Hugging Face's logo

AlignmentResearch
/
robust_llm_r2d2_tom-debug_Qwen2.5-7B-Instruct_full

TensorBoard
Safetensors
qwen2
Generated from Trainer
Model card Files Metrics Community
1
tomtseng commited on
Commit
8213057
·
verified ·
1 Parent(s): 06e616b

Model save

Browse files
Files changed (6) hide show
  1. README.md +2 -2
  2. runs/Feb05_02-57-24_r2d2-devbox-czz9b/events.out.tfevents.1738724788.r2d2-devbox-czz9b.891.0 +2 -2
  3. runs/Feb05_03-10-17_r2d2-devbox-czz9b/events.out.tfevents.1738725060.r2d2-devbox-czz9b.1586.0 +3 -0
  4. runs/Feb05_03-16-54_r2d2-devbox-czz9b/events.out.tfevents.1738725455.r2d2-devbox-czz9b.2254.0 +3 -0
  5. step_0/training_args.bin +1 -1
  6. training_args.bin +1 -1
README.md CHANGED
@@ -33,13 +33,13 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 2e-05
36
- - train_batch_size: 4
37
  - eval_batch_size: 16
38
  - seed: 42
39
  - distributed_type: multi-GPU
40
  - num_devices: 4
41
  - gradient_accumulation_steps: 8
42
- - total_train_batch_size: 128
43
  - total_eval_batch_size: 64
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 2e-05
36
+ - train_batch_size: 8
37
  - eval_batch_size: 16
38
  - seed: 42
39
  - distributed_type: multi-GPU
40
  - num_devices: 4
41
  - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 256
43
  - total_eval_batch_size: 64
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
runs/Feb05_02-57-24_r2d2-devbox-czz9b/events.out.tfevents.1738724788.r2d2-devbox-czz9b.891.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f86efc3483fa9670e91af1dba28ddbea505f990f7bba6bcaec727cef0844aa7a
3
- size 4582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d2ae7c1a69f930a570a9493f9606b89f8cad740eb6fd31db3f441fb2748b3c
3
+ size 4736
runs/Feb05_03-10-17_r2d2-devbox-czz9b/events.out.tfevents.1738725060.r2d2-devbox-czz9b.1586.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053bdc23cf51b88f1dfc80e73998dc1f9b155a5c866c33f17e07cd359875fa10
3
+ size 4582
runs/Feb05_03-16-54_r2d2-devbox-czz9b/events.out.tfevents.1738725455.r2d2-devbox-czz9b.2254.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0234304eccf24a2ef079866ab8f3db77c5c473d1268ef6b050685390fd9d5263
3
+ size 4582
step_0/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:790c690dad5d54a663b3282363d88f14ebfb662fd841bbef2df5e1e14144b4b2
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae515be2b54d1d5c521d1f19ebabb4994cb1b954fc86dc1ba735f3bb63a5541
3
  size 5752
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:790c690dad5d54a663b3282363d88f14ebfb662fd841bbef2df5e1e14144b4b2
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae515be2b54d1d5c521d1f19ebabb4994cb1b954fc86dc1ba735f3bb63a5541
3
  size 5752