Hugging Face's logo

ashabrawy
/
jais-family-590m-gamma-0.0-0-lamda-0.0-0-English-sft

Transformers
Safetensors
Generated from Trainer
trl
sft
Inference Endpoints
Model card Files Community
ashabrawy commited on
Commit
1387f16
•
1 Parent(s): f77d2cd

jais-family-590m_gamma_0.0_0_lamda_0.0-0_English_sft/

Browse files
Files changed (21) hide show
  1. README.md +1 -1
  2. adapter_config.json +4 -4
  3. global_step132/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  4. global_step132/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  5. global_step132/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  6. global_step132/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  7. global_step132/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  8. global_step132/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  9. global_step132/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  10. global_step132/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  11. global_step132/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  12. global_step132/zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  13. global_step132/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  14. global_step132/zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  15. global_step132/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  16. global_step132/zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  17. global_step132/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  18. global_step132/zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  19. latest +1 -1
  20. tokenizer.json +2 -2
  21. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/afz225/uncategorized/runs/o3im3z85)
31
 
32
  This model was trained with SFT.
33
 
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/afz225/uncategorized/runs/vu02b53c)
31
 
32
  This model was trained with SFT.
33
 
adapter_config.json CHANGED
@@ -23,14 +23,14 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
26
  "o_proj",
27
- "gate_proj",
28
  "lm_head",
 
29
  "v_proj",
 
30
  "up_proj",
31
- "k_proj",
32
- "down_proj",
33
- "q_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "down_proj",
27
  "o_proj",
 
28
  "lm_head",
29
+ "gate_proj",
30
  "v_proj",
31
+ "q_proj",
32
  "up_proj",
33
+ "k_proj"
 
 
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "use_dora": false,
global_step132/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:e4bbc0dad22bc25e7ccd174ae9540bee0949a3f3a29c03f00aa040726fbbcc07
3
+ size 160351592
global_step132/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 sha256:6ff39d9f8b1becd45d398490676f69677ffbce48b171b67bf590b4963b88ca71
3
+ size 2080173
global_step132/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 sha256:213b110883f4ae526e08f1951efe2598d850effee19ecbd477afc9003fbb548d
3
+ size 160351464
global_step132/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 sha256:0aa46a5e39c13d8142c77ec4af797996c0600439d8ea843ef423ddebe9bf585e
3
+ size 2080173
global_step132/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 sha256:40c5907f71e050f6d836bad018b0dde99860cde9716582923dc9007d6e32e9d7
3
+ size 160351464
global_step132/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:df73fd7cd83fb039faeaed8ee2fdcde712e283b216c038ae5150f1e60e71cba6
3
+ size 2080173
global_step132/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 sha256:63102a3915b86e990577d3a262f0f520d234362ca3bd8281f7601112c4e01bf3
3
+ size 160351464
global_step132/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 sha256:6e6909ed153b1374402074a9c11c29dd9a6649cfedb719663bb799fcff1a6223
3
+ size 2080173
global_step132/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 sha256:92fde691fa7ab4dceec31ea45f4c1dbce9da333e2526baed1e2490300f084861
3
+ size 160351464
global_step132/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 sha256:5cfce2074283eed8c564b7d6bb2f101d9571a86f7e57e89a4cad2d2a8991718a
3
+ size 2080173
global_step132/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 sha256:11dd28879adf09af844e03744dec61e5a75f7f4e3dafd981b720cdc9dee3af29
3
+ size 160351464
global_step132/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:baef6abae182a76ee975e850d8e42b59ae028aece02d75a6a5230ac14723b526
3
+ size 2080173
global_step132/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 sha256:7ee9541d7410f0267382414e31b9afd4a0b2ccb96e4fd87e3350386f21ecf80b
3
+ size 160351464
global_step132/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:ec861a6ddda3f3aab8cbddb17371a011953ba09849996bda519c1eccf0c4775a
3
+ size 2080173
global_step132/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 sha256:65d2ff7bcdde3d1418fa9f3b5d286a6b2acec951fe49aca37a5707c5999eef8c
3
+ size 160351464
global_step132/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 sha256:87ff6d78edf26d27c7b59540dc445a9b265ff76018bd347ed507ea0092b18fa3
3
+ size 2080173
latest CHANGED
@@ -1 +1 @@
1
- global_step44
 
1
+ global_step132
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 128,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 128
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 256,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 256
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2d6ee9f480a19f5f055086a83648903c4d40c3a73257bf72b182f9fc221e49d
3
  size 6968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:955bf9d747a554fd4cf098450c841b257e20b71d16648ef4e61570eff7164623
3
  size 6968