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
7956338
·
1 Parent(s): df3e006

1000

Browse files
Files changed (5) hide show
  1. optimizer.pt +1 -1
  2. pytorch_model.bin +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. trainer_state.json +9 -3
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66c1c3dbdcff612e7464cf5ae414558dc454324edb0c4e73420511978e11942e
3
  size 2219797189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415cf20de7fc969bd9767f8c02e4f1b23d8585605f8634e4fbabb09dfb068390
3
  size 2219797189
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc8c652ef5cfc839167fb8e43757cfdff727f6046499b379981d74faaaba4242
3
  size 1109883945
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f707764d9e11980c1452927623714cff18b4729620befd5b1192bd057384942b
3
  size 1109883945
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:556647febb788da6dd49a88a8ed603748321637cc7055b1bb12850e2d4f60da4
3
  size 13553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8abc1e67aacfa6a3fa1b2620d9282476381dc49bed6a7fc76e3f6164dd3c6494
3
  size 13553
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a870f21458d323a03674433a89db03696c1277d8f9575a76e764158222f7d4e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4089ca6b8c754c164ef339a3123aa837ac0635645da9a6abf78f5f22a9bbb4f9
3
  size 627
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.6045949214026602,
5
  "eval_steps": 500,
6
- "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -13,13 +13,19 @@
13
  "learning_rate": 2.0931076178960096e-05,
14
  "loss": 2.1458,
15
  "step": 500
 
 
 
 
 
 
16
  }
17
  ],
18
  "logging_steps": 500,
19
  "max_steps": 1654,
20
  "num_train_epochs": 2,
21
  "save_steps": 500,
22
- "total_flos": 1175835405312000.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.2091898428053205,
5
  "eval_steps": 500,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
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
  "logging_steps": 500,
25
  "max_steps": 1654,
26
  "num_train_epochs": 2,
27
  "save_steps": 500,
28
+ "total_flos": 2350690947786240.0,
29
  "trial_name": null,
30
  "trial_params": null
31
  }