Hugging Face's logo

sravanthib
/
s

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
b44d7fa
·
verified ·
1 Parent(s): 51b9eb1

Training completed

Browse files
Files changed (4) hide show
  1. README.md +3 -5
  2. all_results.json +6 -6
  3. train_results.json +6 -6
  4. trainer_state.json +11 -11
README.md CHANGED
@@ -5,14 +5,14 @@ base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
- - name: qwen-7b-squad-lora
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
- # qwen-7b-squad-lora
16
 
17
  This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
18
 
@@ -38,10 +38,8 @@ The following hyperparameters were used during training:
38
  - eval_batch_size: 8
39
  - seed: 42
40
  - distributed_type: multi-GPU
41
- - num_devices: 4
42
  - gradient_accumulation_steps: 10
43
- - total_train_batch_size: 80
44
- - total_eval_batch_size: 32
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.05
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: s
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # s
16
 
17
  This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
18
 
 
38
  - eval_batch_size: 8
39
  - seed: 42
40
  - distributed_type: multi-GPU
 
41
  - gradient_accumulation_steps: 10
42
+ - total_train_batch_size: 20
 
43
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_ratio: 0.05
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.8,
3
- "total_flos": 6.970544231337165e+16,
4
- "train_loss": 4.266504287719727,
5
- "train_runtime": 156.4211,
6
- "train_samples_per_second": 5.114,
7
- "train_steps_per_second": 0.064
8
  }
 
1
  {
2
+ "epoch": 0.2,
3
+ "total_flos": 1.7426360578342912e+16,
4
+ "train_loss": 4.438372421264648,
5
+ "train_runtime": 138.5064,
6
+ "train_samples_per_second": 1.444,
7
+ "train_steps_per_second": 0.072
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.8,
3
- "total_flos": 6.970544231337165e+16,
4
- "train_loss": 4.266504287719727,
5
- "train_runtime": 156.4211,
6
- "train_samples_per_second": 5.114,
7
- "train_steps_per_second": 0.064
8
  }
 
1
  {
2
+ "epoch": 0.2,
3
+ "total_flos": 1.7426360578342912e+16,
4
+ "train_loss": 4.438372421264648,
5
+ "train_runtime": 138.5064,
6
+ "train_samples_per_second": 1.444,
7
+ "train_steps_per_second": 0.072
8
  }
trainer_state.json CHANGED
@@ -2,7 +2,7 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.8,
6
  "eval_steps": 0,
7
  "global_step": 10,
8
  "is_hyper_param_search": false,
@@ -10,20 +10,20 @@
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "epoch": 0.8,
14
- "grad_norm": 0.18490508198738098,
15
  "learning_rate": 0.0001,
16
- "loss": 4.2665,
17
  "step": 10
18
  },
19
  {
20
- "epoch": 0.8,
21
  "step": 10,
22
- "total_flos": 6.970544231337165e+16,
23
- "train_loss": 4.266504287719727,
24
- "train_runtime": 156.4211,
25
- "train_samples_per_second": 5.114,
26
- "train_steps_per_second": 0.064
27
  }
28
  ],
29
  "logging_steps": 10,
@@ -43,7 +43,7 @@
43
  "attributes": {}
44
  }
45
  },
46
- "total_flos": 6.970544231337165e+16,
47
  "train_batch_size": 2,
48
  "trial_name": null,
49
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2,
6
  "eval_steps": 0,
7
  "global_step": 10,
8
  "is_hyper_param_search": false,
 
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "epoch": 0.2,
14
+ "grad_norm": 0.3070150911808014,
15
  "learning_rate": 0.0001,
16
+ "loss": 4.4384,
17
  "step": 10
18
  },
19
  {
20
+ "epoch": 0.2,
21
  "step": 10,
22
+ "total_flos": 1.7426360578342912e+16,
23
+ "train_loss": 4.438372421264648,
24
+ "train_runtime": 138.5064,
25
+ "train_samples_per_second": 1.444,
26
+ "train_steps_per_second": 0.072
27
  }
28
  ],
29
  "logging_steps": 10,
 
43
  "attributes": {}
44
  }
45
  },
46
+ "total_flos": 1.7426360578342912e+16,
47
  "train_batch_size": 2,
48
  "trial_name": null,
49
  "trial_params": null