Hugging Face's logo

sravanthib
/
testing

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
c63e4be
·
verified ·
1 Parent(s): 7e6a74e

Training completed

Browse files
Files changed (3) hide show
  1. all_results.json +7 -7
  2. train_results.json +7 -7
  3. trainer_state.json +6 -6
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "avg_step_time": 7.553769207000732,
3
  "epoch": 0.01,
4
  "total_flos": 4810910442979328.0,
5
- "total_training_time": 89.5426573753357,
6
- "total_training_time_mins": 1.4923776229222616,
7
- "train_loss": 3.214849853515625,
8
- "train_runtime": 82.321,
9
- "train_samples_per_second": 4.859,
10
- "train_steps_per_second": 0.121
11
  }
 
1
  {
2
+ "avg_step_time": 6.689460206031799,
3
  "epoch": 0.01,
4
  "total_flos": 4810910442979328.0,
5
+ "total_training_time": 79.5918402671814,
6
+ "total_training_time_mins": 1.32653067111969,
7
+ "train_loss": 3.181192398071289,
8
+ "train_runtime": 72.5058,
9
+ "train_samples_per_second": 5.517,
10
+ "train_steps_per_second": 0.138
11
  }
train_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "avg_step_time": 7.553769207000732,
3
  "epoch": 0.01,
4
  "total_flos": 4810910442979328.0,
5
- "total_training_time": 89.5426573753357,
6
- "total_training_time_mins": 1.4923776229222616,
7
- "train_loss": 3.214849853515625,
8
- "train_runtime": 82.321,
9
- "train_samples_per_second": 4.859,
10
- "train_steps_per_second": 0.121
11
  }
 
1
  {
2
+ "avg_step_time": 6.689460206031799,
3
  "epoch": 0.01,
4
  "total_flos": 4810910442979328.0,
5
+ "total_training_time": 79.5918402671814,
6
+ "total_training_time_mins": 1.32653067111969,
7
+ "train_loss": 3.181192398071289,
8
+ "train_runtime": 72.5058,
9
+ "train_samples_per_second": 5.517,
10
+ "train_steps_per_second": 0.138
11
  }
trainer_state.json CHANGED
@@ -11,19 +11,19 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.01,
14
- "grad_norm": 0.4434661269187927,
15
  "learning_rate": 0.0001,
16
- "loss": 3.2148,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.01,
21
  "step": 10,
22
  "total_flos": 4810910442979328.0,
23
- "train_loss": 3.214849853515625,
24
- "train_runtime": 82.321,
25
- "train_samples_per_second": 4.859,
26
- "train_steps_per_second": 0.121
27
  }
28
  ],
29
  "logging_steps": 10,
 
11
  "log_history": [
12
  {
13
  "epoch": 0.01,
14
+ "grad_norm": 0.5649898052215576,
15
  "learning_rate": 0.0001,
16
+ "loss": 3.1812,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.01,
21
  "step": 10,
22
  "total_flos": 4810910442979328.0,
23
+ "train_loss": 3.181192398071289,
24
+ "train_runtime": 72.5058,
25
+ "train_samples_per_second": 5.517,
26
+ "train_steps_per_second": 0.138
27
  }
28
  ],
29
  "logging_steps": 10,