Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May17_21-17-12_gpu4-119-5/events.out.tfevents.1715944729.gpu4-119-5.1658112.0 +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-2/phi-2-gpo-v34-merged-i1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-gpo-v4-i2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# phi-2-gpo-v4-i2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO-2/phi-2-gpo-v34-merged-i1](https://huggingface.co/DUAL-GPO-2/phi-2-gpo-v34-merged-i1) on the None dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 3
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 48
|
| 45 |
+
- total_eval_batch_size: 12
|
| 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 167807296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41b990e0f101528270f0bbe10715311b24721ff4f893077c02697a37bf74d9fa
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.8545298270690136,
|
| 4 |
+
"train_runtime": 4214.6598,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 3.559,
|
| 7 |
+
"train_steps_per_second": 0.074
|
| 8 |
+
}
|
runs/May17_21-17-12_gpu4-119-5/events.out.tfevents.1715944729.gpu4-119-5.1658112.0
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 sha256:7448660e4f669609c35c6b16e00bd6a63bcaf5899d6a83a272d610d599b06625
|
| 3 |
+
size 25339
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.8545298270690136,
|
| 4 |
+
"train_runtime": 4214.6598,
|
| 5 |
+
"train_samples": 15000,
|
| 6 |
+
"train_samples_per_second": 3.559,
|
| 7 |
+
"train_steps_per_second": 0.074
|
| 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": -0.23665529489517212,
|
| 15 |
+
"logits/rejected": 0.00744676636531949,
|
| 16 |
+
"logps/chosen": -473.1935729980469,
|
| 17 |
+
"logps/rejected": -432.5630798339844,
|
| 18 |
+
"loss": 2.0507,
|
| 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": -0.1829964816570282,
|
| 29 |
+
"logits/rejected": -0.12090256810188293,
|
| 30 |
+
"logps/chosen": -383.1433410644531,
|
| 31 |
+
"logps/rejected": -396.7732238769531,
|
| 32 |
+
"loss": 2.1635,
|
| 33 |
+
"rewards/accuracies": 0.3611111044883728,
|
| 34 |
+
"rewards/chosen": 0.00011064788850490004,
|
| 35 |
+
"rewards/margins": -0.0001980961678782478,
|
| 36 |
+
"rewards/rejected": 0.00030874405638314784,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06,
|
| 41 |
+
"learning_rate": 3.125e-06,
|
| 42 |
+
"logits/chosen": -0.16048185527324677,
|
| 43 |
+
"logits/rejected": -0.10916981846094131,
|
| 44 |
+
"logps/chosen": -385.62884521484375,
|
| 45 |
+
"logps/rejected": -405.12811279296875,
|
| 46 |
+
"loss": 2.1708,
|
| 47 |
+
"rewards/accuracies": 0.53125,
|
| 48 |
+
"rewards/chosen": -0.0015514277620241046,
|
| 49 |
+
"rewards/margins": 0.0006486388738267124,
|
| 50 |
+
"rewards/rejected": -0.002200066577643156,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 56 |
+
"logits/chosen": -0.13327451050281525,
|
| 57 |
+
"logits/rejected": -0.09481740742921829,
|
| 58 |
+
"logps/chosen": -383.2904968261719,
|
| 59 |
+
"logps/rejected": -386.16241455078125,
|
| 60 |
+
"loss": 2.1136,
|
| 61 |
+
"rewards/accuracies": 0.612500011920929,
|
| 62 |
+
"rewards/chosen": -0.007082388736307621,
|
| 63 |
+
"rewards/margins": 0.004239413887262344,
|
| 64 |
+
"rewards/rejected": -0.011321802623569965,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13,
|
| 69 |
+
"learning_rate": 4.989935734988098e-06,
|
| 70 |
+
"logits/chosen": -0.20482906699180603,
|
| 71 |
+
"logits/rejected": -0.11631456762552261,
|
| 72 |
+
"logps/chosen": -449.19073486328125,
|
| 73 |
+
"logps/rejected": -432.53546142578125,
|
| 74 |
+
"loss": 2.0563,
|
| 75 |
+
"rewards/accuracies": 0.581250011920929,
|
| 76 |
+
"rewards/chosen": -0.04025329276919365,
|
| 77 |
+
"rewards/margins": 0.009497672319412231,
|
| 78 |
+
"rewards/rejected": -0.04975096508860588,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16,
|
| 83 |
+
"learning_rate": 4.949188496058089e-06,
|
| 84 |
+
"logits/chosen": -0.18474937975406647,
|
| 85 |
+
"logits/rejected": -0.15179498493671417,
|
| 86 |
+
"logps/chosen": -466.480224609375,
|
| 87 |
+
"logps/rejected": -564.7294311523438,
|
| 88 |
+
"loss": 2.0206,
|
| 89 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 90 |
+
"rewards/chosen": -0.1005839928984642,
|
| 91 |
+
"rewards/margins": 0.05746855586767197,
|
| 92 |
+
"rewards/rejected": -0.15805256366729736,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.19,
|
| 97 |
+
"learning_rate": 4.8776412907378845e-06,
|
| 98 |
+
"logits/chosen": -0.2444579154253006,
|
| 99 |
+
"logits/rejected": -0.17071941494941711,
|
| 100 |
+
"logps/chosen": -678.161865234375,
|
| 101 |
+
"logps/rejected": -776.6124877929688,
|
| 102 |
+
"loss": 1.9129,
|
| 103 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 104 |
+
"rewards/chosen": -0.25659433007240295,
|
| 105 |
+
"rewards/margins": 0.11048071086406708,
|
| 106 |
+
"rewards/rejected": -0.3670750558376312,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.22,
|
| 111 |
+
"learning_rate": 4.7761938666470405e-06,
|
| 112 |
+
"logits/chosen": -0.2789674401283264,
|
| 113 |
+
"logits/rejected": -0.15984465181827545,
|
| 114 |
+
"logps/chosen": -767.4395751953125,
|
| 115 |
+
"logps/rejected": -960.1740112304688,
|
| 116 |
+
"loss": 1.9228,
|
| 117 |
+
"rewards/accuracies": 0.574999988079071,
|
| 118 |
+
"rewards/chosen": -0.37694883346557617,
|
| 119 |
+
"rewards/margins": 0.17607252299785614,
|
| 120 |
+
"rewards/rejected": -0.5530213117599487,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.26,
|
| 125 |
+
"learning_rate": 4.646121984004666e-06,
|
| 126 |
+
"logits/chosen": -0.1913307160139084,
|
| 127 |
+
"logits/rejected": -0.14110524952411652,
|
| 128 |
+
"logps/chosen": -764.4078979492188,
|
| 129 |
+
"logps/rejected": -998.7781982421875,
|
| 130 |
+
"loss": 1.9313,
|
| 131 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 132 |
+
"rewards/chosen": -0.3331916630268097,
|
| 133 |
+
"rewards/margins": 0.25039905309677124,
|
| 134 |
+
"rewards/rejected": -0.5835906863212585,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.29,
|
| 139 |
+
"learning_rate": 4.4890613722044526e-06,
|
| 140 |
+
"logits/chosen": -0.23566904664039612,
|
| 141 |
+
"logits/rejected": -0.15600116550922394,
|
| 142 |
+
"logps/chosen": -777.1472778320312,
|
| 143 |
+
"logps/rejected": -871.2056884765625,
|
| 144 |
+
"loss": 1.7804,
|
| 145 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 146 |
+
"rewards/chosen": -0.37899401783943176,
|
| 147 |
+
"rewards/margins": 0.1299220621585846,
|
| 148 |
+
"rewards/rejected": -0.5089160203933716,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.32,
|
| 153 |
+
"learning_rate": 4.3069871595684795e-06,
|
| 154 |
+
"logits/chosen": -0.25944238901138306,
|
| 155 |
+
"logits/rejected": -0.1812916249036789,
|
| 156 |
+
"logps/chosen": -820.12255859375,
|
| 157 |
+
"logps/rejected": -1078.459228515625,
|
| 158 |
+
"loss": 1.7734,
|
| 159 |
+
"rewards/accuracies": 0.612500011920929,
|
| 160 |
+
"rewards/chosen": -0.4638814926147461,
|
| 161 |
+
"rewards/margins": 0.24260278046131134,
|
| 162 |
+
"rewards/rejected": -0.7064841985702515,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.35,
|
| 167 |
+
"learning_rate": 4.102189034962561e-06,
|
| 168 |
+
"logits/chosen": -0.22316499054431915,
|
| 169 |
+
"logits/rejected": -0.19235864281654358,
|
| 170 |
+
"logps/chosen": -885.9295654296875,
|
| 171 |
+
"logps/rejected": -1113.445068359375,
|
| 172 |
+
"loss": 1.8059,
|
| 173 |
+
"rewards/accuracies": 0.59375,
|
| 174 |
+
"rewards/chosen": -0.4847044050693512,
|
| 175 |
+
"rewards/margins": 0.23728513717651367,
|
| 176 |
+
"rewards/rejected": -0.7219894528388977,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.38,
|
| 181 |
+
"learning_rate": 3.8772424536302565e-06,
|
| 182 |
+
"logits/chosen": -0.20930325984954834,
|
| 183 |
+
"logits/rejected": -0.1453815996646881,
|
| 184 |
+
"logps/chosen": -880.3770751953125,
|
| 185 |
+
"logps/rejected": -1030.3275146484375,
|
| 186 |
+
"loss": 1.8441,
|
| 187 |
+
"rewards/accuracies": 0.59375,
|
| 188 |
+
"rewards/chosen": -0.4620415270328522,
|
| 189 |
+
"rewards/margins": 0.17096856236457825,
|
| 190 |
+
"rewards/rejected": -0.6330100893974304,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.42,
|
| 195 |
+
"learning_rate": 3.634976249348867e-06,
|
| 196 |
+
"logits/chosen": -0.15696187317371368,
|
| 197 |
+
"logits/rejected": -0.1074260026216507,
|
| 198 |
+
"logps/chosen": -885.1849365234375,
|
| 199 |
+
"logps/rejected": -1044.3388671875,
|
| 200 |
+
"loss": 1.9112,
|
| 201 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 202 |
+
"rewards/chosen": -0.4623374938964844,
|
| 203 |
+
"rewards/margins": 0.17165368795394897,
|
| 204 |
+
"rewards/rejected": -0.6339911222457886,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.45,
|
| 209 |
+
"learning_rate": 3.3784370602033572e-06,
|
| 210 |
+
"logits/chosen": -0.2678197920322418,
|
| 211 |
+
"logits/rejected": -0.23175963759422302,
|
| 212 |
+
"logps/chosen": -806.1285400390625,
|
| 213 |
+
"logps/rejected": -1082.8525390625,
|
| 214 |
+
"loss": 1.8023,
|
| 215 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 216 |
+
"rewards/chosen": -0.42001548409461975,
|
| 217 |
+
"rewards/margins": 0.21150164306163788,
|
| 218 |
+
"rewards/rejected": -0.6315171122550964,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.48,
|
| 223 |
+
"learning_rate": 3.1108510153447352e-06,
|
| 224 |
+
"logits/chosen": -0.21387240290641785,
|
| 225 |
+
"logits/rejected": -0.1143934354186058,
|
| 226 |
+
"logps/chosen": -815.8262939453125,
|
| 227 |
+
"logps/rejected": -906.0357666015625,
|
| 228 |
+
"loss": 1.808,
|
| 229 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 230 |
+
"rewards/chosen": -0.37800681591033936,
|
| 231 |
+
"rewards/margins": 0.16527661681175232,
|
| 232 |
+
"rewards/rejected": -0.5432834029197693,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.51,
|
| 237 |
+
"learning_rate": 2.835583164544139e-06,
|
| 238 |
+
"logits/chosen": -0.14601436257362366,
|
| 239 |
+
"logits/rejected": -0.1241162046790123,
|
| 240 |
+
"logps/chosen": -840.3963623046875,
|
| 241 |
+
"logps/rejected": -1006.9793090820312,
|
| 242 |
+
"loss": 1.9465,
|
| 243 |
+
"rewards/accuracies": 0.606249988079071,
|
| 244 |
+
"rewards/chosen": -0.38944554328918457,
|
| 245 |
+
"rewards/margins": 0.19957077503204346,
|
| 246 |
+
"rewards/rejected": -0.589016318321228,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.54,
|
| 251 |
+
"learning_rate": 2.556095160739513e-06,
|
| 252 |
+
"logits/chosen": -0.1653786599636078,
|
| 253 |
+
"logits/rejected": -0.12808741629123688,
|
| 254 |
+
"logps/chosen": -730.0451049804688,
|
| 255 |
+
"logps/rejected": -965.7391357421875,
|
| 256 |
+
"loss": 1.769,
|
| 257 |
+
"rewards/accuracies": 0.706250011920929,
|
| 258 |
+
"rewards/chosen": -0.35579684376716614,
|
| 259 |
+
"rewards/margins": 0.20604142546653748,
|
| 260 |
+
"rewards/rejected": -0.5618382692337036,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.58,
|
| 265 |
+
"learning_rate": 2.2759017277414165e-06,
|
| 266 |
+
"logits/chosen": -0.19225947558879852,
|
| 267 |
+
"logits/rejected": -0.17646418511867523,
|
| 268 |
+
"logps/chosen": -787.419677734375,
|
| 269 |
+
"logps/rejected": -1047.8543701171875,
|
| 270 |
+
"loss": 1.747,
|
| 271 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 272 |
+
"rewards/chosen": -0.4115837514400482,
|
| 273 |
+
"rewards/margins": 0.2577529549598694,
|
| 274 |
+
"rewards/rejected": -0.6693366765975952,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.61,
|
| 279 |
+
"learning_rate": 1.9985264605418185e-06,
|
| 280 |
+
"logits/chosen": -0.21607378125190735,
|
| 281 |
+
"logits/rejected": -0.18134012818336487,
|
| 282 |
+
"logps/chosen": -850.4358520507812,
|
| 283 |
+
"logps/rejected": -1074.816162109375,
|
| 284 |
+
"loss": 1.7703,
|
| 285 |
+
"rewards/accuracies": 0.675000011920929,
|
| 286 |
+
"rewards/chosen": -0.42398494482040405,
|
| 287 |
+
"rewards/margins": 0.27196767926216125,
|
| 288 |
+
"rewards/rejected": -0.6959526538848877,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.64,
|
| 293 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 294 |
+
"logits/chosen": -0.18237197399139404,
|
| 295 |
+
"logits/rejected": -0.15335983037948608,
|
| 296 |
+
"logps/chosen": -753.6973266601562,
|
| 297 |
+
"logps/rejected": -888.6695556640625,
|
| 298 |
+
"loss": 1.8577,
|
| 299 |
+
"rewards/accuracies": 0.606249988079071,
|
| 300 |
+
"rewards/chosen": -0.3945154547691345,
|
| 301 |
+
"rewards/margins": 0.15583784878253937,
|
| 302 |
+
"rewards/rejected": -0.5503532886505127,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.67,
|
| 307 |
+
"learning_rate": 1.466103737583699e-06,
|
| 308 |
+
"logits/chosen": -0.14478984475135803,
|
| 309 |
+
"logits/rejected": -0.1423361599445343,
|
| 310 |
+
"logps/chosen": -786.3085327148438,
|
| 311 |
+
"logps/rejected": -1014.6956787109375,
|
| 312 |
+
"loss": 1.8453,
|
| 313 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 314 |
+
"rewards/chosen": -0.39204883575439453,
|
| 315 |
+
"rewards/margins": 0.2218962460756302,
|
| 316 |
+
"rewards/rejected": -0.6139450073242188,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7,
|
| 321 |
+
"learning_rate": 1.217751806485235e-06,
|
| 322 |
+
"logits/chosen": -0.1539977490901947,
|
| 323 |
+
"logits/rejected": -0.10850413888692856,
|
| 324 |
+
"logps/chosen": -802.6807861328125,
|
| 325 |
+
"logps/rejected": -1012.9494018554688,
|
| 326 |
+
"loss": 1.679,
|
| 327 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 328 |
+
"rewards/chosen": -0.37582096457481384,
|
| 329 |
+
"rewards/margins": 0.24124114215373993,
|
| 330 |
+
"rewards/rejected": -0.6170621514320374,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.74,
|
| 335 |
+
"learning_rate": 9.855248903979505e-07,
|
| 336 |
+
"logits/chosen": -0.2050359696149826,
|
| 337 |
+
"logits/rejected": -0.11318047344684601,
|
| 338 |
+
"logps/chosen": -806.9402465820312,
|
| 339 |
+
"logps/rejected": -1053.7979736328125,
|
| 340 |
+
"loss": 1.7812,
|
| 341 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 342 |
+
"rewards/chosen": -0.3787270784378052,
|
| 343 |
+
"rewards/margins": 0.25472280383110046,
|
| 344 |
+
"rewards/rejected": -0.633449912071228,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.77,
|
| 349 |
+
"learning_rate": 7.723433775328385e-07,
|
| 350 |
+
"logits/chosen": -0.18793925642967224,
|
| 351 |
+
"logits/rejected": -0.13918839395046234,
|
| 352 |
+
"logps/chosen": -818.8219604492188,
|
| 353 |
+
"logps/rejected": -1038.0279541015625,
|
| 354 |
+
"loss": 1.7375,
|
| 355 |
+
"rewards/accuracies": 0.6875,
|
| 356 |
+
"rewards/chosen": -0.40735897421836853,
|
| 357 |
+
"rewards/margins": 0.23022215068340302,
|
| 358 |
+
"rewards/rejected": -0.6375811696052551,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8,
|
| 363 |
+
"learning_rate": 5.808881491049723e-07,
|
| 364 |
+
"logits/chosen": -0.13271953165531158,
|
| 365 |
+
"logits/rejected": -0.10349054634571075,
|
| 366 |
+
"logps/chosen": -846.697265625,
|
| 367 |
+
"logps/rejected": -1090.2091064453125,
|
| 368 |
+
"loss": 1.7763,
|
| 369 |
+
"rewards/accuracies": 0.675000011920929,
|
| 370 |
+
"rewards/chosen": -0.39346030354499817,
|
| 371 |
+
"rewards/margins": 0.25347214937210083,
|
| 372 |
+
"rewards/rejected": -0.6469324827194214,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.83,
|
| 377 |
+
"learning_rate": 4.1356686569674344e-07,
|
| 378 |
+
"logits/chosen": -0.10151909291744232,
|
| 379 |
+
"logits/rejected": -0.09530433267354965,
|
| 380 |
+
"logps/chosen": -817.2677612304688,
|
| 381 |
+
"logps/rejected": -1003.5374755859375,
|
| 382 |
+
"loss": 1.7718,
|
| 383 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 384 |
+
"rewards/chosen": -0.4086136817932129,
|
| 385 |
+
"rewards/margins": 0.1990220844745636,
|
| 386 |
+
"rewards/rejected": -0.6076357960700989,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.86,
|
| 391 |
+
"learning_rate": 2.7248368952908055e-07,
|
| 392 |
+
"logits/chosen": -0.1809629648923874,
|
| 393 |
+
"logits/rejected": -0.14152123034000397,
|
| 394 |
+
"logps/chosen": -830.4895629882812,
|
| 395 |
+
"logps/rejected": -1007.2437744140625,
|
| 396 |
+
"loss": 1.789,
|
| 397 |
+
"rewards/accuracies": 0.643750011920929,
|
| 398 |
+
"rewards/chosen": -0.4253358840942383,
|
| 399 |
+
"rewards/margins": 0.21133287250995636,
|
| 400 |
+
"rewards/rejected": -0.6366687417030334,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9,
|
| 405 |
+
"learning_rate": 1.59412823400657e-07,
|
| 406 |
+
"logits/chosen": -0.1590525209903717,
|
| 407 |
+
"logits/rejected": -0.10606285184621811,
|
| 408 |
+
"logps/chosen": -817.2872924804688,
|
| 409 |
+
"logps/rejected": -1020.6212158203125,
|
| 410 |
+
"loss": 1.8107,
|
| 411 |
+
"rewards/accuracies": 0.706250011920929,
|
| 412 |
+
"rewards/chosen": -0.3928419053554535,
|
| 413 |
+
"rewards/margins": 0.2158069908618927,
|
| 414 |
+
"rewards/rejected": -0.6086488962173462,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.93,
|
| 419 |
+
"learning_rate": 7.577619905828281e-08,
|
| 420 |
+
"logits/chosen": -0.1407514065504074,
|
| 421 |
+
"logits/rejected": -0.14306677877902985,
|
| 422 |
+
"logps/chosen": -782.491455078125,
|
| 423 |
+
"logps/rejected": -1054.53564453125,
|
| 424 |
+
"loss": 1.7329,
|
| 425 |
+
"rewards/accuracies": 0.612500011920929,
|
| 426 |
+
"rewards/chosen": -0.41321054100990295,
|
| 427 |
+
"rewards/margins": 0.27371519804000854,
|
| 428 |
+
"rewards/rejected": -0.6869257092475891,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.96,
|
| 433 |
+
"learning_rate": 2.262559558016325e-08,
|
| 434 |
+
"logits/chosen": -0.13833969831466675,
|
| 435 |
+
"logits/rejected": -0.14348629117012024,
|
| 436 |
+
"logps/chosen": -808.810791015625,
|
| 437 |
+
"logps/rejected": -1050.609619140625,
|
| 438 |
+
"loss": 1.6973,
|
| 439 |
+
"rewards/accuracies": 0.637499988079071,
|
| 440 |
+
"rewards/chosen": -0.40211352705955505,
|
| 441 |
+
"rewards/margins": 0.259845107793808,
|
| 442 |
+
"rewards/rejected": -0.6619586944580078,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.99,
|
| 447 |
+
"learning_rate": 6.294126437336734e-10,
|
| 448 |
+
"logits/chosen": -0.18316778540611267,
|
| 449 |
+
"logits/rejected": -0.11073551326990128,
|
| 450 |
+
"logps/chosen": -916.8952026367188,
|
| 451 |
+
"logps/rejected": -1118.8402099609375,
|
| 452 |
+
"loss": 1.7781,
|
| 453 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 454 |
+
"rewards/chosen": -0.47190985083580017,
|
| 455 |
+
"rewards/margins": 0.21381942927837372,
|
| 456 |
+
"rewards/rejected": -0.6857293248176575,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.0,
|
| 461 |
+
"step": 312,
|
| 462 |
+
"total_flos": 0.0,
|
| 463 |
+
"train_loss": 1.8545298270690136,
|
| 464 |
+
"train_runtime": 4214.6598,
|
| 465 |
+
"train_samples_per_second": 3.559,
|
| 466 |
+
"train_steps_per_second": 0.074
|
| 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 |
+
}
|