Hugging Face's logo

greatakela
/
mistral_instruct_generation

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
greatakela commited on
Commit
6ec8a25
·
1 Parent(s): 48a207b

greatakela/mistral-instruct-generation

Browse files
Files changed (5) hide show
  1. README.md +7 -13
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Nov27_04-03-17_cece61c58921/events.out.tfevents.1701057808.cece61c58921.1211.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.9044
 
 
 
 
 
19
 
20
  ## Model description
21
 
@@ -41,18 +46,7 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: constant
43
  - lr_scheduler_warmup_steps: 0.03
44
- - training_steps: 100
45
-
46
- ### Training results
47
-
48
- | Training Loss | Epoch | Step | Validation Loss |
49
- |:-------------:|:-----:|:----:|:---------------:|
50
- | 1.0537 | 0.04 | 20 | 1.0320 |
51
- | 0.9374 | 0.08 | 40 | 0.9537 |
52
- | 0.8803 | 0.12 | 60 | 0.9245 |
53
- | 0.8258 | 0.17 | 80 | 0.9054 |
54
- | 0.7823 | 0.21 | 100 | 0.9044 |
55
-
56
 
57
  ### Framework versions
58
 
 
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 1.0472
19
+ - eval_runtime: 4.2822
20
+ - eval_samples_per_second: 79.399
21
+ - eval_steps_per_second: 10.042
22
+ - epoch: 0.62
23
+ - step: 300
24
 
25
  ## Model description
26
 
 
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: 500
 
 
 
 
 
 
 
 
 
 
 
50
 
51
  ### Framework versions
52
 
adapter_config.json CHANGED
@@ -16,8 +16,8 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "v_proj",
20
- "q_proj"
21
  ],
22
  "task_type": "CAUSAL_LM"
23
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
  ],
22
  "task_type": "CAUSAL_LM"
23
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2597e08cb817e5fbfc3fa0cda6aeed21d7ec5e171a4602b9ddc31d15df78757
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac04a488d6295f898ea67e545e265ed262cf5077694c8bd7d3502041af20ae12
3
  size 109069176
runs/Nov27_04-03-17_cece61c58921/events.out.tfevents.1701057808.cece61c58921.1211.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc3ba59d581bc47c664998b92fc63213fcf64a430acff585d4db12f40de95b1
3
+ size 10904
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48a0d6002d66e308d2235a229a4f6210bb9a9641ac6483756df1fbe994531412
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f12494cf93aee05d3c2e95b842f76b943fba9dfe078ef03a73e012290d4bc0
3
  size 4600