Hugging Face's logo

ssarkar4445
/
OpenHathi-7B-v0.1-instruct

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Metrics Community
ssarkar4445 commited on
Commit
c746396
·
verified ·
1 Parent(s): 0f30093

Model save

Browse files
Files changed (5) hide show
  1. README.md +5 -6
  2. adapter_config.json +6 -6
  3. adapter_model.safetensors +1 -1
  4. runs/Jan30_12-00-05_955bf6fd82a0/events.out.tfevents.1706616009.955bf6fd82a0.1214.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [sarvamai/OpenHathi-7B-Hi-v0.1-Base](https://huggingface.co/sarvamai/OpenHathi-7B-Hi-v0.1-Base) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.0433
24
 
25
  ## Model description
26
 
@@ -48,20 +48,19 @@ The following hyperparameters were used during training:
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: cosine
50
  - lr_scheduler_warmup_ratio: 0.03
51
- - num_epochs: 3
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss |
56
  |:-------------:|:-----:|:----:|:---------------:|
57
- | 1.173 | 0.97 | 21 | 1.0945 |
58
- | 0.8513 | 1.98 | 43 | 1.0247 |
59
- | 0.671 | 2.9 | 63 | 1.0433 |
60
 
61
 
62
  ### Framework versions
63
 
64
- - PEFT 0.8.1.dev0
65
  - Transformers 4.38.0.dev0
66
  - Pytorch 2.1.1+cu121
67
  - Datasets 2.16.1
 
20
 
21
  This model is a fine-tuned version of [sarvamai/OpenHathi-7B-Hi-v0.1-Base](https://huggingface.co/sarvamai/OpenHathi-7B-Hi-v0.1-Base) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.0218
24
 
25
  ## Model description
26
 
 
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: cosine
50
  - lr_scheduler_warmup_ratio: 0.03
51
+ - num_epochs: 2
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss |
56
  |:-------------:|:-----:|:----:|:---------------:|
57
+ | 1.1606 | 0.97 | 21 | 1.0843 |
58
+ | 0.9479 | 1.93 | 42 | 1.0218 |
 
59
 
60
 
61
  ### Framework versions
62
 
63
+ - PEFT 0.8.2.dev0
64
  - Transformers 4.38.0.dev0
65
  - Pytorch 2.1.1+cu121
66
  - Datasets 2.16.1
adapter_config.json CHANGED
@@ -19,15 +19,15 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
- "embed_tokens",
24
- "k_proj",
25
- "lm_head",
26
  "down_proj",
 
27
  "gate_proj",
28
- "v_proj",
 
29
  "up_proj",
30
- "o_proj"
 
 
31
  ],
32
  "task_type": "CAUSAL_LM",
33
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
 
 
22
  "down_proj",
23
+ "k_proj",
24
  "gate_proj",
25
+ "embed_tokens",
26
+ "o_proj",
27
  "up_proj",
28
+ "v_proj",
29
+ "q_proj",
30
+ "lm_head"
31
  ],
32
  "task_type": "CAUSAL_LM",
33
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35e04e98669f165f170b9f6e53412e6c02e6694c7a944173b4077e99990d8d46
3
  size 829319376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d7b7b440021ef5aca214f2740a41b0ca61dd99aa5ad83a0f888007e8408e2a
3
  size 829319376
runs/Jan30_12-00-05_955bf6fd82a0/events.out.tfevents.1706616009.955bf6fd82a0.1214.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940d128f3356c16eed061c7420fb58f0f3ecd95854ee06afbe13b2f71e651d36
3
+ size 7011
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b02d9bc8a8b64747526cc632f267b52d13bb8481f54d7d5ceb05c31d420fcd9e
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:535d1daa487e26923efd85d27f368732ca947935cc0761d8cb7e57ee547b4c54
3
  size 4792