Hugging Face's logo

sravanthib
/
qwen_model_testing

Text Generation
PEFT
Safetensors
Transformers
lora
conversational
Model card Files
xet
Community
sravanthib commited on
Commit
5c91c79
·
verified ·
1 Parent(s): f3a1372

Training completed

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. all_results.json +6 -6
  3. train_results.json +6 -6
  4. trainer_state.json +14 -42
README.md CHANGED
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.03
48
- - training_steps: 50
49
 
50
  ### Training results
51
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.03
48
+ - training_steps: 10
49
 
50
  ### Training results
51
 
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.091324200913242,
3
- "total_flos": 6.970544231337165e+17,
4
- "train_loss": 0.934032779932022,
5
- "train_runtime": 669.5576,
6
- "train_samples_per_second": 11.948,
7
- "train_steps_per_second": 0.075
8
  }
 
1
  {
2
+ "epoch": 0.0182648401826484,
3
+ "total_flos": 1.394108846267433e+17,
4
+ "train_loss": 4.435050201416016,
5
+ "train_runtime": 166.2301,
6
+ "train_samples_per_second": 9.625,
7
+ "train_steps_per_second": 0.06
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.091324200913242,
3
- "total_flos": 6.970544231337165e+17,
4
- "train_loss": 0.934032779932022,
5
- "train_runtime": 669.5576,
6
- "train_samples_per_second": 11.948,
7
- "train_steps_per_second": 0.075
8
  }
 
1
  {
2
+ "epoch": 0.0182648401826484,
3
+ "total_flos": 1.394108846267433e+17,
4
+ "train_loss": 4.435050201416016,
5
+ "train_runtime": 166.2301,
6
+ "train_samples_per_second": 9.625,
7
+ "train_steps_per_second": 0.06
8
  }
trainer_state.json CHANGED
@@ -1,63 +1,35 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.091324200913242,
5
  "eval_steps": 0,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0182648401826484,
13
- "grad_norm": 0.20208922028541565,
14
  "learning_rate": 0.0001,
15
- "loss": 4.4712,
16
  "step": 10
17
  },
18
  {
19
- "epoch": 0.0365296803652968,
20
- "grad_norm": 0.1714371293783188,
21
- "learning_rate": 0.0001,
22
- "loss": 0.0572,
23
- "step": 20
24
- },
25
- {
26
- "epoch": 0.0547945205479452,
27
- "grad_norm": 0.16024631261825562,
28
- "learning_rate": 0.0001,
29
- "loss": 0.0547,
30
- "step": 30
31
- },
32
- {
33
- "epoch": 0.0730593607305936,
34
- "grad_norm": 0.13002753257751465,
35
- "learning_rate": 0.0001,
36
- "loss": 0.0471,
37
- "step": 40
38
- },
39
- {
40
- "epoch": 0.091324200913242,
41
- "grad_norm": 0.09344350546598434,
42
- "learning_rate": 0.0001,
43
- "loss": 0.04,
44
- "step": 50
45
- },
46
- {
47
- "epoch": 0.091324200913242,
48
- "step": 50,
49
- "total_flos": 6.970544231337165e+17,
50
- "train_loss": 0.934032779932022,
51
- "train_runtime": 669.5576,
52
- "train_samples_per_second": 11.948,
53
- "train_steps_per_second": 0.075
54
  }
55
  ],
56
  "logging_steps": 10,
57
- "max_steps": 50,
58
  "num_input_tokens_seen": 0,
59
  "num_train_epochs": 1,
60
- "save_steps": 50,
61
  "stateful_callbacks": {
62
  "TrainerControl": {
63
  "args": {
@@ -70,7 +42,7 @@
70
  "attributes": {}
71
  }
72
  },
73
- "total_flos": 6.970544231337165e+17,
74
  "train_batch_size": 2,
75
  "trial_name": null,
76
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0182648401826484,
5
  "eval_steps": 0,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0182648401826484,
13
+ "grad_norm": 0.1791902333498001,
14
  "learning_rate": 0.0001,
15
+ "loss": 4.4351,
16
  "step": 10
17
  },
18
  {
19
+ "epoch": 0.0182648401826484,
20
+ "step": 10,
21
+ "total_flos": 1.394108846267433e+17,
22
+ "train_loss": 4.435050201416016,
23
+ "train_runtime": 166.2301,
24
+ "train_samples_per_second": 9.625,
25
+ "train_steps_per_second": 0.06
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
27
  ],
28
  "logging_steps": 10,
29
+ "max_steps": 10,
30
  "num_input_tokens_seen": 0,
31
  "num_train_epochs": 1,
32
+ "save_steps": 10,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
35
  "args": {
 
42
  "attributes": {}
43
  }
44
  },
45
+ "total_flos": 1.394108846267433e+17,
46
  "train_batch_size": 2,
47
  "trial_name": null,
48
  "trial_params": null