Hugging Face's logo

vpkrishna
/
llama38binstruct_summarize

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
vpkrishna commited on
Commit
80b9f7e
•
1 Parent(s): f740f46

llm/llama38binstruct-summary-100s

Browse files
Files changed (4) hide show
  1. README.md +7 -15
  2. adapter_model.safetensors +2 -2
  3. runs/Jun19_04-27-12_0113f146e29c/events.out.tfevents.1718771246.0113f146e29c.1122.6 +3 -0
  4. 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 [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 3.2478
24
 
25
  ## Model description
26
 
@@ -39,7 +39,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 0.0001
43
  - train_batch_size: 2
44
  - eval_batch_size: 8
45
  - seed: 42
@@ -48,24 +48,16 @@ The following hyperparameters were used during training:
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: constant
50
  - lr_scheduler_warmup_steps: 10
51
- - training_steps: 300
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss |
56
  |:-------------:|:-----:|:----:|:---------------:|
57
- | 0.0063 | 10.0 | 25 | 2.9544 |
58
- | 0.0033 | 20.0 | 50 | 3.1133 |
59
- | 0.0057 | 30.0 | 75 | 2.5821 |
60
- | 0.0032 | 40.0 | 100 | 2.9857 |
61
- | 0.0021 | 50.0 | 125 | 3.1502 |
62
- | 0.0019 | 60.0 | 150 | 3.0546 |
63
- | 0.0026 | 70.0 | 175 | 2.7894 |
64
- | 0.0045 | 80.0 | 200 | 2.6616 |
65
- | 0.0014 | 90.0 | 225 | 3.1916 |
66
- | 0.0009 | 100.0 | 250 | 3.2146 |
67
- | 0.0007 | 110.0 | 275 | 3.2346 |
68
- | 0.0006 | 120.0 | 300 | 3.2478 |
69
 
70
 
71
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 2.8113
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 1e-05
43
  - train_batch_size: 2
44
  - eval_batch_size: 8
45
  - seed: 42
 
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: constant
50
  - lr_scheduler_warmup_steps: 10
51
+ - training_steps: 100
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss |
56
  |:-------------:|:-----:|:----:|:---------------:|
57
+ | 2.3176 | 10.0 | 25 | 2.8113 |
58
+ | 2.3111 | 20.0 | 50 | 2.8113 |
59
+ | 2.3098 | 30.0 | 75 | 2.8113 |
60
+ | 2.3188 | 40.0 | 100 | 2.8113 |
 
 
 
 
 
 
 
 
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:ef728538a619ab3e4f2aa024958451bbd939b654cde566a8a811535264e05487
3
- size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
3
+ size 48
runs/Jun19_04-27-12_0113f146e29c/events.out.tfevents.1718771246.0113f146e29c.1122.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5329dace34d485bd18ce3c6d5f1c91551e37130c2869f081938d5b56cd7d5c0a
3
+ size 9236
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da7ab063a3e2ac331c4fbea43e632b2ee7ef1029442c59327726294ac03a99a1
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e39e9be223e4e51725d5a54334094cd4d30b30442d71c05ce7347ff488a3f1
3
  size 5432