Hugging Face's logo

sravanthib
/
testing

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
eac229b
·
verified ·
1 Parent(s): 3fe57a6

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": 6.669609618186951,
3
  "epoch": 0.01,
4
  "total_flos": 4810910442979328.0,
5
- "total_training_time": 89.90108489990234,
6
- "total_training_time_mins": 1.4983514149983723,
7
- "train_loss": 3.1294017791748048,
8
- "train_runtime": 82.5533,
9
- "train_samples_per_second": 4.845,
10
- "train_steps_per_second": 0.121
11
  }
 
1
  {
2
+ "avg_step_time": 6.863372492790222,
3
  "epoch": 0.01,
4
  "total_flos": 4810910442979328.0,
5
+ "total_training_time": 82.03439784049988,
6
+ "total_training_time_mins": 1.3672399640083313,
7
+ "train_loss": 3.104553985595703,
8
+ "train_runtime": 74.9153,
9
+ "train_samples_per_second": 5.339,
10
+ "train_steps_per_second": 0.133
11
  }
train_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "avg_step_time": 6.669609618186951,
3
  "epoch": 0.01,
4
  "total_flos": 4810910442979328.0,
5
- "total_training_time": 89.90108489990234,
6
- "total_training_time_mins": 1.4983514149983723,
7
- "train_loss": 3.1294017791748048,
8
- "train_runtime": 82.5533,
9
- "train_samples_per_second": 4.845,
10
- "train_steps_per_second": 0.121
11
  }
 
1
  {
2
+ "avg_step_time": 6.863372492790222,
3
  "epoch": 0.01,
4
  "total_flos": 4810910442979328.0,
5
+ "total_training_time": 82.03439784049988,
6
+ "total_training_time_mins": 1.3672399640083313,
7
+ "train_loss": 3.104553985595703,
8
+ "train_runtime": 74.9153,
9
+ "train_samples_per_second": 5.339,
10
+ "train_steps_per_second": 0.133
11
  }
trainer_state.json CHANGED
@@ -11,19 +11,19 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.01,
14
- "grad_norm": 0.5258329510688782,
15
  "learning_rate": 0.0001,
16
- "loss": 3.1294,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.01,
21
  "step": 10,
22
  "total_flos": 4810910442979328.0,
23
- "train_loss": 3.1294017791748048,
24
- "train_runtime": 82.5533,
25
- "train_samples_per_second": 4.845,
26
- "train_steps_per_second": 0.121
27
  }
28
  ],
29
  "logging_steps": 10,
 
11
  "log_history": [
12
  {
13
  "epoch": 0.01,
14
+ "grad_norm": 0.5488150119781494,
15
  "learning_rate": 0.0001,
16
+ "loss": 3.1046,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.01,
21
  "step": 10,
22
  "total_flos": 4810910442979328.0,
23
+ "train_loss": 3.104553985595703,
24
+ "train_runtime": 74.9153,
25
+ "train_samples_per_second": 5.339,
26
+ "train_steps_per_second": 0.133
27
  }
28
  ],
29
  "logging_steps": 10,