Hugging Face's logo

sravanthib
/
refactored-code-llama-3-2-3b

PEFT
Safetensors
llama
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
ad60cc1
·
verified ·
1 Parent(s): 4611c41

Training completed

Browse files
Files changed (3) hide show
  1. all_results.json +4 -4
  2. train_results.json +4 -4
  3. trainer_state.json +8 -8
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.9523809523809526,
3
  "total_flos": 1.1721276362818847e+18,
4
- "train_loss": 1.1249707728624343,
5
- "train_runtime": 814.2134,
6
- "train_samples_per_second": 3.93,
7
- "train_steps_per_second": 0.025
8
  }
 
1
  {
2
  "epoch": 2.9523809523809526,
3
  "total_flos": 1.1721276362818847e+18,
4
+ "train_loss": 1.1126826643943786,
5
+ "train_runtime": 855.5742,
6
+ "train_samples_per_second": 3.74,
7
+ "train_steps_per_second": 0.023
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.9523809523809526,
3
  "total_flos": 1.1721276362818847e+18,
4
- "train_loss": 1.1249707728624343,
5
- "train_runtime": 814.2134,
6
- "train_samples_per_second": 3.93,
7
- "train_steps_per_second": 0.025
8
  }
 
1
  {
2
  "epoch": 2.9523809523809526,
3
  "total_flos": 1.1721276362818847e+18,
4
+ "train_loss": 1.1126826643943786,
5
+ "train_runtime": 855.5742,
6
+ "train_samples_per_second": 3.74,
7
+ "train_steps_per_second": 0.023
8
  }
trainer_state.json CHANGED
@@ -11,26 +11,26 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.4761904761904763,
14
- "grad_norm": 0.11004530638456345,
15
  "learning_rate": 0.0001,
16
- "loss": 2.2288,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 2.9523809523809526,
21
- "grad_norm": 0.06395503133535385,
22
  "learning_rate": 0.0001,
23
- "loss": 0.0211,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 2.9523809523809526,
28
  "step": 20,
29
  "total_flos": 1.1721276362818847e+18,
30
- "train_loss": 1.1249707728624343,
31
- "train_runtime": 814.2134,
32
- "train_samples_per_second": 3.93,
33
- "train_steps_per_second": 0.025
34
  }
35
  ],
36
  "logging_steps": 10,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.4761904761904763,
14
+ "grad_norm": 0.09666553139686584,
15
  "learning_rate": 0.0001,
16
+ "loss": 2.2041,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 2.9523809523809526,
21
+ "grad_norm": 0.06255044788122177,
22
  "learning_rate": 0.0001,
23
+ "loss": 0.0213,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 2.9523809523809526,
28
  "step": 20,
29
  "total_flos": 1.1721276362818847e+18,
30
+ "train_loss": 1.1126826643943786,
31
+ "train_runtime": 855.5742,
32
+ "train_samples_per_second": 3.74,
33
+ "train_steps_per_second": 0.023
34
  }
35
  ],
36
  "logging_steps": 10,