Hugging Face's logo

megha-shroff
/
mistral-rand-300k

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
megha-shroff commited on
Commit
6c9fc14
•
1 Parent(s): 0204bbf

End of training

Browse files
Files changed (5) hide show
  1. .amlignore +6 -0
  2. .amlignore.amltmp +6 -0
  3. README.md +3 -11
  4. adapter_model.safetensors +1 -1
  5. training_args.bin +1 -1
.amlignore ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ ## This file was auto generated by the Azure Machine Learning Studio. Please do not remove.
2
+ ## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
3
+
4
+ .ipynb_aml_checkpoints/
5
+ *.amltmp
6
+ *.amltemp
.amlignore.amltmp ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ ## This file was auto generated by the Azure Machine Learning Studio. Please do not remove.
2
+ ## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
3
+
4
+ .ipynb_aml_checkpoints/
5
+ *.amltmp
6
+ *.amltemp
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3536
22
 
23
  ## Model description
24
 
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
- - training_steps: 12850
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
@@ -298,15 +298,7 @@ The following hyperparameters were used during training:
298
  | 0.3514 | 3.95 | 12300 | 0.3548 |
299
  | 0.3556 | 3.96 | 12350 | 0.3547 |
300
  | 0.3549 | 3.98 | 12400 | 0.3545 |
301
- | 0.3541 | 4.0 | 12450 | 0.3542 |
302
- | 0.3477 | 4.01 | 12500 | 0.3551 |
303
- | 0.3449 | 4.03 | 12550 | 0.3542 |
304
- | 0.3426 | 4.04 | 12600 | 0.3552 |
305
- | 0.3411 | 4.06 | 12650 | 0.3545 |
306
- | 0.3476 | 4.08 | 12700 | 0.3540 |
307
- | 0.3547 | 4.09 | 12750 | 0.3536 |
308
- | 0.3529 | 4.11 | 12800 | 0.3537 |
309
- | 0.3374 | 2.06 | 12850 | 0.3536 |
310
 
311
 
312
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3545
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
+ - training_steps: 12450
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
 
298
  | 0.3514 | 3.95 | 12300 | 0.3548 |
299
  | 0.3556 | 3.96 | 12350 | 0.3547 |
300
  | 0.3549 | 3.98 | 12400 | 0.3545 |
301
+ | 0.3454 | 2.0 | 12450 | 0.3545 |
 
 
 
 
 
 
 
 
302
 
303
 
304
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf34bab6568ddda35b33eab99ededacf76455e13fce7305458a39b61716f837d
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69c4efaadc778deec605b0e70d1354f1a936a339e1b03717e67df4450b44fad
3
  size 109069176
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:549515421a3e673de404ca707c050e805d91eca6172fc2362d9da44fd60cd815
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2057acfc7ed13f07f06400d82a58eeadb57db980ab9bf38e1473a7b9b7ba08c1
3
  size 4664