Qin Liu
commited on
Commit
•
ba0be3a
1
Parent(s):
f4e9f32
Model save
Browse files- README.md +62 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +612 -0
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 9 |
+
model-index:
|
| 10 |
+
- name: llama3-sudo-dpo-instruct-2epochs-jxkey-system
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# llama3-sudo-dpo-instruct-2epochs-jxkey-system
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- total_eval_batch_size: 64
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 2
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- PEFT 0.12.0
|
| 59 |
+
- Transformers 4.44.0
|
| 60 |
+
- Pytorch 2.1.2
|
| 61 |
+
- Datasets 3.0.0
|
| 62 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9946666666666668,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 0.07791340151829097,
|
| 5 |
+
"train_runtime": 6908.9348,
|
| 6 |
+
"train_samples": 12000,
|
| 7 |
+
"train_samples_per_second": 3.474,
|
| 8 |
+
"train_steps_per_second": 0.054
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9946666666666668,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 0.07791340151829097,
|
| 5 |
+
"train_runtime": 6908.9348,
|
| 6 |
+
"train_samples": 12000,
|
| 7 |
+
"train_samples_per_second": 3.474,
|
| 8 |
+
"train_steps_per_second": 0.054
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,612 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9946666666666668,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 374,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005333333333333333,
|
| 13 |
+
"grad_norm": 0.5672486208114706,
|
| 14 |
+
"learning_rate": 1.3157894736842107e-07,
|
| 15 |
+
"logits/chosen": -0.9279001951217651,
|
| 16 |
+
"logits/rejected": -0.858139157295227,
|
| 17 |
+
"logps/chosen": -227.95245361328125,
|
| 18 |
+
"logps/rejected": -298.680908203125,
|
| 19 |
+
"loss": 0.6931,
|
| 20 |
+
"rewards/accuracies": 0.0,
|
| 21 |
+
"rewards/chosen": 0.0,
|
| 22 |
+
"rewards/margins": 0.0,
|
| 23 |
+
"rewards/rejected": 0.0,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05333333333333334,
|
| 28 |
+
"grad_norm": 0.627338544388044,
|
| 29 |
+
"learning_rate": 1.3157894736842106e-06,
|
| 30 |
+
"logits/chosen": -1.0396056175231934,
|
| 31 |
+
"logits/rejected": -1.0286777019500732,
|
| 32 |
+
"logps/chosen": -272.0198974609375,
|
| 33 |
+
"logps/rejected": -275.8685302734375,
|
| 34 |
+
"loss": 0.693,
|
| 35 |
+
"rewards/accuracies": 0.5416666865348816,
|
| 36 |
+
"rewards/chosen": 0.0009284570114687085,
|
| 37 |
+
"rewards/margins": 0.001860518823377788,
|
| 38 |
+
"rewards/rejected": -0.0009320618119090796,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.10666666666666667,
|
| 43 |
+
"grad_norm": 0.6142473047006762,
|
| 44 |
+
"learning_rate": 2.631578947368421e-06,
|
| 45 |
+
"logits/chosen": -0.9923893809318542,
|
| 46 |
+
"logits/rejected": -1.010837197303772,
|
| 47 |
+
"logps/chosen": -281.47979736328125,
|
| 48 |
+
"logps/rejected": -268.1535949707031,
|
| 49 |
+
"loss": 0.6876,
|
| 50 |
+
"rewards/accuracies": 0.824999988079071,
|
| 51 |
+
"rewards/chosen": 0.006842092610895634,
|
| 52 |
+
"rewards/margins": 0.010892460122704506,
|
| 53 |
+
"rewards/rejected": -0.0040503679774701595,
|
| 54 |
+
"step": 20
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.16,
|
| 58 |
+
"grad_norm": 0.7939072580410426,
|
| 59 |
+
"learning_rate": 3.947368421052632e-06,
|
| 60 |
+
"logits/chosen": -1.0665647983551025,
|
| 61 |
+
"logits/rejected": -1.030176043510437,
|
| 62 |
+
"logps/chosen": -265.56134033203125,
|
| 63 |
+
"logps/rejected": -276.7889404296875,
|
| 64 |
+
"loss": 0.658,
|
| 65 |
+
"rewards/accuracies": 1.0,
|
| 66 |
+
"rewards/chosen": 0.03331710770726204,
|
| 67 |
+
"rewards/margins": 0.06989365816116333,
|
| 68 |
+
"rewards/rejected": -0.03657654672861099,
|
| 69 |
+
"step": 30
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.21333333333333335,
|
| 73 |
+
"grad_norm": 1.582486884512004,
|
| 74 |
+
"learning_rate": 4.999562902281866e-06,
|
| 75 |
+
"logits/chosen": -1.0957633256912231,
|
| 76 |
+
"logits/rejected": -1.0948419570922852,
|
| 77 |
+
"logps/chosen": -266.51983642578125,
|
| 78 |
+
"logps/rejected": -322.9562072753906,
|
| 79 |
+
"loss": 0.5339,
|
| 80 |
+
"rewards/accuracies": 1.0,
|
| 81 |
+
"rewards/chosen": 0.11751838773488998,
|
| 82 |
+
"rewards/margins": 0.3626277446746826,
|
| 83 |
+
"rewards/rejected": -0.24510934948921204,
|
| 84 |
+
"step": 40
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.26666666666666666,
|
| 88 |
+
"grad_norm": 0.8169663169771063,
|
| 89 |
+
"learning_rate": 4.984280524733107e-06,
|
| 90 |
+
"logits/chosen": -1.1005247831344604,
|
| 91 |
+
"logits/rejected": -1.1034621000289917,
|
| 92 |
+
"logps/chosen": -270.61724853515625,
|
| 93 |
+
"logps/rejected": -416.21142578125,
|
| 94 |
+
"loss": 0.2383,
|
| 95 |
+
"rewards/accuracies": 1.0,
|
| 96 |
+
"rewards/chosen": 0.15088006854057312,
|
| 97 |
+
"rewards/margins": 1.5602823495864868,
|
| 98 |
+
"rewards/rejected": -1.4094021320343018,
|
| 99 |
+
"step": 50
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.32,
|
| 103 |
+
"grad_norm": 0.3705635446867794,
|
| 104 |
+
"learning_rate": 4.947295864744121e-06,
|
| 105 |
+
"logits/chosen": -1.1092312335968018,
|
| 106 |
+
"logits/rejected": -1.0661927461624146,
|
| 107 |
+
"logps/chosen": -294.2104797363281,
|
| 108 |
+
"logps/rejected": -600.4303588867188,
|
| 109 |
+
"loss": 0.0671,
|
| 110 |
+
"rewards/accuracies": 1.0,
|
| 111 |
+
"rewards/chosen": 0.08243656903505325,
|
| 112 |
+
"rewards/margins": 3.372529983520508,
|
| 113 |
+
"rewards/rejected": -3.2900936603546143,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.37333333333333335,
|
| 118 |
+
"grad_norm": 0.09049040384751605,
|
| 119 |
+
"learning_rate": 4.8889320144653525e-06,
|
| 120 |
+
"logits/chosen": -1.0999512672424316,
|
| 121 |
+
"logits/rejected": -0.9580685496330261,
|
| 122 |
+
"logps/chosen": -330.55194091796875,
|
| 123 |
+
"logps/rejected": -985.8513793945312,
|
| 124 |
+
"loss": 0.0161,
|
| 125 |
+
"rewards/accuracies": 1.0,
|
| 126 |
+
"rewards/chosen": -0.5064759254455566,
|
| 127 |
+
"rewards/margins": 6.231157302856445,
|
| 128 |
+
"rewards/rejected": -6.73763370513916,
|
| 129 |
+
"step": 70
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4266666666666667,
|
| 133 |
+
"grad_norm": 0.03915438076032923,
|
| 134 |
+
"learning_rate": 4.809698831278217e-06,
|
| 135 |
+
"logits/chosen": -0.9111706018447876,
|
| 136 |
+
"logits/rejected": -0.7140064835548401,
|
| 137 |
+
"logps/chosen": -339.89349365234375,
|
| 138 |
+
"logps/rejected": -1143.648681640625,
|
| 139 |
+
"loss": 0.0051,
|
| 140 |
+
"rewards/accuracies": 1.0,
|
| 141 |
+
"rewards/chosen": -0.66388338804245,
|
| 142 |
+
"rewards/margins": 7.908216953277588,
|
| 143 |
+
"rewards/rejected": -8.572099685668945,
|
| 144 |
+
"step": 80
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.48,
|
| 148 |
+
"grad_norm": 0.14297159038439752,
|
| 149 |
+
"learning_rate": 4.710288483761524e-06,
|
| 150 |
+
"logits/chosen": -0.8663455247879028,
|
| 151 |
+
"logits/rejected": -0.5593339800834656,
|
| 152 |
+
"logps/chosen": -336.32037353515625,
|
| 153 |
+
"logps/rejected": -1434.2740478515625,
|
| 154 |
+
"loss": 0.0022,
|
| 155 |
+
"rewards/accuracies": 1.0,
|
| 156 |
+
"rewards/chosen": -0.8545030355453491,
|
| 157 |
+
"rewards/margins": 10.544784545898438,
|
| 158 |
+
"rewards/rejected": -11.399286270141602,
|
| 159 |
+
"step": 90
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.5333333333333333,
|
| 163 |
+
"grad_norm": 0.040959450492445315,
|
| 164 |
+
"learning_rate": 4.59156940501605e-06,
|
| 165 |
+
"logits/chosen": -0.9001060724258423,
|
| 166 |
+
"logits/rejected": -0.6381432414054871,
|
| 167 |
+
"logps/chosen": -347.5130310058594,
|
| 168 |
+
"logps/rejected": -1511.1595458984375,
|
| 169 |
+
"loss": 0.0013,
|
| 170 |
+
"rewards/accuracies": 1.0,
|
| 171 |
+
"rewards/chosen": -0.7411862015724182,
|
| 172 |
+
"rewards/margins": 11.320222854614258,
|
| 173 |
+
"rewards/rejected": -12.061409950256348,
|
| 174 |
+
"step": 100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.5866666666666667,
|
| 178 |
+
"grad_norm": 0.010465140313811594,
|
| 179 |
+
"learning_rate": 4.454578706170075e-06,
|
| 180 |
+
"logits/chosen": -0.8447334170341492,
|
| 181 |
+
"logits/rejected": -0.5461128950119019,
|
| 182 |
+
"logps/chosen": -324.555908203125,
|
| 183 |
+
"logps/rejected": -1563.4332275390625,
|
| 184 |
+
"loss": 0.0009,
|
| 185 |
+
"rewards/accuracies": 1.0,
|
| 186 |
+
"rewards/chosen": -0.7364819645881653,
|
| 187 |
+
"rewards/margins": 11.867830276489258,
|
| 188 |
+
"rewards/rejected": -12.604310989379883,
|
| 189 |
+
"step": 110
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.64,
|
| 193 |
+
"grad_norm": 0.018698800124617214,
|
| 194 |
+
"learning_rate": 4.300513116340317e-06,
|
| 195 |
+
"logits/chosen": -0.869040846824646,
|
| 196 |
+
"logits/rejected": -0.6451767086982727,
|
| 197 |
+
"logps/chosen": -368.4622497558594,
|
| 198 |
+
"logps/rejected": -1524.347412109375,
|
| 199 |
+
"loss": 0.0013,
|
| 200 |
+
"rewards/accuracies": 1.0,
|
| 201 |
+
"rewards/chosen": -0.5922040939331055,
|
| 202 |
+
"rewards/margins": 11.815667152404785,
|
| 203 |
+
"rewards/rejected": -12.407870292663574,
|
| 204 |
+
"step": 120
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.6933333333333334,
|
| 208 |
+
"grad_norm": 0.13074428382691303,
|
| 209 |
+
"learning_rate": 4.130718528195303e-06,
|
| 210 |
+
"logits/chosen": -0.7969690561294556,
|
| 211 |
+
"logits/rejected": -0.5475348234176636,
|
| 212 |
+
"logps/chosen": -344.4666442871094,
|
| 213 |
+
"logps/rejected": -1474.3719482421875,
|
| 214 |
+
"loss": 0.0011,
|
| 215 |
+
"rewards/accuracies": 1.0,
|
| 216 |
+
"rewards/chosen": -0.5560614466667175,
|
| 217 |
+
"rewards/margins": 11.487146377563477,
|
| 218 |
+
"rewards/rejected": -12.043208122253418,
|
| 219 |
+
"step": 130
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7466666666666667,
|
| 223 |
+
"grad_norm": 0.007599436316894573,
|
| 224 |
+
"learning_rate": 3.946678240449515e-06,
|
| 225 |
+
"logits/chosen": -0.8450958132743835,
|
| 226 |
+
"logits/rejected": -0.6068762540817261,
|
| 227 |
+
"logps/chosen": -330.353271484375,
|
| 228 |
+
"logps/rejected": -1493.345947265625,
|
| 229 |
+
"loss": 0.0005,
|
| 230 |
+
"rewards/accuracies": 1.0,
|
| 231 |
+
"rewards/chosen": -0.6169044375419617,
|
| 232 |
+
"rewards/margins": 11.569721221923828,
|
| 233 |
+
"rewards/rejected": -12.186625480651855,
|
| 234 |
+
"step": 140
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.8,
|
| 238 |
+
"grad_norm": 0.007906481570741206,
|
| 239 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 240 |
+
"logits/chosen": -0.7317169308662415,
|
| 241 |
+
"logits/rejected": -0.472684770822525,
|
| 242 |
+
"logps/chosen": -334.15936279296875,
|
| 243 |
+
"logps/rejected": -1581.9859619140625,
|
| 244 |
+
"loss": 0.0005,
|
| 245 |
+
"rewards/accuracies": 1.0,
|
| 246 |
+
"rewards/chosen": -0.6376131176948547,
|
| 247 |
+
"rewards/margins": 12.395392417907715,
|
| 248 |
+
"rewards/rejected": -13.03300666809082,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.8533333333333334,
|
| 253 |
+
"grad_norm": 0.005373942509470849,
|
| 254 |
+
"learning_rate": 3.542401956903321e-06,
|
| 255 |
+
"logits/chosen": -0.802183985710144,
|
| 256 |
+
"logits/rejected": -0.517475962638855,
|
| 257 |
+
"logps/chosen": -346.039306640625,
|
| 258 |
+
"logps/rejected": -1731.537841796875,
|
| 259 |
+
"loss": 0.0005,
|
| 260 |
+
"rewards/accuracies": 1.0,
|
| 261 |
+
"rewards/chosen": -0.6884077787399292,
|
| 262 |
+
"rewards/margins": 13.671854972839355,
|
| 263 |
+
"rewards/rejected": -14.360262870788574,
|
| 264 |
+
"step": 160
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.9066666666666666,
|
| 268 |
+
"grad_norm": 0.006855807463409515,
|
| 269 |
+
"learning_rate": 3.3256976548879183e-06,
|
| 270 |
+
"logits/chosen": -0.7976305484771729,
|
| 271 |
+
"logits/rejected": -0.48461779952049255,
|
| 272 |
+
"logps/chosen": -332.21539306640625,
|
| 273 |
+
"logps/rejected": -1720.519775390625,
|
| 274 |
+
"loss": 0.0003,
|
| 275 |
+
"rewards/accuracies": 1.0,
|
| 276 |
+
"rewards/chosen": -0.6103914380073547,
|
| 277 |
+
"rewards/margins": 13.717634201049805,
|
| 278 |
+
"rewards/rejected": -14.328027725219727,
|
| 279 |
+
"step": 170
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.96,
|
| 283 |
+
"grad_norm": 0.006530794838523059,
|
| 284 |
+
"learning_rate": 3.1017801885224332e-06,
|
| 285 |
+
"logits/chosen": -0.8089723587036133,
|
| 286 |
+
"logits/rejected": -0.547804594039917,
|
| 287 |
+
"logps/chosen": -331.06561279296875,
|
| 288 |
+
"logps/rejected": -1655.431640625,
|
| 289 |
+
"loss": 0.0003,
|
| 290 |
+
"rewards/accuracies": 1.0,
|
| 291 |
+
"rewards/chosen": -0.4778788685798645,
|
| 292 |
+
"rewards/margins": 13.217842102050781,
|
| 293 |
+
"rewards/rejected": -13.695721626281738,
|
| 294 |
+
"step": 180
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.0133333333333334,
|
| 298 |
+
"grad_norm": 0.002402189687585693,
|
| 299 |
+
"learning_rate": 2.872605665440436e-06,
|
| 300 |
+
"logits/chosen": -0.8274615406990051,
|
| 301 |
+
"logits/rejected": -0.6256132125854492,
|
| 302 |
+
"logps/chosen": -343.0153503417969,
|
| 303 |
+
"logps/rejected": -1610.4468994140625,
|
| 304 |
+
"loss": 0.0003,
|
| 305 |
+
"rewards/accuracies": 1.0,
|
| 306 |
+
"rewards/chosen": -0.47418123483657837,
|
| 307 |
+
"rewards/margins": 12.88371753692627,
|
| 308 |
+
"rewards/rejected": -13.357897758483887,
|
| 309 |
+
"step": 190
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.0666666666666667,
|
| 313 |
+
"grad_norm": 0.0030571071844198616,
|
| 314 |
+
"learning_rate": 2.6401761180929798e-06,
|
| 315 |
+
"logits/chosen": -0.8143685460090637,
|
| 316 |
+
"logits/rejected": -0.5041629076004028,
|
| 317 |
+
"logps/chosen": -334.1429138183594,
|
| 318 |
+
"logps/rejected": -1818.0869140625,
|
| 319 |
+
"loss": 0.0005,
|
| 320 |
+
"rewards/accuracies": 1.0,
|
| 321 |
+
"rewards/chosen": -0.558273434638977,
|
| 322 |
+
"rewards/margins": 14.656936645507812,
|
| 323 |
+
"rewards/rejected": -15.2152099609375,
|
| 324 |
+
"step": 200
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.12,
|
| 328 |
+
"grad_norm": 0.00820790094406569,
|
| 329 |
+
"learning_rate": 2.4065220143091863e-06,
|
| 330 |
+
"logits/chosen": -0.8139235377311707,
|
| 331 |
+
"logits/rejected": -0.564848780632019,
|
| 332 |
+
"logps/chosen": -345.9544982910156,
|
| 333 |
+
"logps/rejected": -1764.953125,
|
| 334 |
+
"loss": 0.0004,
|
| 335 |
+
"rewards/accuracies": 1.0,
|
| 336 |
+
"rewards/chosen": -0.475874662399292,
|
| 337 |
+
"rewards/margins": 14.230936050415039,
|
| 338 |
+
"rewards/rejected": -14.706808090209961,
|
| 339 |
+
"step": 210
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.1733333333333333,
|
| 343 |
+
"grad_norm": 0.0043868434266810755,
|
| 344 |
+
"learning_rate": 2.173684519449872e-06,
|
| 345 |
+
"logits/chosen": -0.7210798263549805,
|
| 346 |
+
"logits/rejected": -0.36144906282424927,
|
| 347 |
+
"logps/chosen": -327.31622314453125,
|
| 348 |
+
"logps/rejected": -1841.2216796875,
|
| 349 |
+
"loss": 0.0004,
|
| 350 |
+
"rewards/accuracies": 1.0,
|
| 351 |
+
"rewards/chosen": -0.6532616019248962,
|
| 352 |
+
"rewards/margins": 14.736944198608398,
|
| 353 |
+
"rewards/rejected": -15.39020824432373,
|
| 354 |
+
"step": 220
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.2266666666666666,
|
| 358 |
+
"grad_norm": 0.0068525897764614785,
|
| 359 |
+
"learning_rate": 1.9436976651092143e-06,
|
| 360 |
+
"logits/chosen": -0.7221536636352539,
|
| 361 |
+
"logits/rejected": -0.5240283012390137,
|
| 362 |
+
"logps/chosen": -350.7161865234375,
|
| 363 |
+
"logps/rejected": -1619.64599609375,
|
| 364 |
+
"loss": 0.0002,
|
| 365 |
+
"rewards/accuracies": 1.0,
|
| 366 |
+
"rewards/chosen": -0.45207110047340393,
|
| 367 |
+
"rewards/margins": 13.1558198928833,
|
| 368 |
+
"rewards/rejected": -13.607892990112305,
|
| 369 |
+
"step": 230
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.28,
|
| 373 |
+
"grad_norm": 0.0033954692926207583,
|
| 374 |
+
"learning_rate": 1.7185705801358892e-06,
|
| 375 |
+
"logits/chosen": -0.8645750880241394,
|
| 376 |
+
"logits/rejected": -0.6266194581985474,
|
| 377 |
+
"logps/chosen": -343.2956848144531,
|
| 378 |
+
"logps/rejected": -1709.9945068359375,
|
| 379 |
+
"loss": 0.0002,
|
| 380 |
+
"rewards/accuracies": 1.0,
|
| 381 |
+
"rewards/chosen": -0.46298861503601074,
|
| 382 |
+
"rewards/margins": 13.744463920593262,
|
| 383 |
+
"rewards/rejected": -14.2074556350708,
|
| 384 |
+
"step": 240
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.3333333333333333,
|
| 388 |
+
"grad_norm": 0.008787649845585386,
|
| 389 |
+
"learning_rate": 1.500269939200648e-06,
|
| 390 |
+
"logits/chosen": -0.7889136075973511,
|
| 391 |
+
"logits/rejected": -0.5392887592315674,
|
| 392 |
+
"logps/chosen": -342.34405517578125,
|
| 393 |
+
"logps/rejected": -1703.201171875,
|
| 394 |
+
"loss": 0.0003,
|
| 395 |
+
"rewards/accuracies": 1.0,
|
| 396 |
+
"rewards/chosen": -0.380669504404068,
|
| 397 |
+
"rewards/margins": 13.953561782836914,
|
| 398 |
+
"rewards/rejected": -14.334230422973633,
|
| 399 |
+
"step": 250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.3866666666666667,
|
| 403 |
+
"grad_norm": 0.0019219492245800027,
|
| 404 |
+
"learning_rate": 1.2907027822369006e-06,
|
| 405 |
+
"logits/chosen": -0.8140700459480286,
|
| 406 |
+
"logits/rejected": -0.5784817337989807,
|
| 407 |
+
"logps/chosen": -325.9125061035156,
|
| 408 |
+
"logps/rejected": -1678.7923583984375,
|
| 409 |
+
"loss": 0.0002,
|
| 410 |
+
"rewards/accuracies": 1.0,
|
| 411 |
+
"rewards/chosen": -0.44779616594314575,
|
| 412 |
+
"rewards/margins": 13.65271282196045,
|
| 413 |
+
"rewards/rejected": -14.100509643554688,
|
| 414 |
+
"step": 260
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.44,
|
| 418 |
+
"grad_norm": 0.0029707873083702468,
|
| 419 |
+
"learning_rate": 1.0916998548409449e-06,
|
| 420 |
+
"logits/chosen": -0.7845500111579895,
|
| 421 |
+
"logits/rejected": -0.5012301206588745,
|
| 422 |
+
"logps/chosen": -358.30419921875,
|
| 423 |
+
"logps/rejected": -1745.314697265625,
|
| 424 |
+
"loss": 0.0003,
|
| 425 |
+
"rewards/accuracies": 1.0,
|
| 426 |
+
"rewards/chosen": -0.6766600608825684,
|
| 427 |
+
"rewards/margins": 13.99413013458252,
|
| 428 |
+
"rewards/rejected": -14.67078971862793,
|
| 429 |
+
"step": 270
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.4933333333333334,
|
| 433 |
+
"grad_norm": 0.003009319728743961,
|
| 434 |
+
"learning_rate": 9.04999615167479e-07,
|
| 435 |
+
"logits/chosen": -0.8230724334716797,
|
| 436 |
+
"logits/rejected": -0.550376832485199,
|
| 437 |
+
"logps/chosen": -346.7623596191406,
|
| 438 |
+
"logps/rejected": -1745.7318115234375,
|
| 439 |
+
"loss": 0.0001,
|
| 440 |
+
"rewards/accuracies": 1.0,
|
| 441 |
+
"rewards/chosen": -0.5431645512580872,
|
| 442 |
+
"rewards/margins": 14.117253303527832,
|
| 443 |
+
"rewards/rejected": -14.660417556762695,
|
| 444 |
+
"step": 280
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.5466666666666666,
|
| 448 |
+
"grad_norm": 0.05446004244419421,
|
| 449 |
+
"learning_rate": 7.322330470336314e-07,
|
| 450 |
+
"logits/chosen": -0.8042120933532715,
|
| 451 |
+
"logits/rejected": -0.4271600842475891,
|
| 452 |
+
"logps/chosen": -319.5382080078125,
|
| 453 |
+
"logps/rejected": -1869.0816650390625,
|
| 454 |
+
"loss": 0.0003,
|
| 455 |
+
"rewards/accuracies": 1.0,
|
| 456 |
+
"rewards/chosen": -0.6211446523666382,
|
| 457 |
+
"rewards/margins": 15.130853652954102,
|
| 458 |
+
"rewards/rejected": -15.751996994018555,
|
| 459 |
+
"step": 290
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.6,
|
| 463 |
+
"grad_norm": 0.0026251482158599366,
|
| 464 |
+
"learning_rate": 5.749094119018431e-07,
|
| 465 |
+
"logits/chosen": -0.8732158541679382,
|
| 466 |
+
"logits/rejected": -0.5424922704696655,
|
| 467 |
+
"logps/chosen": -324.2518005371094,
|
| 468 |
+
"logps/rejected": -1899.756591796875,
|
| 469 |
+
"loss": 0.0003,
|
| 470 |
+
"rewards/accuracies": 1.0,
|
| 471 |
+
"rewards/chosen": -0.514877438545227,
|
| 472 |
+
"rewards/margins": 15.413823127746582,
|
| 473 |
+
"rewards/rejected": -15.928703308105469,
|
| 474 |
+
"step": 300
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.6533333333333333,
|
| 478 |
+
"grad_norm": 0.0023975764198324104,
|
| 479 |
+
"learning_rate": 4.344030642100133e-07,
|
| 480 |
+
"logits/chosen": -0.8402504920959473,
|
| 481 |
+
"logits/rejected": -0.5483088493347168,
|
| 482 |
+
"logps/chosen": -330.42828369140625,
|
| 483 |
+
"logps/rejected": -1794.327392578125,
|
| 484 |
+
"loss": 0.0002,
|
| 485 |
+
"rewards/accuracies": 1.0,
|
| 486 |
+
"rewards/chosen": -0.4678085446357727,
|
| 487 |
+
"rewards/margins": 14.648382186889648,
|
| 488 |
+
"rewards/rejected": -15.116189956665039,
|
| 489 |
+
"step": 310
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.7066666666666666,
|
| 493 |
+
"grad_norm": 0.0028734478026904357,
|
| 494 |
+
"learning_rate": 3.119414452281158e-07,
|
| 495 |
+
"logits/chosen": -0.8355986475944519,
|
| 496 |
+
"logits/rejected": -0.5001510977745056,
|
| 497 |
+
"logps/chosen": -328.2898254394531,
|
| 498 |
+
"logps/rejected": -1902.9224853515625,
|
| 499 |
+
"loss": 0.0003,
|
| 500 |
+
"rewards/accuracies": 1.0,
|
| 501 |
+
"rewards/chosen": -0.504935622215271,
|
| 502 |
+
"rewards/margins": 15.536231994628906,
|
| 503 |
+
"rewards/rejected": -16.041166305541992,
|
| 504 |
+
"step": 320
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.76,
|
| 508 |
+
"grad_norm": 0.002690221439778056,
|
| 509 |
+
"learning_rate": 2.0859436032505954e-07,
|
| 510 |
+
"logits/chosen": -0.896633505821228,
|
| 511 |
+
"logits/rejected": -0.6399273872375488,
|
| 512 |
+
"logps/chosen": -357.3143615722656,
|
| 513 |
+
"logps/rejected": -1739.0318603515625,
|
| 514 |
+
"loss": 0.0007,
|
| 515 |
+
"rewards/accuracies": 1.0,
|
| 516 |
+
"rewards/chosen": -0.39237022399902344,
|
| 517 |
+
"rewards/margins": 14.242953300476074,
|
| 518 |
+
"rewards/rejected": -14.635324478149414,
|
| 519 |
+
"step": 330
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.8133333333333335,
|
| 523 |
+
"grad_norm": 0.002170040138657762,
|
| 524 |
+
"learning_rate": 1.2526463331788503e-07,
|
| 525 |
+
"logits/chosen": -0.847479522228241,
|
| 526 |
+
"logits/rejected": -0.6152299642562866,
|
| 527 |
+
"logps/chosen": -348.79742431640625,
|
| 528 |
+
"logps/rejected": -1842.7880859375,
|
| 529 |
+
"loss": 0.0002,
|
| 530 |
+
"rewards/accuracies": 1.0,
|
| 531 |
+
"rewards/chosen": -0.48484006524086,
|
| 532 |
+
"rewards/margins": 15.058262825012207,
|
| 533 |
+
"rewards/rejected": -15.54310131072998,
|
| 534 |
+
"step": 340
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.8666666666666667,
|
| 538 |
+
"grad_norm": 0.003300394252196583,
|
| 539 |
+
"learning_rate": 6.268021954544095e-08,
|
| 540 |
+
"logits/chosen": -0.8356849551200867,
|
| 541 |
+
"logits/rejected": -0.4748550355434418,
|
| 542 |
+
"logps/chosen": -336.01373291015625,
|
| 543 |
+
"logps/rejected": -1930.8939208984375,
|
| 544 |
+
"loss": 0.0002,
|
| 545 |
+
"rewards/accuracies": 1.0,
|
| 546 |
+
"rewards/chosen": -0.5835164785385132,
|
| 547 |
+
"rewards/margins": 15.679295539855957,
|
| 548 |
+
"rewards/rejected": -16.2628116607666,
|
| 549 |
+
"step": 350
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.92,
|
| 553 |
+
"grad_norm": 0.0026600066446259086,
|
| 554 |
+
"learning_rate": 2.1387846565474047e-08,
|
| 555 |
+
"logits/chosen": -0.8271343111991882,
|
| 556 |
+
"logits/rejected": -0.5607911348342896,
|
| 557 |
+
"logps/chosen": -359.8587341308594,
|
| 558 |
+
"logps/rejected": -1746.127685546875,
|
| 559 |
+
"loss": 0.0002,
|
| 560 |
+
"rewards/accuracies": 1.0,
|
| 561 |
+
"rewards/chosen": -0.4917505383491516,
|
| 562 |
+
"rewards/margins": 14.259208679199219,
|
| 563 |
+
"rewards/rejected": -14.750958442687988,
|
| 564 |
+
"step": 360
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.9733333333333334,
|
| 568 |
+
"grad_norm": 0.014374372097938156,
|
| 569 |
+
"learning_rate": 1.7482380290034795e-09,
|
| 570 |
+
"logits/chosen": -0.807357668876648,
|
| 571 |
+
"logits/rejected": -0.4851298928260803,
|
| 572 |
+
"logps/chosen": -321.13861083984375,
|
| 573 |
+
"logps/rejected": -1839.5152587890625,
|
| 574 |
+
"loss": 0.0004,
|
| 575 |
+
"rewards/accuracies": 1.0,
|
| 576 |
+
"rewards/chosen": -0.5102803111076355,
|
| 577 |
+
"rewards/margins": 15.034269332885742,
|
| 578 |
+
"rewards/rejected": -15.544550895690918,
|
| 579 |
+
"step": 370
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.9946666666666668,
|
| 583 |
+
"step": 374,
|
| 584 |
+
"total_flos": 0.0,
|
| 585 |
+
"train_loss": 0.07791340151829097,
|
| 586 |
+
"train_runtime": 6908.9348,
|
| 587 |
+
"train_samples_per_second": 3.474,
|
| 588 |
+
"train_steps_per_second": 0.054
|
| 589 |
+
}
|
| 590 |
+
],
|
| 591 |
+
"logging_steps": 10,
|
| 592 |
+
"max_steps": 374,
|
| 593 |
+
"num_input_tokens_seen": 0,
|
| 594 |
+
"num_train_epochs": 2,
|
| 595 |
+
"save_steps": 1000,
|
| 596 |
+
"stateful_callbacks": {
|
| 597 |
+
"TrainerControl": {
|
| 598 |
+
"args": {
|
| 599 |
+
"should_epoch_stop": false,
|
| 600 |
+
"should_evaluate": false,
|
| 601 |
+
"should_log": false,
|
| 602 |
+
"should_save": true,
|
| 603 |
+
"should_training_stop": true
|
| 604 |
+
},
|
| 605 |
+
"attributes": {}
|
| 606 |
+
}
|
| 607 |
+
},
|
| 608 |
+
"total_flos": 0.0,
|
| 609 |
+
"train_batch_size": 2,
|
| 610 |
+
"trial_name": null,
|
| 611 |
+
"trial_params": null
|
| 612 |
+
}
|