Hugging Face's logo

Casper0508
/
MSc_llama3_finetuned_model_secondData

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Casper0508 commited on
Commit
0e96a4e
•
1 Parent(s): bef3fc5

End of training

Browse files
Files changed (5) hide show
  1. README.md +27 -27
  2. adapter_model.safetensors +1 -1
  3. emissions.csv +1 -1
  4. runs/Jul17_16-38-03_msc-modeltrain-pod/events.out.tfevents.1721234287.msc-modeltrain-pod.1471.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.7514
20
 
21
  ## Model description
22
 
@@ -49,7 +49,7 @@ The following `bitsandbytes` quantization config was used during training:
49
  ### Training hyperparameters
50
 
51
  The following hyperparameters were used during training:
52
- - learning_rate: 5e-05
53
  - train_batch_size: 16
54
  - eval_batch_size: 8
55
  - seed: 42
@@ -64,31 +64,31 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss |
66
  |:-------------:|:-----:|:----:|:---------------:|
67
- | 3.7434 | 1.33 | 10 | 3.3974 |
68
- | 2.8525 | 2.67 | 20 | 2.0794 |
69
- | 1.5978 | 4.0 | 30 | 1.2658 |
70
- | 1.1925 | 5.33 | 40 | 1.1000 |
71
- | 1.0485 | 6.67 | 50 | 1.0146 |
72
- | 0.9864 | 8.0 | 60 | 0.9634 |
73
- | 0.9086 | 9.33 | 70 | 0.9381 |
74
- | 0.8533 | 10.67 | 80 | 0.9026 |
75
- | 0.806 | 12.0 | 90 | 0.8748 |
76
- | 0.7503 | 13.33 | 100 | 0.8585 |
77
- | 0.7001 | 14.67 | 110 | 0.8435 |
78
- | 0.6531 | 16.0 | 120 | 0.8070 |
79
- | 0.5967 | 17.33 | 130 | 0.7617 |
80
- | 0.5378 | 18.67 | 140 | 0.7341 |
81
- | 0.4849 | 20.0 | 150 | 0.7263 |
82
- | 0.4607 | 21.33 | 160 | 0.7204 |
83
- | 0.4454 | 22.67 | 170 | 0.7212 |
84
- | 0.4376 | 24.0 | 180 | 0.7267 |
85
- | 0.4304 | 25.33 | 190 | 0.7319 |
86
- | 0.4154 | 26.67 | 200 | 0.7387 |
87
- | 0.4146 | 28.0 | 210 | 0.7461 |
88
- | 0.4063 | 29.33 | 220 | 0.7467 |
89
- | 0.4061 | 30.67 | 230 | 0.7471 |
90
- | 0.4042 | 32.0 | 240 | 0.7497 |
91
- | 0.4048 | 33.33 | 250 | 0.7514 |
92
 
93
 
94
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.9224
20
 
21
  ## Model description
22
 
 
49
  ### Training hyperparameters
50
 
51
  The following hyperparameters were used during training:
52
+ - learning_rate: 3e-05
53
  - train_batch_size: 16
54
  - eval_batch_size: 8
55
  - seed: 42
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss |
66
  |:-------------:|:-----:|:----:|:---------------:|
67
+ | 3.791 | 1.33 | 10 | 3.6476 |
68
+ | 3.2811 | 2.67 | 20 | 2.9195 |
69
+ | 2.3899 | 4.0 | 30 | 1.8723 |
70
+ | 1.5443 | 5.33 | 40 | 1.3519 |
71
+ | 1.2394 | 6.67 | 50 | 1.1884 |
72
+ | 1.1162 | 8.0 | 60 | 1.1023 |
73
+ | 1.0377 | 9.33 | 70 | 1.0551 |
74
+ | 0.9831 | 10.67 | 80 | 1.0228 |
75
+ | 0.9476 | 12.0 | 90 | 0.9988 |
76
+ | 0.9032 | 13.33 | 100 | 0.9850 |
77
+ | 0.8799 | 14.67 | 110 | 0.9668 |
78
+ | 0.8581 | 16.0 | 120 | 0.9503 |
79
+ | 0.8315 | 17.33 | 130 | 0.9457 |
80
+ | 0.8077 | 18.67 | 140 | 0.9422 |
81
+ | 0.7921 | 20.0 | 150 | 0.9362 |
82
+ | 0.7752 | 21.33 | 160 | 0.9318 |
83
+ | 0.7614 | 22.67 | 170 | 0.9306 |
84
+ | 0.7559 | 24.0 | 180 | 0.9233 |
85
+ | 0.7441 | 25.33 | 190 | 0.9237 |
86
+ | 0.7345 | 26.67 | 200 | 0.9237 |
87
+ | 0.7341 | 28.0 | 210 | 0.9205 |
88
+ | 0.7288 | 29.33 | 220 | 0.9195 |
89
+ | 0.7237 | 30.67 | 230 | 0.9219 |
90
+ | 0.7255 | 32.0 | 240 | 0.9210 |
91
+ | 0.7273 | 33.33 | 250 | 0.9224 |
92
 
93
 
94
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:983b0fd0da103fa514fc7e246e4acba49d300060c120d6a082c6d041efe8ec2b
3
  size 75523312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e4c8865b08c12ceac25c011d87948ac0e7211cabbde5084dc52c8b2b6ab979
3
  size 75523312
emissions.csv CHANGED
@@ -1,2 +1,2 @@
1
  timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
2
- 2024-07-17T16:35:43,79221d90-c4ed-4872-8839-0ffb118e6ba5,codecarbon,707.8558206558228,0.047920488938631406,0.07129868064910394,United Kingdom,GBR,scotland,N,,
 
1
  timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
2
+ 2024-07-17T16:49:56,14ad89ba-873d-4177-8763-006e7acb7e4e,codecarbon,708.9762728214264,0.049197013388741065,0.07319796237858917,United Kingdom,GBR,scotland,N,,
runs/Jul17_16-38-03_msc-modeltrain-pod/events.out.tfevents.1721234287.msc-modeltrain-pod.1471.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc67f7e75bc9755364788d8bbcc442ee3dbd0eb9d8586adba28eff479072d83
3
+ size 17468
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac52630f40163a6513db9e406782ef4286a5aba7e7fc5f1ef142bb32afb460a1
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a734bbf314d44fae2a458e8b7d37bcf2e0accb9a4366f729a3412790bc98da
3
  size 4984