Hugging Face's logo

sravanthib
/
qwen_model_testing

Text Generation
PEFT
Safetensors
Transformers
lora
conversational
Model card Files
xet
 Community
sravanthib commited on
Commit
35318b5
·
verified ·
1 Parent(s): 048483e

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 +6 -6
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0091324200913242,
3
  "total_flos": 6.970544231337165e+16,
4
- "train_loss": 4.522793579101562,
5
- "train_runtime": 135.1739,
6
- "train_samples_per_second": 5.918,
7
- "train_steps_per_second": 0.074
8
  }
 
1
  {
2
  "epoch": 0.0091324200913242,
3
  "total_flos": 6.970544231337165e+16,
4
+ "train_loss": 4.537882995605469,
5
+ "train_runtime": 129.105,
6
+ "train_samples_per_second": 6.197,
7
+ "train_steps_per_second": 0.077
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0091324200913242,
3
  "total_flos": 6.970544231337165e+16,
4
- "train_loss": 4.522793579101562,
5
- "train_runtime": 135.1739,
6
- "train_samples_per_second": 5.918,
7
- "train_steps_per_second": 0.074
8
  }
 
1
  {
2
  "epoch": 0.0091324200913242,
3
  "total_flos": 6.970544231337165e+16,
4
+ "train_loss": 4.537882995605469,
5
+ "train_runtime": 129.105,
6
+ "train_samples_per_second": 6.197,
7
+ "train_steps_per_second": 0.077
8
  }
trainer_state.json CHANGED
@@ -11,19 +11,19 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.0091324200913242,
14
- "grad_norm": 2.4754679203033447,
15
  "learning_rate": 0.0001,
16
- "loss": 4.5228,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.0091324200913242,
21
  "step": 10,
22
  "total_flos": 6.970544231337165e+16,
23
- "train_loss": 4.522793579101562,
24
- "train_runtime": 135.1739,
25
- "train_samples_per_second": 5.918,
26
- "train_steps_per_second": 0.074
27
  }
28
  ],
29
  "logging_steps": 10,
 
11
  "log_history": [
12
  {
13
  "epoch": 0.0091324200913242,
14
+ "grad_norm": 0.6447323560714722,
15
  "learning_rate": 0.0001,
16
+ "loss": 4.5379,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.0091324200913242,
21
  "step": 10,
22
  "total_flos": 6.970544231337165e+16,
23
+ "train_loss": 4.537882995605469,
24
+ "train_runtime": 129.105,
25
+ "train_samples_per_second": 6.197,
26
+ "train_steps_per_second": 0.077
27
  }
28
  ],
29
  "logging_steps": 10,