HeRksTAn commited on
Commit
8a252cd
1 Parent(s): a6daa8c

markat1/mistral-7binstruct-summary-100s

Browse files
README.md CHANGED
@@ -20,12 +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
- - eval_loss: 2.0198
24
- - eval_runtime: 34.7344
25
- - eval_samples_per_second: 2.706
26
- - eval_steps_per_second: 0.345
27
- - epoch: 0.06
28
- - step: 15
29
 
30
  ## Model description
31
 
@@ -55,6 +50,42 @@ The following hyperparameters were used during training:
55
  - lr_scheduler_warmup_steps: 0.03
56
  - training_steps: 150
57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  ### Framework versions
59
 
60
  - PEFT 0.9.0
 
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: 1.6323
 
 
 
 
 
24
 
25
  ## Model description
26
 
 
50
  - lr_scheduler_warmup_steps: 0.03
51
  - training_steps: 150
52
 
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 2.5172 | 0.02 | 5 | 2.3926 |
58
+ | 2.2822 | 0.04 | 10 | 2.1537 |
59
+ | 2.1109 | 0.06 | 15 | 2.0087 |
60
+ | 1.8571 | 0.08 | 20 | 1.9020 |
61
+ | 1.8964 | 0.11 | 25 | 1.8310 |
62
+ | 1.7335 | 0.13 | 30 | 1.7901 |
63
+ | 1.7744 | 0.15 | 35 | 1.7607 |
64
+ | 1.8654 | 0.17 | 40 | 1.7396 |
65
+ | 1.7379 | 0.19 | 45 | 1.7235 |
66
+ | 1.7442 | 0.21 | 50 | 1.7113 |
67
+ | 1.6483 | 0.23 | 55 | 1.7011 |
68
+ | 1.7006 | 0.25 | 60 | 1.6919 |
69
+ | 1.6783 | 0.28 | 65 | 1.6833 |
70
+ | 1.6468 | 0.3 | 70 | 1.6754 |
71
+ | 1.6116 | 0.32 | 75 | 1.6678 |
72
+ | 1.5899 | 0.34 | 80 | 1.6605 |
73
+ | 1.7426 | 0.36 | 85 | 1.6538 |
74
+ | 1.7244 | 0.38 | 90 | 1.6491 |
75
+ | 1.6652 | 0.4 | 95 | 1.6457 |
76
+ | 1.7859 | 0.42 | 100 | 1.6422 |
77
+ | 1.5836 | 0.44 | 105 | 1.6395 |
78
+ | 1.6265 | 0.47 | 110 | 1.6374 |
79
+ | 1.5187 | 0.49 | 115 | 1.6358 |
80
+ | 1.5989 | 0.51 | 120 | 1.6345 |
81
+ | 1.684 | 0.53 | 125 | 1.6336 |
82
+ | 1.6257 | 0.55 | 130 | 1.6329 |
83
+ | 1.7211 | 0.57 | 135 | 1.6325 |
84
+ | 1.6235 | 0.59 | 140 | 1.6324 |
85
+ | 1.5885 | 0.61 | 145 | 1.6323 |
86
+ | 1.5885 | 0.64 | 150 | 1.6323 |
87
+
88
+
89
  ### Framework versions
90
 
91
  - PEFT 0.9.0
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c60b8684e4fc174c64ee65169402174c73475b89d27b094a13d5b595591bc30c
3
- size 54543184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080c32c9d89e81893201d215084cb22ab2f799026d585afbd68f47a470b902f4
3
+ size 54545360
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e328bed096c7f01176f4ccaa21df959a73c03b0f481e67f80ac001bf2d078c94
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7a5483a6ddb2a94c9643206dd99b771e6991fc0b125c048d43ce7d87461ad4
3
  size 4920