lyan62 commited on
Commit
a89e36f
1 Parent(s): b063900

Training in progress, step 20000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de9c1066ffe7cedd3790cf74f90e6b42b28010adb6f755977ef3da6115d6d433
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4230b2f729c6f6b9cf0568a76b10edac946334782498c2cece3434c9ba7192
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24c90f2b89c141a63dd59fa57c3a3739114415c665224cdb6d8703c01f21b2f5
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55e6567afe216163f2add39cb73017a210ac0250560853a89a08c9450611846
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:ef6fab0aad647d44150184b9e3a085bf5367acaceef4345dfcb5f1b251e74c61
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0464f1347d61e84da4d96f6b32a2534e56c3ad806e9bffb354f32a8f0bd031c1
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 sha256:1145a3091a460210ae7da3675a1a49999755433b2c836a2ac8ae1975b4b3b67c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c6a56c106955640f800f31d987f9c243e1d396541c35be5e0ed3d9534cd8df
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 sha256:3fa7aa39f02a35206d52f24c94bb57385d48d208a5d017ded38bea7374ae7e8a
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c49e159e2c2951dcf194176247cf9ff0dc088cb500bb54d6d916a722ca08fa9
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 sha256:45753a61dd9d065df5cc764cca8cc81c848dd8932990c9f4f549f46fe7721b45
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:912fcc6ea4eaec59cfea6708a6a65f4d05da5d26eba880b63d418e4758b26066
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2332b5dfef9cf69443c488e4f08214dae793b15c742568c8e56acc2a65ad60b
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df8a41243d0000edfc13e75c9f4339e9d6523a15a3a1f7fb160e4776f068845
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3513f15afaa200bb7041b668e62843503210a13b0c4a572a8b74a3c40d994fe
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": 0.25531697602573594,
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": 0.0001496894616828291,
187
  "loss": 0.3931,
188
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
189
  }
190
  ],
191
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3404226347009813,
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": 0.0001496894616828291,
187
  "loss": 0.3931,
188
  "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.26,
192
+ "learning_rate": 0.0001496684264412764,
193
+ "loss": 0.3921,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.27,
198
+ "learning_rate": 0.00014964670360048104,
199
+ "loss": 0.3909,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.28,
204
+ "learning_rate": 0.00014962429337483864,
205
+ "loss": 0.3903,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.29,
210
+ "learning_rate": 0.00014960119598552907,
211
+ "loss": 0.3892,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.3,
216
+ "learning_rate": 0.00014957745991457127,
217
+ "loss": 0.3885,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.31,
222
+ "learning_rate": 0.00014955303988623036,
223
+ "loss": 0.3877,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.31,
228
+ "learning_rate": 0.00014952788514615529,
229
+ "loss": 0.3871,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.32,
234
+ "learning_rate": 0.0001495020441939234,
235
+ "loss": 0.3858,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.33,
240
+ "learning_rate": 0.0001494755172845744,
241
+ "loss": 0.3854,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.34,
246
+ "learning_rate": 0.00014944830467991823,
247
+ "loss": 0.3847,
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 sha256:24c90f2b89c141a63dd59fa57c3a3739114415c665224cdb6d8703c01f21b2f5
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55e6567afe216163f2add39cb73017a210ac0250560853a89a08c9450611846
3
  size 201355195