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
dc2421d
•
1 Parent(s): 88c9e29

5500

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 +15 -3
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0abc67d04beb80c63a8253b6416f92f5f0d25de5856c9b42dd09ac59ae2a104e
3
  size 2219797189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad765f47af71011be3d640489246c7085d198b046f8e2dd772864e81ca97a408
3
  size 2219797189
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9381b8766976dd5552c5b2cdf9eacb941d0f1fb9258cdcae1ed22c88cf8aa8e7
3
  size 1109883945
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560bdb3380b22af02e00cdcafea5a445304ab6cf80042fac6513548eeb49fece
3
  size 1109883945
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:990b96eb919994c26104c4b41054ce582e7b7491d6585750b551c1a324e06233
3
  size 13553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd275d096cd6cf629c69200ea47d62fc9cd3b36b7e62400520fe4bf673338149
3
  size 13553
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb01accba939052e7cbf8132c7f0d88545772aa8d7e3eb544633dc6f927474be
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a6cbff39d4fbfc6aec126e1a969fa70287244e7814cf7317a9aaf9b3c0921e
3
  size 627
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -61,13 +61,25 @@
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
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.248569092395748,
5
  "eval_steps": 500,
6
+ "global_step": 5500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
61
  "learning_rate": 1.160261651676206e-05,
62
  "loss": 1.5064,
63
  "step": 4500
64
+ },
65
+ {
66
+ "epoch": 2.04,
67
+ "learning_rate": 9.55846279640229e-06,
68
+ "loss": 1.4177,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 2.25,
73
+ "learning_rate": 7.514309076042518e-06,
74
+ "loss": 1.2049,
75
+ "step": 5500
76
  }
77
  ],
78
  "logging_steps": 500,
79
  "max_steps": 7338,
80
  "num_train_epochs": 3,
81
  "save_steps": 500,
82
+ "total_flos": 1.2931445842486272e+16,
83
  "trial_name": null,
84
  "trial_params": null
85
  }