yhyhy3 commited on
Commit
61104b7
·
1 Parent(s): 3ae7e59

Add model files and configs

Browse files
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.5212204796927316,
4
- "train_runtime": 24.4549,
5
- "train_samples_per_second": 6.87,
6
- "train_steps_per_second": 0.859
7
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.5741025606791178,
4
+ "train_runtime": 21.8228,
5
+ "train_samples_per_second": 8.111,
6
+ "train_steps_per_second": 1.1
7
  }
onnx/model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:039bd4d4f8df5a6901880cde80a9673f4a31cf3d3bf470fd9b464b6462d4af65
3
  size 87112360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c148401cd25f4710e21636a23f9aeae74eaa1a4943dc06982f231a40b2810cba
3
  size 87112360
quantize_config.json CHANGED
@@ -4,30 +4,30 @@
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
7
- "Sqrt",
8
- "Reshape",
9
- "Equal",
10
  "Expand",
11
- "Conv",
12
- "Pow",
13
- "Add",
14
- "Erf",
15
- "Sub",
16
  "Div",
 
17
  "Softmax",
18
- "ReduceMean",
19
- "ConstantOfShape",
20
- "Gather",
21
- "Shape",
22
- "Constant",
23
  "Gemm",
24
- "MatMul",
 
 
 
 
 
 
25
  "Unsqueeze",
26
- "Slice",
27
- "Concat",
28
  "Mul",
29
- "Transpose",
30
- "Where"
 
 
31
  ],
32
  "weight_type": "QUInt8"
33
  }
 
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
 
 
 
7
  "Expand",
8
+ "ConstantOfShape",
9
+ "MatMul",
 
 
 
10
  "Div",
11
+ "Concat",
12
  "Softmax",
13
+ "Erf",
14
+ "Sqrt",
 
 
 
15
  "Gemm",
16
+ "Constant",
17
+ "Transpose",
18
+ "Equal",
19
+ "Sub",
20
+ "Reshape",
21
+ "Shape",
22
+ "ReduceMean",
23
  "Unsqueeze",
24
+ "Gather",
25
+ "Where",
26
  "Mul",
27
+ "Conv",
28
+ "Pow",
29
+ "Add",
30
+ "Slice"
31
  ],
32
  "weight_type": "QUInt8"
33
  }
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.5212204796927316,
4
- "train_runtime": 24.4549,
5
- "train_samples_per_second": 6.87,
6
- "train_steps_per_second": 0.859
7
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.5741025606791178,
4
+ "train_runtime": 21.8228,
5
+ "train_samples_per_second": 8.111,
6
+ "train_steps_per_second": 1.1
7
  }
trainer_state.json CHANGED
@@ -3,26 +3,26 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
- "global_step": 21,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 3.0,
13
- "step": 21,
14
- "total_flos": 1.3020169149775872e+16,
15
- "train_loss": 0.5212204796927316,
16
- "train_runtime": 24.4549,
17
- "train_samples_per_second": 6.87,
18
- "train_steps_per_second": 0.859
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 21,
23
  "num_train_epochs": 3,
24
  "save_steps": 500,
25
- "total_flos": 1.3020169149775872e+16,
26
  "trial_name": null,
27
  "trial_params": null
28
  }
 
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 24,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 3.0,
13
+ "step": 24,
14
+ "total_flos": 1.3717678211371008e+16,
15
+ "train_loss": 0.5741025606791178,
16
+ "train_runtime": 21.8228,
17
+ "train_samples_per_second": 8.111,
18
+ "train_steps_per_second": 1.1
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 24,
23
  "num_train_epochs": 3,
24
  "save_steps": 500,
25
+ "total_flos": 1.3717678211371008e+16,
26
  "trial_name": null,
27
  "trial_params": null
28
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33b9eab7994046e9b62756dcbcea0cbbaa2ec0418b4ccfe5b9ad63756e83cd8a
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07eb2bb8358ee16c8d302239eea02906b9e53fe7bde34e6c71c0ca9b0d1f2055
3
  size 4536