Hugging Face's logo

sravanthib
/
s

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
823a00e
·
verified ·
1 Parent(s): 9047570

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": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
- "train_loss": 4.516284561157226,
5
- "train_runtime": 137.9486,
6
- "train_samples_per_second": 1.45,
7
- "train_steps_per_second": 0.072
8
  }
 
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
+ "train_loss": 4.444633483886719,
5
+ "train_runtime": 141.3075,
6
+ "train_samples_per_second": 1.415,
7
+ "train_steps_per_second": 0.071
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
- "train_loss": 4.516284561157226,
5
- "train_runtime": 137.9486,
6
- "train_samples_per_second": 1.45,
7
- "train_steps_per_second": 0.072
8
  }
 
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
+ "train_loss": 4.444633483886719,
5
+ "train_runtime": 141.3075,
6
+ "train_samples_per_second": 1.415,
7
+ "train_steps_per_second": 0.071
8
  }
trainer_state.json CHANGED
@@ -11,19 +11,19 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.2,
14
- "grad_norm": 0.27265769243240356,
15
  "learning_rate": 0.0001,
16
- "loss": 4.5163,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.2,
21
  "step": 10,
22
  "total_flos": 1.7426360578342912e+16,
23
- "train_loss": 4.516284561157226,
24
- "train_runtime": 137.9486,
25
- "train_samples_per_second": 1.45,
26
- "train_steps_per_second": 0.072
27
  }
28
  ],
29
  "logging_steps": 10,
 
11
  "log_history": [
12
  {
13
  "epoch": 0.2,
14
+ "grad_norm": 0.2844962775707245,
15
  "learning_rate": 0.0001,
16
+ "loss": 4.4446,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.2,
21
  "step": 10,
22
  "total_flos": 1.7426360578342912e+16,
23
+ "train_loss": 4.444633483886719,
24
+ "train_runtime": 141.3075,
25
+ "train_samples_per_second": 1.415,
26
+ "train_steps_per_second": 0.071
27
  }
28
  ],
29
  "logging_steps": 10,