Hugging Face's logo

VictorSanh
/
test-victor

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
VictorSanh commited on
Commit
f69db80
•
1 Parent(s): 5a640a5

End of training

Browse files
Files changed (21) hide show
  1. README.md +5 -5
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +2 -2
  4. global_step616/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  5. global_step616/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. global_step616/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  7. global_step616/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  8. global_step616/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  9. global_step616/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  10. global_step616/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  11. global_step616/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  12. global_step616/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  13. global_step616/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  14. global_step616/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  15. global_step616/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  16. global_step616/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  17. global_step616/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  18. global_step616/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  19. global_step616/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  20. latest +1 -1
  21. training_args.bin +1 -1
README.md CHANGED
@@ -33,14 +33,14 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0001
36
- - train_batch_size: 2
37
  - eval_batch_size: 8
38
  - seed: 42
39
  - distributed_type: multi-GPU
40
- - num_devices: 2
41
- - gradient_accumulation_steps: 32
42
- - total_train_batch_size: 128
43
- - total_eval_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0001
36
+ - train_batch_size: 1
37
  - eval_batch_size: 8
38
  - seed: 42
39
  - distributed_type: multi-GPU
40
+ - num_devices: 8
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 64
43
+ - total_eval_batch_size: 64
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
adapter_config.json CHANGED
@@ -18,7 +18,7 @@
18
  "r": 8,
19
  "rank_pattern": {},
20
  "revision": null,
21
- "target_modules": ".*(text_model|modality_projection|perceiver_resampler|vision_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj|out_proj|fc1|fc2).*$",
22
  "task_type": null,
23
  "use_dora": true,
24
  "use_rslora": false
 
18
  "r": 8,
19
  "rank_pattern": {},
20
  "revision": null,
21
+ "target_modules": ".*(vision_model|modality_projection).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj|out_proj|fc1|fc2).*$",
22
  "task_type": null,
23
  "use_dora": true,
24
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:183b88cdf7b66f47b95296a4106742c41b5b1a92e7ea9bd9fb674c8e74d673fc
3
- size 34071024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed45ef9b1bff1ec4308c65dd51ed6a7e93b87e98f2f9d3673488b4d601365d8
3
+ size 9481928
global_step616/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb06ea49e76e6c0b6736591a46b88f18b0ce53292946caab00ebe8e6eb4e1af
3
+ size 7575767
global_step616/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a110717d19d6a6ac511dcc6e3e071b9eae5b8e8cc25cfd673fab507fe0832877
3
+ size 7575767
global_step616/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785d56ab5e626bc6e006f3e4c4c032acc3485994ae2876a69a7d3af2f2820202
3
+ size 7575767
global_step616/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8131c54b2c12d3708fd3ccb4f2b94907a92b338556a75e6352339722295852
3
+ size 7575767
global_step616/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763fdae1b9429555c12022f2eaa7a4abac742ead11b18f4c0d62072d4bbba3a8
3
+ size 7575767
global_step616/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f44c4927e5a9dddc67694466200860445843d1ae40c0f7c152e407dcaada604
3
+ size 7575767
global_step616/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759b405d012853eefd622a94a10f57522a3c8c1efcfd6d529322923e8a6e8932
3
+ size 7575767
global_step616/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962a5c49f5a47504924aa04d8bbfcabfce4b2163ba8e41ebe7ff8cc81299197f
3
+ size 7575767
global_step616/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe3ae98c2c2733a2863b8333ae356ef1fbbcec89519436bb07571f2f76eaa0c5
3
+ size 2101744109
global_step616/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ee4a12c79984d9c1af06765d01a2ea1331c619e4eb94d01da493bc9d70dd5b
3
+ size 2101744109
global_step616/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95767892d0c3faf4b5d5d333e4e7ec952c59397ceeeeacbd6518962205379d8
3
+ size 2101744109
global_step616/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a55c7ea1769e37d8f9d94c8b5dc1d83c6c22f2185cfa1a033a688734c8abcf3
3
+ size 2101744109
global_step616/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9706bd99d62ae9989f2a0cf3296638017cab983cc13efd3a4fdba5830413695
3
+ size 2101744109
global_step616/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5bdd64d35cd2344c0154b9faa6ce0bacdf37db2f557d1ba064ad54ca257929e
3
+ size 2101744109
global_step616/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c2faf4d751ed6812e41eae9826eada523af03d9c425579f004a604beb4fa26
3
+ size 2101744109
global_step616/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b444cac0e4f4bfa0919a7bdb071fc244c86cb102c12024b06315fafc009bfdd
3
+ size 2101744109
latest CHANGED
@@ -1 +1 @@
1
- global_step1
 
1
+ global_step616
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7779120f3297764cc054eb5738133077aa5bbd2f79162286346fdea761e375d0
3
  size 5627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820d8bf604fb3584d482eda862d5712a0c0b58544d15bd5eb7c66d3f99a8cdc2
3
  size 5627