elsayedissa commited on
Commit
55644d4
1 Parent(s): af4dead

Training in progress, step 25000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd7eb848685ef3f06accf08b0991ae5fb7aca4770e2f824f2a4e024e639e7fb2
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e95d32dcf1313d4d274cdf1f5d1af89486240164e0b3639609c384f3a6aa38
3
  size 12347192855
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e71d25993f756e62aa28d38555706c7d09a30a1163fed42767f77816851100d
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d72bd6229dd4892c0ec31be77fa696d2217e4e04889cd376f1c5656a21f2f9
3
  size 6173655480
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eaf0badf99eb2f5a4bcf7352b7e7e60bdb9fb3eb0aafd7a775251c7a5269cfd
3
- size 14511
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b77749c5af5968880b87d75a81d87a96c674b888d3e33d9bb37ea44ce8d55c4
3
+ size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf5ce6709b8cf97417772fb30cceb44ce3363ceb800bc698892d9018ba93c60f
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f23d7a993773edab63493abcae990440dc2feb5ff92913bd748a46c87b40a2
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0b3ee000403ded4a43ceaf77d66b9d28960f5cc5d0851756133984c89e3a2c4
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc891dbaea2add2de2987a866c707e13cbde49cb55e08b12d463d2745e1171b5
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
- "epoch": 0.8330729980214516,
5
- "global_step": 24000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -5982,11 +5982,260 @@
5982
  "eval_steps_per_second": 0.062,
5983
  "eval_wer": 0.08535018806365434,
5984
  "step": 24000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5985
  }
5986
  ],
5987
  "max_steps": 25000,
5988
  "num_train_epochs": 1,
5989
- "total_flos": 8.152976719872e+20,
5990
  "trial_name": null,
5991
  "trial_params": null
5992
  }
 
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
+ "epoch": 0.8677843729390121,
5
+ "global_step": 25000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
5982
  "eval_steps_per_second": 0.062,
5983
  "eval_wer": 0.08535018806365434,
5984
  "step": 24000
5985
+ },
5986
+ {
5987
+ "epoch": 0.83,
5988
+ "learning_rate": 4.0285714285714287e-07,
5989
+ "loss": 0.1454,
5990
+ "step": 24025
5991
+ },
5992
+ {
5993
+ "epoch": 0.83,
5994
+ "learning_rate": 3.9265306122448983e-07,
5995
+ "loss": 0.1063,
5996
+ "step": 24050
5997
+ },
5998
+ {
5999
+ "epoch": 0.84,
6000
+ "learning_rate": 3.824489795918368e-07,
6001
+ "loss": 0.1344,
6002
+ "step": 24075
6003
+ },
6004
+ {
6005
+ "epoch": 0.84,
6006
+ "learning_rate": 3.722448979591837e-07,
6007
+ "loss": 0.1193,
6008
+ "step": 24100
6009
+ },
6010
+ {
6011
+ "epoch": 0.84,
6012
+ "learning_rate": 3.6204081632653065e-07,
6013
+ "loss": 0.1502,
6014
+ "step": 24125
6015
+ },
6016
+ {
6017
+ "epoch": 0.84,
6018
+ "learning_rate": 3.518367346938776e-07,
6019
+ "loss": 0.137,
6020
+ "step": 24150
6021
+ },
6022
+ {
6023
+ "epoch": 0.84,
6024
+ "learning_rate": 3.4163265306122456e-07,
6025
+ "loss": 0.1305,
6026
+ "step": 24175
6027
+ },
6028
+ {
6029
+ "epoch": 0.84,
6030
+ "learning_rate": 3.314285714285714e-07,
6031
+ "loss": 0.1253,
6032
+ "step": 24200
6033
+ },
6034
+ {
6035
+ "epoch": 0.84,
6036
+ "learning_rate": 3.2122448979591837e-07,
6037
+ "loss": 0.1539,
6038
+ "step": 24225
6039
+ },
6040
+ {
6041
+ "epoch": 0.84,
6042
+ "learning_rate": 3.110204081632653e-07,
6043
+ "loss": 0.1062,
6044
+ "step": 24250
6045
+ },
6046
+ {
6047
+ "epoch": 0.84,
6048
+ "learning_rate": 3.008163265306123e-07,
6049
+ "loss": 0.1738,
6050
+ "step": 24275
6051
+ },
6052
+ {
6053
+ "epoch": 0.84,
6054
+ "learning_rate": 2.9061224489795924e-07,
6055
+ "loss": 0.1179,
6056
+ "step": 24300
6057
+ },
6058
+ {
6059
+ "epoch": 0.84,
6060
+ "learning_rate": 2.8040816326530614e-07,
6061
+ "loss": 0.1602,
6062
+ "step": 24325
6063
+ },
6064
+ {
6065
+ "epoch": 0.85,
6066
+ "learning_rate": 2.702040816326531e-07,
6067
+ "loss": 0.1311,
6068
+ "step": 24350
6069
+ },
6070
+ {
6071
+ "epoch": 0.85,
6072
+ "learning_rate": 2.6e-07,
6073
+ "loss": 0.1538,
6074
+ "step": 24375
6075
+ },
6076
+ {
6077
+ "epoch": 0.85,
6078
+ "learning_rate": 2.502040816326531e-07,
6079
+ "loss": 0.1313,
6080
+ "step": 24400
6081
+ },
6082
+ {
6083
+ "epoch": 0.85,
6084
+ "learning_rate": 2.4000000000000003e-07,
6085
+ "loss": 0.1648,
6086
+ "step": 24425
6087
+ },
6088
+ {
6089
+ "epoch": 0.85,
6090
+ "learning_rate": 2.2979591836734694e-07,
6091
+ "loss": 0.1074,
6092
+ "step": 24450
6093
+ },
6094
+ {
6095
+ "epoch": 0.85,
6096
+ "learning_rate": 2.195918367346939e-07,
6097
+ "loss": 0.1513,
6098
+ "step": 24475
6099
+ },
6100
+ {
6101
+ "epoch": 0.85,
6102
+ "learning_rate": 2.0938775510204082e-07,
6103
+ "loss": 0.1201,
6104
+ "step": 24500
6105
+ },
6106
+ {
6107
+ "epoch": 0.85,
6108
+ "learning_rate": 1.9918367346938778e-07,
6109
+ "loss": 0.1598,
6110
+ "step": 24525
6111
+ },
6112
+ {
6113
+ "epoch": 0.85,
6114
+ "learning_rate": 1.8897959183673468e-07,
6115
+ "loss": 0.1192,
6116
+ "step": 24550
6117
+ },
6118
+ {
6119
+ "epoch": 0.85,
6120
+ "learning_rate": 1.7877551020408164e-07,
6121
+ "loss": 0.1354,
6122
+ "step": 24575
6123
+ },
6124
+ {
6125
+ "epoch": 0.85,
6126
+ "learning_rate": 1.685714285714286e-07,
6127
+ "loss": 0.1305,
6128
+ "step": 24600
6129
+ },
6130
+ {
6131
+ "epoch": 0.85,
6132
+ "learning_rate": 1.5836734693877552e-07,
6133
+ "loss": 0.1446,
6134
+ "step": 24625
6135
+ },
6136
+ {
6137
+ "epoch": 0.86,
6138
+ "learning_rate": 1.4816326530612245e-07,
6139
+ "loss": 0.1064,
6140
+ "step": 24650
6141
+ },
6142
+ {
6143
+ "epoch": 0.86,
6144
+ "learning_rate": 1.3795918367346938e-07,
6145
+ "loss": 0.1283,
6146
+ "step": 24675
6147
+ },
6148
+ {
6149
+ "epoch": 0.86,
6150
+ "learning_rate": 1.2775510204081634e-07,
6151
+ "loss": 0.1159,
6152
+ "step": 24700
6153
+ },
6154
+ {
6155
+ "epoch": 0.86,
6156
+ "learning_rate": 1.1755102040816327e-07,
6157
+ "loss": 0.1518,
6158
+ "step": 24725
6159
+ },
6160
+ {
6161
+ "epoch": 0.86,
6162
+ "learning_rate": 1.073469387755102e-07,
6163
+ "loss": 0.1121,
6164
+ "step": 24750
6165
+ },
6166
+ {
6167
+ "epoch": 0.86,
6168
+ "learning_rate": 9.714285714285714e-08,
6169
+ "loss": 0.1322,
6170
+ "step": 24775
6171
+ },
6172
+ {
6173
+ "epoch": 0.86,
6174
+ "learning_rate": 8.69387755102041e-08,
6175
+ "loss": 0.1158,
6176
+ "step": 24800
6177
+ },
6178
+ {
6179
+ "epoch": 0.86,
6180
+ "learning_rate": 7.673469387755103e-08,
6181
+ "loss": 0.1525,
6182
+ "step": 24825
6183
+ },
6184
+ {
6185
+ "epoch": 0.86,
6186
+ "learning_rate": 6.653061224489796e-08,
6187
+ "loss": 0.127,
6188
+ "step": 24850
6189
+ },
6190
+ {
6191
+ "epoch": 0.86,
6192
+ "learning_rate": 5.63265306122449e-08,
6193
+ "loss": 0.1458,
6194
+ "step": 24875
6195
+ },
6196
+ {
6197
+ "epoch": 0.86,
6198
+ "learning_rate": 4.6122448979591835e-08,
6199
+ "loss": 0.1193,
6200
+ "step": 24900
6201
+ },
6202
+ {
6203
+ "epoch": 0.87,
6204
+ "learning_rate": 3.591836734693878e-08,
6205
+ "loss": 0.1354,
6206
+ "step": 24925
6207
+ },
6208
+ {
6209
+ "epoch": 0.87,
6210
+ "learning_rate": 2.5714285714285715e-08,
6211
+ "loss": 0.1071,
6212
+ "step": 24950
6213
+ },
6214
+ {
6215
+ "epoch": 0.87,
6216
+ "learning_rate": 1.5510204081632655e-08,
6217
+ "loss": 0.1518,
6218
+ "step": 24975
6219
+ },
6220
+ {
6221
+ "epoch": 0.87,
6222
+ "learning_rate": 5.306122448979592e-09,
6223
+ "loss": 0.1289,
6224
+ "step": 25000
6225
+ },
6226
+ {
6227
+ "epoch": 0.87,
6228
+ "eval_loss": 0.14659932255744934,
6229
+ "eval_runtime": 31237.4282,
6230
+ "eval_samples_per_second": 0.994,
6231
+ "eval_steps_per_second": 0.062,
6232
+ "eval_wer": 0.08550209198112428,
6233
+ "step": 25000
6234
  }
6235
  ],
6236
  "max_steps": 25000,
6237
  "num_train_epochs": 1,
6238
+ "total_flos": 8.4926840832e+20,
6239
  "trial_name": null,
6240
  "trial_params": null
6241
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e71d25993f756e62aa28d38555706c7d09a30a1163fed42767f77816851100d
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d72bd6229dd4892c0ec31be77fa696d2217e4e04889cd376f1c5656a21f2f9
3
  size 6173655480
runs/Dec26_19-57-19_gpu07.cyverse.org/events.out.tfevents.1672109970.gpu07.cyverse.org.126369.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3be1bf9d6afc1185ac6ba7539df5045fb2a516aaf0676ce7cb1d8b30a8903c18
3
- size 163704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31cb789f8c864328076774003b86f846c87640b677ecab3bde4a275b556c94c7
3
+ size 170428