Hugging Face's logo

haibotamiu
/
out

Question Answering
Transformers
PyTorch
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
haibotamiu commited on
Commit
e2c69db
•
1 Parent(s): 262245a

Model save

Browse files
Files changed (5) hide show
  1. all_results.json +5 -5
  2. args.bin +1 -1
  3. train_results.json +5 -5
  4. trainer_state.json +9 -9
  5. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 2.116673701227048,
4
- "train_runtime": 309.01,
5
- "train_samples": 30000,
6
- "train_samples_per_second": 291.253,
7
- "train_steps_per_second": 1.146
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 4.621011098225911,
4
+ "train_runtime": 40.2046,
5
+ "train_samples": 3000,
6
+ "train_samples_per_second": 223.855,
7
+ "train_steps_per_second": 0.895
8
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84681b490574eec665dd628028717bdc85fbdb7ad3d54c8ed025f6816f1b69f3
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40abfa4155cddcba82cbf65e16136b1f7f02f9059737d9f4180121e5bafbba5
3
  size 5652
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 2.116673701227048,
4
- "train_runtime": 309.01,
5
- "train_samples": 30000,
6
- "train_samples_per_second": 291.253,
7
- "train_steps_per_second": 1.146
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 4.621011098225911,
4
+ "train_runtime": 40.2046,
5
+ "train_samples": 3000,
6
+ "train_samples_per_second": 223.855,
7
+ "train_steps_per_second": 0.895
8
  }
trainer_state.json CHANGED
@@ -3,26 +3,26 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
- "global_step": 354,
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": 354,
14
- "total_flos": 8819084252160000.0,
15
- "train_loss": 2.116673701227048,
16
- "train_runtime": 309.01,
17
- "train_samples_per_second": 291.253,
18
- "train_steps_per_second": 1.146
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 354,
23
  "num_train_epochs": 3,
24
  "save_steps": 500,
25
- "total_flos": 8819084252160000.0,
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": 36,
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": 36,
14
+ "total_flos": 881908425216000.0,
15
+ "train_loss": 4.621011098225911,
16
+ "train_runtime": 40.2046,
17
+ "train_samples_per_second": 223.855,
18
+ "train_steps_per_second": 0.895
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 36,
23
  "num_train_epochs": 3,
24
  "save_steps": 500,
25
+ "total_flos": 881908425216000.0,
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:ed62376ecc90c8a01bbc2f29b3d92d6ab6a87975e9b65b07bf2310214f6493ce
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c21a7a1d71fbc7505829b21472df420af8d762d2ec82196f32ef3365d115b7e
3
  size 4664