Hugging Face's logo

xz-huggingface-0
/
zephyr-7b-sft-lora

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
xz-huggingface-0 commited on
Commit
2dee8cf
•
1 Parent(s): cdf4c7f

Model save

Browse files
Files changed (7) hide show
  1. README.md +2 -2
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. all_results.json +3 -8
  5. train_results.json +3 -3
  6. trainer_state.json +7 -7
  7. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.0664
19
 
20
  ## Model description
21
 
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | 1.0705 | 0.67 | 34 | 1.0662 |
55
 
56
 
57
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.0663
19
 
20
  ## Model description
21
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.0705 | 0.67 | 34 | 1.0663 |
55
 
56
 
57
  ### Framework versions
adapter_config.json CHANGED
@@ -16,10 +16,10 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "q_proj",
20
- "o_proj",
21
  "k_proj",
22
- "v_proj"
 
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "k_proj",
20
+ "v_proj",
21
+ "q_proj",
22
+ "o_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e19f497c1a2314d323c7c294be89240e3bc32be6b039941943df639a83419bc0
3
  size 109086672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd98740d75b764bd1cc3fcb15fb21ba7ffbf4fe912ea54260aa2eb01248a70b2
3
  size 109086672
all_results.json CHANGED
@@ -1,13 +1,8 @@
1
  {
2
  "epoch": 0.67,
3
- "eval_loss": 1.0663659572601318,
4
- "eval_runtime": 360.1757,
5
- "eval_samples": 23110,
6
- "eval_samples_per_second": 64.163,
7
- "eval_steps_per_second": 1.005,
8
- "train_loss": 1.091969286694246,
9
- "train_runtime": 10565.8845,
10
  "train_samples": 207865,
11
- "train_samples_per_second": 19.673,
12
  "train_steps_per_second": 0.005
13
  }
 
1
  {
2
  "epoch": 0.67,
3
+ "train_loss": 1.0919693988912247,
4
+ "train_runtime": 10567.5625,
 
 
 
 
 
5
  "train_samples": 207865,
6
+ "train_samples_per_second": 19.67,
7
  "train_steps_per_second": 0.005
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.67,
3
- "train_loss": 1.091969286694246,
4
- "train_runtime": 10565.8845,
5
  "train_samples": 207865,
6
- "train_samples_per_second": 19.673,
7
  "train_steps_per_second": 0.005
8
  }
 
1
  {
2
  "epoch": 0.67,
3
+ "train_loss": 1.0919693988912247,
4
+ "train_runtime": 10567.5625,
5
  "train_samples": 207865,
6
+ "train_samples_per_second": 19.67,
7
  "train_steps_per_second": 0.005
8
  }
trainer_state.json CHANGED
@@ -52,19 +52,19 @@
52
  },
53
  {
54
  "epoch": 0.67,
55
- "eval_loss": 1.066247820854187,
56
- "eval_runtime": 359.3813,
57
- "eval_samples_per_second": 64.305,
58
- "eval_steps_per_second": 1.007,
59
  "step": 34
60
  },
61
  {
62
  "epoch": 0.67,
63
  "step": 34,
64
  "total_flos": 5.175876094263296e+16,
65
- "train_loss": 1.091969286694246,
66
- "train_runtime": 10565.8845,
67
- "train_samples_per_second": 19.673,
68
  "train_steps_per_second": 0.005
69
  }
70
  ],
 
52
  },
53
  {
54
  "epoch": 0.67,
55
+ "eval_loss": 1.066256046295166,
56
+ "eval_runtime": 359.6899,
57
+ "eval_samples_per_second": 64.25,
58
+ "eval_steps_per_second": 1.006,
59
  "step": 34
60
  },
61
  {
62
  "epoch": 0.67,
63
  "step": 34,
64
  "total_flos": 5.175876094263296e+16,
65
+ "train_loss": 1.0919693988912247,
66
+ "train_runtime": 10567.5625,
67
+ "train_samples_per_second": 19.67,
68
  "train_steps_per_second": 0.005
69
  }
70
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c2c56271c5d9179a88d13f67a03da9a745a966c640935167f20ae45263a8e7b
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9977e48f8d6567c3265a35aa99f23ba670f89bbf8dea7abf2cdbb0ce4deb9178
3
  size 5624