Hugging Face's logo

Kyrmasch
/
xml-roberta-model-qa

Question Answering
Transformers
PyTorch
xlm-roberta
Inference Endpoints
Model card Files Community
5
Kyrmasch commited on
Commit
10cde6b
•
1 Parent(s): 2276d7b

3-5000

Browse files
Files changed (5) hide show
  1. all_results.json +6 -6
  2. pytorch_model.bin +1 -1
  3. train_results.json +6 -6
  4. trainer_state.json +21 -15
  5. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "train_loss": 1.6453349383580202,
4
- "train_runtime": 6270.6718,
5
- "train_samples": 10370,
6
- "train_samples_per_second": 1.654,
7
- "train_steps_per_second": 0.138
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.263148379344306,
4
+ "train_runtime": 9000.3857,
5
+ "train_samples": 5169,
6
+ "train_samples_per_second": 1.723,
7
+ "train_steps_per_second": 0.144
8
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0d6c3df1021e5d2805eec094101c9756aab92a2c23d7ed5a670d9f95d11a232
3
  size 1109883945
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7638cb9d42b819f57c068ce9276628133fa84cbc7345348a208662950f4c82
3
  size 1109883945
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "train_loss": 1.6453349383580202,
4
- "train_runtime": 6270.6718,
5
- "train_samples": 10370,
6
- "train_samples_per_second": 1.654,
7
- "train_steps_per_second": 0.138
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.263148379344306,
4
+ "train_runtime": 9000.3857,
5
+ "train_samples": 5169,
6
+ "train_samples_per_second": 1.723,
7
+ "train_steps_per_second": 0.144
8
  }
trainer_state.json CHANGED
@@ -1,34 +1,40 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 865,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.58,
13
- "learning_rate": 1.2658959537572255e-05,
14
- "loss": 1.7414,
15
  "step": 500
16
  },
17
  {
18
- "epoch": 1.0,
19
- "step": 865,
20
- "total_flos": 2032235525514240.0,
21
- "train_loss": 1.6453349383580202,
22
- "train_runtime": 6270.6718,
23
- "train_samples_per_second": 1.654,
24
- "train_steps_per_second": 0.138
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 500,
28
- "max_steps": 865,
29
- "num_train_epochs": 1,
30
  "save_steps": 500,
31
- "total_flos": 2032235525514240.0,
32
  "trial_name": null,
33
  "trial_params": null
34
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 1293,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.16,
13
+ "learning_rate": 1.839907192575406e-05,
14
+ "loss": 1.701,
15
  "step": 500
16
  },
17
  {
18
+ "epoch": 2.32,
19
+ "learning_rate": 6.798143851508122e-06,
20
+ "loss": 1.1061,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 3.0,
25
+ "step": 1293,
26
+ "total_flos": 3038946605028864.0,
27
+ "train_loss": 1.263148379344306,
28
+ "train_runtime": 9000.3857,
29
+ "train_samples_per_second": 1.723,
30
+ "train_steps_per_second": 0.144
31
  }
32
  ],
33
  "logging_steps": 500,
34
+ "max_steps": 1293,
35
+ "num_train_epochs": 3,
36
  "save_steps": 500,
37
+ "total_flos": 3038946605028864.0,
38
  "trial_name": null,
39
  "trial_params": null
40
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a448ce07274e9228c49e2d8399ef7896ad395414437462eb8541947ca7e188f
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a46fa7765fd949851d723b013601d5e19a6e4631ad1f839350358738d9d4c0
3
  size 4027