Hugging Face's logo

Magpie-Align
/
Llama-3-8B-OpenHermes-243K

Text Generation
Transformers
PyTorch
Safetensors
llama
axolotl
Generated from Trainer
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
flydust commited on
Commit
31563e4
•
1 Parent(s): 75beeb3

End of training

Browse files
Files changed (9) hide show
  1. README.md +9 -9
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. pytorch_model-00001-of-00004.bin +1 -1
  7. pytorch_model-00002-of-00004.bin +1 -1
  8. pytorch_model-00003-of-00004.bin +1 -1
  9. pytorch_model-00004-of-00004.bin +1 -1
README.md CHANGED
@@ -26,8 +26,8 @@ load_in_4bit: false
26
  strict: false
27
 
28
  datasets:
29
- - path: teknium/openhermes
30
- type: alpaca
31
  conversation: llama3
32
  dataset_prepared_path: last_run_prepared
33
  val_set_size: 0.001
@@ -87,7 +87,7 @@ special_tokens:
87
 
88
  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.
89
  It achieves the following results on the evaluation set:
90
- - Loss: 1.2397
91
 
92
  ## Model description
93
 
@@ -124,12 +124,12 @@ The following hyperparameters were used during training:
124
 
125
  | Training Loss | Epoch | Step | Validation Loss |
126
  |:-------------:|:------:|:----:|:---------------:|
127
- | 0.6409 | 0.0032 | 1 | 1.7961 |
128
- | 0.5064 | 0.3347 | 103 | 1.3826 |
129
- | 0.4803 | 0.6694 | 206 | 1.2820 |
130
- | 0.4433 | 1.0041 | 309 | 1.2518 |
131
- | 0.362 | 1.3258 | 412 | 1.2406 |
132
- | 0.4022 | 1.6604 | 515 | 1.2397 |
133
 
134
 
135
  ### Framework versions
 
26
  strict: false
27
 
28
  datasets:
29
+ - path: mahiatlinux/OpenHermes-v1-ShareGPT
30
+ type: sharegpt
31
  conversation: llama3
32
  dataset_prepared_path: last_run_prepared
33
  val_set_size: 0.001
 
87
 
88
  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.
89
  It achieves the following results on the evaluation set:
90
+ - Loss: 0.9845
91
 
92
  ## Model description
93
 
 
124
 
125
  | Training Loss | Epoch | Step | Validation Loss |
126
  |:-------------:|:------:|:----:|:---------------:|
127
+ | 0.762 | 0.0033 | 1 | 3.9196 |
128
+ | 0.5197 | 0.3336 | 101 | 1.1073 |
129
+ | 0.4766 | 0.6672 | 202 | 1.0158 |
130
+ | 0.4366 | 1.0008 | 303 | 0.9940 |
131
+ | 0.3358 | 1.3216 | 404 | 0.9868 |
132
+ | 0.3299 | 1.6552 | 505 | 0.9845 |
133
 
134
 
135
  ### Framework versions
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5706a8464f7a6dae29fd5e4ae3718c65d79dc60eaf2a9bb65b5b1adb1fa4662b
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:569b077978d10c45debd4b744d4d95d158b6ae009c3b1b2ef979114146fd6095
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6497af56dba61ec24d609e41a636eb4f3c692daa8d6ba4c126031c6adced656e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad3705f3e73da777836577610a07a7ec68f4884add3faddeedfc2173571a38f
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:373259460b7934882826f910bb1056364abe98dd322d01d5c9fd4c71d384d8cc
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8872677789e1b41bb3588dfadf82ecef45cac3a823afd149d3938158c3f0deb
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f5e6e3e49c12e375895a2860f41099855f0d051e13db40b3cafe2f776734c83
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:238161ce90f4df7a5b9c2ca954ffd08d23b10b78ac1db572b574d23fe5b36084
3
  size 1168138808
pytorch_model-00001-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3384a7e35da80e743d499d517bf439e72cec29f78eca995a825ed843ebb931c6
3
  size 4976718466
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b2384f7fd1b99d1ad6e5c89c455e4bfda15f6750e71c9d9ca18d0d2df700d4
3
  size 4976718466
pytorch_model-00002-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d5b1a1921f1b62a055efe775a088cb8b3db8562cb3a96825096dc36b01723ca
3
  size 4999827718
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f985afab5723d0fa92476fd759864d61d11961fa022e89a2ae095c1a7ae8c93d
3
  size 4999827718
pytorch_model-00003-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da506e00853eabbdb3f9c9cf44dbefc64cd7c24a6b7aa93e539a3dd03308fcc1
3
  size 4915940170
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e907e6868a560ac2a08878d2948531f694d2e1feb552de2753a53cf28343fb8
3
  size 4915940170
pytorch_model-00004-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8766bd30d4d798cbf48638b3aa40183c27bdd1f731c9b8b77251600e96fc3626
3
  size 1168140873
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42643403e07c6e7f7392dae4fc6a0eb314b6a09bf5e4bfd64e1989d6f1928ec
3
  size 1168140873