Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May21_07-23-46_gpu4-119-5/events.out.tfevents.1716240383.gpu4-119-5.1398518.0 +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-v14-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-v14-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 sha256:62a336e422eb92d748cb6ea0969b55534989f0773d4f57c2fe62f09f49768f79
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2777036651094288,
|
| 4 |
+
"train_runtime": 6958.035,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 4.312,
|
| 7 |
+
"train_steps_per_second": 0.135
|
| 8 |
+
}
|
runs/May21_07-23-46_gpu4-119-5/events.out.tfevents.1716240383.gpu4-119-5.1398518.0
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 sha256:2d5e4fb1099a0f1227d505507b831e2d0b504218f5c5a8dd8fb3b906c761e0f8
|
| 3 |
+
size 64720
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2777036651094288,
|
| 4 |
+
"train_runtime": 6958.035,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 4.312,
|
| 7 |
+
"train_steps_per_second": 0.135
|
| 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": 0.09486827999353409,
|
| 15 |
+
"logits/rejected": 0.17880678176879883,
|
| 16 |
+
"logps/chosen": -404.6722717285156,
|
| 17 |
+
"logps/rejected": -393.01068115234375,
|
| 18 |
+
"loss": 0.2923,
|
| 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": 0.3109264671802521,
|
| 29 |
+
"logits/rejected": 0.1413353830575943,
|
| 30 |
+
"logps/chosen": -451.60137939453125,
|
| 31 |
+
"logps/rejected": -439.4466857910156,
|
| 32 |
+
"loss": 0.3143,
|
| 33 |
+
"rewards/accuracies": 0.3472222089767456,
|
| 34 |
+
"rewards/chosen": -0.0008689137175679207,
|
| 35 |
+
"rewards/margins": 9.278658399125561e-05,
|
| 36 |
+
"rewards/rejected": -0.0009617002215236425,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.16002216935157776,
|
| 43 |
+
"logits/rejected": 0.29283756017684937,
|
| 44 |
+
"logps/chosen": -446.17352294921875,
|
| 45 |
+
"logps/rejected": -447.1424865722656,
|
| 46 |
+
"loss": 0.3012,
|
| 47 |
+
"rewards/accuracies": 0.40625,
|
| 48 |
+
"rewards/chosen": -0.0012470056535676122,
|
| 49 |
+
"rewards/margins": 7.514755270676687e-05,
|
| 50 |
+
"rewards/rejected": -0.0013221531407907605,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.16278645396232605,
|
| 57 |
+
"logits/rejected": 0.23292532563209534,
|
| 58 |
+
"logps/chosen": -390.2185974121094,
|
| 59 |
+
"logps/rejected": -385.9638977050781,
|
| 60 |
+
"loss": 0.3074,
|
| 61 |
+
"rewards/accuracies": 0.3187499940395355,
|
| 62 |
+
"rewards/chosen": -0.001785513712093234,
|
| 63 |
+
"rewards/margins": -4.0346338209928945e-05,
|
| 64 |
+
"rewards/rejected": -0.0017451674211770296,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.21185627579689026,
|
| 71 |
+
"logits/rejected": 0.16483844816684723,
|
| 72 |
+
"logps/chosen": -396.40234375,
|
| 73 |
+
"logps/rejected": -413.7225036621094,
|
| 74 |
+
"loss": 0.2927,
|
| 75 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 76 |
+
"rewards/chosen": -0.003013796405866742,
|
| 77 |
+
"rewards/margins": 0.0003060643211938441,
|
| 78 |
+
"rewards/rejected": -0.003319860901683569,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.13742004334926605,
|
| 85 |
+
"logits/rejected": 0.31375652551651,
|
| 86 |
+
"logps/chosen": -412.4908142089844,
|
| 87 |
+
"logps/rejected": -392.556640625,
|
| 88 |
+
"loss": 0.3019,
|
| 89 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 90 |
+
"rewards/chosen": -0.005482032895088196,
|
| 91 |
+
"rewards/margins": 0.00019160615920554847,
|
| 92 |
+
"rewards/rejected": -0.005673639010637999,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.22858476638793945,
|
| 99 |
+
"logits/rejected": 0.2066006362438202,
|
| 100 |
+
"logps/chosen": -394.327880859375,
|
| 101 |
+
"logps/rejected": -392.41656494140625,
|
| 102 |
+
"loss": 0.32,
|
| 103 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 104 |
+
"rewards/chosen": -0.009965803474187851,
|
| 105 |
+
"rewards/margins": 0.00048381154192611575,
|
| 106 |
+
"rewards/rejected": -0.010449616238474846,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.29500612616539,
|
| 113 |
+
"logits/rejected": 0.1506035029888153,
|
| 114 |
+
"logps/chosen": -392.02960205078125,
|
| 115 |
+
"logps/rejected": -427.17596435546875,
|
| 116 |
+
"loss": 0.3328,
|
| 117 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 118 |
+
"rewards/chosen": -0.01748177967965603,
|
| 119 |
+
"rewards/margins": 0.0010660603875294328,
|
| 120 |
+
"rewards/rejected": -0.018547840416431427,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.1481747180223465,
|
| 127 |
+
"logits/rejected": 0.2276589423418045,
|
| 128 |
+
"logps/chosen": -396.8224182128906,
|
| 129 |
+
"logps/rejected": -373.9072570800781,
|
| 130 |
+
"loss": 0.3068,
|
| 131 |
+
"rewards/accuracies": 0.39375001192092896,
|
| 132 |
+
"rewards/chosen": -0.019837453961372375,
|
| 133 |
+
"rewards/margins": 0.0006632342119701207,
|
| 134 |
+
"rewards/rejected": -0.020500686019659042,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.13089337944984436,
|
| 141 |
+
"logits/rejected": 0.19030170142650604,
|
| 142 |
+
"logps/chosen": -379.7206115722656,
|
| 143 |
+
"logps/rejected": -391.56512451171875,
|
| 144 |
+
"loss": 0.2966,
|
| 145 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 146 |
+
"rewards/chosen": -0.018794242292642593,
|
| 147 |
+
"rewards/margins": 0.0023801042698323727,
|
| 148 |
+
"rewards/rejected": -0.021174345165491104,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.13803163170814514,
|
| 155 |
+
"logits/rejected": 0.24431411921977997,
|
| 156 |
+
"logps/chosen": -408.5091247558594,
|
| 157 |
+
"logps/rejected": -396.9778747558594,
|
| 158 |
+
"loss": 0.3097,
|
| 159 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 160 |
+
"rewards/chosen": -0.017420392483472824,
|
| 161 |
+
"rewards/margins": 0.0018956039566546679,
|
| 162 |
+
"rewards/rejected": -0.019315997138619423,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.155339315533638,
|
| 169 |
+
"logits/rejected": 0.1211571916937828,
|
| 170 |
+
"logps/chosen": -430.47344970703125,
|
| 171 |
+
"logps/rejected": -437.48956298828125,
|
| 172 |
+
"loss": 0.2946,
|
| 173 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 174 |
+
"rewards/chosen": -0.018004143610596657,
|
| 175 |
+
"rewards/margins": 0.004096529446542263,
|
| 176 |
+
"rewards/rejected": -0.022100670263171196,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.1062009185552597,
|
| 183 |
+
"logits/rejected": 0.26274779438972473,
|
| 184 |
+
"logps/chosen": -413.7748107910156,
|
| 185 |
+
"logps/rejected": -401.53778076171875,
|
| 186 |
+
"loss": 0.3079,
|
| 187 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 188 |
+
"rewards/chosen": -0.01474347896873951,
|
| 189 |
+
"rewards/margins": 0.00652940571308136,
|
| 190 |
+
"rewards/rejected": -0.02127288654446602,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.13843606412410736,
|
| 197 |
+
"logits/rejected": 0.2405589520931244,
|
| 198 |
+
"logps/chosen": -445.410888671875,
|
| 199 |
+
"logps/rejected": -441.92486572265625,
|
| 200 |
+
"loss": 0.3126,
|
| 201 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 202 |
+
"rewards/chosen": -0.016456641256809235,
|
| 203 |
+
"rewards/margins": 0.006972718983888626,
|
| 204 |
+
"rewards/rejected": -0.02342936024069786,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.1316756308078766,
|
| 211 |
+
"logits/rejected": 0.0917954295873642,
|
| 212 |
+
"logps/chosen": -441.77911376953125,
|
| 213 |
+
"logps/rejected": -474.7543029785156,
|
| 214 |
+
"loss": 0.3121,
|
| 215 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 216 |
+
"rewards/chosen": -0.030273189768195152,
|
| 217 |
+
"rewards/margins": 0.006867046467959881,
|
| 218 |
+
"rewards/rejected": -0.03714023157954216,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.07779763638973236,
|
| 225 |
+
"logits/rejected": 0.16235283017158508,
|
| 226 |
+
"logps/chosen": -468.13873291015625,
|
| 227 |
+
"logps/rejected": -508.16888427734375,
|
| 228 |
+
"loss": 0.2735,
|
| 229 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 230 |
+
"rewards/chosen": -0.042156465351581573,
|
| 231 |
+
"rewards/margins": 0.025058995932340622,
|
| 232 |
+
"rewards/rejected": -0.0672154575586319,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.013025517575442791,
|
| 239 |
+
"logits/rejected": 0.05558537319302559,
|
| 240 |
+
"logps/chosen": -490.2015686035156,
|
| 241 |
+
"logps/rejected": -526.5242919921875,
|
| 242 |
+
"loss": 0.296,
|
| 243 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 244 |
+
"rewards/chosen": -0.07817033678293228,
|
| 245 |
+
"rewards/margins": 0.030566949397325516,
|
| 246 |
+
"rewards/rejected": -0.1087372750043869,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.005712971091270447,
|
| 253 |
+
"logits/rejected": -0.005013291724026203,
|
| 254 |
+
"logps/chosen": -577.2238159179688,
|
| 255 |
+
"logps/rejected": -608.1441650390625,
|
| 256 |
+
"loss": 0.2962,
|
| 257 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 258 |
+
"rewards/chosen": -0.12602511048316956,
|
| 259 |
+
"rewards/margins": 0.029870549216866493,
|
| 260 |
+
"rewards/rejected": -0.1558956503868103,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.0872177928686142,
|
| 267 |
+
"logits/rejected": 0.047161780297756195,
|
| 268 |
+
"logps/chosen": -466.25384521484375,
|
| 269 |
+
"logps/rejected": -508.01190185546875,
|
| 270 |
+
"loss": 0.2824,
|
| 271 |
+
"rewards/accuracies": 0.518750011920929,
|
| 272 |
+
"rewards/chosen": -0.06323900073766708,
|
| 273 |
+
"rewards/margins": 0.03396384045481682,
|
| 274 |
+
"rewards/rejected": -0.0972028374671936,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.040699899196624756,
|
| 281 |
+
"logits/rejected": 0.08730391412973404,
|
| 282 |
+
"logps/chosen": -451.14190673828125,
|
| 283 |
+
"logps/rejected": -483.7627868652344,
|
| 284 |
+
"loss": 0.269,
|
| 285 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 286 |
+
"rewards/chosen": -0.05393596366047859,
|
| 287 |
+
"rewards/margins": 0.02897338569164276,
|
| 288 |
+
"rewards/rejected": -0.08290934562683105,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": -0.029990673065185547,
|
| 295 |
+
"logits/rejected": 0.0431547686457634,
|
| 296 |
+
"logps/chosen": -511.7386779785156,
|
| 297 |
+
"logps/rejected": -536.8895263671875,
|
| 298 |
+
"loss": 0.2937,
|
| 299 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 300 |
+
"rewards/chosen": -0.06965841352939606,
|
| 301 |
+
"rewards/margins": 0.030940961092710495,
|
| 302 |
+
"rewards/rejected": -0.10059938579797745,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": -0.017718762159347534,
|
| 309 |
+
"logits/rejected": 0.0021002888679504395,
|
| 310 |
+
"logps/chosen": -475.02398681640625,
|
| 311 |
+
"logps/rejected": -524.1427001953125,
|
| 312 |
+
"loss": 0.2823,
|
| 313 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 314 |
+
"rewards/chosen": -0.09790189564228058,
|
| 315 |
+
"rewards/margins": 0.04916772618889809,
|
| 316 |
+
"rewards/rejected": -0.14706961810588837,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.039277154952287674,
|
| 323 |
+
"logits/rejected": 0.08032336086034775,
|
| 324 |
+
"logps/chosen": -542.1201782226562,
|
| 325 |
+
"logps/rejected": -580.0626220703125,
|
| 326 |
+
"loss": 0.2699,
|
| 327 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 328 |
+
"rewards/chosen": -0.11237654834985733,
|
| 329 |
+
"rewards/margins": 0.05318045616149902,
|
| 330 |
+
"rewards/rejected": -0.16555699706077576,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": -0.040498532354831696,
|
| 337 |
+
"logits/rejected": 0.038641445338726044,
|
| 338 |
+
"logps/chosen": -530.233642578125,
|
| 339 |
+
"logps/rejected": -566.8374633789062,
|
| 340 |
+
"loss": 0.3008,
|
| 341 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 342 |
+
"rewards/chosen": -0.11718879640102386,
|
| 343 |
+
"rewards/margins": 0.04862760379910469,
|
| 344 |
+
"rewards/rejected": -0.16581639647483826,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": 0.03174019977450371,
|
| 351 |
+
"logits/rejected": 0.028316298499703407,
|
| 352 |
+
"logps/chosen": -544.1737060546875,
|
| 353 |
+
"logps/rejected": -595.1419677734375,
|
| 354 |
+
"loss": 0.2807,
|
| 355 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 356 |
+
"rewards/chosen": -0.1217833161354065,
|
| 357 |
+
"rewards/margins": 0.05592575669288635,
|
| 358 |
+
"rewards/rejected": -0.17770907282829285,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": -0.03996685892343521,
|
| 365 |
+
"logits/rejected": 0.0781441181898117,
|
| 366 |
+
"logps/chosen": -561.5933227539062,
|
| 367 |
+
"logps/rejected": -588.9613037109375,
|
| 368 |
+
"loss": 0.289,
|
| 369 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 370 |
+
"rewards/chosen": -0.12694257497787476,
|
| 371 |
+
"rewards/margins": 0.05903642624616623,
|
| 372 |
+
"rewards/rejected": -0.18597903847694397,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": -0.07835476100444794,
|
| 379 |
+
"logits/rejected": -0.022311905398964882,
|
| 380 |
+
"logps/chosen": -542.6710815429688,
|
| 381 |
+
"logps/rejected": -574.5667114257812,
|
| 382 |
+
"loss": 0.2814,
|
| 383 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 384 |
+
"rewards/chosen": -0.13178928196430206,
|
| 385 |
+
"rewards/margins": 0.04299298673868179,
|
| 386 |
+
"rewards/rejected": -0.17478224635124207,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": -0.08058448135852814,
|
| 393 |
+
"logits/rejected": 0.07340067625045776,
|
| 394 |
+
"logps/chosen": -508.29901123046875,
|
| 395 |
+
"logps/rejected": -560.2567138671875,
|
| 396 |
+
"loss": 0.2709,
|
| 397 |
+
"rewards/accuracies": 0.46875,
|
| 398 |
+
"rewards/chosen": -0.11642781645059586,
|
| 399 |
+
"rewards/margins": 0.05028604343533516,
|
| 400 |
+
"rewards/rejected": -0.1667138636112213,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": -0.060424257069826126,
|
| 407 |
+
"logits/rejected": -0.05060155317187309,
|
| 408 |
+
"logps/chosen": -522.2492065429688,
|
| 409 |
+
"logps/rejected": -580.984375,
|
| 410 |
+
"loss": 0.2702,
|
| 411 |
+
"rewards/accuracies": 0.5,
|
| 412 |
+
"rewards/chosen": -0.1186426654458046,
|
| 413 |
+
"rewards/margins": 0.05852733179926872,
|
| 414 |
+
"rewards/rejected": -0.17716999351978302,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": -0.0831371396780014,
|
| 421 |
+
"logits/rejected": 0.1073642149567604,
|
| 422 |
+
"logps/chosen": -578.5635986328125,
|
| 423 |
+
"logps/rejected": -601.4964599609375,
|
| 424 |
+
"loss": 0.2702,
|
| 425 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 426 |
+
"rewards/chosen": -0.14065107703208923,
|
| 427 |
+
"rewards/margins": 0.04782631993293762,
|
| 428 |
+
"rewards/rejected": -0.18847739696502686,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": -0.034952230751514435,
|
| 435 |
+
"logits/rejected": -0.033971935510635376,
|
| 436 |
+
"logps/chosen": -521.9036865234375,
|
| 437 |
+
"logps/rejected": -568.0286865234375,
|
| 438 |
+
"loss": 0.281,
|
| 439 |
+
"rewards/accuracies": 0.5,
|
| 440 |
+
"rewards/chosen": -0.10558326542377472,
|
| 441 |
+
"rewards/margins": 0.05633324384689331,
|
| 442 |
+
"rewards/rejected": -0.16191650927066803,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": -0.05012059211730957,
|
| 449 |
+
"logits/rejected": -0.07782770693302155,
|
| 450 |
+
"logps/chosen": -489.470458984375,
|
| 451 |
+
"logps/rejected": -555.35302734375,
|
| 452 |
+
"loss": 0.2723,
|
| 453 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 454 |
+
"rewards/chosen": -0.09179838001728058,
|
| 455 |
+
"rewards/margins": 0.06358543783426285,
|
| 456 |
+
"rewards/rejected": -0.15538384020328522,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": -0.19141286611557007,
|
| 463 |
+
"logits/rejected": -0.10618031024932861,
|
| 464 |
+
"logps/chosen": -450.0037536621094,
|
| 465 |
+
"logps/rejected": -540.8576049804688,
|
| 466 |
+
"loss": 0.2691,
|
| 467 |
+
"rewards/accuracies": 0.518750011920929,
|
| 468 |
+
"rewards/chosen": -0.09631234407424927,
|
| 469 |
+
"rewards/margins": 0.0666104406118393,
|
| 470 |
+
"rewards/rejected": -0.16292276978492737,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": -0.05697326734662056,
|
| 477 |
+
"logits/rejected": -0.13873888552188873,
|
| 478 |
+
"logps/chosen": -481.6494140625,
|
| 479 |
+
"logps/rejected": -599.4074096679688,
|
| 480 |
+
"loss": 0.2811,
|
| 481 |
+
"rewards/accuracies": 0.543749988079071,
|
| 482 |
+
"rewards/chosen": -0.12175127118825912,
|
| 483 |
+
"rewards/margins": 0.0913892462849617,
|
| 484 |
+
"rewards/rejected": -0.21314053237438202,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": -0.08442874252796173,
|
| 491 |
+
"logits/rejected": -0.0031359121203422546,
|
| 492 |
+
"logps/chosen": -474.0492248535156,
|
| 493 |
+
"logps/rejected": -555.919189453125,
|
| 494 |
+
"loss": 0.2772,
|
| 495 |
+
"rewards/accuracies": 0.46875,
|
| 496 |
+
"rewards/chosen": -0.11865799129009247,
|
| 497 |
+
"rewards/margins": 0.05636826157569885,
|
| 498 |
+
"rewards/rejected": -0.17502623796463013,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": -0.0918760672211647,
|
| 505 |
+
"logits/rejected": 0.022966912016272545,
|
| 506 |
+
"logps/chosen": -555.8822021484375,
|
| 507 |
+
"logps/rejected": -670.1365356445312,
|
| 508 |
+
"loss": 0.2612,
|
| 509 |
+
"rewards/accuracies": 0.543749988079071,
|
| 510 |
+
"rewards/chosen": -0.1380760669708252,
|
| 511 |
+
"rewards/margins": 0.0869637131690979,
|
| 512 |
+
"rewards/rejected": -0.2250397652387619,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": -0.1127350777387619,
|
| 519 |
+
"logits/rejected": -0.15412607789039612,
|
| 520 |
+
"logps/chosen": -516.8878784179688,
|
| 521 |
+
"logps/rejected": -592.467041015625,
|
| 522 |
+
"loss": 0.2765,
|
| 523 |
+
"rewards/accuracies": 0.512499988079071,
|
| 524 |
+
"rewards/chosen": -0.12640734016895294,
|
| 525 |
+
"rewards/margins": 0.06364301592111588,
|
| 526 |
+
"rewards/rejected": -0.19005033373832703,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": -0.1551699936389923,
|
| 533 |
+
"logits/rejected": -0.055733174085617065,
|
| 534 |
+
"logps/chosen": -500.0525817871094,
|
| 535 |
+
"logps/rejected": -564.5525512695312,
|
| 536 |
+
"loss": 0.271,
|
| 537 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 538 |
+
"rewards/chosen": -0.11618797481060028,
|
| 539 |
+
"rewards/margins": 0.05627555400133133,
|
| 540 |
+
"rewards/rejected": -0.17246350646018982,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": -0.15336255729198456,
|
| 547 |
+
"logits/rejected": -0.09010852128267288,
|
| 548 |
+
"logps/chosen": -532.9185180664062,
|
| 549 |
+
"logps/rejected": -579.7677612304688,
|
| 550 |
+
"loss": 0.2518,
|
| 551 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 552 |
+
"rewards/chosen": -0.09618903696537018,
|
| 553 |
+
"rewards/margins": 0.059428442269563675,
|
| 554 |
+
"rewards/rejected": -0.15561747550964355,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": -0.14842228591442108,
|
| 561 |
+
"logits/rejected": -0.18628902733325958,
|
| 562 |
+
"logps/chosen": -499.26495361328125,
|
| 563 |
+
"logps/rejected": -566.7688598632812,
|
| 564 |
+
"loss": 0.2847,
|
| 565 |
+
"rewards/accuracies": 0.5,
|
| 566 |
+
"rewards/chosen": -0.10898256301879883,
|
| 567 |
+
"rewards/margins": 0.05999414250254631,
|
| 568 |
+
"rewards/rejected": -0.16897672414779663,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": -0.16273057460784912,
|
| 575 |
+
"logits/rejected": -0.10563422739505768,
|
| 576 |
+
"logps/chosen": -554.4479370117188,
|
| 577 |
+
"logps/rejected": -563.3797607421875,
|
| 578 |
+
"loss": 0.2849,
|
| 579 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 580 |
+
"rewards/chosen": -0.10144559293985367,
|
| 581 |
+
"rewards/margins": 0.04638112708926201,
|
| 582 |
+
"rewards/rejected": -0.14782671630382538,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": -0.11332042515277863,
|
| 589 |
+
"logits/rejected": -0.11062748730182648,
|
| 590 |
+
"logps/chosen": -518.7150268554688,
|
| 591 |
+
"logps/rejected": -573.0471801757812,
|
| 592 |
+
"loss": 0.259,
|
| 593 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 594 |
+
"rewards/chosen": -0.10492125898599625,
|
| 595 |
+
"rewards/margins": 0.046738140285015106,
|
| 596 |
+
"rewards/rejected": -0.15165939927101135,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": -0.158113032579422,
|
| 603 |
+
"logits/rejected": -0.11588151752948761,
|
| 604 |
+
"logps/chosen": -462.90423583984375,
|
| 605 |
+
"logps/rejected": -516.649658203125,
|
| 606 |
+
"loss": 0.2722,
|
| 607 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 608 |
+
"rewards/chosen": -0.10597708076238632,
|
| 609 |
+
"rewards/margins": 0.0523579902946949,
|
| 610 |
+
"rewards/rejected": -0.15833505988121033,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": -0.21510057151317596,
|
| 617 |
+
"logits/rejected": -0.08049353212118149,
|
| 618 |
+
"logps/chosen": -583.40283203125,
|
| 619 |
+
"logps/rejected": -586.7947998046875,
|
| 620 |
+
"loss": 0.2929,
|
| 621 |
+
"rewards/accuracies": 0.512499988079071,
|
| 622 |
+
"rewards/chosen": -0.11892227083444595,
|
| 623 |
+
"rewards/margins": 0.05448797345161438,
|
| 624 |
+
"rewards/rejected": -0.17341025173664093,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": -0.12544101476669312,
|
| 631 |
+
"logits/rejected": -0.11414500325918198,
|
| 632 |
+
"logps/chosen": -459.9356384277344,
|
| 633 |
+
"logps/rejected": -505.929931640625,
|
| 634 |
+
"loss": 0.2729,
|
| 635 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 636 |
+
"rewards/chosen": -0.11049865186214447,
|
| 637 |
+
"rewards/margins": 0.047077327966690063,
|
| 638 |
+
"rewards/rejected": -0.15757599472999573,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": -0.10923869907855988,
|
| 645 |
+
"logits/rejected": -0.1209484338760376,
|
| 646 |
+
"logps/chosen": -453.79071044921875,
|
| 647 |
+
"logps/rejected": -520.7780151367188,
|
| 648 |
+
"loss": 0.2685,
|
| 649 |
+
"rewards/accuracies": 0.53125,
|
| 650 |
+
"rewards/chosen": -0.09267580509185791,
|
| 651 |
+
"rewards/margins": 0.06151905655860901,
|
| 652 |
+
"rewards/rejected": -0.15419486165046692,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": -0.20092570781707764,
|
| 659 |
+
"logits/rejected": -0.04523925110697746,
|
| 660 |
+
"logps/chosen": -501.44183349609375,
|
| 661 |
+
"logps/rejected": -541.0614624023438,
|
| 662 |
+
"loss": 0.2738,
|
| 663 |
+
"rewards/accuracies": 0.53125,
|
| 664 |
+
"rewards/chosen": -0.1075231060385704,
|
| 665 |
+
"rewards/margins": 0.054855745285749435,
|
| 666 |
+
"rewards/rejected": -0.16237884759902954,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": -0.18216080963611603,
|
| 673 |
+
"logits/rejected": -0.09222938120365143,
|
| 674 |
+
"logps/chosen": -543.4312744140625,
|
| 675 |
+
"logps/rejected": -569.2079467773438,
|
| 676 |
+
"loss": 0.2854,
|
| 677 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 678 |
+
"rewards/chosen": -0.11925343424081802,
|
| 679 |
+
"rewards/margins": 0.03793327510356903,
|
| 680 |
+
"rewards/rejected": -0.15718670189380646,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": -0.12351751327514648,
|
| 687 |
+
"logits/rejected": -0.06279022991657257,
|
| 688 |
+
"logps/chosen": -496.760498046875,
|
| 689 |
+
"logps/rejected": -529.7518310546875,
|
| 690 |
+
"loss": 0.29,
|
| 691 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 692 |
+
"rewards/chosen": -0.0903807058930397,
|
| 693 |
+
"rewards/margins": 0.060529064387083054,
|
| 694 |
+
"rewards/rejected": -0.15090976655483246,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": -0.19289804995059967,
|
| 701 |
+
"logits/rejected": -0.1217590793967247,
|
| 702 |
+
"logps/chosen": -558.1929321289062,
|
| 703 |
+
"logps/rejected": -592.0021362304688,
|
| 704 |
+
"loss": 0.2771,
|
| 705 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 706 |
+
"rewards/chosen": -0.11521999537944794,
|
| 707 |
+
"rewards/margins": 0.05031859874725342,
|
| 708 |
+
"rewards/rejected": -0.16553862392902374,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": -0.033294953405857086,
|
| 715 |
+
"logits/rejected": -0.07580285519361496,
|
| 716 |
+
"logps/chosen": -491.3495178222656,
|
| 717 |
+
"logps/rejected": -552.3511352539062,
|
| 718 |
+
"loss": 0.2827,
|
| 719 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 720 |
+
"rewards/chosen": -0.09923096001148224,
|
| 721 |
+
"rewards/margins": 0.07192887365818024,
|
| 722 |
+
"rewards/rejected": -0.17115983366966248,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": -0.2156916856765747,
|
| 729 |
+
"logits/rejected": -0.06504158675670624,
|
| 730 |
+
"logps/chosen": -521.3781127929688,
|
| 731 |
+
"logps/rejected": -539.2896728515625,
|
| 732 |
+
"loss": 0.2831,
|
| 733 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 734 |
+
"rewards/chosen": -0.10902263969182968,
|
| 735 |
+
"rewards/margins": 0.04854800924658775,
|
| 736 |
+
"rewards/rejected": -0.15757066011428833,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": -0.12651291489601135,
|
| 743 |
+
"logits/rejected": -0.11372752487659454,
|
| 744 |
+
"logps/chosen": -529.92529296875,
|
| 745 |
+
"logps/rejected": -584.7510986328125,
|
| 746 |
+
"loss": 0.2821,
|
| 747 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 748 |
+
"rewards/chosen": -0.11373905837535858,
|
| 749 |
+
"rewards/margins": 0.055428702384233475,
|
| 750 |
+
"rewards/rejected": -0.16916777193546295,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": -0.17947567999362946,
|
| 757 |
+
"logits/rejected": -0.15643848478794098,
|
| 758 |
+
"logps/chosen": -505.3380432128906,
|
| 759 |
+
"logps/rejected": -594.7916259765625,
|
| 760 |
+
"loss": 0.2675,
|
| 761 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 762 |
+
"rewards/chosen": -0.10552126169204712,
|
| 763 |
+
"rewards/margins": 0.07201484590768814,
|
| 764 |
+
"rewards/rejected": -0.17753610014915466,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.1622428297996521,
|
| 771 |
+
"logits/rejected": -0.08399353176355362,
|
| 772 |
+
"logps/chosen": -583.8826904296875,
|
| 773 |
+
"logps/rejected": -565.4668579101562,
|
| 774 |
+
"loss": 0.2736,
|
| 775 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 776 |
+
"rewards/chosen": -0.11298346519470215,
|
| 777 |
+
"rewards/margins": 0.0552997961640358,
|
| 778 |
+
"rewards/rejected": -0.16828325390815735,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": -0.15642212331295013,
|
| 785 |
+
"logits/rejected": -0.11185960471630096,
|
| 786 |
+
"logps/chosen": -478.8877868652344,
|
| 787 |
+
"logps/rejected": -511.4723205566406,
|
| 788 |
+
"loss": 0.2606,
|
| 789 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 790 |
+
"rewards/chosen": -0.09287136793136597,
|
| 791 |
+
"rewards/margins": 0.05674201250076294,
|
| 792 |
+
"rewards/rejected": -0.1496133804321289,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": -0.19819292426109314,
|
| 799 |
+
"logits/rejected": -0.08049633353948593,
|
| 800 |
+
"logps/chosen": -502.8023986816406,
|
| 801 |
+
"logps/rejected": -527.1845703125,
|
| 802 |
+
"loss": 0.2718,
|
| 803 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 804 |
+
"rewards/chosen": -0.11550305783748627,
|
| 805 |
+
"rewards/margins": 0.045039866119623184,
|
| 806 |
+
"rewards/rejected": -0.16054292023181915,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": -0.19029836356639862,
|
| 813 |
+
"logits/rejected": -0.12178380787372589,
|
| 814 |
+
"logps/chosen": -487.24029541015625,
|
| 815 |
+
"logps/rejected": -522.4542846679688,
|
| 816 |
+
"loss": 0.2977,
|
| 817 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 818 |
+
"rewards/chosen": -0.08964806795120239,
|
| 819 |
+
"rewards/margins": 0.05422767996788025,
|
| 820 |
+
"rewards/rejected": -0.14387574791908264,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": -0.11798320710659027,
|
| 827 |
+
"logits/rejected": -0.06398233026266098,
|
| 828 |
+
"logps/chosen": -555.4868774414062,
|
| 829 |
+
"logps/rejected": -606.1224365234375,
|
| 830 |
+
"loss": 0.2674,
|
| 831 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 832 |
+
"rewards/chosen": -0.10348886251449585,
|
| 833 |
+
"rewards/margins": 0.07239896804094315,
|
| 834 |
+
"rewards/rejected": -0.1758878380060196,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": -0.1332792490720749,
|
| 841 |
+
"logits/rejected": -0.1340535581111908,
|
| 842 |
+
"logps/chosen": -518.5892944335938,
|
| 843 |
+
"logps/rejected": -602.2269287109375,
|
| 844 |
+
"loss": 0.253,
|
| 845 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 846 |
+
"rewards/chosen": -0.09993033111095428,
|
| 847 |
+
"rewards/margins": 0.06545485556125641,
|
| 848 |
+
"rewards/rejected": -0.1653851717710495,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": -0.24548590183258057,
|
| 855 |
+
"logits/rejected": -0.07364498823881149,
|
| 856 |
+
"logps/chosen": -528.7620849609375,
|
| 857 |
+
"logps/rejected": -581.3148803710938,
|
| 858 |
+
"loss": 0.2575,
|
| 859 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 860 |
+
"rewards/chosen": -0.10455663502216339,
|
| 861 |
+
"rewards/margins": 0.05815718695521355,
|
| 862 |
+
"rewards/rejected": -0.16271382570266724,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": -0.17857643961906433,
|
| 869 |
+
"logits/rejected": -0.05776941031217575,
|
| 870 |
+
"logps/chosen": -495.97613525390625,
|
| 871 |
+
"logps/rejected": -546.7186279296875,
|
| 872 |
+
"loss": 0.2811,
|
| 873 |
+
"rewards/accuracies": 0.518750011920929,
|
| 874 |
+
"rewards/chosen": -0.09525806456804276,
|
| 875 |
+
"rewards/margins": 0.07870879769325256,
|
| 876 |
+
"rewards/rejected": -0.17396686971187592,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": -0.1720505952835083,
|
| 883 |
+
"logits/rejected": -0.25772562623023987,
|
| 884 |
+
"logps/chosen": -486.467529296875,
|
| 885 |
+
"logps/rejected": -584.5782470703125,
|
| 886 |
+
"loss": 0.2582,
|
| 887 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 888 |
+
"rewards/chosen": -0.09170956909656525,
|
| 889 |
+
"rewards/margins": 0.09501364082098007,
|
| 890 |
+
"rewards/rejected": -0.18672320246696472,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": -0.21994712948799133,
|
| 897 |
+
"logits/rejected": -0.1386212706565857,
|
| 898 |
+
"logps/chosen": -567.0380859375,
|
| 899 |
+
"logps/rejected": -595.9439697265625,
|
| 900 |
+
"loss": 0.2555,
|
| 901 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 902 |
+
"rewards/chosen": -0.11543399095535278,
|
| 903 |
+
"rewards/margins": 0.06394585222005844,
|
| 904 |
+
"rewards/rejected": -0.17937985062599182,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": -0.17482668161392212,
|
| 911 |
+
"logits/rejected": -0.11466997861862183,
|
| 912 |
+
"logps/chosen": -497.3523864746094,
|
| 913 |
+
"logps/rejected": -575.636962890625,
|
| 914 |
+
"loss": 0.2737,
|
| 915 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 916 |
+
"rewards/chosen": -0.10399528592824936,
|
| 917 |
+
"rewards/margins": 0.07409018278121948,
|
| 918 |
+
"rewards/rejected": -0.17808546125888824,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": -0.1267072856426239,
|
| 925 |
+
"logits/rejected": -0.22677993774414062,
|
| 926 |
+
"logps/chosen": -562.6024169921875,
|
| 927 |
+
"logps/rejected": -630.305419921875,
|
| 928 |
+
"loss": 0.2679,
|
| 929 |
+
"rewards/accuracies": 0.550000011920929,
|
| 930 |
+
"rewards/chosen": -0.11934264004230499,
|
| 931 |
+
"rewards/margins": 0.08058986812829971,
|
| 932 |
+
"rewards/rejected": -0.1999325305223465,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": -0.2002047747373581,
|
| 939 |
+
"logits/rejected": -0.1947084367275238,
|
| 940 |
+
"logps/chosen": -541.3032836914062,
|
| 941 |
+
"logps/rejected": -579.1988525390625,
|
| 942 |
+
"loss": 0.2595,
|
| 943 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 944 |
+
"rewards/chosen": -0.10852652788162231,
|
| 945 |
+
"rewards/margins": 0.0627359002828598,
|
| 946 |
+
"rewards/rejected": -0.17126242816448212,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": -0.1807963103055954,
|
| 953 |
+
"logits/rejected": -0.1801833063364029,
|
| 954 |
+
"logps/chosen": -545.267333984375,
|
| 955 |
+
"logps/rejected": -617.2647705078125,
|
| 956 |
+
"loss": 0.2531,
|
| 957 |
+
"rewards/accuracies": 0.543749988079071,
|
| 958 |
+
"rewards/chosen": -0.10741935670375824,
|
| 959 |
+
"rewards/margins": 0.07981701195240021,
|
| 960 |
+
"rewards/rejected": -0.18723638355731964,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": -0.16296163201332092,
|
| 967 |
+
"logits/rejected": -0.16335263848304749,
|
| 968 |
+
"logps/chosen": -568.46923828125,
|
| 969 |
+
"logps/rejected": -639.3665771484375,
|
| 970 |
+
"loss": 0.2827,
|
| 971 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 972 |
+
"rewards/chosen": -0.1257370114326477,
|
| 973 |
+
"rewards/margins": 0.07859646528959274,
|
| 974 |
+
"rewards/rejected": -0.20433346927165985,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": -0.15190322697162628,
|
| 981 |
+
"logits/rejected": -0.023175863549113274,
|
| 982 |
+
"logps/chosen": -568.4057006835938,
|
| 983 |
+
"logps/rejected": -605.7794189453125,
|
| 984 |
+
"loss": 0.2618,
|
| 985 |
+
"rewards/accuracies": 0.5,
|
| 986 |
+
"rewards/chosen": -0.1031126156449318,
|
| 987 |
+
"rewards/margins": 0.07158243656158447,
|
| 988 |
+
"rewards/rejected": -0.17469504475593567,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": -0.2676157057285309,
|
| 995 |
+
"logits/rejected": -0.15279750525951385,
|
| 996 |
+
"logps/chosen": -566.8143310546875,
|
| 997 |
+
"logps/rejected": -579.0692138671875,
|
| 998 |
+
"loss": 0.284,
|
| 999 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1000 |
+
"rewards/chosen": -0.11574618518352509,
|
| 1001 |
+
"rewards/margins": 0.03857272118330002,
|
| 1002 |
+
"rewards/rejected": -0.1543188989162445,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": -0.13174203038215637,
|
| 1009 |
+
"logits/rejected": -0.1824689358472824,
|
| 1010 |
+
"logps/chosen": -478.6060485839844,
|
| 1011 |
+
"logps/rejected": -531.3140869140625,
|
| 1012 |
+
"loss": 0.2583,
|
| 1013 |
+
"rewards/accuracies": 0.5,
|
| 1014 |
+
"rewards/chosen": -0.08994091302156448,
|
| 1015 |
+
"rewards/margins": 0.053567446768283844,
|
| 1016 |
+
"rewards/rejected": -0.14350834488868713,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": -0.08020667731761932,
|
| 1023 |
+
"logits/rejected": -0.13351663947105408,
|
| 1024 |
+
"logps/chosen": -520.2698974609375,
|
| 1025 |
+
"logps/rejected": -585.7660522460938,
|
| 1026 |
+
"loss": 0.2855,
|
| 1027 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1028 |
+
"rewards/chosen": -0.10003659874200821,
|
| 1029 |
+
"rewards/margins": 0.06318075209856033,
|
| 1030 |
+
"rewards/rejected": -0.16321733593940735,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": -0.18519246578216553,
|
| 1037 |
+
"logits/rejected": -0.13630035519599915,
|
| 1038 |
+
"logps/chosen": -504.2767639160156,
|
| 1039 |
+
"logps/rejected": -569.7481689453125,
|
| 1040 |
+
"loss": 0.2545,
|
| 1041 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1042 |
+
"rewards/chosen": -0.09188510477542877,
|
| 1043 |
+
"rewards/margins": 0.06354068219661713,
|
| 1044 |
+
"rewards/rejected": -0.1554257869720459,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": -0.19004374742507935,
|
| 1051 |
+
"logits/rejected": -0.1609114110469818,
|
| 1052 |
+
"logps/chosen": -557.939208984375,
|
| 1053 |
+
"logps/rejected": -546.6970825195312,
|
| 1054 |
+
"loss": 0.2965,
|
| 1055 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1056 |
+
"rewards/chosen": -0.10281065851449966,
|
| 1057 |
+
"rewards/margins": 0.04500015825033188,
|
| 1058 |
+
"rewards/rejected": -0.14781081676483154,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": -0.17647784948349,
|
| 1065 |
+
"logits/rejected": -0.13355641067028046,
|
| 1066 |
+
"logps/chosen": -567.4881591796875,
|
| 1067 |
+
"logps/rejected": -612.3013305664062,
|
| 1068 |
+
"loss": 0.2652,
|
| 1069 |
+
"rewards/accuracies": 0.5,
|
| 1070 |
+
"rewards/chosen": -0.11634314060211182,
|
| 1071 |
+
"rewards/margins": 0.061061274260282516,
|
| 1072 |
+
"rewards/rejected": -0.17740443348884583,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": -0.2159070074558258,
|
| 1079 |
+
"logits/rejected": -0.10073345899581909,
|
| 1080 |
+
"logps/chosen": -459.47149658203125,
|
| 1081 |
+
"logps/rejected": -529.6015014648438,
|
| 1082 |
+
"loss": 0.2666,
|
| 1083 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 1084 |
+
"rewards/chosen": -0.08737196773290634,
|
| 1085 |
+
"rewards/margins": 0.06437215954065323,
|
| 1086 |
+
"rewards/rejected": -0.15174412727355957,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": -0.1441185027360916,
|
| 1093 |
+
"logits/rejected": -0.027431348338723183,
|
| 1094 |
+
"logps/chosen": -476.61798095703125,
|
| 1095 |
+
"logps/rejected": -507.6756286621094,
|
| 1096 |
+
"loss": 0.2678,
|
| 1097 |
+
"rewards/accuracies": 0.46875,
|
| 1098 |
+
"rewards/chosen": -0.09565510600805283,
|
| 1099 |
+
"rewards/margins": 0.05930342152714729,
|
| 1100 |
+
"rewards/rejected": -0.15495853126049042,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": -0.14351201057434082,
|
| 1107 |
+
"logits/rejected": -0.13506287336349487,
|
| 1108 |
+
"logps/chosen": -515.0467529296875,
|
| 1109 |
+
"logps/rejected": -579.8074951171875,
|
| 1110 |
+
"loss": 0.2695,
|
| 1111 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1112 |
+
"rewards/chosen": -0.10201451927423477,
|
| 1113 |
+
"rewards/margins": 0.05492178350687027,
|
| 1114 |
+
"rewards/rejected": -0.15693630278110504,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": -0.12005716562271118,
|
| 1121 |
+
"logits/rejected": -0.13143005967140198,
|
| 1122 |
+
"logps/chosen": -480.64166259765625,
|
| 1123 |
+
"logps/rejected": -542.0699462890625,
|
| 1124 |
+
"loss": 0.2681,
|
| 1125 |
+
"rewards/accuracies": 0.5,
|
| 1126 |
+
"rewards/chosen": -0.10447077453136444,
|
| 1127 |
+
"rewards/margins": 0.0592375211417675,
|
| 1128 |
+
"rewards/rejected": -0.16370829939842224,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": -0.12967665493488312,
|
| 1135 |
+
"logits/rejected": -0.09862512350082397,
|
| 1136 |
+
"logps/chosen": -504.17559814453125,
|
| 1137 |
+
"logps/rejected": -561.1007690429688,
|
| 1138 |
+
"loss": 0.2608,
|
| 1139 |
+
"rewards/accuracies": 0.5,
|
| 1140 |
+
"rewards/chosen": -0.10162999480962753,
|
| 1141 |
+
"rewards/margins": 0.052912771701812744,
|
| 1142 |
+
"rewards/rejected": -0.15454277396202087,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": -0.12466283142566681,
|
| 1149 |
+
"logits/rejected": -0.18476256728172302,
|
| 1150 |
+
"logps/chosen": -521.7217407226562,
|
| 1151 |
+
"logps/rejected": -606.356689453125,
|
| 1152 |
+
"loss": 0.2598,
|
| 1153 |
+
"rewards/accuracies": 0.5,
|
| 1154 |
+
"rewards/chosen": -0.11335861682891846,
|
| 1155 |
+
"rewards/margins": 0.0591861791908741,
|
| 1156 |
+
"rewards/rejected": -0.17254477739334106,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": -0.17083628475666046,
|
| 1163 |
+
"logits/rejected": -0.12109515815973282,
|
| 1164 |
+
"logps/chosen": -456.31787109375,
|
| 1165 |
+
"logps/rejected": -514.2985229492188,
|
| 1166 |
+
"loss": 0.2716,
|
| 1167 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 1168 |
+
"rewards/chosen": -0.09381003677845001,
|
| 1169 |
+
"rewards/margins": 0.06866031140089035,
|
| 1170 |
+
"rewards/rejected": -0.16247034072875977,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": -0.16086441278457642,
|
| 1177 |
+
"logits/rejected": -0.13963501155376434,
|
| 1178 |
+
"logps/chosen": -485.7345275878906,
|
| 1179 |
+
"logps/rejected": -566.4594116210938,
|
| 1180 |
+
"loss": 0.2668,
|
| 1181 |
+
"rewards/accuracies": 0.5,
|
| 1182 |
+
"rewards/chosen": -0.08713211864233017,
|
| 1183 |
+
"rewards/margins": 0.0719505250453949,
|
| 1184 |
+
"rewards/rejected": -0.15908263623714447,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": -0.08465079963207245,
|
| 1191 |
+
"logits/rejected": -0.21077242493629456,
|
| 1192 |
+
"logps/chosen": -507.953369140625,
|
| 1193 |
+
"logps/rejected": -587.9386596679688,
|
| 1194 |
+
"loss": 0.2522,
|
| 1195 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 1196 |
+
"rewards/chosen": -0.09845003485679626,
|
| 1197 |
+
"rewards/margins": 0.0746922716498375,
|
| 1198 |
+
"rewards/rejected": -0.17314231395721436,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": -0.12216424942016602,
|
| 1205 |
+
"logits/rejected": -0.10754810273647308,
|
| 1206 |
+
"logps/chosen": -534.802734375,
|
| 1207 |
+
"logps/rejected": -569.3134155273438,
|
| 1208 |
+
"loss": 0.2789,
|
| 1209 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1210 |
+
"rewards/chosen": -0.1041802167892456,
|
| 1211 |
+
"rewards/margins": 0.06386038661003113,
|
| 1212 |
+
"rewards/rejected": -0.16804060339927673,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": -0.2511650621891022,
|
| 1219 |
+
"logits/rejected": -0.1288149058818817,
|
| 1220 |
+
"logps/chosen": -511.1424255371094,
|
| 1221 |
+
"logps/rejected": -537.6439208984375,
|
| 1222 |
+
"loss": 0.2629,
|
| 1223 |
+
"rewards/accuracies": 0.39375001192092896,
|
| 1224 |
+
"rewards/chosen": -0.08994197845458984,
|
| 1225 |
+
"rewards/margins": 0.051044024527072906,
|
| 1226 |
+
"rewards/rejected": -0.14098599553108215,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": -0.2117297351360321,
|
| 1233 |
+
"logits/rejected": -0.17164471745491028,
|
| 1234 |
+
"logps/chosen": -505.76715087890625,
|
| 1235 |
+
"logps/rejected": -567.2267456054688,
|
| 1236 |
+
"loss": 0.2535,
|
| 1237 |
+
"rewards/accuracies": 0.46875,
|
| 1238 |
+
"rewards/chosen": -0.0884295180439949,
|
| 1239 |
+
"rewards/margins": 0.07234706729650497,
|
| 1240 |
+
"rewards/rejected": -0.16077657043933868,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": -0.13743457198143005,
|
| 1247 |
+
"logits/rejected": -0.13362528383731842,
|
| 1248 |
+
"logps/chosen": -507.50946044921875,
|
| 1249 |
+
"logps/rejected": -544.0374755859375,
|
| 1250 |
+
"loss": 0.2857,
|
| 1251 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 1252 |
+
"rewards/chosen": -0.10853898525238037,
|
| 1253 |
+
"rewards/margins": 0.044584743678569794,
|
| 1254 |
+
"rewards/rejected": -0.15312373638153076,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": -0.16523101925849915,
|
| 1261 |
+
"logits/rejected": -0.1837397962808609,
|
| 1262 |
+
"logps/chosen": -475.5501403808594,
|
| 1263 |
+
"logps/rejected": -527.5878295898438,
|
| 1264 |
+
"loss": 0.2617,
|
| 1265 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1266 |
+
"rewards/chosen": -0.08936251699924469,
|
| 1267 |
+
"rewards/margins": 0.06296424567699432,
|
| 1268 |
+
"rewards/rejected": -0.15232674777507782,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": -0.23205402493476868,
|
| 1275 |
+
"logits/rejected": -0.2261538952589035,
|
| 1276 |
+
"logps/chosen": -500.764892578125,
|
| 1277 |
+
"logps/rejected": -598.1412963867188,
|
| 1278 |
+
"loss": 0.2395,
|
| 1279 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1280 |
+
"rewards/chosen": -0.09027452021837234,
|
| 1281 |
+
"rewards/margins": 0.07599581778049469,
|
| 1282 |
+
"rewards/rejected": -0.16627033054828644,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": -0.18639487028121948,
|
| 1289 |
+
"logits/rejected": -0.2467382252216339,
|
| 1290 |
+
"logps/chosen": -519.2239379882812,
|
| 1291 |
+
"logps/rejected": -602.8407592773438,
|
| 1292 |
+
"loss": 0.2546,
|
| 1293 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 1294 |
+
"rewards/chosen": -0.09007105976343155,
|
| 1295 |
+
"rewards/margins": 0.07813303172588348,
|
| 1296 |
+
"rewards/rejected": -0.16820409893989563,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": -0.09497157484292984,
|
| 1303 |
+
"logits/rejected": -0.20631170272827148,
|
| 1304 |
+
"logps/chosen": -507.2242126464844,
|
| 1305 |
+
"logps/rejected": -574.6315307617188,
|
| 1306 |
+
"loss": 0.2819,
|
| 1307 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 1308 |
+
"rewards/chosen": -0.10080975294113159,
|
| 1309 |
+
"rewards/margins": 0.06279795616865158,
|
| 1310 |
+
"rewards/rejected": -0.16360768675804138,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": -0.13831308484077454,
|
| 1317 |
+
"logits/rejected": -0.15870514512062073,
|
| 1318 |
+
"logps/chosen": -443.75421142578125,
|
| 1319 |
+
"logps/rejected": -540.8892822265625,
|
| 1320 |
+
"loss": 0.2713,
|
| 1321 |
+
"rewards/accuracies": 0.46875,
|
| 1322 |
+
"rewards/chosen": -0.09177975356578827,
|
| 1323 |
+
"rewards/margins": 0.07154536247253418,
|
| 1324 |
+
"rewards/rejected": -0.16332513093948364,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.2777036651094288,
|
| 1332 |
+
"train_runtime": 6958.035,
|
| 1333 |
+
"train_samples_per_second": 4.312,
|
| 1334 |
+
"train_steps_per_second": 0.135
|
| 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 |
+
}
|