Hugging Face's logo

vineetsharma
/
qlora-adapter-Llama-2-7b-hf-databricks-dolly-15k

Safetensors
Generated from Trainer
Model card Files Community
vineetsharma commited on
Commit
8b91614
•
1 Parent(s): 014be1b

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -9
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.2222
18
 
19
  ## Model description
20
 
@@ -40,17 +40,24 @@ The following hyperparameters were used during training:
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: cosine
42
  - lr_scheduler_warmup_ratio: 0.05
43
- - training_steps: 500
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | 1.1946 | 0.01 | 100 | 1.2646 |
50
- | 1.059 | 0.02 | 200 | 1.2391 |
51
- | 1.077 | 0.02 | 300 | 1.2283 |
52
- | 1.1081 | 0.03 | 400 | 1.2234 |
53
- | 1.0519 | 0.04 | 500 | 1.2222 |
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.1313
18
 
19
  ## Model description
20
 
 
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: cosine
42
  - lr_scheduler_warmup_ratio: 0.05
43
+ - num_epochs: 1
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 1.1584 | 0.08 | 1000 | 1.1782 |
50
+ | 1.0667 | 0.17 | 2000 | 1.1710 |
51
+ | 1.0662 | 0.25 | 3000 | 1.1599 |
52
+ | 1.0517 | 0.33 | 4000 | 1.1569 |
53
+ | 1.0479 | 0.42 | 5000 | 1.1502 |
54
+ | 1.0516 | 0.5 | 6000 | 1.1441 |
55
+ | 1.0612 | 0.58 | 7000 | 1.1397 |
56
+ | 1.0235 | 0.67 | 8000 | 1.1361 |
57
+ | 1.0259 | 0.75 | 9000 | 1.1339 |
58
+ | 1.0485 | 0.83 | 10000 | 1.1320 |
59
+ | 1.0406 | 0.92 | 11000 | 1.1314 |
60
+ | 1.0393 | 1.0 | 12000 | 1.1313 |
61
 
62
 
63
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f9be2de44e8d508626ff8fdd2911a4e9b031764b0b37d0a777c499fa3794267
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dfbcd79d475f1724abd0ace43e3eabd032a531e00916824dec6b853cfa5043a
3
  size 159967880
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:869b50412bc6d679473f759dcebdc5ee6d62e2ab2002701d07a226b7cd2d51b2
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cc8752825a83eb31c94dd01451058254b748da4005afe215e47040747d5fa2b
3
  size 4091