Hugging Face's logo

sravanthib
/
testing

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
c845f26
·
verified ·
1 Parent(s): 7b6554a

Training completed

Browse files
Files changed (4) hide show
  1. README.md +1 -3
  2. all_results.json +6 -6
  3. train_results.json +6 -6
  4. trainer_state.json +11 -11
README.md CHANGED
@@ -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: 2
42
  - gradient_accumulation_steps: 10
43
- - total_train_batch_size: 40
44
- - total_eval_batch_size: 16
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
 
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": 0.01,
3
- "total_flos": 4810910442979328.0,
4
- "train_loss": 2.9966007232666017,
5
- "train_runtime": 74.842,
6
- "train_samples_per_second": 5.345,
7
- "train_steps_per_second": 0.134
8
  }
 
1
  {
2
+ "epoch": 0.005,
3
+ "total_flos": 2405455221489664.0,
4
+ "train_loss": 3.079809379577637,
5
+ "train_runtime": 70.7086,
6
+ "train_samples_per_second": 2.829,
7
+ "train_steps_per_second": 0.141
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.01,
3
- "total_flos": 4810910442979328.0,
4
- "train_loss": 2.9966007232666017,
5
- "train_runtime": 74.842,
6
- "train_samples_per_second": 5.345,
7
- "train_steps_per_second": 0.134
8
  }
 
1
  {
2
+ "epoch": 0.005,
3
+ "total_flos": 2405455221489664.0,
4
+ "train_loss": 3.079809379577637,
5
+ "train_runtime": 70.7086,
6
+ "train_samples_per_second": 2.829,
7
+ "train_steps_per_second": 0.141
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": 0.01,
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": 0.01,
14
- "grad_norm": 1.57552170753479,
15
  "learning_rate": 0.0001,
16
- "loss": 2.9966,
17
  "step": 10
18
  },
19
  {
20
- "epoch": 0.01,
21
  "step": 10,
22
- "total_flos": 4810910442979328.0,
23
- "train_loss": 2.9966007232666017,
24
- "train_runtime": 74.842,
25
- "train_samples_per_second": 5.345,
26
- "train_steps_per_second": 0.134
27
  }
28
  ],
29
  "logging_steps": 10,
@@ -43,7 +43,7 @@
43
  "attributes": {}
44
  }
45
  },
46
- "total_flos": 4810910442979328.0,
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": 0.005,
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": 0.005,
14
+ "grad_norm": 1.3369250297546387,
15
  "learning_rate": 0.0001,
16
+ "loss": 3.0798,
17
  "step": 10
18
  },
19
  {
20
+ "epoch": 0.005,
21
  "step": 10,
22
+ "total_flos": 2405455221489664.0,
23
+ "train_loss": 3.079809379577637,
24
+ "train_runtime": 70.7086,
25
+ "train_samples_per_second": 2.829,
26
+ "train_steps_per_second": 0.141
27
  }
28
  ],
29
  "logging_steps": 10,
 
43
  "attributes": {}
44
  }
45
  },
46
+ "total_flos": 2405455221489664.0,
47
  "train_batch_size": 2,
48
  "trial_name": null,
49
  "trial_params": null