Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May22_05-56-37_gpu4-119-5/events.out.tfevents.1716321797.gpu4-119-5.2390651.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1346 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-v1-i1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-irepo-chatml-v2-i2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# phi-2-irepo-chatml-v2-i2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-v1-i1](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-v1-i1) on the None dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 2
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- total_eval_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.7.1
|
| 58 |
+
- Transformers 4.36.2
|
| 59 |
+
- Pytorch 2.1.2+cu121
|
| 60 |
+
- Datasets 2.14.6
|
| 61 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335579632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dca02a912a41164e9d981a05812e54364bec0737d14f1d7ed76579e2bd84c91d
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1892308688214647,
|
| 4 |
+
"train_runtime": 7960.6994,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.769,
|
| 7 |
+
"train_steps_per_second": 0.118
|
| 8 |
+
}
|
runs/May22_05-56-37_gpu4-119-5/events.out.tfevents.1716321797.gpu4-119-5.2390651.0
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:ba50f1668af3290f0aeac70d6aa4d6fac176549c2fa721344a29569d8ba15813
|
| 3 |
+
size 64719
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.1892308688214647,
|
| 4 |
+
"train_runtime": 7960.6994,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.769,
|
| 7 |
+
"train_steps_per_second": 0.118
|
| 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": -0.07764632999897003,
|
| 15 |
+
"logits/rejected": 0.0654495358467102,
|
| 16 |
+
"logps/chosen": -548.1927490234375,
|
| 17 |
+
"logps/rejected": -445.62200927734375,
|
| 18 |
+
"loss": 0.21,
|
| 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": 0.013010119087994099,
|
| 29 |
+
"logits/rejected": 0.14687097072601318,
|
| 30 |
+
"logps/chosen": -445.48004150390625,
|
| 31 |
+
"logps/rejected": -474.8713073730469,
|
| 32 |
+
"loss": 0.2064,
|
| 33 |
+
"rewards/accuracies": 0.3333333432674408,
|
| 34 |
+
"rewards/chosen": 0.0016270489431917667,
|
| 35 |
+
"rewards/margins": -3.060871677007526e-05,
|
| 36 |
+
"rewards/rejected": 0.0016576575580984354,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.04200610890984535,
|
| 43 |
+
"logits/rejected": 0.11701512336730957,
|
| 44 |
+
"logps/chosen": -480.87042236328125,
|
| 45 |
+
"logps/rejected": -453.9954528808594,
|
| 46 |
+
"loss": 0.2121,
|
| 47 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 48 |
+
"rewards/chosen": 0.002087645698338747,
|
| 49 |
+
"rewards/margins": 4.953762254444882e-05,
|
| 50 |
+
"rewards/rejected": 0.002038107719272375,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.08031486719846725,
|
| 57 |
+
"logits/rejected": 0.17916838824748993,
|
| 58 |
+
"logps/chosen": -533.2267456054688,
|
| 59 |
+
"logps/rejected": -509.03192138671875,
|
| 60 |
+
"loss": 0.2044,
|
| 61 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 62 |
+
"rewards/chosen": 0.001751051051542163,
|
| 63 |
+
"rewards/margins": 0.0012214130256325006,
|
| 64 |
+
"rewards/rejected": 0.0005296378512866795,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.02258063293993473,
|
| 71 |
+
"logits/rejected": 0.07948300242424011,
|
| 72 |
+
"logps/chosen": -482.404296875,
|
| 73 |
+
"logps/rejected": -482.5491638183594,
|
| 74 |
+
"loss": 0.2131,
|
| 75 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 76 |
+
"rewards/chosen": -0.0007890533888712525,
|
| 77 |
+
"rewards/margins": 0.002143475692719221,
|
| 78 |
+
"rewards/rejected": -0.002932528965175152,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.12140221893787384,
|
| 85 |
+
"logits/rejected": 0.09028098732233047,
|
| 86 |
+
"logps/chosen": -442.23797607421875,
|
| 87 |
+
"logps/rejected": -465.88214111328125,
|
| 88 |
+
"loss": 0.2105,
|
| 89 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 90 |
+
"rewards/chosen": -0.009099994786083698,
|
| 91 |
+
"rewards/margins": 0.002986655803397298,
|
| 92 |
+
"rewards/rejected": -0.012086650356650352,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.053414009511470795,
|
| 99 |
+
"logits/rejected": 0.18009646236896515,
|
| 100 |
+
"logps/chosen": -528.6683959960938,
|
| 101 |
+
"logps/rejected": -486.89361572265625,
|
| 102 |
+
"loss": 0.1982,
|
| 103 |
+
"rewards/accuracies": 0.46875,
|
| 104 |
+
"rewards/chosen": -0.015702595934271812,
|
| 105 |
+
"rewards/margins": 0.0040222653187811375,
|
| 106 |
+
"rewards/rejected": -0.019724860787391663,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.07392764091491699,
|
| 113 |
+
"logits/rejected": 0.11563147604465485,
|
| 114 |
+
"logps/chosen": -534.7530517578125,
|
| 115 |
+
"logps/rejected": -519.1510009765625,
|
| 116 |
+
"loss": 0.2073,
|
| 117 |
+
"rewards/accuracies": 0.46875,
|
| 118 |
+
"rewards/chosen": -0.02576013281941414,
|
| 119 |
+
"rewards/margins": 0.006931398995220661,
|
| 120 |
+
"rewards/rejected": -0.032691530883312225,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.0789504274725914,
|
| 127 |
+
"logits/rejected": -0.028738999739289284,
|
| 128 |
+
"logps/chosen": -516.7589111328125,
|
| 129 |
+
"logps/rejected": -550.5140991210938,
|
| 130 |
+
"loss": 0.1998,
|
| 131 |
+
"rewards/accuracies": 0.5,
|
| 132 |
+
"rewards/chosen": -0.02832980453968048,
|
| 133 |
+
"rewards/margins": 0.013306397013366222,
|
| 134 |
+
"rewards/rejected": -0.04163619875907898,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.007517285645008087,
|
| 141 |
+
"logits/rejected": 0.06739212572574615,
|
| 142 |
+
"logps/chosen": -530.9830932617188,
|
| 143 |
+
"logps/rejected": -524.5928955078125,
|
| 144 |
+
"loss": 0.2029,
|
| 145 |
+
"rewards/accuracies": 0.39375001192092896,
|
| 146 |
+
"rewards/chosen": -0.06454873085021973,
|
| 147 |
+
"rewards/margins": 0.008291224017739296,
|
| 148 |
+
"rewards/rejected": -0.07283996045589447,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.023702986538410187,
|
| 155 |
+
"logits/rejected": 0.037184469401836395,
|
| 156 |
+
"logps/chosen": -489.89581298828125,
|
| 157 |
+
"logps/rejected": -484.0779724121094,
|
| 158 |
+
"loss": 0.1966,
|
| 159 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 160 |
+
"rewards/chosen": -0.07171402126550674,
|
| 161 |
+
"rewards/margins": 0.024490345269441605,
|
| 162 |
+
"rewards/rejected": -0.09620436280965805,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.09514528512954712,
|
| 169 |
+
"logits/rejected": 0.029327446594834328,
|
| 170 |
+
"logps/chosen": -453.439697265625,
|
| 171 |
+
"logps/rejected": -483.3421325683594,
|
| 172 |
+
"loss": 0.1919,
|
| 173 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 174 |
+
"rewards/chosen": -0.06944920122623444,
|
| 175 |
+
"rewards/margins": 0.02075176127254963,
|
| 176 |
+
"rewards/rejected": -0.09020096063613892,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.052310071885585785,
|
| 183 |
+
"logits/rejected": 0.023372933268547058,
|
| 184 |
+
"logps/chosen": -465.06622314453125,
|
| 185 |
+
"logps/rejected": -487.2718200683594,
|
| 186 |
+
"loss": 0.1983,
|
| 187 |
+
"rewards/accuracies": 0.4375,
|
| 188 |
+
"rewards/chosen": -0.045129794627428055,
|
| 189 |
+
"rewards/margins": 0.017120003700256348,
|
| 190 |
+
"rewards/rejected": -0.0622497983276844,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.040262121707201004,
|
| 197 |
+
"logits/rejected": 0.2257479429244995,
|
| 198 |
+
"logps/chosen": -475.408935546875,
|
| 199 |
+
"logps/rejected": -475.36669921875,
|
| 200 |
+
"loss": 0.1949,
|
| 201 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 202 |
+
"rewards/chosen": -0.03786056488752365,
|
| 203 |
+
"rewards/margins": 0.022892726585268974,
|
| 204 |
+
"rewards/rejected": -0.060753293335437775,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.16925258934497833,
|
| 211 |
+
"logits/rejected": 0.07987479865550995,
|
| 212 |
+
"logps/chosen": -481.04083251953125,
|
| 213 |
+
"logps/rejected": -517.6348876953125,
|
| 214 |
+
"loss": 0.1979,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.07286442816257477,
|
| 217 |
+
"rewards/margins": 0.0315692201256752,
|
| 218 |
+
"rewards/rejected": -0.10443364083766937,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.021633749827742577,
|
| 225 |
+
"logits/rejected": 0.06488915532827377,
|
| 226 |
+
"logps/chosen": -476.21661376953125,
|
| 227 |
+
"logps/rejected": -496.6123046875,
|
| 228 |
+
"loss": 0.1908,
|
| 229 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 230 |
+
"rewards/chosen": -0.10675158351659775,
|
| 231 |
+
"rewards/margins": 0.03962003067135811,
|
| 232 |
+
"rewards/rejected": -0.14637163281440735,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.05234859511256218,
|
| 239 |
+
"logits/rejected": 0.02733474411070347,
|
| 240 |
+
"logps/chosen": -506.60382080078125,
|
| 241 |
+
"logps/rejected": -550.2049560546875,
|
| 242 |
+
"loss": 0.1971,
|
| 243 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 244 |
+
"rewards/chosen": -0.12149013578891754,
|
| 245 |
+
"rewards/margins": 0.03788003325462341,
|
| 246 |
+
"rewards/rejected": -0.15937016904354095,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.00539384875446558,
|
| 253 |
+
"logits/rejected": 0.001964741852134466,
|
| 254 |
+
"logps/chosen": -469.29840087890625,
|
| 255 |
+
"logps/rejected": -486.98504638671875,
|
| 256 |
+
"loss": 0.2055,
|
| 257 |
+
"rewards/accuracies": 0.4375,
|
| 258 |
+
"rewards/chosen": -0.0949864536523819,
|
| 259 |
+
"rewards/margins": 0.023784717544913292,
|
| 260 |
+
"rewards/rejected": -0.11877117305994034,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.03078017197549343,
|
| 267 |
+
"logits/rejected": 0.06562785059213638,
|
| 268 |
+
"logps/chosen": -467.913818359375,
|
| 269 |
+
"logps/rejected": -488.88165283203125,
|
| 270 |
+
"loss": 0.1832,
|
| 271 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 272 |
+
"rewards/chosen": -0.08011925220489502,
|
| 273 |
+
"rewards/margins": 0.03867987170815468,
|
| 274 |
+
"rewards/rejected": -0.1187991127371788,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": -0.012808884494006634,
|
| 281 |
+
"logits/rejected": 0.07382214069366455,
|
| 282 |
+
"logps/chosen": -470.2506408691406,
|
| 283 |
+
"logps/rejected": -483.8114318847656,
|
| 284 |
+
"loss": 0.2019,
|
| 285 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 286 |
+
"rewards/chosen": -0.08619646728038788,
|
| 287 |
+
"rewards/margins": 0.021857351064682007,
|
| 288 |
+
"rewards/rejected": -0.10805382579565048,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.11153273284435272,
|
| 295 |
+
"logits/rejected": 0.0497104674577713,
|
| 296 |
+
"logps/chosen": -451.3377380371094,
|
| 297 |
+
"logps/rejected": -478.8421936035156,
|
| 298 |
+
"loss": 0.1942,
|
| 299 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 300 |
+
"rewards/chosen": -0.0883895754814148,
|
| 301 |
+
"rewards/margins": 0.030626222491264343,
|
| 302 |
+
"rewards/rejected": -0.11901579797267914,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.08737102895975113,
|
| 309 |
+
"logits/rejected": 0.11837353557348251,
|
| 310 |
+
"logps/chosen": -519.548828125,
|
| 311 |
+
"logps/rejected": -513.87255859375,
|
| 312 |
+
"loss": 0.1924,
|
| 313 |
+
"rewards/accuracies": 0.543749988079071,
|
| 314 |
+
"rewards/chosen": -0.11379089206457138,
|
| 315 |
+
"rewards/margins": 0.03358360007405281,
|
| 316 |
+
"rewards/rejected": -0.1473744958639145,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.14104892313480377,
|
| 323 |
+
"logits/rejected": 0.05087919905781746,
|
| 324 |
+
"logps/chosen": -525.2891235351562,
|
| 325 |
+
"logps/rejected": -516.625,
|
| 326 |
+
"loss": 0.2024,
|
| 327 |
+
"rewards/accuracies": 0.46875,
|
| 328 |
+
"rewards/chosen": -0.10455243289470673,
|
| 329 |
+
"rewards/margins": 0.0242080669850111,
|
| 330 |
+
"rewards/rejected": -0.12876050174236298,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": 0.09732341766357422,
|
| 337 |
+
"logits/rejected": 0.06271795928478241,
|
| 338 |
+
"logps/chosen": -514.5999755859375,
|
| 339 |
+
"logps/rejected": -543.45068359375,
|
| 340 |
+
"loss": 0.2006,
|
| 341 |
+
"rewards/accuracies": 0.59375,
|
| 342 |
+
"rewards/chosen": -0.1029946357011795,
|
| 343 |
+
"rewards/margins": 0.033023733645677567,
|
| 344 |
+
"rewards/rejected": -0.13601836562156677,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": 0.06812410056591034,
|
| 351 |
+
"logits/rejected": 0.025554204359650612,
|
| 352 |
+
"logps/chosen": -516.6173095703125,
|
| 353 |
+
"logps/rejected": -508.93511962890625,
|
| 354 |
+
"loss": 0.2079,
|
| 355 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 356 |
+
"rewards/chosen": -0.0961836650967598,
|
| 357 |
+
"rewards/margins": 0.020848505198955536,
|
| 358 |
+
"rewards/rejected": -0.11703218519687653,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": 0.052641429007053375,
|
| 365 |
+
"logits/rejected": 0.11277129501104355,
|
| 366 |
+
"logps/chosen": -499.9371032714844,
|
| 367 |
+
"logps/rejected": -524.9378662109375,
|
| 368 |
+
"loss": 0.2003,
|
| 369 |
+
"rewards/accuracies": 0.512499988079071,
|
| 370 |
+
"rewards/chosen": -0.11769168078899384,
|
| 371 |
+
"rewards/margins": 0.02954215370118618,
|
| 372 |
+
"rewards/rejected": -0.14723384380340576,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": 0.1458149254322052,
|
| 379 |
+
"logits/rejected": 0.18058298528194427,
|
| 380 |
+
"logps/chosen": -461.63262939453125,
|
| 381 |
+
"logps/rejected": -501.23077392578125,
|
| 382 |
+
"loss": 0.195,
|
| 383 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 384 |
+
"rewards/chosen": -0.1235838383436203,
|
| 385 |
+
"rewards/margins": 0.02654830738902092,
|
| 386 |
+
"rewards/rejected": -0.15013214945793152,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": 0.07014019787311554,
|
| 393 |
+
"logits/rejected": 0.16694627702236176,
|
| 394 |
+
"logps/chosen": -472.4525451660156,
|
| 395 |
+
"logps/rejected": -473.22857666015625,
|
| 396 |
+
"loss": 0.1957,
|
| 397 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 398 |
+
"rewards/chosen": -0.12277780473232269,
|
| 399 |
+
"rewards/margins": 0.01745077781379223,
|
| 400 |
+
"rewards/rejected": -0.14022858440876007,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": 0.11594029515981674,
|
| 407 |
+
"logits/rejected": 0.14667686820030212,
|
| 408 |
+
"logps/chosen": -454.9984436035156,
|
| 409 |
+
"logps/rejected": -468.27764892578125,
|
| 410 |
+
"loss": 0.1927,
|
| 411 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 412 |
+
"rewards/chosen": -0.14300423860549927,
|
| 413 |
+
"rewards/margins": 0.037807125598192215,
|
| 414 |
+
"rewards/rejected": -0.18081137537956238,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": 0.08191246539354324,
|
| 421 |
+
"logits/rejected": 0.13855530321598053,
|
| 422 |
+
"logps/chosen": -496.906982421875,
|
| 423 |
+
"logps/rejected": -526.3932495117188,
|
| 424 |
+
"loss": 0.1933,
|
| 425 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 426 |
+
"rewards/chosen": -0.12783119082450867,
|
| 427 |
+
"rewards/margins": 0.03418290615081787,
|
| 428 |
+
"rewards/rejected": -0.16201409697532654,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": 0.10729117691516876,
|
| 435 |
+
"logits/rejected": 0.1382167488336563,
|
| 436 |
+
"logps/chosen": -525.2513427734375,
|
| 437 |
+
"logps/rejected": -557.9173583984375,
|
| 438 |
+
"loss": 0.1848,
|
| 439 |
+
"rewards/accuracies": 0.574999988079071,
|
| 440 |
+
"rewards/chosen": -0.10007178783416748,
|
| 441 |
+
"rewards/margins": 0.03654087707400322,
|
| 442 |
+
"rewards/rejected": -0.136612668633461,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": 0.03605717048048973,
|
| 449 |
+
"logits/rejected": 0.08247358351945877,
|
| 450 |
+
"logps/chosen": -476.7731018066406,
|
| 451 |
+
"logps/rejected": -517.1722412109375,
|
| 452 |
+
"loss": 0.1901,
|
| 453 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 454 |
+
"rewards/chosen": -0.0743183121085167,
|
| 455 |
+
"rewards/margins": 0.028351595625281334,
|
| 456 |
+
"rewards/rejected": -0.10266990959644318,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": 0.03332200273871422,
|
| 463 |
+
"logits/rejected": 0.09907984733581543,
|
| 464 |
+
"logps/chosen": -449.68212890625,
|
| 465 |
+
"logps/rejected": -509.12554931640625,
|
| 466 |
+
"loss": 0.1926,
|
| 467 |
+
"rewards/accuracies": 0.59375,
|
| 468 |
+
"rewards/chosen": -0.05537894368171692,
|
| 469 |
+
"rewards/margins": 0.05774994567036629,
|
| 470 |
+
"rewards/rejected": -0.11312887817621231,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": 0.05158273130655289,
|
| 477 |
+
"logits/rejected": 0.10417857021093369,
|
| 478 |
+
"logps/chosen": -498.09197998046875,
|
| 479 |
+
"logps/rejected": -511.01611328125,
|
| 480 |
+
"loss": 0.1957,
|
| 481 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 482 |
+
"rewards/chosen": -0.06420507282018661,
|
| 483 |
+
"rewards/margins": 0.012455371208488941,
|
| 484 |
+
"rewards/rejected": -0.07666043937206268,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": 0.015417411923408508,
|
| 491 |
+
"logits/rejected": 0.09142233431339264,
|
| 492 |
+
"logps/chosen": -502.4671936035156,
|
| 493 |
+
"logps/rejected": -528.1393432617188,
|
| 494 |
+
"loss": 0.187,
|
| 495 |
+
"rewards/accuracies": 0.512499988079071,
|
| 496 |
+
"rewards/chosen": -0.0401633158326149,
|
| 497 |
+
"rewards/margins": 0.03752883896231651,
|
| 498 |
+
"rewards/rejected": -0.07769216597080231,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.07565109431743622,
|
| 505 |
+
"logits/rejected": 0.14677348732948303,
|
| 506 |
+
"logps/chosen": -490.3994140625,
|
| 507 |
+
"logps/rejected": -483.0618591308594,
|
| 508 |
+
"loss": 0.182,
|
| 509 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 510 |
+
"rewards/chosen": -0.000983755337074399,
|
| 511 |
+
"rewards/margins": 0.04362579435110092,
|
| 512 |
+
"rewards/rejected": -0.04460955038666725,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": -0.012587164528667927,
|
| 519 |
+
"logits/rejected": 0.17615702748298645,
|
| 520 |
+
"logps/chosen": -460.7539978027344,
|
| 521 |
+
"logps/rejected": -496.0394592285156,
|
| 522 |
+
"loss": 0.1765,
|
| 523 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 524 |
+
"rewards/chosen": -0.004288173280656338,
|
| 525 |
+
"rewards/margins": 0.045940086245536804,
|
| 526 |
+
"rewards/rejected": -0.05022825673222542,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": 0.05247374624013901,
|
| 533 |
+
"logits/rejected": 0.06078363209962845,
|
| 534 |
+
"logps/chosen": -500.44384765625,
|
| 535 |
+
"logps/rejected": -511.1734313964844,
|
| 536 |
+
"loss": 0.189,
|
| 537 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 538 |
+
"rewards/chosen": 0.0024426232557743788,
|
| 539 |
+
"rewards/margins": 0.04215018078684807,
|
| 540 |
+
"rewards/rejected": -0.03970755636692047,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": 0.04354017972946167,
|
| 547 |
+
"logits/rejected": 0.12157300859689713,
|
| 548 |
+
"logps/chosen": -477.10601806640625,
|
| 549 |
+
"logps/rejected": -487.3301696777344,
|
| 550 |
+
"loss": 0.1834,
|
| 551 |
+
"rewards/accuracies": 0.46875,
|
| 552 |
+
"rewards/chosen": 0.022890402004122734,
|
| 553 |
+
"rewards/margins": 0.03842080011963844,
|
| 554 |
+
"rewards/rejected": -0.01553039439022541,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": 0.04744056984782219,
|
| 561 |
+
"logits/rejected": 0.07940800487995148,
|
| 562 |
+
"logps/chosen": -472.5918884277344,
|
| 563 |
+
"logps/rejected": -496.16387939453125,
|
| 564 |
+
"loss": 0.1833,
|
| 565 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 566 |
+
"rewards/chosen": 0.019969001412391663,
|
| 567 |
+
"rewards/margins": 0.04812890291213989,
|
| 568 |
+
"rewards/rejected": -0.02815990522503853,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": 0.04268989711999893,
|
| 575 |
+
"logits/rejected": 0.07916353642940521,
|
| 576 |
+
"logps/chosen": -486.46746826171875,
|
| 577 |
+
"logps/rejected": -520.3671875,
|
| 578 |
+
"loss": 0.1851,
|
| 579 |
+
"rewards/accuracies": 0.518750011920929,
|
| 580 |
+
"rewards/chosen": 0.029743488878011703,
|
| 581 |
+
"rewards/margins": 0.04279039055109024,
|
| 582 |
+
"rewards/rejected": -0.013046903535723686,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": -0.027468422427773476,
|
| 589 |
+
"logits/rejected": -0.04074520990252495,
|
| 590 |
+
"logps/chosen": -461.34814453125,
|
| 591 |
+
"logps/rejected": -480.4091796875,
|
| 592 |
+
"loss": 0.1842,
|
| 593 |
+
"rewards/accuracies": 0.518750011920929,
|
| 594 |
+
"rewards/chosen": 0.058516185730695724,
|
| 595 |
+
"rewards/margins": 0.04239815101027489,
|
| 596 |
+
"rewards/rejected": 0.016118034720420837,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": 0.029957780614495277,
|
| 603 |
+
"logits/rejected": 0.1293373703956604,
|
| 604 |
+
"logps/chosen": -476.6888732910156,
|
| 605 |
+
"logps/rejected": -474.581298828125,
|
| 606 |
+
"loss": 0.1863,
|
| 607 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 608 |
+
"rewards/chosen": 0.06844775378704071,
|
| 609 |
+
"rewards/margins": 0.0345512256026268,
|
| 610 |
+
"rewards/rejected": 0.03389652818441391,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": 0.12380461394786835,
|
| 617 |
+
"logits/rejected": 0.08030427992343903,
|
| 618 |
+
"logps/chosen": -501.05419921875,
|
| 619 |
+
"logps/rejected": -540.5864868164062,
|
| 620 |
+
"loss": 0.1833,
|
| 621 |
+
"rewards/accuracies": 0.53125,
|
| 622 |
+
"rewards/chosen": 0.08108590543270111,
|
| 623 |
+
"rewards/margins": 0.04042986035346985,
|
| 624 |
+
"rewards/rejected": 0.040656037628650665,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": 0.07574252784252167,
|
| 631 |
+
"logits/rejected": -0.00224049249663949,
|
| 632 |
+
"logps/chosen": -482.531982421875,
|
| 633 |
+
"logps/rejected": -499.04180908203125,
|
| 634 |
+
"loss": 0.1822,
|
| 635 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 636 |
+
"rewards/chosen": 0.0877564549446106,
|
| 637 |
+
"rewards/margins": 0.03748675435781479,
|
| 638 |
+
"rewards/rejected": 0.05026970058679581,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": 0.10215386003255844,
|
| 645 |
+
"logits/rejected": 0.025258684530854225,
|
| 646 |
+
"logps/chosen": -455.39825439453125,
|
| 647 |
+
"logps/rejected": -464.11016845703125,
|
| 648 |
+
"loss": 0.1929,
|
| 649 |
+
"rewards/accuracies": 0.581250011920929,
|
| 650 |
+
"rewards/chosen": 0.11565859615802765,
|
| 651 |
+
"rewards/margins": 0.04002625495195389,
|
| 652 |
+
"rewards/rejected": 0.07563233375549316,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": 0.07208961248397827,
|
| 659 |
+
"logits/rejected": 0.05293772369623184,
|
| 660 |
+
"logps/chosen": -422.0474548339844,
|
| 661 |
+
"logps/rejected": -466.1214904785156,
|
| 662 |
+
"loss": 0.1867,
|
| 663 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 664 |
+
"rewards/chosen": 0.13345687091350555,
|
| 665 |
+
"rewards/margins": 0.04373367875814438,
|
| 666 |
+
"rewards/rejected": 0.08972318470478058,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": 0.08753691613674164,
|
| 673 |
+
"logits/rejected": 0.13366851210594177,
|
| 674 |
+
"logps/chosen": -493.6244201660156,
|
| 675 |
+
"logps/rejected": -481.61505126953125,
|
| 676 |
+
"loss": 0.1971,
|
| 677 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 678 |
+
"rewards/chosen": 0.15995556116104126,
|
| 679 |
+
"rewards/margins": 0.030286097899079323,
|
| 680 |
+
"rewards/rejected": 0.1296694576740265,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": 0.040917035192251205,
|
| 687 |
+
"logits/rejected": 0.049655430018901825,
|
| 688 |
+
"logps/chosen": -496.69207763671875,
|
| 689 |
+
"logps/rejected": -510.538818359375,
|
| 690 |
+
"loss": 0.1827,
|
| 691 |
+
"rewards/accuracies": 0.612500011920929,
|
| 692 |
+
"rewards/chosen": 0.16031843423843384,
|
| 693 |
+
"rewards/margins": 0.047999344766139984,
|
| 694 |
+
"rewards/rejected": 0.11231908947229385,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": -0.02139192819595337,
|
| 701 |
+
"logits/rejected": 0.07283684611320496,
|
| 702 |
+
"logps/chosen": -455.2607421875,
|
| 703 |
+
"logps/rejected": -484.5707092285156,
|
| 704 |
+
"loss": 0.2065,
|
| 705 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 706 |
+
"rewards/chosen": 0.13160817325115204,
|
| 707 |
+
"rewards/margins": 0.03165828809142113,
|
| 708 |
+
"rewards/rejected": 0.09994987398386002,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": 0.043560974299907684,
|
| 715 |
+
"logits/rejected": 0.0819135308265686,
|
| 716 |
+
"logps/chosen": -448.69793701171875,
|
| 717 |
+
"logps/rejected": -472.7060546875,
|
| 718 |
+
"loss": 0.1844,
|
| 719 |
+
"rewards/accuracies": 0.550000011920929,
|
| 720 |
+
"rewards/chosen": 0.10212703794240952,
|
| 721 |
+
"rewards/margins": 0.038218505680561066,
|
| 722 |
+
"rewards/rejected": 0.06390853226184845,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": 0.005092448554933071,
|
| 729 |
+
"logits/rejected": 0.10958313941955566,
|
| 730 |
+
"logps/chosen": -484.2552185058594,
|
| 731 |
+
"logps/rejected": -514.481689453125,
|
| 732 |
+
"loss": 0.1942,
|
| 733 |
+
"rewards/accuracies": 0.581250011920929,
|
| 734 |
+
"rewards/chosen": 0.09142176806926727,
|
| 735 |
+
"rewards/margins": 0.05243723839521408,
|
| 736 |
+
"rewards/rejected": 0.038984514772892,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": 0.09447602182626724,
|
| 743 |
+
"logits/rejected": 0.08024080842733383,
|
| 744 |
+
"logps/chosen": -485.6512756347656,
|
| 745 |
+
"logps/rejected": -482.0237731933594,
|
| 746 |
+
"loss": 0.1891,
|
| 747 |
+
"rewards/accuracies": 0.550000011920929,
|
| 748 |
+
"rewards/chosen": 0.07477296888828278,
|
| 749 |
+
"rewards/margins": 0.05883296579122543,
|
| 750 |
+
"rewards/rejected": 0.015940004959702492,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": 0.03767072409391403,
|
| 757 |
+
"logits/rejected": 0.02741827443242073,
|
| 758 |
+
"logps/chosen": -440.016357421875,
|
| 759 |
+
"logps/rejected": -472.63873291015625,
|
| 760 |
+
"loss": 0.1917,
|
| 761 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 762 |
+
"rewards/chosen": 0.08402599394321442,
|
| 763 |
+
"rewards/margins": 0.061398398131132126,
|
| 764 |
+
"rewards/rejected": 0.02262760140001774,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.00708337128162384,
|
| 771 |
+
"logits/rejected": 0.055642373859882355,
|
| 772 |
+
"logps/chosen": -446.92498779296875,
|
| 773 |
+
"logps/rejected": -466.16912841796875,
|
| 774 |
+
"loss": 0.1827,
|
| 775 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 776 |
+
"rewards/chosen": 0.07480621337890625,
|
| 777 |
+
"rewards/margins": 0.033216286450624466,
|
| 778 |
+
"rewards/rejected": 0.04158991575241089,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": 0.035645630210638046,
|
| 785 |
+
"logits/rejected": 0.019252488389611244,
|
| 786 |
+
"logps/chosen": -421.6669921875,
|
| 787 |
+
"logps/rejected": -462.30279541015625,
|
| 788 |
+
"loss": 0.1782,
|
| 789 |
+
"rewards/accuracies": 0.53125,
|
| 790 |
+
"rewards/chosen": 0.08298784494400024,
|
| 791 |
+
"rewards/margins": 0.05089961364865303,
|
| 792 |
+
"rewards/rejected": 0.032088227570056915,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": 0.03386590629816055,
|
| 799 |
+
"logits/rejected": 0.0352010652422905,
|
| 800 |
+
"logps/chosen": -497.4388732910156,
|
| 801 |
+
"logps/rejected": -539.6199951171875,
|
| 802 |
+
"loss": 0.184,
|
| 803 |
+
"rewards/accuracies": 0.612500011920929,
|
| 804 |
+
"rewards/chosen": 0.07756824791431427,
|
| 805 |
+
"rewards/margins": 0.06193417310714722,
|
| 806 |
+
"rewards/rejected": 0.01563408225774765,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": 0.06176334619522095,
|
| 813 |
+
"logits/rejected": 0.05909004807472229,
|
| 814 |
+
"logps/chosen": -479.58502197265625,
|
| 815 |
+
"logps/rejected": -504.15118408203125,
|
| 816 |
+
"loss": 0.179,
|
| 817 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 818 |
+
"rewards/chosen": 0.07643002271652222,
|
| 819 |
+
"rewards/margins": 0.055131517350673676,
|
| 820 |
+
"rewards/rejected": 0.021298503503203392,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": 0.10232093185186386,
|
| 827 |
+
"logits/rejected": 0.03354436904191971,
|
| 828 |
+
"logps/chosen": -504.35552978515625,
|
| 829 |
+
"logps/rejected": -500.55242919921875,
|
| 830 |
+
"loss": 0.188,
|
| 831 |
+
"rewards/accuracies": 0.550000011920929,
|
| 832 |
+
"rewards/chosen": 0.0535406656563282,
|
| 833 |
+
"rewards/margins": 0.045547787100076675,
|
| 834 |
+
"rewards/rejected": 0.007992876693606377,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": 0.08256170898675919,
|
| 841 |
+
"logits/rejected": 0.011359182186424732,
|
| 842 |
+
"logps/chosen": -423.5184631347656,
|
| 843 |
+
"logps/rejected": -462.12921142578125,
|
| 844 |
+
"loss": 0.1847,
|
| 845 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 846 |
+
"rewards/chosen": 0.06936874985694885,
|
| 847 |
+
"rewards/margins": 0.04546703025698662,
|
| 848 |
+
"rewards/rejected": 0.023901721462607384,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": 0.05957316234707832,
|
| 855 |
+
"logits/rejected": 0.02687280997633934,
|
| 856 |
+
"logps/chosen": -463.92340087890625,
|
| 857 |
+
"logps/rejected": -488.68524169921875,
|
| 858 |
+
"loss": 0.1841,
|
| 859 |
+
"rewards/accuracies": 0.5625,
|
| 860 |
+
"rewards/chosen": 0.093163400888443,
|
| 861 |
+
"rewards/margins": 0.05278082564473152,
|
| 862 |
+
"rewards/rejected": 0.04038257524371147,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": 0.03663691133260727,
|
| 869 |
+
"logits/rejected": 0.06973805278539658,
|
| 870 |
+
"logps/chosen": -460.896728515625,
|
| 871 |
+
"logps/rejected": -508.50408935546875,
|
| 872 |
+
"loss": 0.1778,
|
| 873 |
+
"rewards/accuracies": 0.581250011920929,
|
| 874 |
+
"rewards/chosen": 0.0800352543592453,
|
| 875 |
+
"rewards/margins": 0.05085815116763115,
|
| 876 |
+
"rewards/rejected": 0.029177110642194748,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": 0.028588274493813515,
|
| 883 |
+
"logits/rejected": 0.081044040620327,
|
| 884 |
+
"logps/chosen": -504.3495178222656,
|
| 885 |
+
"logps/rejected": -515.7532958984375,
|
| 886 |
+
"loss": 0.1676,
|
| 887 |
+
"rewards/accuracies": 0.574999988079071,
|
| 888 |
+
"rewards/chosen": 0.07437646389007568,
|
| 889 |
+
"rewards/margins": 0.04987211152911186,
|
| 890 |
+
"rewards/rejected": 0.02450435608625412,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": 0.03259013965725899,
|
| 897 |
+
"logits/rejected": 0.0049851625226438046,
|
| 898 |
+
"logps/chosen": -485.429443359375,
|
| 899 |
+
"logps/rejected": -495.66802978515625,
|
| 900 |
+
"loss": 0.1771,
|
| 901 |
+
"rewards/accuracies": 0.53125,
|
| 902 |
+
"rewards/chosen": 0.07386799156665802,
|
| 903 |
+
"rewards/margins": 0.05358237773180008,
|
| 904 |
+
"rewards/rejected": 0.02028561569750309,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": 0.040917474776506424,
|
| 911 |
+
"logits/rejected": 0.03524303436279297,
|
| 912 |
+
"logps/chosen": -474.40252685546875,
|
| 913 |
+
"logps/rejected": -492.69415283203125,
|
| 914 |
+
"loss": 0.1848,
|
| 915 |
+
"rewards/accuracies": 0.53125,
|
| 916 |
+
"rewards/chosen": 0.08967775106430054,
|
| 917 |
+
"rewards/margins": 0.04113636165857315,
|
| 918 |
+
"rewards/rejected": 0.04854138568043709,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": -0.0005787253612652421,
|
| 925 |
+
"logits/rejected": 0.05223802477121353,
|
| 926 |
+
"logps/chosen": -469.7098693847656,
|
| 927 |
+
"logps/rejected": -505.01739501953125,
|
| 928 |
+
"loss": 0.1979,
|
| 929 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 930 |
+
"rewards/chosen": 0.08548668771982193,
|
| 931 |
+
"rewards/margins": 0.057396382093429565,
|
| 932 |
+
"rewards/rejected": 0.028090301901102066,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": 0.09496835619211197,
|
| 939 |
+
"logits/rejected": -0.0715503841638565,
|
| 940 |
+
"logps/chosen": -422.630859375,
|
| 941 |
+
"logps/rejected": -483.22479248046875,
|
| 942 |
+
"loss": 0.1824,
|
| 943 |
+
"rewards/accuracies": 0.512499988079071,
|
| 944 |
+
"rewards/chosen": 0.08553356677293777,
|
| 945 |
+
"rewards/margins": 0.059073131531476974,
|
| 946 |
+
"rewards/rejected": 0.02646043337881565,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": -0.00498700188472867,
|
| 953 |
+
"logits/rejected": 0.013168242760002613,
|
| 954 |
+
"logps/chosen": -445.13861083984375,
|
| 955 |
+
"logps/rejected": -466.5567932128906,
|
| 956 |
+
"loss": 0.1776,
|
| 957 |
+
"rewards/accuracies": 0.512499988079071,
|
| 958 |
+
"rewards/chosen": 0.10062942653894424,
|
| 959 |
+
"rewards/margins": 0.04562296345829964,
|
| 960 |
+
"rewards/rejected": 0.055006466805934906,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": 0.0634564682841301,
|
| 967 |
+
"logits/rejected": 0.03239821270108223,
|
| 968 |
+
"logps/chosen": -454.5580139160156,
|
| 969 |
+
"logps/rejected": -471.24456787109375,
|
| 970 |
+
"loss": 0.1788,
|
| 971 |
+
"rewards/accuracies": 0.574999988079071,
|
| 972 |
+
"rewards/chosen": 0.11137165874242783,
|
| 973 |
+
"rewards/margins": 0.06377272307872772,
|
| 974 |
+
"rewards/rejected": 0.0475989505648613,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": 0.13198313117027283,
|
| 981 |
+
"logits/rejected": -0.011327924206852913,
|
| 982 |
+
"logps/chosen": -447.65301513671875,
|
| 983 |
+
"logps/rejected": -485.073974609375,
|
| 984 |
+
"loss": 0.1763,
|
| 985 |
+
"rewards/accuracies": 0.574999988079071,
|
| 986 |
+
"rewards/chosen": 0.11758910119533539,
|
| 987 |
+
"rewards/margins": 0.05051087588071823,
|
| 988 |
+
"rewards/rejected": 0.06707822531461716,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": 0.01844317652285099,
|
| 995 |
+
"logits/rejected": 0.046270035207271576,
|
| 996 |
+
"logps/chosen": -461.8832092285156,
|
| 997 |
+
"logps/rejected": -497.8064880371094,
|
| 998 |
+
"loss": 0.1902,
|
| 999 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1000 |
+
"rewards/chosen": 0.11230479180812836,
|
| 1001 |
+
"rewards/margins": 0.038510359823703766,
|
| 1002 |
+
"rewards/rejected": 0.07379443198442459,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": -0.0005433745682239532,
|
| 1009 |
+
"logits/rejected": 0.07239210605621338,
|
| 1010 |
+
"logps/chosen": -440.7948303222656,
|
| 1011 |
+
"logps/rejected": -482.3118591308594,
|
| 1012 |
+
"loss": 0.1805,
|
| 1013 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1014 |
+
"rewards/chosen": 0.11701339483261108,
|
| 1015 |
+
"rewards/margins": 0.05948741361498833,
|
| 1016 |
+
"rewards/rejected": 0.05752598121762276,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": 0.004731953144073486,
|
| 1023 |
+
"logits/rejected": 0.06949619203805923,
|
| 1024 |
+
"logps/chosen": -495.1181640625,
|
| 1025 |
+
"logps/rejected": -494.14727783203125,
|
| 1026 |
+
"loss": 0.1907,
|
| 1027 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 1028 |
+
"rewards/chosen": 0.11087504774332047,
|
| 1029 |
+
"rewards/margins": 0.05067601799964905,
|
| 1030 |
+
"rewards/rejected": 0.060199033468961716,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": 0.05472816899418831,
|
| 1037 |
+
"logits/rejected": 0.12369577586650848,
|
| 1038 |
+
"logps/chosen": -454.3465270996094,
|
| 1039 |
+
"logps/rejected": -466.5943298339844,
|
| 1040 |
+
"loss": 0.1862,
|
| 1041 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1042 |
+
"rewards/chosen": 0.09320452064275742,
|
| 1043 |
+
"rewards/margins": 0.04919914901256561,
|
| 1044 |
+
"rewards/rejected": 0.0440053753554821,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": 0.049330659210681915,
|
| 1051 |
+
"logits/rejected": -0.05037214607000351,
|
| 1052 |
+
"logps/chosen": -426.7115173339844,
|
| 1053 |
+
"logps/rejected": -468.99169921875,
|
| 1054 |
+
"loss": 0.178,
|
| 1055 |
+
"rewards/accuracies": 0.606249988079071,
|
| 1056 |
+
"rewards/chosen": 0.1173645481467247,
|
| 1057 |
+
"rewards/margins": 0.06448864191770554,
|
| 1058 |
+
"rewards/rejected": 0.05287591367959976,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": 0.018861666321754456,
|
| 1065 |
+
"logits/rejected": 0.04406842216849327,
|
| 1066 |
+
"logps/chosen": -471.93438720703125,
|
| 1067 |
+
"logps/rejected": -496.49993896484375,
|
| 1068 |
+
"loss": 0.1862,
|
| 1069 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1070 |
+
"rewards/chosen": 0.11358505487442017,
|
| 1071 |
+
"rewards/margins": 0.046424929052591324,
|
| 1072 |
+
"rewards/rejected": 0.06716012954711914,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": 0.009539002552628517,
|
| 1079 |
+
"logits/rejected": 0.11306466907262802,
|
| 1080 |
+
"logps/chosen": -520.7066650390625,
|
| 1081 |
+
"logps/rejected": -506.4190368652344,
|
| 1082 |
+
"loss": 0.1811,
|
| 1083 |
+
"rewards/accuracies": 0.59375,
|
| 1084 |
+
"rewards/chosen": 0.11439801752567291,
|
| 1085 |
+
"rewards/margins": 0.042585574090480804,
|
| 1086 |
+
"rewards/rejected": 0.07181242108345032,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": 0.05899236351251602,
|
| 1093 |
+
"logits/rejected": -0.012183750048279762,
|
| 1094 |
+
"logps/chosen": -465.54583740234375,
|
| 1095 |
+
"logps/rejected": -492.99627685546875,
|
| 1096 |
+
"loss": 0.1822,
|
| 1097 |
+
"rewards/accuracies": 0.59375,
|
| 1098 |
+
"rewards/chosen": 0.11408071219921112,
|
| 1099 |
+
"rewards/margins": 0.05036580562591553,
|
| 1100 |
+
"rewards/rejected": 0.06371492147445679,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": 0.04782986640930176,
|
| 1107 |
+
"logits/rejected": 0.0820665955543518,
|
| 1108 |
+
"logps/chosen": -446.2923278808594,
|
| 1109 |
+
"logps/rejected": -473.13330078125,
|
| 1110 |
+
"loss": 0.1747,
|
| 1111 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1112 |
+
"rewards/chosen": 0.10825562477111816,
|
| 1113 |
+
"rewards/margins": 0.04990454763174057,
|
| 1114 |
+
"rewards/rejected": 0.058351077139377594,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": -0.04199203476309776,
|
| 1121 |
+
"logits/rejected": 0.034929946064949036,
|
| 1122 |
+
"logps/chosen": -446.6978454589844,
|
| 1123 |
+
"logps/rejected": -435.03521728515625,
|
| 1124 |
+
"loss": 0.1749,
|
| 1125 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 1126 |
+
"rewards/chosen": 0.09576048702001572,
|
| 1127 |
+
"rewards/margins": 0.045824047178030014,
|
| 1128 |
+
"rewards/rejected": 0.0499364398419857,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": 0.026381831616163254,
|
| 1135 |
+
"logits/rejected": 0.07602212578058243,
|
| 1136 |
+
"logps/chosen": -467.7432556152344,
|
| 1137 |
+
"logps/rejected": -516.2023315429688,
|
| 1138 |
+
"loss": 0.1863,
|
| 1139 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1140 |
+
"rewards/chosen": 0.11635438352823257,
|
| 1141 |
+
"rewards/margins": 0.06682081520557404,
|
| 1142 |
+
"rewards/rejected": 0.04953356832265854,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": 0.04555773735046387,
|
| 1149 |
+
"logits/rejected": 0.0836203470826149,
|
| 1150 |
+
"logps/chosen": -432.5563049316406,
|
| 1151 |
+
"logps/rejected": -469.57196044921875,
|
| 1152 |
+
"loss": 0.1816,
|
| 1153 |
+
"rewards/accuracies": 0.550000011920929,
|
| 1154 |
+
"rewards/chosen": 0.11761243641376495,
|
| 1155 |
+
"rewards/margins": 0.05147726088762283,
|
| 1156 |
+
"rewards/rejected": 0.06613515317440033,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": 0.06100771576166153,
|
| 1163 |
+
"logits/rejected": -0.052108317613601685,
|
| 1164 |
+
"logps/chosen": -411.35906982421875,
|
| 1165 |
+
"logps/rejected": -439.3312072753906,
|
| 1166 |
+
"loss": 0.1838,
|
| 1167 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1168 |
+
"rewards/chosen": 0.12352752685546875,
|
| 1169 |
+
"rewards/margins": 0.057254206389188766,
|
| 1170 |
+
"rewards/rejected": 0.06627332419157028,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": 0.0011749922996386886,
|
| 1177 |
+
"logits/rejected": -0.003739739302545786,
|
| 1178 |
+
"logps/chosen": -458.92919921875,
|
| 1179 |
+
"logps/rejected": -491.05615234375,
|
| 1180 |
+
"loss": 0.1983,
|
| 1181 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1182 |
+
"rewards/chosen": 0.11504600197076797,
|
| 1183 |
+
"rewards/margins": 0.04097086191177368,
|
| 1184 |
+
"rewards/rejected": 0.0740751400589943,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": 0.06734688580036163,
|
| 1191 |
+
"logits/rejected": 0.08023635298013687,
|
| 1192 |
+
"logps/chosen": -494.57342529296875,
|
| 1193 |
+
"logps/rejected": -526.6209716796875,
|
| 1194 |
+
"loss": 0.1857,
|
| 1195 |
+
"rewards/accuracies": 0.5625,
|
| 1196 |
+
"rewards/chosen": 0.1077314019203186,
|
| 1197 |
+
"rewards/margins": 0.04536820203065872,
|
| 1198 |
+
"rewards/rejected": 0.06236319988965988,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": 0.03414052724838257,
|
| 1205 |
+
"logits/rejected": 0.0967903584241867,
|
| 1206 |
+
"logps/chosen": -406.6197204589844,
|
| 1207 |
+
"logps/rejected": -463.4610900878906,
|
| 1208 |
+
"loss": 0.1849,
|
| 1209 |
+
"rewards/accuracies": 0.518750011920929,
|
| 1210 |
+
"rewards/chosen": 0.12588708102703094,
|
| 1211 |
+
"rewards/margins": 0.05215496942400932,
|
| 1212 |
+
"rewards/rejected": 0.07373212277889252,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": 0.046077877283096313,
|
| 1219 |
+
"logits/rejected": -0.010932741686701775,
|
| 1220 |
+
"logps/chosen": -486.12933349609375,
|
| 1221 |
+
"logps/rejected": -490.4742736816406,
|
| 1222 |
+
"loss": 0.1796,
|
| 1223 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1224 |
+
"rewards/chosen": 0.11952760070562363,
|
| 1225 |
+
"rewards/margins": 0.052067436277866364,
|
| 1226 |
+
"rewards/rejected": 0.06746017187833786,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": 0.08364848792552948,
|
| 1233 |
+
"logits/rejected": -0.016565704718232155,
|
| 1234 |
+
"logps/chosen": -421.2782287597656,
|
| 1235 |
+
"logps/rejected": -448.32061767578125,
|
| 1236 |
+
"loss": 0.1673,
|
| 1237 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 1238 |
+
"rewards/chosen": 0.12084163725376129,
|
| 1239 |
+
"rewards/margins": 0.05717577412724495,
|
| 1240 |
+
"rewards/rejected": 0.06366586685180664,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": 0.05045370012521744,
|
| 1247 |
+
"logits/rejected": -0.015437754802405834,
|
| 1248 |
+
"logps/chosen": -436.0224609375,
|
| 1249 |
+
"logps/rejected": -480.992431640625,
|
| 1250 |
+
"loss": 0.1805,
|
| 1251 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1252 |
+
"rewards/chosen": 0.1131979450583458,
|
| 1253 |
+
"rewards/margins": 0.05461297556757927,
|
| 1254 |
+
"rewards/rejected": 0.058584969490766525,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": 0.0034905076026916504,
|
| 1261 |
+
"logits/rejected": 0.10833680629730225,
|
| 1262 |
+
"logps/chosen": -497.405517578125,
|
| 1263 |
+
"logps/rejected": -531.6438598632812,
|
| 1264 |
+
"loss": 0.1902,
|
| 1265 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1266 |
+
"rewards/chosen": 0.10887560993432999,
|
| 1267 |
+
"rewards/margins": 0.053155817091464996,
|
| 1268 |
+
"rewards/rejected": 0.05571979284286499,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": 0.09158419072628021,
|
| 1275 |
+
"logits/rejected": 0.12686944007873535,
|
| 1276 |
+
"logps/chosen": -453.55206298828125,
|
| 1277 |
+
"logps/rejected": -507.8880920410156,
|
| 1278 |
+
"loss": 0.1797,
|
| 1279 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 1280 |
+
"rewards/chosen": 0.11705918610095978,
|
| 1281 |
+
"rewards/margins": 0.061758268624544144,
|
| 1282 |
+
"rewards/rejected": 0.055300913751125336,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": -0.005747838411480188,
|
| 1289 |
+
"logits/rejected": 0.02690596505999565,
|
| 1290 |
+
"logps/chosen": -485.0928649902344,
|
| 1291 |
+
"logps/rejected": -488.77349853515625,
|
| 1292 |
+
"loss": 0.1824,
|
| 1293 |
+
"rewards/accuracies": 0.5625,
|
| 1294 |
+
"rewards/chosen": 0.10394562780857086,
|
| 1295 |
+
"rewards/margins": 0.04496193677186966,
|
| 1296 |
+
"rewards/rejected": 0.058983683586120605,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": 0.04409351199865341,
|
| 1303 |
+
"logits/rejected": 0.023466479033231735,
|
| 1304 |
+
"logps/chosen": -516.257080078125,
|
| 1305 |
+
"logps/rejected": -529.1635131835938,
|
| 1306 |
+
"loss": 0.186,
|
| 1307 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 1308 |
+
"rewards/chosen": 0.11666563898324966,
|
| 1309 |
+
"rewards/margins": 0.0654011145234108,
|
| 1310 |
+
"rewards/rejected": 0.051264531910419464,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": 0.029077816754579544,
|
| 1317 |
+
"logits/rejected": 0.1013563722372055,
|
| 1318 |
+
"logps/chosen": -449.57379150390625,
|
| 1319 |
+
"logps/rejected": -469.8511657714844,
|
| 1320 |
+
"loss": 0.1967,
|
| 1321 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 1322 |
+
"rewards/chosen": 0.10130287706851959,
|
| 1323 |
+
"rewards/margins": 0.050037987530231476,
|
| 1324 |
+
"rewards/rejected": 0.05126488208770752,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.1892308688214647,
|
| 1332 |
+
"train_runtime": 7960.6994,
|
| 1333 |
+
"train_samples_per_second": 3.769,
|
| 1334 |
+
"train_steps_per_second": 0.118
|
| 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 |
+
}
|