Model save
Browse files- README.md +117 -0
- all_results.json +9 -0
- generation_config.json +12 -0
- train_results.json +9 -0
- trainer_state.json +837 -0
README.md
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: llama3.1
|
| 4 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- cpo
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: llama3.1-cpo-full-0919
|
| 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 |
+
# llama3.1-cpo-full-0919
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.0545
|
| 22 |
+
- Rewards/chosen: -18.3931
|
| 23 |
+
- Rewards/rejected: -18.5452
|
| 24 |
+
- Rewards/accuracies: 0.5261
|
| 25 |
+
- Rewards/margins: 0.1521
|
| 26 |
+
- Logps/rejected: -185.4521
|
| 27 |
+
- Logps/chosen: -183.9312
|
| 28 |
+
- Logits/rejected: -0.7551
|
| 29 |
+
- Logits/chosen: -0.7797
|
| 30 |
+
- Nll Loss: 0.5180
|
| 31 |
+
|
| 32 |
+
## Model description
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Intended uses & limitations
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training and evaluation data
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training procedure
|
| 45 |
+
|
| 46 |
+
### Training hyperparameters
|
| 47 |
+
|
| 48 |
+
The following hyperparameters were used during training:
|
| 49 |
+
- learning_rate: 1e-06
|
| 50 |
+
- train_batch_size: 4
|
| 51 |
+
- eval_batch_size: 4
|
| 52 |
+
- seed: 42
|
| 53 |
+
- distributed_type: multi-GPU
|
| 54 |
+
- num_devices: 4
|
| 55 |
+
- gradient_accumulation_steps: 8
|
| 56 |
+
- total_train_batch_size: 128
|
| 57 |
+
- total_eval_batch_size: 16
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 61 |
+
- num_epochs: 1
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss |
|
| 66 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|
|
| 67 |
+
| No log | 0.0230 | 1 | 2.5065 | -26.5532 | -26.5849 | 0.5174 | 0.0317 | -265.8489 | -265.5324 | -0.2622 | -0.2859 | 0.7676 |
|
| 68 |
+
| No log | 0.0460 | 2 | 2.5060 | -26.5180 | -26.5504 | 0.5217 | 0.0324 | -265.5038 | -265.1801 | -0.2634 | -0.2869 | 0.7666 |
|
| 69 |
+
| No log | 0.0690 | 3 | 2.5051 | -26.5009 | -26.5278 | 0.5217 | 0.0269 | -265.2777 | -265.0088 | -0.2657 | -0.2893 | 0.7661 |
|
| 70 |
+
| No log | 0.0920 | 4 | 2.4982 | -26.3952 | -26.4315 | 0.5239 | 0.0363 | -264.3147 | -263.9518 | -0.2690 | -0.2926 | 0.7632 |
|
| 71 |
+
| No log | 0.1149 | 5 | 2.4894 | -26.2651 | -26.3011 | 0.5217 | 0.0360 | -263.0112 | -262.6512 | -0.2750 | -0.2985 | 0.7594 |
|
| 72 |
+
| No log | 0.1379 | 6 | 2.4689 | -25.9450 | -25.9855 | 0.5283 | 0.0405 | -259.8551 | -259.4500 | -0.2858 | -0.3086 | 0.7502 |
|
| 73 |
+
| No log | 0.1609 | 7 | 2.4511 | -25.7084 | -25.7527 | 0.5283 | 0.0443 | -257.5271 | -257.0843 | -0.2972 | -0.3202 | 0.7433 |
|
| 74 |
+
| No log | 0.1839 | 8 | 2.4180 | -25.2215 | -25.2724 | 0.5326 | 0.0510 | -252.7242 | -252.2147 | -0.3254 | -0.3486 | 0.7291 |
|
| 75 |
+
| No log | 0.2069 | 9 | 2.3952 | -24.8845 | -24.9393 | 0.5283 | 0.0548 | -249.3929 | -248.8451 | -0.3463 | -0.3701 | 0.7192 |
|
| 76 |
+
| 2.6865 | 0.2299 | 10 | 2.3761 | -24.6215 | -24.6782 | 0.5348 | 0.0567 | -246.7821 | -246.2148 | -0.3604 | -0.3845 | 0.7115 |
|
| 77 |
+
| 2.6865 | 0.2529 | 11 | 2.3609 | -24.4027 | -24.4705 | 0.5391 | 0.0678 | -244.7050 | -244.0270 | -0.3731 | -0.3976 | 0.7051 |
|
| 78 |
+
| 2.6865 | 0.2759 | 12 | 2.3367 | -24.0560 | -24.1306 | 0.5348 | 0.0746 | -241.3063 | -240.5604 | -0.3970 | -0.4218 | 0.6951 |
|
| 79 |
+
| 2.6865 | 0.2989 | 13 | 2.3109 | -23.6786 | -23.7645 | 0.5304 | 0.0860 | -237.6454 | -236.7858 | -0.4179 | -0.4434 | 0.6840 |
|
| 80 |
+
| 2.6865 | 0.3218 | 14 | 2.2906 | -23.3175 | -23.4031 | 0.5348 | 0.0856 | -234.0311 | -233.1748 | -0.4423 | -0.4679 | 0.6733 |
|
| 81 |
+
| 2.6865 | 0.3448 | 15 | 2.2729 | -22.9946 | -23.0933 | 0.5348 | 0.0988 | -230.9332 | -229.9456 | -0.4660 | -0.4917 | 0.6637 |
|
| 82 |
+
| 2.6865 | 0.3678 | 16 | 2.2576 | -22.7067 | -22.8056 | 0.5370 | 0.0990 | -228.0565 | -227.0665 | -0.4886 | -0.5142 | 0.6549 |
|
| 83 |
+
| 2.6865 | 0.3908 | 17 | 2.2411 | -22.4130 | -22.5166 | 0.5283 | 0.1036 | -225.1658 | -224.1296 | -0.5152 | -0.5408 | 0.6460 |
|
| 84 |
+
| 2.6865 | 0.4138 | 18 | 2.2300 | -22.1594 | -22.2652 | 0.5261 | 0.1058 | -222.6522 | -221.5937 | -0.5400 | -0.5656 | 0.6382 |
|
| 85 |
+
| 2.6865 | 0.4368 | 19 | 2.2170 | -21.9205 | -22.0355 | 0.5304 | 0.1150 | -220.3547 | -219.2051 | -0.5657 | -0.5915 | 0.6308 |
|
| 86 |
+
| 2.3904 | 0.4598 | 20 | 2.2065 | -21.7054 | -21.8209 | 0.5283 | 0.1156 | -218.2092 | -217.0537 | -0.5920 | -0.6175 | 0.6241 |
|
| 87 |
+
| 2.3904 | 0.4828 | 21 | 2.1932 | -21.4871 | -21.6107 | 0.5261 | 0.1236 | -216.1072 | -214.8710 | -0.6189 | -0.6441 | 0.6172 |
|
| 88 |
+
| 2.3904 | 0.5057 | 22 | 2.1839 | -21.2899 | -21.4129 | 0.5196 | 0.1230 | -214.1287 | -212.8987 | -0.6445 | -0.6694 | 0.6109 |
|
| 89 |
+
| 2.3904 | 0.5287 | 23 | 2.1746 | -21.0873 | -21.2117 | 0.5261 | 0.1244 | -212.1172 | -210.8729 | -0.6688 | -0.6940 | 0.6045 |
|
| 90 |
+
| 2.3904 | 0.5517 | 24 | 2.1656 | -20.9136 | -21.0398 | 0.5239 | 0.1262 | -210.3979 | -209.1364 | -0.6938 | -0.7184 | 0.5989 |
|
| 91 |
+
| 2.3904 | 0.5747 | 25 | 2.1555 | -20.7191 | -20.8481 | 0.5283 | 0.1290 | -208.4814 | -207.1911 | -0.7120 | -0.7365 | 0.5926 |
|
| 92 |
+
| 2.3904 | 0.5977 | 26 | 2.1466 | -20.5485 | -20.6790 | 0.5283 | 0.1305 | -206.7897 | -205.4852 | -0.7301 | -0.7545 | 0.5872 |
|
| 93 |
+
| 2.3904 | 0.6207 | 27 | 2.1392 | -20.3722 | -20.5040 | 0.5370 | 0.1318 | -205.0401 | -203.7218 | -0.7476 | -0.7720 | 0.5816 |
|
| 94 |
+
| 2.3904 | 0.6437 | 28 | 2.1308 | -20.1853 | -20.3216 | 0.5326 | 0.1363 | -203.2164 | -201.8533 | -0.7575 | -0.7818 | 0.5756 |
|
| 95 |
+
| 2.3904 | 0.6667 | 29 | 2.1229 | -19.9946 | -20.1315 | 0.5283 | 0.1370 | -201.3155 | -199.9459 | -0.7683 | -0.7925 | 0.5695 |
|
| 96 |
+
| 2.3172 | 0.6897 | 30 | 2.1134 | -19.7893 | -19.9304 | 0.5261 | 0.1411 | -199.3041 | -197.8930 | -0.7735 | -0.7976 | 0.5630 |
|
| 97 |
+
| 2.3172 | 0.7126 | 31 | 2.1055 | -19.5960 | -19.7401 | 0.5283 | 0.1441 | -197.4013 | -195.9599 | -0.7735 | -0.7977 | 0.5569 |
|
| 98 |
+
| 2.3172 | 0.7356 | 32 | 2.0985 | -19.4016 | -19.5462 | 0.5217 | 0.1445 | -195.4615 | -194.0163 | -0.7817 | -0.8060 | 0.5508 |
|
| 99 |
+
| 2.3172 | 0.7586 | 33 | 2.0904 | -19.2117 | -19.3617 | 0.5239 | 0.1501 | -193.6172 | -192.1166 | -0.7785 | -0.8030 | 0.5447 |
|
| 100 |
+
| 2.3172 | 0.7816 | 34 | 2.0850 | -19.0381 | -19.1813 | 0.5239 | 0.1432 | -191.8132 | -190.3807 | -0.7758 | -0.8003 | 0.5392 |
|
| 101 |
+
| 2.3172 | 0.8046 | 35 | 2.0793 | -18.8988 | -19.0437 | 0.5174 | 0.1449 | -190.4374 | -188.9884 | -0.7715 | -0.7964 | 0.5346 |
|
| 102 |
+
| 2.3172 | 0.8276 | 36 | 2.0720 | -18.7545 | -18.8980 | 0.5196 | 0.1435 | -188.9801 | -187.5452 | -0.7701 | -0.7952 | 0.5299 |
|
| 103 |
+
| 2.3172 | 0.8506 | 37 | 2.0663 | -18.6567 | -18.8053 | 0.5261 | 0.1486 | -188.0533 | -186.5672 | -0.7679 | -0.7927 | 0.5266 |
|
| 104 |
+
| 2.3172 | 0.8736 | 38 | 2.0643 | -18.5627 | -18.7139 | 0.5239 | 0.1512 | -187.1391 | -185.6268 | -0.7631 | -0.7882 | 0.5235 |
|
| 105 |
+
| 2.3172 | 0.8966 | 39 | 2.0601 | -18.5100 | -18.6606 | 0.5283 | 0.1507 | -186.6065 | -185.0997 | -0.7609 | -0.7857 | 0.5217 |
|
| 106 |
+
| 2.1039 | 0.9195 | 40 | 2.0598 | -18.4610 | -18.6128 | 0.5283 | 0.1518 | -186.1283 | -184.6099 | -0.7611 | -0.7860 | 0.5201 |
|
| 107 |
+
| 2.1039 | 0.9425 | 41 | 2.0539 | -18.4232 | -18.5801 | 0.5261 | 0.1568 | -185.8007 | -184.2324 | -0.7540 | -0.7789 | 0.5190 |
|
| 108 |
+
| 2.1039 | 0.9655 | 42 | 2.0544 | -18.3969 | -18.5526 | 0.5283 | 0.1557 | -185.5258 | -183.9690 | -0.7525 | -0.7777 | 0.5181 |
|
| 109 |
+
| 2.1039 | 0.9885 | 43 | 2.0545 | -18.3931 | -18.5452 | 0.5261 | 0.1521 | -185.4521 | -183.9312 | -0.7551 | -0.7797 | 0.5180 |
|
| 110 |
+
|
| 111 |
+
|
| 112 |
+
### Framework versions
|
| 113 |
+
|
| 114 |
+
- Transformers 4.44.2
|
| 115 |
+
- Pytorch 2.3.1
|
| 116 |
+
- Datasets 2.21.0
|
| 117 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9885057471264368,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 2.3523660704146985,
|
| 5 |
+
"train_runtime": 5387.5537,
|
| 6 |
+
"train_samples": 5556,
|
| 7 |
+
"train_samples_per_second": 1.031,
|
| 8 |
+
"train_steps_per_second": 0.008
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.44.2"
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9885057471264368,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 2.3523660704146985,
|
| 5 |
+
"train_runtime": 5387.5537,
|
| 6 |
+
"train_samples": 5556,
|
| 7 |
+
"train_samples_per_second": 1.031,
|
| 8 |
+
"train_steps_per_second": 0.008
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,837 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9885057471264368,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 43,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.022988505747126436,
|
| 13 |
+
"eval_logits/chosen": -0.285895973443985,
|
| 14 |
+
"eval_logits/rejected": -0.2622124254703522,
|
| 15 |
+
"eval_logps/chosen": -265.5323791503906,
|
| 16 |
+
"eval_logps/rejected": -265.8489074707031,
|
| 17 |
+
"eval_loss": 2.506535530090332,
|
| 18 |
+
"eval_nll_loss": 0.7676451206207275,
|
| 19 |
+
"eval_rewards/accuracies": 0.5173913240432739,
|
| 20 |
+
"eval_rewards/chosen": -26.55323600769043,
|
| 21 |
+
"eval_rewards/margins": 0.03165607899427414,
|
| 22 |
+
"eval_rewards/rejected": -26.58489227294922,
|
| 23 |
+
"eval_runtime": 73.2699,
|
| 24 |
+
"eval_samples_per_second": 24.922,
|
| 25 |
+
"eval_steps_per_second": 1.57,
|
| 26 |
+
"step": 1
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.04597701149425287,
|
| 30 |
+
"eval_logits/chosen": -0.28692948818206787,
|
| 31 |
+
"eval_logits/rejected": -0.2633576989173889,
|
| 32 |
+
"eval_logps/chosen": -265.1800537109375,
|
| 33 |
+
"eval_logps/rejected": -265.50384521484375,
|
| 34 |
+
"eval_loss": 2.505967855453491,
|
| 35 |
+
"eval_nll_loss": 0.766638994216919,
|
| 36 |
+
"eval_rewards/accuracies": 0.52173912525177,
|
| 37 |
+
"eval_rewards/chosen": -26.51800537109375,
|
| 38 |
+
"eval_rewards/margins": 0.03237998113036156,
|
| 39 |
+
"eval_rewards/rejected": -26.550386428833008,
|
| 40 |
+
"eval_runtime": 73.1616,
|
| 41 |
+
"eval_samples_per_second": 24.958,
|
| 42 |
+
"eval_steps_per_second": 1.572,
|
| 43 |
+
"step": 2
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.06896551724137931,
|
| 47 |
+
"eval_logits/chosen": -0.28926920890808105,
|
| 48 |
+
"eval_logits/rejected": -0.2657304108142853,
|
| 49 |
+
"eval_logps/chosen": -265.0088195800781,
|
| 50 |
+
"eval_logps/rejected": -265.2777404785156,
|
| 51 |
+
"eval_loss": 2.505052328109741,
|
| 52 |
+
"eval_nll_loss": 0.7661022543907166,
|
| 53 |
+
"eval_rewards/accuracies": 0.52173912525177,
|
| 54 |
+
"eval_rewards/chosen": -26.500883102416992,
|
| 55 |
+
"eval_rewards/margins": 0.02689189836382866,
|
| 56 |
+
"eval_rewards/rejected": -26.527772903442383,
|
| 57 |
+
"eval_runtime": 73.4564,
|
| 58 |
+
"eval_samples_per_second": 24.858,
|
| 59 |
+
"eval_steps_per_second": 1.566,
|
| 60 |
+
"step": 3
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.09195402298850575,
|
| 64 |
+
"eval_logits/chosen": -0.29259422421455383,
|
| 65 |
+
"eval_logits/rejected": -0.26898470520973206,
|
| 66 |
+
"eval_logps/chosen": -263.95184326171875,
|
| 67 |
+
"eval_logps/rejected": -264.3146667480469,
|
| 68 |
+
"eval_loss": 2.498246669769287,
|
| 69 |
+
"eval_nll_loss": 0.7631996870040894,
|
| 70 |
+
"eval_rewards/accuracies": 0.5239130258560181,
|
| 71 |
+
"eval_rewards/chosen": -26.395187377929688,
|
| 72 |
+
"eval_rewards/margins": 0.03628147765994072,
|
| 73 |
+
"eval_rewards/rejected": -26.43147087097168,
|
| 74 |
+
"eval_runtime": 73.5575,
|
| 75 |
+
"eval_samples_per_second": 24.824,
|
| 76 |
+
"eval_steps_per_second": 1.563,
|
| 77 |
+
"step": 4
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.11494252873563218,
|
| 81 |
+
"eval_logits/chosen": -0.29848381876945496,
|
| 82 |
+
"eval_logits/rejected": -0.27501967549324036,
|
| 83 |
+
"eval_logps/chosen": -262.6512145996094,
|
| 84 |
+
"eval_logps/rejected": -263.0111999511719,
|
| 85 |
+
"eval_loss": 2.489372968673706,
|
| 86 |
+
"eval_nll_loss": 0.7594311237335205,
|
| 87 |
+
"eval_rewards/accuracies": 0.52173912525177,
|
| 88 |
+
"eval_rewards/chosen": -26.26512336730957,
|
| 89 |
+
"eval_rewards/margins": 0.035997405648231506,
|
| 90 |
+
"eval_rewards/rejected": -26.30112075805664,
|
| 91 |
+
"eval_runtime": 73.7594,
|
| 92 |
+
"eval_samples_per_second": 24.756,
|
| 93 |
+
"eval_steps_per_second": 1.559,
|
| 94 |
+
"step": 5
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13793103448275862,
|
| 98 |
+
"eval_logits/chosen": -0.30859696865081787,
|
| 99 |
+
"eval_logits/rejected": -0.2858428359031677,
|
| 100 |
+
"eval_logps/chosen": -259.449951171875,
|
| 101 |
+
"eval_logps/rejected": -259.8551330566406,
|
| 102 |
+
"eval_loss": 2.4688832759857178,
|
| 103 |
+
"eval_nll_loss": 0.7501848340034485,
|
| 104 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 105 |
+
"eval_rewards/chosen": -25.94499397277832,
|
| 106 |
+
"eval_rewards/margins": 0.040517814457416534,
|
| 107 |
+
"eval_rewards/rejected": -25.98551368713379,
|
| 108 |
+
"eval_runtime": 73.5054,
|
| 109 |
+
"eval_samples_per_second": 24.842,
|
| 110 |
+
"eval_steps_per_second": 1.565,
|
| 111 |
+
"step": 6
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.16091954022988506,
|
| 115 |
+
"eval_logits/chosen": -0.3201945424079895,
|
| 116 |
+
"eval_logits/rejected": -0.297221302986145,
|
| 117 |
+
"eval_logps/chosen": -257.0843200683594,
|
| 118 |
+
"eval_logps/rejected": -257.527099609375,
|
| 119 |
+
"eval_loss": 2.4511067867279053,
|
| 120 |
+
"eval_nll_loss": 0.7433211207389832,
|
| 121 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 122 |
+
"eval_rewards/chosen": -25.708433151245117,
|
| 123 |
+
"eval_rewards/margins": 0.04427630454301834,
|
| 124 |
+
"eval_rewards/rejected": -25.752708435058594,
|
| 125 |
+
"eval_runtime": 73.716,
|
| 126 |
+
"eval_samples_per_second": 24.771,
|
| 127 |
+
"eval_steps_per_second": 1.56,
|
| 128 |
+
"step": 7
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1839080459770115,
|
| 132 |
+
"eval_logits/chosen": -0.348645955324173,
|
| 133 |
+
"eval_logits/rejected": -0.3254188001155853,
|
| 134 |
+
"eval_logps/chosen": -252.2147216796875,
|
| 135 |
+
"eval_logps/rejected": -252.7242431640625,
|
| 136 |
+
"eval_loss": 2.4179530143737793,
|
| 137 |
+
"eval_nll_loss": 0.7291316390037537,
|
| 138 |
+
"eval_rewards/accuracies": 0.532608687877655,
|
| 139 |
+
"eval_rewards/chosen": -25.22147560119629,
|
| 140 |
+
"eval_rewards/margins": 0.05095084756612778,
|
| 141 |
+
"eval_rewards/rejected": -25.27242660522461,
|
| 142 |
+
"eval_runtime": 73.8275,
|
| 143 |
+
"eval_samples_per_second": 24.733,
|
| 144 |
+
"eval_steps_per_second": 1.558,
|
| 145 |
+
"step": 8
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.20689655172413793,
|
| 149 |
+
"eval_logits/chosen": -0.37005820870399475,
|
| 150 |
+
"eval_logits/rejected": -0.3462548851966858,
|
| 151 |
+
"eval_logps/chosen": -248.8451385498047,
|
| 152 |
+
"eval_logps/rejected": -249.3928985595703,
|
| 153 |
+
"eval_loss": 2.3951992988586426,
|
| 154 |
+
"eval_nll_loss": 0.7191779017448425,
|
| 155 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 156 |
+
"eval_rewards/chosen": -24.8845157623291,
|
| 157 |
+
"eval_rewards/margins": 0.054776255041360855,
|
| 158 |
+
"eval_rewards/rejected": -24.939287185668945,
|
| 159 |
+
"eval_runtime": 73.7047,
|
| 160 |
+
"eval_samples_per_second": 24.775,
|
| 161 |
+
"eval_steps_per_second": 1.56,
|
| 162 |
+
"step": 9
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.22988505747126436,
|
| 166 |
+
"grad_norm": 55.518348693847656,
|
| 167 |
+
"learning_rate": 8.684210526315789e-07,
|
| 168 |
+
"logits/chosen": -0.35856884717941284,
|
| 169 |
+
"logits/rejected": -0.3261299431324005,
|
| 170 |
+
"logps/chosen": -264.810302734375,
|
| 171 |
+
"logps/rejected": -258.8919982910156,
|
| 172 |
+
"loss": 2.6865,
|
| 173 |
+
"nll_loss": 0.7651573419570923,
|
| 174 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 175 |
+
"rewards/chosen": -26.481029510498047,
|
| 176 |
+
"rewards/margins": -0.5918328166007996,
|
| 177 |
+
"rewards/rejected": -25.889196395874023,
|
| 178 |
+
"step": 10
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.22988505747126436,
|
| 182 |
+
"eval_logits/chosen": -0.384502112865448,
|
| 183 |
+
"eval_logits/rejected": -0.3603852689266205,
|
| 184 |
+
"eval_logps/chosen": -246.21482849121094,
|
| 185 |
+
"eval_logps/rejected": -246.78208923339844,
|
| 186 |
+
"eval_loss": 2.376126766204834,
|
| 187 |
+
"eval_nll_loss": 0.7115476727485657,
|
| 188 |
+
"eval_rewards/accuracies": 0.5347825884819031,
|
| 189 |
+
"eval_rewards/chosen": -24.621484756469727,
|
| 190 |
+
"eval_rewards/margins": 0.05672362819314003,
|
| 191 |
+
"eval_rewards/rejected": -24.678205490112305,
|
| 192 |
+
"eval_runtime": 73.7798,
|
| 193 |
+
"eval_samples_per_second": 24.749,
|
| 194 |
+
"eval_steps_per_second": 1.559,
|
| 195 |
+
"step": 10
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.25287356321839083,
|
| 199 |
+
"eval_logits/chosen": -0.397601842880249,
|
| 200 |
+
"eval_logits/rejected": -0.3731386959552765,
|
| 201 |
+
"eval_logps/chosen": -244.02699279785156,
|
| 202 |
+
"eval_logps/rejected": -244.7050323486328,
|
| 203 |
+
"eval_loss": 2.3608767986297607,
|
| 204 |
+
"eval_nll_loss": 0.7050958275794983,
|
| 205 |
+
"eval_rewards/accuracies": 0.539130449295044,
|
| 206 |
+
"eval_rewards/chosen": -24.402700424194336,
|
| 207 |
+
"eval_rewards/margins": 0.06780331581830978,
|
| 208 |
+
"eval_rewards/rejected": -24.470500946044922,
|
| 209 |
+
"eval_runtime": 73.0824,
|
| 210 |
+
"eval_samples_per_second": 24.985,
|
| 211 |
+
"eval_steps_per_second": 1.574,
|
| 212 |
+
"step": 11
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.27586206896551724,
|
| 216 |
+
"eval_logits/chosen": -0.4218127429485321,
|
| 217 |
+
"eval_logits/rejected": -0.3970121443271637,
|
| 218 |
+
"eval_logps/chosen": -240.5603790283203,
|
| 219 |
+
"eval_logps/rejected": -241.30628967285156,
|
| 220 |
+
"eval_loss": 2.3367197513580322,
|
| 221 |
+
"eval_nll_loss": 0.6951096057891846,
|
| 222 |
+
"eval_rewards/accuracies": 0.5347825884819031,
|
| 223 |
+
"eval_rewards/chosen": -24.05603790283203,
|
| 224 |
+
"eval_rewards/margins": 0.074591264128685,
|
| 225 |
+
"eval_rewards/rejected": -24.130634307861328,
|
| 226 |
+
"eval_runtime": 73.2125,
|
| 227 |
+
"eval_samples_per_second": 24.941,
|
| 228 |
+
"eval_steps_per_second": 1.571,
|
| 229 |
+
"step": 12
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.2988505747126437,
|
| 233 |
+
"eval_logits/chosen": -0.4434413015842438,
|
| 234 |
+
"eval_logits/rejected": -0.4179251492023468,
|
| 235 |
+
"eval_logps/chosen": -236.7858123779297,
|
| 236 |
+
"eval_logps/rejected": -237.64541625976562,
|
| 237 |
+
"eval_loss": 2.310944080352783,
|
| 238 |
+
"eval_nll_loss": 0.6840075850486755,
|
| 239 |
+
"eval_rewards/accuracies": 0.530434787273407,
|
| 240 |
+
"eval_rewards/chosen": -23.6785831451416,
|
| 241 |
+
"eval_rewards/margins": 0.08595678210258484,
|
| 242 |
+
"eval_rewards/rejected": -23.764541625976562,
|
| 243 |
+
"eval_runtime": 73.2236,
|
| 244 |
+
"eval_samples_per_second": 24.937,
|
| 245 |
+
"eval_steps_per_second": 1.571,
|
| 246 |
+
"step": 13
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.3218390804597701,
|
| 250 |
+
"eval_logits/chosen": -0.4679478406906128,
|
| 251 |
+
"eval_logits/rejected": -0.4422786235809326,
|
| 252 |
+
"eval_logps/chosen": -233.17481994628906,
|
| 253 |
+
"eval_logps/rejected": -234.0310821533203,
|
| 254 |
+
"eval_loss": 2.290565252304077,
|
| 255 |
+
"eval_nll_loss": 0.6733331680297852,
|
| 256 |
+
"eval_rewards/accuracies": 0.5347825884819031,
|
| 257 |
+
"eval_rewards/chosen": -23.317480087280273,
|
| 258 |
+
"eval_rewards/margins": 0.08562804758548737,
|
| 259 |
+
"eval_rewards/rejected": -23.40311050415039,
|
| 260 |
+
"eval_runtime": 73.3905,
|
| 261 |
+
"eval_samples_per_second": 24.881,
|
| 262 |
+
"eval_steps_per_second": 1.567,
|
| 263 |
+
"step": 14
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.3448275862068966,
|
| 267 |
+
"eval_logits/chosen": -0.49170100688934326,
|
| 268 |
+
"eval_logits/rejected": -0.4659886956214905,
|
| 269 |
+
"eval_logps/chosen": -229.94561767578125,
|
| 270 |
+
"eval_logps/rejected": -230.9332275390625,
|
| 271 |
+
"eval_loss": 2.272915840148926,
|
| 272 |
+
"eval_nll_loss": 0.663709819316864,
|
| 273 |
+
"eval_rewards/accuracies": 0.5347825884819031,
|
| 274 |
+
"eval_rewards/chosen": -22.99456024169922,
|
| 275 |
+
"eval_rewards/margins": 0.09876058995723724,
|
| 276 |
+
"eval_rewards/rejected": -23.093320846557617,
|
| 277 |
+
"eval_runtime": 73.5456,
|
| 278 |
+
"eval_samples_per_second": 24.828,
|
| 279 |
+
"eval_steps_per_second": 1.564,
|
| 280 |
+
"step": 15
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.367816091954023,
|
| 284 |
+
"eval_logits/chosen": -0.5142260789871216,
|
| 285 |
+
"eval_logits/rejected": -0.4886496365070343,
|
| 286 |
+
"eval_logps/chosen": -227.06649780273438,
|
| 287 |
+
"eval_logps/rejected": -228.05648803710938,
|
| 288 |
+
"eval_loss": 2.257603406906128,
|
| 289 |
+
"eval_nll_loss": 0.6548909544944763,
|
| 290 |
+
"eval_rewards/accuracies": 0.5369565486907959,
|
| 291 |
+
"eval_rewards/chosen": -22.70665168762207,
|
| 292 |
+
"eval_rewards/margins": 0.09899646788835526,
|
| 293 |
+
"eval_rewards/rejected": -22.805648803710938,
|
| 294 |
+
"eval_runtime": 73.494,
|
| 295 |
+
"eval_samples_per_second": 24.846,
|
| 296 |
+
"eval_steps_per_second": 1.565,
|
| 297 |
+
"step": 16
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.39080459770114945,
|
| 301 |
+
"eval_logits/chosen": -0.5408182144165039,
|
| 302 |
+
"eval_logits/rejected": -0.5151581764221191,
|
| 303 |
+
"eval_logps/chosen": -224.1295928955078,
|
| 304 |
+
"eval_logps/rejected": -225.16580200195312,
|
| 305 |
+
"eval_loss": 2.241145133972168,
|
| 306 |
+
"eval_nll_loss": 0.6459768414497375,
|
| 307 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 308 |
+
"eval_rewards/chosen": -22.4129581451416,
|
| 309 |
+
"eval_rewards/margins": 0.10362222790718079,
|
| 310 |
+
"eval_rewards/rejected": -22.516578674316406,
|
| 311 |
+
"eval_runtime": 73.7057,
|
| 312 |
+
"eval_samples_per_second": 24.774,
|
| 313 |
+
"eval_steps_per_second": 1.56,
|
| 314 |
+
"step": 17
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.41379310344827586,
|
| 318 |
+
"eval_logits/chosen": -0.5656267404556274,
|
| 319 |
+
"eval_logits/rejected": -0.5400449633598328,
|
| 320 |
+
"eval_logps/chosen": -221.59368896484375,
|
| 321 |
+
"eval_logps/rejected": -222.6521759033203,
|
| 322 |
+
"eval_loss": 2.230027198791504,
|
| 323 |
+
"eval_nll_loss": 0.6381992697715759,
|
| 324 |
+
"eval_rewards/accuracies": 0.5260869860649109,
|
| 325 |
+
"eval_rewards/chosen": -22.15936851501465,
|
| 326 |
+
"eval_rewards/margins": 0.10584992170333862,
|
| 327 |
+
"eval_rewards/rejected": -22.265216827392578,
|
| 328 |
+
"eval_runtime": 73.8674,
|
| 329 |
+
"eval_samples_per_second": 24.72,
|
| 330 |
+
"eval_steps_per_second": 1.557,
|
| 331 |
+
"step": 18
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.4367816091954023,
|
| 335 |
+
"eval_logits/chosen": -0.5914514064788818,
|
| 336 |
+
"eval_logits/rejected": -0.565658688545227,
|
| 337 |
+
"eval_logps/chosen": -219.20506286621094,
|
| 338 |
+
"eval_logps/rejected": -220.354736328125,
|
| 339 |
+
"eval_loss": 2.2169623374938965,
|
| 340 |
+
"eval_nll_loss": 0.6308388113975525,
|
| 341 |
+
"eval_rewards/accuracies": 0.530434787273407,
|
| 342 |
+
"eval_rewards/chosen": -21.92050552368164,
|
| 343 |
+
"eval_rewards/margins": 0.11496546864509583,
|
| 344 |
+
"eval_rewards/rejected": -22.035470962524414,
|
| 345 |
+
"eval_runtime": 73.7719,
|
| 346 |
+
"eval_samples_per_second": 24.752,
|
| 347 |
+
"eval_steps_per_second": 1.559,
|
| 348 |
+
"step": 19
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.45977011494252873,
|
| 352 |
+
"grad_norm": 51.48088455200195,
|
| 353 |
+
"learning_rate": 6.052631578947368e-07,
|
| 354 |
+
"logits/chosen": -0.48232191801071167,
|
| 355 |
+
"logits/rejected": -0.4643561840057373,
|
| 356 |
+
"logps/chosen": -226.7048797607422,
|
| 357 |
+
"logps/rejected": -228.0491943359375,
|
| 358 |
+
"loss": 2.3904,
|
| 359 |
+
"nll_loss": 0.6598069667816162,
|
| 360 |
+
"rewards/accuracies": 0.546875,
|
| 361 |
+
"rewards/chosen": -22.670488357543945,
|
| 362 |
+
"rewards/margins": 0.13443148136138916,
|
| 363 |
+
"rewards/rejected": -22.804920196533203,
|
| 364 |
+
"step": 20
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.45977011494252873,
|
| 368 |
+
"eval_logits/chosen": -0.617470383644104,
|
| 369 |
+
"eval_logits/rejected": -0.5920071601867676,
|
| 370 |
+
"eval_logps/chosen": -217.05372619628906,
|
| 371 |
+
"eval_logps/rejected": -218.20924377441406,
|
| 372 |
+
"eval_loss": 2.20650315284729,
|
| 373 |
+
"eval_nll_loss": 0.624081552028656,
|
| 374 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 375 |
+
"eval_rewards/chosen": -21.705373764038086,
|
| 376 |
+
"eval_rewards/margins": 0.11555319279432297,
|
| 377 |
+
"eval_rewards/rejected": -21.8209285736084,
|
| 378 |
+
"eval_runtime": 73.6034,
|
| 379 |
+
"eval_samples_per_second": 24.809,
|
| 380 |
+
"eval_steps_per_second": 1.562,
|
| 381 |
+
"step": 20
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.4827586206896552,
|
| 385 |
+
"eval_logits/chosen": -0.6441444754600525,
|
| 386 |
+
"eval_logits/rejected": -0.6189336180686951,
|
| 387 |
+
"eval_logps/chosen": -214.8709716796875,
|
| 388 |
+
"eval_logps/rejected": -216.1072235107422,
|
| 389 |
+
"eval_loss": 2.193157911300659,
|
| 390 |
+
"eval_nll_loss": 0.6171812415122986,
|
| 391 |
+
"eval_rewards/accuracies": 0.5260869860649109,
|
| 392 |
+
"eval_rewards/chosen": -21.487096786499023,
|
| 393 |
+
"eval_rewards/margins": 0.12362580001354218,
|
| 394 |
+
"eval_rewards/rejected": -21.6107234954834,
|
| 395 |
+
"eval_runtime": 73.1268,
|
| 396 |
+
"eval_samples_per_second": 24.97,
|
| 397 |
+
"eval_steps_per_second": 1.573,
|
| 398 |
+
"step": 21
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.5057471264367817,
|
| 402 |
+
"eval_logits/chosen": -0.6693909168243408,
|
| 403 |
+
"eval_logits/rejected": -0.6444550156593323,
|
| 404 |
+
"eval_logps/chosen": -212.89871215820312,
|
| 405 |
+
"eval_logps/rejected": -214.12872314453125,
|
| 406 |
+
"eval_loss": 2.1838579177856445,
|
| 407 |
+
"eval_nll_loss": 0.6109142899513245,
|
| 408 |
+
"eval_rewards/accuracies": 0.519565224647522,
|
| 409 |
+
"eval_rewards/chosen": -21.289873123168945,
|
| 410 |
+
"eval_rewards/margins": 0.1229993924498558,
|
| 411 |
+
"eval_rewards/rejected": -21.412874221801758,
|
| 412 |
+
"eval_runtime": 73.3336,
|
| 413 |
+
"eval_samples_per_second": 24.9,
|
| 414 |
+
"eval_steps_per_second": 1.568,
|
| 415 |
+
"step": 22
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5287356321839081,
|
| 419 |
+
"eval_logits/chosen": -0.6940123438835144,
|
| 420 |
+
"eval_logits/rejected": -0.6688118577003479,
|
| 421 |
+
"eval_logps/chosen": -210.87289428710938,
|
| 422 |
+
"eval_logps/rejected": -212.1172332763672,
|
| 423 |
+
"eval_loss": 2.17464280128479,
|
| 424 |
+
"eval_nll_loss": 0.6044757962226868,
|
| 425 |
+
"eval_rewards/accuracies": 0.5260869860649109,
|
| 426 |
+
"eval_rewards/chosen": -21.087289810180664,
|
| 427 |
+
"eval_rewards/margins": 0.12443248927593231,
|
| 428 |
+
"eval_rewards/rejected": -21.21172332763672,
|
| 429 |
+
"eval_runtime": 73.7107,
|
| 430 |
+
"eval_samples_per_second": 24.773,
|
| 431 |
+
"eval_steps_per_second": 1.56,
|
| 432 |
+
"step": 23
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.5517241379310345,
|
| 436 |
+
"eval_logits/chosen": -0.7184363603591919,
|
| 437 |
+
"eval_logits/rejected": -0.6937569379806519,
|
| 438 |
+
"eval_logps/chosen": -209.13641357421875,
|
| 439 |
+
"eval_logps/rejected": -210.39794921875,
|
| 440 |
+
"eval_loss": 2.1655774116516113,
|
| 441 |
+
"eval_nll_loss": 0.5988763570785522,
|
| 442 |
+
"eval_rewards/accuracies": 0.5239130258560181,
|
| 443 |
+
"eval_rewards/chosen": -20.91364097595215,
|
| 444 |
+
"eval_rewards/margins": 0.12615376710891724,
|
| 445 |
+
"eval_rewards/rejected": -21.039793014526367,
|
| 446 |
+
"eval_runtime": 73.2196,
|
| 447 |
+
"eval_samples_per_second": 24.939,
|
| 448 |
+
"eval_steps_per_second": 1.571,
|
| 449 |
+
"step": 24
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.5747126436781609,
|
| 453 |
+
"eval_logits/chosen": -0.7364875078201294,
|
| 454 |
+
"eval_logits/rejected": -0.711971640586853,
|
| 455 |
+
"eval_logps/chosen": -207.19107055664062,
|
| 456 |
+
"eval_logps/rejected": -208.48138427734375,
|
| 457 |
+
"eval_loss": 2.155548572540283,
|
| 458 |
+
"eval_nll_loss": 0.5926215052604675,
|
| 459 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 460 |
+
"eval_rewards/chosen": -20.719106674194336,
|
| 461 |
+
"eval_rewards/margins": 0.12903204560279846,
|
| 462 |
+
"eval_rewards/rejected": -20.8481388092041,
|
| 463 |
+
"eval_runtime": 73.1876,
|
| 464 |
+
"eval_samples_per_second": 24.95,
|
| 465 |
+
"eval_steps_per_second": 1.571,
|
| 466 |
+
"step": 25
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.5977011494252874,
|
| 470 |
+
"eval_logits/chosen": -0.7545364499092102,
|
| 471 |
+
"eval_logits/rejected": -0.730129599571228,
|
| 472 |
+
"eval_logps/chosen": -205.48521423339844,
|
| 473 |
+
"eval_logps/rejected": -206.7897186279297,
|
| 474 |
+
"eval_loss": 2.1465742588043213,
|
| 475 |
+
"eval_nll_loss": 0.5872200727462769,
|
| 476 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 477 |
+
"eval_rewards/chosen": -20.548521041870117,
|
| 478 |
+
"eval_rewards/margins": 0.13045117259025574,
|
| 479 |
+
"eval_rewards/rejected": -20.678974151611328,
|
| 480 |
+
"eval_runtime": 73.5262,
|
| 481 |
+
"eval_samples_per_second": 24.835,
|
| 482 |
+
"eval_steps_per_second": 1.564,
|
| 483 |
+
"step": 26
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.6206896551724138,
|
| 487 |
+
"eval_logits/chosen": -0.7720378041267395,
|
| 488 |
+
"eval_logits/rejected": -0.7476205825805664,
|
| 489 |
+
"eval_logps/chosen": -203.7217559814453,
|
| 490 |
+
"eval_logps/rejected": -205.04006958007812,
|
| 491 |
+
"eval_loss": 2.139249801635742,
|
| 492 |
+
"eval_nll_loss": 0.5815550684928894,
|
| 493 |
+
"eval_rewards/accuracies": 0.5369565486907959,
|
| 494 |
+
"eval_rewards/chosen": -20.37217903137207,
|
| 495 |
+
"eval_rewards/margins": 0.13182921707630157,
|
| 496 |
+
"eval_rewards/rejected": -20.504005432128906,
|
| 497 |
+
"eval_runtime": 73.5829,
|
| 498 |
+
"eval_samples_per_second": 24.816,
|
| 499 |
+
"eval_steps_per_second": 1.563,
|
| 500 |
+
"step": 27
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6436781609195402,
|
| 504 |
+
"eval_logits/chosen": -0.781804621219635,
|
| 505 |
+
"eval_logits/rejected": -0.7575309872627258,
|
| 506 |
+
"eval_logps/chosen": -201.85330200195312,
|
| 507 |
+
"eval_logps/rejected": -203.2164306640625,
|
| 508 |
+
"eval_loss": 2.1307995319366455,
|
| 509 |
+
"eval_nll_loss": 0.5756080150604248,
|
| 510 |
+
"eval_rewards/accuracies": 0.532608687877655,
|
| 511 |
+
"eval_rewards/chosen": -20.18532943725586,
|
| 512 |
+
"eval_rewards/margins": 0.13631057739257812,
|
| 513 |
+
"eval_rewards/rejected": -20.321643829345703,
|
| 514 |
+
"eval_runtime": 73.6844,
|
| 515 |
+
"eval_samples_per_second": 24.781,
|
| 516 |
+
"eval_steps_per_second": 1.561,
|
| 517 |
+
"step": 28
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.6666666666666666,
|
| 521 |
+
"eval_logits/chosen": -0.7925211787223816,
|
| 522 |
+
"eval_logits/rejected": -0.768252432346344,
|
| 523 |
+
"eval_logps/chosen": -199.9458770751953,
|
| 524 |
+
"eval_logps/rejected": -201.3154754638672,
|
| 525 |
+
"eval_loss": 2.1228978633880615,
|
| 526 |
+
"eval_nll_loss": 0.5694720149040222,
|
| 527 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 528 |
+
"eval_rewards/chosen": -19.994586944580078,
|
| 529 |
+
"eval_rewards/margins": 0.13696083426475525,
|
| 530 |
+
"eval_rewards/rejected": -20.131547927856445,
|
| 531 |
+
"eval_runtime": 73.7355,
|
| 532 |
+
"eval_samples_per_second": 24.764,
|
| 533 |
+
"eval_steps_per_second": 1.56,
|
| 534 |
+
"step": 29
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6896551724137931,
|
| 538 |
+
"grad_norm": 55.80259323120117,
|
| 539 |
+
"learning_rate": 3.4210526315789473e-07,
|
| 540 |
+
"logits/chosen": -0.6812049150466919,
|
| 541 |
+
"logits/rejected": -0.6623071432113647,
|
| 542 |
+
"logps/chosen": -199.8437042236328,
|
| 543 |
+
"logps/rejected": -201.27694702148438,
|
| 544 |
+
"loss": 2.3172,
|
| 545 |
+
"nll_loss": 0.5909140706062317,
|
| 546 |
+
"rewards/accuracies": 0.53125,
|
| 547 |
+
"rewards/chosen": -19.984371185302734,
|
| 548 |
+
"rewards/margins": 0.14332275092601776,
|
| 549 |
+
"rewards/rejected": -20.127695083618164,
|
| 550 |
+
"step": 30
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6896551724137931,
|
| 554 |
+
"eval_logits/chosen": -0.7975767254829407,
|
| 555 |
+
"eval_logits/rejected": -0.7734904885292053,
|
| 556 |
+
"eval_logps/chosen": -197.8929901123047,
|
| 557 |
+
"eval_logps/rejected": -199.30410766601562,
|
| 558 |
+
"eval_loss": 2.113354206085205,
|
| 559 |
+
"eval_nll_loss": 0.5630350708961487,
|
| 560 |
+
"eval_rewards/accuracies": 0.5260869860649109,
|
| 561 |
+
"eval_rewards/chosen": -19.78929901123047,
|
| 562 |
+
"eval_rewards/margins": 0.1411115825176239,
|
| 563 |
+
"eval_rewards/rejected": -19.93041229248047,
|
| 564 |
+
"eval_runtime": 73.6357,
|
| 565 |
+
"eval_samples_per_second": 24.798,
|
| 566 |
+
"eval_steps_per_second": 1.562,
|
| 567 |
+
"step": 30
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.7126436781609196,
|
| 571 |
+
"eval_logits/chosen": -0.7977136969566345,
|
| 572 |
+
"eval_logits/rejected": -0.7735068202018738,
|
| 573 |
+
"eval_logps/chosen": -195.95989990234375,
|
| 574 |
+
"eval_logps/rejected": -197.4013214111328,
|
| 575 |
+
"eval_loss": 2.1055009365081787,
|
| 576 |
+
"eval_nll_loss": 0.5569384098052979,
|
| 577 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 578 |
+
"eval_rewards/chosen": -19.595989227294922,
|
| 579 |
+
"eval_rewards/margins": 0.1441420167684555,
|
| 580 |
+
"eval_rewards/rejected": -19.74013328552246,
|
| 581 |
+
"eval_runtime": 73.0556,
|
| 582 |
+
"eval_samples_per_second": 24.995,
|
| 583 |
+
"eval_steps_per_second": 1.574,
|
| 584 |
+
"step": 31
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.735632183908046,
|
| 588 |
+
"eval_logits/chosen": -0.80599045753479,
|
| 589 |
+
"eval_logits/rejected": -0.7817136645317078,
|
| 590 |
+
"eval_logps/chosen": -194.0162811279297,
|
| 591 |
+
"eval_logps/rejected": -195.46153259277344,
|
| 592 |
+
"eval_loss": 2.0985281467437744,
|
| 593 |
+
"eval_nll_loss": 0.5507530570030212,
|
| 594 |
+
"eval_rewards/accuracies": 0.52173912525177,
|
| 595 |
+
"eval_rewards/chosen": -19.401628494262695,
|
| 596 |
+
"eval_rewards/margins": 0.14452561736106873,
|
| 597 |
+
"eval_rewards/rejected": -19.546154022216797,
|
| 598 |
+
"eval_runtime": 73.1881,
|
| 599 |
+
"eval_samples_per_second": 24.949,
|
| 600 |
+
"eval_steps_per_second": 1.571,
|
| 601 |
+
"step": 32
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.7586206896551724,
|
| 605 |
+
"eval_logits/chosen": -0.8030232787132263,
|
| 606 |
+
"eval_logits/rejected": -0.7785286903381348,
|
| 607 |
+
"eval_logps/chosen": -192.11659240722656,
|
| 608 |
+
"eval_logps/rejected": -193.61715698242188,
|
| 609 |
+
"eval_loss": 2.0903804302215576,
|
| 610 |
+
"eval_nll_loss": 0.5446676015853882,
|
| 611 |
+
"eval_rewards/accuracies": 0.5239130258560181,
|
| 612 |
+
"eval_rewards/chosen": -19.211658477783203,
|
| 613 |
+
"eval_rewards/margins": 0.1500559002161026,
|
| 614 |
+
"eval_rewards/rejected": -19.36171531677246,
|
| 615 |
+
"eval_runtime": 73.4088,
|
| 616 |
+
"eval_samples_per_second": 24.874,
|
| 617 |
+
"eval_steps_per_second": 1.567,
|
| 618 |
+
"step": 33
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.7816091954022989,
|
| 622 |
+
"eval_logits/chosen": -0.8003183603286743,
|
| 623 |
+
"eval_logits/rejected": -0.7758002281188965,
|
| 624 |
+
"eval_logps/chosen": -190.38067626953125,
|
| 625 |
+
"eval_logps/rejected": -191.8131561279297,
|
| 626 |
+
"eval_loss": 2.08504056930542,
|
| 627 |
+
"eval_nll_loss": 0.539174497127533,
|
| 628 |
+
"eval_rewards/accuracies": 0.5239130258560181,
|
| 629 |
+
"eval_rewards/chosen": -19.038066864013672,
|
| 630 |
+
"eval_rewards/margins": 0.1432473063468933,
|
| 631 |
+
"eval_rewards/rejected": -19.18131446838379,
|
| 632 |
+
"eval_runtime": 73.4902,
|
| 633 |
+
"eval_samples_per_second": 24.847,
|
| 634 |
+
"eval_steps_per_second": 1.565,
|
| 635 |
+
"step": 34
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.8045977011494253,
|
| 639 |
+
"eval_logits/chosen": -0.796375036239624,
|
| 640 |
+
"eval_logits/rejected": -0.7714610695838928,
|
| 641 |
+
"eval_logps/chosen": -188.9884033203125,
|
| 642 |
+
"eval_logps/rejected": -190.43736267089844,
|
| 643 |
+
"eval_loss": 2.0792500972747803,
|
| 644 |
+
"eval_nll_loss": 0.5345708131790161,
|
| 645 |
+
"eval_rewards/accuracies": 0.5173913240432739,
|
| 646 |
+
"eval_rewards/chosen": -18.898839950561523,
|
| 647 |
+
"eval_rewards/margins": 0.1448965221643448,
|
| 648 |
+
"eval_rewards/rejected": -19.043737411499023,
|
| 649 |
+
"eval_runtime": 73.2997,
|
| 650 |
+
"eval_samples_per_second": 24.911,
|
| 651 |
+
"eval_steps_per_second": 1.569,
|
| 652 |
+
"step": 35
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.8275862068965517,
|
| 656 |
+
"eval_logits/chosen": -0.7951973080635071,
|
| 657 |
+
"eval_logits/rejected": -0.7701032757759094,
|
| 658 |
+
"eval_logps/chosen": -187.54518127441406,
|
| 659 |
+
"eval_logps/rejected": -188.98013305664062,
|
| 660 |
+
"eval_loss": 2.0720129013061523,
|
| 661 |
+
"eval_nll_loss": 0.5298618078231812,
|
| 662 |
+
"eval_rewards/accuracies": 0.519565224647522,
|
| 663 |
+
"eval_rewards/chosen": -18.754518508911133,
|
| 664 |
+
"eval_rewards/margins": 0.14349476993083954,
|
| 665 |
+
"eval_rewards/rejected": -18.898012161254883,
|
| 666 |
+
"eval_runtime": 73.4171,
|
| 667 |
+
"eval_samples_per_second": 24.872,
|
| 668 |
+
"eval_steps_per_second": 1.566,
|
| 669 |
+
"step": 36
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.8505747126436781,
|
| 673 |
+
"eval_logits/chosen": -0.7926805019378662,
|
| 674 |
+
"eval_logits/rejected": -0.7679208517074585,
|
| 675 |
+
"eval_logps/chosen": -186.56715393066406,
|
| 676 |
+
"eval_logps/rejected": -188.0532684326172,
|
| 677 |
+
"eval_loss": 2.0663270950317383,
|
| 678 |
+
"eval_nll_loss": 0.526580810546875,
|
| 679 |
+
"eval_rewards/accuracies": 0.5260869860649109,
|
| 680 |
+
"eval_rewards/chosen": -18.656715393066406,
|
| 681 |
+
"eval_rewards/margins": 0.14861242473125458,
|
| 682 |
+
"eval_rewards/rejected": -18.805326461791992,
|
| 683 |
+
"eval_runtime": 73.5278,
|
| 684 |
+
"eval_samples_per_second": 24.834,
|
| 685 |
+
"eval_steps_per_second": 1.564,
|
| 686 |
+
"step": 37
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.8735632183908046,
|
| 690 |
+
"eval_logits/chosen": -0.7882456183433533,
|
| 691 |
+
"eval_logits/rejected": -0.7631468176841736,
|
| 692 |
+
"eval_logps/chosen": -185.62677001953125,
|
| 693 |
+
"eval_logps/rejected": -187.13912963867188,
|
| 694 |
+
"eval_loss": 2.0643482208251953,
|
| 695 |
+
"eval_nll_loss": 0.5234898924827576,
|
| 696 |
+
"eval_rewards/accuracies": 0.5239130258560181,
|
| 697 |
+
"eval_rewards/chosen": -18.56267738342285,
|
| 698 |
+
"eval_rewards/margins": 0.15123440325260162,
|
| 699 |
+
"eval_rewards/rejected": -18.713911056518555,
|
| 700 |
+
"eval_runtime": 73.4858,
|
| 701 |
+
"eval_samples_per_second": 24.848,
|
| 702 |
+
"eval_steps_per_second": 1.565,
|
| 703 |
+
"step": 38
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.896551724137931,
|
| 707 |
+
"eval_logits/chosen": -0.7857053279876709,
|
| 708 |
+
"eval_logits/rejected": -0.7608606815338135,
|
| 709 |
+
"eval_logps/chosen": -185.09970092773438,
|
| 710 |
+
"eval_logps/rejected": -186.60646057128906,
|
| 711 |
+
"eval_loss": 2.0600922107696533,
|
| 712 |
+
"eval_nll_loss": 0.5217379927635193,
|
| 713 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 714 |
+
"eval_rewards/chosen": -18.509971618652344,
|
| 715 |
+
"eval_rewards/margins": 0.15067508816719055,
|
| 716 |
+
"eval_rewards/rejected": -18.66064453125,
|
| 717 |
+
"eval_runtime": 73.7485,
|
| 718 |
+
"eval_samples_per_second": 24.76,
|
| 719 |
+
"eval_steps_per_second": 1.559,
|
| 720 |
+
"step": 39
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.9195402298850575,
|
| 724 |
+
"grad_norm": 50.088340759277344,
|
| 725 |
+
"learning_rate": 7.894736842105262e-08,
|
| 726 |
+
"logits/chosen": -0.8007175326347351,
|
| 727 |
+
"logits/rejected": -0.7798112630844116,
|
| 728 |
+
"logps/chosen": -190.50381469726562,
|
| 729 |
+
"logps/rejected": -193.3760223388672,
|
| 730 |
+
"loss": 2.1039,
|
| 731 |
+
"nll_loss": 0.5438653230667114,
|
| 732 |
+
"rewards/accuracies": 0.546875,
|
| 733 |
+
"rewards/chosen": -19.05038070678711,
|
| 734 |
+
"rewards/margins": 0.2872214913368225,
|
| 735 |
+
"rewards/rejected": -19.337600708007812,
|
| 736 |
+
"step": 40
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.9195402298850575,
|
| 740 |
+
"eval_logits/chosen": -0.785999596118927,
|
| 741 |
+
"eval_logits/rejected": -0.7610748410224915,
|
| 742 |
+
"eval_logps/chosen": -184.6099090576172,
|
| 743 |
+
"eval_logps/rejected": -186.1282958984375,
|
| 744 |
+
"eval_loss": 2.0597591400146484,
|
| 745 |
+
"eval_nll_loss": 0.5201125144958496,
|
| 746 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 747 |
+
"eval_rewards/chosen": -18.46099090576172,
|
| 748 |
+
"eval_rewards/margins": 0.15183939039707184,
|
| 749 |
+
"eval_rewards/rejected": -18.612829208374023,
|
| 750 |
+
"eval_runtime": 73.6777,
|
| 751 |
+
"eval_samples_per_second": 24.784,
|
| 752 |
+
"eval_steps_per_second": 1.561,
|
| 753 |
+
"step": 40
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.9425287356321839,
|
| 757 |
+
"eval_logits/chosen": -0.7789402604103088,
|
| 758 |
+
"eval_logits/rejected": -0.754026472568512,
|
| 759 |
+
"eval_logps/chosen": -184.23236083984375,
|
| 760 |
+
"eval_logps/rejected": -185.80072021484375,
|
| 761 |
+
"eval_loss": 2.0538711547851562,
|
| 762 |
+
"eval_nll_loss": 0.5189568400382996,
|
| 763 |
+
"eval_rewards/accuracies": 0.5260869860649109,
|
| 764 |
+
"eval_rewards/chosen": -18.423233032226562,
|
| 765 |
+
"eval_rewards/margins": 0.15683722496032715,
|
| 766 |
+
"eval_rewards/rejected": -18.5800724029541,
|
| 767 |
+
"eval_runtime": 73.0726,
|
| 768 |
+
"eval_samples_per_second": 24.989,
|
| 769 |
+
"eval_steps_per_second": 1.574,
|
| 770 |
+
"step": 41
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.9655172413793104,
|
| 774 |
+
"eval_logits/chosen": -0.777718722820282,
|
| 775 |
+
"eval_logits/rejected": -0.7525457739830017,
|
| 776 |
+
"eval_logps/chosen": -183.968994140625,
|
| 777 |
+
"eval_logps/rejected": -185.52581787109375,
|
| 778 |
+
"eval_loss": 2.054420232772827,
|
| 779 |
+
"eval_nll_loss": 0.518138587474823,
|
| 780 |
+
"eval_rewards/accuracies": 0.5282608866691589,
|
| 781 |
+
"eval_rewards/chosen": -18.396900177001953,
|
| 782 |
+
"eval_rewards/margins": 0.15568143129348755,
|
| 783 |
+
"eval_rewards/rejected": -18.552579879760742,
|
| 784 |
+
"eval_runtime": 73.2982,
|
| 785 |
+
"eval_samples_per_second": 24.912,
|
| 786 |
+
"eval_steps_per_second": 1.569,
|
| 787 |
+
"step": 42
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.9885057471264368,
|
| 791 |
+
"eval_logits/chosen": -0.779742419719696,
|
| 792 |
+
"eval_logits/rejected": -0.755063533782959,
|
| 793 |
+
"eval_logps/chosen": -183.93116760253906,
|
| 794 |
+
"eval_logps/rejected": -185.45208740234375,
|
| 795 |
+
"eval_loss": 2.0544536113739014,
|
| 796 |
+
"eval_nll_loss": 0.5179869532585144,
|
| 797 |
+
"eval_rewards/accuracies": 0.5260869860649109,
|
| 798 |
+
"eval_rewards/chosen": -18.393117904663086,
|
| 799 |
+
"eval_rewards/margins": 0.15209028124809265,
|
| 800 |
+
"eval_rewards/rejected": -18.54520606994629,
|
| 801 |
+
"eval_runtime": 73.5834,
|
| 802 |
+
"eval_samples_per_second": 24.815,
|
| 803 |
+
"eval_steps_per_second": 1.563,
|
| 804 |
+
"step": 43
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9885057471264368,
|
| 808 |
+
"step": 43,
|
| 809 |
+
"total_flos": 0.0,
|
| 810 |
+
"train_loss": 2.3523660704146985,
|
| 811 |
+
"train_runtime": 5387.5537,
|
| 812 |
+
"train_samples_per_second": 1.031,
|
| 813 |
+
"train_steps_per_second": 0.008
|
| 814 |
+
}
|
| 815 |
+
],
|
| 816 |
+
"logging_steps": 10,
|
| 817 |
+
"max_steps": 43,
|
| 818 |
+
"num_input_tokens_seen": 0,
|
| 819 |
+
"num_train_epochs": 1,
|
| 820 |
+
"save_steps": 10,
|
| 821 |
+
"stateful_callbacks": {
|
| 822 |
+
"TrainerControl": {
|
| 823 |
+
"args": {
|
| 824 |
+
"should_epoch_stop": false,
|
| 825 |
+
"should_evaluate": false,
|
| 826 |
+
"should_log": false,
|
| 827 |
+
"should_save": true,
|
| 828 |
+
"should_training_stop": true
|
| 829 |
+
},
|
| 830 |
+
"attributes": {}
|
| 831 |
+
}
|
| 832 |
+
},
|
| 833 |
+
"total_flos": 0.0,
|
| 834 |
+
"train_batch_size": 4,
|
| 835 |
+
"trial_name": null,
|
| 836 |
+
"trial_params": null
|
| 837 |
+
}
|