Hugging Face's logo

mitultiwari
/
mistral7binstruct_summarize

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
mitultiwari commited on
Commit
1949e78
•
1 Parent(s): c00bc44

mitultiwari/mistral-7b-instruct-summarization-sft-2

Browse files
Files changed (4) hide show
  1. README.md +22 -5
  2. adapter_model.safetensors +1 -1
  3. runs/Mar04_00-46-55_8982399105cf/events.out.tfevents.1709513222.8982399105cf.6924.1 +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 [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.4712
24
 
25
  ## Model description
26
 
@@ -45,15 +45,32 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
- - lr_scheduler_warmup_steps: 0.03
49
- - training_steps: 50
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 1.7461 | 0.22 | 25 | 1.5484 |
56
- | 1.5634 | 0.43 | 50 | 1.4712 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.7060
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
+ - training_steps: 500
 
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.7472 | 0.22 | 25 | 1.5467 |
55
+ | 1.5628 | 0.43 | 50 | 1.4716 |
56
+ | 1.5515 | 0.65 | 75 | 1.4513 |
57
+ | 1.4966 | 0.87 | 100 | 1.4446 |
58
+ | 1.4953 | 1.09 | 125 | 1.4509 |
59
+ | 1.4828 | 1.3 | 150 | 1.4492 |
60
+ | 1.4245 | 1.52 | 175 | 1.4513 |
61
+ | 1.4047 | 1.74 | 200 | 1.4539 |
62
+ | 1.4715 | 1.96 | 225 | 1.4541 |
63
+ | 1.3183 | 2.17 | 250 | 1.4828 |
64
+ | 1.2847 | 2.39 | 275 | 1.4780 |
65
+ | 1.3934 | 2.61 | 300 | 1.4872 |
66
+ | 1.3141 | 2.83 | 325 | 1.4947 |
67
+ | 1.2404 | 3.04 | 350 | 1.5483 |
68
+ | 1.1593 | 3.26 | 375 | 1.5560 |
69
+ | 1.151 | 3.48 | 400 | 1.5593 |
70
+ | 1.1381 | 3.7 | 425 | 1.5506 |
71
+ | 1.2021 | 3.91 | 450 | 1.5614 |
72
+ | 0.9731 | 4.13 | 475 | 1.6335 |
73
+ | 0.9721 | 4.35 | 500 | 1.7060 |
74
 
75
 
76
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:231466cdc2b072fc42f52110cca8d5556b64ff7081cf86b445c809132aca0efc
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ff223b1af3be064011bc009b848f384ff6cfddec45cc4d091f8b547e364f28
3
  size 27280152
runs/Mar04_00-46-55_8982399105cf/events.out.tfevents.1709513222.8982399105cf.6924.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c2baf32aaf72d4a92f61f09b9390a7abde7d686b3f79c61ad81704db0228d72
3
+ size 21300
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:effda184743792267f6dc17f3bf630c7b79cf770218aadd674de247113a2c0cb
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31bcea126e961673c26009cec18453ab73e149c638b0c4b63ad4b97aebb6fc91
3
  size 4920