Model save
Browse files- README.md +62 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May14_11-30-56_gpu4-119-5/events.out.tfevents.1715650409.gpu4-119-5.1413115.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1346 -0
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-v18-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-v18-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 |
+
- num_devices: 2
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- total_eval_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- PEFT 0.7.1
|
| 59 |
+
- Transformers 4.36.2
|
| 60 |
+
- Pytorch 2.1.2+cu121
|
| 61 |
+
- Datasets 2.14.6
|
| 62 |
+
- 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 sha256:827feab1f3e7470b25caae192957a4fd52868fd96785df9437b87e1899bea6dd
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.06840609829860919,
|
| 4 |
+
"train_runtime": 2864.3388,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 10.474,
|
| 7 |
+
"train_steps_per_second": 0.327
|
| 8 |
+
}
|
runs/May14_11-30-56_gpu4-119-5/events.out.tfevents.1715650409.gpu4-119-5.1413115.0
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:af45a71d1a281ff8c26b10bc8a13010c2fc19c81b59e7f97359b82eff917ace8
|
| 3 |
+
size 19763
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.06840609829860919,
|
| 4 |
+
"train_runtime": 2864.3388,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 10.474,
|
| 7 |
+
"train_steps_per_second": 0.327
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9994666666666666,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 937,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5.319148936170213e-08,
|
| 14 |
+
"logits/chosen": 0.0328633114695549,
|
| 15 |
+
"logits/rejected": 0.22779616713523865,
|
| 16 |
+
"logps/chosen": -407.2765197753906,
|
| 17 |
+
"logps/rejected": -295.7368469238281,
|
| 18 |
+
"loss": 0.4178,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 5.319148936170213e-07,
|
| 28 |
+
"logits/chosen": 0.12644250690937042,
|
| 29 |
+
"logits/rejected": 0.25490710139274597,
|
| 30 |
+
"logps/chosen": -342.5318603515625,
|
| 31 |
+
"logps/rejected": -339.8170471191406,
|
| 32 |
+
"loss": 0.3561,
|
| 33 |
+
"rewards/accuracies": 0.4305555522441864,
|
| 34 |
+
"rewards/chosen": 2.7654659788822755e-05,
|
| 35 |
+
"rewards/margins": 8.612655801698565e-05,
|
| 36 |
+
"rewards/rejected": -5.84718982281629e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.11099036037921906,
|
| 43 |
+
"logits/rejected": 0.24831095337867737,
|
| 44 |
+
"logps/chosen": -378.44439697265625,
|
| 45 |
+
"logps/rejected": -353.71014404296875,
|
| 46 |
+
"loss": 0.3639,
|
| 47 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 48 |
+
"rewards/chosen": -4.667802568292245e-05,
|
| 49 |
+
"rewards/margins": -9.378789400216192e-05,
|
| 50 |
+
"rewards/rejected": 4.710986831923947e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.13326099514961243,
|
| 57 |
+
"logits/rejected": 0.1938765048980713,
|
| 58 |
+
"logps/chosen": -396.07440185546875,
|
| 59 |
+
"logps/rejected": -353.0478210449219,
|
| 60 |
+
"loss": 0.3768,
|
| 61 |
+
"rewards/accuracies": 0.518750011920929,
|
| 62 |
+
"rewards/chosen": 4.021604763693176e-05,
|
| 63 |
+
"rewards/margins": -1.0102905434905551e-05,
|
| 64 |
+
"rewards/rejected": 5.0318958528805524e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.15499012172222137,
|
| 71 |
+
"logits/rejected": 0.24013516306877136,
|
| 72 |
+
"logps/chosen": -357.16259765625,
|
| 73 |
+
"logps/rejected": -330.24609375,
|
| 74 |
+
"loss": 0.3838,
|
| 75 |
+
"rewards/accuracies": 0.46875,
|
| 76 |
+
"rewards/chosen": 5.2471255912678316e-05,
|
| 77 |
+
"rewards/margins": 0.00012843578588217497,
|
| 78 |
+
"rewards/rejected": -7.596451177960262e-05,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.08975875377655029,
|
| 85 |
+
"logits/rejected": 0.1924462616443634,
|
| 86 |
+
"logps/chosen": -360.7787780761719,
|
| 87 |
+
"logps/rejected": -345.1267395019531,
|
| 88 |
+
"loss": 0.3709,
|
| 89 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 90 |
+
"rewards/chosen": 0.00022406328935176134,
|
| 91 |
+
"rewards/margins": 0.0003413105441723019,
|
| 92 |
+
"rewards/rejected": -0.00011724724026862532,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.11686824262142181,
|
| 99 |
+
"logits/rejected": 0.2060682326555252,
|
| 100 |
+
"logps/chosen": -301.4020690917969,
|
| 101 |
+
"logps/rejected": -306.5481872558594,
|
| 102 |
+
"loss": 0.379,
|
| 103 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 104 |
+
"rewards/chosen": 0.0006540452013723552,
|
| 105 |
+
"rewards/margins": 0.001110218232497573,
|
| 106 |
+
"rewards/rejected": -0.00045617311843670905,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.061485785990953445,
|
| 113 |
+
"logits/rejected": 0.14367519319057465,
|
| 114 |
+
"logps/chosen": -309.8575134277344,
|
| 115 |
+
"logps/rejected": -319.0173645019531,
|
| 116 |
+
"loss": 0.3678,
|
| 117 |
+
"rewards/accuracies": 0.65625,
|
| 118 |
+
"rewards/chosen": 0.000993106747046113,
|
| 119 |
+
"rewards/margins": 0.0025861565954983234,
|
| 120 |
+
"rewards/rejected": -0.001593050197698176,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.08192186057567596,
|
| 127 |
+
"logits/rejected": 0.18210968375205994,
|
| 128 |
+
"logps/chosen": -313.7688293457031,
|
| 129 |
+
"logps/rejected": -354.7149658203125,
|
| 130 |
+
"loss": 0.3692,
|
| 131 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 132 |
+
"rewards/chosen": 0.0009643015218898654,
|
| 133 |
+
"rewards/margins": 0.005697316490113735,
|
| 134 |
+
"rewards/rejected": -0.004733014386147261,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.11128780990839005,
|
| 141 |
+
"logits/rejected": 0.16921164095401764,
|
| 142 |
+
"logps/chosen": -364.577392578125,
|
| 143 |
+
"logps/rejected": -352.7664489746094,
|
| 144 |
+
"loss": 0.372,
|
| 145 |
+
"rewards/accuracies": 0.625,
|
| 146 |
+
"rewards/chosen": -0.002881403313949704,
|
| 147 |
+
"rewards/margins": 0.005687831435352564,
|
| 148 |
+
"rewards/rejected": -0.008569234982132912,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.08404798805713654,
|
| 155 |
+
"logits/rejected": 0.17940422892570496,
|
| 156 |
+
"logps/chosen": -375.03900146484375,
|
| 157 |
+
"logps/rejected": -333.00775146484375,
|
| 158 |
+
"loss": 0.3432,
|
| 159 |
+
"rewards/accuracies": 0.65625,
|
| 160 |
+
"rewards/chosen": -0.0073157488368451595,
|
| 161 |
+
"rewards/margins": 0.015402473509311676,
|
| 162 |
+
"rewards/rejected": -0.022718224674463272,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.0811820849776268,
|
| 169 |
+
"logits/rejected": 0.12991295754909515,
|
| 170 |
+
"logps/chosen": -374.31103515625,
|
| 171 |
+
"logps/rejected": -350.5423278808594,
|
| 172 |
+
"loss": 0.3508,
|
| 173 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 174 |
+
"rewards/chosen": -0.02395443804562092,
|
| 175 |
+
"rewards/margins": 0.01998896151781082,
|
| 176 |
+
"rewards/rejected": -0.04394339770078659,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.07552331686019897,
|
| 183 |
+
"logits/rejected": 0.10529439151287079,
|
| 184 |
+
"logps/chosen": -385.13165283203125,
|
| 185 |
+
"logps/rejected": -430.96142578125,
|
| 186 |
+
"loss": 0.3218,
|
| 187 |
+
"rewards/accuracies": 0.637499988079071,
|
| 188 |
+
"rewards/chosen": -0.06972260773181915,
|
| 189 |
+
"rewards/margins": 0.05090062692761421,
|
| 190 |
+
"rewards/rejected": -0.12062324583530426,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.1114310622215271,
|
| 197 |
+
"logits/rejected": 0.16347981989383698,
|
| 198 |
+
"logps/chosen": -484.64544677734375,
|
| 199 |
+
"logps/rejected": -562.412109375,
|
| 200 |
+
"loss": 0.3292,
|
| 201 |
+
"rewards/accuracies": 0.6875,
|
| 202 |
+
"rewards/chosen": -0.13593843579292297,
|
| 203 |
+
"rewards/margins": 0.09484948217868805,
|
| 204 |
+
"rewards/rejected": -0.23078791797161102,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.12350474298000336,
|
| 211 |
+
"logits/rejected": 0.17375971376895905,
|
| 212 |
+
"logps/chosen": -554.6981201171875,
|
| 213 |
+
"logps/rejected": -652.0894775390625,
|
| 214 |
+
"loss": 0.3099,
|
| 215 |
+
"rewards/accuracies": 0.65625,
|
| 216 |
+
"rewards/chosen": -0.20147164165973663,
|
| 217 |
+
"rewards/margins": 0.13413165509700775,
|
| 218 |
+
"rewards/rejected": -0.3356032967567444,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.0980851799249649,
|
| 225 |
+
"logits/rejected": 0.21910460293293,
|
| 226 |
+
"logps/chosen": -511.48046875,
|
| 227 |
+
"logps/rejected": -560.3663940429688,
|
| 228 |
+
"loss": 0.3019,
|
| 229 |
+
"rewards/accuracies": 0.581250011920929,
|
| 230 |
+
"rewards/chosen": -0.1676788479089737,
|
| 231 |
+
"rewards/margins": 0.08112357556819916,
|
| 232 |
+
"rewards/rejected": -0.24880242347717285,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.06849007308483124,
|
| 239 |
+
"logits/rejected": 0.16746065020561218,
|
| 240 |
+
"logps/chosen": -522.7907104492188,
|
| 241 |
+
"logps/rejected": -604.654541015625,
|
| 242 |
+
"loss": 0.2982,
|
| 243 |
+
"rewards/accuracies": 0.675000011920929,
|
| 244 |
+
"rewards/chosen": -0.16378344595432281,
|
| 245 |
+
"rewards/margins": 0.10557951033115387,
|
| 246 |
+
"rewards/rejected": -0.2693629264831543,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.09706642478704453,
|
| 253 |
+
"logits/rejected": 0.22275814414024353,
|
| 254 |
+
"logps/chosen": -541.6332397460938,
|
| 255 |
+
"logps/rejected": -655.224609375,
|
| 256 |
+
"loss": 0.2733,
|
| 257 |
+
"rewards/accuracies": 0.768750011920929,
|
| 258 |
+
"rewards/chosen": -0.1621033251285553,
|
| 259 |
+
"rewards/margins": 0.12445729970932007,
|
| 260 |
+
"rewards/rejected": -0.286560595035553,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.14361754059791565,
|
| 267 |
+
"logits/rejected": 0.1780318021774292,
|
| 268 |
+
"logps/chosen": -505.50262451171875,
|
| 269 |
+
"logps/rejected": -618.1754760742188,
|
| 270 |
+
"loss": 0.2927,
|
| 271 |
+
"rewards/accuracies": 0.71875,
|
| 272 |
+
"rewards/chosen": -0.15032632648944855,
|
| 273 |
+
"rewards/margins": 0.1392049789428711,
|
| 274 |
+
"rewards/rejected": -0.28953129053115845,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.07448507845401764,
|
| 281 |
+
"logits/rejected": 0.11850146949291229,
|
| 282 |
+
"logps/chosen": -497.01702880859375,
|
| 283 |
+
"logps/rejected": -640.9612426757812,
|
| 284 |
+
"loss": 0.2788,
|
| 285 |
+
"rewards/accuracies": 0.75,
|
| 286 |
+
"rewards/chosen": -0.1675926297903061,
|
| 287 |
+
"rewards/margins": 0.15780577063560486,
|
| 288 |
+
"rewards/rejected": -0.32539841532707214,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.1496686488389969,
|
| 295 |
+
"logits/rejected": 0.15641534328460693,
|
| 296 |
+
"logps/chosen": -477.30438232421875,
|
| 297 |
+
"logps/rejected": -642.1568603515625,
|
| 298 |
+
"loss": 0.2886,
|
| 299 |
+
"rewards/accuracies": 0.6875,
|
| 300 |
+
"rewards/chosen": -0.18345065414905548,
|
| 301 |
+
"rewards/margins": 0.14235511422157288,
|
| 302 |
+
"rewards/rejected": -0.32580578327178955,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.029586156830191612,
|
| 309 |
+
"logits/rejected": 0.10910207033157349,
|
| 310 |
+
"logps/chosen": -545.3736572265625,
|
| 311 |
+
"logps/rejected": -619.1397705078125,
|
| 312 |
+
"loss": 0.3316,
|
| 313 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 314 |
+
"rewards/chosen": -0.2202235460281372,
|
| 315 |
+
"rewards/margins": 0.1027408093214035,
|
| 316 |
+
"rewards/rejected": -0.3229643702507019,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.07184920459985733,
|
| 323 |
+
"logits/rejected": 0.10738018900156021,
|
| 324 |
+
"logps/chosen": -551.0501708984375,
|
| 325 |
+
"logps/rejected": -633.4860229492188,
|
| 326 |
+
"loss": 0.2955,
|
| 327 |
+
"rewards/accuracies": 0.643750011920929,
|
| 328 |
+
"rewards/chosen": -0.21274058520793915,
|
| 329 |
+
"rewards/margins": 0.10448522865772247,
|
| 330 |
+
"rewards/rejected": -0.3172258138656616,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": 0.07210972160100937,
|
| 337 |
+
"logits/rejected": 0.15474052727222443,
|
| 338 |
+
"logps/chosen": -530.9338989257812,
|
| 339 |
+
"logps/rejected": -641.7281494140625,
|
| 340 |
+
"loss": 0.2748,
|
| 341 |
+
"rewards/accuracies": 0.731249988079071,
|
| 342 |
+
"rewards/chosen": -0.20435886085033417,
|
| 343 |
+
"rewards/margins": 0.1295766979455948,
|
| 344 |
+
"rewards/rejected": -0.33393555879592896,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": 0.1024290919303894,
|
| 351 |
+
"logits/rejected": 0.1865706890821457,
|
| 352 |
+
"logps/chosen": -584.1736450195312,
|
| 353 |
+
"logps/rejected": -625.4171142578125,
|
| 354 |
+
"loss": 0.309,
|
| 355 |
+
"rewards/accuracies": 0.643750011920929,
|
| 356 |
+
"rewards/chosen": -0.20201639831066132,
|
| 357 |
+
"rewards/margins": 0.09904564172029495,
|
| 358 |
+
"rewards/rejected": -0.30106204748153687,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": 0.02927372418344021,
|
| 365 |
+
"logits/rejected": 0.09811622649431229,
|
| 366 |
+
"logps/chosen": -533.7764892578125,
|
| 367 |
+
"logps/rejected": -629.5748901367188,
|
| 368 |
+
"loss": 0.2861,
|
| 369 |
+
"rewards/accuracies": 0.6875,
|
| 370 |
+
"rewards/chosen": -0.18896381556987762,
|
| 371 |
+
"rewards/margins": 0.11862628161907196,
|
| 372 |
+
"rewards/rejected": -0.3075900971889496,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": -0.005825365893542767,
|
| 379 |
+
"logits/rejected": 0.09718175232410431,
|
| 380 |
+
"logps/chosen": -493.98675537109375,
|
| 381 |
+
"logps/rejected": -583.2804565429688,
|
| 382 |
+
"loss": 0.2896,
|
| 383 |
+
"rewards/accuracies": 0.65625,
|
| 384 |
+
"rewards/chosen": -0.20344126224517822,
|
| 385 |
+
"rewards/margins": 0.09909246116876602,
|
| 386 |
+
"rewards/rejected": -0.30253371596336365,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": 0.044513873755931854,
|
| 393 |
+
"logits/rejected": 0.025778833776712418,
|
| 394 |
+
"logps/chosen": -558.865966796875,
|
| 395 |
+
"logps/rejected": -615.7289428710938,
|
| 396 |
+
"loss": 0.2943,
|
| 397 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 398 |
+
"rewards/chosen": -0.2074216902256012,
|
| 399 |
+
"rewards/margins": 0.11120656877756119,
|
| 400 |
+
"rewards/rejected": -0.3186282515525818,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": -0.028864026069641113,
|
| 407 |
+
"logits/rejected": 0.07541537284851074,
|
| 408 |
+
"logps/chosen": -592.0741577148438,
|
| 409 |
+
"logps/rejected": -668.5736083984375,
|
| 410 |
+
"loss": 0.3057,
|
| 411 |
+
"rewards/accuracies": 0.65625,
|
| 412 |
+
"rewards/chosen": -0.21832111477851868,
|
| 413 |
+
"rewards/margins": 0.11492238938808441,
|
| 414 |
+
"rewards/rejected": -0.3332434892654419,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": 0.0018409714102745056,
|
| 421 |
+
"logits/rejected": 0.11235576868057251,
|
| 422 |
+
"logps/chosen": -553.7425537109375,
|
| 423 |
+
"logps/rejected": -655.2655639648438,
|
| 424 |
+
"loss": 0.3027,
|
| 425 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 426 |
+
"rewards/chosen": -0.20998337864875793,
|
| 427 |
+
"rewards/margins": 0.11225197464227676,
|
| 428 |
+
"rewards/rejected": -0.3222353756427765,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": 0.02845548465847969,
|
| 435 |
+
"logits/rejected": 0.060444425791502,
|
| 436 |
+
"logps/chosen": -538.5903930664062,
|
| 437 |
+
"logps/rejected": -638.1737060546875,
|
| 438 |
+
"loss": 0.2801,
|
| 439 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 440 |
+
"rewards/chosen": -0.21026530861854553,
|
| 441 |
+
"rewards/margins": 0.11142082512378693,
|
| 442 |
+
"rewards/rejected": -0.32168611884117126,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": 0.03200574219226837,
|
| 449 |
+
"logits/rejected": 0.09657691419124603,
|
| 450 |
+
"logps/chosen": -566.3619995117188,
|
| 451 |
+
"logps/rejected": -676.0072631835938,
|
| 452 |
+
"loss": 0.2852,
|
| 453 |
+
"rewards/accuracies": 0.637499988079071,
|
| 454 |
+
"rewards/chosen": -0.209668830037117,
|
| 455 |
+
"rewards/margins": 0.10983745008707047,
|
| 456 |
+
"rewards/rejected": -0.3195062577724457,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": 0.009218290448188782,
|
| 463 |
+
"logits/rejected": 0.07068648189306259,
|
| 464 |
+
"logps/chosen": -493.89532470703125,
|
| 465 |
+
"logps/rejected": -595.8672485351562,
|
| 466 |
+
"loss": 0.2807,
|
| 467 |
+
"rewards/accuracies": 0.637499988079071,
|
| 468 |
+
"rewards/chosen": -0.19013245403766632,
|
| 469 |
+
"rewards/margins": 0.11394868791103363,
|
| 470 |
+
"rewards/rejected": -0.30408114194869995,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": 0.040950141847133636,
|
| 477 |
+
"logits/rejected": 0.15327873826026917,
|
| 478 |
+
"logps/chosen": -557.1869506835938,
|
| 479 |
+
"logps/rejected": -644.422119140625,
|
| 480 |
+
"loss": 0.286,
|
| 481 |
+
"rewards/accuracies": 0.637499988079071,
|
| 482 |
+
"rewards/chosen": -0.21056047081947327,
|
| 483 |
+
"rewards/margins": 0.11874810606241226,
|
| 484 |
+
"rewards/rejected": -0.32930856943130493,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": 0.05679699778556824,
|
| 491 |
+
"logits/rejected": 0.10968853533267975,
|
| 492 |
+
"logps/chosen": -576.4144287109375,
|
| 493 |
+
"logps/rejected": -666.2213745117188,
|
| 494 |
+
"loss": 0.2967,
|
| 495 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 496 |
+
"rewards/chosen": -0.23255427181720734,
|
| 497 |
+
"rewards/margins": 0.12515048682689667,
|
| 498 |
+
"rewards/rejected": -0.3577048182487488,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.06001776456832886,
|
| 505 |
+
"logits/rejected": 0.1731962114572525,
|
| 506 |
+
"logps/chosen": -578.7145385742188,
|
| 507 |
+
"logps/rejected": -695.6481323242188,
|
| 508 |
+
"loss": 0.2869,
|
| 509 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 510 |
+
"rewards/chosen": -0.23581092059612274,
|
| 511 |
+
"rewards/margins": 0.13799193501472473,
|
| 512 |
+
"rewards/rejected": -0.37380287051200867,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": 0.12720148265361786,
|
| 519 |
+
"logits/rejected": 0.11129485070705414,
|
| 520 |
+
"logps/chosen": -585.1661376953125,
|
| 521 |
+
"logps/rejected": -674.7999877929688,
|
| 522 |
+
"loss": 0.2751,
|
| 523 |
+
"rewards/accuracies": 0.637499988079071,
|
| 524 |
+
"rewards/chosen": -0.24305827915668488,
|
| 525 |
+
"rewards/margins": 0.1303601711988449,
|
| 526 |
+
"rewards/rejected": -0.3734184205532074,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": 0.046785108745098114,
|
| 533 |
+
"logits/rejected": 0.12497253715991974,
|
| 534 |
+
"logps/chosen": -613.0939331054688,
|
| 535 |
+
"logps/rejected": -778.9556274414062,
|
| 536 |
+
"loss": 0.2816,
|
| 537 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 538 |
+
"rewards/chosen": -0.26795250177383423,
|
| 539 |
+
"rewards/margins": 0.17298182845115662,
|
| 540 |
+
"rewards/rejected": -0.44093433022499084,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": -0.016536608338356018,
|
| 547 |
+
"logits/rejected": 0.08203241974115372,
|
| 548 |
+
"logps/chosen": -619.8163452148438,
|
| 549 |
+
"logps/rejected": -756.1831665039062,
|
| 550 |
+
"loss": 0.2809,
|
| 551 |
+
"rewards/accuracies": 0.737500011920929,
|
| 552 |
+
"rewards/chosen": -0.28122490644454956,
|
| 553 |
+
"rewards/margins": 0.1667798012495041,
|
| 554 |
+
"rewards/rejected": -0.44800466299057007,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": -0.013438811525702477,
|
| 561 |
+
"logits/rejected": 0.056597866117954254,
|
| 562 |
+
"logps/chosen": -660.5250244140625,
|
| 563 |
+
"logps/rejected": -809.8643798828125,
|
| 564 |
+
"loss": 0.2683,
|
| 565 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 566 |
+
"rewards/chosen": -0.30733537673950195,
|
| 567 |
+
"rewards/margins": 0.1618378460407257,
|
| 568 |
+
"rewards/rejected": -0.46917325258255005,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": 0.033776335418224335,
|
| 575 |
+
"logits/rejected": 0.08476515114307404,
|
| 576 |
+
"logps/chosen": -612.4915161132812,
|
| 577 |
+
"logps/rejected": -791.068603515625,
|
| 578 |
+
"loss": 0.2687,
|
| 579 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 580 |
+
"rewards/chosen": -0.298635333776474,
|
| 581 |
+
"rewards/margins": 0.14923743903636932,
|
| 582 |
+
"rewards/rejected": -0.4478727877140045,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": 0.04248402267694473,
|
| 589 |
+
"logits/rejected": 0.13372144103050232,
|
| 590 |
+
"logps/chosen": -653.1471557617188,
|
| 591 |
+
"logps/rejected": -754.6251831054688,
|
| 592 |
+
"loss": 0.2659,
|
| 593 |
+
"rewards/accuracies": 0.706250011920929,
|
| 594 |
+
"rewards/chosen": -0.30667322874069214,
|
| 595 |
+
"rewards/margins": 0.1425372064113617,
|
| 596 |
+
"rewards/rejected": -0.4492104649543762,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": 0.016178572550415993,
|
| 603 |
+
"logits/rejected": 0.09873557835817337,
|
| 604 |
+
"logps/chosen": -632.523193359375,
|
| 605 |
+
"logps/rejected": -767.3197021484375,
|
| 606 |
+
"loss": 0.2715,
|
| 607 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 608 |
+
"rewards/chosen": -0.28947144746780396,
|
| 609 |
+
"rewards/margins": 0.1752663552761078,
|
| 610 |
+
"rewards/rejected": -0.46473783254623413,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": 0.010262581519782543,
|
| 617 |
+
"logits/rejected": 0.09065081179141998,
|
| 618 |
+
"logps/chosen": -607.0426025390625,
|
| 619 |
+
"logps/rejected": -816.6497192382812,
|
| 620 |
+
"loss": 0.2543,
|
| 621 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 622 |
+
"rewards/chosen": -0.3082737326622009,
|
| 623 |
+
"rewards/margins": 0.19562499225139618,
|
| 624 |
+
"rewards/rejected": -0.5038987398147583,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": 0.03939592093229294,
|
| 631 |
+
"logits/rejected": 0.051005780696868896,
|
| 632 |
+
"logps/chosen": -630.1431884765625,
|
| 633 |
+
"logps/rejected": -726.6351318359375,
|
| 634 |
+
"loss": 0.2793,
|
| 635 |
+
"rewards/accuracies": 0.65625,
|
| 636 |
+
"rewards/chosen": -0.28141292929649353,
|
| 637 |
+
"rewards/margins": 0.13616052269935608,
|
| 638 |
+
"rewards/rejected": -0.4175735116004944,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": 0.03237801790237427,
|
| 645 |
+
"logits/rejected": 0.128599613904953,
|
| 646 |
+
"logps/chosen": -699.2102661132812,
|
| 647 |
+
"logps/rejected": -776.4459228515625,
|
| 648 |
+
"loss": 0.2784,
|
| 649 |
+
"rewards/accuracies": 0.737500011920929,
|
| 650 |
+
"rewards/chosen": -0.2957838177680969,
|
| 651 |
+
"rewards/margins": 0.1545422077178955,
|
| 652 |
+
"rewards/rejected": -0.4503260552883148,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": -0.011108310893177986,
|
| 659 |
+
"logits/rejected": 0.0545300655066967,
|
| 660 |
+
"logps/chosen": -605.3892822265625,
|
| 661 |
+
"logps/rejected": -729.7080078125,
|
| 662 |
+
"loss": 0.3022,
|
| 663 |
+
"rewards/accuracies": 0.6875,
|
| 664 |
+
"rewards/chosen": -0.27824196219444275,
|
| 665 |
+
"rewards/margins": 0.1415918618440628,
|
| 666 |
+
"rewards/rejected": -0.41983380913734436,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": -0.010739525780081749,
|
| 673 |
+
"logits/rejected": 0.1061888337135315,
|
| 674 |
+
"logps/chosen": -675.0782470703125,
|
| 675 |
+
"logps/rejected": -811.0116577148438,
|
| 676 |
+
"loss": 0.2543,
|
| 677 |
+
"rewards/accuracies": 0.75,
|
| 678 |
+
"rewards/chosen": -0.32911890745162964,
|
| 679 |
+
"rewards/margins": 0.14946062862873077,
|
| 680 |
+
"rewards/rejected": -0.4785795211791992,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": -0.007434132508933544,
|
| 687 |
+
"logits/rejected": 0.005777590908110142,
|
| 688 |
+
"logps/chosen": -675.082275390625,
|
| 689 |
+
"logps/rejected": -852.5006103515625,
|
| 690 |
+
"loss": 0.2821,
|
| 691 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 692 |
+
"rewards/chosen": -0.3303678631782532,
|
| 693 |
+
"rewards/margins": 0.17629772424697876,
|
| 694 |
+
"rewards/rejected": -0.5066655874252319,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": -0.010230760090053082,
|
| 701 |
+
"logits/rejected": 0.06991882622241974,
|
| 702 |
+
"logps/chosen": -657.92919921875,
|
| 703 |
+
"logps/rejected": -769.2183227539062,
|
| 704 |
+
"loss": 0.2732,
|
| 705 |
+
"rewards/accuracies": 0.675000011920929,
|
| 706 |
+
"rewards/chosen": -0.29096969962120056,
|
| 707 |
+
"rewards/margins": 0.1650645136833191,
|
| 708 |
+
"rewards/rejected": -0.45603418350219727,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": 0.010941145941615105,
|
| 715 |
+
"logits/rejected": 0.06464840471744537,
|
| 716 |
+
"logps/chosen": -660.7554931640625,
|
| 717 |
+
"logps/rejected": -808.1925048828125,
|
| 718 |
+
"loss": 0.2525,
|
| 719 |
+
"rewards/accuracies": 0.737500011920929,
|
| 720 |
+
"rewards/chosen": -0.3170284628868103,
|
| 721 |
+
"rewards/margins": 0.16747084259986877,
|
| 722 |
+
"rewards/rejected": -0.4844993054866791,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": 0.01938098482787609,
|
| 729 |
+
"logits/rejected": 0.10472504049539566,
|
| 730 |
+
"logps/chosen": -665.8427734375,
|
| 731 |
+
"logps/rejected": -784.5371704101562,
|
| 732 |
+
"loss": 0.2657,
|
| 733 |
+
"rewards/accuracies": 0.675000011920929,
|
| 734 |
+
"rewards/chosen": -0.29728442430496216,
|
| 735 |
+
"rewards/margins": 0.14796006679534912,
|
| 736 |
+
"rewards/rejected": -0.4452444911003113,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": 0.014335828833281994,
|
| 743 |
+
"logits/rejected": 0.10104580968618393,
|
| 744 |
+
"logps/chosen": -667.510986328125,
|
| 745 |
+
"logps/rejected": -799.0164794921875,
|
| 746 |
+
"loss": 0.2633,
|
| 747 |
+
"rewards/accuracies": 0.706250011920929,
|
| 748 |
+
"rewards/chosen": -0.30110082030296326,
|
| 749 |
+
"rewards/margins": 0.16439731419086456,
|
| 750 |
+
"rewards/rejected": -0.4654981195926666,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": 0.028812021017074585,
|
| 757 |
+
"logits/rejected": 0.09060634672641754,
|
| 758 |
+
"logps/chosen": -620.7320556640625,
|
| 759 |
+
"logps/rejected": -778.6414184570312,
|
| 760 |
+
"loss": 0.2401,
|
| 761 |
+
"rewards/accuracies": 0.737500011920929,
|
| 762 |
+
"rewards/chosen": -0.2825697362422943,
|
| 763 |
+
"rewards/margins": 0.1802894026041031,
|
| 764 |
+
"rewards/rejected": -0.4628591537475586,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.015088727697730064,
|
| 771 |
+
"logits/rejected": 0.08517689257860184,
|
| 772 |
+
"logps/chosen": -646.2489013671875,
|
| 773 |
+
"logps/rejected": -777.7031860351562,
|
| 774 |
+
"loss": 0.261,
|
| 775 |
+
"rewards/accuracies": 0.71875,
|
| 776 |
+
"rewards/chosen": -0.2979923486709595,
|
| 777 |
+
"rewards/margins": 0.16907855868339539,
|
| 778 |
+
"rewards/rejected": -0.46707090735435486,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": 0.0029529170133173466,
|
| 785 |
+
"logits/rejected": 0.08159308135509491,
|
| 786 |
+
"logps/chosen": -626.0859985351562,
|
| 787 |
+
"logps/rejected": -760.864990234375,
|
| 788 |
+
"loss": 0.2519,
|
| 789 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 790 |
+
"rewards/chosen": -0.2840486168861389,
|
| 791 |
+
"rewards/margins": 0.16967108845710754,
|
| 792 |
+
"rewards/rejected": -0.4537196755409241,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": 0.04737887904047966,
|
| 799 |
+
"logits/rejected": 0.09217114746570587,
|
| 800 |
+
"logps/chosen": -670.5003662109375,
|
| 801 |
+
"logps/rejected": -781.8992309570312,
|
| 802 |
+
"loss": 0.2568,
|
| 803 |
+
"rewards/accuracies": 0.668749988079071,
|
| 804 |
+
"rewards/chosen": -0.3173016309738159,
|
| 805 |
+
"rewards/margins": 0.15325884521007538,
|
| 806 |
+
"rewards/rejected": -0.4705604612827301,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": 0.05551145225763321,
|
| 813 |
+
"logits/rejected": 0.07084596157073975,
|
| 814 |
+
"logps/chosen": -708.875732421875,
|
| 815 |
+
"logps/rejected": -875.9669189453125,
|
| 816 |
+
"loss": 0.2604,
|
| 817 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 818 |
+
"rewards/chosen": -0.3540639579296112,
|
| 819 |
+
"rewards/margins": 0.1768617331981659,
|
| 820 |
+
"rewards/rejected": -0.5309256315231323,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": 0.05049177259206772,
|
| 827 |
+
"logits/rejected": 0.09144983440637589,
|
| 828 |
+
"logps/chosen": -662.368896484375,
|
| 829 |
+
"logps/rejected": -762.068359375,
|
| 830 |
+
"loss": 0.2818,
|
| 831 |
+
"rewards/accuracies": 0.699999988079071,
|
| 832 |
+
"rewards/chosen": -0.2937859892845154,
|
| 833 |
+
"rewards/margins": 0.15120849013328552,
|
| 834 |
+
"rewards/rejected": -0.4449945092201233,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": 0.013850146904587746,
|
| 841 |
+
"logits/rejected": 0.08181043714284897,
|
| 842 |
+
"logps/chosen": -655.6898193359375,
|
| 843 |
+
"logps/rejected": -799.6488037109375,
|
| 844 |
+
"loss": 0.2732,
|
| 845 |
+
"rewards/accuracies": 0.6875,
|
| 846 |
+
"rewards/chosen": -0.2904633581638336,
|
| 847 |
+
"rewards/margins": 0.16650694608688354,
|
| 848 |
+
"rewards/rejected": -0.45697030425071716,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": 0.026665305718779564,
|
| 855 |
+
"logits/rejected": 0.10492020845413208,
|
| 856 |
+
"logps/chosen": -667.7979736328125,
|
| 857 |
+
"logps/rejected": -860.6505737304688,
|
| 858 |
+
"loss": 0.2529,
|
| 859 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 860 |
+
"rewards/chosen": -0.2826516032218933,
|
| 861 |
+
"rewards/margins": 0.18477080762386322,
|
| 862 |
+
"rewards/rejected": -0.4674224257469177,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": 0.04557771235704422,
|
| 869 |
+
"logits/rejected": 0.06558578461408615,
|
| 870 |
+
"logps/chosen": -630.7008056640625,
|
| 871 |
+
"logps/rejected": -797.5521240234375,
|
| 872 |
+
"loss": 0.2553,
|
| 873 |
+
"rewards/accuracies": 0.75,
|
| 874 |
+
"rewards/chosen": -0.29132452607154846,
|
| 875 |
+
"rewards/margins": 0.18406057357788086,
|
| 876 |
+
"rewards/rejected": -0.4753850996494293,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": 0.0122049106284976,
|
| 883 |
+
"logits/rejected": 0.05510292202234268,
|
| 884 |
+
"logps/chosen": -702.2847900390625,
|
| 885 |
+
"logps/rejected": -777.2984619140625,
|
| 886 |
+
"loss": 0.2793,
|
| 887 |
+
"rewards/accuracies": 0.6875,
|
| 888 |
+
"rewards/chosen": -0.32928770780563354,
|
| 889 |
+
"rewards/margins": 0.15212389826774597,
|
| 890 |
+
"rewards/rejected": -0.4814116060733795,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": 0.027809197083115578,
|
| 897 |
+
"logits/rejected": 0.12329945713281631,
|
| 898 |
+
"logps/chosen": -693.8055419921875,
|
| 899 |
+
"logps/rejected": -849.8357543945312,
|
| 900 |
+
"loss": 0.2712,
|
| 901 |
+
"rewards/accuracies": 0.6875,
|
| 902 |
+
"rewards/chosen": -0.3381686210632324,
|
| 903 |
+
"rewards/margins": 0.15602417290210724,
|
| 904 |
+
"rewards/rejected": -0.4941927492618561,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": 0.018910501152276993,
|
| 911 |
+
"logits/rejected": 0.06395964324474335,
|
| 912 |
+
"logps/chosen": -668.9143676757812,
|
| 913 |
+
"logps/rejected": -784.6621704101562,
|
| 914 |
+
"loss": 0.304,
|
| 915 |
+
"rewards/accuracies": 0.637499988079071,
|
| 916 |
+
"rewards/chosen": -0.3322431445121765,
|
| 917 |
+
"rewards/margins": 0.13410837948322296,
|
| 918 |
+
"rewards/rejected": -0.4663515090942383,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": 0.032313134521245956,
|
| 925 |
+
"logits/rejected": 0.09517451375722885,
|
| 926 |
+
"logps/chosen": -650.8678588867188,
|
| 927 |
+
"logps/rejected": -775.7073974609375,
|
| 928 |
+
"loss": 0.2671,
|
| 929 |
+
"rewards/accuracies": 0.6875,
|
| 930 |
+
"rewards/chosen": -0.302242636680603,
|
| 931 |
+
"rewards/margins": 0.15537433326244354,
|
| 932 |
+
"rewards/rejected": -0.45761698484420776,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": -0.0034284330904483795,
|
| 939 |
+
"logits/rejected": 0.08462049067020416,
|
| 940 |
+
"logps/chosen": -646.4454345703125,
|
| 941 |
+
"logps/rejected": -803.33056640625,
|
| 942 |
+
"loss": 0.2708,
|
| 943 |
+
"rewards/accuracies": 0.737500011920929,
|
| 944 |
+
"rewards/chosen": -0.3094111979007721,
|
| 945 |
+
"rewards/margins": 0.16766026616096497,
|
| 946 |
+
"rewards/rejected": -0.47707146406173706,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": 0.01865808106958866,
|
| 953 |
+
"logits/rejected": 0.07240469753742218,
|
| 954 |
+
"logps/chosen": -656.0631103515625,
|
| 955 |
+
"logps/rejected": -819.2371826171875,
|
| 956 |
+
"loss": 0.2438,
|
| 957 |
+
"rewards/accuracies": 0.706250011920929,
|
| 958 |
+
"rewards/chosen": -0.31997841596603394,
|
| 959 |
+
"rewards/margins": 0.1749737411737442,
|
| 960 |
+
"rewards/rejected": -0.49495214223861694,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": 0.007644282188266516,
|
| 967 |
+
"logits/rejected": 0.12147297710180283,
|
| 968 |
+
"logps/chosen": -666.0787353515625,
|
| 969 |
+
"logps/rejected": -814.1128540039062,
|
| 970 |
+
"loss": 0.27,
|
| 971 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 972 |
+
"rewards/chosen": -0.31804323196411133,
|
| 973 |
+
"rewards/margins": 0.1811751127243042,
|
| 974 |
+
"rewards/rejected": -0.49921831488609314,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": 0.002938181161880493,
|
| 981 |
+
"logits/rejected": 0.05325765162706375,
|
| 982 |
+
"logps/chosen": -659.8150634765625,
|
| 983 |
+
"logps/rejected": -826.27294921875,
|
| 984 |
+
"loss": 0.2679,
|
| 985 |
+
"rewards/accuracies": 0.706250011920929,
|
| 986 |
+
"rewards/chosen": -0.33443090319633484,
|
| 987 |
+
"rewards/margins": 0.17140033841133118,
|
| 988 |
+
"rewards/rejected": -0.505831241607666,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": 0.009498851373791695,
|
| 995 |
+
"logits/rejected": 0.10675854980945587,
|
| 996 |
+
"logps/chosen": -641.385986328125,
|
| 997 |
+
"logps/rejected": -772.0265502929688,
|
| 998 |
+
"loss": 0.2745,
|
| 999 |
+
"rewards/accuracies": 0.625,
|
| 1000 |
+
"rewards/chosen": -0.33288660645484924,
|
| 1001 |
+
"rewards/margins": 0.14625254273414612,
|
| 1002 |
+
"rewards/rejected": -0.47913914918899536,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": 0.01779480278491974,
|
| 1009 |
+
"logits/rejected": 0.06852717697620392,
|
| 1010 |
+
"logps/chosen": -658.0755615234375,
|
| 1011 |
+
"logps/rejected": -790.7129516601562,
|
| 1012 |
+
"loss": 0.2472,
|
| 1013 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1014 |
+
"rewards/chosen": -0.3279511630535126,
|
| 1015 |
+
"rewards/margins": 0.15394431352615356,
|
| 1016 |
+
"rewards/rejected": -0.48189544677734375,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": -0.008415929041802883,
|
| 1023 |
+
"logits/rejected": 0.025492772459983826,
|
| 1024 |
+
"logps/chosen": -639.2633056640625,
|
| 1025 |
+
"logps/rejected": -759.4827880859375,
|
| 1026 |
+
"loss": 0.2888,
|
| 1027 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1028 |
+
"rewards/chosen": -0.31683486700057983,
|
| 1029 |
+
"rewards/margins": 0.16635778546333313,
|
| 1030 |
+
"rewards/rejected": -0.48319268226623535,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": 0.036400362849235535,
|
| 1037 |
+
"logits/rejected": 0.06037065386772156,
|
| 1038 |
+
"logps/chosen": -635.8643798828125,
|
| 1039 |
+
"logps/rejected": -806.2174072265625,
|
| 1040 |
+
"loss": 0.2624,
|
| 1041 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1042 |
+
"rewards/chosen": -0.3112700879573822,
|
| 1043 |
+
"rewards/margins": 0.17294862866401672,
|
| 1044 |
+
"rewards/rejected": -0.48421868681907654,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": 0.006747276522219181,
|
| 1051 |
+
"logits/rejected": 0.036448314785957336,
|
| 1052 |
+
"logps/chosen": -682.7285766601562,
|
| 1053 |
+
"logps/rejected": -770.6795654296875,
|
| 1054 |
+
"loss": 0.2916,
|
| 1055 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1056 |
+
"rewards/chosen": -0.3282105326652527,
|
| 1057 |
+
"rewards/margins": 0.13396592438220978,
|
| 1058 |
+
"rewards/rejected": -0.46217647194862366,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": -0.008215249516069889,
|
| 1065 |
+
"logits/rejected": 0.039237380027770996,
|
| 1066 |
+
"logps/chosen": -615.4769897460938,
|
| 1067 |
+
"logps/rejected": -744.2301025390625,
|
| 1068 |
+
"loss": 0.2858,
|
| 1069 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 1070 |
+
"rewards/chosen": -0.31000182032585144,
|
| 1071 |
+
"rewards/margins": 0.12073155492544174,
|
| 1072 |
+
"rewards/rejected": -0.43073344230651855,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": -0.018334541469812393,
|
| 1079 |
+
"logits/rejected": 0.0751979798078537,
|
| 1080 |
+
"logps/chosen": -653.4116821289062,
|
| 1081 |
+
"logps/rejected": -775.2245483398438,
|
| 1082 |
+
"loss": 0.2744,
|
| 1083 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1084 |
+
"rewards/chosen": -0.3128724694252014,
|
| 1085 |
+
"rewards/margins": 0.16823306679725647,
|
| 1086 |
+
"rewards/rejected": -0.4811055064201355,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": -0.01749856024980545,
|
| 1093 |
+
"logits/rejected": 0.0061824568547308445,
|
| 1094 |
+
"logps/chosen": -671.5619506835938,
|
| 1095 |
+
"logps/rejected": -798.6920776367188,
|
| 1096 |
+
"loss": 0.2781,
|
| 1097 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1098 |
+
"rewards/chosen": -0.32307571172714233,
|
| 1099 |
+
"rewards/margins": 0.15197516977787018,
|
| 1100 |
+
"rewards/rejected": -0.4750508666038513,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": -0.031299591064453125,
|
| 1107 |
+
"logits/rejected": 0.11445782333612442,
|
| 1108 |
+
"logps/chosen": -633.4989624023438,
|
| 1109 |
+
"logps/rejected": -759.5948486328125,
|
| 1110 |
+
"loss": 0.276,
|
| 1111 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1112 |
+
"rewards/chosen": -0.2988068461418152,
|
| 1113 |
+
"rewards/margins": 0.14791473746299744,
|
| 1114 |
+
"rewards/rejected": -0.446721613407135,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": 0.01681383140385151,
|
| 1121 |
+
"logits/rejected": 0.06748757511377335,
|
| 1122 |
+
"logps/chosen": -703.5291748046875,
|
| 1123 |
+
"logps/rejected": -790.0008544921875,
|
| 1124 |
+
"loss": 0.2645,
|
| 1125 |
+
"rewards/accuracies": 0.71875,
|
| 1126 |
+
"rewards/chosen": -0.3278062641620636,
|
| 1127 |
+
"rewards/margins": 0.1466275155544281,
|
| 1128 |
+
"rewards/rejected": -0.4744337499141693,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": -0.006874733604490757,
|
| 1135 |
+
"logits/rejected": 0.09821389615535736,
|
| 1136 |
+
"logps/chosen": -696.3887939453125,
|
| 1137 |
+
"logps/rejected": -831.1228637695312,
|
| 1138 |
+
"loss": 0.2456,
|
| 1139 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1140 |
+
"rewards/chosen": -0.31410273909568787,
|
| 1141 |
+
"rewards/margins": 0.19106796383857727,
|
| 1142 |
+
"rewards/rejected": -0.5051707029342651,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": 0.02232988551259041,
|
| 1149 |
+
"logits/rejected": 0.11882144212722778,
|
| 1150 |
+
"logps/chosen": -737.1534423828125,
|
| 1151 |
+
"logps/rejected": -799.8753662109375,
|
| 1152 |
+
"loss": 0.2901,
|
| 1153 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1154 |
+
"rewards/chosen": -0.3397114872932434,
|
| 1155 |
+
"rewards/margins": 0.11829358339309692,
|
| 1156 |
+
"rewards/rejected": -0.45800504088401794,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": -0.005960514303296804,
|
| 1163 |
+
"logits/rejected": 0.08128391206264496,
|
| 1164 |
+
"logps/chosen": -600.1956787109375,
|
| 1165 |
+
"logps/rejected": -725.2703857421875,
|
| 1166 |
+
"loss": 0.2618,
|
| 1167 |
+
"rewards/accuracies": 0.6875,
|
| 1168 |
+
"rewards/chosen": -0.28923314809799194,
|
| 1169 |
+
"rewards/margins": 0.14518693089485168,
|
| 1170 |
+
"rewards/rejected": -0.43442004919052124,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": -0.027128243818879128,
|
| 1177 |
+
"logits/rejected": 0.08068221807479858,
|
| 1178 |
+
"logps/chosen": -648.6610107421875,
|
| 1179 |
+
"logps/rejected": -814.8963012695312,
|
| 1180 |
+
"loss": 0.2565,
|
| 1181 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1182 |
+
"rewards/chosen": -0.31799566745758057,
|
| 1183 |
+
"rewards/margins": 0.18419261276721954,
|
| 1184 |
+
"rewards/rejected": -0.5021882653236389,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": 0.04195733740925789,
|
| 1191 |
+
"logits/rejected": 0.05591679736971855,
|
| 1192 |
+
"logps/chosen": -618.9046630859375,
|
| 1193 |
+
"logps/rejected": -764.7545776367188,
|
| 1194 |
+
"loss": 0.2554,
|
| 1195 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1196 |
+
"rewards/chosen": -0.3056134879589081,
|
| 1197 |
+
"rewards/margins": 0.1550132781267166,
|
| 1198 |
+
"rewards/rejected": -0.4606267511844635,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": 0.007567937020212412,
|
| 1205 |
+
"logits/rejected": 0.08190431445837021,
|
| 1206 |
+
"logps/chosen": -702.777587890625,
|
| 1207 |
+
"logps/rejected": -844.9808349609375,
|
| 1208 |
+
"loss": 0.2738,
|
| 1209 |
+
"rewards/accuracies": 0.75,
|
| 1210 |
+
"rewards/chosen": -0.33942800760269165,
|
| 1211 |
+
"rewards/margins": 0.16622349619865417,
|
| 1212 |
+
"rewards/rejected": -0.5056515336036682,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": -0.011982535012066364,
|
| 1219 |
+
"logits/rejected": 0.029620468616485596,
|
| 1220 |
+
"logps/chosen": -671.661865234375,
|
| 1221 |
+
"logps/rejected": -762.5552978515625,
|
| 1222 |
+
"loss": 0.297,
|
| 1223 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1224 |
+
"rewards/chosen": -0.355450838804245,
|
| 1225 |
+
"rewards/margins": 0.11624264717102051,
|
| 1226 |
+
"rewards/rejected": -0.4716935157775879,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": -0.010390078648924828,
|
| 1233 |
+
"logits/rejected": 0.059226177632808685,
|
| 1234 |
+
"logps/chosen": -709.0919189453125,
|
| 1235 |
+
"logps/rejected": -846.7449340820312,
|
| 1236 |
+
"loss": 0.296,
|
| 1237 |
+
"rewards/accuracies": 0.71875,
|
| 1238 |
+
"rewards/chosen": -0.3520728349685669,
|
| 1239 |
+
"rewards/margins": 0.14244066178798676,
|
| 1240 |
+
"rewards/rejected": -0.49451351165771484,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": 0.030358577147126198,
|
| 1247 |
+
"logits/rejected": 0.1358805149793625,
|
| 1248 |
+
"logps/chosen": -658.2210693359375,
|
| 1249 |
+
"logps/rejected": -764.5792236328125,
|
| 1250 |
+
"loss": 0.2756,
|
| 1251 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1252 |
+
"rewards/chosen": -0.31784769892692566,
|
| 1253 |
+
"rewards/margins": 0.1385163813829422,
|
| 1254 |
+
"rewards/rejected": -0.45636409521102905,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": 0.07536911964416504,
|
| 1261 |
+
"logits/rejected": 0.11495663970708847,
|
| 1262 |
+
"logps/chosen": -674.4959716796875,
|
| 1263 |
+
"logps/rejected": -830.2818603515625,
|
| 1264 |
+
"loss": 0.2589,
|
| 1265 |
+
"rewards/accuracies": 0.59375,
|
| 1266 |
+
"rewards/chosen": -0.32807761430740356,
|
| 1267 |
+
"rewards/margins": 0.15293636918067932,
|
| 1268 |
+
"rewards/rejected": -0.48101386427879333,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": 0.015253638848662376,
|
| 1275 |
+
"logits/rejected": 0.014745418913662434,
|
| 1276 |
+
"logps/chosen": -697.5753173828125,
|
| 1277 |
+
"logps/rejected": -841.8138427734375,
|
| 1278 |
+
"loss": 0.2527,
|
| 1279 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1280 |
+
"rewards/chosen": -0.33767208456993103,
|
| 1281 |
+
"rewards/margins": 0.15997497737407684,
|
| 1282 |
+
"rewards/rejected": -0.4976470470428467,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": 0.04343446344137192,
|
| 1289 |
+
"logits/rejected": 0.05051248520612717,
|
| 1290 |
+
"logps/chosen": -659.9283447265625,
|
| 1291 |
+
"logps/rejected": -793.960205078125,
|
| 1292 |
+
"loss": 0.2637,
|
| 1293 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1294 |
+
"rewards/chosen": -0.3193858563899994,
|
| 1295 |
+
"rewards/margins": 0.15680603682994843,
|
| 1296 |
+
"rewards/rejected": -0.4761919379234314,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": -0.0020548023749142885,
|
| 1303 |
+
"logits/rejected": 0.06288515031337738,
|
| 1304 |
+
"logps/chosen": -699.4730224609375,
|
| 1305 |
+
"logps/rejected": -794.502197265625,
|
| 1306 |
+
"loss": 0.268,
|
| 1307 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1308 |
+
"rewards/chosen": -0.34633034467697144,
|
| 1309 |
+
"rewards/margins": 0.136570543050766,
|
| 1310 |
+
"rewards/rejected": -0.48290085792541504,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": 0.013004904612898827,
|
| 1317 |
+
"logits/rejected": 0.07795099914073944,
|
| 1318 |
+
"logps/chosen": -636.2744750976562,
|
| 1319 |
+
"logps/rejected": -769.828125,
|
| 1320 |
+
"loss": 0.264,
|
| 1321 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1322 |
+
"rewards/chosen": -0.2970486283302307,
|
| 1323 |
+
"rewards/margins": 0.1587102711200714,
|
| 1324 |
+
"rewards/rejected": -0.4557588994503021,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.06840609829860919,
|
| 1332 |
+
"train_runtime": 2864.3388,
|
| 1333 |
+
"train_samples_per_second": 10.474,
|
| 1334 |
+
"train_steps_per_second": 0.327
|
| 1335 |
+
}
|
| 1336 |
+
],
|
| 1337 |
+
"logging_steps": 10,
|
| 1338 |
+
"max_steps": 937,
|
| 1339 |
+
"num_input_tokens_seen": 0,
|
| 1340 |
+
"num_train_epochs": 1,
|
| 1341 |
+
"save_steps": 100,
|
| 1342 |
+
"total_flos": 0.0,
|
| 1343 |
+
"train_batch_size": 4,
|
| 1344 |
+
"trial_name": null,
|
| 1345 |
+
"trial_params": null
|
| 1346 |
+
}
|