gabrielaltay commited on
Commit
97859b5
1 Parent(s): fbd1083

End of training

Browse files
Files changed (5) hide show
  1. README.md +19 -2
  2. all_results.json +15 -0
  3. eval_results.json +10 -0
  4. train_results.json +8 -0
  5. trainer_state.json +0 -0
README.md CHANGED
@@ -1,9 +1,23 @@
1
  ---
2
  tags:
3
  - generated_from_trainer
 
 
 
 
4
  model-index:
5
  - name: usclm-mistral-mk1
6
- results: []
 
 
 
 
 
 
 
 
 
 
7
  ---
8
 
9
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,7 +25,10 @@ should probably proofread and complete it, then remove this comment. -->
11
 
12
  # usclm-mistral-mk1
13
 
14
- This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 
 
 
15
 
16
  ## Model description
17
 
 
1
  ---
2
  tags:
3
  - generated_from_trainer
4
+ datasets:
5
+ - hyperdemocracy/usc-llm-text
6
+ metrics:
7
+ - accuracy
8
  model-index:
9
  - name: usclm-mistral-mk1
10
+ results:
11
+ - task:
12
+ name: Causal Language Modeling
13
+ type: text-generation
14
+ dataset:
15
+ name: hyperdemocracy/usc-llm-text
16
+ type: hyperdemocracy/usc-llm-text
17
+ metrics:
18
+ - name: Accuracy
19
+ type: accuracy
20
+ value: 0.6378780303492917
21
  ---
22
 
23
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
25
 
26
  # usclm-mistral-mk1
27
 
28
+ This model is a fine-tuned version of [](https://huggingface.co/) on the hyperdemocracy/usc-llm-text dataset.
29
+ It achieves the following results on the evaluation set:
30
+ - Loss: 1.7902
31
+ - Accuracy: 0.6379
32
 
33
  ## Model description
34
 
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.6378780303492917,
4
+ "eval_loss": 1.7901718616485596,
5
+ "eval_runtime": 15.7066,
6
+ "eval_samples": 1024,
7
+ "eval_samples_per_second": 65.195,
8
+ "eval_steps_per_second": 8.149,
9
+ "perplexity": 5.990481912016533,
10
+ "train_loss": 2.3174790558589957,
11
+ "train_runtime": 2998.5108,
12
+ "train_samples": 93561,
13
+ "train_samples_per_second": 31.202,
14
+ "train_steps_per_second": 3.901
15
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.6378780303492917,
4
+ "eval_loss": 1.7901718616485596,
5
+ "eval_runtime": 15.7066,
6
+ "eval_samples": 1024,
7
+ "eval_samples_per_second": 65.195,
8
+ "eval_steps_per_second": 8.149,
9
+ "perplexity": 5.990481912016533
10
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.3174790558589957,
4
+ "train_runtime": 2998.5108,
5
+ "train_samples": 93561,
6
+ "train_samples_per_second": 31.202,
7
+ "train_steps_per_second": 3.901
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff