Commit
•
0caa5c2
1
Parent(s):
daac5da
Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- emissions.csv +2 -0
- runs/Sep15_00-06-33_gpu4-119-5/events.out.tfevents.1726322902.gpu4-119-5.437117.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +912 -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-ipo-chatml-merged
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-ipo-chatml-lora-20k-40k-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-ipo-chatml-lora-20k-40k-i1
|
| 17 |
+
|
| 18 |
+
This model was trained from scratch 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
|
| 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 sha256:571d5cfc8101b762c3d9c66008b7d17e4763c3a3cfdbe46be581d21c5d91ff6f
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 217680.7002,
|
| 4 |
+
"train_runtime": 7796.5816,
|
| 5 |
+
"train_samples": 20000,
|
| 6 |
+
"train_samples_per_second": 2.565,
|
| 7 |
+
"train_steps_per_second": 0.08
|
| 8 |
+
}
|
emissions.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
| 2 |
+
2024-09-15T02:18:18,codecarbon,6932c5fd-2281-42ad-9c4c-287760607485,7796.617893218994,0.006349305992029156,8.143667009193026e-07,42.5,963.3670000000001,188.74309015274048,0.09204223800930707,2.171054235514721,0.4078004620693191,2.670896935593349,Canada,CAN,quebec,,,Linux-5.15.0-84-generic-x86_64-with-glibc2.35,3.10.14,2.2.3,32,Intel(R) Xeon(R) W-3335 CPU @ 3.40GHz,4,4 x NVIDIA GeForce RTX 4090,-71.2,46.8,503.3149070739746,machine,N,1.0
|
runs/Sep15_00-06-33_gpu4-119-5/events.out.tfevents.1726322902.gpu4-119-5.437117.0
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 sha256:2d7468d5244cf7ca84ba0c789f2f8bad908c75fc9f6180903a0bd152e29b0a1a
|
| 3 |
+
size 45099
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 217680.7002,
|
| 4 |
+
"train_runtime": 7796.5816,
|
| 5 |
+
"train_samples": 20000,
|
| 6 |
+
"train_samples_per_second": 2.565,
|
| 7 |
+
"train_steps_per_second": 0.08
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,912 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 625,
|
| 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": 7.936507936507937e-08,
|
| 14 |
+
"logits/chosen": 0.9578127264976501,
|
| 15 |
+
"logits/rejected": 0.7914565801620483,
|
| 16 |
+
"logps/chosen": -360.49114990234375,
|
| 17 |
+
"logps/rejected": -309.01898193359375,
|
| 18 |
+
"loss": 250000.0,
|
| 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": 0.02,
|
| 27 |
+
"learning_rate": 7.936507936507937e-07,
|
| 28 |
+
"logits/chosen": 0.7728305459022522,
|
| 29 |
+
"logits/rejected": 0.768233597278595,
|
| 30 |
+
"logps/chosen": -306.1025390625,
|
| 31 |
+
"logps/rejected": -277.5509338378906,
|
| 32 |
+
"loss": 249993.8889,
|
| 33 |
+
"rewards/accuracies": 0.2986111044883728,
|
| 34 |
+
"rewards/chosen": -5.4183616157388315e-05,
|
| 35 |
+
"rewards/margins": -3.124285285593942e-05,
|
| 36 |
+
"rewards/rejected": -2.29407651204383e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03,
|
| 41 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 42 |
+
"logits/chosen": 0.7892485857009888,
|
| 43 |
+
"logits/rejected": 0.8077142834663391,
|
| 44 |
+
"logps/chosen": -343.6685791015625,
|
| 45 |
+
"logps/rejected": -315.8797912597656,
|
| 46 |
+
"loss": 249850.3,
|
| 47 |
+
"rewards/accuracies": 0.550000011920929,
|
| 48 |
+
"rewards/chosen": -0.0003508512454573065,
|
| 49 |
+
"rewards/margins": 0.0002387135464232415,
|
| 50 |
+
"rewards/rejected": -0.0005895647336728871,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 2.380952380952381e-06,
|
| 56 |
+
"logits/chosen": 0.7931613922119141,
|
| 57 |
+
"logits/rejected": 0.856336236000061,
|
| 58 |
+
"logps/chosen": -329.352294921875,
|
| 59 |
+
"logps/rejected": -310.99786376953125,
|
| 60 |
+
"loss": 249686.05,
|
| 61 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 62 |
+
"rewards/chosen": -0.0014547129394486547,
|
| 63 |
+
"rewards/margins": 0.00029922794783487916,
|
| 64 |
+
"rewards/rejected": -0.001753940829075873,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06,
|
| 69 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 70 |
+
"logits/chosen": 0.8100332021713257,
|
| 71 |
+
"logits/rejected": 0.7524169087409973,
|
| 72 |
+
"logps/chosen": -318.7286071777344,
|
| 73 |
+
"logps/rejected": -312.85418701171875,
|
| 74 |
+
"loss": 249475.5,
|
| 75 |
+
"rewards/accuracies": 0.5,
|
| 76 |
+
"rewards/chosen": -0.003864737693220377,
|
| 77 |
+
"rewards/margins": 0.0004840078763663769,
|
| 78 |
+
"rewards/rejected": -0.004348746035248041,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"learning_rate": 3.968253968253968e-06,
|
| 84 |
+
"logits/chosen": 0.7530747652053833,
|
| 85 |
+
"logits/rejected": 0.8437241315841675,
|
| 86 |
+
"logps/chosen": -315.67999267578125,
|
| 87 |
+
"logps/rejected": -298.5876770019531,
|
| 88 |
+
"loss": 248612.35,
|
| 89 |
+
"rewards/accuracies": 0.625,
|
| 90 |
+
"rewards/chosen": -0.008299140259623528,
|
| 91 |
+
"rewards/margins": 0.0013344786129891872,
|
| 92 |
+
"rewards/rejected": -0.009633619338274002,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1,
|
| 97 |
+
"learning_rate": 4.761904761904762e-06,
|
| 98 |
+
"logits/chosen": 0.7030428647994995,
|
| 99 |
+
"logits/rejected": 0.6946632266044617,
|
| 100 |
+
"logps/chosen": -321.80157470703125,
|
| 101 |
+
"logps/rejected": -302.8958740234375,
|
| 102 |
+
"loss": 248274.05,
|
| 103 |
+
"rewards/accuracies": 0.637499988079071,
|
| 104 |
+
"rewards/chosen": -0.016654204577207565,
|
| 105 |
+
"rewards/margins": 0.002316893544048071,
|
| 106 |
+
"rewards/rejected": -0.018971096724271774,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.11,
|
| 111 |
+
"learning_rate": 4.998086282661188e-06,
|
| 112 |
+
"logits/chosen": 0.6814395189285278,
|
| 113 |
+
"logits/rejected": 0.7533793449401855,
|
| 114 |
+
"logps/chosen": -353.67669677734375,
|
| 115 |
+
"logps/rejected": -338.9217224121094,
|
| 116 |
+
"loss": 246213.4,
|
| 117 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 118 |
+
"rewards/chosen": -0.026208389550447464,
|
| 119 |
+
"rewards/margins": 0.0031645516864955425,
|
| 120 |
+
"rewards/rejected": -0.029372945427894592,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.13,
|
| 125 |
+
"learning_rate": 4.988720025682995e-06,
|
| 126 |
+
"logits/chosen": 0.66422039270401,
|
| 127 |
+
"logits/rejected": 0.6669551134109497,
|
| 128 |
+
"logps/chosen": -333.9057312011719,
|
| 129 |
+
"logps/rejected": -346.008544921875,
|
| 130 |
+
"loss": 244032.0,
|
| 131 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 132 |
+
"rewards/chosen": -0.03818231448531151,
|
| 133 |
+
"rewards/margins": 0.00513039855286479,
|
| 134 |
+
"rewards/rejected": -0.043312713503837585,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.14,
|
| 139 |
+
"learning_rate": 4.9715789537359126e-06,
|
| 140 |
+
"logits/chosen": 0.6255489587783813,
|
| 141 |
+
"logits/rejected": 0.6321488618850708,
|
| 142 |
+
"logps/chosen": -334.863525390625,
|
| 143 |
+
"logps/rejected": -334.16644287109375,
|
| 144 |
+
"loss": 240875.95,
|
| 145 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 146 |
+
"rewards/chosen": -0.047401346266269684,
|
| 147 |
+
"rewards/margins": 0.010096731595695019,
|
| 148 |
+
"rewards/rejected": -0.05749807506799698,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.16,
|
| 153 |
+
"learning_rate": 4.946716615897932e-06,
|
| 154 |
+
"logits/chosen": 0.5756382942199707,
|
| 155 |
+
"logits/rejected": 0.5615967512130737,
|
| 156 |
+
"logps/chosen": -333.1421813964844,
|
| 157 |
+
"logps/rejected": -330.11920166015625,
|
| 158 |
+
"loss": 240338.95,
|
| 159 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 160 |
+
"rewards/chosen": -0.0577034130692482,
|
| 161 |
+
"rewards/margins": 0.00923432968556881,
|
| 162 |
+
"rewards/rejected": -0.06693773716688156,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.18,
|
| 167 |
+
"learning_rate": 4.9142106826480114e-06,
|
| 168 |
+
"logits/chosen": 0.4540364742279053,
|
| 169 |
+
"logits/rejected": 0.5108239054679871,
|
| 170 |
+
"logps/chosen": -352.08721923828125,
|
| 171 |
+
"logps/rejected": -346.1022644042969,
|
| 172 |
+
"loss": 240647.4,
|
| 173 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 174 |
+
"rewards/chosen": -0.06690040230751038,
|
| 175 |
+
"rewards/margins": 0.007805522531270981,
|
| 176 |
+
"rewards/rejected": -0.07470591366291046,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.19,
|
| 181 |
+
"learning_rate": 4.874162703221823e-06,
|
| 182 |
+
"logits/chosen": 0.395730584859848,
|
| 183 |
+
"logits/rejected": 0.42432737350463867,
|
| 184 |
+
"logps/chosen": -387.7721252441406,
|
| 185 |
+
"logps/rejected": -377.1489562988281,
|
| 186 |
+
"loss": 235908.05,
|
| 187 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 188 |
+
"rewards/chosen": -0.09094537049531937,
|
| 189 |
+
"rewards/margins": 0.01256307028234005,
|
| 190 |
+
"rewards/rejected": -0.10350845009088516,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.21,
|
| 195 |
+
"learning_rate": 4.826697788369752e-06,
|
| 196 |
+
"logits/chosen": 0.3145865797996521,
|
| 197 |
+
"logits/rejected": 0.3371677100658417,
|
| 198 |
+
"logps/chosen": -404.41522216796875,
|
| 199 |
+
"logps/rejected": -429.7151794433594,
|
| 200 |
+
"loss": 229710.4,
|
| 201 |
+
"rewards/accuracies": 0.643750011920929,
|
| 202 |
+
"rewards/chosen": -0.115650475025177,
|
| 203 |
+
"rewards/margins": 0.024767927825450897,
|
| 204 |
+
"rewards/rejected": -0.1404184103012085,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.22,
|
| 209 |
+
"learning_rate": 4.7719642195082224e-06,
|
| 210 |
+
"logits/chosen": 0.17865605652332306,
|
| 211 |
+
"logits/rejected": 0.24005897343158722,
|
| 212 |
+
"logps/chosen": -409.31573486328125,
|
| 213 |
+
"logps/rejected": -430.16961669921875,
|
| 214 |
+
"loss": 226331.25,
|
| 215 |
+
"rewards/accuracies": 0.625,
|
| 216 |
+
"rewards/chosen": -0.1381843388080597,
|
| 217 |
+
"rewards/margins": 0.028940195217728615,
|
| 218 |
+
"rewards/rejected": -0.16712453961372375,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.24,
|
| 223 |
+
"learning_rate": 4.710132985485355e-06,
|
| 224 |
+
"logits/chosen": 0.05765807628631592,
|
| 225 |
+
"logits/rejected": 0.11190862953662872,
|
| 226 |
+
"logps/chosen": -517.4808959960938,
|
| 227 |
+
"logps/rejected": -503.72503662109375,
|
| 228 |
+
"loss": 217724.3,
|
| 229 |
+
"rewards/accuracies": 0.625,
|
| 230 |
+
"rewards/chosen": -0.1879872977733612,
|
| 231 |
+
"rewards/margins": 0.04196537286043167,
|
| 232 |
+
"rewards/rejected": -0.22995266318321228,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.26,
|
| 237 |
+
"learning_rate": 4.641397248408122e-06,
|
| 238 |
+
"logits/chosen": 0.02083182893693447,
|
| 239 |
+
"logits/rejected": 0.06791719049215317,
|
| 240 |
+
"logps/chosen": -501.41314697265625,
|
| 241 |
+
"logps/rejected": -518.4356689453125,
|
| 242 |
+
"loss": 218921.525,
|
| 243 |
+
"rewards/accuracies": 0.625,
|
| 244 |
+
"rewards/chosen": -0.22430023550987244,
|
| 245 |
+
"rewards/margins": 0.047038402408361435,
|
| 246 |
+
"rewards/rejected": -0.27133864164352417,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.27,
|
| 251 |
+
"learning_rate": 4.5659717401997655e-06,
|
| 252 |
+
"logits/chosen": 0.05980447679758072,
|
| 253 |
+
"logits/rejected": 0.13415992259979248,
|
| 254 |
+
"logps/chosen": -510.23504638671875,
|
| 255 |
+
"logps/rejected": -534.2890014648438,
|
| 256 |
+
"loss": 224117.425,
|
| 257 |
+
"rewards/accuracies": 0.59375,
|
| 258 |
+
"rewards/chosen": -0.20021386444568634,
|
| 259 |
+
"rewards/margins": 0.04722369834780693,
|
| 260 |
+
"rewards/rejected": -0.24743756651878357,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.29,
|
| 265 |
+
"learning_rate": 4.4840920917726425e-06,
|
| 266 |
+
"logits/chosen": 0.0785370022058487,
|
| 267 |
+
"logits/rejected": 0.09097695350646973,
|
| 268 |
+
"logps/chosen": -595.0328369140625,
|
| 269 |
+
"logps/rejected": -597.6621704101562,
|
| 270 |
+
"loss": 213793.725,
|
| 271 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 272 |
+
"rewards/chosen": -0.28900542855262756,
|
| 273 |
+
"rewards/margins": 0.04301437363028526,
|
| 274 |
+
"rewards/rejected": -0.3320198357105255,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3,
|
| 279 |
+
"learning_rate": 4.396014096912182e-06,
|
| 280 |
+
"logits/chosen": -0.02692921832203865,
|
| 281 |
+
"logits/rejected": 0.01183820329606533,
|
| 282 |
+
"logps/chosen": -657.1026611328125,
|
| 283 |
+
"logps/rejected": -674.083251953125,
|
| 284 |
+
"loss": 217000.05,
|
| 285 |
+
"rewards/accuracies": 0.59375,
|
| 286 |
+
"rewards/chosen": -0.35720986127853394,
|
| 287 |
+
"rewards/margins": 0.06607996672391891,
|
| 288 |
+
"rewards/rejected": -0.42328983545303345,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.32,
|
| 293 |
+
"learning_rate": 4.302012913171584e-06,
|
| 294 |
+
"logits/chosen": 0.016970274969935417,
|
| 295 |
+
"logits/rejected": 0.03241819143295288,
|
| 296 |
+
"logps/chosen": -740.4771728515625,
|
| 297 |
+
"logps/rejected": -757.164794921875,
|
| 298 |
+
"loss": 228484.45,
|
| 299 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 300 |
+
"rewards/chosen": -0.3992530405521393,
|
| 301 |
+
"rewards/margins": 0.035844482481479645,
|
| 302 |
+
"rewards/rejected": -0.4350975453853607,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.34,
|
| 307 |
+
"learning_rate": 4.202382202273702e-06,
|
| 308 |
+
"logits/chosen": 0.00015654190792702138,
|
| 309 |
+
"logits/rejected": 0.08966602385044098,
|
| 310 |
+
"logps/chosen": -675.322509765625,
|
| 311 |
+
"logps/rejected": -718.8179931640625,
|
| 312 |
+
"loss": 214730.75,
|
| 313 |
+
"rewards/accuracies": 0.625,
|
| 314 |
+
"rewards/chosen": -0.3644675612449646,
|
| 315 |
+
"rewards/margins": 0.0624375119805336,
|
| 316 |
+
"rewards/rejected": -0.42690515518188477,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.35,
|
| 321 |
+
"learning_rate": 4.097433212705492e-06,
|
| 322 |
+
"logits/chosen": -0.06447938829660416,
|
| 323 |
+
"logits/rejected": -0.055021267384290695,
|
| 324 |
+
"logps/chosen": -613.5958251953125,
|
| 325 |
+
"logps/rejected": -697.4694213867188,
|
| 326 |
+
"loss": 211407.05,
|
| 327 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 328 |
+
"rewards/chosen": -0.3579150140285492,
|
| 329 |
+
"rewards/margins": 0.05921386927366257,
|
| 330 |
+
"rewards/rejected": -0.41712889075279236,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.37,
|
| 335 |
+
"learning_rate": 3.987493807371033e-06,
|
| 336 |
+
"logits/chosen": -0.06768902391195297,
|
| 337 |
+
"logits/rejected": 0.0020426944829523563,
|
| 338 |
+
"logps/chosen": -682.5296020507812,
|
| 339 |
+
"logps/rejected": -710.4071655273438,
|
| 340 |
+
"loss": 207694.0,
|
| 341 |
+
"rewards/accuracies": 0.643750011920929,
|
| 342 |
+
"rewards/chosen": -0.3751247823238373,
|
| 343 |
+
"rewards/margins": 0.06657867878675461,
|
| 344 |
+
"rewards/rejected": -0.4417034983634949,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.38,
|
| 349 |
+
"learning_rate": 3.872907439340758e-06,
|
| 350 |
+
"logits/chosen": 0.005040665622800589,
|
| 351 |
+
"logits/rejected": 0.02079974114894867,
|
| 352 |
+
"logps/chosen": -712.57763671875,
|
| 353 |
+
"logps/rejected": -737.4443969726562,
|
| 354 |
+
"loss": 220043.025,
|
| 355 |
+
"rewards/accuracies": 0.574999988079071,
|
| 356 |
+
"rewards/chosen": -0.404686838388443,
|
| 357 |
+
"rewards/margins": 0.051380474120378494,
|
| 358 |
+
"rewards/rejected": -0.4560673236846924,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.4,
|
| 363 |
+
"learning_rate": 3.75403207889666e-06,
|
| 364 |
+
"logits/chosen": 0.003915914800018072,
|
| 365 |
+
"logits/rejected": 0.031082844361662865,
|
| 366 |
+
"logps/chosen": -672.8313598632812,
|
| 367 |
+
"logps/rejected": -687.6966552734375,
|
| 368 |
+
"loss": 207725.825,
|
| 369 |
+
"rewards/accuracies": 0.625,
|
| 370 |
+
"rewards/chosen": -0.3670479953289032,
|
| 371 |
+
"rewards/margins": 0.065892294049263,
|
| 372 |
+
"rewards/rejected": -0.4329403042793274,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.42,
|
| 377 |
+
"learning_rate": 3.631239095225417e-06,
|
| 378 |
+
"logits/chosen": 0.06261593103408813,
|
| 379 |
+
"logits/rejected": 0.13836300373077393,
|
| 380 |
+
"logps/chosen": -689.614501953125,
|
| 381 |
+
"logps/rejected": -736.5167236328125,
|
| 382 |
+
"loss": 216697.45,
|
| 383 |
+
"rewards/accuracies": 0.574999988079071,
|
| 384 |
+
"rewards/chosen": -0.4008885324001312,
|
| 385 |
+
"rewards/margins": 0.0602349154651165,
|
| 386 |
+
"rewards/rejected": -0.4611234664916992,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.43,
|
| 391 |
+
"learning_rate": 3.5049120962530608e-06,
|
| 392 |
+
"logits/chosen": 0.11205191910266876,
|
| 393 |
+
"logits/rejected": 0.14602160453796387,
|
| 394 |
+
"logps/chosen": -735.8699951171875,
|
| 395 |
+
"logps/rejected": -832.4979248046875,
|
| 396 |
+
"loss": 206147.4,
|
| 397 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 398 |
+
"rewards/chosen": -0.44775643944740295,
|
| 399 |
+
"rewards/margins": 0.07730598002672195,
|
| 400 |
+
"rewards/rejected": -0.5250624418258667,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.45,
|
| 405 |
+
"learning_rate": 3.3754457302455464e-06,
|
| 406 |
+
"logits/chosen": 0.06379252672195435,
|
| 407 |
+
"logits/rejected": 0.08125611394643784,
|
| 408 |
+
"logps/chosen": -791.1683349609375,
|
| 409 |
+
"logps/rejected": -842.2650146484375,
|
| 410 |
+
"loss": 217755.6,
|
| 411 |
+
"rewards/accuracies": 0.5625,
|
| 412 |
+
"rewards/chosen": -0.5111533403396606,
|
| 413 |
+
"rewards/margins": 0.05805770307779312,
|
| 414 |
+
"rewards/rejected": -0.5692110061645508,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.46,
|
| 419 |
+
"learning_rate": 3.2432444529190714e-06,
|
| 420 |
+
"logits/chosen": 0.03794580325484276,
|
| 421 |
+
"logits/rejected": 0.10185732692480087,
|
| 422 |
+
"logps/chosen": -766.0865478515625,
|
| 423 |
+
"logps/rejected": -786.9296875,
|
| 424 |
+
"loss": 205712.7375,
|
| 425 |
+
"rewards/accuracies": 0.643750011920929,
|
| 426 |
+
"rewards/chosen": -0.4407348036766052,
|
| 427 |
+
"rewards/margins": 0.07172349095344543,
|
| 428 |
+
"rewards/rejected": -0.5124582648277283,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.48,
|
| 433 |
+
"learning_rate": 3.1087212639117057e-06,
|
| 434 |
+
"logits/chosen": 0.0560905747115612,
|
| 435 |
+
"logits/rejected": 0.056962113827466965,
|
| 436 |
+
"logps/chosen": -691.1881103515625,
|
| 437 |
+
"logps/rejected": -736.6007690429688,
|
| 438 |
+
"loss": 199775.475,
|
| 439 |
+
"rewards/accuracies": 0.606249988079071,
|
| 440 |
+
"rewards/chosen": -0.3910200595855713,
|
| 441 |
+
"rewards/margins": 0.06142463535070419,
|
| 442 |
+
"rewards/rejected": -0.4524447023868561,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.5,
|
| 447 |
+
"learning_rate": 2.9722964165636263e-06,
|
| 448 |
+
"logits/chosen": 0.0340690053999424,
|
| 449 |
+
"logits/rejected": 0.10146850347518921,
|
| 450 |
+
"logps/chosen": -720.965087890625,
|
| 451 |
+
"logps/rejected": -739.9038696289062,
|
| 452 |
+
"loss": 217950.85,
|
| 453 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 454 |
+
"rewards/chosen": -0.421273797750473,
|
| 455 |
+
"rewards/margins": 0.03930564597249031,
|
| 456 |
+
"rewards/rejected": -0.46057945489883423,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.51,
|
| 461 |
+
"learning_rate": 2.8343961050366275e-06,
|
| 462 |
+
"logits/chosen": 0.054887332022190094,
|
| 463 |
+
"logits/rejected": 0.044551193714141846,
|
| 464 |
+
"logps/chosen": -735.8577880859375,
|
| 465 |
+
"logps/rejected": -789.2850952148438,
|
| 466 |
+
"loss": 218271.95,
|
| 467 |
+
"rewards/accuracies": 0.5562499761581421,
|
| 468 |
+
"rewards/chosen": -0.4242521822452545,
|
| 469 |
+
"rewards/margins": 0.05404456704854965,
|
| 470 |
+
"rewards/rejected": -0.47829669713974,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.53,
|
| 475 |
+
"learning_rate": 2.695451132874385e-06,
|
| 476 |
+
"logits/chosen": 0.020503774285316467,
|
| 477 |
+
"logits/rejected": 0.08877702057361603,
|
| 478 |
+
"logps/chosen": -685.0552978515625,
|
| 479 |
+
"logps/rejected": -749.4927978515625,
|
| 480 |
+
"loss": 208541.825,
|
| 481 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 482 |
+
"rewards/chosen": -0.4152056574821472,
|
| 483 |
+
"rewards/margins": 0.06724479049444199,
|
| 484 |
+
"rewards/rejected": -0.4824504256248474,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.54,
|
| 489 |
+
"learning_rate": 2.5558955671628964e-06,
|
| 490 |
+
"logits/chosen": 0.03993639722466469,
|
| 491 |
+
"logits/rejected": 0.09598435461521149,
|
| 492 |
+
"logps/chosen": -687.928466796875,
|
| 493 |
+
"logps/rejected": -717.9952392578125,
|
| 494 |
+
"loss": 211084.3,
|
| 495 |
+
"rewards/accuracies": 0.612500011920929,
|
| 496 |
+
"rewards/chosen": -0.401594877243042,
|
| 497 |
+
"rewards/margins": 0.05332701653242111,
|
| 498 |
+
"rewards/rejected": -0.45492181181907654,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.56,
|
| 503 |
+
"learning_rate": 2.4161653824955654e-06,
|
| 504 |
+
"logits/chosen": 0.06816108524799347,
|
| 505 |
+
"logits/rejected": 0.08216299116611481,
|
| 506 |
+
"logps/chosen": -716.1536865234375,
|
| 507 |
+
"logps/rejected": -749.4075927734375,
|
| 508 |
+
"loss": 205341.7,
|
| 509 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 510 |
+
"rewards/chosen": -0.42900824546813965,
|
| 511 |
+
"rewards/margins": 0.06950432807207108,
|
| 512 |
+
"rewards/rejected": -0.4985125958919525,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.58,
|
| 517 |
+
"learning_rate": 2.2766970989791697e-06,
|
| 518 |
+
"logits/chosen": 0.012849223800003529,
|
| 519 |
+
"logits/rejected": 0.02745252475142479,
|
| 520 |
+
"logps/chosen": -773.5811157226562,
|
| 521 |
+
"logps/rejected": -870.6488037109375,
|
| 522 |
+
"loss": 204889.025,
|
| 523 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 524 |
+
"rewards/chosen": -0.4782876968383789,
|
| 525 |
+
"rewards/margins": 0.08239278197288513,
|
| 526 |
+
"rewards/rejected": -0.5606805086135864,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.59,
|
| 531 |
+
"learning_rate": 2.1379264185356545e-06,
|
| 532 |
+
"logits/chosen": -0.01748507469892502,
|
| 533 |
+
"logits/rejected": 0.026378531008958817,
|
| 534 |
+
"logps/chosen": -870.5720825195312,
|
| 535 |
+
"logps/rejected": -918.7122192382812,
|
| 536 |
+
"loss": 221285.175,
|
| 537 |
+
"rewards/accuracies": 0.5625,
|
| 538 |
+
"rewards/chosen": -0.5346072316169739,
|
| 539 |
+
"rewards/margins": 0.046777307987213135,
|
| 540 |
+
"rewards/rejected": -0.581384539604187,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.61,
|
| 545 |
+
"learning_rate": 2.000286863759934e-06,
|
| 546 |
+
"logits/chosen": 0.007047905120998621,
|
| 547 |
+
"logits/rejected": 0.08078267425298691,
|
| 548 |
+
"logps/chosen": -755.0501098632812,
|
| 549 |
+
"logps/rejected": -820.9991455078125,
|
| 550 |
+
"loss": 201255.875,
|
| 551 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 552 |
+
"rewards/chosen": -0.45793017745018005,
|
| 553 |
+
"rewards/margins": 0.08488230407238007,
|
| 554 |
+
"rewards/rejected": -0.5428124666213989,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.62,
|
| 559 |
+
"learning_rate": 1.8642084235859764e-06,
|
| 560 |
+
"logits/chosen": 0.011273056268692017,
|
| 561 |
+
"logits/rejected": -0.012196743860840797,
|
| 562 |
+
"logps/chosen": -764.2548828125,
|
| 563 |
+
"logps/rejected": -848.6171875,
|
| 564 |
+
"loss": 214622.65,
|
| 565 |
+
"rewards/accuracies": 0.574999988079071,
|
| 566 |
+
"rewards/chosen": -0.4602470397949219,
|
| 567 |
+
"rewards/margins": 0.07196761667728424,
|
| 568 |
+
"rewards/rejected": -0.5322146415710449,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.64,
|
| 573 |
+
"learning_rate": 1.7301162099921013e-06,
|
| 574 |
+
"logits/chosen": -0.0019163116812705994,
|
| 575 |
+
"logits/rejected": 0.05834005028009415,
|
| 576 |
+
"logps/chosen": -858.6873168945312,
|
| 577 |
+
"logps/rejected": -904.6046142578125,
|
| 578 |
+
"loss": 206360.4125,
|
| 579 |
+
"rewards/accuracies": 0.675000011920929,
|
| 580 |
+
"rewards/chosen": -0.5314964652061462,
|
| 581 |
+
"rewards/margins": 0.08296509087085724,
|
| 582 |
+
"rewards/rejected": -0.6144616603851318,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.66,
|
| 587 |
+
"learning_rate": 1.5984291299420117e-06,
|
| 588 |
+
"logits/chosen": 0.012182576581835747,
|
| 589 |
+
"logits/rejected": 0.0708267092704773,
|
| 590 |
+
"logps/chosen": -813.0255737304688,
|
| 591 |
+
"logps/rejected": -832.9349365234375,
|
| 592 |
+
"loss": 211531.0,
|
| 593 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 594 |
+
"rewards/chosen": -0.49179133772850037,
|
| 595 |
+
"rewards/margins": 0.08578650653362274,
|
| 596 |
+
"rewards/rejected": -0.5775778293609619,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.67,
|
| 601 |
+
"learning_rate": 1.4695585767104092e-06,
|
| 602 |
+
"logits/chosen": 0.0914839580655098,
|
| 603 |
+
"logits/rejected": 0.04479590803384781,
|
| 604 |
+
"logps/chosen": -832.50439453125,
|
| 605 |
+
"logps/rejected": -880.9533081054688,
|
| 606 |
+
"loss": 205329.4,
|
| 607 |
+
"rewards/accuracies": 0.606249988079071,
|
| 608 |
+
"rewards/chosen": -0.48841309547424316,
|
| 609 |
+
"rewards/margins": 0.07340176403522491,
|
| 610 |
+
"rewards/rejected": -0.5618147850036621,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.69,
|
| 615 |
+
"learning_rate": 1.3439071446815452e-06,
|
| 616 |
+
"logits/chosen": 0.08182860910892487,
|
| 617 |
+
"logits/rejected": 0.100291907787323,
|
| 618 |
+
"logps/chosen": -752.081298828125,
|
| 619 |
+
"logps/rejected": -833.1486206054688,
|
| 620 |
+
"loss": 201124.725,
|
| 621 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 622 |
+
"rewards/chosen": -0.45724090933799744,
|
| 623 |
+
"rewards/margins": 0.08672616630792618,
|
| 624 |
+
"rewards/rejected": -0.543967068195343,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.7,
|
| 629 |
+
"learning_rate": 1.2218673716356919e-06,
|
| 630 |
+
"logits/chosen": 0.056249700486660004,
|
| 631 |
+
"logits/rejected": 0.04042553901672363,
|
| 632 |
+
"logps/chosen": -763.6502075195312,
|
| 633 |
+
"logps/rejected": -836.1224365234375,
|
| 634 |
+
"loss": 206556.925,
|
| 635 |
+
"rewards/accuracies": 0.581250011920929,
|
| 636 |
+
"rewards/chosen": -0.4586957097053528,
|
| 637 |
+
"rewards/margins": 0.05668143555521965,
|
| 638 |
+
"rewards/rejected": -0.5153771638870239,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.72,
|
| 643 |
+
"learning_rate": 1.103820512452661e-06,
|
| 644 |
+
"logits/chosen": 0.058336324989795685,
|
| 645 |
+
"logits/rejected": 0.09516619145870209,
|
| 646 |
+
"logps/chosen": -799.2554931640625,
|
| 647 |
+
"logps/rejected": -850.5153198242188,
|
| 648 |
+
"loss": 200567.1625,
|
| 649 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 650 |
+
"rewards/chosen": -0.45398440957069397,
|
| 651 |
+
"rewards/margins": 0.09574355185031891,
|
| 652 |
+
"rewards/rejected": -0.5497279763221741,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.74,
|
| 657 |
+
"learning_rate": 9.901353480633468e-07,
|
| 658 |
+
"logits/chosen": 0.06983263790607452,
|
| 659 |
+
"logits/rejected": 0.10929594188928604,
|
| 660 |
+
"logps/chosen": -735.544189453125,
|
| 661 |
+
"logps/rejected": -794.2623291015625,
|
| 662 |
+
"loss": 208963.425,
|
| 663 |
+
"rewards/accuracies": 0.59375,
|
| 664 |
+
"rewards/chosen": -0.4254637360572815,
|
| 665 |
+
"rewards/margins": 0.08059998601675034,
|
| 666 |
+
"rewards/rejected": -0.5060637593269348,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.75,
|
| 671 |
+
"learning_rate": 8.811670333701544e-07,
|
| 672 |
+
"logits/chosen": 0.035215824842453,
|
| 673 |
+
"logits/rejected": 0.10739400237798691,
|
| 674 |
+
"logps/chosen": -752.6171875,
|
| 675 |
+
"logps/rejected": -820.1688232421875,
|
| 676 |
+
"loss": 208260.5375,
|
| 677 |
+
"rewards/accuracies": 0.606249988079071,
|
| 678 |
+
"rewards/chosen": -0.4630301594734192,
|
| 679 |
+
"rewards/margins": 0.055133186280727386,
|
| 680 |
+
"rewards/rejected": -0.5181634426116943,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.77,
|
| 685 |
+
"learning_rate": 7.772559877354341e-07,
|
| 686 |
+
"logits/chosen": 0.10807295143604279,
|
| 687 |
+
"logits/rejected": 0.0317668542265892,
|
| 688 |
+
"logps/chosen": -756.6256103515625,
|
| 689 |
+
"logps/rejected": -816.7699584960938,
|
| 690 |
+
"loss": 216200.35,
|
| 691 |
+
"rewards/accuracies": 0.612500011920929,
|
| 692 |
+
"rewards/chosen": -0.4670717716217041,
|
| 693 |
+
"rewards/margins": 0.07191431522369385,
|
| 694 |
+
"rewards/rejected": -0.538986086845398,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.78,
|
| 699 |
+
"learning_rate": 6.787268315040604e-07,
|
| 700 |
+
"logits/chosen": 0.04728057235479355,
|
| 701 |
+
"logits/rejected": 0.15024212002754211,
|
| 702 |
+
"logps/chosen": -767.487060546875,
|
| 703 |
+
"logps/rejected": -839.1052856445312,
|
| 704 |
+
"loss": 199459.25,
|
| 705 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 706 |
+
"rewards/chosen": -0.44638481736183167,
|
| 707 |
+
"rewards/margins": 0.08024169504642487,
|
| 708 |
+
"rewards/rejected": -0.526626467704773,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.8,
|
| 713 |
+
"learning_rate": 5.858873718824829e-07,
|
| 714 |
+
"logits/chosen": 0.09359405189752579,
|
| 715 |
+
"logits/rejected": 0.10223015397787094,
|
| 716 |
+
"logps/chosen": -759.4922485351562,
|
| 717 |
+
"logps/rejected": -814.4105224609375,
|
| 718 |
+
"loss": 206686.275,
|
| 719 |
+
"rewards/accuracies": 0.612500011920929,
|
| 720 |
+
"rewards/chosen": -0.46266812086105347,
|
| 721 |
+
"rewards/margins": 0.0593070387840271,
|
| 722 |
+
"rewards/rejected": -0.5219752192497253,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.82,
|
| 727 |
+
"learning_rate": 4.990276413423817e-07,
|
| 728 |
+
"logits/chosen": 0.01493439543992281,
|
| 729 |
+
"logits/rejected": 0.0643661767244339,
|
| 730 |
+
"logps/chosen": -735.6563720703125,
|
| 731 |
+
"logps/rejected": -793.5201416015625,
|
| 732 |
+
"loss": 198584.575,
|
| 733 |
+
"rewards/accuracies": 0.625,
|
| 734 |
+
"rewards/chosen": -0.42836418747901917,
|
| 735 |
+
"rewards/margins": 0.08260954916477203,
|
| 736 |
+
"rewards/rejected": -0.5109737515449524,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.83,
|
| 741 |
+
"learning_rate": 4.184189915529796e-07,
|
| 742 |
+
"logits/chosen": 0.09607640653848648,
|
| 743 |
+
"logits/rejected": 0.12576672434806824,
|
| 744 |
+
"logps/chosen": -765.7574462890625,
|
| 745 |
+
"logps/rejected": -835.0860595703125,
|
| 746 |
+
"loss": 198521.6875,
|
| 747 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 748 |
+
"rewards/chosen": -0.45677047967910767,
|
| 749 |
+
"rewards/margins": 0.08099553734064102,
|
| 750 |
+
"rewards/rejected": -0.5377659797668457,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.85,
|
| 755 |
+
"learning_rate": 3.4431324567258176e-07,
|
| 756 |
+
"logits/chosen": 0.03705473989248276,
|
| 757 |
+
"logits/rejected": 0.07135260850191116,
|
| 758 |
+
"logps/chosen": -806.9525146484375,
|
| 759 |
+
"logps/rejected": -851.9264526367188,
|
| 760 |
+
"loss": 200813.6625,
|
| 761 |
+
"rewards/accuracies": 0.625,
|
| 762 |
+
"rewards/chosen": -0.4773276448249817,
|
| 763 |
+
"rewards/margins": 0.0656534880399704,
|
| 764 |
+
"rewards/rejected": -0.5429811477661133,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.86,
|
| 769 |
+
"learning_rate": 2.769419116476052e-07,
|
| 770 |
+
"logits/chosen": 0.013349669054150581,
|
| 771 |
+
"logits/rejected": 0.04136626794934273,
|
| 772 |
+
"logps/chosen": -748.1133422851562,
|
| 773 |
+
"logps/rejected": -810.5701293945312,
|
| 774 |
+
"loss": 198242.825,
|
| 775 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 776 |
+
"rewards/chosen": -0.4668392241001129,
|
| 777 |
+
"rewards/margins": 0.06354349106550217,
|
| 778 |
+
"rewards/rejected": -0.5303827524185181,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.88,
|
| 783 |
+
"learning_rate": 2.1651545897676512e-07,
|
| 784 |
+
"logits/chosen": 0.06408552080392838,
|
| 785 |
+
"logits/rejected": 0.11870439350605011,
|
| 786 |
+
"logps/chosen": -763.1972045898438,
|
| 787 |
+
"logps/rejected": -839.8497314453125,
|
| 788 |
+
"loss": 211745.225,
|
| 789 |
+
"rewards/accuracies": 0.637499988079071,
|
| 790 |
+
"rewards/chosen": -0.4748295843601227,
|
| 791 |
+
"rewards/margins": 0.0728473886847496,
|
| 792 |
+
"rewards/rejected": -0.5476769208908081,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.9,
|
| 797 |
+
"learning_rate": 1.6322266119983222e-07,
|
| 798 |
+
"logits/chosen": 0.0492372028529644,
|
| 799 |
+
"logits/rejected": 0.09988833963871002,
|
| 800 |
+
"logps/chosen": -789.6986083984375,
|
| 801 |
+
"logps/rejected": -825.2615966796875,
|
| 802 |
+
"loss": 211827.35,
|
| 803 |
+
"rewards/accuracies": 0.581250011920929,
|
| 804 |
+
"rewards/chosen": -0.4770093560218811,
|
| 805 |
+
"rewards/margins": 0.06789447367191315,
|
| 806 |
+
"rewards/rejected": -0.5449038743972778,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.91,
|
| 811 |
+
"learning_rate": 1.1723000616502167e-07,
|
| 812 |
+
"logits/chosen": 0.06743012368679047,
|
| 813 |
+
"logits/rejected": 0.01723661459982395,
|
| 814 |
+
"logps/chosen": -782.1122436523438,
|
| 815 |
+
"logps/rejected": -836.3314208984375,
|
| 816 |
+
"loss": 205469.55,
|
| 817 |
+
"rewards/accuracies": 0.606249988079071,
|
| 818 |
+
"rewards/chosen": -0.47319063544273376,
|
| 819 |
+
"rewards/margins": 0.07614056020975113,
|
| 820 |
+
"rewards/rejected": -0.5493311882019043,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.93,
|
| 825 |
+
"learning_rate": 7.868117591737585e-08,
|
| 826 |
+
"logits/chosen": 0.0372871533036232,
|
| 827 |
+
"logits/rejected": 0.07801343500614166,
|
| 828 |
+
"logps/chosen": -741.191650390625,
|
| 829 |
+
"logps/rejected": -787.1198120117188,
|
| 830 |
+
"loss": 213403.7,
|
| 831 |
+
"rewards/accuracies": 0.59375,
|
| 832 |
+
"rewards/chosen": -0.44429221749305725,
|
| 833 |
+
"rewards/margins": 0.07286076247692108,
|
| 834 |
+
"rewards/rejected": -0.5171529650688171,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.94,
|
| 839 |
+
"learning_rate": 4.769659783295383e-08,
|
| 840 |
+
"logits/chosen": 0.07339660078287125,
|
| 841 |
+
"logits/rejected": 0.138061061501503,
|
| 842 |
+
"logps/chosen": -771.2107543945312,
|
| 843 |
+
"logps/rejected": -813.8905029296875,
|
| 844 |
+
"loss": 210919.15,
|
| 845 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 846 |
+
"rewards/chosen": -0.47977980971336365,
|
| 847 |
+
"rewards/margins": 0.08075427263975143,
|
| 848 |
+
"rewards/rejected": -0.5605341196060181,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.96,
|
| 853 |
+
"learning_rate": 2.4373068401120358e-08,
|
| 854 |
+
"logits/chosen": 0.11042066663503647,
|
| 855 |
+
"logits/rejected": 0.07605646550655365,
|
| 856 |
+
"logps/chosen": -791.4373779296875,
|
| 857 |
+
"logps/rejected": -826.2615356445312,
|
| 858 |
+
"loss": 216413.4,
|
| 859 |
+
"rewards/accuracies": 0.543749988079071,
|
| 860 |
+
"rewards/chosen": -0.49039316177368164,
|
| 861 |
+
"rewards/margins": 0.056141942739486694,
|
| 862 |
+
"rewards/rejected": -0.5465351343154907,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.98,
|
| 867 |
+
"learning_rate": 8.78345083022425e-09,
|
| 868 |
+
"logits/chosen": 0.07623746991157532,
|
| 869 |
+
"logits/rejected": 0.1269301176071167,
|
| 870 |
+
"logps/chosen": -798.3727416992188,
|
| 871 |
+
"logps/rejected": -851.33740234375,
|
| 872 |
+
"loss": 209334.025,
|
| 873 |
+
"rewards/accuracies": 0.581250011920929,
|
| 874 |
+
"rewards/chosen": -0.49323853850364685,
|
| 875 |
+
"rewards/margins": 0.07322792708873749,
|
| 876 |
+
"rewards/rejected": -0.5664664506912231,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.99,
|
| 881 |
+
"learning_rate": 9.764474213677654e-10,
|
| 882 |
+
"logits/chosen": 0.060989219695329666,
|
| 883 |
+
"logits/rejected": 0.09394808858633041,
|
| 884 |
+
"logps/chosen": -785.9288330078125,
|
| 885 |
+
"logps/rejected": -820.1795043945312,
|
| 886 |
+
"loss": 210348.9,
|
| 887 |
+
"rewards/accuracies": 0.637499988079071,
|
| 888 |
+
"rewards/chosen": -0.49476709961891174,
|
| 889 |
+
"rewards/margins": 0.057541172951459885,
|
| 890 |
+
"rewards/rejected": -0.5523082613945007,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.0,
|
| 895 |
+
"step": 625,
|
| 896 |
+
"total_flos": 0.0,
|
| 897 |
+
"train_loss": 217680.7002,
|
| 898 |
+
"train_runtime": 7796.5816,
|
| 899 |
+
"train_samples_per_second": 2.565,
|
| 900 |
+
"train_steps_per_second": 0.08
|
| 901 |
+
}
|
| 902 |
+
],
|
| 903 |
+
"logging_steps": 10,
|
| 904 |
+
"max_steps": 625,
|
| 905 |
+
"num_input_tokens_seen": 0,
|
| 906 |
+
"num_train_epochs": 1,
|
| 907 |
+
"save_steps": 100,
|
| 908 |
+
"total_flos": 0.0,
|
| 909 |
+
"train_batch_size": 4,
|
| 910 |
+
"trial_name": null,
|
| 911 |
+
"trial_params": null
|
| 912 |
+
}
|