Hugging Face's logo

sravanthib
/
qwen_model_testing

Text Generation
PEFT
Safetensors
Transformers
lora
conversational
Model card Files
xet
 Community
sravanthib commited on
Commit
e84d3d3
·
verified ·
1 Parent(s): 023abcb

Training completed

Browse files
Files changed (5) hide show
  1. adapter_config.json +4 -4
  2. adapter_model.safetensors +1 -1
  3. all_results.json +3 -3
  4. train_results.json +3 -3
  5. trainer_state.json +5 -5
adapter_config.json CHANGED
@@ -25,13 +25,13 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "gate_proj",
29
- "up_proj",
30
- "v_proj",
31
  "q_proj",
32
  "o_proj",
 
 
33
  "k_proj",
34
- "down_proj"
 
35
  ],
36
  "task_type": "CAUSAL_LM",
37
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
 
 
28
  "q_proj",
29
  "o_proj",
30
+ "down_proj",
31
+ "gate_proj",
32
  "k_proj",
33
+ "v_proj",
34
+ "up_proj"
35
  ],
36
  "task_type": "CAUSAL_LM",
37
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4011120d61484ba366228771bb4f4d23b97bd371b5f3a47b01777f1f28d40796
3
  size 40422208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be5a9f8760b42794c4abcf2dfe7a3ea53d86803aff66855ff8dac68f7cd17b2
3
  size 40422208
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0091324200913242,
3
  "total_flos": 6.970544231337165e+16,
4
- "train_loss": 4.493294906616211,
5
- "train_runtime": 133.1193,
6
- "train_samples_per_second": 6.01,
7
  "train_steps_per_second": 0.075
8
  }
 
1
  {
2
  "epoch": 0.0091324200913242,
3
  "total_flos": 6.970544231337165e+16,
4
+ "train_loss": 4.553681945800781,
5
+ "train_runtime": 133.9104,
6
+ "train_samples_per_second": 5.974,
7
  "train_steps_per_second": 0.075
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.0091324200913242,
3
  "total_flos": 6.970544231337165e+16,
4
- "train_loss": 4.493294906616211,
5
- "train_runtime": 133.1193,
6
- "train_samples_per_second": 6.01,
7
  "train_steps_per_second": 0.075
8
  }
 
1
  {
2
  "epoch": 0.0091324200913242,
3
  "total_flos": 6.970544231337165e+16,
4
+ "train_loss": 4.553681945800781,
5
+ "train_runtime": 133.9104,
6
+ "train_samples_per_second": 5.974,
7
  "train_steps_per_second": 0.075
8
  }
trainer_state.json CHANGED
@@ -11,18 +11,18 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.0091324200913242,
14
- "grad_norm": 0.7308942675590515,
15
  "learning_rate": 0.0001,
16
- "loss": 4.4933,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.0091324200913242,
21
  "step": 10,
22
  "total_flos": 6.970544231337165e+16,
23
- "train_loss": 4.493294906616211,
24
- "train_runtime": 133.1193,
25
- "train_samples_per_second": 6.01,
26
  "train_steps_per_second": 0.075
27
  }
28
  ],
 
11
  "log_history": [
12
  {
13
  "epoch": 0.0091324200913242,
14
+ "grad_norm": 0.3158293664455414,
15
  "learning_rate": 0.0001,
16
+ "loss": 4.5537,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.0091324200913242,
21
  "step": 10,
22
  "total_flos": 6.970544231337165e+16,
23
+ "train_loss": 4.553681945800781,
24
+ "train_runtime": 133.9104,
25
+ "train_samples_per_second": 5.974,
26
  "train_steps_per_second": 0.075
27
  }
28
  ],