Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May13_13-38-42_gpu4-119-5/events.out.tfevents.1715571664.gpu4-119-5.163041.0 +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-v14-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-v14-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 sha256:3aa6d05ed2eb2175716db0f3bffa52ba38eed2c12e9608ded1cd6b66aceb49b1
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2332912155151367,
|
| 4 |
+
"train_runtime": 17312.5985,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 1.733,
|
| 7 |
+
"train_steps_per_second": 0.108
|
| 8 |
+
}
|
runs/May13_13-38-42_gpu4-119-5/events.out.tfevents.1715571664.gpu4-119-5.163041.0
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 sha256:3cf0d9d9ea93e6fc3aae5d62fdc5da98e45f92ae1d3493683133649a8987eddd
|
| 3 |
+
size 124230
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2332912155151367,
|
| 4 |
+
"train_runtime": 17312.5985,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 1.733,
|
| 7 |
+
"train_steps_per_second": 0.108
|
| 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": 0.09666420519351959,
|
| 15 |
+
"logits/rejected": 0.3057119846343994,
|
| 16 |
+
"logps/chosen": -431.574951171875,
|
| 17 |
+
"logps/rejected": -283.99554443359375,
|
| 18 |
+
"loss": 0.3643,
|
| 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": 0.06902924180030823,
|
| 29 |
+
"logits/rejected": 0.19579637050628662,
|
| 30 |
+
"logps/chosen": -345.7933654785156,
|
| 31 |
+
"logps/rejected": -284.0511779785156,
|
| 32 |
+
"loss": 0.3431,
|
| 33 |
+
"rewards/accuracies": 0.4027777910232544,
|
| 34 |
+
"rewards/chosen": -5.811791925225407e-05,
|
| 35 |
+
"rewards/margins": -0.00014306220691651106,
|
| 36 |
+
"rewards/rejected": 8.494428766425699e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": 0.07102914154529572,
|
| 43 |
+
"logits/rejected": 0.24960489571094513,
|
| 44 |
+
"logps/chosen": -328.02667236328125,
|
| 45 |
+
"logps/rejected": -273.9169006347656,
|
| 46 |
+
"loss": 0.3699,
|
| 47 |
+
"rewards/accuracies": 0.46875,
|
| 48 |
+
"rewards/chosen": -2.8161617592559196e-05,
|
| 49 |
+
"rewards/margins": -6.676381599390879e-05,
|
| 50 |
+
"rewards/rejected": 3.860218566842377e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": 0.10551998764276505,
|
| 57 |
+
"logits/rejected": 0.2433021515607834,
|
| 58 |
+
"logps/chosen": -354.22650146484375,
|
| 59 |
+
"logps/rejected": -284.6506042480469,
|
| 60 |
+
"loss": 0.3402,
|
| 61 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 62 |
+
"rewards/chosen": 0.00011991789506282657,
|
| 63 |
+
"rewards/margins": 2.2664942207484273e-06,
|
| 64 |
+
"rewards/rejected": 0.00011765138333430514,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": 0.12176469713449478,
|
| 71 |
+
"logits/rejected": 0.3288267254829407,
|
| 72 |
+
"logps/chosen": -371.8106384277344,
|
| 73 |
+
"logps/rejected": -293.2636413574219,
|
| 74 |
+
"loss": 0.3463,
|
| 75 |
+
"rewards/accuracies": 0.543749988079071,
|
| 76 |
+
"rewards/chosen": 0.0001882923679659143,
|
| 77 |
+
"rewards/margins": 0.00011801043001469225,
|
| 78 |
+
"rewards/rejected": 7.028193067526445e-05,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": 0.1286633312702179,
|
| 85 |
+
"logits/rejected": 0.13883765041828156,
|
| 86 |
+
"logps/chosen": -318.04205322265625,
|
| 87 |
+
"logps/rejected": -258.83013916015625,
|
| 88 |
+
"loss": 0.3691,
|
| 89 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 90 |
+
"rewards/chosen": 0.0002136583934770897,
|
| 91 |
+
"rewards/margins": 6.237901106942445e-05,
|
| 92 |
+
"rewards/rejected": 0.0001512793533038348,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": 0.11209549754858017,
|
| 99 |
+
"logits/rejected": 0.25248101353645325,
|
| 100 |
+
"logps/chosen": -362.73858642578125,
|
| 101 |
+
"logps/rejected": -315.79681396484375,
|
| 102 |
+
"loss": 0.3559,
|
| 103 |
+
"rewards/accuracies": 0.574999988079071,
|
| 104 |
+
"rewards/chosen": 0.00025600154185667634,
|
| 105 |
+
"rewards/margins": 0.00027534778928384185,
|
| 106 |
+
"rewards/rejected": -1.9346229237271473e-05,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": 0.11582938581705093,
|
| 113 |
+
"logits/rejected": 0.23768457770347595,
|
| 114 |
+
"logps/chosen": -365.4197998046875,
|
| 115 |
+
"logps/rejected": -307.07269287109375,
|
| 116 |
+
"loss": 0.3196,
|
| 117 |
+
"rewards/accuracies": 0.625,
|
| 118 |
+
"rewards/chosen": 0.0007645456935279071,
|
| 119 |
+
"rewards/margins": 0.000753869186155498,
|
| 120 |
+
"rewards/rejected": 1.0676437341317069e-05,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": 0.09230409562587738,
|
| 127 |
+
"logits/rejected": 0.23419447243213654,
|
| 128 |
+
"logps/chosen": -309.068603515625,
|
| 129 |
+
"logps/rejected": -264.81463623046875,
|
| 130 |
+
"loss": 0.3248,
|
| 131 |
+
"rewards/accuracies": 0.6875,
|
| 132 |
+
"rewards/chosen": 0.0010737198172137141,
|
| 133 |
+
"rewards/margins": 0.0011370908468961716,
|
| 134 |
+
"rewards/rejected": -6.337100057862699e-05,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": 0.10440310090780258,
|
| 141 |
+
"logits/rejected": 0.23364253342151642,
|
| 142 |
+
"logps/chosen": -349.4715881347656,
|
| 143 |
+
"logps/rejected": -306.0603332519531,
|
| 144 |
+
"loss": 0.3274,
|
| 145 |
+
"rewards/accuracies": 0.75,
|
| 146 |
+
"rewards/chosen": 0.0017630963120609522,
|
| 147 |
+
"rewards/margins": 0.0020842214580625296,
|
| 148 |
+
"rewards/rejected": -0.00032112523331306875,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": 0.11755403131246567,
|
| 155 |
+
"logits/rejected": 0.20094576478004456,
|
| 156 |
+
"logps/chosen": -346.9091796875,
|
| 157 |
+
"logps/rejected": -281.81396484375,
|
| 158 |
+
"loss": 0.3318,
|
| 159 |
+
"rewards/accuracies": 0.731249988079071,
|
| 160 |
+
"rewards/chosen": 0.002608776092529297,
|
| 161 |
+
"rewards/margins": 0.0030841627158224583,
|
| 162 |
+
"rewards/rejected": -0.00047538644867017865,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": 0.0515226311981678,
|
| 169 |
+
"logits/rejected": 0.22483673691749573,
|
| 170 |
+
"logps/chosen": -371.9663391113281,
|
| 171 |
+
"logps/rejected": -313.88739013671875,
|
| 172 |
+
"loss": 0.3365,
|
| 173 |
+
"rewards/accuracies": 0.737500011920929,
|
| 174 |
+
"rewards/chosen": 0.0030859257094562054,
|
| 175 |
+
"rewards/margins": 0.003779615741223097,
|
| 176 |
+
"rewards/rejected": -0.0006936899153515697,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": 0.07034258544445038,
|
| 183 |
+
"logits/rejected": 0.16451817750930786,
|
| 184 |
+
"logps/chosen": -297.6949768066406,
|
| 185 |
+
"logps/rejected": -275.7294616699219,
|
| 186 |
+
"loss": 0.3283,
|
| 187 |
+
"rewards/accuracies": 0.668749988079071,
|
| 188 |
+
"rewards/chosen": 0.0033937774132937193,
|
| 189 |
+
"rewards/margins": 0.004883460234850645,
|
| 190 |
+
"rewards/rejected": -0.0014896828215569258,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": 0.08784133940935135,
|
| 197 |
+
"logits/rejected": 0.23549315333366394,
|
| 198 |
+
"logps/chosen": -326.3392639160156,
|
| 199 |
+
"logps/rejected": -306.0093994140625,
|
| 200 |
+
"loss": 0.3241,
|
| 201 |
+
"rewards/accuracies": 0.800000011920929,
|
| 202 |
+
"rewards/chosen": 0.0068435766734182835,
|
| 203 |
+
"rewards/margins": 0.011338241398334503,
|
| 204 |
+
"rewards/rejected": -0.00449466472491622,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": 0.03845987841486931,
|
| 211 |
+
"logits/rejected": 0.23602671921253204,
|
| 212 |
+
"logps/chosen": -300.4671630859375,
|
| 213 |
+
"logps/rejected": -283.1863708496094,
|
| 214 |
+
"loss": 0.3267,
|
| 215 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 216 |
+
"rewards/chosen": 0.007321356330066919,
|
| 217 |
+
"rewards/margins": 0.014485524967312813,
|
| 218 |
+
"rewards/rejected": -0.007164168171584606,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": 0.14375978708267212,
|
| 225 |
+
"logits/rejected": 0.21812143921852112,
|
| 226 |
+
"logps/chosen": -331.6351318359375,
|
| 227 |
+
"logps/rejected": -298.9814453125,
|
| 228 |
+
"loss": 0.3286,
|
| 229 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 230 |
+
"rewards/chosen": 0.008922559209167957,
|
| 231 |
+
"rewards/margins": 0.023942312225699425,
|
| 232 |
+
"rewards/rejected": -0.015019752085208893,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": 0.1490752249956131,
|
| 239 |
+
"logits/rejected": 0.27425771951675415,
|
| 240 |
+
"logps/chosen": -365.9402160644531,
|
| 241 |
+
"logps/rejected": -357.152587890625,
|
| 242 |
+
"loss": 0.297,
|
| 243 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 244 |
+
"rewards/chosen": -0.005502852611243725,
|
| 245 |
+
"rewards/margins": 0.04779756814241409,
|
| 246 |
+
"rewards/rejected": -0.05330042913556099,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": 0.14248177409172058,
|
| 253 |
+
"logits/rejected": 0.24203705787658691,
|
| 254 |
+
"logps/chosen": -390.8301696777344,
|
| 255 |
+
"logps/rejected": -387.36309814453125,
|
| 256 |
+
"loss": 0.2796,
|
| 257 |
+
"rewards/accuracies": 0.737500011920929,
|
| 258 |
+
"rewards/chosen": -0.05510077625513077,
|
| 259 |
+
"rewards/margins": 0.06211589649319649,
|
| 260 |
+
"rewards/rejected": -0.11721666902303696,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": 0.10283932834863663,
|
| 267 |
+
"logits/rejected": 0.1948317587375641,
|
| 268 |
+
"logps/chosen": -523.36962890625,
|
| 269 |
+
"logps/rejected": -596.3675537109375,
|
| 270 |
+
"loss": 0.2893,
|
| 271 |
+
"rewards/accuracies": 0.731249988079071,
|
| 272 |
+
"rewards/chosen": -0.17172859609127045,
|
| 273 |
+
"rewards/margins": 0.10832329094409943,
|
| 274 |
+
"rewards/rejected": -0.2800518572330475,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": 0.13617555797100067,
|
| 281 |
+
"logits/rejected": 0.2513347566127777,
|
| 282 |
+
"logps/chosen": -615.2536010742188,
|
| 283 |
+
"logps/rejected": -724.0734252929688,
|
| 284 |
+
"loss": 0.2269,
|
| 285 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 286 |
+
"rewards/chosen": -0.24617168307304382,
|
| 287 |
+
"rewards/margins": 0.17905732989311218,
|
| 288 |
+
"rewards/rejected": -0.425229012966156,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": 0.11373931169509888,
|
| 295 |
+
"logits/rejected": 0.21447698771953583,
|
| 296 |
+
"logps/chosen": -669.2640380859375,
|
| 297 |
+
"logps/rejected": -688.9365844726562,
|
| 298 |
+
"loss": 0.3081,
|
| 299 |
+
"rewards/accuracies": 0.643750011920929,
|
| 300 |
+
"rewards/chosen": -0.27371013164520264,
|
| 301 |
+
"rewards/margins": 0.124347984790802,
|
| 302 |
+
"rewards/rejected": -0.3980581760406494,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": 0.17223823070526123,
|
| 309 |
+
"logits/rejected": 0.25994282960891724,
|
| 310 |
+
"logps/chosen": -524.0916137695312,
|
| 311 |
+
"logps/rejected": -528.10595703125,
|
| 312 |
+
"loss": 0.3009,
|
| 313 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 314 |
+
"rewards/chosen": -0.1624583899974823,
|
| 315 |
+
"rewards/margins": 0.07922794669866562,
|
| 316 |
+
"rewards/rejected": -0.2416863739490509,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": 0.13899263739585876,
|
| 323 |
+
"logits/rejected": 0.2618511915206909,
|
| 324 |
+
"logps/chosen": -438.03125,
|
| 325 |
+
"logps/rejected": -467.33013916015625,
|
| 326 |
+
"loss": 0.2569,
|
| 327 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 328 |
+
"rewards/chosen": -0.10613300651311874,
|
| 329 |
+
"rewards/margins": 0.091960109770298,
|
| 330 |
+
"rewards/rejected": -0.19809311628341675,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": 0.13999655842781067,
|
| 337 |
+
"logits/rejected": 0.26916781067848206,
|
| 338 |
+
"logps/chosen": -510.631103515625,
|
| 339 |
+
"logps/rejected": -519.5391845703125,
|
| 340 |
+
"loss": 0.2849,
|
| 341 |
+
"rewards/accuracies": 0.71875,
|
| 342 |
+
"rewards/chosen": -0.14092272520065308,
|
| 343 |
+
"rewards/margins": 0.08064567297697067,
|
| 344 |
+
"rewards/rejected": -0.22156842052936554,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": 0.15458917617797852,
|
| 351 |
+
"logits/rejected": 0.21037283539772034,
|
| 352 |
+
"logps/chosen": -470.0352478027344,
|
| 353 |
+
"logps/rejected": -535.9059448242188,
|
| 354 |
+
"loss": 0.236,
|
| 355 |
+
"rewards/accuracies": 0.731249988079071,
|
| 356 |
+
"rewards/chosen": -0.14089417457580566,
|
| 357 |
+
"rewards/margins": 0.12119980901479721,
|
| 358 |
+
"rewards/rejected": -0.2620939612388611,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": 0.17321957647800446,
|
| 365 |
+
"logits/rejected": 0.3360803425312042,
|
| 366 |
+
"logps/chosen": -578.07177734375,
|
| 367 |
+
"logps/rejected": -678.3271484375,
|
| 368 |
+
"loss": 0.25,
|
| 369 |
+
"rewards/accuracies": 0.699999988079071,
|
| 370 |
+
"rewards/chosen": -0.23716862499713898,
|
| 371 |
+
"rewards/margins": 0.15940351784229279,
|
| 372 |
+
"rewards/rejected": -0.39657214283943176,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": 0.16144976019859314,
|
| 379 |
+
"logits/rejected": 0.2567829489707947,
|
| 380 |
+
"logps/chosen": -631.9638061523438,
|
| 381 |
+
"logps/rejected": -725.3414916992188,
|
| 382 |
+
"loss": 0.2686,
|
| 383 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 384 |
+
"rewards/chosen": -0.2788200080394745,
|
| 385 |
+
"rewards/margins": 0.14786966145038605,
|
| 386 |
+
"rewards/rejected": -0.42668968439102173,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": 0.16097748279571533,
|
| 393 |
+
"logits/rejected": 0.22262544929981232,
|
| 394 |
+
"logps/chosen": -553.2183837890625,
|
| 395 |
+
"logps/rejected": -640.4689331054688,
|
| 396 |
+
"loss": 0.2476,
|
| 397 |
+
"rewards/accuracies": 0.699999988079071,
|
| 398 |
+
"rewards/chosen": -0.219456285238266,
|
| 399 |
+
"rewards/margins": 0.1420574188232422,
|
| 400 |
+
"rewards/rejected": -0.3615136742591858,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": 0.14573153853416443,
|
| 407 |
+
"logits/rejected": 0.23508696258068085,
|
| 408 |
+
"logps/chosen": -539.7109375,
|
| 409 |
+
"logps/rejected": -651.232421875,
|
| 410 |
+
"loss": 0.2535,
|
| 411 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 412 |
+
"rewards/chosen": -0.2373492270708084,
|
| 413 |
+
"rewards/margins": 0.14303575456142426,
|
| 414 |
+
"rewards/rejected": -0.38038498163223267,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": 0.1654827892780304,
|
| 421 |
+
"logits/rejected": 0.2800630033016205,
|
| 422 |
+
"logps/chosen": -603.4498901367188,
|
| 423 |
+
"logps/rejected": -686.7757568359375,
|
| 424 |
+
"loss": 0.2537,
|
| 425 |
+
"rewards/accuracies": 0.699999988079071,
|
| 426 |
+
"rewards/chosen": -0.2507944703102112,
|
| 427 |
+
"rewards/margins": 0.16016040742397308,
|
| 428 |
+
"rewards/rejected": -0.41095486283302307,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": 0.11868251860141754,
|
| 435 |
+
"logits/rejected": 0.29606184363365173,
|
| 436 |
+
"logps/chosen": -587.1047973632812,
|
| 437 |
+
"logps/rejected": -650.8994750976562,
|
| 438 |
+
"loss": 0.2541,
|
| 439 |
+
"rewards/accuracies": 0.6875,
|
| 440 |
+
"rewards/chosen": -0.23289060592651367,
|
| 441 |
+
"rewards/margins": 0.13534070551395416,
|
| 442 |
+
"rewards/rejected": -0.36823132634162903,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": 0.11233693361282349,
|
| 449 |
+
"logits/rejected": 0.2625276446342468,
|
| 450 |
+
"logps/chosen": -580.7044677734375,
|
| 451 |
+
"logps/rejected": -654.3244018554688,
|
| 452 |
+
"loss": 0.2557,
|
| 453 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 454 |
+
"rewards/chosen": -0.2328997552394867,
|
| 455 |
+
"rewards/margins": 0.13923317193984985,
|
| 456 |
+
"rewards/rejected": -0.37213292717933655,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": 0.14452582597732544,
|
| 463 |
+
"logits/rejected": 0.2437099665403366,
|
| 464 |
+
"logps/chosen": -606.4398803710938,
|
| 465 |
+
"logps/rejected": -706.3465576171875,
|
| 466 |
+
"loss": 0.2552,
|
| 467 |
+
"rewards/accuracies": 0.71875,
|
| 468 |
+
"rewards/chosen": -0.24929067492485046,
|
| 469 |
+
"rewards/margins": 0.1445845663547516,
|
| 470 |
+
"rewards/rejected": -0.39387524127960205,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": 0.09590379893779755,
|
| 477 |
+
"logits/rejected": 0.15467569231987,
|
| 478 |
+
"logps/chosen": -597.2806396484375,
|
| 479 |
+
"logps/rejected": -679.9869384765625,
|
| 480 |
+
"loss": 0.2518,
|
| 481 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 482 |
+
"rewards/chosen": -0.23923709988594055,
|
| 483 |
+
"rewards/margins": 0.15891839563846588,
|
| 484 |
+
"rewards/rejected": -0.3981555104255676,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": 0.11927614361047745,
|
| 491 |
+
"logits/rejected": 0.1604013293981552,
|
| 492 |
+
"logps/chosen": -640.5142822265625,
|
| 493 |
+
"logps/rejected": -841.5134887695312,
|
| 494 |
+
"loss": 0.2283,
|
| 495 |
+
"rewards/accuracies": 0.731249988079071,
|
| 496 |
+
"rewards/chosen": -0.3347136974334717,
|
| 497 |
+
"rewards/margins": 0.2090570628643036,
|
| 498 |
+
"rewards/rejected": -0.5437707901000977,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": 0.12204344570636749,
|
| 505 |
+
"logits/rejected": 0.2500421106815338,
|
| 506 |
+
"logps/chosen": -715.3956298828125,
|
| 507 |
+
"logps/rejected": -785.560791015625,
|
| 508 |
+
"loss": 0.2628,
|
| 509 |
+
"rewards/accuracies": 0.706250011920929,
|
| 510 |
+
"rewards/chosen": -0.34101438522338867,
|
| 511 |
+
"rewards/margins": 0.1506863236427307,
|
| 512 |
+
"rewards/rejected": -0.4917007386684418,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": 0.15500317513942719,
|
| 519 |
+
"logits/rejected": 0.29695573449134827,
|
| 520 |
+
"logps/chosen": -633.2789306640625,
|
| 521 |
+
"logps/rejected": -729.1109619140625,
|
| 522 |
+
"loss": 0.2473,
|
| 523 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 524 |
+
"rewards/chosen": -0.2560732960700989,
|
| 525 |
+
"rewards/margins": 0.17503255605697632,
|
| 526 |
+
"rewards/rejected": -0.4311058521270752,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": 0.0852101594209671,
|
| 533 |
+
"logits/rejected": 0.1848641186952591,
|
| 534 |
+
"logps/chosen": -561.0950927734375,
|
| 535 |
+
"logps/rejected": -703.2201538085938,
|
| 536 |
+
"loss": 0.2509,
|
| 537 |
+
"rewards/accuracies": 0.71875,
|
| 538 |
+
"rewards/chosen": -0.25699612498283386,
|
| 539 |
+
"rewards/margins": 0.1455649882555008,
|
| 540 |
+
"rewards/rejected": -0.40256109833717346,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": 0.12055132538080215,
|
| 547 |
+
"logits/rejected": 0.22479526698589325,
|
| 548 |
+
"logps/chosen": -564.7427978515625,
|
| 549 |
+
"logps/rejected": -672.8660888671875,
|
| 550 |
+
"loss": 0.1755,
|
| 551 |
+
"rewards/accuracies": 0.75,
|
| 552 |
+
"rewards/chosen": -0.2189377099275589,
|
| 553 |
+
"rewards/margins": 0.18233411014080048,
|
| 554 |
+
"rewards/rejected": -0.4012718200683594,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": 0.07654919475317001,
|
| 561 |
+
"logits/rejected": 0.18854263424873352,
|
| 562 |
+
"logps/chosen": -660.2512817382812,
|
| 563 |
+
"logps/rejected": -773.058837890625,
|
| 564 |
+
"loss": 0.2193,
|
| 565 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 566 |
+
"rewards/chosen": -0.2836855351924896,
|
| 567 |
+
"rewards/margins": 0.19571776688098907,
|
| 568 |
+
"rewards/rejected": -0.4794033169746399,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": 0.09550791233778,
|
| 575 |
+
"logits/rejected": 0.19389700889587402,
|
| 576 |
+
"logps/chosen": -669.1429443359375,
|
| 577 |
+
"logps/rejected": -838.7755126953125,
|
| 578 |
+
"loss": 0.2165,
|
| 579 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 580 |
+
"rewards/chosen": -0.31033799052238464,
|
| 581 |
+
"rewards/margins": 0.2328120917081833,
|
| 582 |
+
"rewards/rejected": -0.5431500673294067,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": 0.001080992049537599,
|
| 589 |
+
"logits/rejected": 0.14185592532157898,
|
| 590 |
+
"logps/chosen": -594.972900390625,
|
| 591 |
+
"logps/rejected": -736.0914306640625,
|
| 592 |
+
"loss": 0.2722,
|
| 593 |
+
"rewards/accuracies": 0.706250011920929,
|
| 594 |
+
"rewards/chosen": -0.2792796492576599,
|
| 595 |
+
"rewards/margins": 0.17098276317119598,
|
| 596 |
+
"rewards/rejected": -0.4502624571323395,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": 0.08192798495292664,
|
| 603 |
+
"logits/rejected": 0.138724684715271,
|
| 604 |
+
"logps/chosen": -556.79345703125,
|
| 605 |
+
"logps/rejected": -625.5200805664062,
|
| 606 |
+
"loss": 0.2453,
|
| 607 |
+
"rewards/accuracies": 0.643750011920929,
|
| 608 |
+
"rewards/chosen": -0.21958652138710022,
|
| 609 |
+
"rewards/margins": 0.12120404094457626,
|
| 610 |
+
"rewards/rejected": -0.3407905697822571,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": 0.08842509239912033,
|
| 617 |
+
"logits/rejected": 0.12143252789974213,
|
| 618 |
+
"logps/chosen": -575.1492919921875,
|
| 619 |
+
"logps/rejected": -664.153564453125,
|
| 620 |
+
"loss": 0.2486,
|
| 621 |
+
"rewards/accuracies": 0.6875,
|
| 622 |
+
"rewards/chosen": -0.24815413355827332,
|
| 623 |
+
"rewards/margins": 0.13290396332740784,
|
| 624 |
+
"rewards/rejected": -0.38105809688568115,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": 0.0016645323485136032,
|
| 631 |
+
"logits/rejected": 0.1351255476474762,
|
| 632 |
+
"logps/chosen": -573.5245971679688,
|
| 633 |
+
"logps/rejected": -703.4102783203125,
|
| 634 |
+
"loss": 0.2377,
|
| 635 |
+
"rewards/accuracies": 0.699999988079071,
|
| 636 |
+
"rewards/chosen": -0.24630823731422424,
|
| 637 |
+
"rewards/margins": 0.16149748861789703,
|
| 638 |
+
"rewards/rejected": -0.40780574083328247,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": 0.04974130541086197,
|
| 645 |
+
"logits/rejected": 0.10218667984008789,
|
| 646 |
+
"logps/chosen": -575.5032958984375,
|
| 647 |
+
"logps/rejected": -679.7342529296875,
|
| 648 |
+
"loss": 0.2552,
|
| 649 |
+
"rewards/accuracies": 0.668749988079071,
|
| 650 |
+
"rewards/chosen": -0.2367144078016281,
|
| 651 |
+
"rewards/margins": 0.15034009516239166,
|
| 652 |
+
"rewards/rejected": -0.38705453276634216,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": 0.03959808871150017,
|
| 659 |
+
"logits/rejected": 0.16889765858650208,
|
| 660 |
+
"logps/chosen": -601.1052856445312,
|
| 661 |
+
"logps/rejected": -735.5942993164062,
|
| 662 |
+
"loss": 0.2556,
|
| 663 |
+
"rewards/accuracies": 0.706250011920929,
|
| 664 |
+
"rewards/chosen": -0.2658396363258362,
|
| 665 |
+
"rewards/margins": 0.17807722091674805,
|
| 666 |
+
"rewards/rejected": -0.44391685724258423,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": 0.060259442776441574,
|
| 673 |
+
"logits/rejected": 0.17572340369224548,
|
| 674 |
+
"logps/chosen": -625.7338256835938,
|
| 675 |
+
"logps/rejected": -786.9043579101562,
|
| 676 |
+
"loss": 0.2364,
|
| 677 |
+
"rewards/accuracies": 0.737500011920929,
|
| 678 |
+
"rewards/chosen": -0.29917049407958984,
|
| 679 |
+
"rewards/margins": 0.1899183690547943,
|
| 680 |
+
"rewards/rejected": -0.48908883333206177,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": 0.05524193122982979,
|
| 687 |
+
"logits/rejected": 0.1667497456073761,
|
| 688 |
+
"logps/chosen": -640.2739868164062,
|
| 689 |
+
"logps/rejected": -716.3453369140625,
|
| 690 |
+
"loss": 0.2418,
|
| 691 |
+
"rewards/accuracies": 0.706250011920929,
|
| 692 |
+
"rewards/chosen": -0.28584688901901245,
|
| 693 |
+
"rewards/margins": 0.1426083743572235,
|
| 694 |
+
"rewards/rejected": -0.42845526337623596,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": 0.05645556375384331,
|
| 701 |
+
"logits/rejected": 0.1303979605436325,
|
| 702 |
+
"logps/chosen": -594.4942016601562,
|
| 703 |
+
"logps/rejected": -682.8673095703125,
|
| 704 |
+
"loss": 0.2491,
|
| 705 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 706 |
+
"rewards/chosen": -0.25856301188468933,
|
| 707 |
+
"rewards/margins": 0.15196993947029114,
|
| 708 |
+
"rewards/rejected": -0.41053295135498047,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": 0.07052268087863922,
|
| 715 |
+
"logits/rejected": 0.13902485370635986,
|
| 716 |
+
"logps/chosen": -585.3961181640625,
|
| 717 |
+
"logps/rejected": -691.311767578125,
|
| 718 |
+
"loss": 0.2537,
|
| 719 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 720 |
+
"rewards/chosen": -0.2726908326148987,
|
| 721 |
+
"rewards/margins": 0.1488717794418335,
|
| 722 |
+
"rewards/rejected": -0.4215625822544098,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": 0.05198805406689644,
|
| 729 |
+
"logits/rejected": 0.10118089616298676,
|
| 730 |
+
"logps/chosen": -598.3322143554688,
|
| 731 |
+
"logps/rejected": -739.3489990234375,
|
| 732 |
+
"loss": 0.2355,
|
| 733 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 734 |
+
"rewards/chosen": -0.25981515645980835,
|
| 735 |
+
"rewards/margins": 0.2083590030670166,
|
| 736 |
+
"rewards/rejected": -0.46817412972450256,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": 0.09554968029260635,
|
| 743 |
+
"logits/rejected": 0.22383460402488708,
|
| 744 |
+
"logps/chosen": -621.1278076171875,
|
| 745 |
+
"logps/rejected": -703.5054931640625,
|
| 746 |
+
"loss": 0.2346,
|
| 747 |
+
"rewards/accuracies": 0.737500011920929,
|
| 748 |
+
"rewards/chosen": -0.2537866532802582,
|
| 749 |
+
"rewards/margins": 0.1655985414981842,
|
| 750 |
+
"rewards/rejected": -0.4193851947784424,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": 0.07675488293170929,
|
| 757 |
+
"logits/rejected": 0.22268608212471008,
|
| 758 |
+
"logps/chosen": -649.4010009765625,
|
| 759 |
+
"logps/rejected": -696.96337890625,
|
| 760 |
+
"loss": 0.2337,
|
| 761 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 762 |
+
"rewards/chosen": -0.24650602042675018,
|
| 763 |
+
"rewards/margins": 0.1643296480178833,
|
| 764 |
+
"rewards/rejected": -0.4108356535434723,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": -0.009524239227175713,
|
| 771 |
+
"logits/rejected": 0.13664120435714722,
|
| 772 |
+
"logps/chosen": -608.6438598632812,
|
| 773 |
+
"logps/rejected": -744.18701171875,
|
| 774 |
+
"loss": 0.2511,
|
| 775 |
+
"rewards/accuracies": 0.762499988079071,
|
| 776 |
+
"rewards/chosen": -0.2557665705680847,
|
| 777 |
+
"rewards/margins": 0.1905471682548523,
|
| 778 |
+
"rewards/rejected": -0.4463137090206146,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": 0.04823983460664749,
|
| 785 |
+
"logits/rejected": 0.21495167911052704,
|
| 786 |
+
"logps/chosen": -668.1390991210938,
|
| 787 |
+
"logps/rejected": -764.8587036132812,
|
| 788 |
+
"loss": 0.2063,
|
| 789 |
+
"rewards/accuracies": 0.793749988079071,
|
| 790 |
+
"rewards/chosen": -0.2886661887168884,
|
| 791 |
+
"rewards/margins": 0.20503409206867218,
|
| 792 |
+
"rewards/rejected": -0.4937002658843994,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": 0.14659680426120758,
|
| 799 |
+
"logits/rejected": 0.19975139200687408,
|
| 800 |
+
"logps/chosen": -691.0910034179688,
|
| 801 |
+
"logps/rejected": -818.7584228515625,
|
| 802 |
+
"loss": 0.216,
|
| 803 |
+
"rewards/accuracies": 0.768750011920929,
|
| 804 |
+
"rewards/chosen": -0.33451852202415466,
|
| 805 |
+
"rewards/margins": 0.21299397945404053,
|
| 806 |
+
"rewards/rejected": -0.5475125312805176,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": 0.10968673229217529,
|
| 813 |
+
"logits/rejected": 0.2234468162059784,
|
| 814 |
+
"logps/chosen": -732.4443359375,
|
| 815 |
+
"logps/rejected": -899.6062622070312,
|
| 816 |
+
"loss": 0.2183,
|
| 817 |
+
"rewards/accuracies": 0.78125,
|
| 818 |
+
"rewards/chosen": -0.33378008008003235,
|
| 819 |
+
"rewards/margins": 0.2530228793621063,
|
| 820 |
+
"rewards/rejected": -0.5868029594421387,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": 0.10406269133090973,
|
| 827 |
+
"logits/rejected": 0.15065929293632507,
|
| 828 |
+
"logps/chosen": -659.9013671875,
|
| 829 |
+
"logps/rejected": -766.6561279296875,
|
| 830 |
+
"loss": 0.2346,
|
| 831 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 832 |
+
"rewards/chosen": -0.29572516679763794,
|
| 833 |
+
"rewards/margins": 0.1765248328447342,
|
| 834 |
+
"rewards/rejected": -0.47224998474121094,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": 0.0664634108543396,
|
| 841 |
+
"logits/rejected": 0.16555871069431305,
|
| 842 |
+
"logps/chosen": -600.4996948242188,
|
| 843 |
+
"logps/rejected": -713.78466796875,
|
| 844 |
+
"loss": 0.2461,
|
| 845 |
+
"rewards/accuracies": 0.706250011920929,
|
| 846 |
+
"rewards/chosen": -0.2576759457588196,
|
| 847 |
+
"rewards/margins": 0.1549091637134552,
|
| 848 |
+
"rewards/rejected": -0.4125851094722748,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": 0.16024425625801086,
|
| 855 |
+
"logits/rejected": 0.22183863818645477,
|
| 856 |
+
"logps/chosen": -619.4130859375,
|
| 857 |
+
"logps/rejected": -696.956787109375,
|
| 858 |
+
"loss": 0.2457,
|
| 859 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 860 |
+
"rewards/chosen": -0.24661366641521454,
|
| 861 |
+
"rewards/margins": 0.1785852015018463,
|
| 862 |
+
"rewards/rejected": -0.42519888281822205,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": 0.07459579408168793,
|
| 869 |
+
"logits/rejected": 0.20276884734630585,
|
| 870 |
+
"logps/chosen": -657.4212646484375,
|
| 871 |
+
"logps/rejected": -731.3056640625,
|
| 872 |
+
"loss": 0.231,
|
| 873 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 874 |
+
"rewards/chosen": -0.2757970690727234,
|
| 875 |
+
"rewards/margins": 0.1686132848262787,
|
| 876 |
+
"rewards/rejected": -0.44441038370132446,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": 0.056164585053920746,
|
| 883 |
+
"logits/rejected": 0.22885584831237793,
|
| 884 |
+
"logps/chosen": -652.3689575195312,
|
| 885 |
+
"logps/rejected": -749.9366455078125,
|
| 886 |
+
"loss": 0.227,
|
| 887 |
+
"rewards/accuracies": 0.737500011920929,
|
| 888 |
+
"rewards/chosen": -0.29479923844337463,
|
| 889 |
+
"rewards/margins": 0.16815118491649628,
|
| 890 |
+
"rewards/rejected": -0.4629504680633545,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": 0.10070328414440155,
|
| 897 |
+
"logits/rejected": 0.16475458443164825,
|
| 898 |
+
"logps/chosen": -708.42529296875,
|
| 899 |
+
"logps/rejected": -811.713134765625,
|
| 900 |
+
"loss": 0.2415,
|
| 901 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 902 |
+
"rewards/chosen": -0.33783578872680664,
|
| 903 |
+
"rewards/margins": 0.18223688006401062,
|
| 904 |
+
"rewards/rejected": -0.5200726389884949,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": 0.10311365127563477,
|
| 911 |
+
"logits/rejected": 0.15643465518951416,
|
| 912 |
+
"logps/chosen": -583.4866333007812,
|
| 913 |
+
"logps/rejected": -729.7852783203125,
|
| 914 |
+
"loss": 0.2016,
|
| 915 |
+
"rewards/accuracies": 0.75,
|
| 916 |
+
"rewards/chosen": -0.2622414231300354,
|
| 917 |
+
"rewards/margins": 0.19530150294303894,
|
| 918 |
+
"rewards/rejected": -0.45754295587539673,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": 0.10025729984045029,
|
| 925 |
+
"logits/rejected": 0.2146105021238327,
|
| 926 |
+
"logps/chosen": -681.4263916015625,
|
| 927 |
+
"logps/rejected": -823.4031372070312,
|
| 928 |
+
"loss": 0.2163,
|
| 929 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 930 |
+
"rewards/chosen": -0.3132783770561218,
|
| 931 |
+
"rewards/margins": 0.21751663088798523,
|
| 932 |
+
"rewards/rejected": -0.5307949781417847,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": 0.10832244157791138,
|
| 939 |
+
"logits/rejected": 0.20945067703723907,
|
| 940 |
+
"logps/chosen": -660.5101318359375,
|
| 941 |
+
"logps/rejected": -768.7022705078125,
|
| 942 |
+
"loss": 0.2215,
|
| 943 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 944 |
+
"rewards/chosen": -0.30939123034477234,
|
| 945 |
+
"rewards/margins": 0.18488983809947968,
|
| 946 |
+
"rewards/rejected": -0.49428099393844604,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": 0.08686210215091705,
|
| 953 |
+
"logits/rejected": 0.2045850306749344,
|
| 954 |
+
"logps/chosen": -723.7673950195312,
|
| 955 |
+
"logps/rejected": -883.3922119140625,
|
| 956 |
+
"loss": 0.2512,
|
| 957 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 958 |
+
"rewards/chosen": -0.38144949078559875,
|
| 959 |
+
"rewards/margins": 0.195582315325737,
|
| 960 |
+
"rewards/rejected": -0.5770317912101746,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": 0.09274314343929291,
|
| 967 |
+
"logits/rejected": 0.1920190155506134,
|
| 968 |
+
"logps/chosen": -618.1563720703125,
|
| 969 |
+
"logps/rejected": -740.8644409179688,
|
| 970 |
+
"loss": 0.2629,
|
| 971 |
+
"rewards/accuracies": 0.668749988079071,
|
| 972 |
+
"rewards/chosen": -0.3001014292240143,
|
| 973 |
+
"rewards/margins": 0.1581810563802719,
|
| 974 |
+
"rewards/rejected": -0.458282470703125,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": 0.021902620792388916,
|
| 981 |
+
"logits/rejected": 0.11925847828388214,
|
| 982 |
+
"logps/chosen": -595.6156005859375,
|
| 983 |
+
"logps/rejected": -711.0296630859375,
|
| 984 |
+
"loss": 0.2626,
|
| 985 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 986 |
+
"rewards/chosen": -0.2705914080142975,
|
| 987 |
+
"rewards/margins": 0.16306385397911072,
|
| 988 |
+
"rewards/rejected": -0.4336552619934082,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": 0.05186104774475098,
|
| 995 |
+
"logits/rejected": 0.20855280756950378,
|
| 996 |
+
"logps/chosen": -584.5855102539062,
|
| 997 |
+
"logps/rejected": -713.7994384765625,
|
| 998 |
+
"loss": 0.1958,
|
| 999 |
+
"rewards/accuracies": 0.71875,
|
| 1000 |
+
"rewards/chosen": -0.25383633375167847,
|
| 1001 |
+
"rewards/margins": 0.1767672598361969,
|
| 1002 |
+
"rewards/rejected": -0.43060359358787537,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": 0.022304801270365715,
|
| 1009 |
+
"logits/rejected": 0.14363619685173035,
|
| 1010 |
+
"logps/chosen": -643.5025634765625,
|
| 1011 |
+
"logps/rejected": -748.3091430664062,
|
| 1012 |
+
"loss": 0.2237,
|
| 1013 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1014 |
+
"rewards/chosen": -0.29282766580581665,
|
| 1015 |
+
"rewards/margins": 0.17381563782691956,
|
| 1016 |
+
"rewards/rejected": -0.4666433334350586,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": 0.09528463333845139,
|
| 1023 |
+
"logits/rejected": 0.18656165897846222,
|
| 1024 |
+
"logps/chosen": -692.3035888671875,
|
| 1025 |
+
"logps/rejected": -819.2098388671875,
|
| 1026 |
+
"loss": 0.2097,
|
| 1027 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1028 |
+
"rewards/chosen": -0.31982243061065674,
|
| 1029 |
+
"rewards/margins": 0.20729240775108337,
|
| 1030 |
+
"rewards/rejected": -0.5271148085594177,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": 0.04973004013299942,
|
| 1037 |
+
"logits/rejected": 0.19504304230213165,
|
| 1038 |
+
"logps/chosen": -688.0816650390625,
|
| 1039 |
+
"logps/rejected": -852.9588012695312,
|
| 1040 |
+
"loss": 0.2432,
|
| 1041 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1042 |
+
"rewards/chosen": -0.36149436235427856,
|
| 1043 |
+
"rewards/margins": 0.1907968968153,
|
| 1044 |
+
"rewards/rejected": -0.5522913336753845,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": 0.09976281225681305,
|
| 1051 |
+
"logits/rejected": 0.19117242097854614,
|
| 1052 |
+
"logps/chosen": -680.7174072265625,
|
| 1053 |
+
"logps/rejected": -797.1549072265625,
|
| 1054 |
+
"loss": 0.2341,
|
| 1055 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1056 |
+
"rewards/chosen": -0.3415672183036804,
|
| 1057 |
+
"rewards/margins": 0.1845674216747284,
|
| 1058 |
+
"rewards/rejected": -0.5261346101760864,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": 0.07142799347639084,
|
| 1065 |
+
"logits/rejected": 0.22169947624206543,
|
| 1066 |
+
"logps/chosen": -626.5697021484375,
|
| 1067 |
+
"logps/rejected": -787.6502075195312,
|
| 1068 |
+
"loss": 0.2383,
|
| 1069 |
+
"rewards/accuracies": 0.71875,
|
| 1070 |
+
"rewards/chosen": -0.2981518507003784,
|
| 1071 |
+
"rewards/margins": 0.206342414021492,
|
| 1072 |
+
"rewards/rejected": -0.504494309425354,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": 0.1079743355512619,
|
| 1079 |
+
"logits/rejected": 0.13973113894462585,
|
| 1080 |
+
"logps/chosen": -665.4769287109375,
|
| 1081 |
+
"logps/rejected": -744.9660034179688,
|
| 1082 |
+
"loss": 0.2612,
|
| 1083 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1084 |
+
"rewards/chosen": -0.3199656009674072,
|
| 1085 |
+
"rewards/margins": 0.16452810168266296,
|
| 1086 |
+
"rewards/rejected": -0.4844936728477478,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": 0.075187087059021,
|
| 1093 |
+
"logits/rejected": 0.15009218454360962,
|
| 1094 |
+
"logps/chosen": -644.90478515625,
|
| 1095 |
+
"logps/rejected": -790.0805053710938,
|
| 1096 |
+
"loss": 0.2429,
|
| 1097 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1098 |
+
"rewards/chosen": -0.30303993821144104,
|
| 1099 |
+
"rewards/margins": 0.19713596999645233,
|
| 1100 |
+
"rewards/rejected": -0.500175952911377,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": 0.06037820130586624,
|
| 1107 |
+
"logits/rejected": 0.12935443222522736,
|
| 1108 |
+
"logps/chosen": -659.0757446289062,
|
| 1109 |
+
"logps/rejected": -834.96533203125,
|
| 1110 |
+
"loss": 0.207,
|
| 1111 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1112 |
+
"rewards/chosen": -0.31061092019081116,
|
| 1113 |
+
"rewards/margins": 0.22491443157196045,
|
| 1114 |
+
"rewards/rejected": -0.535525381565094,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": 0.062171898782253265,
|
| 1121 |
+
"logits/rejected": 0.20288972556591034,
|
| 1122 |
+
"logps/chosen": -650.5526733398438,
|
| 1123 |
+
"logps/rejected": -812.0040893554688,
|
| 1124 |
+
"loss": 0.2295,
|
| 1125 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1126 |
+
"rewards/chosen": -0.3222615122795105,
|
| 1127 |
+
"rewards/margins": 0.2239852249622345,
|
| 1128 |
+
"rewards/rejected": -0.5462467670440674,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": 0.07936866581439972,
|
| 1135 |
+
"logits/rejected": 0.23025266826152802,
|
| 1136 |
+
"logps/chosen": -730.1929321289062,
|
| 1137 |
+
"logps/rejected": -875.7835693359375,
|
| 1138 |
+
"loss": 0.1995,
|
| 1139 |
+
"rewards/accuracies": 0.78125,
|
| 1140 |
+
"rewards/chosen": -0.3494511842727661,
|
| 1141 |
+
"rewards/margins": 0.2297430783510208,
|
| 1142 |
+
"rewards/rejected": -0.5791942477226257,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": 0.11655671894550323,
|
| 1149 |
+
"logits/rejected": 0.1666901409626007,
|
| 1150 |
+
"logps/chosen": -654.1530151367188,
|
| 1151 |
+
"logps/rejected": -815.29296875,
|
| 1152 |
+
"loss": 0.2193,
|
| 1153 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1154 |
+
"rewards/chosen": -0.30700844526290894,
|
| 1155 |
+
"rewards/margins": 0.21489982306957245,
|
| 1156 |
+
"rewards/rejected": -0.5219083428382874,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": 0.11936108767986298,
|
| 1163 |
+
"logits/rejected": 0.18859058618545532,
|
| 1164 |
+
"logps/chosen": -630.1988525390625,
|
| 1165 |
+
"logps/rejected": -762.0612182617188,
|
| 1166 |
+
"loss": 0.2079,
|
| 1167 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1168 |
+
"rewards/chosen": -0.25710731744766235,
|
| 1169 |
+
"rewards/margins": 0.2074425220489502,
|
| 1170 |
+
"rewards/rejected": -0.46454983949661255,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": 0.05629768967628479,
|
| 1177 |
+
"logits/rejected": 0.1666196882724762,
|
| 1178 |
+
"logps/chosen": -649.73046875,
|
| 1179 |
+
"logps/rejected": -818.6950073242188,
|
| 1180 |
+
"loss": 0.1792,
|
| 1181 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1182 |
+
"rewards/chosen": -0.2980211675167084,
|
| 1183 |
+
"rewards/margins": 0.23819315433502197,
|
| 1184 |
+
"rewards/rejected": -0.5362143516540527,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": 0.04574333503842354,
|
| 1191 |
+
"logits/rejected": 0.17197957634925842,
|
| 1192 |
+
"logps/chosen": -702.0049438476562,
|
| 1193 |
+
"logps/rejected": -867.20947265625,
|
| 1194 |
+
"loss": 0.2038,
|
| 1195 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1196 |
+
"rewards/chosen": -0.35734453797340393,
|
| 1197 |
+
"rewards/margins": 0.22116133570671082,
|
| 1198 |
+
"rewards/rejected": -0.5785058736801147,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": 0.055036939680576324,
|
| 1205 |
+
"logits/rejected": 0.18666990101337433,
|
| 1206 |
+
"logps/chosen": -772.3389282226562,
|
| 1207 |
+
"logps/rejected": -934.3049926757812,
|
| 1208 |
+
"loss": 0.2081,
|
| 1209 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1210 |
+
"rewards/chosen": -0.3967970013618469,
|
| 1211 |
+
"rewards/margins": 0.2379632443189621,
|
| 1212 |
+
"rewards/rejected": -0.6347602605819702,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": 0.06958106905221939,
|
| 1219 |
+
"logits/rejected": 0.1442635953426361,
|
| 1220 |
+
"logps/chosen": -669.5227661132812,
|
| 1221 |
+
"logps/rejected": -853.2138671875,
|
| 1222 |
+
"loss": 0.207,
|
| 1223 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1224 |
+
"rewards/chosen": -0.3451857566833496,
|
| 1225 |
+
"rewards/margins": 0.2383837252855301,
|
| 1226 |
+
"rewards/rejected": -0.5835694074630737,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": 0.0513598695397377,
|
| 1233 |
+
"logits/rejected": 0.13928762078285217,
|
| 1234 |
+
"logps/chosen": -653.1226806640625,
|
| 1235 |
+
"logps/rejected": -795.4114379882812,
|
| 1236 |
+
"loss": 0.2438,
|
| 1237 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1238 |
+
"rewards/chosen": -0.327537477016449,
|
| 1239 |
+
"rewards/margins": 0.18883965909481049,
|
| 1240 |
+
"rewards/rejected": -0.5163770914077759,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": 0.07376402616500854,
|
| 1247 |
+
"logits/rejected": 0.17226745188236237,
|
| 1248 |
+
"logps/chosen": -704.4319458007812,
|
| 1249 |
+
"logps/rejected": -898.2445068359375,
|
| 1250 |
+
"loss": 0.1766,
|
| 1251 |
+
"rewards/accuracies": 0.84375,
|
| 1252 |
+
"rewards/chosen": -0.33583196997642517,
|
| 1253 |
+
"rewards/margins": 0.25600650906562805,
|
| 1254 |
+
"rewards/rejected": -0.5918384790420532,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": 0.04906494915485382,
|
| 1261 |
+
"logits/rejected": 0.1545862853527069,
|
| 1262 |
+
"logps/chosen": -670.8369140625,
|
| 1263 |
+
"logps/rejected": -803.107421875,
|
| 1264 |
+
"loss": 0.2318,
|
| 1265 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1266 |
+
"rewards/chosen": -0.3352956175804138,
|
| 1267 |
+
"rewards/margins": 0.2003110647201538,
|
| 1268 |
+
"rewards/rejected": -0.5356066823005676,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": 0.12640194594860077,
|
| 1275 |
+
"logits/rejected": 0.219802588224411,
|
| 1276 |
+
"logps/chosen": -742.6751098632812,
|
| 1277 |
+
"logps/rejected": -895.0465698242188,
|
| 1278 |
+
"loss": 0.1921,
|
| 1279 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1280 |
+
"rewards/chosen": -0.3457973599433899,
|
| 1281 |
+
"rewards/margins": 0.24558237195014954,
|
| 1282 |
+
"rewards/rejected": -0.591379702091217,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": -0.01623944379389286,
|
| 1289 |
+
"logits/rejected": 0.16946300864219666,
|
| 1290 |
+
"logps/chosen": -649.9053955078125,
|
| 1291 |
+
"logps/rejected": -832.1677856445312,
|
| 1292 |
+
"loss": 0.1958,
|
| 1293 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1294 |
+
"rewards/chosen": -0.3138830065727234,
|
| 1295 |
+
"rewards/margins": 0.23707744479179382,
|
| 1296 |
+
"rewards/rejected": -0.5509604215621948,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": 0.05111056566238403,
|
| 1303 |
+
"logits/rejected": 0.14114698767662048,
|
| 1304 |
+
"logps/chosen": -662.3326416015625,
|
| 1305 |
+
"logps/rejected": -784.4324951171875,
|
| 1306 |
+
"loss": 0.2388,
|
| 1307 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1308 |
+
"rewards/chosen": -0.32007449865341187,
|
| 1309 |
+
"rewards/margins": 0.1715754121541977,
|
| 1310 |
+
"rewards/rejected": -0.49164995551109314,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": -0.006915999110788107,
|
| 1317 |
+
"logits/rejected": 0.11657528579235077,
|
| 1318 |
+
"logps/chosen": -666.0967407226562,
|
| 1319 |
+
"logps/rejected": -806.9496459960938,
|
| 1320 |
+
"loss": 0.2169,
|
| 1321 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1322 |
+
"rewards/chosen": -0.30281534790992737,
|
| 1323 |
+
"rewards/margins": 0.22429080307483673,
|
| 1324 |
+
"rewards/rejected": -0.5271061062812805,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": 0.056006837636232376,
|
| 1331 |
+
"logits/rejected": 0.17199097573757172,
|
| 1332 |
+
"logps/chosen": -652.8565673828125,
|
| 1333 |
+
"logps/rejected": -816.8966674804688,
|
| 1334 |
+
"loss": 0.2207,
|
| 1335 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1336 |
+
"rewards/chosen": -0.27928978204727173,
|
| 1337 |
+
"rewards/margins": 0.23044073581695557,
|
| 1338 |
+
"rewards/rejected": -0.5097305178642273,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": 0.06072944402694702,
|
| 1345 |
+
"logits/rejected": 0.13912425935268402,
|
| 1346 |
+
"logps/chosen": -622.7828369140625,
|
| 1347 |
+
"logps/rejected": -809.6715698242188,
|
| 1348 |
+
"loss": 0.2059,
|
| 1349 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1350 |
+
"rewards/chosen": -0.2813548147678375,
|
| 1351 |
+
"rewards/margins": 0.23472395539283752,
|
| 1352 |
+
"rewards/rejected": -0.5160787105560303,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": -0.0010059855412691832,
|
| 1359 |
+
"logits/rejected": 0.11881496012210846,
|
| 1360 |
+
"logps/chosen": -682.4347534179688,
|
| 1361 |
+
"logps/rejected": -841.9749755859375,
|
| 1362 |
+
"loss": 0.2177,
|
| 1363 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1364 |
+
"rewards/chosen": -0.3291272521018982,
|
| 1365 |
+
"rewards/margins": 0.23086945712566376,
|
| 1366 |
+
"rewards/rejected": -0.5599966645240784,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": 0.05394923686981201,
|
| 1373 |
+
"logits/rejected": 0.16719438135623932,
|
| 1374 |
+
"logps/chosen": -690.3303833007812,
|
| 1375 |
+
"logps/rejected": -856.0970458984375,
|
| 1376 |
+
"loss": 0.2469,
|
| 1377 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1378 |
+
"rewards/chosen": -0.3471989035606384,
|
| 1379 |
+
"rewards/margins": 0.21049991250038147,
|
| 1380 |
+
"rewards/rejected": -0.5576988458633423,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": 0.043146662414073944,
|
| 1387 |
+
"logits/rejected": 0.08542972058057785,
|
| 1388 |
+
"logps/chosen": -734.964599609375,
|
| 1389 |
+
"logps/rejected": -885.3410034179688,
|
| 1390 |
+
"loss": 0.2057,
|
| 1391 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1392 |
+
"rewards/chosen": -0.3733413815498352,
|
| 1393 |
+
"rewards/margins": 0.21346192061901093,
|
| 1394 |
+
"rewards/rejected": -0.5868033170700073,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": 0.01986471749842167,
|
| 1401 |
+
"logits/rejected": 0.1354392021894455,
|
| 1402 |
+
"logps/chosen": -722.3784790039062,
|
| 1403 |
+
"logps/rejected": -825.0411376953125,
|
| 1404 |
+
"loss": 0.2134,
|
| 1405 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1406 |
+
"rewards/chosen": -0.33837828040122986,
|
| 1407 |
+
"rewards/margins": 0.21411871910095215,
|
| 1408 |
+
"rewards/rejected": -0.5524970293045044,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": 0.04280179738998413,
|
| 1415 |
+
"logits/rejected": 0.16137579083442688,
|
| 1416 |
+
"logps/chosen": -761.4157104492188,
|
| 1417 |
+
"logps/rejected": -863.3331909179688,
|
| 1418 |
+
"loss": 0.2193,
|
| 1419 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1420 |
+
"rewards/chosen": -0.3615965247154236,
|
| 1421 |
+
"rewards/margins": 0.20891360938549042,
|
| 1422 |
+
"rewards/rejected": -0.5705101490020752,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": 0.028211206197738647,
|
| 1429 |
+
"logits/rejected": 0.09348297864198685,
|
| 1430 |
+
"logps/chosen": -724.6305541992188,
|
| 1431 |
+
"logps/rejected": -880.3488159179688,
|
| 1432 |
+
"loss": 0.2079,
|
| 1433 |
+
"rewards/accuracies": 0.8125,
|
| 1434 |
+
"rewards/chosen": -0.36276954412460327,
|
| 1435 |
+
"rewards/margins": 0.22737035155296326,
|
| 1436 |
+
"rewards/rejected": -0.5901398658752441,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": 0.05322765186429024,
|
| 1443 |
+
"logits/rejected": 0.13077041506767273,
|
| 1444 |
+
"logps/chosen": -760.7427978515625,
|
| 1445 |
+
"logps/rejected": -912.9437255859375,
|
| 1446 |
+
"loss": 0.2429,
|
| 1447 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1448 |
+
"rewards/chosen": -0.41152581572532654,
|
| 1449 |
+
"rewards/margins": 0.21826231479644775,
|
| 1450 |
+
"rewards/rejected": -0.6297882199287415,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": -0.0053452602587640285,
|
| 1457 |
+
"logits/rejected": 0.112821564078331,
|
| 1458 |
+
"logps/chosen": -674.3397827148438,
|
| 1459 |
+
"logps/rejected": -873.40087890625,
|
| 1460 |
+
"loss": 0.1812,
|
| 1461 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1462 |
+
"rewards/chosen": -0.34911829233169556,
|
| 1463 |
+
"rewards/margins": 0.24309155344963074,
|
| 1464 |
+
"rewards/rejected": -0.5922098159790039,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": 0.0023634755052626133,
|
| 1471 |
+
"logits/rejected": 0.12815037369728088,
|
| 1472 |
+
"logps/chosen": -758.9469604492188,
|
| 1473 |
+
"logps/rejected": -931.2481689453125,
|
| 1474 |
+
"loss": 0.2024,
|
| 1475 |
+
"rewards/accuracies": 0.8125,
|
| 1476 |
+
"rewards/chosen": -0.37650245428085327,
|
| 1477 |
+
"rewards/margins": 0.25763195753097534,
|
| 1478 |
+
"rewards/rejected": -0.6341344118118286,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": 0.035070545971393585,
|
| 1485 |
+
"logits/rejected": 0.12803152203559875,
|
| 1486 |
+
"logps/chosen": -736.931396484375,
|
| 1487 |
+
"logps/rejected": -923.0338745117188,
|
| 1488 |
+
"loss": 0.184,
|
| 1489 |
+
"rewards/accuracies": 0.78125,
|
| 1490 |
+
"rewards/chosen": -0.36943623423576355,
|
| 1491 |
+
"rewards/margins": 0.2507568597793579,
|
| 1492 |
+
"rewards/rejected": -0.6201931238174438,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": 5.705729199689813e-05,
|
| 1499 |
+
"logits/rejected": 0.1263124793767929,
|
| 1500 |
+
"logps/chosen": -706.70068359375,
|
| 1501 |
+
"logps/rejected": -814.0146484375,
|
| 1502 |
+
"loss": 0.2331,
|
| 1503 |
+
"rewards/accuracies": 0.65625,
|
| 1504 |
+
"rewards/chosen": -0.3658052086830139,
|
| 1505 |
+
"rewards/margins": 0.1808270514011383,
|
| 1506 |
+
"rewards/rejected": -0.5466322898864746,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": 0.015436547808349133,
|
| 1513 |
+
"logits/rejected": 0.10843756049871445,
|
| 1514 |
+
"logps/chosen": -703.6624755859375,
|
| 1515 |
+
"logps/rejected": -858.7509765625,
|
| 1516 |
+
"loss": 0.1987,
|
| 1517 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1518 |
+
"rewards/chosen": -0.31511586904525757,
|
| 1519 |
+
"rewards/margins": 0.2355271279811859,
|
| 1520 |
+
"rewards/rejected": -0.5506430268287659,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": 0.012071605771780014,
|
| 1527 |
+
"logits/rejected": 0.11224579811096191,
|
| 1528 |
+
"logps/chosen": -666.1785888671875,
|
| 1529 |
+
"logps/rejected": -801.8255004882812,
|
| 1530 |
+
"loss": 0.2259,
|
| 1531 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1532 |
+
"rewards/chosen": -0.34429460763931274,
|
| 1533 |
+
"rewards/margins": 0.19534102082252502,
|
| 1534 |
+
"rewards/rejected": -0.5396356582641602,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": -0.010557098314166069,
|
| 1541 |
+
"logits/rejected": 0.06913888454437256,
|
| 1542 |
+
"logps/chosen": -734.2570190429688,
|
| 1543 |
+
"logps/rejected": -892.15625,
|
| 1544 |
+
"loss": 0.2044,
|
| 1545 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1546 |
+
"rewards/chosen": -0.36991119384765625,
|
| 1547 |
+
"rewards/margins": 0.2224087417125702,
|
| 1548 |
+
"rewards/rejected": -0.5923199653625488,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": -0.006013315636664629,
|
| 1555 |
+
"logits/rejected": 0.08018209785223007,
|
| 1556 |
+
"logps/chosen": -695.9881591796875,
|
| 1557 |
+
"logps/rejected": -833.2312622070312,
|
| 1558 |
+
"loss": 0.2152,
|
| 1559 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1560 |
+
"rewards/chosen": -0.36053889989852905,
|
| 1561 |
+
"rewards/margins": 0.20316271483898163,
|
| 1562 |
+
"rewards/rejected": -0.5637016296386719,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": -0.008084287866950035,
|
| 1569 |
+
"logits/rejected": 0.0774918869137764,
|
| 1570 |
+
"logps/chosen": -716.2960815429688,
|
| 1571 |
+
"logps/rejected": -869.6041259765625,
|
| 1572 |
+
"loss": 0.2309,
|
| 1573 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1574 |
+
"rewards/chosen": -0.3821774125099182,
|
| 1575 |
+
"rewards/margins": 0.20834413170814514,
|
| 1576 |
+
"rewards/rejected": -0.5905215740203857,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": 0.007766352035105228,
|
| 1583 |
+
"logits/rejected": 0.030095476657152176,
|
| 1584 |
+
"logps/chosen": -695.3117065429688,
|
| 1585 |
+
"logps/rejected": -871.33837890625,
|
| 1586 |
+
"loss": 0.1987,
|
| 1587 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1588 |
+
"rewards/chosen": -0.3631244897842407,
|
| 1589 |
+
"rewards/margins": 0.22518320381641388,
|
| 1590 |
+
"rewards/rejected": -0.5883077383041382,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": -0.024640878662467003,
|
| 1597 |
+
"logits/rejected": 0.09226598590612411,
|
| 1598 |
+
"logps/chosen": -703.4818115234375,
|
| 1599 |
+
"logps/rejected": -877.7662353515625,
|
| 1600 |
+
"loss": 0.2056,
|
| 1601 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1602 |
+
"rewards/chosen": -0.3533559739589691,
|
| 1603 |
+
"rewards/margins": 0.22752220928668976,
|
| 1604 |
+
"rewards/rejected": -0.5808781385421753,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": 0.009741904214024544,
|
| 1611 |
+
"logits/rejected": 0.17097178101539612,
|
| 1612 |
+
"logps/chosen": -810.0487670898438,
|
| 1613 |
+
"logps/rejected": -879.8194580078125,
|
| 1614 |
+
"loss": 0.1982,
|
| 1615 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1616 |
+
"rewards/chosen": -0.3632999062538147,
|
| 1617 |
+
"rewards/margins": 0.2137196958065033,
|
| 1618 |
+
"rewards/rejected": -0.5770195722579956,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": 0.012245150282979012,
|
| 1625 |
+
"logits/rejected": 0.12731657922267914,
|
| 1626 |
+
"logps/chosen": -676.3506469726562,
|
| 1627 |
+
"logps/rejected": -802.7940063476562,
|
| 1628 |
+
"loss": 0.2275,
|
| 1629 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1630 |
+
"rewards/chosen": -0.33614057302474976,
|
| 1631 |
+
"rewards/margins": 0.19641144573688507,
|
| 1632 |
+
"rewards/rejected": -0.5325520634651184,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": 0.02413441613316536,
|
| 1639 |
+
"logits/rejected": 0.19431506097316742,
|
| 1640 |
+
"logps/chosen": -700.3193359375,
|
| 1641 |
+
"logps/rejected": -871.38232421875,
|
| 1642 |
+
"loss": 0.1795,
|
| 1643 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1644 |
+
"rewards/chosen": -0.32141950726509094,
|
| 1645 |
+
"rewards/margins": 0.23818500339984894,
|
| 1646 |
+
"rewards/rejected": -0.5596045255661011,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": 0.041377656161785126,
|
| 1653 |
+
"logits/rejected": 0.15879663825035095,
|
| 1654 |
+
"logps/chosen": -665.6008911132812,
|
| 1655 |
+
"logps/rejected": -830.9329223632812,
|
| 1656 |
+
"loss": 0.2267,
|
| 1657 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1658 |
+
"rewards/chosen": -0.342972993850708,
|
| 1659 |
+
"rewards/margins": 0.20079226791858673,
|
| 1660 |
+
"rewards/rejected": -0.5437651872634888,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": 0.022486714646220207,
|
| 1667 |
+
"logits/rejected": 0.146213561296463,
|
| 1668 |
+
"logps/chosen": -672.7999877929688,
|
| 1669 |
+
"logps/rejected": -847.8994140625,
|
| 1670 |
+
"loss": 0.1819,
|
| 1671 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1672 |
+
"rewards/chosen": -0.3093092739582062,
|
| 1673 |
+
"rewards/margins": 0.2545778453350067,
|
| 1674 |
+
"rewards/rejected": -0.5638871192932129,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": 0.04687700420618057,
|
| 1681 |
+
"logits/rejected": 0.12050887197256088,
|
| 1682 |
+
"logps/chosen": -672.9434814453125,
|
| 1683 |
+
"logps/rejected": -819.170654296875,
|
| 1684 |
+
"loss": 0.2352,
|
| 1685 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1686 |
+
"rewards/chosen": -0.3423709273338318,
|
| 1687 |
+
"rewards/margins": 0.20281191170215607,
|
| 1688 |
+
"rewards/rejected": -0.5451828241348267,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": 0.045673031359910965,
|
| 1695 |
+
"logits/rejected": 0.11997739970684052,
|
| 1696 |
+
"logps/chosen": -611.8385009765625,
|
| 1697 |
+
"logps/rejected": -820.4505615234375,
|
| 1698 |
+
"loss": 0.2063,
|
| 1699 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1700 |
+
"rewards/chosen": -0.29818734526634216,
|
| 1701 |
+
"rewards/margins": 0.22259333729743958,
|
| 1702 |
+
"rewards/rejected": -0.5207806825637817,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": 0.06439246237277985,
|
| 1709 |
+
"logits/rejected": 0.10217195749282837,
|
| 1710 |
+
"logps/chosen": -665.1314697265625,
|
| 1711 |
+
"logps/rejected": -801.7761840820312,
|
| 1712 |
+
"loss": 0.2283,
|
| 1713 |
+
"rewards/accuracies": 0.75,
|
| 1714 |
+
"rewards/chosen": -0.3135600686073303,
|
| 1715 |
+
"rewards/margins": 0.20070858299732208,
|
| 1716 |
+
"rewards/rejected": -0.514268696308136,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": 0.03967912867665291,
|
| 1723 |
+
"logits/rejected": 0.1717870980501175,
|
| 1724 |
+
"logps/chosen": -683.311767578125,
|
| 1725 |
+
"logps/rejected": -844.0208129882812,
|
| 1726 |
+
"loss": 0.2371,
|
| 1727 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1728 |
+
"rewards/chosen": -0.3242947459220886,
|
| 1729 |
+
"rewards/margins": 0.2034534513950348,
|
| 1730 |
+
"rewards/rejected": -0.5277482271194458,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": 0.013939693570137024,
|
| 1737 |
+
"logits/rejected": 0.12744280695915222,
|
| 1738 |
+
"logps/chosen": -689.4755859375,
|
| 1739 |
+
"logps/rejected": -812.0987548828125,
|
| 1740 |
+
"loss": 0.2429,
|
| 1741 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1742 |
+
"rewards/chosen": -0.3416514992713928,
|
| 1743 |
+
"rewards/margins": 0.1776062697172165,
|
| 1744 |
+
"rewards/rejected": -0.5192577838897705,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": 0.06095554679632187,
|
| 1751 |
+
"logits/rejected": 0.14684705436229706,
|
| 1752 |
+
"logps/chosen": -654.1356811523438,
|
| 1753 |
+
"logps/rejected": -810.3081665039062,
|
| 1754 |
+
"loss": 0.2229,
|
| 1755 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1756 |
+
"rewards/chosen": -0.3114492893218994,
|
| 1757 |
+
"rewards/margins": 0.1974024623632431,
|
| 1758 |
+
"rewards/rejected": -0.5088517665863037,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": 0.05724464729428291,
|
| 1765 |
+
"logits/rejected": 0.14580979943275452,
|
| 1766 |
+
"logps/chosen": -657.7913818359375,
|
| 1767 |
+
"logps/rejected": -799.1402587890625,
|
| 1768 |
+
"loss": 0.2055,
|
| 1769 |
+
"rewards/accuracies": 0.78125,
|
| 1770 |
+
"rewards/chosen": -0.308960497379303,
|
| 1771 |
+
"rewards/margins": 0.21290500462055206,
|
| 1772 |
+
"rewards/rejected": -0.5218654870986938,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": 0.04883120581507683,
|
| 1779 |
+
"logits/rejected": 0.11742043495178223,
|
| 1780 |
+
"logps/chosen": -645.9979248046875,
|
| 1781 |
+
"logps/rejected": -819.2106323242188,
|
| 1782 |
+
"loss": 0.1943,
|
| 1783 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1784 |
+
"rewards/chosen": -0.3161103129386902,
|
| 1785 |
+
"rewards/margins": 0.21235115826129913,
|
| 1786 |
+
"rewards/rejected": -0.5284615159034729,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": 0.08411203324794769,
|
| 1793 |
+
"logits/rejected": 0.14393514394760132,
|
| 1794 |
+
"logps/chosen": -695.6365966796875,
|
| 1795 |
+
"logps/rejected": -878.0914306640625,
|
| 1796 |
+
"loss": 0.2218,
|
| 1797 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1798 |
+
"rewards/chosen": -0.34891873598098755,
|
| 1799 |
+
"rewards/margins": 0.24423813819885254,
|
| 1800 |
+
"rewards/rejected": -0.5931568741798401,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": 0.045291513204574585,
|
| 1807 |
+
"logits/rejected": 0.13728824257850647,
|
| 1808 |
+
"logps/chosen": -707.1044311523438,
|
| 1809 |
+
"logps/rejected": -854.4798583984375,
|
| 1810 |
+
"loss": 0.2101,
|
| 1811 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1812 |
+
"rewards/chosen": -0.3448121249675751,
|
| 1813 |
+
"rewards/margins": 0.23182924091815948,
|
| 1814 |
+
"rewards/rejected": -0.5766413807868958,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": 0.029178116470575333,
|
| 1821 |
+
"logits/rejected": 0.17620958387851715,
|
| 1822 |
+
"logps/chosen": -674.8609008789062,
|
| 1823 |
+
"logps/rejected": -858.0894775390625,
|
| 1824 |
+
"loss": 0.1804,
|
| 1825 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1826 |
+
"rewards/chosen": -0.3337288498878479,
|
| 1827 |
+
"rewards/margins": 0.24131789803504944,
|
| 1828 |
+
"rewards/rejected": -0.5750466585159302,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": 0.038364656269550323,
|
| 1835 |
+
"logits/rejected": 0.15578509867191315,
|
| 1836 |
+
"logps/chosen": -692.9742431640625,
|
| 1837 |
+
"logps/rejected": -857.2974853515625,
|
| 1838 |
+
"loss": 0.2094,
|
| 1839 |
+
"rewards/accuracies": 0.75,
|
| 1840 |
+
"rewards/chosen": -0.3217311501502991,
|
| 1841 |
+
"rewards/margins": 0.2241102159023285,
|
| 1842 |
+
"rewards/rejected": -0.54584139585495,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": 0.01667640171945095,
|
| 1849 |
+
"logits/rejected": 0.10969080030918121,
|
| 1850 |
+
"logps/chosen": -627.9285888671875,
|
| 1851 |
+
"logps/rejected": -815.8270263671875,
|
| 1852 |
+
"loss": 0.2083,
|
| 1853 |
+
"rewards/accuracies": 0.78125,
|
| 1854 |
+
"rewards/chosen": -0.3187568783760071,
|
| 1855 |
+
"rewards/margins": 0.22442683577537537,
|
| 1856 |
+
"rewards/rejected": -0.5431837439537048,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": 0.04231597110629082,
|
| 1863 |
+
"logits/rejected": 0.14465740323066711,
|
| 1864 |
+
"logps/chosen": -721.646484375,
|
| 1865 |
+
"logps/rejected": -825.8064575195312,
|
| 1866 |
+
"loss": 0.2264,
|
| 1867 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1868 |
+
"rewards/chosen": -0.3264230787754059,
|
| 1869 |
+
"rewards/margins": 0.21109537780284882,
|
| 1870 |
+
"rewards/rejected": -0.5375184416770935,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": 0.0638522133231163,
|
| 1877 |
+
"logits/rejected": 0.14387431740760803,
|
| 1878 |
+
"logps/chosen": -669.5394287109375,
|
| 1879 |
+
"logps/rejected": -838.8292236328125,
|
| 1880 |
+
"loss": 0.1997,
|
| 1881 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1882 |
+
"rewards/chosen": -0.33911409974098206,
|
| 1883 |
+
"rewards/margins": 0.22880196571350098,
|
| 1884 |
+
"rewards/rejected": -0.5679160356521606,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": 0.014098724350333214,
|
| 1891 |
+
"logits/rejected": 0.13527414202690125,
|
| 1892 |
+
"logps/chosen": -669.8994750976562,
|
| 1893 |
+
"logps/rejected": -806.6534423828125,
|
| 1894 |
+
"loss": 0.2604,
|
| 1895 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1896 |
+
"rewards/chosen": -0.34625038504600525,
|
| 1897 |
+
"rewards/margins": 0.17370744049549103,
|
| 1898 |
+
"rewards/rejected": -0.5199578404426575,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": 0.027355173602700233,
|
| 1905 |
+
"logits/rejected": 0.12094994634389877,
|
| 1906 |
+
"logps/chosen": -686.2830200195312,
|
| 1907 |
+
"logps/rejected": -793.8912353515625,
|
| 1908 |
+
"loss": 0.2006,
|
| 1909 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1910 |
+
"rewards/chosen": -0.3198310434818268,
|
| 1911 |
+
"rewards/margins": 0.2038339078426361,
|
| 1912 |
+
"rewards/rejected": -0.5236650109291077,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": 0.011197770945727825,
|
| 1919 |
+
"logits/rejected": 0.1233413964509964,
|
| 1920 |
+
"logps/chosen": -663.2740478515625,
|
| 1921 |
+
"logps/rejected": -827.7921142578125,
|
| 1922 |
+
"loss": 0.2023,
|
| 1923 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1924 |
+
"rewards/chosen": -0.31737273931503296,
|
| 1925 |
+
"rewards/margins": 0.2423689365386963,
|
| 1926 |
+
"rewards/rejected": -0.5597416162490845,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": 0.012365484610199928,
|
| 1933 |
+
"logits/rejected": 0.14399036765098572,
|
| 1934 |
+
"logps/chosen": -723.01611328125,
|
| 1935 |
+
"logps/rejected": -888.5731201171875,
|
| 1936 |
+
"loss": 0.2107,
|
| 1937 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1938 |
+
"rewards/chosen": -0.3377194106578827,
|
| 1939 |
+
"rewards/margins": 0.25036248564720154,
|
| 1940 |
+
"rewards/rejected": -0.588081955909729,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": 0.03630852699279785,
|
| 1947 |
+
"logits/rejected": 0.1697433888912201,
|
| 1948 |
+
"logps/chosen": -692.0089111328125,
|
| 1949 |
+
"logps/rejected": -841.7423706054688,
|
| 1950 |
+
"loss": 0.2225,
|
| 1951 |
+
"rewards/accuracies": 0.71875,
|
| 1952 |
+
"rewards/chosen": -0.33607909083366394,
|
| 1953 |
+
"rewards/margins": 0.2240186482667923,
|
| 1954 |
+
"rewards/rejected": -0.5600977540016174,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": 0.06855352222919464,
|
| 1961 |
+
"logits/rejected": 0.16431955993175507,
|
| 1962 |
+
"logps/chosen": -735.5272216796875,
|
| 1963 |
+
"logps/rejected": -859.2053833007812,
|
| 1964 |
+
"loss": 0.2056,
|
| 1965 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1966 |
+
"rewards/chosen": -0.3497410714626312,
|
| 1967 |
+
"rewards/margins": 0.21472422778606415,
|
| 1968 |
+
"rewards/rejected": -0.564465343952179,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": -0.0006916738930158317,
|
| 1975 |
+
"logits/rejected": 0.11941851675510406,
|
| 1976 |
+
"logps/chosen": -708.4884643554688,
|
| 1977 |
+
"logps/rejected": -896.8206787109375,
|
| 1978 |
+
"loss": 0.1853,
|
| 1979 |
+
"rewards/accuracies": 0.8125,
|
| 1980 |
+
"rewards/chosen": -0.35898059606552124,
|
| 1981 |
+
"rewards/margins": 0.240576833486557,
|
| 1982 |
+
"rewards/rejected": -0.5995574593544006,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": 0.039211105555295944,
|
| 1989 |
+
"logits/rejected": 0.11498727649450302,
|
| 1990 |
+
"logps/chosen": -711.9271850585938,
|
| 1991 |
+
"logps/rejected": -853.4754638671875,
|
| 1992 |
+
"loss": 0.2018,
|
| 1993 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1994 |
+
"rewards/chosen": -0.3567042946815491,
|
| 1995 |
+
"rewards/margins": 0.21128018200397491,
|
| 1996 |
+
"rewards/rejected": -0.567984402179718,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": 0.02443738654255867,
|
| 2003 |
+
"logits/rejected": 0.05825776979327202,
|
| 2004 |
+
"logps/chosen": -668.7024536132812,
|
| 2005 |
+
"logps/rejected": -816.4102172851562,
|
| 2006 |
+
"loss": 0.2303,
|
| 2007 |
+
"rewards/accuracies": 0.71875,
|
| 2008 |
+
"rewards/chosen": -0.332243412733078,
|
| 2009 |
+
"rewards/margins": 0.21151785552501678,
|
| 2010 |
+
"rewards/rejected": -0.5437612533569336,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": 0.04351818934082985,
|
| 2017 |
+
"logits/rejected": 0.10868921130895615,
|
| 2018 |
+
"logps/chosen": -673.7401123046875,
|
| 2019 |
+
"logps/rejected": -815.3800659179688,
|
| 2020 |
+
"loss": 0.2565,
|
| 2021 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2022 |
+
"rewards/chosen": -0.35063451528549194,
|
| 2023 |
+
"rewards/margins": 0.17919650673866272,
|
| 2024 |
+
"rewards/rejected": -0.529831051826477,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": 0.035469502210617065,
|
| 2031 |
+
"logits/rejected": 0.10574381053447723,
|
| 2032 |
+
"logps/chosen": -697.9148559570312,
|
| 2033 |
+
"logps/rejected": -829.6324462890625,
|
| 2034 |
+
"loss": 0.191,
|
| 2035 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 2036 |
+
"rewards/chosen": -0.3119833469390869,
|
| 2037 |
+
"rewards/margins": 0.24292249977588654,
|
| 2038 |
+
"rewards/rejected": -0.5549058318138123,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": -0.019414827227592468,
|
| 2045 |
+
"logits/rejected": 0.18325455486774445,
|
| 2046 |
+
"logps/chosen": -718.9652099609375,
|
| 2047 |
+
"logps/rejected": -853.3225708007812,
|
| 2048 |
+
"loss": 0.2266,
|
| 2049 |
+
"rewards/accuracies": 0.75,
|
| 2050 |
+
"rewards/chosen": -0.35121822357177734,
|
| 2051 |
+
"rewards/margins": 0.2009017914533615,
|
| 2052 |
+
"rewards/rejected": -0.5521200299263,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": 0.023696620017290115,
|
| 2059 |
+
"logits/rejected": 0.10542090982198715,
|
| 2060 |
+
"logps/chosen": -635.32373046875,
|
| 2061 |
+
"logps/rejected": -819.9827880859375,
|
| 2062 |
+
"loss": 0.177,
|
| 2063 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2064 |
+
"rewards/chosen": -0.30631598830223083,
|
| 2065 |
+
"rewards/margins": 0.2354573756456375,
|
| 2066 |
+
"rewards/rejected": -0.5417734384536743,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": 0.0738513395190239,
|
| 2073 |
+
"logits/rejected": 0.12634918093681335,
|
| 2074 |
+
"logps/chosen": -659.0910034179688,
|
| 2075 |
+
"logps/rejected": -865.4376831054688,
|
| 2076 |
+
"loss": 0.2054,
|
| 2077 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 2078 |
+
"rewards/chosen": -0.3390515446662903,
|
| 2079 |
+
"rewards/margins": 0.23071372509002686,
|
| 2080 |
+
"rewards/rejected": -0.5697652697563171,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": 0.0322534441947937,
|
| 2087 |
+
"logits/rejected": 0.1811327189207077,
|
| 2088 |
+
"logps/chosen": -716.4608764648438,
|
| 2089 |
+
"logps/rejected": -811.6767578125,
|
| 2090 |
+
"loss": 0.231,
|
| 2091 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2092 |
+
"rewards/chosen": -0.3598640263080597,
|
| 2093 |
+
"rewards/margins": 0.19128559529781342,
|
| 2094 |
+
"rewards/rejected": -0.5511496663093567,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": -0.00073561369208619,
|
| 2101 |
+
"logits/rejected": 0.0718742161989212,
|
| 2102 |
+
"logps/chosen": -638.3681640625,
|
| 2103 |
+
"logps/rejected": -820.8011474609375,
|
| 2104 |
+
"loss": 0.2099,
|
| 2105 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2106 |
+
"rewards/chosen": -0.3302134573459625,
|
| 2107 |
+
"rewards/margins": 0.2071600705385208,
|
| 2108 |
+
"rewards/rejected": -0.5373734831809998,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": 0.00898817926645279,
|
| 2115 |
+
"logits/rejected": 0.10342226177453995,
|
| 2116 |
+
"logps/chosen": -722.0171508789062,
|
| 2117 |
+
"logps/rejected": -861.2794189453125,
|
| 2118 |
+
"loss": 0.2237,
|
| 2119 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2120 |
+
"rewards/chosen": -0.3676268458366394,
|
| 2121 |
+
"rewards/margins": 0.21328619122505188,
|
| 2122 |
+
"rewards/rejected": -0.5809130072593689,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": 0.01620279997587204,
|
| 2129 |
+
"logits/rejected": 0.12123896926641464,
|
| 2130 |
+
"logps/chosen": -617.8934326171875,
|
| 2131 |
+
"logps/rejected": -802.05859375,
|
| 2132 |
+
"loss": 0.2168,
|
| 2133 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2134 |
+
"rewards/chosen": -0.299948513507843,
|
| 2135 |
+
"rewards/margins": 0.219092458486557,
|
| 2136 |
+
"rewards/rejected": -0.5190409421920776,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": 0.0352124460041523,
|
| 2143 |
+
"logits/rejected": 0.1431238204240799,
|
| 2144 |
+
"logps/chosen": -697.825927734375,
|
| 2145 |
+
"logps/rejected": -875.0059814453125,
|
| 2146 |
+
"loss": 0.2137,
|
| 2147 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2148 |
+
"rewards/chosen": -0.3430352807044983,
|
| 2149 |
+
"rewards/margins": 0.21984973549842834,
|
| 2150 |
+
"rewards/rejected": -0.562885046005249,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": 0.04245247319340706,
|
| 2157 |
+
"logits/rejected": 0.13526387512683868,
|
| 2158 |
+
"logps/chosen": -697.025390625,
|
| 2159 |
+
"logps/rejected": -813.5718994140625,
|
| 2160 |
+
"loss": 0.2386,
|
| 2161 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 2162 |
+
"rewards/chosen": -0.33000361919403076,
|
| 2163 |
+
"rewards/margins": 0.21133120357990265,
|
| 2164 |
+
"rewards/rejected": -0.5413348078727722,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": 0.02729245461523533,
|
| 2171 |
+
"logits/rejected": 0.14574703574180603,
|
| 2172 |
+
"logps/chosen": -676.8394775390625,
|
| 2173 |
+
"logps/rejected": -825.9822998046875,
|
| 2174 |
+
"loss": 0.2333,
|
| 2175 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2176 |
+
"rewards/chosen": -0.3324502110481262,
|
| 2177 |
+
"rewards/margins": 0.20352134108543396,
|
| 2178 |
+
"rewards/rejected": -0.5359715223312378,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": 0.04532911255955696,
|
| 2185 |
+
"logits/rejected": 0.12752528488636017,
|
| 2186 |
+
"logps/chosen": -633.0133056640625,
|
| 2187 |
+
"logps/rejected": -786.7761840820312,
|
| 2188 |
+
"loss": 0.2063,
|
| 2189 |
+
"rewards/accuracies": 0.71875,
|
| 2190 |
+
"rewards/chosen": -0.29472070932388306,
|
| 2191 |
+
"rewards/margins": 0.21680741012096405,
|
| 2192 |
+
"rewards/rejected": -0.5115281343460083,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": 0.07257268577814102,
|
| 2199 |
+
"logits/rejected": 0.11432480812072754,
|
| 2200 |
+
"logps/chosen": -690.2648315429688,
|
| 2201 |
+
"logps/rejected": -863.9197998046875,
|
| 2202 |
+
"loss": 0.2096,
|
| 2203 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2204 |
+
"rewards/chosen": -0.3343331217765808,
|
| 2205 |
+
"rewards/margins": 0.23166866600513458,
|
| 2206 |
+
"rewards/rejected": -0.5660017728805542,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": 0.06963463127613068,
|
| 2213 |
+
"logits/rejected": 0.12501554191112518,
|
| 2214 |
+
"logps/chosen": -634.1485595703125,
|
| 2215 |
+
"logps/rejected": -776.090576171875,
|
| 2216 |
+
"loss": 0.2422,
|
| 2217 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2218 |
+
"rewards/chosen": -0.32659441232681274,
|
| 2219 |
+
"rewards/margins": 0.19114482402801514,
|
| 2220 |
+
"rewards/rejected": -0.5177391767501831,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": 0.0035268261563032866,
|
| 2227 |
+
"logits/rejected": 0.03672543540596962,
|
| 2228 |
+
"logps/chosen": -623.8313598632812,
|
| 2229 |
+
"logps/rejected": -851.9779052734375,
|
| 2230 |
+
"loss": 0.2306,
|
| 2231 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2232 |
+
"rewards/chosen": -0.3241678476333618,
|
| 2233 |
+
"rewards/margins": 0.22523315250873566,
|
| 2234 |
+
"rewards/rejected": -0.5494009852409363,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": 0.03905852884054184,
|
| 2241 |
+
"logits/rejected": 0.0981665775179863,
|
| 2242 |
+
"logps/chosen": -628.8436889648438,
|
| 2243 |
+
"logps/rejected": -775.3961791992188,
|
| 2244 |
+
"loss": 0.2274,
|
| 2245 |
+
"rewards/accuracies": 0.668749988079071,
|
| 2246 |
+
"rewards/chosen": -0.3110875189304352,
|
| 2247 |
+
"rewards/margins": 0.2002953737974167,
|
| 2248 |
+
"rewards/rejected": -0.5113828778266907,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": 0.06323795020580292,
|
| 2255 |
+
"logits/rejected": 0.1348869502544403,
|
| 2256 |
+
"logps/chosen": -645.1129150390625,
|
| 2257 |
+
"logps/rejected": -793.5126953125,
|
| 2258 |
+
"loss": 0.1864,
|
| 2259 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2260 |
+
"rewards/chosen": -0.3031459450721741,
|
| 2261 |
+
"rewards/margins": 0.22209510207176208,
|
| 2262 |
+
"rewards/rejected": -0.5252410173416138,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": 0.07657162100076675,
|
| 2269 |
+
"logits/rejected": 0.11810870468616486,
|
| 2270 |
+
"logps/chosen": -679.9815673828125,
|
| 2271 |
+
"logps/rejected": -822.6639404296875,
|
| 2272 |
+
"loss": 0.2164,
|
| 2273 |
+
"rewards/accuracies": 0.75,
|
| 2274 |
+
"rewards/chosen": -0.342891126871109,
|
| 2275 |
+
"rewards/margins": 0.2010626345872879,
|
| 2276 |
+
"rewards/rejected": -0.5439537167549133,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": 0.065867580473423,
|
| 2283 |
+
"logits/rejected": 0.15143200755119324,
|
| 2284 |
+
"logps/chosen": -630.640869140625,
|
| 2285 |
+
"logps/rejected": -778.2337036132812,
|
| 2286 |
+
"loss": 0.1918,
|
| 2287 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2288 |
+
"rewards/chosen": -0.3079833388328552,
|
| 2289 |
+
"rewards/margins": 0.2207847535610199,
|
| 2290 |
+
"rewards/rejected": -0.5287681221961975,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": 0.07310919463634491,
|
| 2297 |
+
"logits/rejected": 0.12045961618423462,
|
| 2298 |
+
"logps/chosen": -711.3140869140625,
|
| 2299 |
+
"logps/rejected": -828.66015625,
|
| 2300 |
+
"loss": 0.2413,
|
| 2301 |
+
"rewards/accuracies": 0.71875,
|
| 2302 |
+
"rewards/chosen": -0.34624183177948,
|
| 2303 |
+
"rewards/margins": 0.1804010570049286,
|
| 2304 |
+
"rewards/rejected": -0.526642918586731,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": 0.038972992449998856,
|
| 2311 |
+
"logits/rejected": 0.1098276823759079,
|
| 2312 |
+
"logps/chosen": -679.78271484375,
|
| 2313 |
+
"logps/rejected": -838.59765625,
|
| 2314 |
+
"loss": 0.2205,
|
| 2315 |
+
"rewards/accuracies": 0.75,
|
| 2316 |
+
"rewards/chosen": -0.3377990126609802,
|
| 2317 |
+
"rewards/margins": 0.21535663306713104,
|
| 2318 |
+
"rewards/rejected": -0.5531556606292725,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": 0.05230052396655083,
|
| 2325 |
+
"logits/rejected": 0.14600692689418793,
|
| 2326 |
+
"logps/chosen": -679.2337036132812,
|
| 2327 |
+
"logps/rejected": -837.9591674804688,
|
| 2328 |
+
"loss": 0.2071,
|
| 2329 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2330 |
+
"rewards/chosen": -0.3297780156135559,
|
| 2331 |
+
"rewards/margins": 0.22520343959331512,
|
| 2332 |
+
"rewards/rejected": -0.5549814701080322,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": 0.09260080009698868,
|
| 2339 |
+
"logits/rejected": 0.1418459266424179,
|
| 2340 |
+
"logps/chosen": -681.7306518554688,
|
| 2341 |
+
"logps/rejected": -802.3380126953125,
|
| 2342 |
+
"loss": 0.2068,
|
| 2343 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2344 |
+
"rewards/chosen": -0.31467029452323914,
|
| 2345 |
+
"rewards/margins": 0.21341577172279358,
|
| 2346 |
+
"rewards/rejected": -0.5280860662460327,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": 0.01892709732055664,
|
| 2353 |
+
"logits/rejected": 0.10615235567092896,
|
| 2354 |
+
"logps/chosen": -638.789794921875,
|
| 2355 |
+
"logps/rejected": -835.4816284179688,
|
| 2356 |
+
"loss": 0.2051,
|
| 2357 |
+
"rewards/accuracies": 0.78125,
|
| 2358 |
+
"rewards/chosen": -0.3251439332962036,
|
| 2359 |
+
"rewards/margins": 0.21179835498332977,
|
| 2360 |
+
"rewards/rejected": -0.5369422435760498,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": 0.07935929298400879,
|
| 2367 |
+
"logits/rejected": 0.2099631130695343,
|
| 2368 |
+
"logps/chosen": -729.1849365234375,
|
| 2369 |
+
"logps/rejected": -823.9190673828125,
|
| 2370 |
+
"loss": 0.2305,
|
| 2371 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2372 |
+
"rewards/chosen": -0.32880938053131104,
|
| 2373 |
+
"rewards/margins": 0.21041882038116455,
|
| 2374 |
+
"rewards/rejected": -0.5392282009124756,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": 0.056362926959991455,
|
| 2381 |
+
"logits/rejected": 0.13600429892539978,
|
| 2382 |
+
"logps/chosen": -694.4349975585938,
|
| 2383 |
+
"logps/rejected": -821.8929443359375,
|
| 2384 |
+
"loss": 0.2202,
|
| 2385 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2386 |
+
"rewards/chosen": -0.3222964107990265,
|
| 2387 |
+
"rewards/margins": 0.22275909781455994,
|
| 2388 |
+
"rewards/rejected": -0.5450555086135864,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": 0.07223354279994965,
|
| 2395 |
+
"logits/rejected": 0.13364526629447937,
|
| 2396 |
+
"logps/chosen": -760.1466674804688,
|
| 2397 |
+
"logps/rejected": -892.9208984375,
|
| 2398 |
+
"loss": 0.1978,
|
| 2399 |
+
"rewards/accuracies": 0.78125,
|
| 2400 |
+
"rewards/chosen": -0.37695029377937317,
|
| 2401 |
+
"rewards/margins": 0.20259904861450195,
|
| 2402 |
+
"rewards/rejected": -0.5795493721961975,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": 0.004451720509678125,
|
| 2409 |
+
"logits/rejected": 0.1476518213748932,
|
| 2410 |
+
"logps/chosen": -679.5355224609375,
|
| 2411 |
+
"logps/rejected": -841.3785400390625,
|
| 2412 |
+
"loss": 0.2127,
|
| 2413 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2414 |
+
"rewards/chosen": -0.3298358917236328,
|
| 2415 |
+
"rewards/margins": 0.2245192527770996,
|
| 2416 |
+
"rewards/rejected": -0.5543551445007324,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": 0.008707459084689617,
|
| 2423 |
+
"logits/rejected": 0.09261924773454666,
|
| 2424 |
+
"logps/chosen": -672.3406982421875,
|
| 2425 |
+
"logps/rejected": -848.3216552734375,
|
| 2426 |
+
"loss": 0.1905,
|
| 2427 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2428 |
+
"rewards/chosen": -0.3172846734523773,
|
| 2429 |
+
"rewards/margins": 0.24588418006896973,
|
| 2430 |
+
"rewards/rejected": -0.5631688833236694,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": 0.0769379660487175,
|
| 2437 |
+
"logits/rejected": 0.10007413476705551,
|
| 2438 |
+
"logps/chosen": -699.5477294921875,
|
| 2439 |
+
"logps/rejected": -884.2034301757812,
|
| 2440 |
+
"loss": 0.1939,
|
| 2441 |
+
"rewards/accuracies": 0.800000011920929,
|
| 2442 |
+
"rewards/chosen": -0.3175678253173828,
|
| 2443 |
+
"rewards/margins": 0.25022247433662415,
|
| 2444 |
+
"rewards/rejected": -0.5677902698516846,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": 0.055988211184740067,
|
| 2451 |
+
"logits/rejected": 0.1475806087255478,
|
| 2452 |
+
"logps/chosen": -652.2313842773438,
|
| 2453 |
+
"logps/rejected": -836.2672119140625,
|
| 2454 |
+
"loss": 0.1983,
|
| 2455 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2456 |
+
"rewards/chosen": -0.3141983151435852,
|
| 2457 |
+
"rewards/margins": 0.24290838837623596,
|
| 2458 |
+
"rewards/rejected": -0.5571067333221436,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": 0.04174142703413963,
|
| 2465 |
+
"logits/rejected": 0.14616337418556213,
|
| 2466 |
+
"logps/chosen": -674.041015625,
|
| 2467 |
+
"logps/rejected": -825.32470703125,
|
| 2468 |
+
"loss": 0.1955,
|
| 2469 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2470 |
+
"rewards/chosen": -0.31099969148635864,
|
| 2471 |
+
"rewards/margins": 0.22915931046009064,
|
| 2472 |
+
"rewards/rejected": -0.5401589870452881,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": 0.057897310703992844,
|
| 2479 |
+
"logits/rejected": 0.157648503780365,
|
| 2480 |
+
"logps/chosen": -703.7222290039062,
|
| 2481 |
+
"logps/rejected": -847.68115234375,
|
| 2482 |
+
"loss": 0.2134,
|
| 2483 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2484 |
+
"rewards/chosen": -0.3606089949607849,
|
| 2485 |
+
"rewards/margins": 0.21621307730674744,
|
| 2486 |
+
"rewards/rejected": -0.5768221616744995,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": 0.06264643371105194,
|
| 2493 |
+
"logits/rejected": 0.14495016634464264,
|
| 2494 |
+
"logps/chosen": -730.0210571289062,
|
| 2495 |
+
"logps/rejected": -846.86474609375,
|
| 2496 |
+
"loss": 0.2213,
|
| 2497 |
+
"rewards/accuracies": 0.71875,
|
| 2498 |
+
"rewards/chosen": -0.35915127396583557,
|
| 2499 |
+
"rewards/margins": 0.19883516430854797,
|
| 2500 |
+
"rewards/rejected": -0.5579863786697388,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": 0.07288487255573273,
|
| 2507 |
+
"logits/rejected": 0.1731829047203064,
|
| 2508 |
+
"logps/chosen": -698.0350341796875,
|
| 2509 |
+
"logps/rejected": -848.1388549804688,
|
| 2510 |
+
"loss": 0.1737,
|
| 2511 |
+
"rewards/accuracies": 0.824999988079071,
|
| 2512 |
+
"rewards/chosen": -0.31695953011512756,
|
| 2513 |
+
"rewards/margins": 0.2423754632472992,
|
| 2514 |
+
"rewards/rejected": -0.5593350529670715,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": 0.06433729827404022,
|
| 2521 |
+
"logits/rejected": 0.13777321577072144,
|
| 2522 |
+
"logps/chosen": -716.5806884765625,
|
| 2523 |
+
"logps/rejected": -871.9490356445312,
|
| 2524 |
+
"loss": 0.2003,
|
| 2525 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2526 |
+
"rewards/chosen": -0.3185502290725708,
|
| 2527 |
+
"rewards/margins": 0.23725280165672302,
|
| 2528 |
+
"rewards/rejected": -0.5558030009269714,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": 0.038981080055236816,
|
| 2535 |
+
"logits/rejected": 0.1305188238620758,
|
| 2536 |
+
"logps/chosen": -728.6278076171875,
|
| 2537 |
+
"logps/rejected": -865.8338012695312,
|
| 2538 |
+
"loss": 0.2074,
|
| 2539 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2540 |
+
"rewards/chosen": -0.34264928102493286,
|
| 2541 |
+
"rewards/margins": 0.23139305412769318,
|
| 2542 |
+
"rewards/rejected": -0.5740423202514648,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": 0.06916898488998413,
|
| 2549 |
+
"logits/rejected": 0.18797878921031952,
|
| 2550 |
+
"logps/chosen": -702.5946044921875,
|
| 2551 |
+
"logps/rejected": -872.0211791992188,
|
| 2552 |
+
"loss": 0.2173,
|
| 2553 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2554 |
+
"rewards/chosen": -0.34207233786582947,
|
| 2555 |
+
"rewards/margins": 0.2262537032365799,
|
| 2556 |
+
"rewards/rejected": -0.5683261156082153,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": 0.05317959189414978,
|
| 2563 |
+
"logits/rejected": 0.11542042344808578,
|
| 2564 |
+
"logps/chosen": -715.3739624023438,
|
| 2565 |
+
"logps/rejected": -858.2398681640625,
|
| 2566 |
+
"loss": 0.2227,
|
| 2567 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2568 |
+
"rewards/chosen": -0.34564128518104553,
|
| 2569 |
+
"rewards/margins": 0.21440550684928894,
|
| 2570 |
+
"rewards/rejected": -0.5600467920303345,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": 0.07714705169200897,
|
| 2577 |
+
"logits/rejected": 0.1786491423845291,
|
| 2578 |
+
"logps/chosen": -677.5328979492188,
|
| 2579 |
+
"logps/rejected": -854.1397705078125,
|
| 2580 |
+
"loss": 0.2085,
|
| 2581 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2582 |
+
"rewards/chosen": -0.32333892583847046,
|
| 2583 |
+
"rewards/margins": 0.22118084132671356,
|
| 2584 |
+
"rewards/rejected": -0.5445197820663452,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": 0.09814608097076416,
|
| 2591 |
+
"logits/rejected": 0.09552597999572754,
|
| 2592 |
+
"logps/chosen": -678.3449096679688,
|
| 2593 |
+
"logps/rejected": -837.9964599609375,
|
| 2594 |
+
"loss": 0.2152,
|
| 2595 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2596 |
+
"rewards/chosen": -0.3395656943321228,
|
| 2597 |
+
"rewards/margins": 0.21091222763061523,
|
| 2598 |
+
"rewards/rejected": -0.5504779815673828,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": 0.08845305442810059,
|
| 2605 |
+
"logits/rejected": 0.13582393527030945,
|
| 2606 |
+
"logps/chosen": -649.8729248046875,
|
| 2607 |
+
"logps/rejected": -840.5818481445312,
|
| 2608 |
+
"loss": 0.2022,
|
| 2609 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2610 |
+
"rewards/chosen": -0.32875552773475647,
|
| 2611 |
+
"rewards/margins": 0.22628939151763916,
|
| 2612 |
+
"rewards/rejected": -0.555044949054718,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": 0.041667476296424866,
|
| 2619 |
+
"logits/rejected": 0.1802738904953003,
|
| 2620 |
+
"logps/chosen": -713.4054565429688,
|
| 2621 |
+
"logps/rejected": -848.8229370117188,
|
| 2622 |
+
"loss": 0.2413,
|
| 2623 |
+
"rewards/accuracies": 0.6875,
|
| 2624 |
+
"rewards/chosen": -0.3549792766571045,
|
| 2625 |
+
"rewards/margins": 0.2078593522310257,
|
| 2626 |
+
"rewards/rejected": -0.5628384947776794,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": 0.07584629207849503,
|
| 2633 |
+
"logits/rejected": 0.15728022158145905,
|
| 2634 |
+
"logps/chosen": -741.0794677734375,
|
| 2635 |
+
"logps/rejected": -853.7579956054688,
|
| 2636 |
+
"loss": 0.2253,
|
| 2637 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2638 |
+
"rewards/chosen": -0.3356108069419861,
|
| 2639 |
+
"rewards/margins": 0.20086529850959778,
|
| 2640 |
+
"rewards/rejected": -0.5364760756492615,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 0.2332912155151367,
|
| 2648 |
+
"train_runtime": 17312.5985,
|
| 2649 |
+
"train_samples_per_second": 1.733,
|
| 2650 |
+
"train_steps_per_second": 0.108
|
| 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 |
+
}
|