Model save
Browse files- README.md +81 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- train_results.json +9 -0
- trainer_state.json +1475 -0
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: alignment-handbook/zephyr-7b-sft-full
|
5 |
+
tags:
|
6 |
+
- trl
|
7 |
+
- dpo
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: zephyr-7b-align-scan-3e-07-0.62-polynomial-3.0
|
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 |
+
# zephyr-7b-align-scan-3e-07-0.62-polynomial-3.0
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.8766
|
22 |
+
- Rewards/chosen: -0.9523
|
23 |
+
- Rewards/rejected: -2.5666
|
24 |
+
- Rewards/accuracies: 0.3611
|
25 |
+
- Rewards/margins: 1.6143
|
26 |
+
- Logps/rejected: -85.2680
|
27 |
+
- Logps/chosen: -76.0272
|
28 |
+
- Logits/rejected: -2.6367
|
29 |
+
- Logits/chosen: -2.6538
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 3e-07
|
49 |
+
- train_batch_size: 8
|
50 |
+
- eval_batch_size: 8
|
51 |
+
- seed: 42
|
52 |
+
- distributed_type: multi-GPU
|
53 |
+
- num_devices: 4
|
54 |
+
- gradient_accumulation_steps: 2
|
55 |
+
- total_train_batch_size: 64
|
56 |
+
- total_eval_batch_size: 32
|
57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
+
- lr_scheduler_type: polynomial
|
59 |
+
- lr_scheduler_warmup_ratio: 0.1
|
60 |
+
- num_epochs: 3
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
65 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
66 |
+
| 0.6629 | 0.3484 | 100 | 0.6374 | 0.7586 | 0.3997 | 0.3452 | 0.3589 | -80.4837 | -73.2678 | -2.5455 | -2.5615 |
|
67 |
+
| 0.7044 | 0.6969 | 200 | 0.6785 | 0.6115 | 0.1187 | 0.3353 | 0.4927 | -80.9369 | -73.5050 | -2.5325 | -2.5487 |
|
68 |
+
| 0.3945 | 1.0453 | 300 | 0.6975 | 0.7667 | 0.1071 | 0.3552 | 0.6597 | -80.9557 | -73.2546 | -2.5596 | -2.5753 |
|
69 |
+
| 0.3859 | 1.3937 | 400 | 0.7396 | 1.4671 | 0.5658 | 0.3571 | 0.9013 | -80.2158 | -72.1250 | -2.5834 | -2.5995 |
|
70 |
+
| 0.3893 | 1.7422 | 500 | 0.7904 | -0.4771 | -1.4060 | 0.3492 | 0.9290 | -83.3962 | -75.2607 | -2.6499 | -2.6659 |
|
71 |
+
| 0.3749 | 2.0906 | 600 | 0.8125 | 0.5611 | -0.4847 | 0.3631 | 1.0458 | -81.9100 | -73.5862 | -2.6159 | -2.6321 |
|
72 |
+
| 0.3662 | 2.4390 | 700 | 0.8412 | -0.6104 | -2.0869 | 0.3651 | 1.4765 | -84.4944 | -75.4757 | -2.5941 | -2.6112 |
|
73 |
+
| 0.3615 | 2.7875 | 800 | 0.8766 | -0.9523 | -2.5666 | 0.3611 | 1.6143 | -85.2680 | -76.0272 | -2.6367 | -2.6538 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.44.2
|
79 |
+
- Pytorch 2.4.0
|
80 |
+
- Datasets 2.21.0
|
81 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.4762609164889266,
|
5 |
+
"train_runtime": 9670.9508,
|
6 |
+
"train_samples": 18340,
|
7 |
+
"train_samples_per_second": 5.689,
|
8 |
+
"train_steps_per_second": 0.089
|
9 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.44.2"
|
6 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.4762609164889266,
|
5 |
+
"train_runtime": 9670.9508,
|
6 |
+
"train_samples": 18340,
|
7 |
+
"train_samples_per_second": 5.689,
|
8 |
+
"train_steps_per_second": 0.089
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1475 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 861,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.003484320557491289,
|
13 |
+
"grad_norm": 358.6503200029449,
|
14 |
+
"learning_rate": 3.4482758620689654e-09,
|
15 |
+
"logits/chosen": -2.5345611572265625,
|
16 |
+
"logits/rejected": -2.581700563430786,
|
17 |
+
"logps/chosen": -60.002105712890625,
|
18 |
+
"logps/rejected": -99.98374938964844,
|
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": 0.03484320557491289,
|
28 |
+
"grad_norm": 335.50819535600175,
|
29 |
+
"learning_rate": 3.448275862068965e-08,
|
30 |
+
"logits/chosen": -2.5634875297546387,
|
31 |
+
"logits/rejected": -2.562131881713867,
|
32 |
+
"logps/chosen": -59.66706085205078,
|
33 |
+
"logps/rejected": -73.39751434326172,
|
34 |
+
"loss": 0.6938,
|
35 |
+
"rewards/accuracies": 0.2222222238779068,
|
36 |
+
"rewards/chosen": -0.00458882749080658,
|
37 |
+
"rewards/margins": 0.005699412431567907,
|
38 |
+
"rewards/rejected": -0.010288238525390625,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.06968641114982578,
|
43 |
+
"grad_norm": 431.2142268974989,
|
44 |
+
"learning_rate": 6.89655172413793e-08,
|
45 |
+
"logits/chosen": -2.6049625873565674,
|
46 |
+
"logits/rejected": -2.563797950744629,
|
47 |
+
"logps/chosen": -104.11083984375,
|
48 |
+
"logps/rejected": -94.92049407958984,
|
49 |
+
"loss": 0.6946,
|
50 |
+
"rewards/accuracies": 0.29374998807907104,
|
51 |
+
"rewards/chosen": 0.010060709901154041,
|
52 |
+
"rewards/margins": 0.026405800133943558,
|
53 |
+
"rewards/rejected": -0.016345087438821793,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.10452961672473868,
|
58 |
+
"grad_norm": 412.06640261613535,
|
59 |
+
"learning_rate": 1.0344827586206897e-07,
|
60 |
+
"logits/chosen": -2.591465711593628,
|
61 |
+
"logits/rejected": -2.5714292526245117,
|
62 |
+
"logps/chosen": -82.47346496582031,
|
63 |
+
"logps/rejected": -91.5473403930664,
|
64 |
+
"loss": 0.6905,
|
65 |
+
"rewards/accuracies": 0.2750000059604645,
|
66 |
+
"rewards/chosen": 0.014319317415356636,
|
67 |
+
"rewards/margins": 0.018754545599222183,
|
68 |
+
"rewards/rejected": -0.0044352286495268345,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.13937282229965156,
|
73 |
+
"grad_norm": 362.45244079994615,
|
74 |
+
"learning_rate": 1.379310344827586e-07,
|
75 |
+
"logits/chosen": -2.498384475708008,
|
76 |
+
"logits/rejected": -2.496023654937744,
|
77 |
+
"logps/chosen": -77.94225311279297,
|
78 |
+
"logps/rejected": -73.06587219238281,
|
79 |
+
"loss": 0.679,
|
80 |
+
"rewards/accuracies": 0.23125000298023224,
|
81 |
+
"rewards/chosen": -0.01477863360196352,
|
82 |
+
"rewards/margins": 0.02524409256875515,
|
83 |
+
"rewards/rejected": -0.040022727102041245,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.17421602787456447,
|
88 |
+
"grad_norm": 320.1865662448919,
|
89 |
+
"learning_rate": 1.7241379310344825e-07,
|
90 |
+
"logits/chosen": -2.533860683441162,
|
91 |
+
"logits/rejected": -2.537620782852173,
|
92 |
+
"logps/chosen": -63.8255729675293,
|
93 |
+
"logps/rejected": -76.09891510009766,
|
94 |
+
"loss": 0.6708,
|
95 |
+
"rewards/accuracies": 0.2562499940395355,
|
96 |
+
"rewards/chosen": 0.0704144611954689,
|
97 |
+
"rewards/margins": 0.06760600954294205,
|
98 |
+
"rewards/rejected": 0.0028084414079785347,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.20905923344947736,
|
103 |
+
"grad_norm": 315.3790948714663,
|
104 |
+
"learning_rate": 2.0689655172413793e-07,
|
105 |
+
"logits/chosen": -2.5066819190979004,
|
106 |
+
"logits/rejected": -2.500108480453491,
|
107 |
+
"logps/chosen": -72.56768798828125,
|
108 |
+
"logps/rejected": -67.95696258544922,
|
109 |
+
"loss": 0.6664,
|
110 |
+
"rewards/accuracies": 0.34375,
|
111 |
+
"rewards/chosen": 0.3960721492767334,
|
112 |
+
"rewards/margins": 0.11608312278985977,
|
113 |
+
"rewards/rejected": 0.2799890339374542,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.24390243902439024,
|
118 |
+
"grad_norm": 311.35919136752943,
|
119 |
+
"learning_rate": 2.413793103448276e-07,
|
120 |
+
"logits/chosen": -2.529073715209961,
|
121 |
+
"logits/rejected": -2.5245697498321533,
|
122 |
+
"logps/chosen": -63.03422164916992,
|
123 |
+
"logps/rejected": -67.55048370361328,
|
124 |
+
"loss": 0.6571,
|
125 |
+
"rewards/accuracies": 0.30000001192092896,
|
126 |
+
"rewards/chosen": 0.7452259063720703,
|
127 |
+
"rewards/margins": 0.20201978087425232,
|
128 |
+
"rewards/rejected": 0.5432060956954956,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.2787456445993031,
|
133 |
+
"grad_norm": 380.6379547994258,
|
134 |
+
"learning_rate": 2.758620689655172e-07,
|
135 |
+
"logits/chosen": -2.4771764278411865,
|
136 |
+
"logits/rejected": -2.4673564434051514,
|
137 |
+
"logps/chosen": -74.3353271484375,
|
138 |
+
"logps/rejected": -76.72254943847656,
|
139 |
+
"loss": 0.6584,
|
140 |
+
"rewards/accuracies": 0.3125,
|
141 |
+
"rewards/chosen": 0.8243219256401062,
|
142 |
+
"rewards/margins": 0.3330293893814087,
|
143 |
+
"rewards/rejected": 0.49129247665405273,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.313588850174216,
|
148 |
+
"grad_norm": 290.2304014635751,
|
149 |
+
"learning_rate": 2.9922480620155034e-07,
|
150 |
+
"logits/chosen": -2.4918248653411865,
|
151 |
+
"logits/rejected": -2.505871295928955,
|
152 |
+
"logps/chosen": -65.13265228271484,
|
153 |
+
"logps/rejected": -69.66169738769531,
|
154 |
+
"loss": 0.6595,
|
155 |
+
"rewards/accuracies": 0.29374998807907104,
|
156 |
+
"rewards/chosen": 0.5267654657363892,
|
157 |
+
"rewards/margins": 0.24630899727344513,
|
158 |
+
"rewards/rejected": 0.28045645356178284,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.34843205574912894,
|
163 |
+
"grad_norm": 362.13853654937515,
|
164 |
+
"learning_rate": 2.96640826873385e-07,
|
165 |
+
"logits/chosen": -2.475275754928589,
|
166 |
+
"logits/rejected": -2.4764583110809326,
|
167 |
+
"logps/chosen": -74.12995910644531,
|
168 |
+
"logps/rejected": -80.4610366821289,
|
169 |
+
"loss": 0.6629,
|
170 |
+
"rewards/accuracies": 0.3125,
|
171 |
+
"rewards/chosen": 0.7075541019439697,
|
172 |
+
"rewards/margins": 0.3413715958595276,
|
173 |
+
"rewards/rejected": 0.36618250608444214,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.34843205574912894,
|
178 |
+
"eval_logits/chosen": -2.5614964962005615,
|
179 |
+
"eval_logits/rejected": -2.545496940612793,
|
180 |
+
"eval_logps/chosen": -73.26775360107422,
|
181 |
+
"eval_logps/rejected": -80.48373413085938,
|
182 |
+
"eval_loss": 0.6374358534812927,
|
183 |
+
"eval_rewards/accuracies": 0.3452380895614624,
|
184 |
+
"eval_rewards/chosen": 0.7585535645484924,
|
185 |
+
"eval_rewards/margins": 0.3588891923427582,
|
186 |
+
"eval_rewards/rejected": 0.39966443181037903,
|
187 |
+
"eval_runtime": 113.5456,
|
188 |
+
"eval_samples_per_second": 17.614,
|
189 |
+
"eval_steps_per_second": 0.555,
|
190 |
+
"step": 100
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.3832752613240418,
|
194 |
+
"grad_norm": 402.8431072761315,
|
195 |
+
"learning_rate": 2.940568475452196e-07,
|
196 |
+
"logits/chosen": -2.5034003257751465,
|
197 |
+
"logits/rejected": -2.465451717376709,
|
198 |
+
"logps/chosen": -72.49577331542969,
|
199 |
+
"logps/rejected": -62.814613342285156,
|
200 |
+
"loss": 0.6492,
|
201 |
+
"rewards/accuracies": 0.28125,
|
202 |
+
"rewards/chosen": 0.41803866624832153,
|
203 |
+
"rewards/margins": 0.29653844237327576,
|
204 |
+
"rewards/rejected": 0.12150021642446518,
|
205 |
+
"step": 110
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.4181184668989547,
|
209 |
+
"grad_norm": 276.5279613655658,
|
210 |
+
"learning_rate": 2.9147286821705423e-07,
|
211 |
+
"logits/chosen": -2.528160333633423,
|
212 |
+
"logits/rejected": -2.497156858444214,
|
213 |
+
"logps/chosen": -76.75882720947266,
|
214 |
+
"logps/rejected": -66.54231262207031,
|
215 |
+
"loss": 0.6394,
|
216 |
+
"rewards/accuracies": 0.3187499940395355,
|
217 |
+
"rewards/chosen": 0.4357032775878906,
|
218 |
+
"rewards/margins": 0.3555503487586975,
|
219 |
+
"rewards/rejected": 0.08015286922454834,
|
220 |
+
"step": 120
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.4529616724738676,
|
224 |
+
"grad_norm": 438.9130471992716,
|
225 |
+
"learning_rate": 2.888888888888889e-07,
|
226 |
+
"logits/chosen": -2.5648016929626465,
|
227 |
+
"logits/rejected": -2.5454888343811035,
|
228 |
+
"logps/chosen": -83.2737808227539,
|
229 |
+
"logps/rejected": -87.85270690917969,
|
230 |
+
"loss": 0.6666,
|
231 |
+
"rewards/accuracies": 0.36250001192092896,
|
232 |
+
"rewards/chosen": 0.3763393759727478,
|
233 |
+
"rewards/margins": 0.5897358655929565,
|
234 |
+
"rewards/rejected": -0.21339651942253113,
|
235 |
+
"step": 130
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.4878048780487805,
|
239 |
+
"grad_norm": 322.57184174769804,
|
240 |
+
"learning_rate": 2.863049095607235e-07,
|
241 |
+
"logits/chosen": -2.4603538513183594,
|
242 |
+
"logits/rejected": -2.4488110542297363,
|
243 |
+
"logps/chosen": -80.25636291503906,
|
244 |
+
"logps/rejected": -70.93235778808594,
|
245 |
+
"loss": 0.6249,
|
246 |
+
"rewards/accuracies": 0.375,
|
247 |
+
"rewards/chosen": 0.5512245893478394,
|
248 |
+
"rewards/margins": 0.6554535627365112,
|
249 |
+
"rewards/rejected": -0.10422901809215546,
|
250 |
+
"step": 140
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.5226480836236934,
|
254 |
+
"grad_norm": 359.54734158147613,
|
255 |
+
"learning_rate": 2.837209302325581e-07,
|
256 |
+
"logits/chosen": -2.5226199626922607,
|
257 |
+
"logits/rejected": -2.4783759117126465,
|
258 |
+
"logps/chosen": -78.67804718017578,
|
259 |
+
"logps/rejected": -79.57527160644531,
|
260 |
+
"loss": 0.6633,
|
261 |
+
"rewards/accuracies": 0.3187499940395355,
|
262 |
+
"rewards/chosen": 0.4999012351036072,
|
263 |
+
"rewards/margins": 0.5150824785232544,
|
264 |
+
"rewards/rejected": -0.01518118567764759,
|
265 |
+
"step": 150
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.5574912891986062,
|
269 |
+
"grad_norm": 312.3603092848705,
|
270 |
+
"learning_rate": 2.811369509043928e-07,
|
271 |
+
"logits/chosen": -2.486689805984497,
|
272 |
+
"logits/rejected": -2.507362127304077,
|
273 |
+
"logps/chosen": -64.26698303222656,
|
274 |
+
"logps/rejected": -72.27865600585938,
|
275 |
+
"loss": 0.6722,
|
276 |
+
"rewards/accuracies": 0.26249998807907104,
|
277 |
+
"rewards/chosen": 0.15987662971019745,
|
278 |
+
"rewards/margins": 0.3494376838207245,
|
279 |
+
"rewards/rejected": -0.18956105411052704,
|
280 |
+
"step": 160
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.5923344947735192,
|
284 |
+
"grad_norm": 391.74254314560164,
|
285 |
+
"learning_rate": 2.7855297157622735e-07,
|
286 |
+
"logits/chosen": -2.4955577850341797,
|
287 |
+
"logits/rejected": -2.48069167137146,
|
288 |
+
"logps/chosen": -69.2925796508789,
|
289 |
+
"logps/rejected": -77.45768737792969,
|
290 |
+
"loss": 0.6399,
|
291 |
+
"rewards/accuracies": 0.3125,
|
292 |
+
"rewards/chosen": -0.20161184668540955,
|
293 |
+
"rewards/margins": 0.5074432492256165,
|
294 |
+
"rewards/rejected": -0.7090551257133484,
|
295 |
+
"step": 170
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.627177700348432,
|
299 |
+
"grad_norm": 354.9896897534272,
|
300 |
+
"learning_rate": 2.75968992248062e-07,
|
301 |
+
"logits/chosen": -2.545736789703369,
|
302 |
+
"logits/rejected": -2.534653663635254,
|
303 |
+
"logps/chosen": -91.68567657470703,
|
304 |
+
"logps/rejected": -86.991943359375,
|
305 |
+
"loss": 0.6933,
|
306 |
+
"rewards/accuracies": 0.32499998807907104,
|
307 |
+
"rewards/chosen": 0.1063336730003357,
|
308 |
+
"rewards/margins": 0.40485674142837524,
|
309 |
+
"rewards/rejected": -0.29852309823036194,
|
310 |
+
"step": 180
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.662020905923345,
|
314 |
+
"grad_norm": 251.86613571396995,
|
315 |
+
"learning_rate": 2.733850129198967e-07,
|
316 |
+
"logits/chosen": -2.5427966117858887,
|
317 |
+
"logits/rejected": -2.5337371826171875,
|
318 |
+
"logps/chosen": -70.1039810180664,
|
319 |
+
"logps/rejected": -81.1055908203125,
|
320 |
+
"loss": 0.6537,
|
321 |
+
"rewards/accuracies": 0.3187499940395355,
|
322 |
+
"rewards/chosen": 0.587446928024292,
|
323 |
+
"rewards/margins": 0.3254398703575134,
|
324 |
+
"rewards/rejected": 0.26200705766677856,
|
325 |
+
"step": 190
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.6968641114982579,
|
329 |
+
"grad_norm": 448.52473154376446,
|
330 |
+
"learning_rate": 2.7080103359173124e-07,
|
331 |
+
"logits/chosen": -2.5728795528411865,
|
332 |
+
"logits/rejected": -2.580472469329834,
|
333 |
+
"logps/chosen": -88.97058868408203,
|
334 |
+
"logps/rejected": -91.36177062988281,
|
335 |
+
"loss": 0.7044,
|
336 |
+
"rewards/accuracies": 0.35624998807907104,
|
337 |
+
"rewards/chosen": 1.0451823472976685,
|
338 |
+
"rewards/margins": 0.6180461645126343,
|
339 |
+
"rewards/rejected": 0.42713627219200134,
|
340 |
+
"step": 200
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.6968641114982579,
|
344 |
+
"eval_logits/chosen": -2.548659324645996,
|
345 |
+
"eval_logits/rejected": -2.5324509143829346,
|
346 |
+
"eval_logps/chosen": -73.5050048828125,
|
347 |
+
"eval_logps/rejected": -80.9368667602539,
|
348 |
+
"eval_loss": 0.6785250902175903,
|
349 |
+
"eval_rewards/accuracies": 0.335317462682724,
|
350 |
+
"eval_rewards/chosen": 0.6114616394042969,
|
351 |
+
"eval_rewards/margins": 0.4927373230457306,
|
352 |
+
"eval_rewards/rejected": 0.11872433125972748,
|
353 |
+
"eval_runtime": 113.5716,
|
354 |
+
"eval_samples_per_second": 17.61,
|
355 |
+
"eval_steps_per_second": 0.555,
|
356 |
+
"step": 200
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.7317073170731707,
|
360 |
+
"grad_norm": 539.9357015144649,
|
361 |
+
"learning_rate": 2.682170542635659e-07,
|
362 |
+
"logits/chosen": -2.5559327602386475,
|
363 |
+
"logits/rejected": -2.529869794845581,
|
364 |
+
"logps/chosen": -68.37545013427734,
|
365 |
+
"logps/rejected": -63.614356994628906,
|
366 |
+
"loss": 0.7042,
|
367 |
+
"rewards/accuracies": 0.3687500059604645,
|
368 |
+
"rewards/chosen": 0.58504319190979,
|
369 |
+
"rewards/margins": 0.7152014970779419,
|
370 |
+
"rewards/rejected": -0.13015827536582947,
|
371 |
+
"step": 210
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.7665505226480837,
|
375 |
+
"grad_norm": 286.2044305000258,
|
376 |
+
"learning_rate": 2.6563307493540046e-07,
|
377 |
+
"logits/chosen": -2.591370105743408,
|
378 |
+
"logits/rejected": -2.5699965953826904,
|
379 |
+
"logps/chosen": -72.25666809082031,
|
380 |
+
"logps/rejected": -70.89804077148438,
|
381 |
+
"loss": 0.6966,
|
382 |
+
"rewards/accuracies": 0.25,
|
383 |
+
"rewards/chosen": 0.74493408203125,
|
384 |
+
"rewards/margins": 0.2705448865890503,
|
385 |
+
"rewards/rejected": 0.4743892252445221,
|
386 |
+
"step": 220
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.8013937282229965,
|
390 |
+
"grad_norm": 398.39083722167163,
|
391 |
+
"learning_rate": 2.6304909560723513e-07,
|
392 |
+
"logits/chosen": -2.5968384742736816,
|
393 |
+
"logits/rejected": -2.574525833129883,
|
394 |
+
"logps/chosen": -88.1639633178711,
|
395 |
+
"logps/rejected": -87.76924133300781,
|
396 |
+
"loss": 0.685,
|
397 |
+
"rewards/accuracies": 0.38749998807907104,
|
398 |
+
"rewards/chosen": 1.1387383937835693,
|
399 |
+
"rewards/margins": 0.9033845663070679,
|
400 |
+
"rewards/rejected": 0.23535379767417908,
|
401 |
+
"step": 230
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.8362369337979094,
|
405 |
+
"grad_norm": 339.80066659715754,
|
406 |
+
"learning_rate": 2.6046511627906974e-07,
|
407 |
+
"logits/chosen": -2.589068651199341,
|
408 |
+
"logits/rejected": -2.5533642768859863,
|
409 |
+
"logps/chosen": -85.19193267822266,
|
410 |
+
"logps/rejected": -79.42808532714844,
|
411 |
+
"loss": 0.6884,
|
412 |
+
"rewards/accuracies": 0.3687500059604645,
|
413 |
+
"rewards/chosen": 0.9607963562011719,
|
414 |
+
"rewards/margins": 0.5218255519866943,
|
415 |
+
"rewards/rejected": 0.4389708638191223,
|
416 |
+
"step": 240
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.8710801393728222,
|
420 |
+
"grad_norm": 341.3674177311404,
|
421 |
+
"learning_rate": 2.5788113695090435e-07,
|
422 |
+
"logits/chosen": -2.6001765727996826,
|
423 |
+
"logits/rejected": -2.56406831741333,
|
424 |
+
"logps/chosen": -94.24848937988281,
|
425 |
+
"logps/rejected": -89.58869934082031,
|
426 |
+
"loss": 0.6149,
|
427 |
+
"rewards/accuracies": 0.38749998807907104,
|
428 |
+
"rewards/chosen": 0.7444799542427063,
|
429 |
+
"rewards/margins": 0.5228375196456909,
|
430 |
+
"rewards/rejected": 0.2216424196958542,
|
431 |
+
"step": 250
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.9059233449477352,
|
435 |
+
"grad_norm": 283.98484381974555,
|
436 |
+
"learning_rate": 2.55297157622739e-07,
|
437 |
+
"logits/chosen": -2.506063461303711,
|
438 |
+
"logits/rejected": -2.5218896865844727,
|
439 |
+
"logps/chosen": -57.92702102661133,
|
440 |
+
"logps/rejected": -65.19326782226562,
|
441 |
+
"loss": 0.682,
|
442 |
+
"rewards/accuracies": 0.29374998807907104,
|
443 |
+
"rewards/chosen": 0.6958502531051636,
|
444 |
+
"rewards/margins": 0.4261382520198822,
|
445 |
+
"rewards/rejected": 0.26971206068992615,
|
446 |
+
"step": 260
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.9407665505226481,
|
450 |
+
"grad_norm": 372.62325379603294,
|
451 |
+
"learning_rate": 2.5271317829457363e-07,
|
452 |
+
"logits/chosen": -2.6025278568267822,
|
453 |
+
"logits/rejected": -2.6028153896331787,
|
454 |
+
"logps/chosen": -67.53540802001953,
|
455 |
+
"logps/rejected": -82.33738708496094,
|
456 |
+
"loss": 0.6525,
|
457 |
+
"rewards/accuracies": 0.32499998807907104,
|
458 |
+
"rewards/chosen": 0.8337510228157043,
|
459 |
+
"rewards/margins": 0.713237464427948,
|
460 |
+
"rewards/rejected": 0.12051346153020859,
|
461 |
+
"step": 270
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.975609756097561,
|
465 |
+
"grad_norm": 314.12151123620725,
|
466 |
+
"learning_rate": 2.5012919896640824e-07,
|
467 |
+
"logits/chosen": -2.5111606121063232,
|
468 |
+
"logits/rejected": -2.487565517425537,
|
469 |
+
"logps/chosen": -66.56291198730469,
|
470 |
+
"logps/rejected": -70.64192199707031,
|
471 |
+
"loss": 0.6164,
|
472 |
+
"rewards/accuracies": 0.3375000059604645,
|
473 |
+
"rewards/chosen": 0.7883111238479614,
|
474 |
+
"rewards/margins": 0.668962836265564,
|
475 |
+
"rewards/rejected": 0.11934838443994522,
|
476 |
+
"step": 280
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.0104529616724738,
|
480 |
+
"grad_norm": 72.54916768701123,
|
481 |
+
"learning_rate": 2.475452196382429e-07,
|
482 |
+
"logits/chosen": -2.524649143218994,
|
483 |
+
"logits/rejected": -2.4943947792053223,
|
484 |
+
"logps/chosen": -69.41844177246094,
|
485 |
+
"logps/rejected": -65.09283447265625,
|
486 |
+
"loss": 0.5485,
|
487 |
+
"rewards/accuracies": 0.38749998807907104,
|
488 |
+
"rewards/chosen": 1.642530083656311,
|
489 |
+
"rewards/margins": 1.75347900390625,
|
490 |
+
"rewards/rejected": -0.11094935238361359,
|
491 |
+
"step": 290
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 1.0452961672473868,
|
495 |
+
"grad_norm": 25.060931202079587,
|
496 |
+
"learning_rate": 2.4496124031007747e-07,
|
497 |
+
"logits/chosen": -2.5531129837036133,
|
498 |
+
"logits/rejected": -2.5395359992980957,
|
499 |
+
"logps/chosen": -62.507972717285156,
|
500 |
+
"logps/rejected": -72.49549865722656,
|
501 |
+
"loss": 0.3945,
|
502 |
+
"rewards/accuracies": 0.42500001192092896,
|
503 |
+
"rewards/chosen": 2.5053844451904297,
|
504 |
+
"rewards/margins": 4.567110061645508,
|
505 |
+
"rewards/rejected": -2.06172513961792,
|
506 |
+
"step": 300
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.0452961672473868,
|
510 |
+
"eval_logits/chosen": -2.575260877609253,
|
511 |
+
"eval_logits/rejected": -2.559643507003784,
|
512 |
+
"eval_logps/chosen": -73.25456237792969,
|
513 |
+
"eval_logps/rejected": -80.9556655883789,
|
514 |
+
"eval_loss": 0.6974567770957947,
|
515 |
+
"eval_rewards/accuracies": 0.3551587164402008,
|
516 |
+
"eval_rewards/chosen": 0.7667317986488342,
|
517 |
+
"eval_rewards/margins": 0.6596661806106567,
|
518 |
+
"eval_rewards/rejected": 0.10706562548875809,
|
519 |
+
"eval_runtime": 113.4908,
|
520 |
+
"eval_samples_per_second": 17.623,
|
521 |
+
"eval_steps_per_second": 0.555,
|
522 |
+
"step": 300
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 1.0801393728222997,
|
526 |
+
"grad_norm": 19.10824587006278,
|
527 |
+
"learning_rate": 2.4237726098191214e-07,
|
528 |
+
"logits/chosen": -2.530690908432007,
|
529 |
+
"logits/rejected": -2.5344767570495605,
|
530 |
+
"logps/chosen": -63.4401969909668,
|
531 |
+
"logps/rejected": -79.88385772705078,
|
532 |
+
"loss": 0.4065,
|
533 |
+
"rewards/accuracies": 0.4375,
|
534 |
+
"rewards/chosen": 2.601799488067627,
|
535 |
+
"rewards/margins": 5.476699352264404,
|
536 |
+
"rewards/rejected": -2.8749003410339355,
|
537 |
+
"step": 310
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 1.1149825783972125,
|
541 |
+
"grad_norm": 13.055135863878375,
|
542 |
+
"learning_rate": 2.397932816537468e-07,
|
543 |
+
"logits/chosen": -2.583162546157837,
|
544 |
+
"logits/rejected": -2.5704259872436523,
|
545 |
+
"logps/chosen": -70.44621276855469,
|
546 |
+
"logps/rejected": -82.24694061279297,
|
547 |
+
"loss": 0.3998,
|
548 |
+
"rewards/accuracies": 0.4749999940395355,
|
549 |
+
"rewards/chosen": 2.1784868240356445,
|
550 |
+
"rewards/margins": 4.678074359893799,
|
551 |
+
"rewards/rejected": -2.499587059020996,
|
552 |
+
"step": 320
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 1.1498257839721253,
|
556 |
+
"grad_norm": 73.70458680382093,
|
557 |
+
"learning_rate": 2.3720930232558136e-07,
|
558 |
+
"logits/chosen": -2.574796438217163,
|
559 |
+
"logits/rejected": -2.550279140472412,
|
560 |
+
"logps/chosen": -79.08229064941406,
|
561 |
+
"logps/rejected": -82.61952209472656,
|
562 |
+
"loss": 0.3644,
|
563 |
+
"rewards/accuracies": 0.53125,
|
564 |
+
"rewards/chosen": 3.124291181564331,
|
565 |
+
"rewards/margins": 5.5998125076293945,
|
566 |
+
"rewards/rejected": -2.4755213260650635,
|
567 |
+
"step": 330
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 1.1846689895470384,
|
571 |
+
"grad_norm": 28.850587508009358,
|
572 |
+
"learning_rate": 2.34625322997416e-07,
|
573 |
+
"logits/chosen": -2.557753562927246,
|
574 |
+
"logits/rejected": -2.5632052421569824,
|
575 |
+
"logps/chosen": -78.73472595214844,
|
576 |
+
"logps/rejected": -99.98568725585938,
|
577 |
+
"loss": 0.389,
|
578 |
+
"rewards/accuracies": 0.5375000238418579,
|
579 |
+
"rewards/chosen": 3.1080851554870605,
|
580 |
+
"rewards/margins": 6.023845672607422,
|
581 |
+
"rewards/rejected": -2.9157605171203613,
|
582 |
+
"step": 340
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 1.2195121951219512,
|
586 |
+
"grad_norm": 85.64045808230581,
|
587 |
+
"learning_rate": 2.3204134366925064e-07,
|
588 |
+
"logits/chosen": -2.5850272178649902,
|
589 |
+
"logits/rejected": -2.551978588104248,
|
590 |
+
"logps/chosen": -64.38944244384766,
|
591 |
+
"logps/rejected": -68.43348693847656,
|
592 |
+
"loss": 0.3897,
|
593 |
+
"rewards/accuracies": 0.4749999940395355,
|
594 |
+
"rewards/chosen": 2.608705759048462,
|
595 |
+
"rewards/margins": 4.316413402557373,
|
596 |
+
"rewards/rejected": -1.7077077627182007,
|
597 |
+
"step": 350
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 1.254355400696864,
|
601 |
+
"grad_norm": 52.17293262552292,
|
602 |
+
"learning_rate": 2.2945736434108528e-07,
|
603 |
+
"logits/chosen": -2.5734505653381348,
|
604 |
+
"logits/rejected": -2.5436837673187256,
|
605 |
+
"logps/chosen": -67.31871032714844,
|
606 |
+
"logps/rejected": -67.99309539794922,
|
607 |
+
"loss": 0.3729,
|
608 |
+
"rewards/accuracies": 0.44999998807907104,
|
609 |
+
"rewards/chosen": 2.8094611167907715,
|
610 |
+
"rewards/margins": 4.253398895263672,
|
611 |
+
"rewards/rejected": -1.44393789768219,
|
612 |
+
"step": 360
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.289198606271777,
|
616 |
+
"grad_norm": 73.55818831421092,
|
617 |
+
"learning_rate": 2.268733850129199e-07,
|
618 |
+
"logits/chosen": -2.5357134342193604,
|
619 |
+
"logits/rejected": -2.556293487548828,
|
620 |
+
"logps/chosen": -65.90876770019531,
|
621 |
+
"logps/rejected": -77.08678436279297,
|
622 |
+
"loss": 0.4065,
|
623 |
+
"rewards/accuracies": 0.44999998807907104,
|
624 |
+
"rewards/chosen": 3.1975178718566895,
|
625 |
+
"rewards/margins": 4.904288291931152,
|
626 |
+
"rewards/rejected": -1.7067703008651733,
|
627 |
+
"step": 370
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 1.32404181184669,
|
631 |
+
"grad_norm": 63.56754205504431,
|
632 |
+
"learning_rate": 2.2428940568475453e-07,
|
633 |
+
"logits/chosen": -2.543696880340576,
|
634 |
+
"logits/rejected": -2.542275905609131,
|
635 |
+
"logps/chosen": -79.8168716430664,
|
636 |
+
"logps/rejected": -90.68196105957031,
|
637 |
+
"loss": 0.383,
|
638 |
+
"rewards/accuracies": 0.550000011920929,
|
639 |
+
"rewards/chosen": 4.3757524490356445,
|
640 |
+
"rewards/margins": 6.989476680755615,
|
641 |
+
"rewards/rejected": -2.61372447013855,
|
642 |
+
"step": 380
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 1.3588850174216027,
|
646 |
+
"grad_norm": 84.5304582436996,
|
647 |
+
"learning_rate": 2.2170542635658914e-07,
|
648 |
+
"logits/chosen": -2.616854190826416,
|
649 |
+
"logits/rejected": -2.6028048992156982,
|
650 |
+
"logps/chosen": -62.09540939331055,
|
651 |
+
"logps/rejected": -74.197265625,
|
652 |
+
"loss": 0.3743,
|
653 |
+
"rewards/accuracies": 0.4437499940395355,
|
654 |
+
"rewards/chosen": 3.0379724502563477,
|
655 |
+
"rewards/margins": 4.858659744262695,
|
656 |
+
"rewards/rejected": -1.8206875324249268,
|
657 |
+
"step": 390
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 1.3937282229965158,
|
661 |
+
"grad_norm": 45.47639364698017,
|
662 |
+
"learning_rate": 2.1912144702842375e-07,
|
663 |
+
"logits/chosen": -2.5946788787841797,
|
664 |
+
"logits/rejected": -2.564770221710205,
|
665 |
+
"logps/chosen": -80.40516662597656,
|
666 |
+
"logps/rejected": -101.68209075927734,
|
667 |
+
"loss": 0.3859,
|
668 |
+
"rewards/accuracies": 0.5249999761581421,
|
669 |
+
"rewards/chosen": 3.559967041015625,
|
670 |
+
"rewards/margins": 5.592529296875,
|
671 |
+
"rewards/rejected": -2.032562732696533,
|
672 |
+
"step": 400
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 1.3937282229965158,
|
676 |
+
"eval_logits/chosen": -2.5995094776153564,
|
677 |
+
"eval_logits/rejected": -2.5833675861358643,
|
678 |
+
"eval_logps/chosen": -72.12498474121094,
|
679 |
+
"eval_logps/rejected": -80.21580505371094,
|
680 |
+
"eval_loss": 0.7395845651626587,
|
681 |
+
"eval_rewards/accuracies": 0.3571428656578064,
|
682 |
+
"eval_rewards/chosen": 1.4670709371566772,
|
683 |
+
"eval_rewards/margins": 0.9012959599494934,
|
684 |
+
"eval_rewards/rejected": 0.5657750368118286,
|
685 |
+
"eval_runtime": 113.4528,
|
686 |
+
"eval_samples_per_second": 17.628,
|
687 |
+
"eval_steps_per_second": 0.555,
|
688 |
+
"step": 400
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 1.4285714285714286,
|
692 |
+
"grad_norm": 9.035779538567592,
|
693 |
+
"learning_rate": 2.1653746770025842e-07,
|
694 |
+
"logits/chosen": -2.587205410003662,
|
695 |
+
"logits/rejected": -2.577908515930176,
|
696 |
+
"logps/chosen": -76.38627624511719,
|
697 |
+
"logps/rejected": -81.7760009765625,
|
698 |
+
"loss": 0.3719,
|
699 |
+
"rewards/accuracies": 0.4749999940395355,
|
700 |
+
"rewards/chosen": 3.8607609272003174,
|
701 |
+
"rewards/margins": 4.7285661697387695,
|
702 |
+
"rewards/rejected": -0.8678053021430969,
|
703 |
+
"step": 410
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 1.4634146341463414,
|
707 |
+
"grad_norm": 31.70641333825559,
|
708 |
+
"learning_rate": 2.1395348837209303e-07,
|
709 |
+
"logits/chosen": -2.637145519256592,
|
710 |
+
"logits/rejected": -2.637343168258667,
|
711 |
+
"logps/chosen": -69.94471740722656,
|
712 |
+
"logps/rejected": -86.88435363769531,
|
713 |
+
"loss": 0.3975,
|
714 |
+
"rewards/accuracies": 0.4375,
|
715 |
+
"rewards/chosen": 3.812042236328125,
|
716 |
+
"rewards/margins": 5.059989929199219,
|
717 |
+
"rewards/rejected": -1.2479479312896729,
|
718 |
+
"step": 420
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 1.4982578397212545,
|
722 |
+
"grad_norm": 65.50905056120632,
|
723 |
+
"learning_rate": 2.1136950904392762e-07,
|
724 |
+
"logits/chosen": -2.594949960708618,
|
725 |
+
"logits/rejected": -2.582991123199463,
|
726 |
+
"logps/chosen": -62.43513870239258,
|
727 |
+
"logps/rejected": -74.3114013671875,
|
728 |
+
"loss": 0.3952,
|
729 |
+
"rewards/accuracies": 0.46875,
|
730 |
+
"rewards/chosen": 3.8608689308166504,
|
731 |
+
"rewards/margins": 4.990710258483887,
|
732 |
+
"rewards/rejected": -1.1298413276672363,
|
733 |
+
"step": 430
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 1.533101045296167,
|
737 |
+
"grad_norm": 103.25920597551605,
|
738 |
+
"learning_rate": 2.0878552971576226e-07,
|
739 |
+
"logits/chosen": -2.587477207183838,
|
740 |
+
"logits/rejected": -2.596736192703247,
|
741 |
+
"logps/chosen": -64.37332916259766,
|
742 |
+
"logps/rejected": -75.4191665649414,
|
743 |
+
"loss": 0.401,
|
744 |
+
"rewards/accuracies": 0.4312500059604645,
|
745 |
+
"rewards/chosen": 3.475306987762451,
|
746 |
+
"rewards/margins": 4.665290832519531,
|
747 |
+
"rewards/rejected": -1.1899840831756592,
|
748 |
+
"step": 440
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 1.5679442508710801,
|
752 |
+
"grad_norm": 46.90858224938077,
|
753 |
+
"learning_rate": 2.062015503875969e-07,
|
754 |
+
"logits/chosen": -2.641456127166748,
|
755 |
+
"logits/rejected": -2.6066718101501465,
|
756 |
+
"logps/chosen": -84.70106506347656,
|
757 |
+
"logps/rejected": -90.63847351074219,
|
758 |
+
"loss": 0.3861,
|
759 |
+
"rewards/accuracies": 0.518750011920929,
|
760 |
+
"rewards/chosen": 3.8073742389678955,
|
761 |
+
"rewards/margins": 6.706219673156738,
|
762 |
+
"rewards/rejected": -2.8988451957702637,
|
763 |
+
"step": 450
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 1.6027874564459932,
|
767 |
+
"grad_norm": 73.13862861246201,
|
768 |
+
"learning_rate": 2.0361757105943153e-07,
|
769 |
+
"logits/chosen": -2.6171023845672607,
|
770 |
+
"logits/rejected": -2.5963072776794434,
|
771 |
+
"logps/chosen": -70.6004867553711,
|
772 |
+
"logps/rejected": -81.99185943603516,
|
773 |
+
"loss": 0.4031,
|
774 |
+
"rewards/accuracies": 0.5,
|
775 |
+
"rewards/chosen": 3.4589905738830566,
|
776 |
+
"rewards/margins": 6.551025390625,
|
777 |
+
"rewards/rejected": -3.0920345783233643,
|
778 |
+
"step": 460
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 1.6376306620209058,
|
782 |
+
"grad_norm": 55.407817129230025,
|
783 |
+
"learning_rate": 2.0103359173126615e-07,
|
784 |
+
"logits/chosen": -2.617323637008667,
|
785 |
+
"logits/rejected": -2.6086113452911377,
|
786 |
+
"logps/chosen": -57.063804626464844,
|
787 |
+
"logps/rejected": -75.29525756835938,
|
788 |
+
"loss": 0.4097,
|
789 |
+
"rewards/accuracies": 0.38749998807907104,
|
790 |
+
"rewards/chosen": 2.6279244422912598,
|
791 |
+
"rewards/margins": 4.8750505447387695,
|
792 |
+
"rewards/rejected": -2.247126817703247,
|
793 |
+
"step": 470
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 1.6724738675958188,
|
797 |
+
"grad_norm": 95.66039903353,
|
798 |
+
"learning_rate": 1.9844961240310078e-07,
|
799 |
+
"logits/chosen": -2.636000156402588,
|
800 |
+
"logits/rejected": -2.619654893875122,
|
801 |
+
"logps/chosen": -50.774810791015625,
|
802 |
+
"logps/rejected": -55.16005325317383,
|
803 |
+
"loss": 0.4027,
|
804 |
+
"rewards/accuracies": 0.3499999940395355,
|
805 |
+
"rewards/chosen": 2.037757158279419,
|
806 |
+
"rewards/margins": 4.008673667907715,
|
807 |
+
"rewards/rejected": -1.970916986465454,
|
808 |
+
"step": 480
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 1.7073170731707317,
|
812 |
+
"grad_norm": 194.80847235958515,
|
813 |
+
"learning_rate": 1.958656330749354e-07,
|
814 |
+
"logits/chosen": -2.6303064823150635,
|
815 |
+
"logits/rejected": -2.617170810699463,
|
816 |
+
"logps/chosen": -70.10054779052734,
|
817 |
+
"logps/rejected": -74.9827880859375,
|
818 |
+
"loss": 0.4809,
|
819 |
+
"rewards/accuracies": 0.38749998807907104,
|
820 |
+
"rewards/chosen": 1.9351723194122314,
|
821 |
+
"rewards/margins": 4.985955715179443,
|
822 |
+
"rewards/rejected": -3.05078387260437,
|
823 |
+
"step": 490
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 1.7421602787456445,
|
827 |
+
"grad_norm": 134.98085943724894,
|
828 |
+
"learning_rate": 1.9328165374677e-07,
|
829 |
+
"logits/chosen": -2.5582988262176514,
|
830 |
+
"logits/rejected": -2.551264524459839,
|
831 |
+
"logps/chosen": -73.02742004394531,
|
832 |
+
"logps/rejected": -89.30897521972656,
|
833 |
+
"loss": 0.3893,
|
834 |
+
"rewards/accuracies": 0.46875,
|
835 |
+
"rewards/chosen": 2.0215065479278564,
|
836 |
+
"rewards/margins": 5.4846272468566895,
|
837 |
+
"rewards/rejected": -3.463120222091675,
|
838 |
+
"step": 500
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 1.7421602787456445,
|
842 |
+
"eval_logits/chosen": -2.6659271717071533,
|
843 |
+
"eval_logits/rejected": -2.6499409675598145,
|
844 |
+
"eval_logps/chosen": -75.26073455810547,
|
845 |
+
"eval_logps/rejected": -83.39617919921875,
|
846 |
+
"eval_loss": 0.7903804183006287,
|
847 |
+
"eval_rewards/accuracies": 0.3492063581943512,
|
848 |
+
"eval_rewards/chosen": -0.47709161043167114,
|
849 |
+
"eval_rewards/margins": 0.9289572834968567,
|
850 |
+
"eval_rewards/rejected": -1.4060487747192383,
|
851 |
+
"eval_runtime": 121.402,
|
852 |
+
"eval_samples_per_second": 16.474,
|
853 |
+
"eval_steps_per_second": 0.519,
|
854 |
+
"step": 500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 1.7770034843205575,
|
858 |
+
"grad_norm": 28.87847596006846,
|
859 |
+
"learning_rate": 1.9069767441860465e-07,
|
860 |
+
"logits/chosen": -2.623152732849121,
|
861 |
+
"logits/rejected": -2.60357666015625,
|
862 |
+
"logps/chosen": -68.32408142089844,
|
863 |
+
"logps/rejected": -75.5625991821289,
|
864 |
+
"loss": 0.3872,
|
865 |
+
"rewards/accuracies": 0.4625000059604645,
|
866 |
+
"rewards/chosen": 1.5080443620681763,
|
867 |
+
"rewards/margins": 5.214726448059082,
|
868 |
+
"rewards/rejected": -3.706681728363037,
|
869 |
+
"step": 510
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 1.8118466898954704,
|
873 |
+
"grad_norm": 24.57794510996642,
|
874 |
+
"learning_rate": 1.8811369509043926e-07,
|
875 |
+
"logits/chosen": -2.635575532913208,
|
876 |
+
"logits/rejected": -2.630188226699829,
|
877 |
+
"logps/chosen": -71.8682861328125,
|
878 |
+
"logps/rejected": -82.45121002197266,
|
879 |
+
"loss": 0.3947,
|
880 |
+
"rewards/accuracies": 0.46875,
|
881 |
+
"rewards/chosen": 1.4898183345794678,
|
882 |
+
"rewards/margins": 4.737631797790527,
|
883 |
+
"rewards/rejected": -3.247814178466797,
|
884 |
+
"step": 520
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 1.8466898954703832,
|
888 |
+
"grad_norm": 43.47081299094027,
|
889 |
+
"learning_rate": 1.8552971576227387e-07,
|
890 |
+
"logits/chosen": -2.6130404472351074,
|
891 |
+
"logits/rejected": -2.6072745323181152,
|
892 |
+
"logps/chosen": -67.63585662841797,
|
893 |
+
"logps/rejected": -76.81507873535156,
|
894 |
+
"loss": 0.4098,
|
895 |
+
"rewards/accuracies": 0.45625001192092896,
|
896 |
+
"rewards/chosen": 2.294175386428833,
|
897 |
+
"rewards/margins": 5.674102306365967,
|
898 |
+
"rewards/rejected": -3.379927158355713,
|
899 |
+
"step": 530
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 1.8815331010452963,
|
903 |
+
"grad_norm": 379.9980856009288,
|
904 |
+
"learning_rate": 1.829457364341085e-07,
|
905 |
+
"logits/chosen": -2.6233439445495605,
|
906 |
+
"logits/rejected": -2.6407742500305176,
|
907 |
+
"logps/chosen": -59.39795684814453,
|
908 |
+
"logps/rejected": -78.36451721191406,
|
909 |
+
"loss": 0.4218,
|
910 |
+
"rewards/accuracies": 0.45625001192092896,
|
911 |
+
"rewards/chosen": 2.6863512992858887,
|
912 |
+
"rewards/margins": 5.80073881149292,
|
913 |
+
"rewards/rejected": -3.114386796951294,
|
914 |
+
"step": 540
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 1.916376306620209,
|
918 |
+
"grad_norm": 36.16567370320362,
|
919 |
+
"learning_rate": 1.8036175710594315e-07,
|
920 |
+
"logits/chosen": -2.6051318645477295,
|
921 |
+
"logits/rejected": -2.5861499309539795,
|
922 |
+
"logps/chosen": -85.02639770507812,
|
923 |
+
"logps/rejected": -92.01643371582031,
|
924 |
+
"loss": 0.3918,
|
925 |
+
"rewards/accuracies": 0.5,
|
926 |
+
"rewards/chosen": 3.6012024879455566,
|
927 |
+
"rewards/margins": 6.781991004943848,
|
928 |
+
"rewards/rejected": -3.180788993835449,
|
929 |
+
"step": 550
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 1.951219512195122,
|
933 |
+
"grad_norm": 113.77212344428047,
|
934 |
+
"learning_rate": 1.7777777777777776e-07,
|
935 |
+
"logits/chosen": -2.601555347442627,
|
936 |
+
"logits/rejected": -2.6108827590942383,
|
937 |
+
"logps/chosen": -59.21348190307617,
|
938 |
+
"logps/rejected": -73.62416076660156,
|
939 |
+
"loss": 0.4326,
|
940 |
+
"rewards/accuracies": 0.4375,
|
941 |
+
"rewards/chosen": 2.7940502166748047,
|
942 |
+
"rewards/margins": 4.857416152954102,
|
943 |
+
"rewards/rejected": -2.063365936279297,
|
944 |
+
"step": 560
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 1.986062717770035,
|
948 |
+
"grad_norm": 84.29111668630037,
|
949 |
+
"learning_rate": 1.7519379844961235e-07,
|
950 |
+
"logits/chosen": -2.676542282104492,
|
951 |
+
"logits/rejected": -2.6477246284484863,
|
952 |
+
"logps/chosen": -60.66288375854492,
|
953 |
+
"logps/rejected": -65.19253540039062,
|
954 |
+
"loss": 0.4049,
|
955 |
+
"rewards/accuracies": 0.4312500059604645,
|
956 |
+
"rewards/chosen": 2.821211338043213,
|
957 |
+
"rewards/margins": 4.4517645835876465,
|
958 |
+
"rewards/rejected": -1.6305538415908813,
|
959 |
+
"step": 570
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 2.0209059233449476,
|
963 |
+
"grad_norm": 1.1269554094711256,
|
964 |
+
"learning_rate": 1.7260981912144704e-07,
|
965 |
+
"logits/chosen": -2.685316801071167,
|
966 |
+
"logits/rejected": -2.6868529319763184,
|
967 |
+
"logps/chosen": -73.15747833251953,
|
968 |
+
"logps/rejected": -84.87666320800781,
|
969 |
+
"loss": 0.3613,
|
970 |
+
"rewards/accuracies": 0.5,
|
971 |
+
"rewards/chosen": 3.4528770446777344,
|
972 |
+
"rewards/margins": 6.801962852478027,
|
973 |
+
"rewards/rejected": -3.349086046218872,
|
974 |
+
"step": 580
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 2.0557491289198606,
|
978 |
+
"grad_norm": 25.976934863727717,
|
979 |
+
"learning_rate": 1.7002583979328165e-07,
|
980 |
+
"logits/chosen": -2.589168071746826,
|
981 |
+
"logits/rejected": -2.530686378479004,
|
982 |
+
"logps/chosen": -87.9363021850586,
|
983 |
+
"logps/rejected": -83.9460220336914,
|
984 |
+
"loss": 0.343,
|
985 |
+
"rewards/accuracies": 0.5375000238418579,
|
986 |
+
"rewards/chosen": 4.061544895172119,
|
987 |
+
"rewards/margins": 7.5588788986206055,
|
988 |
+
"rewards/rejected": -3.4973349571228027,
|
989 |
+
"step": 590
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 2.0905923344947737,
|
993 |
+
"grad_norm": 4.291125808983435,
|
994 |
+
"learning_rate": 1.6744186046511627e-07,
|
995 |
+
"logits/chosen": -2.6059463024139404,
|
996 |
+
"logits/rejected": -2.5761430263519287,
|
997 |
+
"logps/chosen": -57.32917404174805,
|
998 |
+
"logps/rejected": -64.40930938720703,
|
999 |
+
"loss": 0.3749,
|
1000 |
+
"rewards/accuracies": 0.44999998807907104,
|
1001 |
+
"rewards/chosen": 2.808424234390259,
|
1002 |
+
"rewards/margins": 5.987191200256348,
|
1003 |
+
"rewards/rejected": -3.1787662506103516,
|
1004 |
+
"step": 600
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 2.0905923344947737,
|
1008 |
+
"eval_logits/chosen": -2.6320791244506836,
|
1009 |
+
"eval_logits/rejected": -2.6158933639526367,
|
1010 |
+
"eval_logps/chosen": -73.58616638183594,
|
1011 |
+
"eval_logps/rejected": -81.91004180908203,
|
1012 |
+
"eval_loss": 0.8125157952308655,
|
1013 |
+
"eval_rewards/accuracies": 0.363095223903656,
|
1014 |
+
"eval_rewards/chosen": 0.5611402988433838,
|
1015 |
+
"eval_rewards/margins": 1.0457921028137207,
|
1016 |
+
"eval_rewards/rejected": -0.48465171456336975,
|
1017 |
+
"eval_runtime": 113.5505,
|
1018 |
+
"eval_samples_per_second": 17.613,
|
1019 |
+
"eval_steps_per_second": 0.555,
|
1020 |
+
"step": 600
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 2.1254355400696863,
|
1024 |
+
"grad_norm": 7.908116387433432,
|
1025 |
+
"learning_rate": 1.6485788113695088e-07,
|
1026 |
+
"logits/chosen": -2.655932664871216,
|
1027 |
+
"logits/rejected": -2.618626117706299,
|
1028 |
+
"logps/chosen": -77.79930114746094,
|
1029 |
+
"logps/rejected": -76.16334533691406,
|
1030 |
+
"loss": 0.3651,
|
1031 |
+
"rewards/accuracies": 0.4749999940395355,
|
1032 |
+
"rewards/chosen": 3.5249366760253906,
|
1033 |
+
"rewards/margins": 6.6772894859313965,
|
1034 |
+
"rewards/rejected": -3.152352809906006,
|
1035 |
+
"step": 610
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 2.1602787456445993,
|
1039 |
+
"grad_norm": 12.816821249204288,
|
1040 |
+
"learning_rate": 1.6227390180878554e-07,
|
1041 |
+
"logits/chosen": -2.6253597736358643,
|
1042 |
+
"logits/rejected": -2.570455551147461,
|
1043 |
+
"logps/chosen": -72.71697998046875,
|
1044 |
+
"logps/rejected": -84.75135040283203,
|
1045 |
+
"loss": 0.3665,
|
1046 |
+
"rewards/accuracies": 0.518750011920929,
|
1047 |
+
"rewards/chosen": 3.5354607105255127,
|
1048 |
+
"rewards/margins": 7.969748020172119,
|
1049 |
+
"rewards/rejected": -4.434287071228027,
|
1050 |
+
"step": 620
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 2.1951219512195124,
|
1054 |
+
"grad_norm": 8.050269883900128,
|
1055 |
+
"learning_rate": 1.5968992248062013e-07,
|
1056 |
+
"logits/chosen": -2.5422072410583496,
|
1057 |
+
"logits/rejected": -2.559743881225586,
|
1058 |
+
"logps/chosen": -67.67036437988281,
|
1059 |
+
"logps/rejected": -95.14600372314453,
|
1060 |
+
"loss": 0.3449,
|
1061 |
+
"rewards/accuracies": 0.5249999761581421,
|
1062 |
+
"rewards/chosen": 3.445582866668701,
|
1063 |
+
"rewards/margins": 8.744329452514648,
|
1064 |
+
"rewards/rejected": -5.2987470626831055,
|
1065 |
+
"step": 630
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 2.229965156794425,
|
1069 |
+
"grad_norm": 5.758994331059265,
|
1070 |
+
"learning_rate": 1.5710594315245477e-07,
|
1071 |
+
"logits/chosen": -2.5750184059143066,
|
1072 |
+
"logits/rejected": -2.5732388496398926,
|
1073 |
+
"logps/chosen": -66.1601333618164,
|
1074 |
+
"logps/rejected": -90.6006851196289,
|
1075 |
+
"loss": 0.3713,
|
1076 |
+
"rewards/accuracies": 0.45625001192092896,
|
1077 |
+
"rewards/chosen": 2.1229605674743652,
|
1078 |
+
"rewards/margins": 6.844090938568115,
|
1079 |
+
"rewards/rejected": -4.721129894256592,
|
1080 |
+
"step": 640
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 2.264808362369338,
|
1084 |
+
"grad_norm": 4.106714414729963,
|
1085 |
+
"learning_rate": 1.5452196382428938e-07,
|
1086 |
+
"logits/chosen": -2.571296215057373,
|
1087 |
+
"logits/rejected": -2.5443153381347656,
|
1088 |
+
"logps/chosen": -76.41832733154297,
|
1089 |
+
"logps/rejected": -84.57535552978516,
|
1090 |
+
"loss": 0.3914,
|
1091 |
+
"rewards/accuracies": 0.42500001192092896,
|
1092 |
+
"rewards/chosen": 2.150641918182373,
|
1093 |
+
"rewards/margins": 6.811266899108887,
|
1094 |
+
"rewards/rejected": -4.660625457763672,
|
1095 |
+
"step": 650
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 2.2996515679442506,
|
1099 |
+
"grad_norm": 26.12193694012493,
|
1100 |
+
"learning_rate": 1.5193798449612402e-07,
|
1101 |
+
"logits/chosen": -2.601414203643799,
|
1102 |
+
"logits/rejected": -2.5880684852600098,
|
1103 |
+
"logps/chosen": -76.15614318847656,
|
1104 |
+
"logps/rejected": -84.27168273925781,
|
1105 |
+
"loss": 0.3595,
|
1106 |
+
"rewards/accuracies": 0.4437499940395355,
|
1107 |
+
"rewards/chosen": 1.7724649906158447,
|
1108 |
+
"rewards/margins": 7.21490478515625,
|
1109 |
+
"rewards/rejected": -5.442440986633301,
|
1110 |
+
"step": 660
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 2.3344947735191637,
|
1114 |
+
"grad_norm": 10.794985780975221,
|
1115 |
+
"learning_rate": 1.4935400516795863e-07,
|
1116 |
+
"logits/chosen": -2.593954563140869,
|
1117 |
+
"logits/rejected": -2.5915369987487793,
|
1118 |
+
"logps/chosen": -70.91958618164062,
|
1119 |
+
"logps/rejected": -83.38150787353516,
|
1120 |
+
"loss": 0.3772,
|
1121 |
+
"rewards/accuracies": 0.45625001192092896,
|
1122 |
+
"rewards/chosen": 1.1422145366668701,
|
1123 |
+
"rewards/margins": 7.140495300292969,
|
1124 |
+
"rewards/rejected": -5.998281002044678,
|
1125 |
+
"step": 670
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 2.3693379790940767,
|
1129 |
+
"grad_norm": 2.1208474931059706,
|
1130 |
+
"learning_rate": 1.4677002583979327e-07,
|
1131 |
+
"logits/chosen": -2.635155439376831,
|
1132 |
+
"logits/rejected": -2.622910499572754,
|
1133 |
+
"logps/chosen": -70.04927062988281,
|
1134 |
+
"logps/rejected": -82.35643005371094,
|
1135 |
+
"loss": 0.3572,
|
1136 |
+
"rewards/accuracies": 0.48750001192092896,
|
1137 |
+
"rewards/chosen": 2.0802841186523438,
|
1138 |
+
"rewards/margins": 8.326448440551758,
|
1139 |
+
"rewards/rejected": -6.246163845062256,
|
1140 |
+
"step": 680
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 2.40418118466899,
|
1144 |
+
"grad_norm": 10.487007281103297,
|
1145 |
+
"learning_rate": 1.4418604651162788e-07,
|
1146 |
+
"logits/chosen": -2.6031365394592285,
|
1147 |
+
"logits/rejected": -2.5714783668518066,
|
1148 |
+
"logps/chosen": -77.78074645996094,
|
1149 |
+
"logps/rejected": -97.24638366699219,
|
1150 |
+
"loss": 0.3613,
|
1151 |
+
"rewards/accuracies": 0.4749999940395355,
|
1152 |
+
"rewards/chosen": 2.6356489658355713,
|
1153 |
+
"rewards/margins": 8.40825080871582,
|
1154 |
+
"rewards/rejected": -5.7726030349731445,
|
1155 |
+
"step": 690
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 2.4390243902439024,
|
1159 |
+
"grad_norm": 7.007416212948012,
|
1160 |
+
"learning_rate": 1.4160206718346252e-07,
|
1161 |
+
"logits/chosen": -2.5922415256500244,
|
1162 |
+
"logits/rejected": -2.5560450553894043,
|
1163 |
+
"logps/chosen": -83.61808776855469,
|
1164 |
+
"logps/rejected": -89.99815368652344,
|
1165 |
+
"loss": 0.3662,
|
1166 |
+
"rewards/accuracies": 0.53125,
|
1167 |
+
"rewards/chosen": 3.2752013206481934,
|
1168 |
+
"rewards/margins": 8.457530975341797,
|
1169 |
+
"rewards/rejected": -5.182328701019287,
|
1170 |
+
"step": 700
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 2.4390243902439024,
|
1174 |
+
"eval_logits/chosen": -2.6111857891082764,
|
1175 |
+
"eval_logits/rejected": -2.594111442565918,
|
1176 |
+
"eval_logps/chosen": -75.47573852539062,
|
1177 |
+
"eval_logps/rejected": -84.49435424804688,
|
1178 |
+
"eval_loss": 0.8411857485771179,
|
1179 |
+
"eval_rewards/accuracies": 0.3650793731212616,
|
1180 |
+
"eval_rewards/chosen": -0.6103957891464233,
|
1181 |
+
"eval_rewards/margins": 1.476527214050293,
|
1182 |
+
"eval_rewards/rejected": -2.086923122406006,
|
1183 |
+
"eval_runtime": 113.5556,
|
1184 |
+
"eval_samples_per_second": 17.613,
|
1185 |
+
"eval_steps_per_second": 0.555,
|
1186 |
+
"step": 700
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 2.4738675958188154,
|
1190 |
+
"grad_norm": 0.4711439948410044,
|
1191 |
+
"learning_rate": 1.3901808785529716e-07,
|
1192 |
+
"logits/chosen": -2.632316827774048,
|
1193 |
+
"logits/rejected": -2.612363576889038,
|
1194 |
+
"logps/chosen": -91.01361083984375,
|
1195 |
+
"logps/rejected": -111.48197937011719,
|
1196 |
+
"loss": 0.3629,
|
1197 |
+
"rewards/accuracies": 0.5249999761581421,
|
1198 |
+
"rewards/chosen": 2.5902059078216553,
|
1199 |
+
"rewards/margins": 9.54753303527832,
|
1200 |
+
"rewards/rejected": -6.957326412200928,
|
1201 |
+
"step": 710
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 2.508710801393728,
|
1205 |
+
"grad_norm": 0.03547147611253739,
|
1206 |
+
"learning_rate": 1.3643410852713177e-07,
|
1207 |
+
"logits/chosen": -2.6036946773529053,
|
1208 |
+
"logits/rejected": -2.5696444511413574,
|
1209 |
+
"logps/chosen": -66.248779296875,
|
1210 |
+
"logps/rejected": -71.01225280761719,
|
1211 |
+
"loss": 0.4025,
|
1212 |
+
"rewards/accuracies": 0.45625001192092896,
|
1213 |
+
"rewards/chosen": 2.9773497581481934,
|
1214 |
+
"rewards/margins": 7.88436222076416,
|
1215 |
+
"rewards/rejected": -4.907011985778809,
|
1216 |
+
"step": 720
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 2.543554006968641,
|
1220 |
+
"grad_norm": 4.675015379292036,
|
1221 |
+
"learning_rate": 1.3385012919896641e-07,
|
1222 |
+
"logits/chosen": -2.6531801223754883,
|
1223 |
+
"logits/rejected": -2.628028392791748,
|
1224 |
+
"logps/chosen": -65.84535217285156,
|
1225 |
+
"logps/rejected": -67.12870025634766,
|
1226 |
+
"loss": 0.3706,
|
1227 |
+
"rewards/accuracies": 0.34375,
|
1228 |
+
"rewards/chosen": 2.7976653575897217,
|
1229 |
+
"rewards/margins": 6.484448432922363,
|
1230 |
+
"rewards/rejected": -3.6867833137512207,
|
1231 |
+
"step": 730
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 2.578397212543554,
|
1235 |
+
"grad_norm": 15.399000464963422,
|
1236 |
+
"learning_rate": 1.3126614987080103e-07,
|
1237 |
+
"logits/chosen": -2.5426218509674072,
|
1238 |
+
"logits/rejected": -2.5461742877960205,
|
1239 |
+
"logps/chosen": -61.294456481933594,
|
1240 |
+
"logps/rejected": -87.54208374023438,
|
1241 |
+
"loss": 0.3653,
|
1242 |
+
"rewards/accuracies": 0.4375,
|
1243 |
+
"rewards/chosen": 2.92600154876709,
|
1244 |
+
"rewards/margins": 8.220406532287598,
|
1245 |
+
"rewards/rejected": -5.29440450668335,
|
1246 |
+
"step": 740
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 2.6132404181184667,
|
1250 |
+
"grad_norm": 1.423350223185656,
|
1251 |
+
"learning_rate": 1.2868217054263566e-07,
|
1252 |
+
"logits/chosen": -2.6260664463043213,
|
1253 |
+
"logits/rejected": -2.613114595413208,
|
1254 |
+
"logps/chosen": -62.37495040893555,
|
1255 |
+
"logps/rejected": -72.44084930419922,
|
1256 |
+
"loss": 0.35,
|
1257 |
+
"rewards/accuracies": 0.4937500059604645,
|
1258 |
+
"rewards/chosen": 3.621440887451172,
|
1259 |
+
"rewards/margins": 6.8329291343688965,
|
1260 |
+
"rewards/rejected": -3.2114882469177246,
|
1261 |
+
"step": 750
|
1262 |
+
},
|
1263 |
+
{
|
1264 |
+
"epoch": 2.64808362369338,
|
1265 |
+
"grad_norm": 28.902176788755387,
|
1266 |
+
"learning_rate": 1.2609819121447028e-07,
|
1267 |
+
"logits/chosen": -2.54823637008667,
|
1268 |
+
"logits/rejected": -2.536100387573242,
|
1269 |
+
"logps/chosen": -48.50947189331055,
|
1270 |
+
"logps/rejected": -61.75891876220703,
|
1271 |
+
"loss": 0.3804,
|
1272 |
+
"rewards/accuracies": 0.38749998807907104,
|
1273 |
+
"rewards/chosen": 2.9782872200012207,
|
1274 |
+
"rewards/margins": 6.0528998374938965,
|
1275 |
+
"rewards/rejected": -3.074612855911255,
|
1276 |
+
"step": 760
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 2.682926829268293,
|
1280 |
+
"grad_norm": 0.05604179114051096,
|
1281 |
+
"learning_rate": 1.2351421188630492e-07,
|
1282 |
+
"logits/chosen": -2.6780683994293213,
|
1283 |
+
"logits/rejected": -2.659198522567749,
|
1284 |
+
"logps/chosen": -71.71595764160156,
|
1285 |
+
"logps/rejected": -86.19725036621094,
|
1286 |
+
"loss": 0.3745,
|
1287 |
+
"rewards/accuracies": 0.45625001192092896,
|
1288 |
+
"rewards/chosen": 3.0666489601135254,
|
1289 |
+
"rewards/margins": 7.4923295974731445,
|
1290 |
+
"rewards/rejected": -4.425681114196777,
|
1291 |
+
"step": 770
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 2.7177700348432055,
|
1295 |
+
"grad_norm": 0.283574851628151,
|
1296 |
+
"learning_rate": 1.2093023255813953e-07,
|
1297 |
+
"logits/chosen": -2.6133499145507812,
|
1298 |
+
"logits/rejected": -2.612217426300049,
|
1299 |
+
"logps/chosen": -74.23127746582031,
|
1300 |
+
"logps/rejected": -91.57493591308594,
|
1301 |
+
"loss": 0.3447,
|
1302 |
+
"rewards/accuracies": 0.512499988079071,
|
1303 |
+
"rewards/chosen": 4.144797325134277,
|
1304 |
+
"rewards/margins": 9.933080673217773,
|
1305 |
+
"rewards/rejected": -5.788283348083496,
|
1306 |
+
"step": 780
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 2.7526132404181185,
|
1310 |
+
"grad_norm": 0.8997563908630796,
|
1311 |
+
"learning_rate": 1.1834625322997414e-07,
|
1312 |
+
"logits/chosen": -2.6512093544006348,
|
1313 |
+
"logits/rejected": -2.6401140689849854,
|
1314 |
+
"logps/chosen": -64.2149429321289,
|
1315 |
+
"logps/rejected": -82.6252212524414,
|
1316 |
+
"loss": 0.3748,
|
1317 |
+
"rewards/accuracies": 0.4625000059604645,
|
1318 |
+
"rewards/chosen": 1.9805446863174438,
|
1319 |
+
"rewards/margins": 7.318342685699463,
|
1320 |
+
"rewards/rejected": -5.337798118591309,
|
1321 |
+
"step": 790
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 2.7874564459930316,
|
1325 |
+
"grad_norm": 20.667512714719013,
|
1326 |
+
"learning_rate": 1.1576227390180877e-07,
|
1327 |
+
"logits/chosen": -2.621532440185547,
|
1328 |
+
"logits/rejected": -2.5869758129119873,
|
1329 |
+
"logps/chosen": -75.92918395996094,
|
1330 |
+
"logps/rejected": -84.97443389892578,
|
1331 |
+
"loss": 0.3615,
|
1332 |
+
"rewards/accuracies": 0.46875,
|
1333 |
+
"rewards/chosen": 2.5894510746002197,
|
1334 |
+
"rewards/margins": 8.263704299926758,
|
1335 |
+
"rewards/rejected": -5.674252510070801,
|
1336 |
+
"step": 800
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 2.7874564459930316,
|
1340 |
+
"eval_logits/chosen": -2.6538193225860596,
|
1341 |
+
"eval_logits/rejected": -2.636691093444824,
|
1342 |
+
"eval_logps/chosen": -76.02718353271484,
|
1343 |
+
"eval_logps/rejected": -85.26797485351562,
|
1344 |
+
"eval_loss": 0.8766492605209351,
|
1345 |
+
"eval_rewards/accuracies": 0.3611111044883728,
|
1346 |
+
"eval_rewards/chosen": -0.9522846937179565,
|
1347 |
+
"eval_rewards/margins": 1.6142810583114624,
|
1348 |
+
"eval_rewards/rejected": -2.566565990447998,
|
1349 |
+
"eval_runtime": 113.6286,
|
1350 |
+
"eval_samples_per_second": 17.601,
|
1351 |
+
"eval_steps_per_second": 0.554,
|
1352 |
+
"step": 800
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 2.822299651567944,
|
1356 |
+
"grad_norm": 2.1853706150186754,
|
1357 |
+
"learning_rate": 1.131782945736434e-07,
|
1358 |
+
"logits/chosen": -2.6088814735412598,
|
1359 |
+
"logits/rejected": -2.5650715827941895,
|
1360 |
+
"logps/chosen": -85.81961822509766,
|
1361 |
+
"logps/rejected": -88.84381103515625,
|
1362 |
+
"loss": 0.3574,
|
1363 |
+
"rewards/accuracies": 0.5249999761581421,
|
1364 |
+
"rewards/chosen": 2.4687106609344482,
|
1365 |
+
"rewards/margins": 8.304216384887695,
|
1366 |
+
"rewards/rejected": -5.835506439208984,
|
1367 |
+
"step": 810
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 2.857142857142857,
|
1371 |
+
"grad_norm": 3.1905831999742365,
|
1372 |
+
"learning_rate": 1.1059431524547802e-07,
|
1373 |
+
"logits/chosen": -2.621854305267334,
|
1374 |
+
"logits/rejected": -2.6245625019073486,
|
1375 |
+
"logps/chosen": -87.5467529296875,
|
1376 |
+
"logps/rejected": -108.12459564208984,
|
1377 |
+
"loss": 0.3825,
|
1378 |
+
"rewards/accuracies": 0.512499988079071,
|
1379 |
+
"rewards/chosen": 2.308243989944458,
|
1380 |
+
"rewards/margins": 8.762375831604004,
|
1381 |
+
"rewards/rejected": -6.454131126403809,
|
1382 |
+
"step": 820
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 2.89198606271777,
|
1386 |
+
"grad_norm": 0.7951775803731691,
|
1387 |
+
"learning_rate": 1.0801033591731266e-07,
|
1388 |
+
"logits/chosen": -2.5292835235595703,
|
1389 |
+
"logits/rejected": -2.5408291816711426,
|
1390 |
+
"logps/chosen": -59.091575622558594,
|
1391 |
+
"logps/rejected": -82.16059112548828,
|
1392 |
+
"loss": 0.3596,
|
1393 |
+
"rewards/accuracies": 0.4437499940395355,
|
1394 |
+
"rewards/chosen": 1.360400915145874,
|
1395 |
+
"rewards/margins": 7.509343147277832,
|
1396 |
+
"rewards/rejected": -6.148941993713379,
|
1397 |
+
"step": 830
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 2.926829268292683,
|
1401 |
+
"grad_norm": 1.1924411554401215,
|
1402 |
+
"learning_rate": 1.054263565891473e-07,
|
1403 |
+
"logits/chosen": -2.617638111114502,
|
1404 |
+
"logits/rejected": -2.5782742500305176,
|
1405 |
+
"logps/chosen": -76.57533264160156,
|
1406 |
+
"logps/rejected": -92.98815155029297,
|
1407 |
+
"loss": 0.3733,
|
1408 |
+
"rewards/accuracies": 0.4937500059604645,
|
1409 |
+
"rewards/chosen": 3.365124464035034,
|
1410 |
+
"rewards/margins": 9.208218574523926,
|
1411 |
+
"rewards/rejected": -5.843094825744629,
|
1412 |
+
"step": 840
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 2.961672473867596,
|
1416 |
+
"grad_norm": 0.8910844109249688,
|
1417 |
+
"learning_rate": 1.0284237726098191e-07,
|
1418 |
+
"logits/chosen": -2.6461727619171143,
|
1419 |
+
"logits/rejected": -2.616791009902954,
|
1420 |
+
"logps/chosen": -86.35088348388672,
|
1421 |
+
"logps/rejected": -93.9124526977539,
|
1422 |
+
"loss": 0.3609,
|
1423 |
+
"rewards/accuracies": 0.518750011920929,
|
1424 |
+
"rewards/chosen": 3.4399936199188232,
|
1425 |
+
"rewards/margins": 8.806478500366211,
|
1426 |
+
"rewards/rejected": -5.366484642028809,
|
1427 |
+
"step": 850
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 2.996515679442509,
|
1431 |
+
"grad_norm": 43.871948824299515,
|
1432 |
+
"learning_rate": 1.0025839793281653e-07,
|
1433 |
+
"logits/chosen": -2.576416015625,
|
1434 |
+
"logits/rejected": -2.5809175968170166,
|
1435 |
+
"logps/chosen": -69.1751708984375,
|
1436 |
+
"logps/rejected": -86.57472229003906,
|
1437 |
+
"loss": 0.3403,
|
1438 |
+
"rewards/accuracies": 0.45625001192092896,
|
1439 |
+
"rewards/chosen": 3.5098342895507812,
|
1440 |
+
"rewards/margins": 9.559127807617188,
|
1441 |
+
"rewards/rejected": -6.049294471740723,
|
1442 |
+
"step": 860
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 3.0,
|
1446 |
+
"step": 861,
|
1447 |
+
"total_flos": 0.0,
|
1448 |
+
"train_loss": 0.4762609164889266,
|
1449 |
+
"train_runtime": 9670.9508,
|
1450 |
+
"train_samples_per_second": 5.689,
|
1451 |
+
"train_steps_per_second": 0.089
|
1452 |
+
}
|
1453 |
+
],
|
1454 |
+
"logging_steps": 10,
|
1455 |
+
"max_steps": 861,
|
1456 |
+
"num_input_tokens_seen": 0,
|
1457 |
+
"num_train_epochs": 3,
|
1458 |
+
"save_steps": 100,
|
1459 |
+
"stateful_callbacks": {
|
1460 |
+
"TrainerControl": {
|
1461 |
+
"args": {
|
1462 |
+
"should_epoch_stop": false,
|
1463 |
+
"should_evaluate": false,
|
1464 |
+
"should_log": false,
|
1465 |
+
"should_save": true,
|
1466 |
+
"should_training_stop": true
|
1467 |
+
},
|
1468 |
+
"attributes": {}
|
1469 |
+
}
|
1470 |
+
},
|
1471 |
+
"total_flos": 0.0,
|
1472 |
+
"train_batch_size": 8,
|
1473 |
+
"trial_name": null,
|
1474 |
+
"trial_params": null
|
1475 |
+
}
|