Hugging Face's logo

phunguyen01
/
II-Tulu-3B-DPO

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
phunguyen01 commited on
Commit
2341ff4
•
1 Parent(s): 4bb15a2

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. model-00001-of-00002.safetensors +1 -1
  2. model-00002-of-00002.safetensors +1 -1
  3. runs/Dec10_07-49-13_gpu-3/events.out.tfevents.1733816981.gpu-3.617213.0 +3 -0
  4. runs/Dec10_07-59-08_gpu-3/events.out.tfevents.1733817574.gpu-3.623998.0 +3 -0
  5. runs/Dec10_08-04-03_gpu-3/events.out.tfevents.1733817870.gpu-3.629447.0 +3 -0
  6. runs/Dec10_08-09-19_gpu-3/events.out.tfevents.1733818185.gpu-3.636390.0 +3 -0
  7. runs/Dec10_08-43-24_gpu-3/events.out.tfevents.1733820229.gpu-3.671128.0 +3 -0
  8. training_args.bin +2 -2
  9. training_config.yaml +3 -1
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507567601a31bb597a13a4b5719ee71e818c6a61de6f3455de04f73a01bb48a6
3
  size 4957560304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9bccca09228fdecec1e76647b8a3caed850bee588810943ea8be18ef17ff3fb
3
  size 4957560304
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bc9c00db5de205b52865bf49c9bcfbe2b6a9dadd587756252fcb895dcfe4a1f
3
  size 1214366696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b413b2c7468e4cf8ac03f4c1dcaaddadee7143577eb98f7527a1867cff12ca98
3
  size 1214366696
runs/Dec10_07-49-13_gpu-3/events.out.tfevents.1733816981.gpu-3.617213.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5edc00ab91b0e764e65eecf85ca19e238c948cff7516760d3d9d6f0a01519e70
3
+ size 14509
runs/Dec10_07-59-08_gpu-3/events.out.tfevents.1733817574.gpu-3.623998.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e957f6f50f280524ccad0f7220e929525ce37465113d7b5d9ae0065cac330467
3
+ size 11193
runs/Dec10_08-04-03_gpu-3/events.out.tfevents.1733817870.gpu-3.629447.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39169a0cfa7ab95bd3efb59bf11c2e805379f7f9fc13f24559d8863a17b4c76e
3
+ size 13180
runs/Dec10_08-09-19_gpu-3/events.out.tfevents.1733818185.gpu-3.636390.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c074bf11d33a8d17f432447350ebf39b2597d5ccebb73a81305d39203952189
3
+ size 60628
runs/Dec10_08-43-24_gpu-3/events.out.tfevents.1733820229.gpu-3.671128.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:719a64c5bfb3041818eb6cd00b2352b55ba3769b5414fc74fd5bf5726a757cc2
3
+ size 1174178
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec93a0e758c8342edb4e0f50c867272e87101388c4c70cdaa085a14be5e9b88d
3
- size 8056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24cf65fcedbd25f6d685a51278432036deeb426060948a723e5280448895ae9
3
+ size 8120
training_config.yaml CHANGED
@@ -30,12 +30,14 @@ num_train_epochs: 1
30
  hub_model_id: phunguyen01/II-Tulu-3B-DPO
31
  max_length: 2048
32
  max_prompt_length: 1024
 
 
33
  evals_per_epoch: 1
34
  bf16: true
35
  logging_steps: 10
 
36
  push_to_hub: true
37
  optim: rmsprop
38
- lr_scheduler_type: linear
39
  wandb_project: llm-training-platform
40
  wandb_run_name: II-Tulu-3B-DPO
41
  wandb_token: d6057554afd47904923154654e9d6bdff5988592
 
30
  hub_model_id: phunguyen01/II-Tulu-3B-DPO
31
  max_length: 2048
32
  max_prompt_length: 1024
33
+ lr_scheduler_type: linear
34
+ gradient_checkpointing: false
35
  evals_per_epoch: 1
36
  bf16: true
37
  logging_steps: 10
38
+ save_strategy: epoch
39
  push_to_hub: true
40
  optim: rmsprop
 
41
  wandb_project: llm-training-platform
42
  wandb_run_name: II-Tulu-3B-DPO
43
  wandb_token: d6057554afd47904923154654e9d6bdff5988592