Hugging Face's logo

mlfoundations-dev
/
mistral_alpaca_sft_sample_4

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
4739a6f
·
verified ·
1 Parent(s): de7c621

End of training

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. all_results.json +7 -7
  3. eval_results.json +4 -4
  4. model-00001-of-00003.safetensors +1 -1
  5. model-00002-of-00003.safetensors +1 -1
  6. model-00003-of-00003.safetensors +1 -1
  7. train_results.json +3 -3
  8. trainer_state.json +7 -7
  9. training_args.bin +1 -1
  10. training_eval_loss.png +0 -0
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 [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the llamafactory/alpaca_en dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.6951
22
 
23
  ## Model description
24
 
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:----:|:---------------:|
58
- | No log | 0.1304 | 3 | 1.6951 |
59
 
60
 
61
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the llamafactory/alpaca_en dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.6958
22
 
23
  ## Model description
24
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:----:|:---------------:|
58
+ | No log | 0.1304 | 3 | 1.6958 |
59
 
60
 
61
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 0.13043478260869565,
3
- "eval_loss": 1.6950849294662476,
4
- "eval_runtime": 2.1355,
5
- "eval_samples_per_second": 288.927,
6
- "eval_steps_per_second": 4.683,
7
  "total_flos": 3.355230384370483e+16,
8
- "train_loss": 1.413622538248698,
9
- "train_runtime": 202.5208,
10
- "train_samples_per_second": 7.584,
11
  "train_steps_per_second": 0.015
12
  }
 
1
  {
2
  "epoch": 0.13043478260869565,
3
+ "eval_loss": 1.6957746744155884,
4
+ "eval_runtime": 2.107,
5
+ "eval_samples_per_second": 292.834,
6
+ "eval_steps_per_second": 4.746,
7
  "total_flos": 3.355230384370483e+16,
8
+ "train_loss": 1.4135390917460124,
9
+ "train_runtime": 205.1131,
10
+ "train_samples_per_second": 7.489,
11
  "train_steps_per_second": 0.015
12
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 0.13043478260869565,
3
- "eval_loss": 1.6950849294662476,
4
- "eval_runtime": 2.1355,
5
- "eval_samples_per_second": 288.927,
6
- "eval_steps_per_second": 4.683
7
  }
 
1
  {
2
  "epoch": 0.13043478260869565,
3
+ "eval_loss": 1.6957746744155884,
4
+ "eval_runtime": 2.107,
5
+ "eval_samples_per_second": 292.834,
6
+ "eval_steps_per_second": 4.746
7
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7506f318198c2d814e43faa833a01e4a9d7e10bbce7af8eb09bee3095c6293d8
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da1fd319178bd8e8a554ef8a0e201d30b82a73d36120fc3615c205ebbb0cacf
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d4eb08b4c1fdbe10f845d76af3e308b704df1378e161dc5f421d4ae0450b6d1
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cee781b5eaf5706f6fe1f400d049f2f1b77024de4867c57427055f467e1c46
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd2880571d69437c46f47305f228e83c5a453b77ec65da718774d5f1aeabc8a2
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1ff7069b10fb2ebfb308f1c72ac3e75ba2ff41f1d919ecfa5a04b68aa99d86
3
  size 4540516344
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.13043478260869565,
3
  "total_flos": 3.355230384370483e+16,
4
- "train_loss": 1.413622538248698,
5
- "train_runtime": 202.5208,
6
- "train_samples_per_second": 7.584,
7
  "train_steps_per_second": 0.015
8
  }
 
1
  {
2
  "epoch": 0.13043478260869565,
3
  "total_flos": 3.355230384370483e+16,
4
+ "train_loss": 1.4135390917460124,
5
+ "train_runtime": 205.1131,
6
+ "train_samples_per_second": 7.489,
7
  "train_steps_per_second": 0.015
8
  }
trainer_state.json CHANGED
@@ -10,19 +10,19 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13043478260869565,
13
- "eval_loss": 1.6950849294662476,
14
- "eval_runtime": 1.8356,
15
- "eval_samples_per_second": 336.121,
16
- "eval_steps_per_second": 5.448,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 0.13043478260869565,
21
  "step": 3,
22
  "total_flos": 3.355230384370483e+16,
23
- "train_loss": 1.413622538248698,
24
- "train_runtime": 202.5208,
25
- "train_samples_per_second": 7.584,
26
  "train_steps_per_second": 0.015
27
  }
28
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13043478260869565,
13
+ "eval_loss": 1.6957746744155884,
14
+ "eval_runtime": 1.7972,
15
+ "eval_samples_per_second": 343.319,
16
+ "eval_steps_per_second": 5.564,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 0.13043478260869565,
21
  "step": 3,
22
  "total_flos": 3.355230384370483e+16,
23
+ "train_loss": 1.4135390917460124,
24
+ "train_runtime": 205.1131,
25
+ "train_samples_per_second": 7.489,
26
  "train_steps_per_second": 0.015
27
  }
28
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e7de179ac43644a8bba72023c4267d576e1fda40054213ae2c109ddc1794552
3
  size 6520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524ceec4e35c9f17cd2671076c7a11884e246f231aee4881a9578d1f1a851bb2
3
  size 6520
training_eval_loss.png CHANGED