Qin Liu
commited on
Commit
•
a0486eb
1
Parent(s):
bbc1ad4
Model save
Browse files- README.md +62 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1557 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: Jackie999/llama3-sudo-5epochs-tofu_full_sft
|
9 |
+
model-index:
|
10 |
+
- name: llama3-sudo-dpo-instruct-20epochs-forget10-1sft-2lora
|
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 |
+
# llama3-sudo-dpo-instruct-20epochs-forget10-1sft-2lora
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [Jackie999/llama3-sudo-5epochs-tofu_full_sft](https://huggingface.co/Jackie999/llama3-sudo-5epochs-tofu_full_sft) on an unknown 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: 2
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- num_devices: 2
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 16
|
46 |
+
- total_eval_batch_size: 16
|
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: 20
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- PEFT 0.12.0
|
59 |
+
- Transformers 4.44.0
|
60 |
+
- Pytorch 2.1.2
|
61 |
+
- Datasets 3.0.0
|
62 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.07008945742505603,
|
5 |
+
"train_runtime": 8233.3372,
|
6 |
+
"train_samples": 800,
|
7 |
+
"train_samples_per_second": 1.943,
|
8 |
+
"train_steps_per_second": 0.121
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.07008945742505603,
|
5 |
+
"train_runtime": 8233.3372,
|
6 |
+
"train_samples": 800,
|
7 |
+
"train_samples_per_second": 1.943,
|
8 |
+
"train_steps_per_second": 0.121
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1557 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 0.35460313427884693,
|
14 |
+
"learning_rate": 5.0000000000000004e-08,
|
15 |
+
"logits/chosen": -1.8231227397918701,
|
16 |
+
"logits/rejected": -1.5560479164123535,
|
17 |
+
"logps/chosen": -85.02825927734375,
|
18 |
+
"logps/rejected": -71.86117553710938,
|
19 |
+
"loss": 0.6931,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.2,
|
28 |
+
"grad_norm": 0.30411563112440204,
|
29 |
+
"learning_rate": 5.000000000000001e-07,
|
30 |
+
"logits/chosen": -1.7207438945770264,
|
31 |
+
"logits/rejected": -1.698093295097351,
|
32 |
+
"logps/chosen": -75.15734100341797,
|
33 |
+
"logps/rejected": -80.09143829345703,
|
34 |
+
"loss": 0.6931,
|
35 |
+
"rewards/accuracies": 0.5,
|
36 |
+
"rewards/chosen": 9.971462714020163e-05,
|
37 |
+
"rewards/margins": 0.0002858855586964637,
|
38 |
+
"rewards/rejected": -0.00018617100431583822,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.4,
|
43 |
+
"grad_norm": 0.29583445812044185,
|
44 |
+
"learning_rate": 1.0000000000000002e-06,
|
45 |
+
"logits/chosen": -1.7815284729003906,
|
46 |
+
"logits/rejected": -1.7640860080718994,
|
47 |
+
"logps/chosen": -74.8746566772461,
|
48 |
+
"logps/rejected": -77.6731185913086,
|
49 |
+
"loss": 0.6927,
|
50 |
+
"rewards/accuracies": 0.6499999761581421,
|
51 |
+
"rewards/chosen": 0.00024838969693519175,
|
52 |
+
"rewards/margins": 0.0008968595648184419,
|
53 |
+
"rewards/rejected": -0.0006484698969870806,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.6,
|
58 |
+
"grad_norm": 0.2966957448432536,
|
59 |
+
"learning_rate": 1.5e-06,
|
60 |
+
"logits/chosen": -1.739800214767456,
|
61 |
+
"logits/rejected": -1.7370967864990234,
|
62 |
+
"logps/chosen": -75.44456481933594,
|
63 |
+
"logps/rejected": -77.48068237304688,
|
64 |
+
"loss": 0.6917,
|
65 |
+
"rewards/accuracies": 0.875,
|
66 |
+
"rewards/chosen": 0.0010354876285418868,
|
67 |
+
"rewards/margins": 0.0030451309867203236,
|
68 |
+
"rewards/rejected": -0.002009643241763115,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.8,
|
73 |
+
"grad_norm": 0.33102320941887775,
|
74 |
+
"learning_rate": 2.0000000000000003e-06,
|
75 |
+
"logits/chosen": -1.7791082859039307,
|
76 |
+
"logits/rejected": -1.733616590499878,
|
77 |
+
"logps/chosen": -76.32530212402344,
|
78 |
+
"logps/rejected": -75.00889587402344,
|
79 |
+
"loss": 0.689,
|
80 |
+
"rewards/accuracies": 1.0,
|
81 |
+
"rewards/chosen": 0.007160990033298731,
|
82 |
+
"rewards/margins": 0.008440766483545303,
|
83 |
+
"rewards/rejected": -0.0012797765666618943,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.0,
|
88 |
+
"grad_norm": 0.5247728899006847,
|
89 |
+
"learning_rate": 2.5e-06,
|
90 |
+
"logits/chosen": -1.7112547159194946,
|
91 |
+
"logits/rejected": -1.7392151355743408,
|
92 |
+
"logps/chosen": -73.26392364501953,
|
93 |
+
"logps/rejected": -79.31649780273438,
|
94 |
+
"loss": 0.6832,
|
95 |
+
"rewards/accuracies": 1.0,
|
96 |
+
"rewards/chosen": 0.013615945354104042,
|
97 |
+
"rewards/margins": 0.019877230748534203,
|
98 |
+
"rewards/rejected": -0.006261286325752735,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 1.2,
|
103 |
+
"grad_norm": 0.4135013743852781,
|
104 |
+
"learning_rate": 3e-06,
|
105 |
+
"logits/chosen": -1.732405424118042,
|
106 |
+
"logits/rejected": -1.7449699640274048,
|
107 |
+
"logps/chosen": -71.77066040039062,
|
108 |
+
"logps/rejected": -80.100341796875,
|
109 |
+
"loss": 0.6732,
|
110 |
+
"rewards/accuracies": 1.0,
|
111 |
+
"rewards/chosen": 0.024410251528024673,
|
112 |
+
"rewards/margins": 0.03932947292923927,
|
113 |
+
"rewards/rejected": -0.01491921953856945,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.4,
|
118 |
+
"grad_norm": 0.392415113956775,
|
119 |
+
"learning_rate": 3.5e-06,
|
120 |
+
"logits/chosen": -1.716195821762085,
|
121 |
+
"logits/rejected": -1.731308937072754,
|
122 |
+
"logps/chosen": -72.06253051757812,
|
123 |
+
"logps/rejected": -80.39039611816406,
|
124 |
+
"loss": 0.6542,
|
125 |
+
"rewards/accuracies": 1.0,
|
126 |
+
"rewards/chosen": 0.04634103178977966,
|
127 |
+
"rewards/margins": 0.07862894982099533,
|
128 |
+
"rewards/rejected": -0.032287921756505966,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.6,
|
133 |
+
"grad_norm": 0.5321176658546207,
|
134 |
+
"learning_rate": 4.000000000000001e-06,
|
135 |
+
"logits/chosen": -1.69076406955719,
|
136 |
+
"logits/rejected": -1.6509063243865967,
|
137 |
+
"logps/chosen": -68.82267761230469,
|
138 |
+
"logps/rejected": -88.67816162109375,
|
139 |
+
"loss": 0.605,
|
140 |
+
"rewards/accuracies": 1.0,
|
141 |
+
"rewards/chosen": 0.08192411065101624,
|
142 |
+
"rewards/margins": 0.19158878922462463,
|
143 |
+
"rewards/rejected": -0.1096646636724472,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.8,
|
148 |
+
"grad_norm": 0.5696532480733786,
|
149 |
+
"learning_rate": 4.5e-06,
|
150 |
+
"logits/chosen": -1.7061433792114258,
|
151 |
+
"logits/rejected": -1.684195876121521,
|
152 |
+
"logps/chosen": -59.4539680480957,
|
153 |
+
"logps/rejected": -106.4749526977539,
|
154 |
+
"loss": 0.4742,
|
155 |
+
"rewards/accuracies": 1.0,
|
156 |
+
"rewards/chosen": 0.18270966410636902,
|
157 |
+
"rewards/margins": 0.5085535645484924,
|
158 |
+
"rewards/rejected": -0.325843870639801,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 2.0,
|
163 |
+
"grad_norm": 0.3568428380556091,
|
164 |
+
"learning_rate": 5e-06,
|
165 |
+
"logits/chosen": -1.5610880851745605,
|
166 |
+
"logits/rejected": -1.4533908367156982,
|
167 |
+
"logps/chosen": -48.31792449951172,
|
168 |
+
"logps/rejected": -164.77566528320312,
|
169 |
+
"loss": 0.3175,
|
170 |
+
"rewards/accuracies": 1.0,
|
171 |
+
"rewards/chosen": 0.2694377899169922,
|
172 |
+
"rewards/margins": 1.1592490673065186,
|
173 |
+
"rewards/rejected": -0.8898113965988159,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.2,
|
178 |
+
"grad_norm": 0.28794719016802656,
|
179 |
+
"learning_rate": 4.99847706754774e-06,
|
180 |
+
"logits/chosen": -1.5363928079605103,
|
181 |
+
"logits/rejected": -1.4212225675582886,
|
182 |
+
"logps/chosen": -42.558448791503906,
|
183 |
+
"logps/rejected": -187.63729858398438,
|
184 |
+
"loss": 0.2626,
|
185 |
+
"rewards/accuracies": 1.0,
|
186 |
+
"rewards/chosen": 0.39137277007102966,
|
187 |
+
"rewards/margins": 1.5502681732177734,
|
188 |
+
"rewards/rejected": -1.1588953733444214,
|
189 |
+
"step": 110
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 2.4,
|
193 |
+
"grad_norm": 0.15078063761313237,
|
194 |
+
"learning_rate": 4.993910125649561e-06,
|
195 |
+
"logits/chosen": -1.51887845993042,
|
196 |
+
"logits/rejected": -1.437011957168579,
|
197 |
+
"logps/chosen": -38.434608459472656,
|
198 |
+
"logps/rejected": -232.57766723632812,
|
199 |
+
"loss": 0.223,
|
200 |
+
"rewards/accuracies": 1.0,
|
201 |
+
"rewards/chosen": 0.42294931411743164,
|
202 |
+
"rewards/margins": 2.0381760597229004,
|
203 |
+
"rewards/rejected": -1.6152267456054688,
|
204 |
+
"step": 120
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 2.6,
|
208 |
+
"grad_norm": 0.4347861863265109,
|
209 |
+
"learning_rate": 4.986304738420684e-06,
|
210 |
+
"logits/chosen": -1.3788427114486694,
|
211 |
+
"logits/rejected": -1.37319016456604,
|
212 |
+
"logps/chosen": -33.37788391113281,
|
213 |
+
"logps/rejected": -288.50018310546875,
|
214 |
+
"loss": 0.1776,
|
215 |
+
"rewards/accuracies": 1.0,
|
216 |
+
"rewards/chosen": 0.44394317269325256,
|
217 |
+
"rewards/margins": 2.571049928665161,
|
218 |
+
"rewards/rejected": -2.1271069049835205,
|
219 |
+
"step": 130
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.8,
|
223 |
+
"grad_norm": 0.7461810630936248,
|
224 |
+
"learning_rate": 4.975670171853926e-06,
|
225 |
+
"logits/chosen": -1.190661072731018,
|
226 |
+
"logits/rejected": -1.1670948266983032,
|
227 |
+
"logps/chosen": -32.81340026855469,
|
228 |
+
"logps/rejected": -336.36962890625,
|
229 |
+
"loss": 0.1102,
|
230 |
+
"rewards/accuracies": 1.0,
|
231 |
+
"rewards/chosen": 0.4285716414451599,
|
232 |
+
"rewards/margins": 3.032412528991699,
|
233 |
+
"rewards/rejected": -2.6038408279418945,
|
234 |
+
"step": 140
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 3.0,
|
238 |
+
"grad_norm": 0.053630215551159044,
|
239 |
+
"learning_rate": 4.962019382530521e-06,
|
240 |
+
"logits/chosen": -1.1552760601043701,
|
241 |
+
"logits/rejected": -1.1048529148101807,
|
242 |
+
"logps/chosen": -60.1913948059082,
|
243 |
+
"logps/rejected": -567.5430908203125,
|
244 |
+
"loss": 0.0207,
|
245 |
+
"rewards/accuracies": 1.0,
|
246 |
+
"rewards/chosen": 0.1675727218389511,
|
247 |
+
"rewards/margins": 5.098362922668457,
|
248 |
+
"rewards/rejected": -4.930790901184082,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 3.2,
|
253 |
+
"grad_norm": 0.031903287512855885,
|
254 |
+
"learning_rate": 4.9453690018345144e-06,
|
255 |
+
"logits/chosen": -1.0522866249084473,
|
256 |
+
"logits/rejected": -1.0280696153640747,
|
257 |
+
"logps/chosen": -102.0748062133789,
|
258 |
+
"logps/rejected": -891.6737060546875,
|
259 |
+
"loss": 0.0036,
|
260 |
+
"rewards/accuracies": 1.0,
|
261 |
+
"rewards/chosen": -0.2856892943382263,
|
262 |
+
"rewards/margins": 7.848362922668457,
|
263 |
+
"rewards/rejected": -8.134051322937012,
|
264 |
+
"step": 160
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 3.4,
|
268 |
+
"grad_norm": 0.0197914954559647,
|
269 |
+
"learning_rate": 4.925739315689991e-06,
|
270 |
+
"logits/chosen": -1.1597774028778076,
|
271 |
+
"logits/rejected": -1.1589906215667725,
|
272 |
+
"logps/chosen": -61.60524368286133,
|
273 |
+
"logps/rejected": -1039.020751953125,
|
274 |
+
"loss": 0.0022,
|
275 |
+
"rewards/accuracies": 1.0,
|
276 |
+
"rewards/chosen": 0.12755107879638672,
|
277 |
+
"rewards/margins": 9.746142387390137,
|
278 |
+
"rewards/rejected": -9.61859130859375,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 3.6,
|
283 |
+
"grad_norm": 0.023011571746249113,
|
284 |
+
"learning_rate": 4.903154239845798e-06,
|
285 |
+
"logits/chosen": -1.2340686321258545,
|
286 |
+
"logits/rejected": -1.0457987785339355,
|
287 |
+
"logps/chosen": -59.74028778076172,
|
288 |
+
"logps/rejected": -1156.054931640625,
|
289 |
+
"loss": 0.0014,
|
290 |
+
"rewards/accuracies": 1.0,
|
291 |
+
"rewards/chosen": 0.25307127833366394,
|
292 |
+
"rewards/margins": 11.132636070251465,
|
293 |
+
"rewards/rejected": -10.879566192626953,
|
294 |
+
"step": 180
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 3.8,
|
298 |
+
"grad_norm": 0.010025707600426755,
|
299 |
+
"learning_rate": 4.8776412907378845e-06,
|
300 |
+
"logits/chosen": -1.0119726657867432,
|
301 |
+
"logits/rejected": -1.0299015045166016,
|
302 |
+
"logps/chosen": -51.19286346435547,
|
303 |
+
"logps/rejected": -1030.427490234375,
|
304 |
+
"loss": 0.0015,
|
305 |
+
"rewards/accuracies": 1.0,
|
306 |
+
"rewards/chosen": 0.22199800610542297,
|
307 |
+
"rewards/margins": 9.714365005493164,
|
308 |
+
"rewards/rejected": -9.492366790771484,
|
309 |
+
"step": 190
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 4.0,
|
313 |
+
"grad_norm": 0.009363825045997377,
|
314 |
+
"learning_rate": 4.849231551964771e-06,
|
315 |
+
"logits/chosen": -1.1452789306640625,
|
316 |
+
"logits/rejected": -1.0538662672042847,
|
317 |
+
"logps/chosen": -55.855430603027344,
|
318 |
+
"logps/rejected": -1116.4219970703125,
|
319 |
+
"loss": 0.0012,
|
320 |
+
"rewards/accuracies": 1.0,
|
321 |
+
"rewards/chosen": 0.2577177882194519,
|
322 |
+
"rewards/margins": 10.68994140625,
|
323 |
+
"rewards/rejected": -10.43222427368164,
|
324 |
+
"step": 200
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 4.2,
|
328 |
+
"grad_norm": 0.007917186035092368,
|
329 |
+
"learning_rate": 4.817959636416969e-06,
|
330 |
+
"logits/chosen": -0.979863166809082,
|
331 |
+
"logits/rejected": -0.954973042011261,
|
332 |
+
"logps/chosen": -51.2191276550293,
|
333 |
+
"logps/rejected": -1067.7679443359375,
|
334 |
+
"loss": 0.0012,
|
335 |
+
"rewards/accuracies": 1.0,
|
336 |
+
"rewards/chosen": 0.21226799488067627,
|
337 |
+
"rewards/margins": 10.104147911071777,
|
338 |
+
"rewards/rejected": -9.89188003540039,
|
339 |
+
"step": 210
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 4.4,
|
343 |
+
"grad_norm": 0.004467951143379201,
|
344 |
+
"learning_rate": 4.783863644106502e-06,
|
345 |
+
"logits/chosen": -1.0173983573913574,
|
346 |
+
"logits/rejected": -0.9798928499221802,
|
347 |
+
"logps/chosen": -52.295379638671875,
|
348 |
+
"logps/rejected": -1050.406494140625,
|
349 |
+
"loss": 0.001,
|
350 |
+
"rewards/accuracies": 1.0,
|
351 |
+
"rewards/chosen": 0.21525339782238007,
|
352 |
+
"rewards/margins": 9.93811321258545,
|
353 |
+
"rewards/rejected": -9.722859382629395,
|
354 |
+
"step": 220
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 4.6,
|
358 |
+
"grad_norm": 0.0036885023764270065,
|
359 |
+
"learning_rate": 4.746985115747918e-06,
|
360 |
+
"logits/chosen": -1.1039237976074219,
|
361 |
+
"logits/rejected": -0.9902089238166809,
|
362 |
+
"logps/chosen": -56.54585647583008,
|
363 |
+
"logps/rejected": -1109.8258056640625,
|
364 |
+
"loss": 0.0008,
|
365 |
+
"rewards/accuracies": 1.0,
|
366 |
+
"rewards/chosen": 0.2429007589817047,
|
367 |
+
"rewards/margins": 10.61030101776123,
|
368 |
+
"rewards/rejected": -10.367398262023926,
|
369 |
+
"step": 230
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 4.8,
|
373 |
+
"grad_norm": 0.0065247264850717725,
|
374 |
+
"learning_rate": 4.707368982147318e-06,
|
375 |
+
"logits/chosen": -1.1152589321136475,
|
376 |
+
"logits/rejected": -1.0077005624771118,
|
377 |
+
"logps/chosen": -54.775856018066406,
|
378 |
+
"logps/rejected": -1131.518310546875,
|
379 |
+
"loss": 0.0008,
|
380 |
+
"rewards/accuracies": 1.0,
|
381 |
+
"rewards/chosen": 0.22144417464733124,
|
382 |
+
"rewards/margins": 10.786369323730469,
|
383 |
+
"rewards/rejected": -10.564926147460938,
|
384 |
+
"step": 240
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 5.0,
|
388 |
+
"grad_norm": 0.0032674373668132675,
|
389 |
+
"learning_rate": 4.665063509461098e-06,
|
390 |
+
"logits/chosen": -1.0255931615829468,
|
391 |
+
"logits/rejected": -0.9475139379501343,
|
392 |
+
"logps/chosen": -56.231163024902344,
|
393 |
+
"logps/rejected": -1138.18115234375,
|
394 |
+
"loss": 0.0008,
|
395 |
+
"rewards/accuracies": 1.0,
|
396 |
+
"rewards/chosen": 0.22440902888774872,
|
397 |
+
"rewards/margins": 10.85453987121582,
|
398 |
+
"rewards/rejected": -10.630131721496582,
|
399 |
+
"step": 250
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 5.2,
|
403 |
+
"grad_norm": 0.004115527916331285,
|
404 |
+
"learning_rate": 4.620120240391065e-06,
|
405 |
+
"logits/chosen": -1.0400116443634033,
|
406 |
+
"logits/rejected": -0.9953556060791016,
|
407 |
+
"logps/chosen": -54.63758087158203,
|
408 |
+
"logps/rejected": -1113.4554443359375,
|
409 |
+
"loss": 0.0007,
|
410 |
+
"rewards/accuracies": 1.0,
|
411 |
+
"rewards/chosen": 0.21181125938892365,
|
412 |
+
"rewards/margins": 10.56176471710205,
|
413 |
+
"rewards/rejected": -10.34995174407959,
|
414 |
+
"step": 260
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 5.4,
|
418 |
+
"grad_norm": 0.0030662391394572284,
|
419 |
+
"learning_rate": 4.572593931387604e-06,
|
420 |
+
"logits/chosen": -1.100754976272583,
|
421 |
+
"logits/rejected": -0.9190059900283813,
|
422 |
+
"logps/chosen": -55.8875846862793,
|
423 |
+
"logps/rejected": -1182.8133544921875,
|
424 |
+
"loss": 0.0007,
|
425 |
+
"rewards/accuracies": 1.0,
|
426 |
+
"rewards/chosen": 0.2545715868473053,
|
427 |
+
"rewards/margins": 11.359747886657715,
|
428 |
+
"rewards/rejected": -11.105175018310547,
|
429 |
+
"step": 270
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 5.6,
|
433 |
+
"grad_norm": 0.004246284055742857,
|
434 |
+
"learning_rate": 4.522542485937369e-06,
|
435 |
+
"logits/chosen": -1.0873005390167236,
|
436 |
+
"logits/rejected": -0.91912841796875,
|
437 |
+
"logps/chosen": -57.15370559692383,
|
438 |
+
"logps/rejected": -1198.202392578125,
|
439 |
+
"loss": 0.0007,
|
440 |
+
"rewards/accuracies": 1.0,
|
441 |
+
"rewards/chosen": 0.24588795006275177,
|
442 |
+
"rewards/margins": 11.502182960510254,
|
443 |
+
"rewards/rejected": -11.256293296813965,
|
444 |
+
"step": 280
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 5.8,
|
448 |
+
"grad_norm": 0.004139329336955742,
|
449 |
+
"learning_rate": 4.470026884016805e-06,
|
450 |
+
"logits/chosen": -0.9481426477432251,
|
451 |
+
"logits/rejected": -0.9623401761054993,
|
452 |
+
"logps/chosen": -52.13285446166992,
|
453 |
+
"logps/rejected": -1074.572509765625,
|
454 |
+
"loss": 0.0007,
|
455 |
+
"rewards/accuracies": 1.0,
|
456 |
+
"rewards/chosen": 0.20849105715751648,
|
457 |
+
"rewards/margins": 10.169190406799316,
|
458 |
+
"rewards/rejected": -9.960699081420898,
|
459 |
+
"step": 290
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 6.0,
|
463 |
+
"grad_norm": 0.003034900790871541,
|
464 |
+
"learning_rate": 4.415111107797445e-06,
|
465 |
+
"logits/chosen": -1.0314205884933472,
|
466 |
+
"logits/rejected": -1.0098388195037842,
|
467 |
+
"logps/chosen": -54.42866134643555,
|
468 |
+
"logps/rejected": -1097.184326171875,
|
469 |
+
"loss": 0.0006,
|
470 |
+
"rewards/accuracies": 1.0,
|
471 |
+
"rewards/chosen": 0.20703566074371338,
|
472 |
+
"rewards/margins": 10.398859024047852,
|
473 |
+
"rewards/rejected": -10.19182300567627,
|
474 |
+
"step": 300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 6.2,
|
478 |
+
"grad_norm": 0.0038510374493456907,
|
479 |
+
"learning_rate": 4.357862063693486e-06,
|
480 |
+
"logits/chosen": -1.026374101638794,
|
481 |
+
"logits/rejected": -0.9435133934020996,
|
482 |
+
"logps/chosen": -53.9544792175293,
|
483 |
+
"logps/rejected": -1142.4066162109375,
|
484 |
+
"loss": 0.0006,
|
485 |
+
"rewards/accuracies": 1.0,
|
486 |
+
"rewards/chosen": 0.21439966559410095,
|
487 |
+
"rewards/margins": 10.869270324707031,
|
488 |
+
"rewards/rejected": -10.654870986938477,
|
489 |
+
"step": 310
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 6.4,
|
493 |
+
"grad_norm": 0.0035014469049547427,
|
494 |
+
"learning_rate": 4.2983495008466285e-06,
|
495 |
+
"logits/chosen": -1.105359673500061,
|
496 |
+
"logits/rejected": -0.9964410066604614,
|
497 |
+
"logps/chosen": -57.14154815673828,
|
498 |
+
"logps/rejected": -1162.7977294921875,
|
499 |
+
"loss": 0.0006,
|
500 |
+
"rewards/accuracies": 1.0,
|
501 |
+
"rewards/chosen": 0.21488821506500244,
|
502 |
+
"rewards/margins": 11.113906860351562,
|
503 |
+
"rewards/rejected": -10.899017333984375,
|
504 |
+
"step": 320
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 6.6,
|
508 |
+
"grad_norm": 0.002634385062559098,
|
509 |
+
"learning_rate": 4.236645926147493e-06,
|
510 |
+
"logits/chosen": -1.0640833377838135,
|
511 |
+
"logits/rejected": -0.9242901802062988,
|
512 |
+
"logps/chosen": -56.49944305419922,
|
513 |
+
"logps/rejected": -1212.7708740234375,
|
514 |
+
"loss": 0.0005,
|
515 |
+
"rewards/accuracies": 1.0,
|
516 |
+
"rewards/chosen": 0.23322686553001404,
|
517 |
+
"rewards/margins": 11.629671096801758,
|
518 |
+
"rewards/rejected": -11.396444320678711,
|
519 |
+
"step": 330
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 6.8,
|
523 |
+
"grad_norm": 0.0030996294667543192,
|
524 |
+
"learning_rate": 4.172826515897146e-06,
|
525 |
+
"logits/chosen": -1.082220435142517,
|
526 |
+
"logits/rejected": -0.9698995351791382,
|
527 |
+
"logps/chosen": -59.28369903564453,
|
528 |
+
"logps/rejected": -1214.587646484375,
|
529 |
+
"loss": 0.0005,
|
530 |
+
"rewards/accuracies": 1.0,
|
531 |
+
"rewards/chosen": 0.19337359070777893,
|
532 |
+
"rewards/margins": 11.616683959960938,
|
533 |
+
"rewards/rejected": -11.423309326171875,
|
534 |
+
"step": 340
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 7.0,
|
538 |
+
"grad_norm": 0.0015310049705482352,
|
539 |
+
"learning_rate": 4.106969024216348e-06,
|
540 |
+
"logits/chosen": -0.9850069284439087,
|
541 |
+
"logits/rejected": -0.9987241625785828,
|
542 |
+
"logps/chosen": -54.036949157714844,
|
543 |
+
"logps/rejected": -1109.0908203125,
|
544 |
+
"loss": 0.0006,
|
545 |
+
"rewards/accuracies": 1.0,
|
546 |
+
"rewards/chosen": 0.19889585673809052,
|
547 |
+
"rewards/margins": 10.489348411560059,
|
548 |
+
"rewards/rejected": -10.29045295715332,
|
549 |
+
"step": 350
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 7.2,
|
553 |
+
"grad_norm": 0.001899366605942392,
|
554 |
+
"learning_rate": 4.039153688314146e-06,
|
555 |
+
"logits/chosen": -1.0366054773330688,
|
556 |
+
"logits/rejected": -0.9512063264846802,
|
557 |
+
"logps/chosen": -56.377410888671875,
|
558 |
+
"logps/rejected": -1194.2122802734375,
|
559 |
+
"loss": 0.0005,
|
560 |
+
"rewards/accuracies": 1.0,
|
561 |
+
"rewards/chosen": 0.2178737223148346,
|
562 |
+
"rewards/margins": 11.424546241760254,
|
563 |
+
"rewards/rejected": -11.206673622131348,
|
564 |
+
"step": 360
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 7.4,
|
568 |
+
"grad_norm": 0.003085448477067617,
|
569 |
+
"learning_rate": 3.969463130731183e-06,
|
570 |
+
"logits/chosen": -1.058009147644043,
|
571 |
+
"logits/rejected": -0.9505330324172974,
|
572 |
+
"logps/chosen": -55.610870361328125,
|
573 |
+
"logps/rejected": -1222.853515625,
|
574 |
+
"loss": 0.0005,
|
575 |
+
"rewards/accuracies": 1.0,
|
576 |
+
"rewards/chosen": 0.2119036167860031,
|
577 |
+
"rewards/margins": 11.69975471496582,
|
578 |
+
"rewards/rejected": -11.4878511428833,
|
579 |
+
"step": 370
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 7.6,
|
583 |
+
"grad_norm": 0.002631100351440524,
|
584 |
+
"learning_rate": 3.897982258676867e-06,
|
585 |
+
"logits/chosen": -0.9967459440231323,
|
586 |
+
"logits/rejected": -1.021655797958374,
|
587 |
+
"logps/chosen": -52.216705322265625,
|
588 |
+
"logps/rejected": -1100.6519775390625,
|
589 |
+
"loss": 0.0005,
|
590 |
+
"rewards/accuracies": 1.0,
|
591 |
+
"rewards/chosen": 0.19106148183345795,
|
592 |
+
"rewards/margins": 10.369633674621582,
|
593 |
+
"rewards/rejected": -10.178572654724121,
|
594 |
+
"step": 380
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 7.8,
|
598 |
+
"grad_norm": 0.0031329070413845662,
|
599 |
+
"learning_rate": 3.824798160583012e-06,
|
600 |
+
"logits/chosen": -1.0442421436309814,
|
601 |
+
"logits/rejected": -0.9009174108505249,
|
602 |
+
"logps/chosen": -56.89820098876953,
|
603 |
+
"logps/rejected": -1184.45263671875,
|
604 |
+
"loss": 0.0005,
|
605 |
+
"rewards/accuracies": 1.0,
|
606 |
+
"rewards/chosen": 0.22130858898162842,
|
607 |
+
"rewards/margins": 11.319818496704102,
|
608 |
+
"rewards/rejected": -11.098509788513184,
|
609 |
+
"step": 390
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 8.0,
|
613 |
+
"grad_norm": 0.003423988945465294,
|
614 |
+
"learning_rate": 3.7500000000000005e-06,
|
615 |
+
"logits/chosen": -1.035902500152588,
|
616 |
+
"logits/rejected": -0.9636209607124329,
|
617 |
+
"logps/chosen": -56.99961471557617,
|
618 |
+
"logps/rejected": -1206.747802734375,
|
619 |
+
"loss": 0.0005,
|
620 |
+
"rewards/accuracies": 1.0,
|
621 |
+
"rewards/chosen": 0.18911413848400116,
|
622 |
+
"rewards/margins": 11.49039363861084,
|
623 |
+
"rewards/rejected": -11.301280975341797,
|
624 |
+
"step": 400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 8.2,
|
628 |
+
"grad_norm": 0.003864669112701001,
|
629 |
+
"learning_rate": 3.6736789069647273e-06,
|
630 |
+
"logits/chosen": -0.9635273218154907,
|
631 |
+
"logits/rejected": -0.8587255477905273,
|
632 |
+
"logps/chosen": -58.7963981628418,
|
633 |
+
"logps/rejected": -1161.4803466796875,
|
634 |
+
"loss": 0.0005,
|
635 |
+
"rewards/accuracies": 1.0,
|
636 |
+
"rewards/chosen": 0.19340120255947113,
|
637 |
+
"rewards/margins": 11.068787574768066,
|
638 |
+
"rewards/rejected": -10.875386238098145,
|
639 |
+
"step": 410
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 8.4,
|
643 |
+
"grad_norm": 0.003245040701864265,
|
644 |
+
"learning_rate": 3.595927866972694e-06,
|
645 |
+
"logits/chosen": -1.0136067867279053,
|
646 |
+
"logits/rejected": -0.9350364804267883,
|
647 |
+
"logps/chosen": -55.97736358642578,
|
648 |
+
"logps/rejected": -1197.21484375,
|
649 |
+
"loss": 0.0004,
|
650 |
+
"rewards/accuracies": 1.0,
|
651 |
+
"rewards/chosen": 0.20746412873268127,
|
652 |
+
"rewards/margins": 11.428886413574219,
|
653 |
+
"rewards/rejected": -11.221421241760254,
|
654 |
+
"step": 420
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 8.6,
|
658 |
+
"grad_norm": 0.0023560411348610777,
|
659 |
+
"learning_rate": 3.516841607689501e-06,
|
660 |
+
"logits/chosen": -0.9947836995124817,
|
661 |
+
"logits/rejected": -0.9126423597335815,
|
662 |
+
"logps/chosen": -57.561622619628906,
|
663 |
+
"logps/rejected": -1165.994384765625,
|
664 |
+
"loss": 0.0004,
|
665 |
+
"rewards/accuracies": 1.0,
|
666 |
+
"rewards/chosen": 0.18999549746513367,
|
667 |
+
"rewards/margins": 11.074243545532227,
|
668 |
+
"rewards/rejected": -10.884247779846191,
|
669 |
+
"step": 430
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 8.8,
|
673 |
+
"grad_norm": 0.0025971993823853895,
|
674 |
+
"learning_rate": 3.436516483539781e-06,
|
675 |
+
"logits/chosen": -1.0256311893463135,
|
676 |
+
"logits/rejected": -0.8973512649536133,
|
677 |
+
"logps/chosen": -59.285438537597656,
|
678 |
+
"logps/rejected": -1248.3521728515625,
|
679 |
+
"loss": 0.0004,
|
680 |
+
"rewards/accuracies": 1.0,
|
681 |
+
"rewards/chosen": 0.18996688723564148,
|
682 |
+
"rewards/margins": 11.936816215515137,
|
683 |
+
"rewards/rejected": -11.746848106384277,
|
684 |
+
"step": 440
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 9.0,
|
688 |
+
"grad_norm": 0.0032315637570330567,
|
689 |
+
"learning_rate": 3.3550503583141726e-06,
|
690 |
+
"logits/chosen": -1.0244309902191162,
|
691 |
+
"logits/rejected": -0.8780086636543274,
|
692 |
+
"logps/chosen": -57.84431076049805,
|
693 |
+
"logps/rejected": -1234.871337890625,
|
694 |
+
"loss": 0.0004,
|
695 |
+
"rewards/accuracies": 1.0,
|
696 |
+
"rewards/chosen": 0.1998531073331833,
|
697 |
+
"rewards/margins": 11.807432174682617,
|
698 |
+
"rewards/rejected": -11.607580184936523,
|
699 |
+
"step": 450
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 9.2,
|
703 |
+
"grad_norm": 0.0036226784518706475,
|
704 |
+
"learning_rate": 3.272542485937369e-06,
|
705 |
+
"logits/chosen": -0.9375013113021851,
|
706 |
+
"logits/rejected": -0.8737777471542358,
|
707 |
+
"logps/chosen": -54.31487274169922,
|
708 |
+
"logps/rejected": -1172.191162109375,
|
709 |
+
"loss": 0.0004,
|
710 |
+
"rewards/accuracies": 1.0,
|
711 |
+
"rewards/chosen": 0.19032403826713562,
|
712 |
+
"rewards/margins": 11.127653121948242,
|
713 |
+
"rewards/rejected": -10.937328338623047,
|
714 |
+
"step": 460
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 9.4,
|
718 |
+
"grad_norm": 0.002997930586361418,
|
719 |
+
"learning_rate": 3.189093389542498e-06,
|
720 |
+
"logits/chosen": -1.0432255268096924,
|
721 |
+
"logits/rejected": -0.9277008175849915,
|
722 |
+
"logps/chosen": -58.5209846496582,
|
723 |
+
"logps/rejected": -1200.554931640625,
|
724 |
+
"loss": 0.0004,
|
725 |
+
"rewards/accuracies": 1.0,
|
726 |
+
"rewards/chosen": 0.19790109992027283,
|
727 |
+
"rewards/margins": 11.468005180358887,
|
728 |
+
"rewards/rejected": -11.270103454589844,
|
729 |
+
"step": 470
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 9.6,
|
733 |
+
"grad_norm": 0.0022499622323506746,
|
734 |
+
"learning_rate": 3.1048047389991693e-06,
|
735 |
+
"logits/chosen": -1.0687272548675537,
|
736 |
+
"logits/rejected": -0.9239826202392578,
|
737 |
+
"logps/chosen": -60.52696990966797,
|
738 |
+
"logps/rejected": -1241.221435546875,
|
739 |
+
"loss": 0.0004,
|
740 |
+
"rewards/accuracies": 1.0,
|
741 |
+
"rewards/chosen": 0.18703293800354004,
|
742 |
+
"rewards/margins": 11.873010635375977,
|
743 |
+
"rewards/rejected": -11.685976028442383,
|
744 |
+
"step": 480
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 9.8,
|
748 |
+
"grad_norm": 0.0019412808634179527,
|
749 |
+
"learning_rate": 3.019779227044398e-06,
|
750 |
+
"logits/chosen": -0.9789573550224304,
|
751 |
+
"logits/rejected": -0.7663965225219727,
|
752 |
+
"logps/chosen": -61.904319763183594,
|
753 |
+
"logps/rejected": -1237.324951171875,
|
754 |
+
"loss": 0.0003,
|
755 |
+
"rewards/accuracies": 1.0,
|
756 |
+
"rewards/chosen": 0.1967342346906662,
|
757 |
+
"rewards/margins": 11.862494468688965,
|
758 |
+
"rewards/rejected": -11.66576099395752,
|
759 |
+
"step": 490
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 10.0,
|
763 |
+
"grad_norm": 0.002323126626066593,
|
764 |
+
"learning_rate": 2.9341204441673267e-06,
|
765 |
+
"logits/chosen": -1.0079948902130127,
|
766 |
+
"logits/rejected": -0.9249541163444519,
|
767 |
+
"logps/chosen": -58.3544807434082,
|
768 |
+
"logps/rejected": -1210.3780517578125,
|
769 |
+
"loss": 0.0004,
|
770 |
+
"rewards/accuracies": 1.0,
|
771 |
+
"rewards/chosen": 0.16591690480709076,
|
772 |
+
"rewards/margins": 11.488636016845703,
|
773 |
+
"rewards/rejected": -11.32271957397461,
|
774 |
+
"step": 500
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 10.2,
|
778 |
+
"grad_norm": 0.0018387058134298486,
|
779 |
+
"learning_rate": 2.847932752400164e-06,
|
780 |
+
"logits/chosen": -0.9845121502876282,
|
781 |
+
"logits/rejected": -0.8383527994155884,
|
782 |
+
"logps/chosen": -59.52973556518555,
|
783 |
+
"logps/rejected": -1259.748291015625,
|
784 |
+
"loss": 0.0004,
|
785 |
+
"rewards/accuracies": 1.0,
|
786 |
+
"rewards/chosen": 0.17635658383369446,
|
787 |
+
"rewards/margins": 12.032411575317383,
|
788 |
+
"rewards/rejected": -11.856054306030273,
|
789 |
+
"step": 510
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 10.4,
|
793 |
+
"grad_norm": 0.0013643138700466504,
|
794 |
+
"learning_rate": 2.761321158169134e-06,
|
795 |
+
"logits/chosen": -1.0216516256332397,
|
796 |
+
"logits/rejected": -0.9077258110046387,
|
797 |
+
"logps/chosen": -59.731300354003906,
|
798 |
+
"logps/rejected": -1231.614501953125,
|
799 |
+
"loss": 0.0004,
|
800 |
+
"rewards/accuracies": 1.0,
|
801 |
+
"rewards/chosen": 0.1921447217464447,
|
802 |
+
"rewards/margins": 11.769120216369629,
|
803 |
+
"rewards/rejected": -11.576974868774414,
|
804 |
+
"step": 520
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 10.6,
|
808 |
+
"grad_norm": 0.002977922307910112,
|
809 |
+
"learning_rate": 2.6743911843603134e-06,
|
810 |
+
"logits/chosen": -1.0051695108413696,
|
811 |
+
"logits/rejected": -0.8601359128952026,
|
812 |
+
"logps/chosen": -62.12017822265625,
|
813 |
+
"logps/rejected": -1268.072509765625,
|
814 |
+
"loss": 0.0003,
|
815 |
+
"rewards/accuracies": 1.0,
|
816 |
+
"rewards/chosen": 0.1786160171031952,
|
817 |
+
"rewards/margins": 12.141373634338379,
|
818 |
+
"rewards/rejected": -11.962759017944336,
|
819 |
+
"step": 530
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 10.8,
|
823 |
+
"grad_norm": 0.0019745371274113147,
|
824 |
+
"learning_rate": 2.587248741756253e-06,
|
825 |
+
"logits/chosen": -1.0047599077224731,
|
826 |
+
"logits/rejected": -0.8642932176589966,
|
827 |
+
"logps/chosen": -61.087615966796875,
|
828 |
+
"logps/rejected": -1251.1107177734375,
|
829 |
+
"loss": 0.0003,
|
830 |
+
"rewards/accuracies": 1.0,
|
831 |
+
"rewards/chosen": 0.18852102756500244,
|
832 |
+
"rewards/margins": 11.956985473632812,
|
833 |
+
"rewards/rejected": -11.768463134765625,
|
834 |
+
"step": 540
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 11.0,
|
838 |
+
"grad_norm": 0.0018986393686723218,
|
839 |
+
"learning_rate": 2.5e-06,
|
840 |
+
"logits/chosen": -1.0309114456176758,
|
841 |
+
"logits/rejected": -0.9270389676094055,
|
842 |
+
"logps/chosen": -59.46849822998047,
|
843 |
+
"logps/rejected": -1210.13720703125,
|
844 |
+
"loss": 0.0003,
|
845 |
+
"rewards/accuracies": 1.0,
|
846 |
+
"rewards/chosen": 0.18577028810977936,
|
847 |
+
"rewards/margins": 11.525289535522461,
|
848 |
+
"rewards/rejected": -11.339518547058105,
|
849 |
+
"step": 550
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 11.2,
|
853 |
+
"grad_norm": 0.0016611092816266825,
|
854 |
+
"learning_rate": 2.4127512582437486e-06,
|
855 |
+
"logits/chosen": -0.9609254598617554,
|
856 |
+
"logits/rejected": -0.9043042063713074,
|
857 |
+
"logps/chosen": -54.84800338745117,
|
858 |
+
"logps/rejected": -1216.4305419921875,
|
859 |
+
"loss": 0.0003,
|
860 |
+
"rewards/accuracies": 1.0,
|
861 |
+
"rewards/chosen": 0.20413394272327423,
|
862 |
+
"rewards/margins": 11.576135635375977,
|
863 |
+
"rewards/rejected": -11.372001647949219,
|
864 |
+
"step": 560
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 11.4,
|
868 |
+
"grad_norm": 0.0019080916476901313,
|
869 |
+
"learning_rate": 2.325608815639687e-06,
|
870 |
+
"logits/chosen": -0.9941130876541138,
|
871 |
+
"logits/rejected": -0.8515572547912598,
|
872 |
+
"logps/chosen": -59.786705017089844,
|
873 |
+
"logps/rejected": -1280.828857421875,
|
874 |
+
"loss": 0.0003,
|
875 |
+
"rewards/accuracies": 1.0,
|
876 |
+
"rewards/chosen": 0.19204822182655334,
|
877 |
+
"rewards/margins": 12.262724876403809,
|
878 |
+
"rewards/rejected": -12.070676803588867,
|
879 |
+
"step": 570
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 11.6,
|
883 |
+
"grad_norm": 0.001417529626290414,
|
884 |
+
"learning_rate": 2.238678841830867e-06,
|
885 |
+
"logits/chosen": -1.0167783498764038,
|
886 |
+
"logits/rejected": -0.8408117294311523,
|
887 |
+
"logps/chosen": -61.850563049316406,
|
888 |
+
"logps/rejected": -1273.6541748046875,
|
889 |
+
"loss": 0.0003,
|
890 |
+
"rewards/accuracies": 1.0,
|
891 |
+
"rewards/chosen": 0.17794856429100037,
|
892 |
+
"rewards/margins": 12.197797775268555,
|
893 |
+
"rewards/rejected": -12.019848823547363,
|
894 |
+
"step": 580
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 11.8,
|
898 |
+
"grad_norm": 0.001985700625240649,
|
899 |
+
"learning_rate": 2.1520672475998374e-06,
|
900 |
+
"logits/chosen": -0.9488497972488403,
|
901 |
+
"logits/rejected": -0.8910242319107056,
|
902 |
+
"logps/chosen": -56.951904296875,
|
903 |
+
"logps/rejected": -1185.1470947265625,
|
904 |
+
"loss": 0.0003,
|
905 |
+
"rewards/accuracies": 1.0,
|
906 |
+
"rewards/chosen": 0.17158612608909607,
|
907 |
+
"rewards/margins": 11.239965438842773,
|
908 |
+
"rewards/rejected": -11.068379402160645,
|
909 |
+
"step": 590
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 12.0,
|
913 |
+
"grad_norm": 0.0014036347657331724,
|
914 |
+
"learning_rate": 2.0658795558326745e-06,
|
915 |
+
"logits/chosen": -0.9536435008049011,
|
916 |
+
"logits/rejected": -0.8297941088676453,
|
917 |
+
"logps/chosen": -57.86296463012695,
|
918 |
+
"logps/rejected": -1237.7889404296875,
|
919 |
+
"loss": 0.0003,
|
920 |
+
"rewards/accuracies": 1.0,
|
921 |
+
"rewards/chosen": 0.1768932044506073,
|
922 |
+
"rewards/margins": 11.793856620788574,
|
923 |
+
"rewards/rejected": -11.616963386535645,
|
924 |
+
"step": 600
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 12.2,
|
928 |
+
"grad_norm": 0.0014637474046611807,
|
929 |
+
"learning_rate": 1.9802207729556023e-06,
|
930 |
+
"logits/chosen": -0.9591706395149231,
|
931 |
+
"logits/rejected": -0.8812329173088074,
|
932 |
+
"logps/chosen": -56.78215789794922,
|
933 |
+
"logps/rejected": -1231.258056640625,
|
934 |
+
"loss": 0.0003,
|
935 |
+
"rewards/accuracies": 1.0,
|
936 |
+
"rewards/chosen": 0.1855459213256836,
|
937 |
+
"rewards/margins": 11.722236633300781,
|
938 |
+
"rewards/rejected": -11.536690711975098,
|
939 |
+
"step": 610
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 12.4,
|
943 |
+
"grad_norm": 0.0017805033618398401,
|
944 |
+
"learning_rate": 1.895195261000831e-06,
|
945 |
+
"logits/chosen": -1.019749641418457,
|
946 |
+
"logits/rejected": -0.9892827868461609,
|
947 |
+
"logps/chosen": -58.21343994140625,
|
948 |
+
"logps/rejected": -1209.8052978515625,
|
949 |
+
"loss": 0.0003,
|
950 |
+
"rewards/accuracies": 1.0,
|
951 |
+
"rewards/chosen": 0.16973453760147095,
|
952 |
+
"rewards/margins": 11.481805801391602,
|
953 |
+
"rewards/rejected": -11.312070846557617,
|
954 |
+
"step": 620
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 12.6,
|
958 |
+
"grad_norm": 0.0011184561683295657,
|
959 |
+
"learning_rate": 1.8109066104575023e-06,
|
960 |
+
"logits/chosen": -0.9216413497924805,
|
961 |
+
"logits/rejected": -0.8319498300552368,
|
962 |
+
"logps/chosen": -58.66545486450195,
|
963 |
+
"logps/rejected": -1199.0224609375,
|
964 |
+
"loss": 0.0003,
|
965 |
+
"rewards/accuracies": 1.0,
|
966 |
+
"rewards/chosen": 0.17631840705871582,
|
967 |
+
"rewards/margins": 11.408339500427246,
|
968 |
+
"rewards/rejected": -11.232022285461426,
|
969 |
+
"step": 630
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 12.8,
|
973 |
+
"grad_norm": 0.0014408987665450045,
|
974 |
+
"learning_rate": 1.7274575140626318e-06,
|
975 |
+
"logits/chosen": -0.9979192614555359,
|
976 |
+
"logits/rejected": -0.7878575325012207,
|
977 |
+
"logps/chosen": -62.93827438354492,
|
978 |
+
"logps/rejected": -1300.874755859375,
|
979 |
+
"loss": 0.0003,
|
980 |
+
"rewards/accuracies": 1.0,
|
981 |
+
"rewards/chosen": 0.18857316672801971,
|
982 |
+
"rewards/margins": 12.50341510772705,
|
983 |
+
"rewards/rejected": -12.314840316772461,
|
984 |
+
"step": 640
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 13.0,
|
988 |
+
"grad_norm": 0.0020645792333772377,
|
989 |
+
"learning_rate": 1.6449496416858285e-06,
|
990 |
+
"logits/chosen": -0.9246803522109985,
|
991 |
+
"logits/rejected": -0.8380001783370972,
|
992 |
+
"logps/chosen": -57.9194221496582,
|
993 |
+
"logps/rejected": -1195.3837890625,
|
994 |
+
"loss": 0.0003,
|
995 |
+
"rewards/accuracies": 1.0,
|
996 |
+
"rewards/chosen": 0.16603608429431915,
|
997 |
+
"rewards/margins": 11.333303451538086,
|
998 |
+
"rewards/rejected": -11.167266845703125,
|
999 |
+
"step": 650
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 13.2,
|
1003 |
+
"grad_norm": 0.0015139495857028652,
|
1004 |
+
"learning_rate": 1.56348351646022e-06,
|
1005 |
+
"logits/chosen": -1.0453752279281616,
|
1006 |
+
"logits/rejected": -0.8043217658996582,
|
1007 |
+
"logps/chosen": -63.8051872253418,
|
1008 |
+
"logps/rejected": -1392.04443359375,
|
1009 |
+
"loss": 0.0002,
|
1010 |
+
"rewards/accuracies": 1.0,
|
1011 |
+
"rewards/chosen": 0.19428420066833496,
|
1012 |
+
"rewards/margins": 13.428848266601562,
|
1013 |
+
"rewards/rejected": -13.234565734863281,
|
1014 |
+
"step": 660
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 13.4,
|
1018 |
+
"grad_norm": 0.0013498029319408118,
|
1019 |
+
"learning_rate": 1.4831583923105e-06,
|
1020 |
+
"logits/chosen": -0.979832649230957,
|
1021 |
+
"logits/rejected": -0.8365589380264282,
|
1022 |
+
"logps/chosen": -60.9407844543457,
|
1023 |
+
"logps/rejected": -1260.807861328125,
|
1024 |
+
"loss": 0.0003,
|
1025 |
+
"rewards/accuracies": 1.0,
|
1026 |
+
"rewards/chosen": 0.16681666672229767,
|
1027 |
+
"rewards/margins": 12.033578872680664,
|
1028 |
+
"rewards/rejected": -11.866762161254883,
|
1029 |
+
"step": 670
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 13.6,
|
1033 |
+
"grad_norm": 0.0018616946971343861,
|
1034 |
+
"learning_rate": 1.4040721330273063e-06,
|
1035 |
+
"logits/chosen": -0.9041559100151062,
|
1036 |
+
"logits/rejected": -0.8964747190475464,
|
1037 |
+
"logps/chosen": -54.83356857299805,
|
1038 |
+
"logps/rejected": -1143.5806884765625,
|
1039 |
+
"loss": 0.0003,
|
1040 |
+
"rewards/accuracies": 1.0,
|
1041 |
+
"rewards/chosen": 0.16955164074897766,
|
1042 |
+
"rewards/margins": 10.786935806274414,
|
1043 |
+
"rewards/rejected": -10.617385864257812,
|
1044 |
+
"step": 680
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 13.8,
|
1048 |
+
"grad_norm": 0.0012150873329068216,
|
1049 |
+
"learning_rate": 1.3263210930352737e-06,
|
1050 |
+
"logits/chosen": -0.8522924184799194,
|
1051 |
+
"logits/rejected": -0.8536826968193054,
|
1052 |
+
"logps/chosen": -57.020355224609375,
|
1053 |
+
"logps/rejected": -1151.3582763671875,
|
1054 |
+
"loss": 0.0003,
|
1055 |
+
"rewards/accuracies": 1.0,
|
1056 |
+
"rewards/chosen": 0.16875942051410675,
|
1057 |
+
"rewards/margins": 10.881406784057617,
|
1058 |
+
"rewards/rejected": -10.712648391723633,
|
1059 |
+
"step": 690
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 14.0,
|
1063 |
+
"grad_norm": 0.0015006535309411454,
|
1064 |
+
"learning_rate": 1.2500000000000007e-06,
|
1065 |
+
"logits/chosen": -0.9550180435180664,
|
1066 |
+
"logits/rejected": -0.8258699178695679,
|
1067 |
+
"logps/chosen": -58.025535583496094,
|
1068 |
+
"logps/rejected": -1249.10546875,
|
1069 |
+
"loss": 0.0003,
|
1070 |
+
"rewards/accuracies": 1.0,
|
1071 |
+
"rewards/chosen": 0.17841221392154694,
|
1072 |
+
"rewards/margins": 11.912469863891602,
|
1073 |
+
"rewards/rejected": -11.73405647277832,
|
1074 |
+
"step": 700
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 14.2,
|
1078 |
+
"grad_norm": 0.0015715381830458688,
|
1079 |
+
"learning_rate": 1.1752018394169882e-06,
|
1080 |
+
"logits/chosen": -0.9631673693656921,
|
1081 |
+
"logits/rejected": -0.8420494794845581,
|
1082 |
+
"logps/chosen": -60.133888244628906,
|
1083 |
+
"logps/rejected": -1249.9853515625,
|
1084 |
+
"loss": 0.0002,
|
1085 |
+
"rewards/accuracies": 1.0,
|
1086 |
+
"rewards/chosen": 0.1643882542848587,
|
1087 |
+
"rewards/margins": 11.908964157104492,
|
1088 |
+
"rewards/rejected": -11.744573593139648,
|
1089 |
+
"step": 710
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 14.4,
|
1093 |
+
"grad_norm": 0.0013660785683358696,
|
1094 |
+
"learning_rate": 1.1020177413231334e-06,
|
1095 |
+
"logits/chosen": -0.8709633946418762,
|
1096 |
+
"logits/rejected": -0.8834745287895203,
|
1097 |
+
"logps/chosen": -54.35590362548828,
|
1098 |
+
"logps/rejected": -1181.2337646484375,
|
1099 |
+
"loss": 0.0003,
|
1100 |
+
"rewards/accuracies": 1.0,
|
1101 |
+
"rewards/chosen": 0.17913100123405457,
|
1102 |
+
"rewards/margins": 11.173266410827637,
|
1103 |
+
"rewards/rejected": -10.994134902954102,
|
1104 |
+
"step": 720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 14.6,
|
1108 |
+
"grad_norm": 0.0016180177521581223,
|
1109 |
+
"learning_rate": 1.0305368692688175e-06,
|
1110 |
+
"logits/chosen": -0.9120365381240845,
|
1111 |
+
"logits/rejected": -0.7947243452072144,
|
1112 |
+
"logps/chosen": -59.50437545776367,
|
1113 |
+
"logps/rejected": -1239.4515380859375,
|
1114 |
+
"loss": 0.0003,
|
1115 |
+
"rewards/accuracies": 1.0,
|
1116 |
+
"rewards/chosen": 0.15415535867214203,
|
1117 |
+
"rewards/margins": 11.778593063354492,
|
1118 |
+
"rewards/rejected": -11.624438285827637,
|
1119 |
+
"step": 730
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 14.8,
|
1123 |
+
"grad_norm": 0.0009131551082822374,
|
1124 |
+
"learning_rate": 9.608463116858544e-07,
|
1125 |
+
"logits/chosen": -0.9982080459594727,
|
1126 |
+
"logits/rejected": -0.8127807378768921,
|
1127 |
+
"logps/chosen": -62.322227478027344,
|
1128 |
+
"logps/rejected": -1302.121337890625,
|
1129 |
+
"loss": 0.0003,
|
1130 |
+
"rewards/accuracies": 1.0,
|
1131 |
+
"rewards/chosen": 0.17191007733345032,
|
1132 |
+
"rewards/margins": 12.468157768249512,
|
1133 |
+
"rewards/rejected": -12.296248435974121,
|
1134 |
+
"step": 740
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 15.0,
|
1138 |
+
"grad_norm": 0.004586809943697903,
|
1139 |
+
"learning_rate": 8.930309757836517e-07,
|
1140 |
+
"logits/chosen": -0.9402343034744263,
|
1141 |
+
"logits/rejected": -0.8805861473083496,
|
1142 |
+
"logps/chosen": -56.05229568481445,
|
1143 |
+
"logps/rejected": -1228.699951171875,
|
1144 |
+
"loss": 0.0003,
|
1145 |
+
"rewards/accuracies": 1.0,
|
1146 |
+
"rewards/chosen": 0.19031982123851776,
|
1147 |
+
"rewards/margins": 11.688825607299805,
|
1148 |
+
"rewards/rejected": -11.498506546020508,
|
1149 |
+
"step": 750
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 15.2,
|
1153 |
+
"grad_norm": 0.001855508098495543,
|
1154 |
+
"learning_rate": 8.271734841028553e-07,
|
1155 |
+
"logits/chosen": -0.9797531962394714,
|
1156 |
+
"logits/rejected": -0.8751746416091919,
|
1157 |
+
"logps/chosen": -59.685791015625,
|
1158 |
+
"logps/rejected": -1249.674560546875,
|
1159 |
+
"loss": 0.0003,
|
1160 |
+
"rewards/accuracies": 1.0,
|
1161 |
+
"rewards/chosen": 0.17554932832717896,
|
1162 |
+
"rewards/margins": 11.926473617553711,
|
1163 |
+
"rewards/rejected": -11.750923156738281,
|
1164 |
+
"step": 760
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 15.4,
|
1168 |
+
"grad_norm": 0.0009559205861326566,
|
1169 |
+
"learning_rate": 7.633540738525066e-07,
|
1170 |
+
"logits/chosen": -0.9692495465278625,
|
1171 |
+
"logits/rejected": -0.8025411367416382,
|
1172 |
+
"logps/chosen": -60.701194763183594,
|
1173 |
+
"logps/rejected": -1309.8841552734375,
|
1174 |
+
"loss": 0.0002,
|
1175 |
+
"rewards/accuracies": 1.0,
|
1176 |
+
"rewards/chosen": 0.183763325214386,
|
1177 |
+
"rewards/margins": 12.551748275756836,
|
1178 |
+
"rewards/rejected": -12.367984771728516,
|
1179 |
+
"step": 770
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 15.6,
|
1183 |
+
"grad_norm": 0.0016221612239979135,
|
1184 |
+
"learning_rate": 7.016504991533727e-07,
|
1185 |
+
"logits/chosen": -0.9435825347900391,
|
1186 |
+
"logits/rejected": -0.873455822467804,
|
1187 |
+
"logps/chosen": -58.68913650512695,
|
1188 |
+
"logps/rejected": -1226.319091796875,
|
1189 |
+
"loss": 0.0003,
|
1190 |
+
"rewards/accuracies": 1.0,
|
1191 |
+
"rewards/chosen": 0.16507244110107422,
|
1192 |
+
"rewards/margins": 11.652719497680664,
|
1193 |
+
"rewards/rejected": -11.487646102905273,
|
1194 |
+
"step": 780
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 15.8,
|
1198 |
+
"grad_norm": 0.0011565013550164168,
|
1199 |
+
"learning_rate": 6.421379363065142e-07,
|
1200 |
+
"logits/chosen": -1.0095231533050537,
|
1201 |
+
"logits/rejected": -0.7704787850379944,
|
1202 |
+
"logps/chosen": -65.56999206542969,
|
1203 |
+
"logps/rejected": -1337.3360595703125,
|
1204 |
+
"loss": 0.0003,
|
1205 |
+
"rewards/accuracies": 1.0,
|
1206 |
+
"rewards/chosen": 0.18380019068717957,
|
1207 |
+
"rewards/margins": 12.87743091583252,
|
1208 |
+
"rewards/rejected": -12.693631172180176,
|
1209 |
+
"step": 790
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 16.0,
|
1213 |
+
"grad_norm": 0.0012537423983021187,
|
1214 |
+
"learning_rate": 5.848888922025553e-07,
|
1215 |
+
"logits/chosen": -0.8937209248542786,
|
1216 |
+
"logits/rejected": -0.8747299313545227,
|
1217 |
+
"logps/chosen": -54.911643981933594,
|
1218 |
+
"logps/rejected": -1144.4791259765625,
|
1219 |
+
"loss": 0.0003,
|
1220 |
+
"rewards/accuracies": 1.0,
|
1221 |
+
"rewards/chosen": 0.16021445393562317,
|
1222 |
+
"rewards/margins": 10.787330627441406,
|
1223 |
+
"rewards/rejected": -10.627116203308105,
|
1224 |
+
"step": 800
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 16.2,
|
1228 |
+
"grad_norm": 0.0014373038754308242,
|
1229 |
+
"learning_rate": 5.299731159831953e-07,
|
1230 |
+
"logits/chosen": -0.9762552976608276,
|
1231 |
+
"logits/rejected": -0.8652079701423645,
|
1232 |
+
"logps/chosen": -58.197059631347656,
|
1233 |
+
"logps/rejected": -1232.221435546875,
|
1234 |
+
"loss": 0.0003,
|
1235 |
+
"rewards/accuracies": 1.0,
|
1236 |
+
"rewards/chosen": 0.1831381916999817,
|
1237 |
+
"rewards/margins": 11.740102767944336,
|
1238 |
+
"rewards/rejected": -11.556963920593262,
|
1239 |
+
"step": 810
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 16.4,
|
1243 |
+
"grad_norm": 0.000862440552553043,
|
1244 |
+
"learning_rate": 4.774575140626317e-07,
|
1245 |
+
"logits/chosen": -0.9985950589179993,
|
1246 |
+
"logits/rejected": -0.8936964273452759,
|
1247 |
+
"logps/chosen": -58.0911979675293,
|
1248 |
+
"logps/rejected": -1282.3681640625,
|
1249 |
+
"loss": 0.0003,
|
1250 |
+
"rewards/accuracies": 1.0,
|
1251 |
+
"rewards/chosen": 0.19094052910804749,
|
1252 |
+
"rewards/margins": 12.265246391296387,
|
1253 |
+
"rewards/rejected": -12.074307441711426,
|
1254 |
+
"step": 820
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 16.6,
|
1258 |
+
"grad_norm": 0.0011309096722098083,
|
1259 |
+
"learning_rate": 4.27406068612396e-07,
|
1260 |
+
"logits/chosen": -0.9642303586006165,
|
1261 |
+
"logits/rejected": -0.8438752293586731,
|
1262 |
+
"logps/chosen": -59.80333709716797,
|
1263 |
+
"logps/rejected": -1246.0048828125,
|
1264 |
+
"loss": 0.0002,
|
1265 |
+
"rewards/accuracies": 1.0,
|
1266 |
+
"rewards/chosen": 0.16420656442642212,
|
1267 |
+
"rewards/margins": 11.867765426635742,
|
1268 |
+
"rewards/rejected": -11.703559875488281,
|
1269 |
+
"step": 830
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 16.8,
|
1273 |
+
"grad_norm": 0.001634196377460084,
|
1274 |
+
"learning_rate": 3.798797596089351e-07,
|
1275 |
+
"logits/chosen": -0.9439367055892944,
|
1276 |
+
"logits/rejected": -0.8413814306259155,
|
1277 |
+
"logps/chosen": -59.905982971191406,
|
1278 |
+
"logps/rejected": -1256.216796875,
|
1279 |
+
"loss": 0.0003,
|
1280 |
+
"rewards/accuracies": 1.0,
|
1281 |
+
"rewards/chosen": 0.16103532910346985,
|
1282 |
+
"rewards/margins": 11.955886840820312,
|
1283 |
+
"rewards/rejected": -11.794851303100586,
|
1284 |
+
"step": 840
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 17.0,
|
1288 |
+
"grad_norm": 0.0011128513110797832,
|
1289 |
+
"learning_rate": 3.3493649053890325e-07,
|
1290 |
+
"logits/chosen": -0.9567734003067017,
|
1291 |
+
"logits/rejected": -0.7875978350639343,
|
1292 |
+
"logps/chosen": -61.99500274658203,
|
1293 |
+
"logps/rejected": -1306.9703369140625,
|
1294 |
+
"loss": 0.0002,
|
1295 |
+
"rewards/accuracies": 1.0,
|
1296 |
+
"rewards/chosen": 0.1775272786617279,
|
1297 |
+
"rewards/margins": 12.505702018737793,
|
1298 |
+
"rewards/rejected": -12.32817554473877,
|
1299 |
+
"step": 850
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 17.2,
|
1303 |
+
"grad_norm": 0.0013520172966032026,
|
1304 |
+
"learning_rate": 2.9263101785268253e-07,
|
1305 |
+
"logits/chosen": -0.9488283395767212,
|
1306 |
+
"logits/rejected": -0.8742234110832214,
|
1307 |
+
"logps/chosen": -56.80482864379883,
|
1308 |
+
"logps/rejected": -1268.548095703125,
|
1309 |
+
"loss": 0.0003,
|
1310 |
+
"rewards/accuracies": 1.0,
|
1311 |
+
"rewards/chosen": 0.17435792088508606,
|
1312 |
+
"rewards/margins": 12.08137321472168,
|
1313 |
+
"rewards/rejected": -11.907015800476074,
|
1314 |
+
"step": 860
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 17.4,
|
1318 |
+
"grad_norm": 0.0012511118706732029,
|
1319 |
+
"learning_rate": 2.53014884252083e-07,
|
1320 |
+
"logits/chosen": -1.0541223287582397,
|
1321 |
+
"logits/rejected": -0.81927490234375,
|
1322 |
+
"logps/chosen": -63.943763732910156,
|
1323 |
+
"logps/rejected": -1374.1676025390625,
|
1324 |
+
"loss": 0.0002,
|
1325 |
+
"rewards/accuracies": 1.0,
|
1326 |
+
"rewards/chosen": 0.18310335278511047,
|
1327 |
+
"rewards/margins": 13.212549209594727,
|
1328 |
+
"rewards/rejected": -13.029446601867676,
|
1329 |
+
"step": 870
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 17.6,
|
1333 |
+
"grad_norm": 0.0018809600968994445,
|
1334 |
+
"learning_rate": 2.1613635589349756e-07,
|
1335 |
+
"logits/chosen": -0.8839080929756165,
|
1336 |
+
"logits/rejected": -0.7969019412994385,
|
1337 |
+
"logps/chosen": -56.40065383911133,
|
1338 |
+
"logps/rejected": -1226.865478515625,
|
1339 |
+
"loss": 0.0003,
|
1340 |
+
"rewards/accuracies": 1.0,
|
1341 |
+
"rewards/chosen": 0.17095676064491272,
|
1342 |
+
"rewards/margins": 11.626653671264648,
|
1343 |
+
"rewards/rejected": -11.455695152282715,
|
1344 |
+
"step": 880
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 17.8,
|
1348 |
+
"grad_norm": 0.0016373893137363934,
|
1349 |
+
"learning_rate": 1.8204036358303173e-07,
|
1350 |
+
"logits/chosen": -0.9771726727485657,
|
1351 |
+
"logits/rejected": -0.8529565930366516,
|
1352 |
+
"logps/chosen": -57.20879364013672,
|
1353 |
+
"logps/rejected": -1290.327880859375,
|
1354 |
+
"loss": 0.0002,
|
1355 |
+
"rewards/accuracies": 1.0,
|
1356 |
+
"rewards/chosen": 0.18934224545955658,
|
1357 |
+
"rewards/margins": 12.324792861938477,
|
1358 |
+
"rewards/rejected": -12.135449409484863,
|
1359 |
+
"step": 890
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 18.0,
|
1363 |
+
"grad_norm": 0.000786600665947747,
|
1364 |
+
"learning_rate": 1.507684480352292e-07,
|
1365 |
+
"logits/chosen": -0.9094891548156738,
|
1366 |
+
"logits/rejected": -0.8147133588790894,
|
1367 |
+
"logps/chosen": -59.374755859375,
|
1368 |
+
"logps/rejected": -1234.203125,
|
1369 |
+
"loss": 0.0003,
|
1370 |
+
"rewards/accuracies": 1.0,
|
1371 |
+
"rewards/chosen": 0.1541765034198761,
|
1372 |
+
"rewards/margins": 11.714710235595703,
|
1373 |
+
"rewards/rejected": -11.560534477233887,
|
1374 |
+
"step": 900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 18.2,
|
1378 |
+
"grad_norm": 0.002709830744526596,
|
1379 |
+
"learning_rate": 1.223587092621162e-07,
|
1380 |
+
"logits/chosen": -1.00485098361969,
|
1381 |
+
"logits/rejected": -0.7558645606040955,
|
1382 |
+
"logps/chosen": -67.38685607910156,
|
1383 |
+
"logps/rejected": -1367.7635498046875,
|
1384 |
+
"loss": 0.0002,
|
1385 |
+
"rewards/accuracies": 1.0,
|
1386 |
+
"rewards/chosen": 0.17096880078315735,
|
1387 |
+
"rewards/margins": 13.181119918823242,
|
1388 |
+
"rewards/rejected": -13.010151863098145,
|
1389 |
+
"step": 910
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 18.4,
|
1393 |
+
"grad_norm": 0.0010941683716015594,
|
1394 |
+
"learning_rate": 9.684576015420277e-08,
|
1395 |
+
"logits/chosen": -0.9139689207077026,
|
1396 |
+
"logits/rejected": -0.8125830888748169,
|
1397 |
+
"logps/chosen": -58.29936599731445,
|
1398 |
+
"logps/rejected": -1264.84033203125,
|
1399 |
+
"loss": 0.0003,
|
1400 |
+
"rewards/accuracies": 1.0,
|
1401 |
+
"rewards/chosen": 0.16245688498020172,
|
1402 |
+
"rewards/margins": 12.02514934539795,
|
1403 |
+
"rewards/rejected": -11.862692832946777,
|
1404 |
+
"step": 920
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 18.6,
|
1408 |
+
"grad_norm": 0.001790071139550289,
|
1409 |
+
"learning_rate": 7.426068431000883e-08,
|
1410 |
+
"logits/chosen": -0.9928874969482422,
|
1411 |
+
"logits/rejected": -0.8945854306221008,
|
1412 |
+
"logps/chosen": -59.90386962890625,
|
1413 |
+
"logps/rejected": -1225.345458984375,
|
1414 |
+
"loss": 0.0002,
|
1415 |
+
"rewards/accuracies": 1.0,
|
1416 |
+
"rewards/chosen": 0.18468160927295685,
|
1417 |
+
"rewards/margins": 11.685681343078613,
|
1418 |
+
"rewards/rejected": -11.500999450683594,
|
1419 |
+
"step": 930
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 18.8,
|
1423 |
+
"grad_norm": 0.001444924500021094,
|
1424 |
+
"learning_rate": 5.463099816548578e-08,
|
1425 |
+
"logits/chosen": -0.8352192640304565,
|
1426 |
+
"logits/rejected": -0.8455368876457214,
|
1427 |
+
"logps/chosen": -53.367652893066406,
|
1428 |
+
"logps/rejected": -1094.0107421875,
|
1429 |
+
"loss": 0.0003,
|
1430 |
+
"rewards/accuracies": 1.0,
|
1431 |
+
"rewards/chosen": 0.15318068861961365,
|
1432 |
+
"rewards/margins": 10.247284889221191,
|
1433 |
+
"rewards/rejected": -10.094103813171387,
|
1434 |
+
"step": 940
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 19.0,
|
1438 |
+
"grad_norm": 0.0011127218090168816,
|
1439 |
+
"learning_rate": 3.798061746947995e-08,
|
1440 |
+
"logits/chosen": -0.9996277689933777,
|
1441 |
+
"logits/rejected": -0.7810768485069275,
|
1442 |
+
"logps/chosen": -62.9672737121582,
|
1443 |
+
"logps/rejected": -1361.350341796875,
|
1444 |
+
"loss": 0.0002,
|
1445 |
+
"rewards/accuracies": 1.0,
|
1446 |
+
"rewards/chosen": 0.1840919703245163,
|
1447 |
+
"rewards/margins": 13.088468551635742,
|
1448 |
+
"rewards/rejected": -12.904377937316895,
|
1449 |
+
"step": 950
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 19.2,
|
1453 |
+
"grad_norm": 0.0011199039962919363,
|
1454 |
+
"learning_rate": 2.4329828146074096e-08,
|
1455 |
+
"logits/chosen": -0.9857956171035767,
|
1456 |
+
"logits/rejected": -0.8834479451179504,
|
1457 |
+
"logps/chosen": -61.652801513671875,
|
1458 |
+
"logps/rejected": -1269.288330078125,
|
1459 |
+
"loss": 0.0003,
|
1460 |
+
"rewards/accuracies": 1.0,
|
1461 |
+
"rewards/chosen": 0.14881816506385803,
|
1462 |
+
"rewards/margins": 12.092996597290039,
|
1463 |
+
"rewards/rejected": -11.944178581237793,
|
1464 |
+
"step": 960
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 19.4,
|
1468 |
+
"grad_norm": 0.0013686833523596474,
|
1469 |
+
"learning_rate": 1.3695261579316776e-08,
|
1470 |
+
"logits/chosen": -0.9996697306632996,
|
1471 |
+
"logits/rejected": -0.8662905693054199,
|
1472 |
+
"logps/chosen": -60.64554977416992,
|
1473 |
+
"logps/rejected": -1260.70458984375,
|
1474 |
+
"loss": 0.0003,
|
1475 |
+
"rewards/accuracies": 1.0,
|
1476 |
+
"rewards/chosen": 0.18075986206531525,
|
1477 |
+
"rewards/margins": 12.048669815063477,
|
1478 |
+
"rewards/rejected": -11.867908477783203,
|
1479 |
+
"step": 970
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 19.6,
|
1483 |
+
"grad_norm": 0.0017745592515844095,
|
1484 |
+
"learning_rate": 6.089874350439507e-09,
|
1485 |
+
"logits/chosen": -1.0439860820770264,
|
1486 |
+
"logits/rejected": -0.9185269474983215,
|
1487 |
+
"logps/chosen": -59.79936981201172,
|
1488 |
+
"logps/rejected": -1267.5032958984375,
|
1489 |
+
"loss": 0.0003,
|
1490 |
+
"rewards/accuracies": 1.0,
|
1491 |
+
"rewards/chosen": 0.18838214874267578,
|
1492 |
+
"rewards/margins": 12.108388900756836,
|
1493 |
+
"rewards/rejected": -11.92000675201416,
|
1494 |
+
"step": 980
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 19.8,
|
1498 |
+
"grad_norm": 0.0013032690672856834,
|
1499 |
+
"learning_rate": 1.5229324522605949e-09,
|
1500 |
+
"logits/chosen": -0.9330822229385376,
|
1501 |
+
"logits/rejected": -0.8125349879264832,
|
1502 |
+
"logps/chosen": -58.721580505371094,
|
1503 |
+
"logps/rejected": -1287.365966796875,
|
1504 |
+
"loss": 0.0002,
|
1505 |
+
"rewards/accuracies": 1.0,
|
1506 |
+
"rewards/chosen": 0.17665794491767883,
|
1507 |
+
"rewards/margins": 12.307037353515625,
|
1508 |
+
"rewards/rejected": -12.130378723144531,
|
1509 |
+
"step": 990
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 20.0,
|
1513 |
+
"grad_norm": 0.003965487525700407,
|
1514 |
+
"learning_rate": 0.0,
|
1515 |
+
"logits/chosen": -0.9679548144340515,
|
1516 |
+
"logits/rejected": -0.8124309778213501,
|
1517 |
+
"logps/chosen": -61.12044143676758,
|
1518 |
+
"logps/rejected": -1297.4541015625,
|
1519 |
+
"loss": 0.0002,
|
1520 |
+
"rewards/accuracies": 1.0,
|
1521 |
+
"rewards/chosen": 0.1760241687297821,
|
1522 |
+
"rewards/margins": 12.41258716583252,
|
1523 |
+
"rewards/rejected": -12.236563682556152,
|
1524 |
+
"step": 1000
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 20.0,
|
1528 |
+
"step": 1000,
|
1529 |
+
"total_flos": 0.0,
|
1530 |
+
"train_loss": 0.07008945742505603,
|
1531 |
+
"train_runtime": 8233.3372,
|
1532 |
+
"train_samples_per_second": 1.943,
|
1533 |
+
"train_steps_per_second": 0.121
|
1534 |
+
}
|
1535 |
+
],
|
1536 |
+
"logging_steps": 10,
|
1537 |
+
"max_steps": 1000,
|
1538 |
+
"num_input_tokens_seen": 0,
|
1539 |
+
"num_train_epochs": 20,
|
1540 |
+
"save_steps": 1000,
|
1541 |
+
"stateful_callbacks": {
|
1542 |
+
"TrainerControl": {
|
1543 |
+
"args": {
|
1544 |
+
"should_epoch_stop": false,
|
1545 |
+
"should_evaluate": false,
|
1546 |
+
"should_log": false,
|
1547 |
+
"should_save": true,
|
1548 |
+
"should_training_stop": true
|
1549 |
+
},
|
1550 |
+
"attributes": {}
|
1551 |
+
}
|
1552 |
+
},
|
1553 |
+
"total_flos": 0.0,
|
1554 |
+
"train_batch_size": 2,
|
1555 |
+
"trial_name": null,
|
1556 |
+
"trial_params": null
|
1557 |
+
}
|