Hugging Face's logo

lewtun
/
dummy-model

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
lewtun HF staff commited on
Commit
25af8ba
•
1 Parent(s): c3a5ee2

End of training

Browse files
Files changed (5) hide show
  1. README.md +3 -0
  2. all_results.json +3 -3
  3. train_results.json +3 -3
  4. trainer_state.json +6 -6
  5. training_args.bin +1 -1
README.md CHANGED
@@ -37,6 +37,9 @@ The following hyperparameters were used during training:
37
  - eval_batch_size: 8
38
  - seed: 42
39
  - distributed_type: multi-GPU
 
 
 
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - lr_scheduler_warmup_ratio: 0.1
 
37
  - eval_batch_size: 8
38
  - seed: 42
39
  - distributed_type: multi-GPU
40
+ - num_devices: 2
41
+ - total_train_batch_size: 16
42
+ - total_eval_batch_size: 16
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_ratio: 0.1
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
- "train_runtime": 5.5894,
5
- "train_samples_per_second": 1.431,
6
- "train_steps_per_second": 0.179
7
  }
 
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
+ "train_runtime": 10.6682,
5
+ "train_samples_per_second": 1.5,
6
+ "train_steps_per_second": 0.094
7
  }
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
- "train_runtime": 5.5894,
5
- "train_samples_per_second": 1.431,
6
- "train_steps_per_second": 0.179
7
  }
 
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
+ "train_runtime": 10.6682,
5
+ "train_samples_per_second": 1.5,
6
+ "train_steps_per_second": 0.094
7
  }
trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.00016066838046272492,
5
  "eval_steps": 500,
6
  "global_step": 1,
7
  "is_hyper_param_search": false,
@@ -11,8 +11,8 @@
11
  {
12
  "epoch": 0.0,
13
  "learning_rate": 0.0,
14
- "logits/generated": -1.85471510887146,
15
- "logits/real": -1.7835122346878052,
16
  "logps/generated": -667.4280395507812,
17
  "logps/real": -384.09954833984375,
18
  "loss": 0.6931,
@@ -27,9 +27,9 @@
27
  "step": 1,
28
  "total_flos": 0.0,
29
  "train_loss": 0.6931471824645996,
30
- "train_runtime": 5.5894,
31
- "train_samples_per_second": 1.431,
32
- "train_steps_per_second": 0.179
33
  }
34
  ],
35
  "logging_steps": 10,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00032133676092544985,
5
  "eval_steps": 500,
6
  "global_step": 1,
7
  "is_hyper_param_search": false,
 
11
  {
12
  "epoch": 0.0,
13
  "learning_rate": 0.0,
14
+ "logits/generated": -1.854715347290039,
15
+ "logits/real": -1.7835123538970947,
16
  "logps/generated": -667.4280395507812,
17
  "logps/real": -384.09954833984375,
18
  "loss": 0.6931,
 
27
  "step": 1,
28
  "total_flos": 0.0,
29
  "train_loss": 0.6931471824645996,
30
+ "train_runtime": 10.6682,
31
+ "train_samples_per_second": 1.5,
32
+ "train_steps_per_second": 0.094
33
  }
34
  ],
35
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6d3e2546740d7f6f9c46fb71cf117eeec16eba45237766eb24cb6dd4b178259
3
  size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27400530099be3b59bee84a18af706fa5330678ad8aa576bb769c5f20bf70284
3
  size 5880