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
88c9e29
•
1 Parent(s): 2ffff59

4000

Browse files
Files changed (7) hide show
  1. optimizer.pt +2 -2
  2. pytorch_model.bin +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. tokenizer.json +2 -2
  6. trainer_state.json +48 -21
  7. training_args.bin +1 -1
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb4ba9d920882db665a7f8ed561c2e0164bf7175d907c1270c05e7520cdcb1d0
3
- size 2156667008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abc67d04beb80c63a8253b6416f92f5f0d25de5856c9b42dd09ac59ae2a104e
3
+ size 2219797189
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5571ae930847af4c347f2e9313953b93fee21ec3588ecd8d0e904f1f268716d
3
  size 1109883945
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9381b8766976dd5552c5b2cdf9eacb941d0f1fb9258cdcae1ed22c88cf8aa8e7
3
  size 1109883945
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8abc1e67aacfa6a3fa1b2620d9282476381dc49bed6a7fc76e3f6164dd3c6494
3
  size 13553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990b96eb919994c26104c4b41054ce582e7b7491d6585750b551c1a324e06233
3
  size 13553
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4089ca6b8c754c164ef339a3123aa837ac0635645da9a6abf78f5f22a9bbb4f9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb01accba939052e7cbf8132c7f0d88545772aa8d7e3eb544633dc6f927474be
3
  size 627
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:167066c03829058ec15ff5404e54585316251e89eec3f758bced173717de5322
3
- size 17098346
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bae0289b9bb66bfbf85d834f6313ebd8e40f484df2bd0351539e74a0e4ddeb4
3
+ size 17098081
trainer_state.json CHANGED
@@ -1,46 +1,73 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
- "global_step": 1654,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.6,
13
- "learning_rate": 2.0931076178960096e-05,
14
- "loss": 2.1458,
15
  "step": 500
16
  },
17
  {
18
- "epoch": 1.21,
19
- "learning_rate": 1.1862152357920194e-05,
20
- "loss": 1.7773,
21
  "step": 1000
22
  },
23
  {
24
- "epoch": 1.81,
25
- "learning_rate": 2.7932285368802904e-06,
26
- "loss": 1.4845,
27
  "step": 1500
28
  },
29
  {
30
- "epoch": 2.0,
31
- "step": 1654,
32
- "total_flos": 3887703795096576.0,
33
- "train_loss": 1.7669375141701935,
34
- "train_runtime": 10839.0571,
35
- "train_samples_per_second": 1.83,
36
- "train_steps_per_second": 0.153
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  }
38
  ],
39
  "logging_steps": 500,
40
- "max_steps": 1654,
41
- "num_train_epochs": 2,
42
  "save_steps": 500,
43
- "total_flos": 3887703795096576.0,
44
  "trial_name": null,
45
  "trial_params": null
46
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.839738348323794,
5
  "eval_steps": 500,
6
+ "global_step": 4500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.2,
13
+ "learning_rate": 2.795584627964023e-05,
14
+ "loss": 2.2019,
15
  "step": 500
16
  },
17
  {
18
+ "epoch": 0.41,
19
+ "learning_rate": 2.591169255928046e-05,
20
+ "loss": 1.9636,
21
  "step": 1000
22
  },
23
  {
24
+ "epoch": 0.61,
25
+ "learning_rate": 2.3867538838920688e-05,
26
+ "loss": 1.9246,
27
  "step": 1500
28
  },
29
  {
30
+ "epoch": 0.82,
31
+ "learning_rate": 2.1823385118560917e-05,
32
+ "loss": 1.8572,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.02,
37
+ "learning_rate": 1.9779231398201146e-05,
38
+ "loss": 1.7804,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.23,
43
+ "learning_rate": 1.7735077677841375e-05,
44
+ "loss": 1.5332,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 1.43,
49
+ "learning_rate": 1.56909239574816e-05,
50
+ "loss": 1.5243,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.64,
55
+ "learning_rate": 1.3646770237121831e-05,
56
+ "loss": 1.5248,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.84,
61
+ "learning_rate": 1.160261651676206e-05,
62
+ "loss": 1.5064,
63
+ "step": 4500
64
  }
65
  ],
66
  "logging_steps": 500,
67
+ "max_steps": 7338,
68
+ "num_train_epochs": 3,
69
  "save_steps": 500,
70
+ "total_flos": 1.0581146839835136e+16,
71
  "trial_name": null,
72
  "trial_params": null
73
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76548b5d9f84ad0e2c1469a44406152c4de27fabab91f2a69cbe9c8ebeb1c4ed
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f4841925514c34c11b4abf14bd89c4a66c79f5e0b25faec4459849fb0e99b2
3
  size 4027