Hugging Face's logo

sravanthib
/
model

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
b812f21
·
verified ·
1 Parent(s): 17525c7

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 +10 -10
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0547945205479452,
3
  "total_flos": 8.348676830055629e+16,
4
- "train_loss": 2.759544785817464,
5
- "train_runtime": 440.1219,
6
- "train_samples_per_second": 10.906,
7
- "train_steps_per_second": 0.068
8
  }
 
1
  {
2
  "epoch": 0.0547945205479452,
3
  "total_flos": 8.348676830055629e+16,
4
+ "train_loss": 2.75271688302358,
5
+ "train_runtime": 423.9764,
6
+ "train_samples_per_second": 11.321,
7
+ "train_steps_per_second": 0.071
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0547945205479452,
3
  "total_flos": 8.348676830055629e+16,
4
- "train_loss": 2.759544785817464,
5
- "train_runtime": 440.1219,
6
- "train_samples_per_second": 10.906,
7
- "train_steps_per_second": 0.068
8
  }
 
1
  {
2
  "epoch": 0.0547945205479452,
3
  "total_flos": 8.348676830055629e+16,
4
+ "train_loss": 2.75271688302358,
5
+ "train_runtime": 423.9764,
6
+ "train_samples_per_second": 11.321,
7
+ "train_steps_per_second": 0.071
8
  }
trainer_state.json CHANGED
@@ -10,33 +10,33 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.0182648401826484,
13
- "grad_norm": 3.4625627994537354,
14
  "learning_rate": 0.0001,
15
- "loss": 5.8804,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.0365296803652968,
20
- "grad_norm": 5.154474258422852,
21
  "learning_rate": 0.0001,
22
- "loss": 2.1357,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.0547945205479452,
27
- "grad_norm": 0.09764906764030457,
28
  "learning_rate": 0.0001,
29
- "loss": 0.2626,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.0547945205479452,
34
  "step": 30,
35
  "total_flos": 8.348676830055629e+16,
36
- "train_loss": 2.759544785817464,
37
- "train_runtime": 440.1219,
38
- "train_samples_per_second": 10.906,
39
- "train_steps_per_second": 0.068
40
  }
41
  ],
42
  "logging_steps": 10,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.0182648401826484,
13
+ "grad_norm": 2.923218011856079,
14
  "learning_rate": 0.0001,
15
+ "loss": 6.0475,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.0365296803652968,
20
+ "grad_norm": 5.51038122177124,
21
  "learning_rate": 0.0001,
22
+ "loss": 1.929,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.0547945205479452,
27
+ "grad_norm": 0.20810189843177795,
28
  "learning_rate": 0.0001,
29
+ "loss": 0.2817,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.0547945205479452,
34
  "step": 30,
35
  "total_flos": 8.348676830055629e+16,
36
+ "train_loss": 2.75271688302358,
37
+ "train_runtime": 423.9764,
38
+ "train_samples_per_second": 11.321,
39
+ "train_steps_per_second": 0.071
40
  }
41
  ],
42
  "logging_steps": 10,