Hugging Face's logo

deboramachadoandrade
/
mistral7binstruct_summarize

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
deboramachadoandrade commited on
Commit
dbbff83
·
verified ·
1 Parent(s): f352201

<deboramachadoandrade>/mistral-7binstruct-summary-100s

Browse files
Files changed (5) hide show
  1. README.md +6 -10
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Mar04_23-52-56_19d606c365e8/events.out.tfevents.1709596378.19d606c365e8.3636.0 +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-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.5221
24
 
25
  ## Model description
26
 
@@ -46,20 +46,16 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: cosine
48
  - lr_scheduler_warmup_steps: 3
49
- - training_steps: 200
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 1.6694 | 0.03 | 25 | 1.6401 |
56
- | 1.5146 | 0.05 | 50 | 1.5519 |
57
- | 1.5803 | 0.08 | 75 | 1.5408 |
58
- | 1.5458 | 0.11 | 100 | 1.5345 |
59
- | 1.4207 | 0.13 | 125 | 1.5274 |
60
- | 1.5952 | 0.16 | 150 | 1.5242 |
61
- | 1.5299 | 0.19 | 175 | 1.5224 |
62
- | 1.5765 | 0.22 | 200 | 1.5221 |
63
 
64
 
65
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.4587
24
 
25
  ## Model description
26
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: cosine
48
  - lr_scheduler_warmup_steps: 3
49
+ - training_steps: 100
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
+ | 1.6938 | 0.22 | 25 | 1.5762 |
56
+ | 1.5801 | 0.43 | 50 | 1.4713 |
57
+ | 1.5327 | 0.65 | 75 | 1.4617 |
58
+ | 1.5411 | 0.86 | 100 | 1.4587 |
 
 
 
 
59
 
60
 
61
  ### Framework versions
adapter_config.json CHANGED
@@ -19,8 +19,8 @@
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,
 
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,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61bcd0a374135e4c249d5aec3ce1b64e10a87bf1955f8b777da2bbcad519c9e8
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8144a3b3e7bfa33c88b35a1d1f62f6401a643fd009b109774c7142df3d8b7e3f
3
  size 27280152
runs/Mar04_23-52-56_19d606c365e8/events.out.tfevents.1709596378.19d606c365e8.3636.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea8a296479e639e34d608e3d77e8b6541533dfece70ddec2a8dcb4232c2c60f
3
+ size 8529
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c450e5d116b364cdc20420171fc71cf9dd93b778b22228cb000fb5706d15ef16
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f545718b2b127ca21456e3fbf192f30e091286e3cfebd02cd9980d5a052a8062
3
  size 4920