Hugging Face's logo

T0KII
/
MASRIBERTv3

Fill-Mask
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
T0KII commited on
Commit
ddfb62d
·
verified ·
1 Parent(s): 4bdbeee

Training in progress, step 7000

Browse files
Files changed (8) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +6 -42
  7. last-checkpoint/training_args.bin +1 -1
  8. model.safetensors +1 -1
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fbd17b2ef796ffdb776502b4e54ebe5870575552ecf57a289b06fd09b913987
3
  size 775678032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fac5a6f55f232c4fa9d6549a6328f337a2b19680eb125c0fea7538df9c7926c
3
  size 775678032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c7e919b97730a7da9859d6b1464771915fbe8f95af7a022ba742465a39f96ee
3
  size 1551478091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eca38b61a90273520ce4023b3b85dcc51e6f53ebe3dc341ee434151989a26ee
3
  size 1551478091
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:508ce3e5b92544d9fea7a56e78a9a3dbbc2ff6650cef6c156b494d8d001ef855
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11306c827003ca872f3dbb7eff94c18246ba935b4c57aadab9bda8e1ac77df7
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2dd5d54f49a7afdfffbf998ae6372fcdee770c6d02602d924eacb55d51a6aa9
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2253d135196644bbe0b3e20f4c763c557a93f595b853f202dd6200feeeb354db
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 6000,
3
- "best_metric": 4.957474231719971,
4
- "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-6000",
5
- "epoch": 0.9019504678868052,
6
  "eval_steps": 1000,
7
- "global_step": 6000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -188,42 +188,6 @@
188
  "eval_samples_per_second": 69.793,
189
  "eval_steps_per_second": 1.091,
190
  "step": 5000
191
- },
192
- {
193
- "epoch": 0.7892066594009546,
194
- "grad_norm": 86.16392517089844,
195
- "learning_rate": 4.535199292287709e-05,
196
- "loss": 42.626734375,
197
- "step": 5250
198
- },
199
- {
200
- "epoch": 0.8267879288962381,
201
- "grad_norm": 87.34744262695312,
202
- "learning_rate": 4.491469912957297e-05,
203
- "loss": 42.33,
204
- "step": 5500
205
- },
206
- {
207
- "epoch": 0.8643691983915217,
208
- "grad_norm": 79.0370101928711,
209
- "learning_rate": 4.4460060629603434e-05,
210
- "loss": 41.88755078125,
211
- "step": 5750
212
- },
213
- {
214
- "epoch": 0.9019504678868052,
215
- "grad_norm": 83.2159423828125,
216
- "learning_rate": 4.398847339035767e-05,
217
- "loss": 41.65294140625,
218
- "step": 6000
219
- },
220
- {
221
- "epoch": 0.9019504678868052,
222
- "eval_loss": 4.957474231719971,
223
- "eval_runtime": 239.2537,
224
- "eval_samples_per_second": 71.899,
225
- "eval_steps_per_second": 1.124,
226
- "step": 6000
227
  }
228
  ],
229
  "logging_steps": 250,
@@ -252,7 +216,7 @@
252
  "attributes": {}
253
  }
254
  },
255
- "total_flos": 1.01200116842496e+17,
256
  "train_batch_size": 32,
257
  "trial_name": null,
258
  "trial_params": null
 
1
  {
2
+ "best_global_step": 5000,
3
+ "best_metric": 5.109297752380371,
4
+ "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-5000",
5
+ "epoch": 0.751625389905671,
6
  "eval_steps": 1000,
7
+ "global_step": 5000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
188
  "eval_samples_per_second": 69.793,
189
  "eval_steps_per_second": 1.091,
190
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
191
  }
192
  ],
193
  "logging_steps": 250,
 
216
  "attributes": {}
217
  }
218
  },
219
+ "total_flos": 8.433343070208e+16,
220
  "train_batch_size": 32,
221
  "trial_name": null,
222
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e81ef68ecf6d54adfcba782e86ddd0804ab77ba8d53704fbef9e1dfb6174a6bf
3
  size 5201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efefbcb0e8b57f988b34f042db56f28887d1f06d14ec2b11a9e87dc1b7486213
3
  size 5201
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fbd17b2ef796ffdb776502b4e54ebe5870575552ecf57a289b06fd09b913987
3
  size 775678032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df50b8a580ea8526eb0730d57704938f14070df067dee66888ec8693240b765e
3
  size 775678032