Hugging Face's logo

sravanthib
/
qwen_model_testing

Text Generation
PEFT
Safetensors
Transformers
lora
conversational
Model card Files
xet
 Community
sravanthib commited on
Commit
7617b0e
·
verified ·
1 Parent(s): 1963dcc

Training completed

Browse files
Files changed (3) hide show
  1. all_results.json +3 -3
  2. train_results.json +3 -3
  3. trainer_state.json +7 -7
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0365296803652968,
3
  "total_flos": 2.788217692534866e+17,
4
- "train_loss": 4.396173620223999,
5
- "train_runtime": 365.615,
6
- "train_samples_per_second": 8.752,
7
  "train_steps_per_second": 0.055
8
  }
 
1
  {
2
  "epoch": 0.0365296803652968,
3
  "total_flos": 2.788217692534866e+17,
4
+ "train_loss": 4.457736051082611,
5
+ "train_runtime": 365.5565,
6
+ "train_samples_per_second": 8.754,
7
  "train_steps_per_second": 0.055
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0365296803652968,
3
  "total_flos": 2.788217692534866e+17,
4
- "train_loss": 4.396173620223999,
5
- "train_runtime": 365.615,
6
- "train_samples_per_second": 8.752,
7
  "train_steps_per_second": 0.055
8
  }
 
1
  {
2
  "epoch": 0.0365296803652968,
3
  "total_flos": 2.788217692534866e+17,
4
+ "train_loss": 4.457736051082611,
5
+ "train_runtime": 365.5565,
6
+ "train_samples_per_second": 8.754,
7
  "train_steps_per_second": 0.055
8
  }
trainer_state.json CHANGED
@@ -10,25 +10,25 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.0182648401826484,
13
- "grad_norm": 10.253478050231934,
14
  "learning_rate": 0.0001,
15
- "loss": 8.455,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.0365296803652968,
20
- "grad_norm": 0.12031922489404678,
21
  "learning_rate": 0.0001,
22
- "loss": 0.3374,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.0365296803652968,
27
  "step": 20,
28
  "total_flos": 2.788217692534866e+17,
29
- "train_loss": 4.396173620223999,
30
- "train_runtime": 365.615,
31
- "train_samples_per_second": 8.752,
32
  "train_steps_per_second": 0.055
33
  }
34
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.0182648401826484,
13
+ "grad_norm": 10.570018768310547,
14
  "learning_rate": 0.0001,
15
+ "loss": 8.549,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.0365296803652968,
20
+ "grad_norm": 0.13333489000797272,
21
  "learning_rate": 0.0001,
22
+ "loss": 0.3664,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.0365296803652968,
27
  "step": 20,
28
  "total_flos": 2.788217692534866e+17,
29
+ "train_loss": 4.457736051082611,
30
+ "train_runtime": 365.5565,
31
+ "train_samples_per_second": 8.754,
32
  "train_steps_per_second": 0.055
33
  }
34
  ],