Hugging Face's logo

mlfoundations-dev
/
mistral_alpaca_sft_sample_5

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
32dc908
·
verified ·
1 Parent(s): bd72f27

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: 1.6997
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 | 1.6997 |
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: 1.6953
22
 
23
  ## Model description
24
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:----:|:---------------:|
58
+ | No log | 0.1304 | 3 | 1.6953 |
59
 
60
 
61
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 0.13043478260869565,
3
- "eval_loss": 1.6996564865112305,
4
- "eval_runtime": 3.7243,
5
- "eval_samples_per_second": 165.668,
6
- "eval_steps_per_second": 2.685,
7
  "total_flos": 3.355230384370483e+16,
8
- "train_loss": 1.413604736328125,
9
- "train_runtime": 209.8464,
10
- "train_samples_per_second": 7.32,
11
  "train_steps_per_second": 0.014
12
  }
 
1
  {
2
  "epoch": 0.13043478260869565,
3
+ "eval_loss": 1.6953213214874268,
4
+ "eval_runtime": 2.0013,
5
+ "eval_samples_per_second": 308.301,
6
+ "eval_steps_per_second": 4.997,
7
  "total_flos": 3.355230384370483e+16,
8
+ "train_loss": 1.413663387298584,
9
+ "train_runtime": 207.2235,
10
+ "train_samples_per_second": 7.412,
11
  "train_steps_per_second": 0.014
12
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 0.13043478260869565,
3
- "eval_loss": 1.6996564865112305,
4
- "eval_runtime": 3.7243,
5
- "eval_samples_per_second": 165.668,
6
- "eval_steps_per_second": 2.685
7
  }
 
1
  {
2
  "epoch": 0.13043478260869565,
3
+ "eval_loss": 1.6953213214874268,
4
+ "eval_runtime": 2.0013,
5
+ "eval_samples_per_second": 308.301,
6
+ "eval_steps_per_second": 4.997
7
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39fd425c2691693d271bee5ea875bc2f1b6b1017f01e653ba8b6c3b62a4633de
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f6c64e7586d2f1793e7a6c1cb5a2bd111a00d06bef7c247a3670f477a47ec0
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080f42ac9101b71fcd1daa06890b34c920bad36feefa58370a9541928028703f
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48857a16db2c84c919e06b45e27434cf5c1d9686fe24dbb08f4052d02f9333ba
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:763a774370b3520296b4b083d0c293822a3441d5ecb4ef6c50593e287848e06d
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d467f5b79ba09c79b2ed2d1f76ef4112da99f4f460f264430a7ade0115d532
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": 1.413604736328125,
5
- "train_runtime": 209.8464,
6
- "train_samples_per_second": 7.32,
7
  "train_steps_per_second": 0.014
8
  }
 
1
  {
2
  "epoch": 0.13043478260869565,
3
  "total_flos": 3.355230384370483e+16,
4
+ "train_loss": 1.413663387298584,
5
+ "train_runtime": 207.2235,
6
+ "train_samples_per_second": 7.412,
7
  "train_steps_per_second": 0.014
8
  }
trainer_state.json CHANGED
@@ -10,19 +10,19 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13043478260869565,
13
- "eval_loss": 1.6996564865112305,
14
- "eval_runtime": 3.6392,
15
- "eval_samples_per_second": 169.54,
16
- "eval_steps_per_second": 2.748,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 0.13043478260869565,
21
  "step": 3,
22
  "total_flos": 3.355230384370483e+16,
23
- "train_loss": 1.413604736328125,
24
- "train_runtime": 209.8464,
25
- "train_samples_per_second": 7.32,
26
  "train_steps_per_second": 0.014
27
  }
28
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13043478260869565,
13
+ "eval_loss": 1.6953213214874268,
14
+ "eval_runtime": 1.8012,
15
+ "eval_samples_per_second": 342.542,
16
+ "eval_steps_per_second": 5.552,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 0.13043478260869565,
21
  "step": 3,
22
  "total_flos": 3.355230384370483e+16,
23
+ "train_loss": 1.413663387298584,
24
+ "train_runtime": 207.2235,
25
+ "train_samples_per_second": 7.412,
26
  "train_steps_per_second": 0.014
27
  }
28
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82eb5f4ba327bda293928b93e3ee0739a8a789c729db7c85c739cc28b0b3adaa
3
  size 6520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef1010c8b16c9b0403e090ac25b6dab8a778d189921cf247ccbdee31f744f33
3
  size 6520
training_eval_loss.png CHANGED