Hugging Face's logo

sravanthib
/
model

PEFT
Safetensors
Generated from Trainer
Model card Files Community
sravanthib commited on
Commit
83aa47d
·
verified ·
1 Parent(s): 3075935

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": 1.6697353660111258e+17,
4
- "train_loss": 2.030022064844767,
5
- "train_runtime": 481.4543,
6
- "train_samples_per_second": 9.97,
7
- "train_steps_per_second": 0.062
8
  }
 
1
  {
2
  "epoch": 0.0547945205479452,
3
  "total_flos": 1.6697353660111258e+17,
4
+ "train_loss": 2.0425025622049966,
5
+ "train_runtime": 461.7117,
6
+ "train_samples_per_second": 10.396,
7
+ "train_steps_per_second": 0.065
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0547945205479452,
3
  "total_flos": 1.6697353660111258e+17,
4
- "train_loss": 2.030022064844767,
5
- "train_runtime": 481.4543,
6
- "train_samples_per_second": 9.97,
7
- "train_steps_per_second": 0.062
8
  }
 
1
  {
2
  "epoch": 0.0547945205479452,
3
  "total_flos": 1.6697353660111258e+17,
4
+ "train_loss": 2.0425025622049966,
5
+ "train_runtime": 461.7117,
6
+ "train_samples_per_second": 10.396,
7
+ "train_steps_per_second": 0.065
8
  }
trainer_state.json CHANGED
@@ -10,33 +10,33 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.0182648401826484,
13
- "grad_norm": 1.4427909851074219,
14
  "learning_rate": 0.0001,
15
- "loss": 4.6764,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.0365296803652968,
20
- "grad_norm": 4.036961555480957,
21
  "learning_rate": 0.0001,
22
- "loss": 1.0438,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.0547945205479452,
27
- "grad_norm": 0.26397082209587097,
28
  "learning_rate": 0.0001,
29
- "loss": 0.3698,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.0547945205479452,
34
  "step": 30,
35
  "total_flos": 1.6697353660111258e+17,
36
- "train_loss": 2.030022064844767,
37
- "train_runtime": 481.4543,
38
- "train_samples_per_second": 9.97,
39
- "train_steps_per_second": 0.062
40
  }
41
  ],
42
  "logging_steps": 10,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.0182648401826484,
13
+ "grad_norm": 1.4506075382232666,
14
  "learning_rate": 0.0001,
15
+ "loss": 4.6632,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.0365296803652968,
20
+ "grad_norm": 4.050724983215332,
21
  "learning_rate": 0.0001,
22
+ "loss": 1.0722,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.0547945205479452,
27
+ "grad_norm": 0.32392966747283936,
28
  "learning_rate": 0.0001,
29
+ "loss": 0.3922,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.0547945205479452,
34
  "step": 30,
35
  "total_flos": 1.6697353660111258e+17,
36
+ "train_loss": 2.0425025622049966,
37
+ "train_runtime": 461.7117,
38
+ "train_samples_per_second": 10.396,
39
+ "train_steps_per_second": 0.065
40
  }
41
  ],
42
  "logging_steps": 10,