yhyhy3 commited on
Commit
63f1ce4
1 Parent(s): 2a220ba

Add model files and configs

Browse files
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.5953705310821533,
4
- "train_runtime": 22.7307,
5
- "train_samples_per_second": 8.183,
6
- "train_steps_per_second": 1.056
7
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.6169168684217665,
4
+ "train_runtime": 24.7305,
5
+ "train_samples_per_second": 7.885,
6
+ "train_steps_per_second": 1.092
7
  }
onnx/model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6a382ddc11e568915fa205c55174e03550e69c4a0f771a5899549a6a952a5d3
3
  size 87112360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a2c65e770aa3d504ae301be61c49eb14aa6aa2ccbaf45600c3c567d883b02d0
3
  size 87112360
quantize_config.json CHANGED
@@ -4,30 +4,30 @@
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
7
- "MatMul",
8
  "Sqrt",
9
- "ConstantOfShape",
10
- "Mul",
11
- "Concat",
12
- "Gather",
13
- "Transpose",
14
- "Expand",
15
- "Gemm",
16
- "Div",
17
- "ReduceMean",
18
- "Conv",
19
  "Unsqueeze",
20
- "Sub",
21
  "Softmax",
22
- "Add",
23
  "Slice",
24
- "Pow",
25
- "Erf",
26
- "Where",
27
- "Constant",
 
 
 
 
28
  "Reshape",
 
29
  "Shape",
30
- "Equal"
 
 
 
 
 
 
 
31
  ],
32
  "weight_type": "QUInt8"
33
  }
 
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
 
7
  "Sqrt",
8
+ "Pow",
 
 
 
 
 
 
 
 
 
9
  "Unsqueeze",
 
10
  "Softmax",
 
11
  "Slice",
12
+ "ReduceMean",
13
+ "Gather",
14
+ "Concat",
15
+ "Mul",
16
+ "Conv",
17
+ "Expand",
18
+ "Gemm",
19
+ "Transpose",
20
  "Reshape",
21
+ "Add",
22
  "Shape",
23
+ "Constant",
24
+ "Where",
25
+ "Sub",
26
+ "Equal",
27
+ "Erf",
28
+ "ConstantOfShape",
29
+ "MatMul",
30
+ "Div"
31
  ],
32
  "weight_type": "QUInt8"
33
  }
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.5953705310821533,
4
- "train_runtime": 22.7307,
5
- "train_samples_per_second": 8.183,
6
- "train_steps_per_second": 1.056
7
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.6169168684217665,
4
+ "train_runtime": 24.7305,
5
+ "train_samples_per_second": 7.885,
6
+ "train_steps_per_second": 1.092
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": 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": 1.4415187272966144e+16,
15
- "train_loss": 0.5953705310821533,
16
- "train_runtime": 22.7307,
17
- "train_samples_per_second": 8.183,
18
- "train_steps_per_second": 1.056
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 24,
23
  "num_train_epochs": 3,
24
  "save_steps": 500,
25
- "total_flos": 1.4415187272966144e+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": 27,
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": 27,
14
+ "total_flos": 1.511269633456128e+16,
15
+ "train_loss": 0.6169168684217665,
16
+ "train_runtime": 24.7305,
17
+ "train_samples_per_second": 7.885,
18
+ "train_steps_per_second": 1.092
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 27,
23
  "num_train_epochs": 3,
24
  "save_steps": 500,
25
+ "total_flos": 1.511269633456128e+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:e02720ee20fec8b4598a5fba809bb682e12e584fcae6a810511f14d329ec20a9
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcda69e54f5f1cec25cd8381adf4941b7cb79df3e933b22e4d18e5d81434cbe7
3
  size 4536