Hugging Face's logo

WhirlwindAI
/
Translate-25T

Translation
Transformers
Safetensors
mt5
text2text-generation
machine-translation
whirlwindai
Model card Files
xet
 Community
QuantaSparkLabs commited on
Commit
d2e0f6c
·
verified ·
1 Parent(s): bca10e8

checkpoint-3000

Browse files
Files changed (6) hide show
  1. model.safetensors +1 -1
  2. optimizer.pt +1 -1
  3. rng_state.pth +1 -1
  4. scaler.pt +1 -1
  5. scheduler.pt +1 -1
  6. trainer_state.json +89 -3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51da6e268a7e285fa9fb540d68be4c972283d7aa667860dc4bca0b6ec3f79e72
3
  size 2225188480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f64733363c4ab84fc7a91b7e6056521940e864fa3dde9cefae41d6441176bcb
3
  size 2225188480
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e632b9dbf6e8ba3eb9f1ca85acbf780a221a805a3fc861f1fd5875de233282e
3
  size 4450498267
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9dbcf3c45dd8f88e56068b62bc6a894b03559b0f6580ed774fcd76a18a432c2
3
  size 4450498267
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e90a3ac540f4bb00d958e0f5cfffc49fadcc08f2a0ec1edb79bff07e215cf9f2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd26160ab842c822518103cb963d5530d3a1db9d1f97a9b0b60e08b0a504981
3
  size 14645
scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
3
  size 1383
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:987254f92f549faf4a01f8204aaa238914b04e56fd8eb3229fc905ce11ffe5cb
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b23d2336a6dedfd0ec92ca5bf7a3a04e0f8095e554e3b126d5fdaf26a4e1028
3
  size 1465
trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 1.3468013468013469,
6
  "eval_steps": 500,
7
- "global_step": 2000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -180,6 +180,92 @@
180
  "eval_samples_per_second": 13.567,
181
  "eval_steps_per_second": 3.392,
182
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
183
  }
184
  ],
185
  "logging_steps": 100,
@@ -199,7 +285,7 @@
199
  "attributes": {}
200
  }
201
  },
202
- "total_flos": 7694596829675520.0,
203
  "train_batch_size": 8,
204
  "trial_name": null,
205
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 2.0202020202020203,
6
  "eval_steps": 500,
7
+ "global_step": 3000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
180
  "eval_samples_per_second": 13.567,
181
  "eval_steps_per_second": 3.392,
182
  "step": 2000
183
+ },
184
+ {
185
+ "epoch": 1.4141414141414141,
186
+ "grad_norm": 22.914306640625,
187
+ "learning_rate": 0.00016611045828437133,
188
+ "loss": 53.9832177734375,
189
+ "step": 2100
190
+ },
191
+ {
192
+ "epoch": 1.4814814814814814,
193
+ "grad_norm": 22.693891525268555,
194
+ "learning_rate": 0.00015905992949471207,
195
+ "loss": 53.846845703125,
196
+ "step": 2200
197
+ },
198
+ {
199
+ "epoch": 1.5488215488215489,
200
+ "grad_norm": 22.133243560791016,
201
+ "learning_rate": 0.00015200940070505287,
202
+ "loss": 54.00986328125,
203
+ "step": 2300
204
+ },
205
+ {
206
+ "epoch": 1.6161616161616161,
207
+ "grad_norm": 23.607688903808594,
208
+ "learning_rate": 0.00014495887191539364,
209
+ "loss": 53.8654638671875,
210
+ "step": 2400
211
+ },
212
+ {
213
+ "epoch": 1.6835016835016834,
214
+ "grad_norm": 22.71261215209961,
215
+ "learning_rate": 0.0001379083431257344,
216
+ "loss": 53.5878173828125,
217
+ "step": 2500
218
+ },
219
+ {
220
+ "epoch": 1.6835016835016834,
221
+ "eval_loss": 5.490618705749512,
222
+ "eval_runtime": 72.5632,
223
+ "eval_samples_per_second": 13.23,
224
+ "eval_steps_per_second": 3.307,
225
+ "step": 2500
226
+ },
227
+ {
228
+ "epoch": 1.7508417508417509,
229
+ "grad_norm": 19.942703247070312,
230
+ "learning_rate": 0.0001308578143360752,
231
+ "loss": 52.879384765625,
232
+ "step": 2600
233
+ },
234
+ {
235
+ "epoch": 1.8181818181818183,
236
+ "grad_norm": 20.36492919921875,
237
+ "learning_rate": 0.00012380728554641597,
238
+ "loss": 52.678017578125,
239
+ "step": 2700
240
+ },
241
+ {
242
+ "epoch": 1.8855218855218854,
243
+ "grad_norm": 20.429353713989258,
244
+ "learning_rate": 0.00011675675675675675,
245
+ "loss": 53.1516796875,
246
+ "step": 2800
247
+ },
248
+ {
249
+ "epoch": 1.9528619528619529,
250
+ "grad_norm": 20.908979415893555,
251
+ "learning_rate": 0.00010970622796709752,
252
+ "loss": 52.3822607421875,
253
+ "step": 2900
254
+ },
255
+ {
256
+ "epoch": 2.0202020202020203,
257
+ "grad_norm": 24.01288604736328,
258
+ "learning_rate": 0.0001026556991774383,
259
+ "loss": 51.8819384765625,
260
+ "step": 3000
261
+ },
262
+ {
263
+ "epoch": 2.0202020202020203,
264
+ "eval_loss": 5.448428153991699,
265
+ "eval_runtime": 70.4982,
266
+ "eval_samples_per_second": 13.617,
267
+ "eval_steps_per_second": 3.404,
268
+ "step": 3000
269
  }
270
  ],
271
  "logging_steps": 100,
 
285
  "attributes": {}
286
  }
287
  },
288
+ "total_flos": 1.154443985240064e+16,
289
  "train_batch_size": 8,
290
  "trial_name": null,
291
  "trial_params": null