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
23f3b82
·
verified ·
1 Parent(s): d9a726d

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 +6 -6
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.5873015873015874,
3
  "total_flos": 1.394108846267433e+17,
4
- "train_loss": 4.180461883544922,
5
- "train_runtime": 165.3706,
6
- "train_samples_per_second": 9.675,
7
- "train_steps_per_second": 0.06
8
  }
 
1
  {
2
  "epoch": 1.5873015873015874,
3
  "total_flos": 1.394108846267433e+17,
4
+ "train_loss": 4.131035614013672,
5
+ "train_runtime": 154.8297,
6
+ "train_samples_per_second": 10.334,
7
+ "train_steps_per_second": 0.065
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.5873015873015874,
3
  "total_flos": 1.394108846267433e+17,
4
- "train_loss": 4.180461883544922,
5
- "train_runtime": 165.3706,
6
- "train_samples_per_second": 9.675,
7
- "train_steps_per_second": 0.06
8
  }
 
1
  {
2
  "epoch": 1.5873015873015874,
3
  "total_flos": 1.394108846267433e+17,
4
+ "train_loss": 4.131035614013672,
5
+ "train_runtime": 154.8297,
6
+ "train_samples_per_second": 10.334,
7
+ "train_steps_per_second": 0.065
8
  }
trainer_state.json CHANGED
@@ -10,19 +10,19 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.5873015873015874,
13
- "grad_norm": 0.37594524025917053,
14
  "learning_rate": 0.0001,
15
- "loss": 4.1805,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 1.5873015873015874,
20
  "step": 10,
21
  "total_flos": 1.394108846267433e+17,
22
- "train_loss": 4.180461883544922,
23
- "train_runtime": 165.3706,
24
- "train_samples_per_second": 9.675,
25
- "train_steps_per_second": 0.06
26
  }
27
  ],
28
  "logging_steps": 10,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.5873015873015874,
13
+ "grad_norm": 0.2575690448284149,
14
  "learning_rate": 0.0001,
15
+ "loss": 4.131,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 1.5873015873015874,
20
  "step": 10,
21
  "total_flos": 1.394108846267433e+17,
22
+ "train_loss": 4.131035614013672,
23
+ "train_runtime": 154.8297,
24
+ "train_samples_per_second": 10.334,
25
+ "train_steps_per_second": 0.065
26
  }
27
  ],
28
  "logging_steps": 10,