Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May21_09-47-51_gpu4-119-5/events.out.tfevents.1716248964.gpu4-119-5.1572664.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +478 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-i0
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-irepo-chatml-v16-i1
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# phi-2-irepo-chatml-v16-i1
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-i0](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-i0) on the None dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 2
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- total_eval_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.7.1
|
| 58 |
+
- Transformers 4.36.2
|
| 59 |
+
- Pytorch 2.1.2+cu121
|
| 60 |
+
- Datasets 2.14.6
|
| 61 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335579632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b78a8795cc10405ba0814ffa566dcc6014e0b0d1a449218ca42e53a602d2888b
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.19580436278230104,
|
| 4 |
+
"train_runtime": 2618.6186,
|
| 5 |
+
"train_samples": 10000,
|
| 6 |
+
"train_samples_per_second": 3.819,
|
| 7 |
+
"train_steps_per_second": 0.119
|
| 8 |
+
}
|
runs/May21_09-47-51_gpu4-119-5/events.out.tfevents.1716248964.gpu4-119-5.1572664.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78b0639b4b41d844b4279714c4790da17f6beec3b0cc351180f086ba238fe62a
|
| 3 |
+
size 25412
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.19580436278230104,
|
| 4 |
+
"train_runtime": 2618.6186,
|
| 5 |
+
"train_samples": 10000,
|
| 6 |
+
"train_samples_per_second": 3.819,
|
| 7 |
+
"train_steps_per_second": 0.119
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,478 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9984,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 312,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.5625e-07,
|
| 14 |
+
"logits/chosen": 0.184401273727417,
|
| 15 |
+
"logits/rejected": 0.45644012093544006,
|
| 16 |
+
"logps/chosen": -431.40997314453125,
|
| 17 |
+
"logps/rejected": -374.7772521972656,
|
| 18 |
+
"loss": 0.1668,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 1.5625e-06,
|
| 28 |
+
"logits/chosen": 0.19659145176410675,
|
| 29 |
+
"logits/rejected": 0.16923505067825317,
|
| 30 |
+
"logps/chosen": -399.8372802734375,
|
| 31 |
+
"logps/rejected": -407.80474853515625,
|
| 32 |
+
"loss": 0.2135,
|
| 33 |
+
"rewards/accuracies": 0.3055555522441864,
|
| 34 |
+
"rewards/chosen": -0.001171681797131896,
|
| 35 |
+
"rewards/margins": -4.31987973570358e-05,
|
| 36 |
+
"rewards/rejected": -0.001128483098000288,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06,
|
| 41 |
+
"learning_rate": 3.125e-06,
|
| 42 |
+
"logits/chosen": 0.19973915815353394,
|
| 43 |
+
"logits/rejected": 0.2067337930202484,
|
| 44 |
+
"logps/chosen": -425.3497619628906,
|
| 45 |
+
"logps/rejected": -433.87921142578125,
|
| 46 |
+
"loss": 0.2124,
|
| 47 |
+
"rewards/accuracies": 0.38749998807907104,
|
| 48 |
+
"rewards/chosen": -0.0007560320082120597,
|
| 49 |
+
"rewards/margins": 8.589267963543534e-06,
|
| 50 |
+
"rewards/rejected": -0.0007646213052794337,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 56 |
+
"logits/chosen": 0.18633976578712463,
|
| 57 |
+
"logits/rejected": 0.30335497856140137,
|
| 58 |
+
"logps/chosen": -459.7779235839844,
|
| 59 |
+
"logps/rejected": -473.452392578125,
|
| 60 |
+
"loss": 0.1993,
|
| 61 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 62 |
+
"rewards/chosen": -0.0007412955746985972,
|
| 63 |
+
"rewards/margins": 0.00032791445846669376,
|
| 64 |
+
"rewards/rejected": -0.0010692101204767823,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13,
|
| 69 |
+
"learning_rate": 4.989935734988098e-06,
|
| 70 |
+
"logits/chosen": 0.13782885670661926,
|
| 71 |
+
"logits/rejected": 0.31285157799720764,
|
| 72 |
+
"logps/chosen": -400.82794189453125,
|
| 73 |
+
"logps/rejected": -394.58905029296875,
|
| 74 |
+
"loss": 0.2101,
|
| 75 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 76 |
+
"rewards/chosen": -0.0014155835378915071,
|
| 77 |
+
"rewards/margins": 0.0005916984518989921,
|
| 78 |
+
"rewards/rejected": -0.0020072818733751774,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16,
|
| 83 |
+
"learning_rate": 4.949188496058089e-06,
|
| 84 |
+
"logits/chosen": 0.1621820479631424,
|
| 85 |
+
"logits/rejected": 0.3057764172554016,
|
| 86 |
+
"logps/chosen": -386.84515380859375,
|
| 87 |
+
"logps/rejected": -372.78460693359375,
|
| 88 |
+
"loss": 0.1983,
|
| 89 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 90 |
+
"rewards/chosen": -0.003419263754040003,
|
| 91 |
+
"rewards/margins": 0.0011660968884825706,
|
| 92 |
+
"rewards/rejected": -0.0045853606425225735,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.19,
|
| 97 |
+
"learning_rate": 4.8776412907378845e-06,
|
| 98 |
+
"logits/chosen": 0.12111353874206543,
|
| 99 |
+
"logits/rejected": 0.23442435264587402,
|
| 100 |
+
"logps/chosen": -416.0478515625,
|
| 101 |
+
"logps/rejected": -421.8002014160156,
|
| 102 |
+
"loss": 0.2125,
|
| 103 |
+
"rewards/accuracies": 0.46875,
|
| 104 |
+
"rewards/chosen": -0.0044263326562941074,
|
| 105 |
+
"rewards/margins": 0.0019439695170149207,
|
| 106 |
+
"rewards/rejected": -0.006370303221046925,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.22,
|
| 111 |
+
"learning_rate": 4.7761938666470405e-06,
|
| 112 |
+
"logits/chosen": 0.18056654930114746,
|
| 113 |
+
"logits/rejected": 0.24711184203624725,
|
| 114 |
+
"logps/chosen": -412.12152099609375,
|
| 115 |
+
"logps/rejected": -416.8878479003906,
|
| 116 |
+
"loss": 0.2155,
|
| 117 |
+
"rewards/accuracies": 0.5,
|
| 118 |
+
"rewards/chosen": -0.0073882960714399815,
|
| 119 |
+
"rewards/margins": 0.0029027846176177263,
|
| 120 |
+
"rewards/rejected": -0.010291079990565777,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.26,
|
| 125 |
+
"learning_rate": 4.646121984004666e-06,
|
| 126 |
+
"logits/chosen": 0.11649110168218613,
|
| 127 |
+
"logits/rejected": 0.18730294704437256,
|
| 128 |
+
"logps/chosen": -455.03399658203125,
|
| 129 |
+
"logps/rejected": -423.7317810058594,
|
| 130 |
+
"loss": 0.2059,
|
| 131 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 132 |
+
"rewards/chosen": -0.01960514858365059,
|
| 133 |
+
"rewards/margins": 0.0047067212872207165,
|
| 134 |
+
"rewards/rejected": -0.024311870336532593,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.29,
|
| 139 |
+
"learning_rate": 4.4890613722044526e-06,
|
| 140 |
+
"logits/chosen": 0.13214334845542908,
|
| 141 |
+
"logits/rejected": 0.1627044379711151,
|
| 142 |
+
"logps/chosen": -420.0687561035156,
|
| 143 |
+
"logps/rejected": -419.1974182128906,
|
| 144 |
+
"loss": 0.1974,
|
| 145 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 146 |
+
"rewards/chosen": -0.036356501281261444,
|
| 147 |
+
"rewards/margins": 0.009195582941174507,
|
| 148 |
+
"rewards/rejected": -0.0455520860850811,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.32,
|
| 153 |
+
"learning_rate": 4.3069871595684795e-06,
|
| 154 |
+
"logits/chosen": 0.09840121865272522,
|
| 155 |
+
"logits/rejected": 0.19065344333648682,
|
| 156 |
+
"logps/chosen": -573.3145751953125,
|
| 157 |
+
"logps/rejected": -588.6065063476562,
|
| 158 |
+
"loss": 0.1903,
|
| 159 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 160 |
+
"rewards/chosen": -0.07631657272577286,
|
| 161 |
+
"rewards/margins": 0.014788051135838032,
|
| 162 |
+
"rewards/rejected": -0.09110463410615921,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.35,
|
| 167 |
+
"learning_rate": 4.102189034962561e-06,
|
| 168 |
+
"logits/chosen": 0.03982686251401901,
|
| 169 |
+
"logits/rejected": 0.06170179322361946,
|
| 170 |
+
"logps/chosen": -483.71844482421875,
|
| 171 |
+
"logps/rejected": -537.0131225585938,
|
| 172 |
+
"loss": 0.1974,
|
| 173 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 174 |
+
"rewards/chosen": -0.09070506691932678,
|
| 175 |
+
"rewards/margins": 0.014559125527739525,
|
| 176 |
+
"rewards/rejected": -0.10526418685913086,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.38,
|
| 181 |
+
"learning_rate": 3.8772424536302565e-06,
|
| 182 |
+
"logits/chosen": 0.018964925780892372,
|
| 183 |
+
"logits/rejected": 0.08643153309822083,
|
| 184 |
+
"logps/chosen": -517.4832763671875,
|
| 185 |
+
"logps/rejected": -530.7005615234375,
|
| 186 |
+
"loss": 0.2021,
|
| 187 |
+
"rewards/accuracies": 0.53125,
|
| 188 |
+
"rewards/chosen": -0.1091010719537735,
|
| 189 |
+
"rewards/margins": 0.02261071279644966,
|
| 190 |
+
"rewards/rejected": -0.13171178102493286,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.42,
|
| 195 |
+
"learning_rate": 3.634976249348867e-06,
|
| 196 |
+
"logits/chosen": 0.055875927209854126,
|
| 197 |
+
"logits/rejected": 0.0218794047832489,
|
| 198 |
+
"logps/chosen": -516.7933959960938,
|
| 199 |
+
"logps/rejected": -543.1007690429688,
|
| 200 |
+
"loss": 0.1878,
|
| 201 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 202 |
+
"rewards/chosen": -0.1324981302022934,
|
| 203 |
+
"rewards/margins": 0.03664865717291832,
|
| 204 |
+
"rewards/rejected": -0.1691468060016632,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.45,
|
| 209 |
+
"learning_rate": 3.3784370602033572e-06,
|
| 210 |
+
"logits/chosen": -0.0752568170428276,
|
| 211 |
+
"logits/rejected": 0.07607444375753403,
|
| 212 |
+
"logps/chosen": -510.17987060546875,
|
| 213 |
+
"logps/rejected": -535.81494140625,
|
| 214 |
+
"loss": 0.1899,
|
| 215 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 216 |
+
"rewards/chosen": -0.13363127410411835,
|
| 217 |
+
"rewards/margins": 0.040403980761766434,
|
| 218 |
+
"rewards/rejected": -0.1740352362394333,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.48,
|
| 223 |
+
"learning_rate": 3.1108510153447352e-06,
|
| 224 |
+
"logits/chosen": -0.08575725555419922,
|
| 225 |
+
"logits/rejected": -0.02042851224541664,
|
| 226 |
+
"logps/chosen": -584.4342041015625,
|
| 227 |
+
"logps/rejected": -560.9251708984375,
|
| 228 |
+
"loss": 0.2106,
|
| 229 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 230 |
+
"rewards/chosen": -0.163564532995224,
|
| 231 |
+
"rewards/margins": 0.027438053861260414,
|
| 232 |
+
"rewards/rejected": -0.19100257754325867,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.51,
|
| 237 |
+
"learning_rate": 2.835583164544139e-06,
|
| 238 |
+
"logits/chosen": 0.0028429715894162655,
|
| 239 |
+
"logits/rejected": 0.10017697513103485,
|
| 240 |
+
"logps/chosen": -546.78515625,
|
| 241 |
+
"logps/rejected": -583.113525390625,
|
| 242 |
+
"loss": 0.2005,
|
| 243 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 244 |
+
"rewards/chosen": -0.13426996767520905,
|
| 245 |
+
"rewards/margins": 0.034793704748153687,
|
| 246 |
+
"rewards/rejected": -0.16906365752220154,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.54,
|
| 251 |
+
"learning_rate": 2.556095160739513e-06,
|
| 252 |
+
"logits/chosen": -0.0652703195810318,
|
| 253 |
+
"logits/rejected": 0.08785363286733627,
|
| 254 |
+
"logps/chosen": -474.89013671875,
|
| 255 |
+
"logps/rejected": -519.8175048828125,
|
| 256 |
+
"loss": 0.1939,
|
| 257 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 258 |
+
"rewards/chosen": -0.11705396324396133,
|
| 259 |
+
"rewards/margins": 0.03326694667339325,
|
| 260 |
+
"rewards/rejected": -0.150320902466774,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.58,
|
| 265 |
+
"learning_rate": 2.2759017277414165e-06,
|
| 266 |
+
"logits/chosen": -0.06097496673464775,
|
| 267 |
+
"logits/rejected": -0.00452041020616889,
|
| 268 |
+
"logps/chosen": -511.9466247558594,
|
| 269 |
+
"logps/rejected": -552.163330078125,
|
| 270 |
+
"loss": 0.1901,
|
| 271 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 272 |
+
"rewards/chosen": -0.12096891552209854,
|
| 273 |
+
"rewards/margins": 0.03578288108110428,
|
| 274 |
+
"rewards/rejected": -0.15675179660320282,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.61,
|
| 279 |
+
"learning_rate": 1.9985264605418185e-06,
|
| 280 |
+
"logits/chosen": -0.005833833012729883,
|
| 281 |
+
"logits/rejected": 0.08312544971704483,
|
| 282 |
+
"logps/chosen": -529.5341796875,
|
| 283 |
+
"logps/rejected": -528.4331665039062,
|
| 284 |
+
"loss": 0.1788,
|
| 285 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 286 |
+
"rewards/chosen": -0.12104544788599014,
|
| 287 |
+
"rewards/margins": 0.03279378265142441,
|
| 288 |
+
"rewards/rejected": -0.15383923053741455,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.64,
|
| 293 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 294 |
+
"logits/chosen": -0.053509682416915894,
|
| 295 |
+
"logits/rejected": -0.0027845636941492558,
|
| 296 |
+
"logps/chosen": -601.9525146484375,
|
| 297 |
+
"logps/rejected": -663.5382690429688,
|
| 298 |
+
"loss": 0.1869,
|
| 299 |
+
"rewards/accuracies": 0.574999988079071,
|
| 300 |
+
"rewards/chosen": -0.1414756029844284,
|
| 301 |
+
"rewards/margins": 0.056746870279312134,
|
| 302 |
+
"rewards/rejected": -0.19822247326374054,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.67,
|
| 307 |
+
"learning_rate": 1.466103737583699e-06,
|
| 308 |
+
"logits/chosen": -0.005456715822219849,
|
| 309 |
+
"logits/rejected": -0.13148556649684906,
|
| 310 |
+
"logps/chosen": -496.91949462890625,
|
| 311 |
+
"logps/rejected": -558.6058959960938,
|
| 312 |
+
"loss": 0.1844,
|
| 313 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 314 |
+
"rewards/chosen": -0.13160409033298492,
|
| 315 |
+
"rewards/margins": 0.049931664019823074,
|
| 316 |
+
"rewards/rejected": -0.1815357506275177,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7,
|
| 321 |
+
"learning_rate": 1.217751806485235e-06,
|
| 322 |
+
"logits/chosen": -0.046624261885881424,
|
| 323 |
+
"logits/rejected": -0.01640903949737549,
|
| 324 |
+
"logps/chosen": -458.24212646484375,
|
| 325 |
+
"logps/rejected": -496.15985107421875,
|
| 326 |
+
"loss": 0.195,
|
| 327 |
+
"rewards/accuracies": 0.46875,
|
| 328 |
+
"rewards/chosen": -0.11825968325138092,
|
| 329 |
+
"rewards/margins": 0.04362802952528,
|
| 330 |
+
"rewards/rejected": -0.16188772022724152,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.74,
|
| 335 |
+
"learning_rate": 9.855248903979505e-07,
|
| 336 |
+
"logits/chosen": -0.058581192046403885,
|
| 337 |
+
"logits/rejected": 0.12358301877975464,
|
| 338 |
+
"logps/chosen": -599.2974853515625,
|
| 339 |
+
"logps/rejected": -605.1329345703125,
|
| 340 |
+
"loss": 0.1807,
|
| 341 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 342 |
+
"rewards/chosen": -0.14849095046520233,
|
| 343 |
+
"rewards/margins": 0.043377481400966644,
|
| 344 |
+
"rewards/rejected": -0.19186842441558838,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.77,
|
| 349 |
+
"learning_rate": 7.723433775328385e-07,
|
| 350 |
+
"logits/chosen": -0.04961230233311653,
|
| 351 |
+
"logits/rejected": 0.06744717061519623,
|
| 352 |
+
"logps/chosen": -500.963134765625,
|
| 353 |
+
"logps/rejected": -533.319580078125,
|
| 354 |
+
"loss": 0.1874,
|
| 355 |
+
"rewards/accuracies": 0.512499988079071,
|
| 356 |
+
"rewards/chosen": -0.1264745444059372,
|
| 357 |
+
"rewards/margins": 0.0465153343975544,
|
| 358 |
+
"rewards/rejected": -0.1729898750782013,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8,
|
| 363 |
+
"learning_rate": 5.808881491049723e-07,
|
| 364 |
+
"logits/chosen": -0.012030300684273243,
|
| 365 |
+
"logits/rejected": -0.08321252465248108,
|
| 366 |
+
"logps/chosen": -509.8011169433594,
|
| 367 |
+
"logps/rejected": -570.6807861328125,
|
| 368 |
+
"loss": 0.1886,
|
| 369 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 370 |
+
"rewards/chosen": -0.1262587606906891,
|
| 371 |
+
"rewards/margins": 0.05674763396382332,
|
| 372 |
+
"rewards/rejected": -0.1830063760280609,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.83,
|
| 377 |
+
"learning_rate": 4.1356686569674344e-07,
|
| 378 |
+
"logits/chosen": -0.07445530593395233,
|
| 379 |
+
"logits/rejected": 0.04640640690922737,
|
| 380 |
+
"logps/chosen": -479.8208923339844,
|
| 381 |
+
"logps/rejected": -571.5008544921875,
|
| 382 |
+
"loss": 0.192,
|
| 383 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 384 |
+
"rewards/chosen": -0.1300186812877655,
|
| 385 |
+
"rewards/margins": 0.055131178349256516,
|
| 386 |
+
"rewards/rejected": -0.18514983355998993,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.86,
|
| 391 |
+
"learning_rate": 2.7248368952908055e-07,
|
| 392 |
+
"logits/chosen": -0.024127716198563576,
|
| 393 |
+
"logits/rejected": 0.048486463725566864,
|
| 394 |
+
"logps/chosen": -492.6990661621094,
|
| 395 |
+
"logps/rejected": -528.9088134765625,
|
| 396 |
+
"loss": 0.1872,
|
| 397 |
+
"rewards/accuracies": 0.4375,
|
| 398 |
+
"rewards/chosen": -0.1340349167585373,
|
| 399 |
+
"rewards/margins": 0.04594132676720619,
|
| 400 |
+
"rewards/rejected": -0.17997623980045319,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9,
|
| 405 |
+
"learning_rate": 1.59412823400657e-07,
|
| 406 |
+
"logits/chosen": -0.0358465239405632,
|
| 407 |
+
"logits/rejected": 0.059707850217819214,
|
| 408 |
+
"logps/chosen": -528.1822509765625,
|
| 409 |
+
"logps/rejected": -566.1701049804688,
|
| 410 |
+
"loss": 0.1907,
|
| 411 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 412 |
+
"rewards/chosen": -0.1274920403957367,
|
| 413 |
+
"rewards/margins": 0.05404983088374138,
|
| 414 |
+
"rewards/rejected": -0.18154187500476837,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.93,
|
| 419 |
+
"learning_rate": 7.577619905828281e-08,
|
| 420 |
+
"logits/chosen": -0.04293031617999077,
|
| 421 |
+
"logits/rejected": -0.02192228101193905,
|
| 422 |
+
"logps/chosen": -562.0809936523438,
|
| 423 |
+
"logps/rejected": -616.6372680664062,
|
| 424 |
+
"loss": 0.1825,
|
| 425 |
+
"rewards/accuracies": 0.5625,
|
| 426 |
+
"rewards/chosen": -0.13138429820537567,
|
| 427 |
+
"rewards/margins": 0.05358911678195,
|
| 428 |
+
"rewards/rejected": -0.18497340381145477,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.96,
|
| 433 |
+
"learning_rate": 2.262559558016325e-08,
|
| 434 |
+
"logits/chosen": 0.016219165176153183,
|
| 435 |
+
"logits/rejected": -0.03756276145577431,
|
| 436 |
+
"logps/chosen": -530.8041381835938,
|
| 437 |
+
"logps/rejected": -577.8040161132812,
|
| 438 |
+
"loss": 0.1984,
|
| 439 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 440 |
+
"rewards/chosen": -0.12510040402412415,
|
| 441 |
+
"rewards/margins": 0.048407431691884995,
|
| 442 |
+
"rewards/rejected": -0.17350783944129944,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.99,
|
| 447 |
+
"learning_rate": 6.294126437336734e-10,
|
| 448 |
+
"logits/chosen": -0.057995982468128204,
|
| 449 |
+
"logits/rejected": -0.08621449768543243,
|
| 450 |
+
"logps/chosen": -543.5442504882812,
|
| 451 |
+
"logps/rejected": -563.89599609375,
|
| 452 |
+
"loss": 0.1927,
|
| 453 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 454 |
+
"rewards/chosen": -0.13217976689338684,
|
| 455 |
+
"rewards/margins": 0.04179350286722183,
|
| 456 |
+
"rewards/rejected": -0.17397327721118927,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.0,
|
| 461 |
+
"step": 312,
|
| 462 |
+
"total_flos": 0.0,
|
| 463 |
+
"train_loss": 0.19580436278230104,
|
| 464 |
+
"train_runtime": 2618.6186,
|
| 465 |
+
"train_samples_per_second": 3.819,
|
| 466 |
+
"train_steps_per_second": 0.119
|
| 467 |
+
}
|
| 468 |
+
],
|
| 469 |
+
"logging_steps": 10,
|
| 470 |
+
"max_steps": 312,
|
| 471 |
+
"num_input_tokens_seen": 0,
|
| 472 |
+
"num_train_epochs": 1,
|
| 473 |
+
"save_steps": 100,
|
| 474 |
+
"total_flos": 0.0,
|
| 475 |
+
"train_batch_size": 4,
|
| 476 |
+
"trial_name": null,
|
| 477 |
+
"trial_params": null
|
| 478 |
+
}
|