Hugging Face's logo

Viral04
/
mistral_instruct_generation

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
Viral04 commited on
Commit
750eef3
·
verified ·
1 Parent(s): 0cda341

Viral04/CUAD_Finetuned

Browse files
Files changed (5) hide show
  1. README.md +7 -6
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Mar18_18-30-59_96cb8199a2b8/events.out.tfevents.1710786878.96cb8199a2b8.7106.0 +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 [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.9593
24
 
25
  ## Model description
26
 
@@ -47,16 +47,17 @@ The following hyperparameters were used during training:
47
  - lr_scheduler_type: constant
48
  - lr_scheduler_warmup_steps: 0.03
49
  - training_steps: 100
 
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 2.0288 | 0.08 | 20 | 2.0121 |
56
- | 1.9859 | 0.15 | 40 | 1.9932 |
57
- | 1.972 | 0.23 | 60 | 1.9786 |
58
- | 1.9645 | 0.3 | 80 | 1.9665 |
59
- | 1.9412 | 0.38 | 100 | 1.9593 |
60
 
61
 
62
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.3202
24
 
25
  ## Model description
26
 
 
47
  - lr_scheduler_type: constant
48
  - lr_scheduler_warmup_steps: 0.03
49
  - training_steps: 100
50
+ - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
+ | 1.4597 | 0.0 | 20 | 1.3668 |
57
+ | 1.4026 | 0.0 | 40 | 1.3473 |
58
+ | 1.4525 | 0.01 | 60 | 1.3343 |
59
+ | 1.4547 | 0.01 | 80 | 1.3256 |
60
+ | 1.3827 | 0.01 | 100 | 1.3202 |
61
 
62
 
63
  ### Framework versions
adapter_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
- "v_proj"
24
  ],
25
  "task_type": "CAUSAL_LM",
26
  "use_dora": false,
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
  ],
25
  "task_type": "CAUSAL_LM",
26
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e9c124e121eaddca720d28beb16bb93e5eddf604e438974518a186a6ec0bff
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d43695c5203ee288accbe923024837c40f7bc415d9c9d4cf8af56b443321eee
3
  size 109069176
runs/Mar18_18-30-59_96cb8199a2b8/events.out.tfevents.1710786878.96cb8199a2b8.7106.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d266280f6f102b1a66fdb1d5f3f7a09b64ab53483689eed7a69701c9cd3e77fe
3
+ size 8797
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d27596c137feb8f6dd02e2e57d273d2c071c80a5ae1178485acdc361c7163a5
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d31ea7a93f15082ed5c9492a7e9b967b2ae13c52d5242a45d4e54d216bb1897
3
  size 4920