Hugging Face's logo

Jukaboo
/
Llama2_7B_chat_LR

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Jukaboo commited on
Commit
e690022
•
1 Parent(s): cfed544

End of training

Browse files
Files changed (4) hide show
  1. README.md +8 -8
  2. adapter_model.safetensors +1 -1
  3. runs/Dec01_13-48-13_7f9337b2413a/events.out.tfevents.1701438543.7f9337b2413a.22338.0 +3 -0
  4. 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-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.1425
18
 
19
  ## Model description
20
 
@@ -34,11 +34,11 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.0002
37
- - train_batch_size: 4
38
  - eval_batch_size: 8
39
  - seed: 42
40
- - gradient_accumulation_steps: 4
41
- - total_train_batch_size: 16
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.05
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 2.2348 | 0.2 | 13 | 2.3243 |
53
- | 2.1848 | 0.4 | 26 | 2.2166 |
54
- | 2.2501 | 0.6 | 39 | 2.1606 |
55
- | 2.2727 | 0.8 | 52 | 2.1425 |
56
 
57
 
58
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 2.2693
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.0002
37
+ - train_batch_size: 6
38
  - eval_batch_size: 8
39
  - seed: 42
40
+ - gradient_accumulation_steps: 6
41
+ - total_train_batch_size: 36
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.05
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 2.5075 | 0.21 | 6 | 2.4168 |
53
+ | 2.29 | 0.42 | 12 | 2.3278 |
54
+ | 2.2582 | 0.62 | 18 | 2.2871 |
55
+ | 2.3052 | 0.83 | 24 | 2.2693 |
56
 
57
 
58
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90d90d672ab33e4fd5ed637a5545318d655334def584db4f73be6d14f45129a6
3
  size 16794200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ad302964c81974baedd96b4bf11832af183b6a1fc6761fe8f09d404a37f1de
3
  size 16794200
runs/Dec01_13-48-13_7f9337b2413a/events.out.tfevents.1701438543.7f9337b2413a.22338.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec31ffaedb464b438a03a30c40297af9b2fe5f686ebd97c250878e4376cabf1
3
+ size 10361
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deb1b020e419fe2bfe59babcdcecc69adff48514ea87307d37ed763d8a2e2d9e
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25882701440621fcd872e447278faee768d119c9b8fdc5582da157c741e1ce3
3
  size 4600