Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
a3e0fef
•
1 Parent(s): 3113f19

Training in progress, step 20000

Browse files
Files changed (10) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scaler.pt +1 -1
  8. last-checkpoint/scheduler.pt +1 -1
  9. last-checkpoint/trainer_state.json +62 -2
  10. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:666f31b71f688592a2ebec72cbadc00c8aaee821b8eb7771699d6c823471e0cc
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f8d440dee0bab83268031d3ca51cab7f723eefc2ce80fc493ac3c6717c71e7
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca890677bdefc691a4ae67775aa72a92ad5cd2df8c160e6ad53e945377e03e27
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad0dc798bf3ab8bc86e8ca945a4782e43cd0d5a1828253e63883880781b3cdf
3
  size 201355195
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:850ae05229fe1ff6e41b675b726702223f1525583dd9434a160b5ed0d7191665
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa36bb0d4cec624b08cc83d638858ce248a094ffa647685bae58b915dff037e9
3
  size 14503
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f74419249bf29830712440b12c1e85996438d926aea7250a4e6ac14a39e8683f
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a9401956a29de2159a5b1a96f5c8acb3c2df03434a7575562e5bff46d935cf
3
  size 14503
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a64c1a11cc81ac8192bd75a90c14d20536e7e07041595e558f54ede2d84f1a21
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76dc75ea1a15c659d60f8d677cdda9bb534c90320b07847d866dce5eee22958
3
  size 14503
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:665c414e8bb61ec28c1998307283516f963f621b54cf6255d89b6f4ba9dd8be9
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fda5933a166c0774efdde4c472d56f927648e883235c5867dc882b3657f0455
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8617ac21bddb0215639029e71b10a4eb309c92f6b26783c1657277dbc000388a
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e171ab488f2f0f70ef9238e83eeacee5c282c69323a08adb507167abf9a3ee7
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:189312512188440cf844c33231cd5f9af5c7d8dc4e11cd7c24cda5639fe93158
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c641ad045fc2fcec80756b378b25cace7a7d7436b423b673949d42813805e426
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.2553191489361702,
5
- "global_step": 15000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -186,6 +186,66 @@
186
  "learning_rate": 0.00014968937891183796,
187
  "loss": 0.3938,
188
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
189
  }
190
  ],
191
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3404255319148936,
5
+ "global_step": 20000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
186
  "learning_rate": 0.00014968937891183796,
187
  "loss": 0.3938,
188
  "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.26,
192
+ "learning_rate": 0.00014966834091947024,
193
+ "loss": 0.3927,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.27,
198
+ "learning_rate": 0.0001496466594659672,
199
+ "loss": 0.3924,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.28,
204
+ "learning_rate": 0.00014962424786577448,
205
+ "loss": 0.3908,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.29,
210
+ "learning_rate": 0.00014960114910236375,
211
+ "loss": 0.3898,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.3,
216
+ "learning_rate": 0.0001495774116605143,
217
+ "loss": 0.389,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.31,
222
+ "learning_rate": 0.00014955294063453595,
223
+ "loss": 0.3883,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.31,
228
+ "learning_rate": 0.00014952778314911323,
229
+ "loss": 0.3875,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.32,
234
+ "learning_rate": 0.0001495019394525403,
235
+ "loss": 0.3871,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.33,
240
+ "learning_rate": 0.0001494755172845744,
241
+ "loss": 0.3857,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.34,
246
+ "learning_rate": 0.00014944830467991823,
247
+ "loss": 0.3855,
248
+ "step": 20000
249
  }
250
  ],
251
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca890677bdefc691a4ae67775aa72a92ad5cd2df8c160e6ad53e945377e03e27
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad0dc798bf3ab8bc86e8ca945a4782e43cd0d5a1828253e63883880781b3cdf
3
  size 201355195