+
"train_samples_per_second": 3.824,
|
| 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 |
+
}
|