Hugging Face's logo

sravanthib
/
testing

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
228d147
·
verified ·
1 Parent(s): 947f8da

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": 6.869749426841736,
3
  "epoch": 0.02,
4
  "total_flos": 9621820885958656.0,
5
- "total_training_time": 87.23009157180786,
6
- "total_training_time_mins": 1.453834859530131,
7
- "train_loss": 2.993947219848633,
8
- "train_runtime": 75.826,
9
- "train_samples_per_second": 10.55,
10
- "train_steps_per_second": 0.132
11
  }
 
1
  {
2
+ "avg_step_time": 7.642647361755371,
3
  "epoch": 0.02,
4
  "total_flos": 9621820885958656.0,
5
+ "total_training_time": 93.81911158561707,
6
+ "total_training_time_mins": 1.5636518597602844,
7
+ "train_loss": 3.0537273406982424,
8
+ "train_runtime": 83.3739,
9
+ "train_samples_per_second": 9.595,
10
+ "train_steps_per_second": 0.12
11
  }
train_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "avg_step_time": 6.869749426841736,
3
  "epoch": 0.02,
4
  "total_flos": 9621820885958656.0,
5
- "total_training_time": 87.23009157180786,
6
- "total_training_time_mins": 1.453834859530131,
7
- "train_loss": 2.993947219848633,
8
- "train_runtime": 75.826,
9
- "train_samples_per_second": 10.55,
10
- "train_steps_per_second": 0.132
11
  }
 
1
  {
2
+ "avg_step_time": 7.642647361755371,
3
  "epoch": 0.02,
4
  "total_flos": 9621820885958656.0,
5
+ "total_training_time": 93.81911158561707,
6
+ "total_training_time_mins": 1.5636518597602844,
7
+ "train_loss": 3.0537273406982424,
8
+ "train_runtime": 83.3739,
9
+ "train_samples_per_second": 9.595,
10
+ "train_steps_per_second": 0.12
11
  }
trainer_state.json CHANGED
@@ -11,19 +11,19 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.02,
14
- "grad_norm": 0.5400242805480957,
15
  "learning_rate": 0.0001,
16
- "loss": 2.9939,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.02,
21
  "step": 10,
22
  "total_flos": 9621820885958656.0,
23
- "train_loss": 2.993947219848633,
24
- "train_runtime": 75.826,
25
- "train_samples_per_second": 10.55,
26
- "train_steps_per_second": 0.132
27
  }
28
  ],
29
  "logging_steps": 10,
 
11
  "log_history": [
12
  {
13
  "epoch": 0.02,
14
+ "grad_norm": 0.49432897567749023,
15
  "learning_rate": 0.0001,
16
+ "loss": 3.0537,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.02,
21
  "step": 10,
22
  "total_flos": 9621820885958656.0,
23
+ "train_loss": 3.0537273406982424,
24
+ "train_runtime": 83.3739,
25
+ "train_samples_per_second": 9.595,
26
+ "train_steps_per_second": 0.12
27
  }
28
  ],
29
  "logging_steps": 10,