Hugging Face's logo

sravanthib
/
s

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
4b0fee7
·
verified ·
1 Parent(s): 943469e

Training completed

Browse files
Files changed (3) hide show
  1. all_results.json +3 -3
  2. train_results.json +3 -3
  3. trainer_state.json +5 -5
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
- "train_loss": 4.45857048034668,
5
- "train_runtime": 140.4374,
6
- "train_samples_per_second": 1.424,
7
  "train_steps_per_second": 0.071
8
  }
 
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
+ "train_loss": 4.486104583740234,
5
+ "train_runtime": 141.8169,
6
+ "train_samples_per_second": 1.41,
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": 4.45857048034668,
5
- "train_runtime": 140.4374,
6
- "train_samples_per_second": 1.424,
7
  "train_steps_per_second": 0.071
8
  }
 
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
+ "train_loss": 4.486104583740234,
5
+ "train_runtime": 141.8169,
6
+ "train_samples_per_second": 1.41,
7
  "train_steps_per_second": 0.071
8
  }
trainer_state.json CHANGED
@@ -11,18 +11,18 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.2,
14
- "grad_norm": 0.2821710705757141,
15
  "learning_rate": 0.0001,
16
- "loss": 4.4586,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.2,
21
  "step": 10,
22
  "total_flos": 1.7426360578342912e+16,
23
- "train_loss": 4.45857048034668,
24
- "train_runtime": 140.4374,
25
- "train_samples_per_second": 1.424,
26
  "train_steps_per_second": 0.071
27
  }
28
  ],
 
11
  "log_history": [
12
  {
13
  "epoch": 0.2,
14
+ "grad_norm": 0.3187005817890167,
15
  "learning_rate": 0.0001,
16
+ "loss": 4.4861,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.2,
21
  "step": 10,
22
  "total_flos": 1.7426360578342912e+16,
23
+ "train_loss": 4.486104583740234,
24
+ "train_runtime": 141.8169,
25
+ "train_samples_per_second": 1.41,
26
  "train_steps_per_second": 0.071
27
  }
28
  ],