Model save
Browse files- README.md +61 -0
- all_results.json +8 -0
- runs/May21_21-02-50_gpu4-119-5/events.out.tfevents.1716289530.gpu4-119-5.1903212.0 +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-v21-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-v21-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
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 6824.5604,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 4.396,
|
| 7 |
+
"train_steps_per_second": 0.137
|
| 8 |
+
}
|
runs/May21_21-02-50_gpu4-119-5/events.out.tfevents.1716289530.gpu4-119-5.1903212.0
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 sha256:9662877e5a68641c15786fd70e4a680f3f1e8db2d22e895dd26570a13c85fa2d
|
| 3 |
+
size 64720
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 6824.5604,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 4.396,
|
| 7 |
+
"train_steps_per_second": 0.137
|
| 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": 0.0,
|
| 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": 0.15122921764850616,
|
| 29 |
+
"logits/rejected": 0.29006803035736084,
|
| 30 |
+
"logps/chosen": -365.09381103515625,
|
| 31 |
+
"logps/rejected": -352.4356994628906,
|
| 32 |
+
"loss": 0.0,
|
| 33 |
+
"rewards/accuracies": 0.0,
|
| 34 |
+
"rewards/chosen": 0.0,
|
| 35 |
+
"rewards/margins": 0.0,
|
| 36 |
+
"rewards/rejected": 0.0,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.11831488460302353,
|
| 43 |
+
"logits/rejected": 0.20268961787223816,
|
| 44 |
+
"logps/chosen": -339.44415283203125,
|
| 45 |
+
"logps/rejected": -347.7588806152344,
|
| 46 |
+
"loss": 0.0,
|
| 47 |
+
"rewards/accuracies": 0.0,
|
| 48 |
+
"rewards/chosen": 0.0,
|
| 49 |
+
"rewards/margins": 0.0,
|
| 50 |
+
"rewards/rejected": 0.0,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.25372257828712463,
|
| 57 |
+
"logits/rejected": 0.2503891885280609,
|
| 58 |
+
"logps/chosen": -382.58709716796875,
|
| 59 |
+
"logps/rejected": -363.3986511230469,
|
| 60 |
+
"loss": 0.0,
|
| 61 |
+
"rewards/accuracies": 0.0,
|
| 62 |
+
"rewards/chosen": 0.0,
|
| 63 |
+
"rewards/margins": 0.0,
|
| 64 |
+
"rewards/rejected": 0.0,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.15515519678592682,
|
| 71 |
+
"logits/rejected": 0.2712388336658478,
|
| 72 |
+
"logps/chosen": -401.01165771484375,
|
| 73 |
+
"logps/rejected": -385.3412170410156,
|
| 74 |
+
"loss": 0.0,
|
| 75 |
+
"rewards/accuracies": 0.0,
|
| 76 |
+
"rewards/chosen": 0.0,
|
| 77 |
+
"rewards/margins": 0.0,
|
| 78 |
+
"rewards/rejected": 0.0,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.23549167811870575,
|
| 85 |
+
"logits/rejected": 0.27643483877182007,
|
| 86 |
+
"logps/chosen": -440.90948486328125,
|
| 87 |
+
"logps/rejected": -431.11541748046875,
|
| 88 |
+
"loss": 0.0,
|
| 89 |
+
"rewards/accuracies": 0.0,
|
| 90 |
+
"rewards/chosen": 0.0,
|
| 91 |
+
"rewards/margins": 0.0,
|
| 92 |
+
"rewards/rejected": 0.0,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.17448191344738007,
|
| 99 |
+
"logits/rejected": 0.3222740590572357,
|
| 100 |
+
"logps/chosen": -408.9176940917969,
|
| 101 |
+
"logps/rejected": -412.7042541503906,
|
| 102 |
+
"loss": 0.0,
|
| 103 |
+
"rewards/accuracies": 0.0,
|
| 104 |
+
"rewards/chosen": 0.0,
|
| 105 |
+
"rewards/margins": 0.0,
|
| 106 |
+
"rewards/rejected": 0.0,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.131931334733963,
|
| 113 |
+
"logits/rejected": 0.2314920872449875,
|
| 114 |
+
"logps/chosen": -354.6463623046875,
|
| 115 |
+
"logps/rejected": -355.9555969238281,
|
| 116 |
+
"loss": 0.0,
|
| 117 |
+
"rewards/accuracies": 0.0,
|
| 118 |
+
"rewards/chosen": 0.0,
|
| 119 |
+
"rewards/margins": 0.0,
|
| 120 |
+
"rewards/rejected": 0.0,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.15874435007572174,
|
| 127 |
+
"logits/rejected": 0.26632028818130493,
|
| 128 |
+
"logps/chosen": -392.85498046875,
|
| 129 |
+
"logps/rejected": -379.8575744628906,
|
| 130 |
+
"loss": 0.0,
|
| 131 |
+
"rewards/accuracies": 0.0,
|
| 132 |
+
"rewards/chosen": 0.0,
|
| 133 |
+
"rewards/margins": 0.0,
|
| 134 |
+
"rewards/rejected": 0.0,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.26180005073547363,
|
| 141 |
+
"logits/rejected": 0.19905249774456024,
|
| 142 |
+
"logps/chosen": -392.9334716796875,
|
| 143 |
+
"logps/rejected": -414.093017578125,
|
| 144 |
+
"loss": 0.0,
|
| 145 |
+
"rewards/accuracies": 0.0,
|
| 146 |
+
"rewards/chosen": 0.0,
|
| 147 |
+
"rewards/margins": 0.0,
|
| 148 |
+
"rewards/rejected": 0.0,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.1863372027873993,
|
| 155 |
+
"logits/rejected": 0.19517865777015686,
|
| 156 |
+
"logps/chosen": -417.194580078125,
|
| 157 |
+
"logps/rejected": -409.6343688964844,
|
| 158 |
+
"loss": 0.0,
|
| 159 |
+
"rewards/accuracies": 0.0,
|
| 160 |
+
"rewards/chosen": 0.0,
|
| 161 |
+
"rewards/margins": 0.0,
|
| 162 |
+
"rewards/rejected": 0.0,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.2684422731399536,
|
| 169 |
+
"logits/rejected": 0.19285789132118225,
|
| 170 |
+
"logps/chosen": -419.1029357910156,
|
| 171 |
+
"logps/rejected": -400.07568359375,
|
| 172 |
+
"loss": 0.0,
|
| 173 |
+
"rewards/accuracies": 0.0,
|
| 174 |
+
"rewards/chosen": 0.0,
|
| 175 |
+
"rewards/margins": 0.0,
|
| 176 |
+
"rewards/rejected": 0.0,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.1304994523525238,
|
| 183 |
+
"logits/rejected": 0.3027098774909973,
|
| 184 |
+
"logps/chosen": -414.75128173828125,
|
| 185 |
+
"logps/rejected": -442.08343505859375,
|
| 186 |
+
"loss": 0.0,
|
| 187 |
+
"rewards/accuracies": 0.0,
|
| 188 |
+
"rewards/chosen": 0.0,
|
| 189 |
+
"rewards/margins": 0.0,
|
| 190 |
+
"rewards/rejected": 0.0,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.21744604408740997,
|
| 197 |
+
"logits/rejected": 0.3507159650325775,
|
| 198 |
+
"logps/chosen": -412.56658935546875,
|
| 199 |
+
"logps/rejected": -398.8998107910156,
|
| 200 |
+
"loss": 0.0,
|
| 201 |
+
"rewards/accuracies": 0.0,
|
| 202 |
+
"rewards/chosen": 0.0,
|
| 203 |
+
"rewards/margins": 0.0,
|
| 204 |
+
"rewards/rejected": 0.0,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.2333650141954422,
|
| 211 |
+
"logits/rejected": 0.2951519191265106,
|
| 212 |
+
"logps/chosen": -384.1523132324219,
|
| 213 |
+
"logps/rejected": -364.6881408691406,
|
| 214 |
+
"loss": 0.0,
|
| 215 |
+
"rewards/accuracies": 0.0,
|
| 216 |
+
"rewards/chosen": 0.0,
|
| 217 |
+
"rewards/margins": 0.0,
|
| 218 |
+
"rewards/rejected": 0.0,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.12179046869277954,
|
| 225 |
+
"logits/rejected": 0.17499811947345734,
|
| 226 |
+
"logps/chosen": -382.7596740722656,
|
| 227 |
+
"logps/rejected": -385.5395812988281,
|
| 228 |
+
"loss": 0.0,
|
| 229 |
+
"rewards/accuracies": 0.0,
|
| 230 |
+
"rewards/chosen": 0.0,
|
| 231 |
+
"rewards/margins": 0.0,
|
| 232 |
+
"rewards/rejected": 0.0,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.2078637331724167,
|
| 239 |
+
"logits/rejected": 0.29525110125541687,
|
| 240 |
+
"logps/chosen": -423.19097900390625,
|
| 241 |
+
"logps/rejected": -411.33038330078125,
|
| 242 |
+
"loss": 0.0,
|
| 243 |
+
"rewards/accuracies": 0.0,
|
| 244 |
+
"rewards/chosen": 0.0,
|
| 245 |
+
"rewards/margins": 0.0,
|
| 246 |
+
"rewards/rejected": 0.0,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.17098727822303772,
|
| 253 |
+
"logits/rejected": 0.3464776873588562,
|
| 254 |
+
"logps/chosen": -440.69927978515625,
|
| 255 |
+
"logps/rejected": -413.71343994140625,
|
| 256 |
+
"loss": 0.0,
|
| 257 |
+
"rewards/accuracies": 0.0,
|
| 258 |
+
"rewards/chosen": 0.0,
|
| 259 |
+
"rewards/margins": 0.0,
|
| 260 |
+
"rewards/rejected": 0.0,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.2748049795627594,
|
| 267 |
+
"logits/rejected": 0.28834646940231323,
|
| 268 |
+
"logps/chosen": -381.0144958496094,
|
| 269 |
+
"logps/rejected": -380.5312805175781,
|
| 270 |
+
"loss": 0.0,
|
| 271 |
+
"rewards/accuracies": 0.0,
|
| 272 |
+
"rewards/chosen": 0.0,
|
| 273 |
+
"rewards/margins": 0.0,
|
| 274 |
+
"rewards/rejected": 0.0,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.21008631587028503,
|
| 281 |
+
"logits/rejected": 0.2946034371852875,
|
| 282 |
+
"logps/chosen": -484.1692810058594,
|
| 283 |
+
"logps/rejected": -452.757080078125,
|
| 284 |
+
"loss": 0.0,
|
| 285 |
+
"rewards/accuracies": 0.0,
|
| 286 |
+
"rewards/chosen": 0.0,
|
| 287 |
+
"rewards/margins": 0.0,
|
| 288 |
+
"rewards/rejected": 0.0,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.14078669250011444,
|
| 295 |
+
"logits/rejected": 0.28049755096435547,
|
| 296 |
+
"logps/chosen": -404.1522216796875,
|
| 297 |
+
"logps/rejected": -421.33856201171875,
|
| 298 |
+
"loss": 0.0,
|
| 299 |
+
"rewards/accuracies": 0.0,
|
| 300 |
+
"rewards/chosen": 0.0,
|
| 301 |
+
"rewards/margins": 0.0,
|
| 302 |
+
"rewards/rejected": 0.0,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.2193254977464676,
|
| 309 |
+
"logits/rejected": 0.22546172142028809,
|
| 310 |
+
"logps/chosen": -401.60546875,
|
| 311 |
+
"logps/rejected": -405.28582763671875,
|
| 312 |
+
"loss": 0.0,
|
| 313 |
+
"rewards/accuracies": 0.0,
|
| 314 |
+
"rewards/chosen": 0.0,
|
| 315 |
+
"rewards/margins": 0.0,
|
| 316 |
+
"rewards/rejected": 0.0,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.22740697860717773,
|
| 323 |
+
"logits/rejected": 0.2075118124485016,
|
| 324 |
+
"logps/chosen": -401.9066467285156,
|
| 325 |
+
"logps/rejected": -396.5219421386719,
|
| 326 |
+
"loss": 0.0,
|
| 327 |
+
"rewards/accuracies": 0.0,
|
| 328 |
+
"rewards/chosen": 0.0,
|
| 329 |
+
"rewards/margins": 0.0,
|
| 330 |
+
"rewards/rejected": 0.0,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": 0.2253454476594925,
|
| 337 |
+
"logits/rejected": 0.24970141053199768,
|
| 338 |
+
"logps/chosen": -399.9390563964844,
|
| 339 |
+
"logps/rejected": -400.8056335449219,
|
| 340 |
+
"loss": 0.0,
|
| 341 |
+
"rewards/accuracies": 0.0,
|
| 342 |
+
"rewards/chosen": 0.0,
|
| 343 |
+
"rewards/margins": 0.0,
|
| 344 |
+
"rewards/rejected": 0.0,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": 0.09361274540424347,
|
| 351 |
+
"logits/rejected": 0.2551277279853821,
|
| 352 |
+
"logps/chosen": -377.5755310058594,
|
| 353 |
+
"logps/rejected": -380.84381103515625,
|
| 354 |
+
"loss": 0.0,
|
| 355 |
+
"rewards/accuracies": 0.0,
|
| 356 |
+
"rewards/chosen": 0.0,
|
| 357 |
+
"rewards/margins": 0.0,
|
| 358 |
+
"rewards/rejected": 0.0,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": 0.21397773921489716,
|
| 365 |
+
"logits/rejected": 0.27325302362442017,
|
| 366 |
+
"logps/chosen": -414.1591796875,
|
| 367 |
+
"logps/rejected": -400.00323486328125,
|
| 368 |
+
"loss": 0.0,
|
| 369 |
+
"rewards/accuracies": 0.0,
|
| 370 |
+
"rewards/chosen": 0.0,
|
| 371 |
+
"rewards/margins": 0.0,
|
| 372 |
+
"rewards/rejected": 0.0,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": 0.20620456337928772,
|
| 379 |
+
"logits/rejected": 0.25625258684158325,
|
| 380 |
+
"logps/chosen": -431.2455139160156,
|
| 381 |
+
"logps/rejected": -444.0306701660156,
|
| 382 |
+
"loss": 0.0,
|
| 383 |
+
"rewards/accuracies": 0.0,
|
| 384 |
+
"rewards/chosen": 0.0,
|
| 385 |
+
"rewards/margins": 0.0,
|
| 386 |
+
"rewards/rejected": 0.0,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": 0.17776310443878174,
|
| 393 |
+
"logits/rejected": 0.22469878196716309,
|
| 394 |
+
"logps/chosen": -433.8826599121094,
|
| 395 |
+
"logps/rejected": -453.208740234375,
|
| 396 |
+
"loss": 0.0,
|
| 397 |
+
"rewards/accuracies": 0.0,
|
| 398 |
+
"rewards/chosen": 0.0,
|
| 399 |
+
"rewards/margins": 0.0,
|
| 400 |
+
"rewards/rejected": 0.0,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": 0.16825468838214874,
|
| 407 |
+
"logits/rejected": 0.25171762704849243,
|
| 408 |
+
"logps/chosen": -408.1540832519531,
|
| 409 |
+
"logps/rejected": -394.03704833984375,
|
| 410 |
+
"loss": 0.0,
|
| 411 |
+
"rewards/accuracies": 0.0,
|
| 412 |
+
"rewards/chosen": 0.0,
|
| 413 |
+
"rewards/margins": 0.0,
|
| 414 |
+
"rewards/rejected": 0.0,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": 0.17698076367378235,
|
| 421 |
+
"logits/rejected": 0.2516983151435852,
|
| 422 |
+
"logps/chosen": -402.94781494140625,
|
| 423 |
+
"logps/rejected": -432.970947265625,
|
| 424 |
+
"loss": 0.0,
|
| 425 |
+
"rewards/accuracies": 0.0,
|
| 426 |
+
"rewards/chosen": 0.0,
|
| 427 |
+
"rewards/margins": 0.0,
|
| 428 |
+
"rewards/rejected": 0.0,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": 0.2270512878894806,
|
| 435 |
+
"logits/rejected": 0.2209252119064331,
|
| 436 |
+
"logps/chosen": -423.2540588378906,
|
| 437 |
+
"logps/rejected": -388.04620361328125,
|
| 438 |
+
"loss": 0.0,
|
| 439 |
+
"rewards/accuracies": 0.0,
|
| 440 |
+
"rewards/chosen": 0.0,
|
| 441 |
+
"rewards/margins": 0.0,
|
| 442 |
+
"rewards/rejected": 0.0,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": 0.1234111562371254,
|
| 449 |
+
"logits/rejected": 0.27970707416534424,
|
| 450 |
+
"logps/chosen": -379.5980529785156,
|
| 451 |
+
"logps/rejected": -379.2107849121094,
|
| 452 |
+
"loss": 0.0,
|
| 453 |
+
"rewards/accuracies": 0.0,
|
| 454 |
+
"rewards/chosen": 0.0,
|
| 455 |
+
"rewards/margins": 0.0,
|
| 456 |
+
"rewards/rejected": 0.0,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": 0.20214669406414032,
|
| 463 |
+
"logits/rejected": 0.2584760785102844,
|
| 464 |
+
"logps/chosen": -382.29937744140625,
|
| 465 |
+
"logps/rejected": -370.25616455078125,
|
| 466 |
+
"loss": 0.0,
|
| 467 |
+
"rewards/accuracies": 0.0,
|
| 468 |
+
"rewards/chosen": 0.0,
|
| 469 |
+
"rewards/margins": 0.0,
|
| 470 |
+
"rewards/rejected": 0.0,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": 0.24651730060577393,
|
| 477 |
+
"logits/rejected": 0.24896959960460663,
|
| 478 |
+
"logps/chosen": -437.11859130859375,
|
| 479 |
+
"logps/rejected": -405.49566650390625,
|
| 480 |
+
"loss": 0.0,
|
| 481 |
+
"rewards/accuracies": 0.0,
|
| 482 |
+
"rewards/chosen": 0.0,
|
| 483 |
+
"rewards/margins": 0.0,
|
| 484 |
+
"rewards/rejected": 0.0,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": 0.28022533655166626,
|
| 491 |
+
"logits/rejected": 0.31104576587677,
|
| 492 |
+
"logps/chosen": -419.55438232421875,
|
| 493 |
+
"logps/rejected": -423.57391357421875,
|
| 494 |
+
"loss": 0.0,
|
| 495 |
+
"rewards/accuracies": 0.0,
|
| 496 |
+
"rewards/chosen": 0.0,
|
| 497 |
+
"rewards/margins": 0.0,
|
| 498 |
+
"rewards/rejected": 0.0,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.18333196640014648,
|
| 505 |
+
"logits/rejected": 0.3204515278339386,
|
| 506 |
+
"logps/chosen": -437.1458435058594,
|
| 507 |
+
"logps/rejected": -431.79461669921875,
|
| 508 |
+
"loss": 0.0,
|
| 509 |
+
"rewards/accuracies": 0.0,
|
| 510 |
+
"rewards/chosen": 0.0,
|
| 511 |
+
"rewards/margins": 0.0,
|
| 512 |
+
"rewards/rejected": 0.0,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": 0.11528631299734116,
|
| 519 |
+
"logits/rejected": 0.2239673137664795,
|
| 520 |
+
"logps/chosen": -450.3658142089844,
|
| 521 |
+
"logps/rejected": -414.203369140625,
|
| 522 |
+
"loss": 0.0,
|
| 523 |
+
"rewards/accuracies": 0.0,
|
| 524 |
+
"rewards/chosen": 0.0,
|
| 525 |
+
"rewards/margins": 0.0,
|
| 526 |
+
"rewards/rejected": 0.0,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": 0.24927763640880585,
|
| 533 |
+
"logits/rejected": 0.26546379923820496,
|
| 534 |
+
"logps/chosen": -399.69439697265625,
|
| 535 |
+
"logps/rejected": -403.4917907714844,
|
| 536 |
+
"loss": 0.0,
|
| 537 |
+
"rewards/accuracies": 0.0,
|
| 538 |
+
"rewards/chosen": 0.0,
|
| 539 |
+
"rewards/margins": 0.0,
|
| 540 |
+
"rewards/rejected": 0.0,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": 0.11166371405124664,
|
| 547 |
+
"logits/rejected": 0.2701989710330963,
|
| 548 |
+
"logps/chosen": -404.04449462890625,
|
| 549 |
+
"logps/rejected": -379.7621765136719,
|
| 550 |
+
"loss": 0.0,
|
| 551 |
+
"rewards/accuracies": 0.0,
|
| 552 |
+
"rewards/chosen": 0.0,
|
| 553 |
+
"rewards/margins": 0.0,
|
| 554 |
+
"rewards/rejected": 0.0,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": 0.17965979874134064,
|
| 561 |
+
"logits/rejected": 0.2478092461824417,
|
| 562 |
+
"logps/chosen": -421.53173828125,
|
| 563 |
+
"logps/rejected": -430.0699768066406,
|
| 564 |
+
"loss": 0.0,
|
| 565 |
+
"rewards/accuracies": 0.0,
|
| 566 |
+
"rewards/chosen": 0.0,
|
| 567 |
+
"rewards/margins": 0.0,
|
| 568 |
+
"rewards/rejected": 0.0,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": 0.2598588168621063,
|
| 575 |
+
"logits/rejected": 0.292039692401886,
|
| 576 |
+
"logps/chosen": -423.152099609375,
|
| 577 |
+
"logps/rejected": -419.819091796875,
|
| 578 |
+
"loss": 0.0,
|
| 579 |
+
"rewards/accuracies": 0.0,
|
| 580 |
+
"rewards/chosen": 0.0,
|
| 581 |
+
"rewards/margins": 0.0,
|
| 582 |
+
"rewards/rejected": 0.0,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": 0.2145676165819168,
|
| 589 |
+
"logits/rejected": 0.2213706225156784,
|
| 590 |
+
"logps/chosen": -421.8087463378906,
|
| 591 |
+
"logps/rejected": -441.27716064453125,
|
| 592 |
+
"loss": 0.0,
|
| 593 |
+
"rewards/accuracies": 0.0,
|
| 594 |
+
"rewards/chosen": 0.0,
|
| 595 |
+
"rewards/margins": 0.0,
|
| 596 |
+
"rewards/rejected": 0.0,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": 0.23070721328258514,
|
| 603 |
+
"logits/rejected": 0.2725136876106262,
|
| 604 |
+
"logps/chosen": -446.6600036621094,
|
| 605 |
+
"logps/rejected": -443.410400390625,
|
| 606 |
+
"loss": 0.0,
|
| 607 |
+
"rewards/accuracies": 0.0,
|
| 608 |
+
"rewards/chosen": 0.0,
|
| 609 |
+
"rewards/margins": 0.0,
|
| 610 |
+
"rewards/rejected": 0.0,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": 0.22015449404716492,
|
| 617 |
+
"logits/rejected": 0.22397899627685547,
|
| 618 |
+
"logps/chosen": -367.9841613769531,
|
| 619 |
+
"logps/rejected": -366.0374450683594,
|
| 620 |
+
"loss": 0.0,
|
| 621 |
+
"rewards/accuracies": 0.0,
|
| 622 |
+
"rewards/chosen": 0.0,
|
| 623 |
+
"rewards/margins": 0.0,
|
| 624 |
+
"rewards/rejected": 0.0,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": 0.22503578662872314,
|
| 631 |
+
"logits/rejected": 0.2497364729642868,
|
| 632 |
+
"logps/chosen": -451.5084533691406,
|
| 633 |
+
"logps/rejected": -441.224365234375,
|
| 634 |
+
"loss": 0.0,
|
| 635 |
+
"rewards/accuracies": 0.0,
|
| 636 |
+
"rewards/chosen": 0.0,
|
| 637 |
+
"rewards/margins": 0.0,
|
| 638 |
+
"rewards/rejected": 0.0,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": 0.21670684218406677,
|
| 645 |
+
"logits/rejected": 0.2709944248199463,
|
| 646 |
+
"logps/chosen": -425.6534729003906,
|
| 647 |
+
"logps/rejected": -408.99920654296875,
|
| 648 |
+
"loss": 0.0,
|
| 649 |
+
"rewards/accuracies": 0.0,
|
| 650 |
+
"rewards/chosen": 0.0,
|
| 651 |
+
"rewards/margins": 0.0,
|
| 652 |
+
"rewards/rejected": 0.0,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": 0.2238447666168213,
|
| 659 |
+
"logits/rejected": 0.28349417448043823,
|
| 660 |
+
"logps/chosen": -438.446533203125,
|
| 661 |
+
"logps/rejected": -419.7816467285156,
|
| 662 |
+
"loss": 0.0,
|
| 663 |
+
"rewards/accuracies": 0.0,
|
| 664 |
+
"rewards/chosen": 0.0,
|
| 665 |
+
"rewards/margins": 0.0,
|
| 666 |
+
"rewards/rejected": 0.0,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": 0.21700212359428406,
|
| 673 |
+
"logits/rejected": 0.250012069940567,
|
| 674 |
+
"logps/chosen": -414.27703857421875,
|
| 675 |
+
"logps/rejected": -413.127197265625,
|
| 676 |
+
"loss": 0.0,
|
| 677 |
+
"rewards/accuracies": 0.0,
|
| 678 |
+
"rewards/chosen": 0.0,
|
| 679 |
+
"rewards/margins": 0.0,
|
| 680 |
+
"rewards/rejected": 0.0,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": 0.18912899494171143,
|
| 687 |
+
"logits/rejected": 0.30137619376182556,
|
| 688 |
+
"logps/chosen": -388.0596923828125,
|
| 689 |
+
"logps/rejected": -392.78375244140625,
|
| 690 |
+
"loss": 0.0,
|
| 691 |
+
"rewards/accuracies": 0.0,
|
| 692 |
+
"rewards/chosen": 0.0,
|
| 693 |
+
"rewards/margins": 0.0,
|
| 694 |
+
"rewards/rejected": 0.0,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": 0.257573664188385,
|
| 701 |
+
"logits/rejected": 0.27977752685546875,
|
| 702 |
+
"logps/chosen": -377.6993713378906,
|
| 703 |
+
"logps/rejected": -384.7877197265625,
|
| 704 |
+
"loss": 0.0,
|
| 705 |
+
"rewards/accuracies": 0.0,
|
| 706 |
+
"rewards/chosen": 0.0,
|
| 707 |
+
"rewards/margins": 0.0,
|
| 708 |
+
"rewards/rejected": 0.0,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": 0.18493638932704926,
|
| 715 |
+
"logits/rejected": 0.15904666483402252,
|
| 716 |
+
"logps/chosen": -369.86480712890625,
|
| 717 |
+
"logps/rejected": -374.7712097167969,
|
| 718 |
+
"loss": 0.0,
|
| 719 |
+
"rewards/accuracies": 0.0,
|
| 720 |
+
"rewards/chosen": 0.0,
|
| 721 |
+
"rewards/margins": 0.0,
|
| 722 |
+
"rewards/rejected": 0.0,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": 0.2099113166332245,
|
| 729 |
+
"logits/rejected": 0.26101061701774597,
|
| 730 |
+
"logps/chosen": -445.0758361816406,
|
| 731 |
+
"logps/rejected": -431.1841735839844,
|
| 732 |
+
"loss": 0.0,
|
| 733 |
+
"rewards/accuracies": 0.0,
|
| 734 |
+
"rewards/chosen": 0.0,
|
| 735 |
+
"rewards/margins": 0.0,
|
| 736 |
+
"rewards/rejected": 0.0,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": 0.15272489190101624,
|
| 743 |
+
"logits/rejected": 0.2410932034254074,
|
| 744 |
+
"logps/chosen": -411.3912658691406,
|
| 745 |
+
"logps/rejected": -378.7525939941406,
|
| 746 |
+
"loss": 0.0,
|
| 747 |
+
"rewards/accuracies": 0.0,
|
| 748 |
+
"rewards/chosen": 0.0,
|
| 749 |
+
"rewards/margins": 0.0,
|
| 750 |
+
"rewards/rejected": 0.0,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": 0.2886171042919159,
|
| 757 |
+
"logits/rejected": 0.24891161918640137,
|
| 758 |
+
"logps/chosen": -412.112548828125,
|
| 759 |
+
"logps/rejected": -403.3191223144531,
|
| 760 |
+
"loss": 0.0,
|
| 761 |
+
"rewards/accuracies": 0.0,
|
| 762 |
+
"rewards/chosen": 0.0,
|
| 763 |
+
"rewards/margins": 0.0,
|
| 764 |
+
"rewards/rejected": 0.0,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": 0.14852824807167053,
|
| 771 |
+
"logits/rejected": 0.23693397641181946,
|
| 772 |
+
"logps/chosen": -404.3973693847656,
|
| 773 |
+
"logps/rejected": -389.05389404296875,
|
| 774 |
+
"loss": 0.0,
|
| 775 |
+
"rewards/accuracies": 0.0,
|
| 776 |
+
"rewards/chosen": 0.0,
|
| 777 |
+
"rewards/margins": 0.0,
|
| 778 |
+
"rewards/rejected": 0.0,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": 0.16628649830818176,
|
| 785 |
+
"logits/rejected": 0.27538853883743286,
|
| 786 |
+
"logps/chosen": -418.27752685546875,
|
| 787 |
+
"logps/rejected": -411.8797302246094,
|
| 788 |
+
"loss": 0.0,
|
| 789 |
+
"rewards/accuracies": 0.0,
|
| 790 |
+
"rewards/chosen": 0.0,
|
| 791 |
+
"rewards/margins": 0.0,
|
| 792 |
+
"rewards/rejected": 0.0,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": 0.25115758180618286,
|
| 799 |
+
"logits/rejected": 0.27927032113075256,
|
| 800 |
+
"logps/chosen": -378.09954833984375,
|
| 801 |
+
"logps/rejected": -408.1378173828125,
|
| 802 |
+
"loss": 0.0,
|
| 803 |
+
"rewards/accuracies": 0.0,
|
| 804 |
+
"rewards/chosen": 0.0,
|
| 805 |
+
"rewards/margins": 0.0,
|
| 806 |
+
"rewards/rejected": 0.0,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": 0.15070781111717224,
|
| 813 |
+
"logits/rejected": 0.18165943026542664,
|
| 814 |
+
"logps/chosen": -366.8854064941406,
|
| 815 |
+
"logps/rejected": -366.2696533203125,
|
| 816 |
+
"loss": 0.0,
|
| 817 |
+
"rewards/accuracies": 0.0,
|
| 818 |
+
"rewards/chosen": 0.0,
|
| 819 |
+
"rewards/margins": 0.0,
|
| 820 |
+
"rewards/rejected": 0.0,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": 0.2222457379102707,
|
| 827 |
+
"logits/rejected": 0.27251940965652466,
|
| 828 |
+
"logps/chosen": -410.501708984375,
|
| 829 |
+
"logps/rejected": -397.37176513671875,
|
| 830 |
+
"loss": 0.0,
|
| 831 |
+
"rewards/accuracies": 0.0,
|
| 832 |
+
"rewards/chosen": 0.0,
|
| 833 |
+
"rewards/margins": 0.0,
|
| 834 |
+
"rewards/rejected": 0.0,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": 0.20956209301948547,
|
| 841 |
+
"logits/rejected": 0.33177804946899414,
|
| 842 |
+
"logps/chosen": -430.733154296875,
|
| 843 |
+
"logps/rejected": -419.57171630859375,
|
| 844 |
+
"loss": 0.0,
|
| 845 |
+
"rewards/accuracies": 0.0,
|
| 846 |
+
"rewards/chosen": 0.0,
|
| 847 |
+
"rewards/margins": 0.0,
|
| 848 |
+
"rewards/rejected": 0.0,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": 0.18513911962509155,
|
| 855 |
+
"logits/rejected": 0.23731224238872528,
|
| 856 |
+
"logps/chosen": -357.6490173339844,
|
| 857 |
+
"logps/rejected": -381.7027893066406,
|
| 858 |
+
"loss": 0.0,
|
| 859 |
+
"rewards/accuracies": 0.0,
|
| 860 |
+
"rewards/chosen": 0.0,
|
| 861 |
+
"rewards/margins": 0.0,
|
| 862 |
+
"rewards/rejected": 0.0,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": 0.15748406946659088,
|
| 869 |
+
"logits/rejected": 0.15097612142562866,
|
| 870 |
+
"logps/chosen": -408.1110534667969,
|
| 871 |
+
"logps/rejected": -388.00592041015625,
|
| 872 |
+
"loss": 0.0,
|
| 873 |
+
"rewards/accuracies": 0.0,
|
| 874 |
+
"rewards/chosen": 0.0,
|
| 875 |
+
"rewards/margins": 0.0,
|
| 876 |
+
"rewards/rejected": 0.0,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": 0.2554689049720764,
|
| 883 |
+
"logits/rejected": 0.17269960045814514,
|
| 884 |
+
"logps/chosen": -394.124755859375,
|
| 885 |
+
"logps/rejected": -425.56640625,
|
| 886 |
+
"loss": 0.0,
|
| 887 |
+
"rewards/accuracies": 0.0,
|
| 888 |
+
"rewards/chosen": 0.0,
|
| 889 |
+
"rewards/margins": 0.0,
|
| 890 |
+
"rewards/rejected": 0.0,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": 0.17127978801727295,
|
| 897 |
+
"logits/rejected": 0.19732491672039032,
|
| 898 |
+
"logps/chosen": -372.42608642578125,
|
| 899 |
+
"logps/rejected": -354.8905944824219,
|
| 900 |
+
"loss": 0.0,
|
| 901 |
+
"rewards/accuracies": 0.0,
|
| 902 |
+
"rewards/chosen": 0.0,
|
| 903 |
+
"rewards/margins": 0.0,
|
| 904 |
+
"rewards/rejected": 0.0,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": 0.15929067134857178,
|
| 911 |
+
"logits/rejected": 0.21373197436332703,
|
| 912 |
+
"logps/chosen": -389.2451477050781,
|
| 913 |
+
"logps/rejected": -373.00384521484375,
|
| 914 |
+
"loss": 0.0,
|
| 915 |
+
"rewards/accuracies": 0.0,
|
| 916 |
+
"rewards/chosen": 0.0,
|
| 917 |
+
"rewards/margins": 0.0,
|
| 918 |
+
"rewards/rejected": 0.0,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": 0.16366329789161682,
|
| 925 |
+
"logits/rejected": 0.35690051317214966,
|
| 926 |
+
"logps/chosen": -423.4112854003906,
|
| 927 |
+
"logps/rejected": -407.52838134765625,
|
| 928 |
+
"loss": 0.0,
|
| 929 |
+
"rewards/accuracies": 0.0,
|
| 930 |
+
"rewards/chosen": 0.0,
|
| 931 |
+
"rewards/margins": 0.0,
|
| 932 |
+
"rewards/rejected": 0.0,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": 0.1489204317331314,
|
| 939 |
+
"logits/rejected": 0.2767201364040375,
|
| 940 |
+
"logps/chosen": -428.436279296875,
|
| 941 |
+
"logps/rejected": -410.24310302734375,
|
| 942 |
+
"loss": 0.0,
|
| 943 |
+
"rewards/accuracies": 0.0,
|
| 944 |
+
"rewards/chosen": 0.0,
|
| 945 |
+
"rewards/margins": 0.0,
|
| 946 |
+
"rewards/rejected": 0.0,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": 0.2932317554950714,
|
| 953 |
+
"logits/rejected": 0.2427135407924652,
|
| 954 |
+
"logps/chosen": -389.24945068359375,
|
| 955 |
+
"logps/rejected": -385.98431396484375,
|
| 956 |
+
"loss": 0.0,
|
| 957 |
+
"rewards/accuracies": 0.0,
|
| 958 |
+
"rewards/chosen": 0.0,
|
| 959 |
+
"rewards/margins": 0.0,
|
| 960 |
+
"rewards/rejected": 0.0,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": 0.2365073710680008,
|
| 967 |
+
"logits/rejected": 0.2310241162776947,
|
| 968 |
+
"logps/chosen": -370.1266174316406,
|
| 969 |
+
"logps/rejected": -356.8659973144531,
|
| 970 |
+
"loss": 0.0,
|
| 971 |
+
"rewards/accuracies": 0.0,
|
| 972 |
+
"rewards/chosen": 0.0,
|
| 973 |
+
"rewards/margins": 0.0,
|
| 974 |
+
"rewards/rejected": 0.0,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": 0.15916849672794342,
|
| 981 |
+
"logits/rejected": 0.27135321497917175,
|
| 982 |
+
"logps/chosen": -395.91595458984375,
|
| 983 |
+
"logps/rejected": -390.37420654296875,
|
| 984 |
+
"loss": 0.0,
|
| 985 |
+
"rewards/accuracies": 0.0,
|
| 986 |
+
"rewards/chosen": 0.0,
|
| 987 |
+
"rewards/margins": 0.0,
|
| 988 |
+
"rewards/rejected": 0.0,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": 0.15306909382343292,
|
| 995 |
+
"logits/rejected": 0.2204822301864624,
|
| 996 |
+
"logps/chosen": -395.4036865234375,
|
| 997 |
+
"logps/rejected": -399.2796325683594,
|
| 998 |
+
"loss": 0.0,
|
| 999 |
+
"rewards/accuracies": 0.0,
|
| 1000 |
+
"rewards/chosen": 0.0,
|
| 1001 |
+
"rewards/margins": 0.0,
|
| 1002 |
+
"rewards/rejected": 0.0,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": 0.17490191757678986,
|
| 1009 |
+
"logits/rejected": 0.27996110916137695,
|
| 1010 |
+
"logps/chosen": -409.8934631347656,
|
| 1011 |
+
"logps/rejected": -411.23480224609375,
|
| 1012 |
+
"loss": 0.0,
|
| 1013 |
+
"rewards/accuracies": 0.0,
|
| 1014 |
+
"rewards/chosen": 0.0,
|
| 1015 |
+
"rewards/margins": 0.0,
|
| 1016 |
+
"rewards/rejected": 0.0,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": 0.20883989334106445,
|
| 1023 |
+
"logits/rejected": 0.22538049519062042,
|
| 1024 |
+
"logps/chosen": -420.298095703125,
|
| 1025 |
+
"logps/rejected": -409.4375305175781,
|
| 1026 |
+
"loss": 0.0,
|
| 1027 |
+
"rewards/accuracies": 0.0,
|
| 1028 |
+
"rewards/chosen": 0.0,
|
| 1029 |
+
"rewards/margins": 0.0,
|
| 1030 |
+
"rewards/rejected": 0.0,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": 0.2503129839897156,
|
| 1037 |
+
"logits/rejected": 0.21712422370910645,
|
| 1038 |
+
"logps/chosen": -424.7351989746094,
|
| 1039 |
+
"logps/rejected": -402.7471618652344,
|
| 1040 |
+
"loss": 0.0,
|
| 1041 |
+
"rewards/accuracies": 0.0,
|
| 1042 |
+
"rewards/chosen": 0.0,
|
| 1043 |
+
"rewards/margins": 0.0,
|
| 1044 |
+
"rewards/rejected": 0.0,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": 0.18410465121269226,
|
| 1051 |
+
"logits/rejected": 0.2769954800605774,
|
| 1052 |
+
"logps/chosen": -381.27532958984375,
|
| 1053 |
+
"logps/rejected": -350.406494140625,
|
| 1054 |
+
"loss": 0.0,
|
| 1055 |
+
"rewards/accuracies": 0.0,
|
| 1056 |
+
"rewards/chosen": 0.0,
|
| 1057 |
+
"rewards/margins": 0.0,
|
| 1058 |
+
"rewards/rejected": 0.0,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": 0.19894076883792877,
|
| 1065 |
+
"logits/rejected": 0.2793256342411041,
|
| 1066 |
+
"logps/chosen": -423.1390075683594,
|
| 1067 |
+
"logps/rejected": -429.28472900390625,
|
| 1068 |
+
"loss": 0.0,
|
| 1069 |
+
"rewards/accuracies": 0.0,
|
| 1070 |
+
"rewards/chosen": 0.0,
|
| 1071 |
+
"rewards/margins": 0.0,
|
| 1072 |
+
"rewards/rejected": 0.0,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": 0.14793696999549866,
|
| 1079 |
+
"logits/rejected": 0.34965780377388,
|
| 1080 |
+
"logps/chosen": -386.9423522949219,
|
| 1081 |
+
"logps/rejected": -361.16180419921875,
|
| 1082 |
+
"loss": 0.0,
|
| 1083 |
+
"rewards/accuracies": 0.0,
|
| 1084 |
+
"rewards/chosen": 0.0,
|
| 1085 |
+
"rewards/margins": 0.0,
|
| 1086 |
+
"rewards/rejected": 0.0,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": 0.1257942169904709,
|
| 1093 |
+
"logits/rejected": 0.19840510189533234,
|
| 1094 |
+
"logps/chosen": -433.75634765625,
|
| 1095 |
+
"logps/rejected": -401.2398376464844,
|
| 1096 |
+
"loss": 0.0,
|
| 1097 |
+
"rewards/accuracies": 0.0,
|
| 1098 |
+
"rewards/chosen": 0.0,
|
| 1099 |
+
"rewards/margins": 0.0,
|
| 1100 |
+
"rewards/rejected": 0.0,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": 0.1670645773410797,
|
| 1107 |
+
"logits/rejected": 0.28423744440078735,
|
| 1108 |
+
"logps/chosen": -436.582763671875,
|
| 1109 |
+
"logps/rejected": -441.0210876464844,
|
| 1110 |
+
"loss": 0.0,
|
| 1111 |
+
"rewards/accuracies": 0.0,
|
| 1112 |
+
"rewards/chosen": 0.0,
|
| 1113 |
+
"rewards/margins": 0.0,
|
| 1114 |
+
"rewards/rejected": 0.0,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": 0.2583349943161011,
|
| 1121 |
+
"logits/rejected": 0.29037925601005554,
|
| 1122 |
+
"logps/chosen": -402.0462951660156,
|
| 1123 |
+
"logps/rejected": -401.1708068847656,
|
| 1124 |
+
"loss": 0.0,
|
| 1125 |
+
"rewards/accuracies": 0.0,
|
| 1126 |
+
"rewards/chosen": 0.0,
|
| 1127 |
+
"rewards/margins": 0.0,
|
| 1128 |
+
"rewards/rejected": 0.0,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": 0.15391795337200165,
|
| 1135 |
+
"logits/rejected": 0.2551635205745697,
|
| 1136 |
+
"logps/chosen": -418.2384338378906,
|
| 1137 |
+
"logps/rejected": -386.5793762207031,
|
| 1138 |
+
"loss": 0.0,
|
| 1139 |
+
"rewards/accuracies": 0.0,
|
| 1140 |
+
"rewards/chosen": 0.0,
|
| 1141 |
+
"rewards/margins": 0.0,
|
| 1142 |
+
"rewards/rejected": 0.0,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": 0.24473810195922852,
|
| 1149 |
+
"logits/rejected": 0.2084934264421463,
|
| 1150 |
+
"logps/chosen": -445.95849609375,
|
| 1151 |
+
"logps/rejected": -444.5816345214844,
|
| 1152 |
+
"loss": 0.0,
|
| 1153 |
+
"rewards/accuracies": 0.0,
|
| 1154 |
+
"rewards/chosen": 0.0,
|
| 1155 |
+
"rewards/margins": 0.0,
|
| 1156 |
+
"rewards/rejected": 0.0,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": 0.14975102245807648,
|
| 1163 |
+
"logits/rejected": 0.33251649141311646,
|
| 1164 |
+
"logps/chosen": -438.55206298828125,
|
| 1165 |
+
"logps/rejected": -396.28961181640625,
|
| 1166 |
+
"loss": 0.0,
|
| 1167 |
+
"rewards/accuracies": 0.0,
|
| 1168 |
+
"rewards/chosen": 0.0,
|
| 1169 |
+
"rewards/margins": 0.0,
|
| 1170 |
+
"rewards/rejected": 0.0,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": 0.28815943002700806,
|
| 1177 |
+
"logits/rejected": 0.2893601059913635,
|
| 1178 |
+
"logps/chosen": -418.80413818359375,
|
| 1179 |
+
"logps/rejected": -398.5482177734375,
|
| 1180 |
+
"loss": 0.0,
|
| 1181 |
+
"rewards/accuracies": 0.0,
|
| 1182 |
+
"rewards/chosen": 0.0,
|
| 1183 |
+
"rewards/margins": 0.0,
|
| 1184 |
+
"rewards/rejected": 0.0,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": 0.14490856230258942,
|
| 1191 |
+
"logits/rejected": 0.22375395894050598,
|
| 1192 |
+
"logps/chosen": -368.81512451171875,
|
| 1193 |
+
"logps/rejected": -351.7200012207031,
|
| 1194 |
+
"loss": 0.0,
|
| 1195 |
+
"rewards/accuracies": 0.0,
|
| 1196 |
+
"rewards/chosen": 0.0,
|
| 1197 |
+
"rewards/margins": 0.0,
|
| 1198 |
+
"rewards/rejected": 0.0,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": 0.1880328208208084,
|
| 1205 |
+
"logits/rejected": 0.25640177726745605,
|
| 1206 |
+
"logps/chosen": -419.2107849121094,
|
| 1207 |
+
"logps/rejected": -408.9618835449219,
|
| 1208 |
+
"loss": 0.0,
|
| 1209 |
+
"rewards/accuracies": 0.0,
|
| 1210 |
+
"rewards/chosen": 0.0,
|
| 1211 |
+
"rewards/margins": 0.0,
|
| 1212 |
+
"rewards/rejected": 0.0,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": 0.34192991256713867,
|
| 1219 |
+
"logits/rejected": 0.2116626501083374,
|
| 1220 |
+
"logps/chosen": -400.17901611328125,
|
| 1221 |
+
"logps/rejected": -410.69036865234375,
|
| 1222 |
+
"loss": 0.0,
|
| 1223 |
+
"rewards/accuracies": 0.0,
|
| 1224 |
+
"rewards/chosen": 0.0,
|
| 1225 |
+
"rewards/margins": 0.0,
|
| 1226 |
+
"rewards/rejected": 0.0,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": 0.2738000750541687,
|
| 1233 |
+
"logits/rejected": 0.19856445491313934,
|
| 1234 |
+
"logps/chosen": -449.3203125,
|
| 1235 |
+
"logps/rejected": -424.33392333984375,
|
| 1236 |
+
"loss": 0.0,
|
| 1237 |
+
"rewards/accuracies": 0.0,
|
| 1238 |
+
"rewards/chosen": 0.0,
|
| 1239 |
+
"rewards/margins": 0.0,
|
| 1240 |
+
"rewards/rejected": 0.0,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": 0.1780010461807251,
|
| 1247 |
+
"logits/rejected": 0.23323968052864075,
|
| 1248 |
+
"logps/chosen": -403.2125244140625,
|
| 1249 |
+
"logps/rejected": -399.965087890625,
|
| 1250 |
+
"loss": 0.0,
|
| 1251 |
+
"rewards/accuracies": 0.0,
|
| 1252 |
+
"rewards/chosen": 0.0,
|
| 1253 |
+
"rewards/margins": 0.0,
|
| 1254 |
+
"rewards/rejected": 0.0,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": 0.14893004298210144,
|
| 1261 |
+
"logits/rejected": 0.25546133518218994,
|
| 1262 |
+
"logps/chosen": -415.7379455566406,
|
| 1263 |
+
"logps/rejected": -399.75103759765625,
|
| 1264 |
+
"loss": 0.0,
|
| 1265 |
+
"rewards/accuracies": 0.0,
|
| 1266 |
+
"rewards/chosen": 0.0,
|
| 1267 |
+
"rewards/margins": 0.0,
|
| 1268 |
+
"rewards/rejected": 0.0,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": 0.2190527468919754,
|
| 1275 |
+
"logits/rejected": 0.18029525876045227,
|
| 1276 |
+
"logps/chosen": -382.27874755859375,
|
| 1277 |
+
"logps/rejected": -406.80657958984375,
|
| 1278 |
+
"loss": 0.0,
|
| 1279 |
+
"rewards/accuracies": 0.0,
|
| 1280 |
+
"rewards/chosen": 0.0,
|
| 1281 |
+
"rewards/margins": 0.0,
|
| 1282 |
+
"rewards/rejected": 0.0,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": 0.22972765564918518,
|
| 1289 |
+
"logits/rejected": 0.21643073856830597,
|
| 1290 |
+
"logps/chosen": -430.3443298339844,
|
| 1291 |
+
"logps/rejected": -428.8854064941406,
|
| 1292 |
+
"loss": 0.0,
|
| 1293 |
+
"rewards/accuracies": 0.0,
|
| 1294 |
+
"rewards/chosen": 0.0,
|
| 1295 |
+
"rewards/margins": 0.0,
|
| 1296 |
+
"rewards/rejected": 0.0,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": 0.1947575956583023,
|
| 1303 |
+
"logits/rejected": 0.18881197273731232,
|
| 1304 |
+
"logps/chosen": -383.63995361328125,
|
| 1305 |
+
"logps/rejected": -366.2297668457031,
|
| 1306 |
+
"loss": 0.0,
|
| 1307 |
+
"rewards/accuracies": 0.0,
|
| 1308 |
+
"rewards/chosen": 0.0,
|
| 1309 |
+
"rewards/margins": 0.0,
|
| 1310 |
+
"rewards/rejected": 0.0,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": 0.22291317582130432,
|
| 1317 |
+
"logits/rejected": 0.2307729721069336,
|
| 1318 |
+
"logps/chosen": -384.4226379394531,
|
| 1319 |
+
"logps/rejected": -388.9614562988281,
|
| 1320 |
+
"loss": 0.0,
|
| 1321 |
+
"rewards/accuracies": 0.0,
|
| 1322 |
+
"rewards/chosen": 0.0,
|
| 1323 |
+
"rewards/margins": 0.0,
|
| 1324 |
+
"rewards/rejected": 0.0,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.0,
|
| 1332 |
+
"train_runtime": 6824.5604,
|
| 1333 |
+
"train_samples_per_second": 4.396,
|
| 1334 |
+
"train_steps_per_second": 0.137
|
| 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 |
+
}
|