KotshinZ commited on
Commit
0977550
·
verified ·
1 Parent(s): 6d3b002

End of training

Browse files
Files changed (4) hide show
  1. README.md +3 -1
  2. all_results.json +5 -0
  3. config.json +1 -1
  4. eval_results.json +7 -0
README.md CHANGED
@@ -1,9 +1,11 @@
1
  ---
2
  base_model: tiiuae/falcon-mamba-7b-instruct
 
3
  library_name: transformers
4
  model_name: mamba-distill-7b
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
  - sft
9
  licence: license
@@ -11,7 +13,7 @@ licence: license
11
 
12
  # Model Card for mamba-distill-7b
13
 
14
- This model is a fine-tuned version of [tiiuae/falcon-mamba-7b-instruct](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
1
  ---
2
  base_model: tiiuae/falcon-mamba-7b-instruct
3
+ datasets: HuggingFaceH4/Bespoke-Stratos-17k
4
  library_name: transformers
5
  model_name: mamba-distill-7b
6
  tags:
7
  - generated_from_trainer
8
+ - open-r1
9
  - trl
10
  - sft
11
  licence: license
 
13
 
14
  # Model Card for mamba-distill-7b
15
 
16
+ This model is a fine-tuned version of [tiiuae/falcon-mamba-7b-instruct](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
17
  It has been trained using [TRL](https://github.com/huggingface/trl).
18
 
19
  ## Quick start
all_results.json CHANGED
@@ -1,4 +1,9 @@
1
  {
 
 
 
 
 
2
  "total_flos": 3.616227566899167e+18,
3
  "train_loss": 16.595592213948567,
4
  "train_runtime": 29081.677,
 
1
  {
2
+ "eval_loss": 3.7433252334594727,
3
+ "eval_runtime": 42.3244,
4
+ "eval_samples": 100,
5
+ "eval_samples_per_second": 3.402,
6
+ "eval_steps_per_second": 0.425,
7
  "total_flos": 3.616227566899167e+18,
8
  "train_loss": 16.595592213948567,
9
  "train_runtime": 29081.677,
config.json CHANGED
@@ -28,7 +28,7 @@
28
  "torch_dtype": "bfloat16",
29
  "transformers_version": "4.50.1",
30
  "use_bias": false,
31
- "use_cache": false,
32
  "use_conv_bias": true,
33
  "use_mambapy": false,
34
  "vocab_size": 65024
 
28
  "torch_dtype": "bfloat16",
29
  "transformers_version": "4.50.1",
30
  "use_bias": false,
31
+ "use_cache": true,
32
  "use_conv_bias": true,
33
  "use_mambapy": false,
34
  "vocab_size": 65024
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss": 3.7433252334594727,
3
+ "eval_runtime": 42.3244,
4
+ "eval_samples": 100,
5
+ "eval_samples_per_second": 3.402,
6
+ "eval_steps_per_second": 0.425
7
+ }