Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May13_12-47-35_gpu4-119-5/events.out.tfevents.1715568592.gpu4-119-5.125152.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: DUAL-GPO/phi-2-gpo-new-i0
|
| 9 |
+
model-index:
|
| 10 |
+
- name: phi-2-gpo-v13-i1
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# phi-2-gpo-v13-i1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- PEFT 0.7.1
|
| 57 |
+
- Transformers 4.36.2
|
| 58 |
+
- Pytorch 2.1.2+cu121
|
| 59 |
+
- Datasets 2.14.6
|
| 60 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167807296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0f0433db623ca4d86b7c03833dd78d72d5dad6147f6f3d6e667ce7707e99685
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.23111479535102844,
|
| 4 |
+
"train_runtime": 16991.5507,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 1.766,
|
| 7 |
+
"train_steps_per_second": 0.11
|
| 8 |
+
}
|
runs/May13_12-47-35_gpu4-119-5/events.out.tfevents.1715568592.gpu4-119-5.125152.0
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:ad0a2c58b72c4e42a0682d0b4a3bf1c373552992e09e4cca928ce24ee9b39049
|
| 3 |
+
size 124230
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.23111479535102844,
|
| 4 |
+
"train_runtime": 16991.5507,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 1.766,
|
| 7 |
+
"train_steps_per_second": 0.11
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2662 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1875,
|
| 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": 2.6595744680851065e-08,
|
| 14 |
+
"logits/chosen": 0.1680368036031723,
|
| 15 |
+
"logits/rejected": 0.19713005423545837,
|
| 16 |
+
"logps/chosen": -393.7256164550781,
|
| 17 |
+
"logps/rejected": -273.0241394042969,
|
| 18 |
+
"loss": 0.4136,
|
| 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": 2.6595744680851066e-07,
|
| 28 |
+
"logits/chosen": 0.1247146800160408,
|
| 29 |
+
"logits/rejected": 0.257645845413208,
|
| 30 |
+
"logps/chosen": -338.6689147949219,
|
| 31 |
+
"logps/rejected": -323.99322509765625,
|
| 32 |
+
"loss": 0.3312,
|
| 33 |
+
"rewards/accuracies": 0.4722222089767456,
|
| 34 |
+
"rewards/chosen": 0.00012141283514210954,
|
| 35 |
+
"rewards/margins": 0.00012025787145830691,
|
| 36 |
+
"rewards/rejected": 1.154946744463814e-06,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": 0.11776206642389297,
|
| 43 |
+
"logits/rejected": 0.2888662815093994,
|
| 44 |
+
"logps/chosen": -342.19476318359375,
|
| 45 |
+
"logps/rejected": -288.05242919921875,
|
| 46 |
+
"loss": 0.3206,
|
| 47 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 48 |
+
"rewards/chosen": -3.678434222820215e-05,
|
| 49 |
+
"rewards/margins": -0.0001559042138978839,
|
| 50 |
+
"rewards/rejected": 0.00011911986803170294,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": 0.05618368461728096,
|
| 57 |
+
"logits/rejected": 0.21764644980430603,
|
| 58 |
+
"logps/chosen": -348.53204345703125,
|
| 59 |
+
"logps/rejected": -298.0450134277344,
|
| 60 |
+
"loss": 0.3618,
|
| 61 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 62 |
+
"rewards/chosen": -7.375622953986749e-05,
|
| 63 |
+
"rewards/margins": -8.439932571491227e-05,
|
| 64 |
+
"rewards/rejected": 1.0643097994034179e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": 0.10220017284154892,
|
| 71 |
+
"logits/rejected": 0.21337243914604187,
|
| 72 |
+
"logps/chosen": -362.06536865234375,
|
| 73 |
+
"logps/rejected": -303.7508544921875,
|
| 74 |
+
"loss": 0.323,
|
| 75 |
+
"rewards/accuracies": 0.46875,
|
| 76 |
+
"rewards/chosen": 4.589342097460758e-06,
|
| 77 |
+
"rewards/margins": 6.563085662492085e-06,
|
| 78 |
+
"rewards/rejected": -1.973749021999538e-06,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": 0.17307938635349274,
|
| 85 |
+
"logits/rejected": 0.2492096871137619,
|
| 86 |
+
"logps/chosen": -357.7861633300781,
|
| 87 |
+
"logps/rejected": -262.5830993652344,
|
| 88 |
+
"loss": 0.3332,
|
| 89 |
+
"rewards/accuracies": 0.46875,
|
| 90 |
+
"rewards/chosen": 0.00020471049356274307,
|
| 91 |
+
"rewards/margins": 0.0001833896094467491,
|
| 92 |
+
"rewards/rejected": 2.1320887753972784e-05,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": 0.09367106109857559,
|
| 99 |
+
"logits/rejected": 0.27534765005111694,
|
| 100 |
+
"logps/chosen": -365.8818359375,
|
| 101 |
+
"logps/rejected": -301.4277038574219,
|
| 102 |
+
"loss": 0.325,
|
| 103 |
+
"rewards/accuracies": 0.574999988079071,
|
| 104 |
+
"rewards/chosen": 0.00033300495124422014,
|
| 105 |
+
"rewards/margins": 0.00035451535950414836,
|
| 106 |
+
"rewards/rejected": -2.1510411897907034e-05,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": 0.0627938061952591,
|
| 113 |
+
"logits/rejected": 0.26493480801582336,
|
| 114 |
+
"logps/chosen": -373.78619384765625,
|
| 115 |
+
"logps/rejected": -256.60858154296875,
|
| 116 |
+
"loss": 0.3137,
|
| 117 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 118 |
+
"rewards/chosen": 0.0005881573888473213,
|
| 119 |
+
"rewards/margins": 0.0005571565707214177,
|
| 120 |
+
"rewards/rejected": 3.1000781746115535e-05,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": 0.07975228130817413,
|
| 127 |
+
"logits/rejected": 0.18873457610607147,
|
| 128 |
+
"logps/chosen": -351.62811279296875,
|
| 129 |
+
"logps/rejected": -268.86175537109375,
|
| 130 |
+
"loss": 0.3427,
|
| 131 |
+
"rewards/accuracies": 0.675000011920929,
|
| 132 |
+
"rewards/chosen": 0.0011552410433068871,
|
| 133 |
+
"rewards/margins": 0.0011365157552063465,
|
| 134 |
+
"rewards/rejected": 1.8725168047240004e-05,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": 0.10162068903446198,
|
| 141 |
+
"logits/rejected": 0.2277887761592865,
|
| 142 |
+
"logps/chosen": -334.11505126953125,
|
| 143 |
+
"logps/rejected": -277.01123046875,
|
| 144 |
+
"loss": 0.3284,
|
| 145 |
+
"rewards/accuracies": 0.706250011920929,
|
| 146 |
+
"rewards/chosen": 0.0022371101658791304,
|
| 147 |
+
"rewards/margins": 0.0022209202870726585,
|
| 148 |
+
"rewards/rejected": 1.619003523956053e-05,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": 0.09252412617206573,
|
| 155 |
+
"logits/rejected": 0.27979540824890137,
|
| 156 |
+
"logps/chosen": -377.9844970703125,
|
| 157 |
+
"logps/rejected": -289.419677734375,
|
| 158 |
+
"loss": 0.3082,
|
| 159 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 160 |
+
"rewards/chosen": 0.00396860484033823,
|
| 161 |
+
"rewards/margins": 0.002819900633767247,
|
| 162 |
+
"rewards/rejected": 0.001148704090155661,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": 0.10446289926767349,
|
| 169 |
+
"logits/rejected": 0.19878003001213074,
|
| 170 |
+
"logps/chosen": -369.4442443847656,
|
| 171 |
+
"logps/rejected": -287.75946044921875,
|
| 172 |
+
"loss": 0.33,
|
| 173 |
+
"rewards/accuracies": 0.706250011920929,
|
| 174 |
+
"rewards/chosen": 0.006103604566305876,
|
| 175 |
+
"rewards/margins": 0.0044761234894394875,
|
| 176 |
+
"rewards/rejected": 0.0016274808440357447,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": 0.1083141341805458,
|
| 183 |
+
"logits/rejected": 0.2530149817466736,
|
| 184 |
+
"logps/chosen": -323.8044128417969,
|
| 185 |
+
"logps/rejected": -300.437255859375,
|
| 186 |
+
"loss": 0.3517,
|
| 187 |
+
"rewards/accuracies": 0.625,
|
| 188 |
+
"rewards/chosen": 0.008737698197364807,
|
| 189 |
+
"rewards/margins": 0.006680602673441172,
|
| 190 |
+
"rewards/rejected": 0.0020570955239236355,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": 0.1410514861345291,
|
| 197 |
+
"logits/rejected": 0.2637427747249603,
|
| 198 |
+
"logps/chosen": -328.4124450683594,
|
| 199 |
+
"logps/rejected": -277.685791015625,
|
| 200 |
+
"loss": 0.3177,
|
| 201 |
+
"rewards/accuracies": 0.699999988079071,
|
| 202 |
+
"rewards/chosen": 0.01055722963064909,
|
| 203 |
+
"rewards/margins": 0.010405505076050758,
|
| 204 |
+
"rewards/rejected": 0.0001517242781119421,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": 0.15804480016231537,
|
| 211 |
+
"logits/rejected": 0.24627968668937683,
|
| 212 |
+
"logps/chosen": -309.4755554199219,
|
| 213 |
+
"logps/rejected": -280.66851806640625,
|
| 214 |
+
"loss": 0.3346,
|
| 215 |
+
"rewards/accuracies": 0.668749988079071,
|
| 216 |
+
"rewards/chosen": 0.011000417172908783,
|
| 217 |
+
"rewards/margins": 0.013859736733138561,
|
| 218 |
+
"rewards/rejected": -0.0028593200258910656,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": 0.17287364602088928,
|
| 225 |
+
"logits/rejected": 0.2511886954307556,
|
| 226 |
+
"logps/chosen": -343.8251953125,
|
| 227 |
+
"logps/rejected": -319.0948181152344,
|
| 228 |
+
"loss": 0.3016,
|
| 229 |
+
"rewards/accuracies": 0.675000011920929,
|
| 230 |
+
"rewards/chosen": 0.01205248199403286,
|
| 231 |
+
"rewards/margins": 0.023393789306282997,
|
| 232 |
+
"rewards/rejected": -0.011341306380927563,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": 0.13911333680152893,
|
| 239 |
+
"logits/rejected": 0.3385851979255676,
|
| 240 |
+
"logps/chosen": -357.8835144042969,
|
| 241 |
+
"logps/rejected": -313.824951171875,
|
| 242 |
+
"loss": 0.3054,
|
| 243 |
+
"rewards/accuracies": 0.65625,
|
| 244 |
+
"rewards/chosen": -0.0063235037960112095,
|
| 245 |
+
"rewards/margins": 0.03163896128535271,
|
| 246 |
+
"rewards/rejected": -0.03796246275305748,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": 0.20543082058429718,
|
| 253 |
+
"logits/rejected": 0.286451518535614,
|
| 254 |
+
"logps/chosen": -427.0508728027344,
|
| 255 |
+
"logps/rejected": -397.6676025390625,
|
| 256 |
+
"loss": 0.2817,
|
| 257 |
+
"rewards/accuracies": 0.737500011920929,
|
| 258 |
+
"rewards/chosen": -0.032296378165483475,
|
| 259 |
+
"rewards/margins": 0.06459534913301468,
|
| 260 |
+
"rewards/rejected": -0.09689172357320786,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": 0.17126373946666718,
|
| 267 |
+
"logits/rejected": 0.25217366218566895,
|
| 268 |
+
"logps/chosen": -439.67840576171875,
|
| 269 |
+
"logps/rejected": -456.2896423339844,
|
| 270 |
+
"loss": 0.292,
|
| 271 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 272 |
+
"rewards/chosen": -0.10424342006444931,
|
| 273 |
+
"rewards/margins": 0.08777059614658356,
|
| 274 |
+
"rewards/rejected": -0.19201400876045227,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": 0.16082295775413513,
|
| 281 |
+
"logits/rejected": 0.2546341121196747,
|
| 282 |
+
"logps/chosen": -461.6935119628906,
|
| 283 |
+
"logps/rejected": -500.5730895996094,
|
| 284 |
+
"loss": 0.2571,
|
| 285 |
+
"rewards/accuracies": 0.699999988079071,
|
| 286 |
+
"rewards/chosen": -0.12413378804922104,
|
| 287 |
+
"rewards/margins": 0.08718255907297134,
|
| 288 |
+
"rewards/rejected": -0.21131631731987,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": 0.10711757093667984,
|
| 295 |
+
"logits/rejected": 0.21617627143859863,
|
| 296 |
+
"logps/chosen": -522.9395141601562,
|
| 297 |
+
"logps/rejected": -570.61083984375,
|
| 298 |
+
"loss": 0.2479,
|
| 299 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 300 |
+
"rewards/chosen": -0.15697070956230164,
|
| 301 |
+
"rewards/margins": 0.11644785106182098,
|
| 302 |
+
"rewards/rejected": -0.2734185755252838,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": 0.22454562783241272,
|
| 309 |
+
"logits/rejected": 0.3751831650733948,
|
| 310 |
+
"logps/chosen": -618.0147094726562,
|
| 311 |
+
"logps/rejected": -661.6094970703125,
|
| 312 |
+
"loss": 0.2742,
|
| 313 |
+
"rewards/accuracies": 0.6875,
|
| 314 |
+
"rewards/chosen": -0.2251421958208084,
|
| 315 |
+
"rewards/margins": 0.1425340622663498,
|
| 316 |
+
"rewards/rejected": -0.3676762282848358,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": 0.2090134620666504,
|
| 323 |
+
"logits/rejected": 0.2619253993034363,
|
| 324 |
+
"logps/chosen": -585.8196411132812,
|
| 325 |
+
"logps/rejected": -695.9527587890625,
|
| 326 |
+
"loss": 0.2409,
|
| 327 |
+
"rewards/accuracies": 0.71875,
|
| 328 |
+
"rewards/chosen": -0.23935195803642273,
|
| 329 |
+
"rewards/margins": 0.16129860281944275,
|
| 330 |
+
"rewards/rejected": -0.4006505608558655,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": 0.21562126278877258,
|
| 337 |
+
"logits/rejected": 0.30403202772140503,
|
| 338 |
+
"logps/chosen": -583.1571044921875,
|
| 339 |
+
"logps/rejected": -664.2890625,
|
| 340 |
+
"loss": 0.2766,
|
| 341 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 342 |
+
"rewards/chosen": -0.22509849071502686,
|
| 343 |
+
"rewards/margins": 0.1467365324497223,
|
| 344 |
+
"rewards/rejected": -0.37183502316474915,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": 0.09697722643613815,
|
| 351 |
+
"logits/rejected": 0.240617036819458,
|
| 352 |
+
"logps/chosen": -562.3460083007812,
|
| 353 |
+
"logps/rejected": -621.7235107421875,
|
| 354 |
+
"loss": 0.2826,
|
| 355 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 356 |
+
"rewards/chosen": -0.21679548919200897,
|
| 357 |
+
"rewards/margins": 0.14000090956687927,
|
| 358 |
+
"rewards/rejected": -0.35679641366004944,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": 0.13605690002441406,
|
| 365 |
+
"logits/rejected": 0.2448308765888214,
|
| 366 |
+
"logps/chosen": -535.7677001953125,
|
| 367 |
+
"logps/rejected": -593.754638671875,
|
| 368 |
+
"loss": 0.2796,
|
| 369 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 370 |
+
"rewards/chosen": -0.18055127561092377,
|
| 371 |
+
"rewards/margins": 0.10934337228536606,
|
| 372 |
+
"rewards/rejected": -0.28989464044570923,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": 0.10516633838415146,
|
| 379 |
+
"logits/rejected": 0.23380067944526672,
|
| 380 |
+
"logps/chosen": -482.5274353027344,
|
| 381 |
+
"logps/rejected": -600.8789672851562,
|
| 382 |
+
"loss": 0.2452,
|
| 383 |
+
"rewards/accuracies": 0.706250011920929,
|
| 384 |
+
"rewards/chosen": -0.1688566356897354,
|
| 385 |
+
"rewards/margins": 0.15834231674671173,
|
| 386 |
+
"rewards/rejected": -0.32719895243644714,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": 0.1699642688035965,
|
| 393 |
+
"logits/rejected": 0.2693479657173157,
|
| 394 |
+
"logps/chosen": -505.5724182128906,
|
| 395 |
+
"logps/rejected": -634.6489868164062,
|
| 396 |
+
"loss": 0.2573,
|
| 397 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 398 |
+
"rewards/chosen": -0.1955190747976303,
|
| 399 |
+
"rewards/margins": 0.16697654128074646,
|
| 400 |
+
"rewards/rejected": -0.3624956011772156,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": 0.16180387139320374,
|
| 407 |
+
"logits/rejected": 0.2788015604019165,
|
| 408 |
+
"logps/chosen": -564.1033935546875,
|
| 409 |
+
"logps/rejected": -646.7479248046875,
|
| 410 |
+
"loss": 0.2496,
|
| 411 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 412 |
+
"rewards/chosen": -0.2246371954679489,
|
| 413 |
+
"rewards/margins": 0.13526742160320282,
|
| 414 |
+
"rewards/rejected": -0.35990458726882935,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": 0.1516331136226654,
|
| 421 |
+
"logits/rejected": 0.20982889831066132,
|
| 422 |
+
"logps/chosen": -544.4299926757812,
|
| 423 |
+
"logps/rejected": -642.7681274414062,
|
| 424 |
+
"loss": 0.2689,
|
| 425 |
+
"rewards/accuracies": 0.643750011920929,
|
| 426 |
+
"rewards/chosen": -0.22307808697223663,
|
| 427 |
+
"rewards/margins": 0.14021030068397522,
|
| 428 |
+
"rewards/rejected": -0.36328837275505066,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": 0.0853557214140892,
|
| 435 |
+
"logits/rejected": 0.24294111132621765,
|
| 436 |
+
"logps/chosen": -587.2979125976562,
|
| 437 |
+
"logps/rejected": -675.4234619140625,
|
| 438 |
+
"loss": 0.2403,
|
| 439 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 440 |
+
"rewards/chosen": -0.22484929859638214,
|
| 441 |
+
"rewards/margins": 0.1554943472146988,
|
| 442 |
+
"rewards/rejected": -0.38034364581108093,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": 0.1488361358642578,
|
| 449 |
+
"logits/rejected": 0.22367210686206818,
|
| 450 |
+
"logps/chosen": -545.3068237304688,
|
| 451 |
+
"logps/rejected": -659.3970336914062,
|
| 452 |
+
"loss": 0.2389,
|
| 453 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 454 |
+
"rewards/chosen": -0.18365520238876343,
|
| 455 |
+
"rewards/margins": 0.17183148860931396,
|
| 456 |
+
"rewards/rejected": -0.3554866909980774,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": 0.08838851749897003,
|
| 463 |
+
"logits/rejected": 0.21153846383094788,
|
| 464 |
+
"logps/chosen": -565.9591064453125,
|
| 465 |
+
"logps/rejected": -670.2896728515625,
|
| 466 |
+
"loss": 0.2343,
|
| 467 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 468 |
+
"rewards/chosen": -0.22553689777851105,
|
| 469 |
+
"rewards/margins": 0.15771272778511047,
|
| 470 |
+
"rewards/rejected": -0.3832496404647827,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": 0.11703666299581528,
|
| 477 |
+
"logits/rejected": 0.19987936317920685,
|
| 478 |
+
"logps/chosen": -552.8609008789062,
|
| 479 |
+
"logps/rejected": -671.7772216796875,
|
| 480 |
+
"loss": 0.2388,
|
| 481 |
+
"rewards/accuracies": 0.706250011920929,
|
| 482 |
+
"rewards/chosen": -0.2358858585357666,
|
| 483 |
+
"rewards/margins": 0.1468653529882431,
|
| 484 |
+
"rewards/rejected": -0.3827512562274933,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": 0.12850847840309143,
|
| 491 |
+
"logits/rejected": 0.22665157914161682,
|
| 492 |
+
"logps/chosen": -592.2838134765625,
|
| 493 |
+
"logps/rejected": -709.990966796875,
|
| 494 |
+
"loss": 0.2315,
|
| 495 |
+
"rewards/accuracies": 0.706250011920929,
|
| 496 |
+
"rewards/chosen": -0.2650226652622223,
|
| 497 |
+
"rewards/margins": 0.156343013048172,
|
| 498 |
+
"rewards/rejected": -0.4213656783103943,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": 0.19187921285629272,
|
| 505 |
+
"logits/rejected": 0.2653835117816925,
|
| 506 |
+
"logps/chosen": -580.5294189453125,
|
| 507 |
+
"logps/rejected": -682.482421875,
|
| 508 |
+
"loss": 0.2615,
|
| 509 |
+
"rewards/accuracies": 0.731249988079071,
|
| 510 |
+
"rewards/chosen": -0.2366868555545807,
|
| 511 |
+
"rewards/margins": 0.16842707991600037,
|
| 512 |
+
"rewards/rejected": -0.40511393547058105,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": 0.20482924580574036,
|
| 519 |
+
"logits/rejected": 0.2829897999763489,
|
| 520 |
+
"logps/chosen": -568.0645751953125,
|
| 521 |
+
"logps/rejected": -742.5205078125,
|
| 522 |
+
"loss": 0.231,
|
| 523 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 524 |
+
"rewards/chosen": -0.23385734856128693,
|
| 525 |
+
"rewards/margins": 0.20819666981697083,
|
| 526 |
+
"rewards/rejected": -0.44205403327941895,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": 0.1813650131225586,
|
| 533 |
+
"logits/rejected": 0.28613919019699097,
|
| 534 |
+
"logps/chosen": -620.7769775390625,
|
| 535 |
+
"logps/rejected": -805.1932983398438,
|
| 536 |
+
"loss": 0.2268,
|
| 537 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 538 |
+
"rewards/chosen": -0.2879635691642761,
|
| 539 |
+
"rewards/margins": 0.2243933230638504,
|
| 540 |
+
"rewards/rejected": -0.5123568773269653,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": 0.1462257206439972,
|
| 547 |
+
"logits/rejected": 0.2905661463737488,
|
| 548 |
+
"logps/chosen": -616.0975341796875,
|
| 549 |
+
"logps/rejected": -712.8366088867188,
|
| 550 |
+
"loss": 0.2361,
|
| 551 |
+
"rewards/accuracies": 0.75,
|
| 552 |
+
"rewards/chosen": -0.26976972818374634,
|
| 553 |
+
"rewards/margins": 0.16418993473052979,
|
| 554 |
+
"rewards/rejected": -0.4339596629142761,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": 0.21741768717765808,
|
| 561 |
+
"logits/rejected": 0.28720468282699585,
|
| 562 |
+
"logps/chosen": -553.0687255859375,
|
| 563 |
+
"logps/rejected": -674.6417236328125,
|
| 564 |
+
"loss": 0.2391,
|
| 565 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 566 |
+
"rewards/chosen": -0.22814492881298065,
|
| 567 |
+
"rewards/margins": 0.16390588879585266,
|
| 568 |
+
"rewards/rejected": -0.3920508027076721,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": 0.13199961185455322,
|
| 575 |
+
"logits/rejected": 0.28842002153396606,
|
| 576 |
+
"logps/chosen": -572.0911254882812,
|
| 577 |
+
"logps/rejected": -669.98046875,
|
| 578 |
+
"loss": 0.2511,
|
| 579 |
+
"rewards/accuracies": 0.768750011920929,
|
| 580 |
+
"rewards/chosen": -0.24041178822517395,
|
| 581 |
+
"rewards/margins": 0.1423041820526123,
|
| 582 |
+
"rewards/rejected": -0.38271597027778625,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": 0.23625163733959198,
|
| 589 |
+
"logits/rejected": 0.3224749267101288,
|
| 590 |
+
"logps/chosen": -669.3237915039062,
|
| 591 |
+
"logps/rejected": -783.9891357421875,
|
| 592 |
+
"loss": 0.2422,
|
| 593 |
+
"rewards/accuracies": 0.75,
|
| 594 |
+
"rewards/chosen": -0.316593199968338,
|
| 595 |
+
"rewards/margins": 0.19081000983715057,
|
| 596 |
+
"rewards/rejected": -0.5074031949043274,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": 0.20555272698402405,
|
| 603 |
+
"logits/rejected": 0.3196572959423065,
|
| 604 |
+
"logps/chosen": -729.6986083984375,
|
| 605 |
+
"logps/rejected": -817.2890625,
|
| 606 |
+
"loss": 0.2429,
|
| 607 |
+
"rewards/accuracies": 0.737500011920929,
|
| 608 |
+
"rewards/chosen": -0.341257780790329,
|
| 609 |
+
"rewards/margins": 0.18218111991882324,
|
| 610 |
+
"rewards/rejected": -0.5234388113021851,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": 0.20105445384979248,
|
| 617 |
+
"logits/rejected": 0.2788250744342804,
|
| 618 |
+
"logps/chosen": -735.6785888671875,
|
| 619 |
+
"logps/rejected": -862.8883056640625,
|
| 620 |
+
"loss": 0.2052,
|
| 621 |
+
"rewards/accuracies": 0.793749988079071,
|
| 622 |
+
"rewards/chosen": -0.3522084653377533,
|
| 623 |
+
"rewards/margins": 0.2194521129131317,
|
| 624 |
+
"rewards/rejected": -0.5716606378555298,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": 0.1956392228603363,
|
| 631 |
+
"logits/rejected": 0.3031262755393982,
|
| 632 |
+
"logps/chosen": -678.7946166992188,
|
| 633 |
+
"logps/rejected": -765.5419921875,
|
| 634 |
+
"loss": 0.298,
|
| 635 |
+
"rewards/accuracies": 0.625,
|
| 636 |
+
"rewards/chosen": -0.35866203904151917,
|
| 637 |
+
"rewards/margins": 0.15328657627105713,
|
| 638 |
+
"rewards/rejected": -0.5119485855102539,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": 0.17509567737579346,
|
| 645 |
+
"logits/rejected": 0.27089959383010864,
|
| 646 |
+
"logps/chosen": -666.20458984375,
|
| 647 |
+
"logps/rejected": -816.4446411132812,
|
| 648 |
+
"loss": 0.2403,
|
| 649 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 650 |
+
"rewards/chosen": -0.31221580505371094,
|
| 651 |
+
"rewards/margins": 0.20367129147052765,
|
| 652 |
+
"rewards/rejected": -0.5158870816230774,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": 0.17904916405677795,
|
| 659 |
+
"logits/rejected": 0.20903074741363525,
|
| 660 |
+
"logps/chosen": -623.48193359375,
|
| 661 |
+
"logps/rejected": -798.4592895507812,
|
| 662 |
+
"loss": 0.1872,
|
| 663 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 664 |
+
"rewards/chosen": -0.28309115767478943,
|
| 665 |
+
"rewards/margins": 0.22119691967964172,
|
| 666 |
+
"rewards/rejected": -0.5042880773544312,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": 0.17857761681079865,
|
| 673 |
+
"logits/rejected": 0.22934532165527344,
|
| 674 |
+
"logps/chosen": -671.294189453125,
|
| 675 |
+
"logps/rejected": -820.5545654296875,
|
| 676 |
+
"loss": 0.2177,
|
| 677 |
+
"rewards/accuracies": 0.762499988079071,
|
| 678 |
+
"rewards/chosen": -0.340231329202652,
|
| 679 |
+
"rewards/margins": 0.1799103319644928,
|
| 680 |
+
"rewards/rejected": -0.5201416611671448,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": 0.21654605865478516,
|
| 687 |
+
"logits/rejected": 0.331270307302475,
|
| 688 |
+
"logps/chosen": -630.5990600585938,
|
| 689 |
+
"logps/rejected": -743.7600708007812,
|
| 690 |
+
"loss": 0.2503,
|
| 691 |
+
"rewards/accuracies": 0.731249988079071,
|
| 692 |
+
"rewards/chosen": -0.2956790328025818,
|
| 693 |
+
"rewards/margins": 0.1739194393157959,
|
| 694 |
+
"rewards/rejected": -0.4695984721183777,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": 0.13878825306892395,
|
| 701 |
+
"logits/rejected": 0.2916678488254547,
|
| 702 |
+
"logps/chosen": -620.2591552734375,
|
| 703 |
+
"logps/rejected": -782.7337646484375,
|
| 704 |
+
"loss": 0.2216,
|
| 705 |
+
"rewards/accuracies": 0.71875,
|
| 706 |
+
"rewards/chosen": -0.31532377004623413,
|
| 707 |
+
"rewards/margins": 0.2057572305202484,
|
| 708 |
+
"rewards/rejected": -0.5210810303688049,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": 0.17934757471084595,
|
| 715 |
+
"logits/rejected": 0.2883814871311188,
|
| 716 |
+
"logps/chosen": -649.7817993164062,
|
| 717 |
+
"logps/rejected": -799.4210815429688,
|
| 718 |
+
"loss": 0.2229,
|
| 719 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 720 |
+
"rewards/chosen": -0.3004361689090729,
|
| 721 |
+
"rewards/margins": 0.2075958251953125,
|
| 722 |
+
"rewards/rejected": -0.508031964302063,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": 0.17266924679279327,
|
| 729 |
+
"logits/rejected": 0.32525214552879333,
|
| 730 |
+
"logps/chosen": -700.376220703125,
|
| 731 |
+
"logps/rejected": -833.9622192382812,
|
| 732 |
+
"loss": 0.2532,
|
| 733 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 734 |
+
"rewards/chosen": -0.3490568995475769,
|
| 735 |
+
"rewards/margins": 0.1844739019870758,
|
| 736 |
+
"rewards/rejected": -0.5335308313369751,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": 0.19843865931034088,
|
| 743 |
+
"logits/rejected": 0.27735739946365356,
|
| 744 |
+
"logps/chosen": -654.317626953125,
|
| 745 |
+
"logps/rejected": -793.0462646484375,
|
| 746 |
+
"loss": 0.2342,
|
| 747 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 748 |
+
"rewards/chosen": -0.33207401633262634,
|
| 749 |
+
"rewards/margins": 0.18460185825824738,
|
| 750 |
+
"rewards/rejected": -0.5166758894920349,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": 0.1701696366071701,
|
| 757 |
+
"logits/rejected": 0.2598097026348114,
|
| 758 |
+
"logps/chosen": -640.8900146484375,
|
| 759 |
+
"logps/rejected": -793.0274658203125,
|
| 760 |
+
"loss": 0.1985,
|
| 761 |
+
"rewards/accuracies": 0.75,
|
| 762 |
+
"rewards/chosen": -0.31474485993385315,
|
| 763 |
+
"rewards/margins": 0.19083499908447266,
|
| 764 |
+
"rewards/rejected": -0.5055798292160034,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": 0.232101172208786,
|
| 771 |
+
"logits/rejected": 0.30248063802719116,
|
| 772 |
+
"logps/chosen": -695.262451171875,
|
| 773 |
+
"logps/rejected": -817.1578369140625,
|
| 774 |
+
"loss": 0.2421,
|
| 775 |
+
"rewards/accuracies": 0.731249988079071,
|
| 776 |
+
"rewards/chosen": -0.33937522768974304,
|
| 777 |
+
"rewards/margins": 0.19629260897636414,
|
| 778 |
+
"rewards/rejected": -0.5356678366661072,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": 0.21882247924804688,
|
| 785 |
+
"logits/rejected": 0.3331480920314789,
|
| 786 |
+
"logps/chosen": -711.1233520507812,
|
| 787 |
+
"logps/rejected": -841.3557739257812,
|
| 788 |
+
"loss": 0.214,
|
| 789 |
+
"rewards/accuracies": 0.699999988079071,
|
| 790 |
+
"rewards/chosen": -0.3614684045314789,
|
| 791 |
+
"rewards/margins": 0.19178052246570587,
|
| 792 |
+
"rewards/rejected": -0.553248941898346,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": 0.14314863085746765,
|
| 799 |
+
"logits/rejected": 0.3489857614040375,
|
| 800 |
+
"logps/chosen": -778.8663330078125,
|
| 801 |
+
"logps/rejected": -877.1080932617188,
|
| 802 |
+
"loss": 0.2251,
|
| 803 |
+
"rewards/accuracies": 0.731249988079071,
|
| 804 |
+
"rewards/chosen": -0.4136313498020172,
|
| 805 |
+
"rewards/margins": 0.19483810663223267,
|
| 806 |
+
"rewards/rejected": -0.6084694266319275,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": 0.19116893410682678,
|
| 813 |
+
"logits/rejected": 0.32879945635795593,
|
| 814 |
+
"logps/chosen": -710.8887939453125,
|
| 815 |
+
"logps/rejected": -837.41748046875,
|
| 816 |
+
"loss": 0.212,
|
| 817 |
+
"rewards/accuracies": 0.706250011920929,
|
| 818 |
+
"rewards/chosen": -0.3603808283805847,
|
| 819 |
+
"rewards/margins": 0.19663426280021667,
|
| 820 |
+
"rewards/rejected": -0.557015061378479,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": 0.14669467508792877,
|
| 827 |
+
"logits/rejected": 0.3146809935569763,
|
| 828 |
+
"logps/chosen": -662.716064453125,
|
| 829 |
+
"logps/rejected": -765.9783935546875,
|
| 830 |
+
"loss": 0.2587,
|
| 831 |
+
"rewards/accuracies": 0.6875,
|
| 832 |
+
"rewards/chosen": -0.32042309641838074,
|
| 833 |
+
"rewards/margins": 0.1730494648218155,
|
| 834 |
+
"rewards/rejected": -0.4934725761413574,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": 0.171834796667099,
|
| 841 |
+
"logits/rejected": 0.30899518728256226,
|
| 842 |
+
"logps/chosen": -648.413330078125,
|
| 843 |
+
"logps/rejected": -787.9014892578125,
|
| 844 |
+
"loss": 0.195,
|
| 845 |
+
"rewards/accuracies": 0.768750011920929,
|
| 846 |
+
"rewards/chosen": -0.29140716791152954,
|
| 847 |
+
"rewards/margins": 0.20431244373321533,
|
| 848 |
+
"rewards/rejected": -0.4957196116447449,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": 0.1850585639476776,
|
| 855 |
+
"logits/rejected": 0.3111046552658081,
|
| 856 |
+
"logps/chosen": -640.8422241210938,
|
| 857 |
+
"logps/rejected": -784.2683715820312,
|
| 858 |
+
"loss": 0.2277,
|
| 859 |
+
"rewards/accuracies": 0.71875,
|
| 860 |
+
"rewards/chosen": -0.31103643774986267,
|
| 861 |
+
"rewards/margins": 0.19471977651119232,
|
| 862 |
+
"rewards/rejected": -0.5057561993598938,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": 0.2157634198665619,
|
| 869 |
+
"logits/rejected": 0.2784191071987152,
|
| 870 |
+
"logps/chosen": -641.7967529296875,
|
| 871 |
+
"logps/rejected": -809.9637451171875,
|
| 872 |
+
"loss": 0.2216,
|
| 873 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 874 |
+
"rewards/chosen": -0.30600252747535706,
|
| 875 |
+
"rewards/margins": 0.2282377928495407,
|
| 876 |
+
"rewards/rejected": -0.5342403650283813,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": 0.17053952813148499,
|
| 883 |
+
"logits/rejected": 0.3547263741493225,
|
| 884 |
+
"logps/chosen": -663.431884765625,
|
| 885 |
+
"logps/rejected": -784.136474609375,
|
| 886 |
+
"loss": 0.2201,
|
| 887 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 888 |
+
"rewards/chosen": -0.31853628158569336,
|
| 889 |
+
"rewards/margins": 0.19354286789894104,
|
| 890 |
+
"rewards/rejected": -0.512079119682312,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": 0.11867985874414444,
|
| 897 |
+
"logits/rejected": 0.3206768035888672,
|
| 898 |
+
"logps/chosen": -657.0588989257812,
|
| 899 |
+
"logps/rejected": -777.2775268554688,
|
| 900 |
+
"loss": 0.2433,
|
| 901 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 902 |
+
"rewards/chosen": -0.32349634170532227,
|
| 903 |
+
"rewards/margins": 0.1930086761713028,
|
| 904 |
+
"rewards/rejected": -0.5165050029754639,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": 0.20680156350135803,
|
| 911 |
+
"logits/rejected": 0.3131827116012573,
|
| 912 |
+
"logps/chosen": -677.2208251953125,
|
| 913 |
+
"logps/rejected": -788.533447265625,
|
| 914 |
+
"loss": 0.2271,
|
| 915 |
+
"rewards/accuracies": 0.71875,
|
| 916 |
+
"rewards/chosen": -0.303560733795166,
|
| 917 |
+
"rewards/margins": 0.18881794810295105,
|
| 918 |
+
"rewards/rejected": -0.4923786520957947,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": 0.17017784714698792,
|
| 925 |
+
"logits/rejected": 0.2720898985862732,
|
| 926 |
+
"logps/chosen": -604.7415161132812,
|
| 927 |
+
"logps/rejected": -724.3334350585938,
|
| 928 |
+
"loss": 0.2259,
|
| 929 |
+
"rewards/accuracies": 0.731249988079071,
|
| 930 |
+
"rewards/chosen": -0.27009710669517517,
|
| 931 |
+
"rewards/margins": 0.1792145073413849,
|
| 932 |
+
"rewards/rejected": -0.44931164383888245,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": 0.1530022919178009,
|
| 939 |
+
"logits/rejected": 0.30241402983665466,
|
| 940 |
+
"logps/chosen": -639.620361328125,
|
| 941 |
+
"logps/rejected": -807.2040405273438,
|
| 942 |
+
"loss": 0.214,
|
| 943 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 944 |
+
"rewards/chosen": -0.2783825993537903,
|
| 945 |
+
"rewards/margins": 0.229055255651474,
|
| 946 |
+
"rewards/rejected": -0.5074378848075867,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": 0.12180732190608978,
|
| 953 |
+
"logits/rejected": 0.2914981245994568,
|
| 954 |
+
"logps/chosen": -710.6832885742188,
|
| 955 |
+
"logps/rejected": -850.0335083007812,
|
| 956 |
+
"loss": 0.225,
|
| 957 |
+
"rewards/accuracies": 0.699999988079071,
|
| 958 |
+
"rewards/chosen": -0.363064706325531,
|
| 959 |
+
"rewards/margins": 0.19931283593177795,
|
| 960 |
+
"rewards/rejected": -0.5623775720596313,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": 0.17398427426815033,
|
| 967 |
+
"logits/rejected": 0.3090857267379761,
|
| 968 |
+
"logps/chosen": -684.0886840820312,
|
| 969 |
+
"logps/rejected": -895.4011840820312,
|
| 970 |
+
"loss": 0.1855,
|
| 971 |
+
"rewards/accuracies": 0.8125,
|
| 972 |
+
"rewards/chosen": -0.3387846052646637,
|
| 973 |
+
"rewards/margins": 0.2770841717720032,
|
| 974 |
+
"rewards/rejected": -0.6158688068389893,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": 0.20324131846427917,
|
| 981 |
+
"logits/rejected": 0.30140548944473267,
|
| 982 |
+
"logps/chosen": -664.1101684570312,
|
| 983 |
+
"logps/rejected": -785.5363159179688,
|
| 984 |
+
"loss": 0.2282,
|
| 985 |
+
"rewards/accuracies": 0.731249988079071,
|
| 986 |
+
"rewards/chosen": -0.29074573516845703,
|
| 987 |
+
"rewards/margins": 0.2039407193660736,
|
| 988 |
+
"rewards/rejected": -0.4946863651275635,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": 0.1982668787240982,
|
| 995 |
+
"logits/rejected": 0.2695184648036957,
|
| 996 |
+
"logps/chosen": -575.2810668945312,
|
| 997 |
+
"logps/rejected": -737.6761474609375,
|
| 998 |
+
"loss": 0.1907,
|
| 999 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1000 |
+
"rewards/chosen": -0.25107094645500183,
|
| 1001 |
+
"rewards/margins": 0.1953134834766388,
|
| 1002 |
+
"rewards/rejected": -0.4463844895362854,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": 0.17798396944999695,
|
| 1009 |
+
"logits/rejected": 0.32517749071121216,
|
| 1010 |
+
"logps/chosen": -664.4030151367188,
|
| 1011 |
+
"logps/rejected": -806.2379760742188,
|
| 1012 |
+
"loss": 0.2163,
|
| 1013 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1014 |
+
"rewards/chosen": -0.2954537868499756,
|
| 1015 |
+
"rewards/margins": 0.22870102524757385,
|
| 1016 |
+
"rewards/rejected": -0.524154782295227,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": 0.23220598697662354,
|
| 1023 |
+
"logits/rejected": 0.3328869938850403,
|
| 1024 |
+
"logps/chosen": -631.212158203125,
|
| 1025 |
+
"logps/rejected": -779.985107421875,
|
| 1026 |
+
"loss": 0.2106,
|
| 1027 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1028 |
+
"rewards/chosen": -0.28802287578582764,
|
| 1029 |
+
"rewards/margins": 0.21716487407684326,
|
| 1030 |
+
"rewards/rejected": -0.5051878094673157,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": 0.20683269202709198,
|
| 1037 |
+
"logits/rejected": 0.2652401924133301,
|
| 1038 |
+
"logps/chosen": -639.0568237304688,
|
| 1039 |
+
"logps/rejected": -799.6007690429688,
|
| 1040 |
+
"loss": 0.2347,
|
| 1041 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1042 |
+
"rewards/chosen": -0.29507094621658325,
|
| 1043 |
+
"rewards/margins": 0.2053174525499344,
|
| 1044 |
+
"rewards/rejected": -0.5003883838653564,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": 0.19919940829277039,
|
| 1051 |
+
"logits/rejected": 0.3394211530685425,
|
| 1052 |
+
"logps/chosen": -686.8181762695312,
|
| 1053 |
+
"logps/rejected": -870.0245361328125,
|
| 1054 |
+
"loss": 0.2058,
|
| 1055 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1056 |
+
"rewards/chosen": -0.3031126856803894,
|
| 1057 |
+
"rewards/margins": 0.2735733389854431,
|
| 1058 |
+
"rewards/rejected": -0.5766860246658325,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": 0.21238520741462708,
|
| 1065 |
+
"logits/rejected": 0.22055749595165253,
|
| 1066 |
+
"logps/chosen": -629.7884521484375,
|
| 1067 |
+
"logps/rejected": -798.6253662109375,
|
| 1068 |
+
"loss": 0.2525,
|
| 1069 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1070 |
+
"rewards/chosen": -0.31108587980270386,
|
| 1071 |
+
"rewards/margins": 0.18138930201530457,
|
| 1072 |
+
"rewards/rejected": -0.4924752116203308,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": 0.16632458567619324,
|
| 1079 |
+
"logits/rejected": 0.2695624828338623,
|
| 1080 |
+
"logps/chosen": -619.755126953125,
|
| 1081 |
+
"logps/rejected": -766.7147216796875,
|
| 1082 |
+
"loss": 0.2216,
|
| 1083 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1084 |
+
"rewards/chosen": -0.283473938703537,
|
| 1085 |
+
"rewards/margins": 0.18939343094825745,
|
| 1086 |
+
"rewards/rejected": -0.4728673994541168,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": 0.17467322945594788,
|
| 1093 |
+
"logits/rejected": 0.21252937614917755,
|
| 1094 |
+
"logps/chosen": -616.0049438476562,
|
| 1095 |
+
"logps/rejected": -769.6994018554688,
|
| 1096 |
+
"loss": 0.2496,
|
| 1097 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1098 |
+
"rewards/chosen": -0.3090468943119049,
|
| 1099 |
+
"rewards/margins": 0.16970062255859375,
|
| 1100 |
+
"rewards/rejected": -0.47874751687049866,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": 0.1817772388458252,
|
| 1107 |
+
"logits/rejected": 0.22469213604927063,
|
| 1108 |
+
"logps/chosen": -679.7005615234375,
|
| 1109 |
+
"logps/rejected": -825.8623046875,
|
| 1110 |
+
"loss": 0.215,
|
| 1111 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1112 |
+
"rewards/chosen": -0.3420635461807251,
|
| 1113 |
+
"rewards/margins": 0.1958375722169876,
|
| 1114 |
+
"rewards/rejected": -0.5379011034965515,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": 0.11898622661828995,
|
| 1121 |
+
"logits/rejected": 0.23143093287944794,
|
| 1122 |
+
"logps/chosen": -700.2951049804688,
|
| 1123 |
+
"logps/rejected": -797.0465087890625,
|
| 1124 |
+
"loss": 0.2019,
|
| 1125 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1126 |
+
"rewards/chosen": -0.33859121799468994,
|
| 1127 |
+
"rewards/margins": 0.1829417496919632,
|
| 1128 |
+
"rewards/rejected": -0.5215329527854919,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": 0.09929606318473816,
|
| 1135 |
+
"logits/rejected": 0.23305658996105194,
|
| 1136 |
+
"logps/chosen": -629.5419311523438,
|
| 1137 |
+
"logps/rejected": -787.3818359375,
|
| 1138 |
+
"loss": 0.201,
|
| 1139 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1140 |
+
"rewards/chosen": -0.2896836996078491,
|
| 1141 |
+
"rewards/margins": 0.22416365146636963,
|
| 1142 |
+
"rewards/rejected": -0.5138473510742188,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": 0.1264248788356781,
|
| 1149 |
+
"logits/rejected": 0.2334756851196289,
|
| 1150 |
+
"logps/chosen": -656.5744018554688,
|
| 1151 |
+
"logps/rejected": -850.2476806640625,
|
| 1152 |
+
"loss": 0.2062,
|
| 1153 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1154 |
+
"rewards/chosen": -0.3103203773498535,
|
| 1155 |
+
"rewards/margins": 0.24082545936107635,
|
| 1156 |
+
"rewards/rejected": -0.5511458516120911,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": 0.15474265813827515,
|
| 1163 |
+
"logits/rejected": 0.22842803597450256,
|
| 1164 |
+
"logps/chosen": -671.4266357421875,
|
| 1165 |
+
"logps/rejected": -916.7794799804688,
|
| 1166 |
+
"loss": 0.1971,
|
| 1167 |
+
"rewards/accuracies": 0.84375,
|
| 1168 |
+
"rewards/chosen": -0.31731024384498596,
|
| 1169 |
+
"rewards/margins": 0.28582102060317993,
|
| 1170 |
+
"rewards/rejected": -0.6031311750411987,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": 0.13778944313526154,
|
| 1177 |
+
"logits/rejected": 0.27569061517715454,
|
| 1178 |
+
"logps/chosen": -631.9242553710938,
|
| 1179 |
+
"logps/rejected": -814.20068359375,
|
| 1180 |
+
"loss": 0.2123,
|
| 1181 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1182 |
+
"rewards/chosen": -0.31727999448776245,
|
| 1183 |
+
"rewards/margins": 0.21109680831432343,
|
| 1184 |
+
"rewards/rejected": -0.5283767580986023,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": 0.09538077563047409,
|
| 1191 |
+
"logits/rejected": 0.2515682578086853,
|
| 1192 |
+
"logps/chosen": -641.342529296875,
|
| 1193 |
+
"logps/rejected": -826.2974853515625,
|
| 1194 |
+
"loss": 0.1821,
|
| 1195 |
+
"rewards/accuracies": 0.831250011920929,
|
| 1196 |
+
"rewards/chosen": -0.26377955079078674,
|
| 1197 |
+
"rewards/margins": 0.26421433687210083,
|
| 1198 |
+
"rewards/rejected": -0.5279938578605652,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": 0.1294173300266266,
|
| 1205 |
+
"logits/rejected": 0.27691131830215454,
|
| 1206 |
+
"logps/chosen": -666.8058471679688,
|
| 1207 |
+
"logps/rejected": -798.5427856445312,
|
| 1208 |
+
"loss": 0.2291,
|
| 1209 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1210 |
+
"rewards/chosen": -0.3166380226612091,
|
| 1211 |
+
"rewards/margins": 0.19483907520771027,
|
| 1212 |
+
"rewards/rejected": -0.5114771127700806,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": 0.1251804232597351,
|
| 1219 |
+
"logits/rejected": 0.19463461637496948,
|
| 1220 |
+
"logps/chosen": -661.3643798828125,
|
| 1221 |
+
"logps/rejected": -868.736328125,
|
| 1222 |
+
"loss": 0.2382,
|
| 1223 |
+
"rewards/accuracies": 0.75,
|
| 1224 |
+
"rewards/chosen": -0.3124701678752899,
|
| 1225 |
+
"rewards/margins": 0.2407514601945877,
|
| 1226 |
+
"rewards/rejected": -0.553221583366394,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": 0.1276322454214096,
|
| 1233 |
+
"logits/rejected": 0.18467645347118378,
|
| 1234 |
+
"logps/chosen": -618.6890869140625,
|
| 1235 |
+
"logps/rejected": -740.9835815429688,
|
| 1236 |
+
"loss": 0.2676,
|
| 1237 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1238 |
+
"rewards/chosen": -0.31308645009994507,
|
| 1239 |
+
"rewards/margins": 0.14988043904304504,
|
| 1240 |
+
"rewards/rejected": -0.4629668593406677,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": 0.12038137763738632,
|
| 1247 |
+
"logits/rejected": 0.2056489735841751,
|
| 1248 |
+
"logps/chosen": -667.7818603515625,
|
| 1249 |
+
"logps/rejected": -825.8253173828125,
|
| 1250 |
+
"loss": 0.2025,
|
| 1251 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1252 |
+
"rewards/chosen": -0.303612619638443,
|
| 1253 |
+
"rewards/margins": 0.212577223777771,
|
| 1254 |
+
"rewards/rejected": -0.5161898136138916,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": 0.1971738338470459,
|
| 1261 |
+
"logits/rejected": 0.2837975025177002,
|
| 1262 |
+
"logps/chosen": -673.0835571289062,
|
| 1263 |
+
"logps/rejected": -819.943359375,
|
| 1264 |
+
"loss": 0.1922,
|
| 1265 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 1266 |
+
"rewards/chosen": -0.31264692544937134,
|
| 1267 |
+
"rewards/margins": 0.226339653134346,
|
| 1268 |
+
"rewards/rejected": -0.5389865636825562,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": 0.15372741222381592,
|
| 1275 |
+
"logits/rejected": 0.2788582444190979,
|
| 1276 |
+
"logps/chosen": -612.5509033203125,
|
| 1277 |
+
"logps/rejected": -792.030517578125,
|
| 1278 |
+
"loss": 0.1956,
|
| 1279 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1280 |
+
"rewards/chosen": -0.30290934443473816,
|
| 1281 |
+
"rewards/margins": 0.2101304531097412,
|
| 1282 |
+
"rewards/rejected": -0.5130398273468018,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": 0.1545824110507965,
|
| 1289 |
+
"logits/rejected": 0.25414803624153137,
|
| 1290 |
+
"logps/chosen": -599.8353271484375,
|
| 1291 |
+
"logps/rejected": -818.6397705078125,
|
| 1292 |
+
"loss": 0.1907,
|
| 1293 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1294 |
+
"rewards/chosen": -0.295954167842865,
|
| 1295 |
+
"rewards/margins": 0.24365074932575226,
|
| 1296 |
+
"rewards/rejected": -0.5396049618721008,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": 0.18323026597499847,
|
| 1303 |
+
"logits/rejected": 0.3210206925868988,
|
| 1304 |
+
"logps/chosen": -620.0147705078125,
|
| 1305 |
+
"logps/rejected": -791.1729125976562,
|
| 1306 |
+
"loss": 0.2099,
|
| 1307 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1308 |
+
"rewards/chosen": -0.2964519262313843,
|
| 1309 |
+
"rewards/margins": 0.2253306806087494,
|
| 1310 |
+
"rewards/rejected": -0.521782636642456,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": 0.20417118072509766,
|
| 1317 |
+
"logits/rejected": 0.3416239619255066,
|
| 1318 |
+
"logps/chosen": -689.14697265625,
|
| 1319 |
+
"logps/rejected": -801.5291137695312,
|
| 1320 |
+
"loss": 0.256,
|
| 1321 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1322 |
+
"rewards/chosen": -0.3329721689224243,
|
| 1323 |
+
"rewards/margins": 0.19175252318382263,
|
| 1324 |
+
"rewards/rejected": -0.5247246026992798,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": 0.16527384519577026,
|
| 1331 |
+
"logits/rejected": 0.3157365918159485,
|
| 1332 |
+
"logps/chosen": -678.1207885742188,
|
| 1333 |
+
"logps/rejected": -844.8040161132812,
|
| 1334 |
+
"loss": 0.2264,
|
| 1335 |
+
"rewards/accuracies": 0.78125,
|
| 1336 |
+
"rewards/chosen": -0.3161105513572693,
|
| 1337 |
+
"rewards/margins": 0.22557704150676727,
|
| 1338 |
+
"rewards/rejected": -0.541687548160553,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": 0.11534378677606583,
|
| 1345 |
+
"logits/rejected": 0.2540052831172943,
|
| 1346 |
+
"logps/chosen": -608.9468994140625,
|
| 1347 |
+
"logps/rejected": -772.9508666992188,
|
| 1348 |
+
"loss": 0.2025,
|
| 1349 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1350 |
+
"rewards/chosen": -0.2806348502635956,
|
| 1351 |
+
"rewards/margins": 0.1979130059480667,
|
| 1352 |
+
"rewards/rejected": -0.4785478711128235,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": 0.14051546156406403,
|
| 1359 |
+
"logits/rejected": 0.24735793471336365,
|
| 1360 |
+
"logps/chosen": -619.1126708984375,
|
| 1361 |
+
"logps/rejected": -770.658203125,
|
| 1362 |
+
"loss": 0.2095,
|
| 1363 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1364 |
+
"rewards/chosen": -0.27908432483673096,
|
| 1365 |
+
"rewards/margins": 0.2014855593442917,
|
| 1366 |
+
"rewards/rejected": -0.48056989908218384,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": 0.16361235082149506,
|
| 1373 |
+
"logits/rejected": 0.2182026356458664,
|
| 1374 |
+
"logps/chosen": -574.9110107421875,
|
| 1375 |
+
"logps/rejected": -739.6251220703125,
|
| 1376 |
+
"loss": 0.1942,
|
| 1377 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1378 |
+
"rewards/chosen": -0.26594382524490356,
|
| 1379 |
+
"rewards/margins": 0.22089500725269318,
|
| 1380 |
+
"rewards/rejected": -0.48683881759643555,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": 0.10398687422275543,
|
| 1387 |
+
"logits/rejected": 0.2140096127986908,
|
| 1388 |
+
"logps/chosen": -646.896240234375,
|
| 1389 |
+
"logps/rejected": -763.9075317382812,
|
| 1390 |
+
"loss": 0.2499,
|
| 1391 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1392 |
+
"rewards/chosen": -0.2980521321296692,
|
| 1393 |
+
"rewards/margins": 0.1578332483768463,
|
| 1394 |
+
"rewards/rejected": -0.4558853507041931,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": 0.17513594031333923,
|
| 1401 |
+
"logits/rejected": 0.25838881731033325,
|
| 1402 |
+
"logps/chosen": -671.4928588867188,
|
| 1403 |
+
"logps/rejected": -827.3790893554688,
|
| 1404 |
+
"loss": 0.2148,
|
| 1405 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 1406 |
+
"rewards/chosen": -0.30318453907966614,
|
| 1407 |
+
"rewards/margins": 0.2151859700679779,
|
| 1408 |
+
"rewards/rejected": -0.518370509147644,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": 0.1189759150147438,
|
| 1415 |
+
"logits/rejected": 0.2538264989852905,
|
| 1416 |
+
"logps/chosen": -628.1451416015625,
|
| 1417 |
+
"logps/rejected": -789.3397827148438,
|
| 1418 |
+
"loss": 0.2139,
|
| 1419 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1420 |
+
"rewards/chosen": -0.27723228931427,
|
| 1421 |
+
"rewards/margins": 0.2113499641418457,
|
| 1422 |
+
"rewards/rejected": -0.48858222365379333,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": 0.15936598181724548,
|
| 1429 |
+
"logits/rejected": 0.300658255815506,
|
| 1430 |
+
"logps/chosen": -649.9871215820312,
|
| 1431 |
+
"logps/rejected": -798.48193359375,
|
| 1432 |
+
"loss": 0.2091,
|
| 1433 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1434 |
+
"rewards/chosen": -0.2968089282512665,
|
| 1435 |
+
"rewards/margins": 0.22261710464954376,
|
| 1436 |
+
"rewards/rejected": -0.5194259881973267,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": 0.14960740506649017,
|
| 1443 |
+
"logits/rejected": 0.24492999911308289,
|
| 1444 |
+
"logps/chosen": -646.4168701171875,
|
| 1445 |
+
"logps/rejected": -794.9764404296875,
|
| 1446 |
+
"loss": 0.2394,
|
| 1447 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1448 |
+
"rewards/chosen": -0.3242790699005127,
|
| 1449 |
+
"rewards/margins": 0.1874123513698578,
|
| 1450 |
+
"rewards/rejected": -0.5116914510726929,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": 0.18958871066570282,
|
| 1457 |
+
"logits/rejected": 0.3043481707572937,
|
| 1458 |
+
"logps/chosen": -704.5410766601562,
|
| 1459 |
+
"logps/rejected": -824.1947021484375,
|
| 1460 |
+
"loss": 0.1955,
|
| 1461 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1462 |
+
"rewards/chosen": -0.3319619297981262,
|
| 1463 |
+
"rewards/margins": 0.21646328270435333,
|
| 1464 |
+
"rewards/rejected": -0.5484252572059631,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": 0.12721054255962372,
|
| 1471 |
+
"logits/rejected": 0.2843805253505707,
|
| 1472 |
+
"logps/chosen": -730.2723388671875,
|
| 1473 |
+
"logps/rejected": -913.4192504882812,
|
| 1474 |
+
"loss": 0.1972,
|
| 1475 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1476 |
+
"rewards/chosen": -0.33351242542266846,
|
| 1477 |
+
"rewards/margins": 0.27772635221481323,
|
| 1478 |
+
"rewards/rejected": -0.6112387776374817,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": 0.13960017263889313,
|
| 1485 |
+
"logits/rejected": 0.27561983466148376,
|
| 1486 |
+
"logps/chosen": -659.7611083984375,
|
| 1487 |
+
"logps/rejected": -837.8316650390625,
|
| 1488 |
+
"loss": 0.2062,
|
| 1489 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1490 |
+
"rewards/chosen": -0.32992517948150635,
|
| 1491 |
+
"rewards/margins": 0.23987038433551788,
|
| 1492 |
+
"rewards/rejected": -0.569795548915863,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": 0.13057874143123627,
|
| 1499 |
+
"logits/rejected": 0.2790360152721405,
|
| 1500 |
+
"logps/chosen": -669.2300415039062,
|
| 1501 |
+
"logps/rejected": -898.046875,
|
| 1502 |
+
"loss": 0.1519,
|
| 1503 |
+
"rewards/accuracies": 0.78125,
|
| 1504 |
+
"rewards/chosen": -0.3232869505882263,
|
| 1505 |
+
"rewards/margins": 0.28473716974258423,
|
| 1506 |
+
"rewards/rejected": -0.6080241799354553,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": 0.1361253708600998,
|
| 1513 |
+
"logits/rejected": 0.3236284852027893,
|
| 1514 |
+
"logps/chosen": -678.397216796875,
|
| 1515 |
+
"logps/rejected": -851.6448974609375,
|
| 1516 |
+
"loss": 0.2201,
|
| 1517 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1518 |
+
"rewards/chosen": -0.3409735858440399,
|
| 1519 |
+
"rewards/margins": 0.22014662623405457,
|
| 1520 |
+
"rewards/rejected": -0.5611202120780945,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": 0.17740760743618011,
|
| 1527 |
+
"logits/rejected": 0.29873278737068176,
|
| 1528 |
+
"logps/chosen": -659.0814208984375,
|
| 1529 |
+
"logps/rejected": -794.0924682617188,
|
| 1530 |
+
"loss": 0.2546,
|
| 1531 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1532 |
+
"rewards/chosen": -0.3093605041503906,
|
| 1533 |
+
"rewards/margins": 0.18395116925239563,
|
| 1534 |
+
"rewards/rejected": -0.49331164360046387,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": 0.19297020137310028,
|
| 1541 |
+
"logits/rejected": 0.243372842669487,
|
| 1542 |
+
"logps/chosen": -609.9807739257812,
|
| 1543 |
+
"logps/rejected": -758.6661987304688,
|
| 1544 |
+
"loss": 0.2502,
|
| 1545 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1546 |
+
"rewards/chosen": -0.28266817331314087,
|
| 1547 |
+
"rewards/margins": 0.1889321208000183,
|
| 1548 |
+
"rewards/rejected": -0.4716002941131592,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": 0.1229313462972641,
|
| 1555 |
+
"logits/rejected": 0.24323606491088867,
|
| 1556 |
+
"logps/chosen": -608.5326538085938,
|
| 1557 |
+
"logps/rejected": -756.6920776367188,
|
| 1558 |
+
"loss": 0.2236,
|
| 1559 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1560 |
+
"rewards/chosen": -0.2758868932723999,
|
| 1561 |
+
"rewards/margins": 0.189192533493042,
|
| 1562 |
+
"rewards/rejected": -0.4650794565677643,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": 0.1506945639848709,
|
| 1569 |
+
"logits/rejected": 0.22459396719932556,
|
| 1570 |
+
"logps/chosen": -615.982177734375,
|
| 1571 |
+
"logps/rejected": -760.8124389648438,
|
| 1572 |
+
"loss": 0.2145,
|
| 1573 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1574 |
+
"rewards/chosen": -0.28815990686416626,
|
| 1575 |
+
"rewards/margins": 0.20497973263263702,
|
| 1576 |
+
"rewards/rejected": -0.4931396543979645,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": 0.15958169102668762,
|
| 1583 |
+
"logits/rejected": 0.2522016763687134,
|
| 1584 |
+
"logps/chosen": -692.9052124023438,
|
| 1585 |
+
"logps/rejected": -839.1974487304688,
|
| 1586 |
+
"loss": 0.2082,
|
| 1587 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1588 |
+
"rewards/chosen": -0.34207481145858765,
|
| 1589 |
+
"rewards/margins": 0.2148832082748413,
|
| 1590 |
+
"rewards/rejected": -0.556958019733429,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": 0.1427229940891266,
|
| 1597 |
+
"logits/rejected": 0.27327024936676025,
|
| 1598 |
+
"logps/chosen": -729.3465576171875,
|
| 1599 |
+
"logps/rejected": -863.1507568359375,
|
| 1600 |
+
"loss": 0.256,
|
| 1601 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1602 |
+
"rewards/chosen": -0.37482136487960815,
|
| 1603 |
+
"rewards/margins": 0.2067115306854248,
|
| 1604 |
+
"rewards/rejected": -0.5815330147743225,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": 0.13450102508068085,
|
| 1611 |
+
"logits/rejected": 0.2727622091770172,
|
| 1612 |
+
"logps/chosen": -695.5301513671875,
|
| 1613 |
+
"logps/rejected": -844.9054565429688,
|
| 1614 |
+
"loss": 0.2451,
|
| 1615 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1616 |
+
"rewards/chosen": -0.3660709857940674,
|
| 1617 |
+
"rewards/margins": 0.19018250703811646,
|
| 1618 |
+
"rewards/rejected": -0.5562534928321838,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": 0.1129334345459938,
|
| 1625 |
+
"logits/rejected": 0.24487635493278503,
|
| 1626 |
+
"logps/chosen": -764.1828002929688,
|
| 1627 |
+
"logps/rejected": -941.0518798828125,
|
| 1628 |
+
"loss": 0.1934,
|
| 1629 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1630 |
+
"rewards/chosen": -0.36524254083633423,
|
| 1631 |
+
"rewards/margins": 0.24579265713691711,
|
| 1632 |
+
"rewards/rejected": -0.6110352277755737,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": 0.06655772030353546,
|
| 1639 |
+
"logits/rejected": 0.20836982131004333,
|
| 1640 |
+
"logps/chosen": -686.903564453125,
|
| 1641 |
+
"logps/rejected": -835.3270263671875,
|
| 1642 |
+
"loss": 0.2293,
|
| 1643 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1644 |
+
"rewards/chosen": -0.3618778586387634,
|
| 1645 |
+
"rewards/margins": 0.20230205357074738,
|
| 1646 |
+
"rewards/rejected": -0.5641800165176392,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": 0.12320109456777573,
|
| 1653 |
+
"logits/rejected": 0.22472088038921356,
|
| 1654 |
+
"logps/chosen": -739.9735107421875,
|
| 1655 |
+
"logps/rejected": -892.1875,
|
| 1656 |
+
"loss": 0.211,
|
| 1657 |
+
"rewards/accuracies": 0.75,
|
| 1658 |
+
"rewards/chosen": -0.3738134503364563,
|
| 1659 |
+
"rewards/margins": 0.21076083183288574,
|
| 1660 |
+
"rewards/rejected": -0.5845743417739868,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": 0.12588045001029968,
|
| 1667 |
+
"logits/rejected": 0.23388127982616425,
|
| 1668 |
+
"logps/chosen": -743.3089599609375,
|
| 1669 |
+
"logps/rejected": -864.0367431640625,
|
| 1670 |
+
"loss": 0.2328,
|
| 1671 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1672 |
+
"rewards/chosen": -0.38337722420692444,
|
| 1673 |
+
"rewards/margins": 0.19610758125782013,
|
| 1674 |
+
"rewards/rejected": -0.579484760761261,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": 0.11823949962854385,
|
| 1681 |
+
"logits/rejected": 0.27891501784324646,
|
| 1682 |
+
"logps/chosen": -762.4296264648438,
|
| 1683 |
+
"logps/rejected": -890.8868408203125,
|
| 1684 |
+
"loss": 0.2148,
|
| 1685 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1686 |
+
"rewards/chosen": -0.3807776868343353,
|
| 1687 |
+
"rewards/margins": 0.21602845191955566,
|
| 1688 |
+
"rewards/rejected": -0.5968061685562134,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": 0.10199010372161865,
|
| 1695 |
+
"logits/rejected": 0.19605082273483276,
|
| 1696 |
+
"logps/chosen": -696.8466186523438,
|
| 1697 |
+
"logps/rejected": -917.4085693359375,
|
| 1698 |
+
"loss": 0.1802,
|
| 1699 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1700 |
+
"rewards/chosen": -0.331060528755188,
|
| 1701 |
+
"rewards/margins": 0.27726510167121887,
|
| 1702 |
+
"rewards/rejected": -0.6083256006240845,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": 0.09005758911371231,
|
| 1709 |
+
"logits/rejected": 0.19088336825370789,
|
| 1710 |
+
"logps/chosen": -639.28369140625,
|
| 1711 |
+
"logps/rejected": -782.0608520507812,
|
| 1712 |
+
"loss": 0.2276,
|
| 1713 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1714 |
+
"rewards/chosen": -0.3297976553440094,
|
| 1715 |
+
"rewards/margins": 0.19218826293945312,
|
| 1716 |
+
"rewards/rejected": -0.5219858884811401,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": 0.11749686300754547,
|
| 1723 |
+
"logits/rejected": 0.2290586233139038,
|
| 1724 |
+
"logps/chosen": -687.2972412109375,
|
| 1725 |
+
"logps/rejected": -768.551025390625,
|
| 1726 |
+
"loss": 0.2672,
|
| 1727 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1728 |
+
"rewards/chosen": -0.33632606267929077,
|
| 1729 |
+
"rewards/margins": 0.16481277346611023,
|
| 1730 |
+
"rewards/rejected": -0.5011388063430786,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": 0.05939929559826851,
|
| 1737 |
+
"logits/rejected": 0.21132275462150574,
|
| 1738 |
+
"logps/chosen": -681.4169311523438,
|
| 1739 |
+
"logps/rejected": -855.4088134765625,
|
| 1740 |
+
"loss": 0.2162,
|
| 1741 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1742 |
+
"rewards/chosen": -0.32602256536483765,
|
| 1743 |
+
"rewards/margins": 0.2201872617006302,
|
| 1744 |
+
"rewards/rejected": -0.5462098121643066,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": 0.09077402204275131,
|
| 1751 |
+
"logits/rejected": 0.18115364015102386,
|
| 1752 |
+
"logps/chosen": -656.8944091796875,
|
| 1753 |
+
"logps/rejected": -790.2760009765625,
|
| 1754 |
+
"loss": 0.2539,
|
| 1755 |
+
"rewards/accuracies": 0.75,
|
| 1756 |
+
"rewards/chosen": -0.3007816672325134,
|
| 1757 |
+
"rewards/margins": 0.20733746886253357,
|
| 1758 |
+
"rewards/rejected": -0.5081192255020142,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": 0.07764784246683121,
|
| 1765 |
+
"logits/rejected": 0.2526463568210602,
|
| 1766 |
+
"logps/chosen": -716.9674682617188,
|
| 1767 |
+
"logps/rejected": -843.5106201171875,
|
| 1768 |
+
"loss": 0.2041,
|
| 1769 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1770 |
+
"rewards/chosen": -0.30957937240600586,
|
| 1771 |
+
"rewards/margins": 0.23023274540901184,
|
| 1772 |
+
"rewards/rejected": -0.5398121476173401,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": 0.13033337891101837,
|
| 1779 |
+
"logits/rejected": 0.21490690112113953,
|
| 1780 |
+
"logps/chosen": -674.5143432617188,
|
| 1781 |
+
"logps/rejected": -827.2547607421875,
|
| 1782 |
+
"loss": 0.212,
|
| 1783 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1784 |
+
"rewards/chosen": -0.3340405523777008,
|
| 1785 |
+
"rewards/margins": 0.21128436923027039,
|
| 1786 |
+
"rewards/rejected": -0.5453249216079712,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": 0.0994940996170044,
|
| 1793 |
+
"logits/rejected": 0.23082152009010315,
|
| 1794 |
+
"logps/chosen": -656.1998291015625,
|
| 1795 |
+
"logps/rejected": -833.0138549804688,
|
| 1796 |
+
"loss": 0.2029,
|
| 1797 |
+
"rewards/accuracies": 0.78125,
|
| 1798 |
+
"rewards/chosen": -0.3017929196357727,
|
| 1799 |
+
"rewards/margins": 0.23969045281410217,
|
| 1800 |
+
"rewards/rejected": -0.5414833426475525,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": 0.10936876386404037,
|
| 1807 |
+
"logits/rejected": 0.20990300178527832,
|
| 1808 |
+
"logps/chosen": -660.2184448242188,
|
| 1809 |
+
"logps/rejected": -846.3512573242188,
|
| 1810 |
+
"loss": 0.2101,
|
| 1811 |
+
"rewards/accuracies": 0.75,
|
| 1812 |
+
"rewards/chosen": -0.31637948751449585,
|
| 1813 |
+
"rewards/margins": 0.23163414001464844,
|
| 1814 |
+
"rewards/rejected": -0.5480136871337891,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": 0.10218968242406845,
|
| 1821 |
+
"logits/rejected": 0.2423768788576126,
|
| 1822 |
+
"logps/chosen": -733.5655517578125,
|
| 1823 |
+
"logps/rejected": -864.4533081054688,
|
| 1824 |
+
"loss": 0.2025,
|
| 1825 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1826 |
+
"rewards/chosen": -0.324023574590683,
|
| 1827 |
+
"rewards/margins": 0.2365175038576126,
|
| 1828 |
+
"rewards/rejected": -0.560541033744812,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": 0.09106200188398361,
|
| 1835 |
+
"logits/rejected": 0.196526437997818,
|
| 1836 |
+
"logps/chosen": -663.4789428710938,
|
| 1837 |
+
"logps/rejected": -786.8779907226562,
|
| 1838 |
+
"loss": 0.2498,
|
| 1839 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1840 |
+
"rewards/chosen": -0.32671403884887695,
|
| 1841 |
+
"rewards/margins": 0.19609105587005615,
|
| 1842 |
+
"rewards/rejected": -0.5228050351142883,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": 0.09490621089935303,
|
| 1849 |
+
"logits/rejected": 0.26305851340293884,
|
| 1850 |
+
"logps/chosen": -669.8858032226562,
|
| 1851 |
+
"logps/rejected": -820.6624755859375,
|
| 1852 |
+
"loss": 0.1875,
|
| 1853 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1854 |
+
"rewards/chosen": -0.3120814263820648,
|
| 1855 |
+
"rewards/margins": 0.2310735285282135,
|
| 1856 |
+
"rewards/rejected": -0.5431549549102783,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": 0.07294271886348724,
|
| 1863 |
+
"logits/rejected": 0.15242712199687958,
|
| 1864 |
+
"logps/chosen": -652.7977294921875,
|
| 1865 |
+
"logps/rejected": -800.0413208007812,
|
| 1866 |
+
"loss": 0.2138,
|
| 1867 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1868 |
+
"rewards/chosen": -0.33722367882728577,
|
| 1869 |
+
"rewards/margins": 0.18947935104370117,
|
| 1870 |
+
"rewards/rejected": -0.5267030000686646,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": 0.07662687450647354,
|
| 1877 |
+
"logits/rejected": 0.206211119890213,
|
| 1878 |
+
"logps/chosen": -651.1556396484375,
|
| 1879 |
+
"logps/rejected": -795.70556640625,
|
| 1880 |
+
"loss": 0.2235,
|
| 1881 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1882 |
+
"rewards/chosen": -0.33270731568336487,
|
| 1883 |
+
"rewards/margins": 0.18210896849632263,
|
| 1884 |
+
"rewards/rejected": -0.5148162841796875,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": 0.10683353245258331,
|
| 1891 |
+
"logits/rejected": 0.14309810101985931,
|
| 1892 |
+
"logps/chosen": -733.0233154296875,
|
| 1893 |
+
"logps/rejected": -832.6646728515625,
|
| 1894 |
+
"loss": 0.2157,
|
| 1895 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1896 |
+
"rewards/chosen": -0.33933931589126587,
|
| 1897 |
+
"rewards/margins": 0.19576075673103333,
|
| 1898 |
+
"rewards/rejected": -0.5351000428199768,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": 0.045632436871528625,
|
| 1905 |
+
"logits/rejected": 0.22544965147972107,
|
| 1906 |
+
"logps/chosen": -701.60205078125,
|
| 1907 |
+
"logps/rejected": -801.7410888671875,
|
| 1908 |
+
"loss": 0.205,
|
| 1909 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1910 |
+
"rewards/chosen": -0.3220959007740021,
|
| 1911 |
+
"rewards/margins": 0.21180233359336853,
|
| 1912 |
+
"rewards/rejected": -0.5338982343673706,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": 0.11129830032587051,
|
| 1919 |
+
"logits/rejected": 0.277961790561676,
|
| 1920 |
+
"logps/chosen": -685.46923828125,
|
| 1921 |
+
"logps/rejected": -835.8211059570312,
|
| 1922 |
+
"loss": 0.1954,
|
| 1923 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1924 |
+
"rewards/chosen": -0.3089851438999176,
|
| 1925 |
+
"rewards/margins": 0.24158485233783722,
|
| 1926 |
+
"rewards/rejected": -0.550570011138916,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": 0.08607203513383865,
|
| 1933 |
+
"logits/rejected": 0.2120324820280075,
|
| 1934 |
+
"logps/chosen": -670.0626831054688,
|
| 1935 |
+
"logps/rejected": -819.9489135742188,
|
| 1936 |
+
"loss": 0.2555,
|
| 1937 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1938 |
+
"rewards/chosen": -0.3491436243057251,
|
| 1939 |
+
"rewards/margins": 0.190331369638443,
|
| 1940 |
+
"rewards/rejected": -0.5394749641418457,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": 0.09642196446657181,
|
| 1947 |
+
"logits/rejected": 0.21866998076438904,
|
| 1948 |
+
"logps/chosen": -670.3609619140625,
|
| 1949 |
+
"logps/rejected": -831.7306518554688,
|
| 1950 |
+
"loss": 0.1985,
|
| 1951 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1952 |
+
"rewards/chosen": -0.30979031324386597,
|
| 1953 |
+
"rewards/margins": 0.22851744294166565,
|
| 1954 |
+
"rewards/rejected": -0.538307785987854,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": 0.15417559444904327,
|
| 1961 |
+
"logits/rejected": 0.23215246200561523,
|
| 1962 |
+
"logps/chosen": -644.1177368164062,
|
| 1963 |
+
"logps/rejected": -855.5202026367188,
|
| 1964 |
+
"loss": 0.2107,
|
| 1965 |
+
"rewards/accuracies": 0.75,
|
| 1966 |
+
"rewards/chosen": -0.30276650190353394,
|
| 1967 |
+
"rewards/margins": 0.25079673528671265,
|
| 1968 |
+
"rewards/rejected": -0.5535632371902466,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": 0.1388302445411682,
|
| 1975 |
+
"logits/rejected": 0.2623920440673828,
|
| 1976 |
+
"logps/chosen": -750.0091552734375,
|
| 1977 |
+
"logps/rejected": -935.58251953125,
|
| 1978 |
+
"loss": 0.1996,
|
| 1979 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1980 |
+
"rewards/chosen": -0.36703410744667053,
|
| 1981 |
+
"rewards/margins": 0.24573786556720734,
|
| 1982 |
+
"rewards/rejected": -0.6127719283103943,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": 0.1403401494026184,
|
| 1989 |
+
"logits/rejected": 0.2397807389497757,
|
| 1990 |
+
"logps/chosen": -718.9532470703125,
|
| 1991 |
+
"logps/rejected": -856.7537231445312,
|
| 1992 |
+
"loss": 0.1984,
|
| 1993 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1994 |
+
"rewards/chosen": -0.32988426089286804,
|
| 1995 |
+
"rewards/margins": 0.23926320672035217,
|
| 1996 |
+
"rewards/rejected": -0.5691474676132202,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": 0.10472740232944489,
|
| 2003 |
+
"logits/rejected": 0.3000238537788391,
|
| 2004 |
+
"logps/chosen": -734.3883056640625,
|
| 2005 |
+
"logps/rejected": -850.7344970703125,
|
| 2006 |
+
"loss": 0.1807,
|
| 2007 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2008 |
+
"rewards/chosen": -0.341549813747406,
|
| 2009 |
+
"rewards/margins": 0.23151779174804688,
|
| 2010 |
+
"rewards/rejected": -0.5730676054954529,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": 0.16170555353164673,
|
| 2017 |
+
"logits/rejected": 0.23735301196575165,
|
| 2018 |
+
"logps/chosen": -682.0318603515625,
|
| 2019 |
+
"logps/rejected": -834.2679443359375,
|
| 2020 |
+
"loss": 0.2227,
|
| 2021 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 2022 |
+
"rewards/chosen": -0.3349572718143463,
|
| 2023 |
+
"rewards/margins": 0.20067913830280304,
|
| 2024 |
+
"rewards/rejected": -0.5356364250183105,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": 0.09115556627511978,
|
| 2031 |
+
"logits/rejected": 0.20479066669940948,
|
| 2032 |
+
"logps/chosen": -661.0646362304688,
|
| 2033 |
+
"logps/rejected": -865.4320068359375,
|
| 2034 |
+
"loss": 0.2056,
|
| 2035 |
+
"rewards/accuracies": 0.793749988079071,
|
| 2036 |
+
"rewards/chosen": -0.3348444104194641,
|
| 2037 |
+
"rewards/margins": 0.23586812615394592,
|
| 2038 |
+
"rewards/rejected": -0.5707124471664429,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": 0.09788443148136139,
|
| 2045 |
+
"logits/rejected": 0.24574396014213562,
|
| 2046 |
+
"logps/chosen": -734.4356689453125,
|
| 2047 |
+
"logps/rejected": -870.92236328125,
|
| 2048 |
+
"loss": 0.2197,
|
| 2049 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2050 |
+
"rewards/chosen": -0.35589176416397095,
|
| 2051 |
+
"rewards/margins": 0.2205926477909088,
|
| 2052 |
+
"rewards/rejected": -0.5764843225479126,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": 0.11591117084026337,
|
| 2059 |
+
"logits/rejected": 0.23913173377513885,
|
| 2060 |
+
"logps/chosen": -703.4747314453125,
|
| 2061 |
+
"logps/rejected": -862.8414916992188,
|
| 2062 |
+
"loss": 0.2322,
|
| 2063 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 2064 |
+
"rewards/chosen": -0.3314746022224426,
|
| 2065 |
+
"rewards/margins": 0.23115992546081543,
|
| 2066 |
+
"rewards/rejected": -0.5626345872879028,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": 0.16051790118217468,
|
| 2073 |
+
"logits/rejected": 0.27909934520721436,
|
| 2074 |
+
"logps/chosen": -696.7191772460938,
|
| 2075 |
+
"logps/rejected": -821.4385986328125,
|
| 2076 |
+
"loss": 0.2326,
|
| 2077 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2078 |
+
"rewards/chosen": -0.3547061085700989,
|
| 2079 |
+
"rewards/margins": 0.1964879333972931,
|
| 2080 |
+
"rewards/rejected": -0.5511940717697144,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": 0.12144766002893448,
|
| 2087 |
+
"logits/rejected": 0.21441468596458435,
|
| 2088 |
+
"logps/chosen": -707.2329711914062,
|
| 2089 |
+
"logps/rejected": -870.8890380859375,
|
| 2090 |
+
"loss": 0.2213,
|
| 2091 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2092 |
+
"rewards/chosen": -0.34999531507492065,
|
| 2093 |
+
"rewards/margins": 0.2191038429737091,
|
| 2094 |
+
"rewards/rejected": -0.5690991282463074,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": 0.16252949833869934,
|
| 2101 |
+
"logits/rejected": 0.3306509852409363,
|
| 2102 |
+
"logps/chosen": -655.1351318359375,
|
| 2103 |
+
"logps/rejected": -821.1975708007812,
|
| 2104 |
+
"loss": 0.2245,
|
| 2105 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2106 |
+
"rewards/chosen": -0.33034515380859375,
|
| 2107 |
+
"rewards/margins": 0.22635062038898468,
|
| 2108 |
+
"rewards/rejected": -0.5566957592964172,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": 0.11046645790338516,
|
| 2115 |
+
"logits/rejected": 0.2029370814561844,
|
| 2116 |
+
"logps/chosen": -685.1182861328125,
|
| 2117 |
+
"logps/rejected": -852.0540161132812,
|
| 2118 |
+
"loss": 0.1796,
|
| 2119 |
+
"rewards/accuracies": 0.78125,
|
| 2120 |
+
"rewards/chosen": -0.3330523669719696,
|
| 2121 |
+
"rewards/margins": 0.2372111976146698,
|
| 2122 |
+
"rewards/rejected": -0.5702635645866394,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": 0.13619574904441833,
|
| 2129 |
+
"logits/rejected": 0.21550631523132324,
|
| 2130 |
+
"logps/chosen": -650.5691528320312,
|
| 2131 |
+
"logps/rejected": -879.0435791015625,
|
| 2132 |
+
"loss": 0.2037,
|
| 2133 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2134 |
+
"rewards/chosen": -0.3198038637638092,
|
| 2135 |
+
"rewards/margins": 0.2528200149536133,
|
| 2136 |
+
"rewards/rejected": -0.5726238489151001,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": 0.10330195724964142,
|
| 2143 |
+
"logits/rejected": 0.2254125326871872,
|
| 2144 |
+
"logps/chosen": -674.9971923828125,
|
| 2145 |
+
"logps/rejected": -825.3990478515625,
|
| 2146 |
+
"loss": 0.2224,
|
| 2147 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2148 |
+
"rewards/chosen": -0.3395020067691803,
|
| 2149 |
+
"rewards/margins": 0.21332807838916779,
|
| 2150 |
+
"rewards/rejected": -0.5528300404548645,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": 0.142780140042305,
|
| 2157 |
+
"logits/rejected": 0.23002369701862335,
|
| 2158 |
+
"logps/chosen": -725.0726318359375,
|
| 2159 |
+
"logps/rejected": -843.7293701171875,
|
| 2160 |
+
"loss": 0.2347,
|
| 2161 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2162 |
+
"rewards/chosen": -0.3490670323371887,
|
| 2163 |
+
"rewards/margins": 0.21415701508522034,
|
| 2164 |
+
"rewards/rejected": -0.5632239580154419,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": 0.1431182622909546,
|
| 2171 |
+
"logits/rejected": 0.2636813521385193,
|
| 2172 |
+
"logps/chosen": -640.8516845703125,
|
| 2173 |
+
"logps/rejected": -807.3698120117188,
|
| 2174 |
+
"loss": 0.2157,
|
| 2175 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2176 |
+
"rewards/chosen": -0.3060576617717743,
|
| 2177 |
+
"rewards/margins": 0.24311813712120056,
|
| 2178 |
+
"rewards/rejected": -0.5491757988929749,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": 0.09661155939102173,
|
| 2185 |
+
"logits/rejected": 0.21029344201087952,
|
| 2186 |
+
"logps/chosen": -712.8273315429688,
|
| 2187 |
+
"logps/rejected": -845.70263671875,
|
| 2188 |
+
"loss": 0.2374,
|
| 2189 |
+
"rewards/accuracies": 0.75,
|
| 2190 |
+
"rewards/chosen": -0.32992398738861084,
|
| 2191 |
+
"rewards/margins": 0.21484914422035217,
|
| 2192 |
+
"rewards/rejected": -0.5447731018066406,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": 0.1100638136267662,
|
| 2199 |
+
"logits/rejected": 0.25361213088035583,
|
| 2200 |
+
"logps/chosen": -619.2400512695312,
|
| 2201 |
+
"logps/rejected": -786.0677490234375,
|
| 2202 |
+
"loss": 0.2424,
|
| 2203 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2204 |
+
"rewards/chosen": -0.3038698732852936,
|
| 2205 |
+
"rewards/margins": 0.20768532156944275,
|
| 2206 |
+
"rewards/rejected": -0.5115551948547363,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": 0.1189003735780716,
|
| 2213 |
+
"logits/rejected": 0.21380853652954102,
|
| 2214 |
+
"logps/chosen": -671.5353393554688,
|
| 2215 |
+
"logps/rejected": -847.8660888671875,
|
| 2216 |
+
"loss": 0.2415,
|
| 2217 |
+
"rewards/accuracies": 0.71875,
|
| 2218 |
+
"rewards/chosen": -0.34101420640945435,
|
| 2219 |
+
"rewards/margins": 0.20406432449817657,
|
| 2220 |
+
"rewards/rejected": -0.545078456401825,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": 0.10434021800756454,
|
| 2227 |
+
"logits/rejected": 0.2150150090456009,
|
| 2228 |
+
"logps/chosen": -659.5474853515625,
|
| 2229 |
+
"logps/rejected": -801.54052734375,
|
| 2230 |
+
"loss": 0.2019,
|
| 2231 |
+
"rewards/accuracies": 0.75,
|
| 2232 |
+
"rewards/chosen": -0.28841426968574524,
|
| 2233 |
+
"rewards/margins": 0.23222117125988007,
|
| 2234 |
+
"rewards/rejected": -0.5206354856491089,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": 0.13257619738578796,
|
| 2241 |
+
"logits/rejected": 0.2614479959011078,
|
| 2242 |
+
"logps/chosen": -638.5202026367188,
|
| 2243 |
+
"logps/rejected": -793.9677734375,
|
| 2244 |
+
"loss": 0.1989,
|
| 2245 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2246 |
+
"rewards/chosen": -0.29665178060531616,
|
| 2247 |
+
"rewards/margins": 0.21199484169483185,
|
| 2248 |
+
"rewards/rejected": -0.5086466073989868,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": 0.10789693892002106,
|
| 2255 |
+
"logits/rejected": 0.24690580368041992,
|
| 2256 |
+
"logps/chosen": -667.6051025390625,
|
| 2257 |
+
"logps/rejected": -793.3514404296875,
|
| 2258 |
+
"loss": 0.2256,
|
| 2259 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2260 |
+
"rewards/chosen": -0.3308831751346588,
|
| 2261 |
+
"rewards/margins": 0.1889718472957611,
|
| 2262 |
+
"rewards/rejected": -0.5198550224304199,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": 0.052944671362638474,
|
| 2269 |
+
"logits/rejected": 0.1601809859275818,
|
| 2270 |
+
"logps/chosen": -652.5521240234375,
|
| 2271 |
+
"logps/rejected": -823.5758666992188,
|
| 2272 |
+
"loss": 0.2115,
|
| 2273 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2274 |
+
"rewards/chosen": -0.32761263847351074,
|
| 2275 |
+
"rewards/margins": 0.21856379508972168,
|
| 2276 |
+
"rewards/rejected": -0.5461763739585876,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": 0.10616923868656158,
|
| 2283 |
+
"logits/rejected": 0.2180422991514206,
|
| 2284 |
+
"logps/chosen": -636.3297119140625,
|
| 2285 |
+
"logps/rejected": -800.4964599609375,
|
| 2286 |
+
"loss": 0.203,
|
| 2287 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2288 |
+
"rewards/chosen": -0.303327739238739,
|
| 2289 |
+
"rewards/margins": 0.21036402881145477,
|
| 2290 |
+
"rewards/rejected": -0.513691782951355,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": 0.09138272702693939,
|
| 2297 |
+
"logits/rejected": 0.20507724583148956,
|
| 2298 |
+
"logps/chosen": -648.2923583984375,
|
| 2299 |
+
"logps/rejected": -802.4161987304688,
|
| 2300 |
+
"loss": 0.2113,
|
| 2301 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2302 |
+
"rewards/chosen": -0.3106837868690491,
|
| 2303 |
+
"rewards/margins": 0.21935255825519562,
|
| 2304 |
+
"rewards/rejected": -0.5300363302230835,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": 0.07225445657968521,
|
| 2311 |
+
"logits/rejected": 0.2319096028804779,
|
| 2312 |
+
"logps/chosen": -682.279296875,
|
| 2313 |
+
"logps/rejected": -819.6962890625,
|
| 2314 |
+
"loss": 0.2117,
|
| 2315 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2316 |
+
"rewards/chosen": -0.32190632820129395,
|
| 2317 |
+
"rewards/margins": 0.2106344997882843,
|
| 2318 |
+
"rewards/rejected": -0.5325408577919006,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": 0.09080176055431366,
|
| 2325 |
+
"logits/rejected": 0.22487780451774597,
|
| 2326 |
+
"logps/chosen": -728.700439453125,
|
| 2327 |
+
"logps/rejected": -872.6180419921875,
|
| 2328 |
+
"loss": 0.2372,
|
| 2329 |
+
"rewards/accuracies": 0.75,
|
| 2330 |
+
"rewards/chosen": -0.35785117745399475,
|
| 2331 |
+
"rewards/margins": 0.20169305801391602,
|
| 2332 |
+
"rewards/rejected": -0.5595442056655884,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": 0.11907955259084702,
|
| 2339 |
+
"logits/rejected": 0.2156171053647995,
|
| 2340 |
+
"logps/chosen": -644.99560546875,
|
| 2341 |
+
"logps/rejected": -801.831787109375,
|
| 2342 |
+
"loss": 0.2024,
|
| 2343 |
+
"rewards/accuracies": 0.75,
|
| 2344 |
+
"rewards/chosen": -0.308158278465271,
|
| 2345 |
+
"rewards/margins": 0.2264772653579712,
|
| 2346 |
+
"rewards/rejected": -0.5346355438232422,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": 0.12947291135787964,
|
| 2353 |
+
"logits/rejected": 0.22007863223552704,
|
| 2354 |
+
"logps/chosen": -710.0556030273438,
|
| 2355 |
+
"logps/rejected": -859.5272216796875,
|
| 2356 |
+
"loss": 0.1906,
|
| 2357 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2358 |
+
"rewards/chosen": -0.3359071612358093,
|
| 2359 |
+
"rewards/margins": 0.237164705991745,
|
| 2360 |
+
"rewards/rejected": -0.5730718374252319,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": 0.09690668433904648,
|
| 2367 |
+
"logits/rejected": 0.19589988887310028,
|
| 2368 |
+
"logps/chosen": -685.9202880859375,
|
| 2369 |
+
"logps/rejected": -816.6348876953125,
|
| 2370 |
+
"loss": 0.2104,
|
| 2371 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 2372 |
+
"rewards/chosen": -0.3336608111858368,
|
| 2373 |
+
"rewards/margins": 0.20780424773693085,
|
| 2374 |
+
"rewards/rejected": -0.5414651036262512,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": 0.10044785588979721,
|
| 2381 |
+
"logits/rejected": 0.1938716471195221,
|
| 2382 |
+
"logps/chosen": -668.4989013671875,
|
| 2383 |
+
"logps/rejected": -797.7630615234375,
|
| 2384 |
+
"loss": 0.2075,
|
| 2385 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2386 |
+
"rewards/chosen": -0.3294285535812378,
|
| 2387 |
+
"rewards/margins": 0.20013563334941864,
|
| 2388 |
+
"rewards/rejected": -0.5295641422271729,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": 0.11922971159219742,
|
| 2395 |
+
"logits/rejected": 0.1923786997795105,
|
| 2396 |
+
"logps/chosen": -688.7864990234375,
|
| 2397 |
+
"logps/rejected": -845.6558837890625,
|
| 2398 |
+
"loss": 0.2053,
|
| 2399 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2400 |
+
"rewards/chosen": -0.34360042214393616,
|
| 2401 |
+
"rewards/margins": 0.2216511070728302,
|
| 2402 |
+
"rewards/rejected": -0.5652515292167664,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": 0.0872936099767685,
|
| 2409 |
+
"logits/rejected": 0.1970546394586563,
|
| 2410 |
+
"logps/chosen": -678.56982421875,
|
| 2411 |
+
"logps/rejected": -870.0894775390625,
|
| 2412 |
+
"loss": 0.2064,
|
| 2413 |
+
"rewards/accuracies": 0.8125,
|
| 2414 |
+
"rewards/chosen": -0.32151633501052856,
|
| 2415 |
+
"rewards/margins": 0.24507319927215576,
|
| 2416 |
+
"rewards/rejected": -0.5665895342826843,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": 0.09590867161750793,
|
| 2423 |
+
"logits/rejected": 0.20923268795013428,
|
| 2424 |
+
"logps/chosen": -639.2576904296875,
|
| 2425 |
+
"logps/rejected": -808.9605712890625,
|
| 2426 |
+
"loss": 0.191,
|
| 2427 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 2428 |
+
"rewards/chosen": -0.3116968870162964,
|
| 2429 |
+
"rewards/margins": 0.22501316666603088,
|
| 2430 |
+
"rewards/rejected": -0.5367100834846497,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": 0.10010067373514175,
|
| 2437 |
+
"logits/rejected": 0.24267680943012238,
|
| 2438 |
+
"logps/chosen": -634.7396850585938,
|
| 2439 |
+
"logps/rejected": -830.8876953125,
|
| 2440 |
+
"loss": 0.2178,
|
| 2441 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2442 |
+
"rewards/chosen": -0.29997509717941284,
|
| 2443 |
+
"rewards/margins": 0.24514777958393097,
|
| 2444 |
+
"rewards/rejected": -0.5451229214668274,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": 0.08919323980808258,
|
| 2451 |
+
"logits/rejected": 0.17960329353809357,
|
| 2452 |
+
"logps/chosen": -699.3638916015625,
|
| 2453 |
+
"logps/rejected": -878.31689453125,
|
| 2454 |
+
"loss": 0.1988,
|
| 2455 |
+
"rewards/accuracies": 0.793749988079071,
|
| 2456 |
+
"rewards/chosen": -0.32689014077186584,
|
| 2457 |
+
"rewards/margins": 0.23287110030651093,
|
| 2458 |
+
"rewards/rejected": -0.5597612857818604,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": 0.07647444307804108,
|
| 2465 |
+
"logits/rejected": 0.25179851055145264,
|
| 2466 |
+
"logps/chosen": -693.7523803710938,
|
| 2467 |
+
"logps/rejected": -840.65234375,
|
| 2468 |
+
"loss": 0.2016,
|
| 2469 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2470 |
+
"rewards/chosen": -0.3338211476802826,
|
| 2471 |
+
"rewards/margins": 0.21626095473766327,
|
| 2472 |
+
"rewards/rejected": -0.5500820875167847,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": 0.05137849971652031,
|
| 2479 |
+
"logits/rejected": 0.19751080870628357,
|
| 2480 |
+
"logps/chosen": -635.8048095703125,
|
| 2481 |
+
"logps/rejected": -825.5013427734375,
|
| 2482 |
+
"loss": 0.212,
|
| 2483 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2484 |
+
"rewards/chosen": -0.31089353561401367,
|
| 2485 |
+
"rewards/margins": 0.23858308792114258,
|
| 2486 |
+
"rewards/rejected": -0.5494766235351562,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": 0.13479098677635193,
|
| 2493 |
+
"logits/rejected": 0.22830185294151306,
|
| 2494 |
+
"logps/chosen": -664.4447631835938,
|
| 2495 |
+
"logps/rejected": -820.0628662109375,
|
| 2496 |
+
"loss": 0.2085,
|
| 2497 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2498 |
+
"rewards/chosen": -0.2986433804035187,
|
| 2499 |
+
"rewards/margins": 0.2351032793521881,
|
| 2500 |
+
"rewards/rejected": -0.533746600151062,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": 0.0736847072839737,
|
| 2507 |
+
"logits/rejected": 0.21154184639453888,
|
| 2508 |
+
"logps/chosen": -644.4476928710938,
|
| 2509 |
+
"logps/rejected": -827.611328125,
|
| 2510 |
+
"loss": 0.2101,
|
| 2511 |
+
"rewards/accuracies": 0.793749988079071,
|
| 2512 |
+
"rewards/chosen": -0.32568278908729553,
|
| 2513 |
+
"rewards/margins": 0.22031357884407043,
|
| 2514 |
+
"rewards/rejected": -0.5459963083267212,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": 0.11332382261753082,
|
| 2521 |
+
"logits/rejected": 0.2286304533481598,
|
| 2522 |
+
"logps/chosen": -655.7117919921875,
|
| 2523 |
+
"logps/rejected": -838.4694213867188,
|
| 2524 |
+
"loss": 0.2403,
|
| 2525 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2526 |
+
"rewards/chosen": -0.3177303373813629,
|
| 2527 |
+
"rewards/margins": 0.2210434377193451,
|
| 2528 |
+
"rewards/rejected": -0.538773775100708,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": 0.09552569687366486,
|
| 2535 |
+
"logits/rejected": 0.21039338409900665,
|
| 2536 |
+
"logps/chosen": -625.5585327148438,
|
| 2537 |
+
"logps/rejected": -785.0277099609375,
|
| 2538 |
+
"loss": 0.2167,
|
| 2539 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2540 |
+
"rewards/chosen": -0.3133324980735779,
|
| 2541 |
+
"rewards/margins": 0.19650213420391083,
|
| 2542 |
+
"rewards/rejected": -0.5098346471786499,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": 0.12665894627571106,
|
| 2549 |
+
"logits/rejected": 0.25432324409484863,
|
| 2550 |
+
"logps/chosen": -717.9019775390625,
|
| 2551 |
+
"logps/rejected": -885.8001098632812,
|
| 2552 |
+
"loss": 0.181,
|
| 2553 |
+
"rewards/accuracies": 0.831250011920929,
|
| 2554 |
+
"rewards/chosen": -0.34058862924575806,
|
| 2555 |
+
"rewards/margins": 0.23419833183288574,
|
| 2556 |
+
"rewards/rejected": -0.5747869610786438,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": 0.07009974867105484,
|
| 2563 |
+
"logits/rejected": 0.18696331977844238,
|
| 2564 |
+
"logps/chosen": -648.749267578125,
|
| 2565 |
+
"logps/rejected": -838.9640502929688,
|
| 2566 |
+
"loss": 0.2079,
|
| 2567 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2568 |
+
"rewards/chosen": -0.30777597427368164,
|
| 2569 |
+
"rewards/margins": 0.23736786842346191,
|
| 2570 |
+
"rewards/rejected": -0.5451437830924988,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": 0.04345223680138588,
|
| 2577 |
+
"logits/rejected": 0.21128901839256287,
|
| 2578 |
+
"logps/chosen": -680.11376953125,
|
| 2579 |
+
"logps/rejected": -825.4275512695312,
|
| 2580 |
+
"loss": 0.2032,
|
| 2581 |
+
"rewards/accuracies": 0.75,
|
| 2582 |
+
"rewards/chosen": -0.3200992941856384,
|
| 2583 |
+
"rewards/margins": 0.22688953578472137,
|
| 2584 |
+
"rewards/rejected": -0.546988844871521,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": 0.11998043209314346,
|
| 2591 |
+
"logits/rejected": 0.20321743190288544,
|
| 2592 |
+
"logps/chosen": -673.5576782226562,
|
| 2593 |
+
"logps/rejected": -804.1566162109375,
|
| 2594 |
+
"loss": 0.2202,
|
| 2595 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2596 |
+
"rewards/chosen": -0.32543522119522095,
|
| 2597 |
+
"rewards/margins": 0.22123821079730988,
|
| 2598 |
+
"rewards/rejected": -0.5466734170913696,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": 0.08479473739862442,
|
| 2605 |
+
"logits/rejected": 0.24488599598407745,
|
| 2606 |
+
"logps/chosen": -624.8433837890625,
|
| 2607 |
+
"logps/rejected": -800.512939453125,
|
| 2608 |
+
"loss": 0.2102,
|
| 2609 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2610 |
+
"rewards/chosen": -0.3155784010887146,
|
| 2611 |
+
"rewards/margins": 0.21801578998565674,
|
| 2612 |
+
"rewards/rejected": -0.5335941910743713,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": 0.0935547798871994,
|
| 2619 |
+
"logits/rejected": 0.16574546694755554,
|
| 2620 |
+
"logps/chosen": -698.1727294921875,
|
| 2621 |
+
"logps/rejected": -887.7645263671875,
|
| 2622 |
+
"loss": 0.214,
|
| 2623 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2624 |
+
"rewards/chosen": -0.36060822010040283,
|
| 2625 |
+
"rewards/margins": 0.218820258975029,
|
| 2626 |
+
"rewards/rejected": -0.5794284343719482,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": 0.07583248615264893,
|
| 2633 |
+
"logits/rejected": 0.24347925186157227,
|
| 2634 |
+
"logps/chosen": -675.1774291992188,
|
| 2635 |
+
"logps/rejected": -852.7301025390625,
|
| 2636 |
+
"loss": 0.2069,
|
| 2637 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2638 |
+
"rewards/chosen": -0.3129870295524597,
|
| 2639 |
+
"rewards/margins": 0.24173569679260254,
|
| 2640 |
+
"rewards/rejected": -0.5547226667404175,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 0.23111479535102844,
|
| 2648 |
+
"train_runtime": 16991.5507,
|
| 2649 |
+
"train_samples_per_second": 1.766,
|
| 2650 |
+
"train_steps_per_second": 0.11
|
| 2651 |
+
}
|
| 2652 |
+
],
|
| 2653 |
+
"logging_steps": 10,
|
| 2654 |
+
"max_steps": 1875,
|
| 2655 |
+
"num_input_tokens_seen": 0,
|
| 2656 |
+
"num_train_epochs": 1,
|
| 2657 |
+
"save_steps": 100,
|
| 2658 |
+
"total_flos": 0.0,
|
| 2659 |
+
"train_batch_size": 4,
|
| 2660 |
+
"trial_name": null,
|
| 2661 |
+
"trial_params": null
|
| 2662 |
+
}
|