elsayedissa commited on
Commit
e30e002
1 Parent(s): 8fb8892

Training in progress, step 17000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2828bba9c0610d92bcb9ced115dba1825e24c111402867d65a37cba2fd4cdf3
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0afdff77222472257de0ba34c36739c26555750dfdb27e7b6f2ffed753b60d4e
3
  size 12347192855
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ddc7f21fd5cb7cbeac420cbf26556fe05d0d0276c5d96c3c5d572508243cc6
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46b6b71b47c9b3cdde4a1d39cea580e81a6bbf969d5738793f41c7f51939ad5
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:d6024b9a42abf2c5787dca8b8ac21caaa78ef8edc18fdd3f5727713a6bded2de
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009dbf954364aba5d9d07623c2bc3be59611e798b46569f55549a02c3eabd95e
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8beddb254d719968614077f7da7885f0decec146856dee753939f87ce125fd6c
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9006cc2f9bf0c15a1ea19a9fdf3bcc02dfdb969110e593a43ce6b82aac6cf3
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fd534b0cae4142fc61b98b6723afbc5b4255a5022df3ad8a29653d61c4f84f8
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3675e25dffe1ac318cb230ca76cdb84aec69a7bf2cb79f6d7b5f6265ec4df7c8
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": 0.5553819986809677,
5
- "global_step": 16000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -3990,11 +3990,260 @@
3990
  "eval_steps_per_second": 0.063,
3991
  "eval_wer": 0.09301142911866007,
3992
  "step": 16000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3993
  }
3994
  ],
3995
  "max_steps": 25000,
3996
  "num_train_epochs": 1,
3997
- "total_flos": 5.435317813248e+20,
3998
  "trial_name": null,
3999
  "trial_params": null
4000
  }
 
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
+ "epoch": 0.5900933735985282,
5
+ "global_step": 17000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
3990
  "eval_steps_per_second": 0.063,
3991
  "eval_wer": 0.09301142911866007,
3992
  "step": 16000
3993
+ },
3994
+ {
3995
+ "epoch": 0.56,
3996
+ "learning_rate": 3.6677551020408162e-06,
3997
+ "loss": 0.1708,
3998
+ "step": 16025
3999
+ },
4000
+ {
4001
+ "epoch": 0.56,
4002
+ "learning_rate": 3.6575510204081637e-06,
4003
+ "loss": 0.1467,
4004
+ "step": 16050
4005
+ },
4006
+ {
4007
+ "epoch": 0.56,
4008
+ "learning_rate": 3.6473469387755108e-06,
4009
+ "loss": 0.1532,
4010
+ "step": 16075
4011
+ },
4012
+ {
4013
+ "epoch": 0.56,
4014
+ "learning_rate": 3.6371428571428574e-06,
4015
+ "loss": 0.1422,
4016
+ "step": 16100
4017
+ },
4018
+ {
4019
+ "epoch": 0.56,
4020
+ "learning_rate": 3.626938775510204e-06,
4021
+ "loss": 0.1711,
4022
+ "step": 16125
4023
+ },
4024
+ {
4025
+ "epoch": 0.56,
4026
+ "learning_rate": 3.616734693877551e-06,
4027
+ "loss": 0.1462,
4028
+ "step": 16150
4029
+ },
4030
+ {
4031
+ "epoch": 0.56,
4032
+ "learning_rate": 3.6065306122448986e-06,
4033
+ "loss": 0.1686,
4034
+ "step": 16175
4035
+ },
4036
+ {
4037
+ "epoch": 0.56,
4038
+ "learning_rate": 3.5963265306122452e-06,
4039
+ "loss": 0.1512,
4040
+ "step": 16200
4041
+ },
4042
+ {
4043
+ "epoch": 0.56,
4044
+ "learning_rate": 3.586122448979592e-06,
4045
+ "loss": 0.1702,
4046
+ "step": 16225
4047
+ },
4048
+ {
4049
+ "epoch": 0.56,
4050
+ "learning_rate": 3.575918367346939e-06,
4051
+ "loss": 0.1339,
4052
+ "step": 16250
4053
+ },
4054
+ {
4055
+ "epoch": 0.56,
4056
+ "learning_rate": 3.5657142857142864e-06,
4057
+ "loss": 0.17,
4058
+ "step": 16275
4059
+ },
4060
+ {
4061
+ "epoch": 0.57,
4062
+ "learning_rate": 3.555510204081633e-06,
4063
+ "loss": 0.1701,
4064
+ "step": 16300
4065
+ },
4066
+ {
4067
+ "epoch": 0.57,
4068
+ "learning_rate": 3.5453061224489797e-06,
4069
+ "loss": 0.1606,
4070
+ "step": 16325
4071
+ },
4072
+ {
4073
+ "epoch": 0.57,
4074
+ "learning_rate": 3.5351020408163268e-06,
4075
+ "loss": 0.1479,
4076
+ "step": 16350
4077
+ },
4078
+ {
4079
+ "epoch": 0.57,
4080
+ "learning_rate": 3.5248979591836734e-06,
4081
+ "loss": 0.1524,
4082
+ "step": 16375
4083
+ },
4084
+ {
4085
+ "epoch": 0.57,
4086
+ "learning_rate": 3.514693877551021e-06,
4087
+ "loss": 0.1392,
4088
+ "step": 16400
4089
+ },
4090
+ {
4091
+ "epoch": 0.57,
4092
+ "learning_rate": 3.5044897959183675e-06,
4093
+ "loss": 0.1603,
4094
+ "step": 16425
4095
+ },
4096
+ {
4097
+ "epoch": 0.57,
4098
+ "learning_rate": 3.4942857142857146e-06,
4099
+ "loss": 0.1426,
4100
+ "step": 16450
4101
+ },
4102
+ {
4103
+ "epoch": 0.57,
4104
+ "learning_rate": 3.4840816326530612e-06,
4105
+ "loss": 0.1652,
4106
+ "step": 16475
4107
+ },
4108
+ {
4109
+ "epoch": 0.57,
4110
+ "learning_rate": 3.4738775510204087e-06,
4111
+ "loss": 0.1475,
4112
+ "step": 16500
4113
+ },
4114
+ {
4115
+ "epoch": 0.57,
4116
+ "learning_rate": 3.4636734693877554e-06,
4117
+ "loss": 0.1568,
4118
+ "step": 16525
4119
+ },
4120
+ {
4121
+ "epoch": 0.57,
4122
+ "learning_rate": 3.4534693877551024e-06,
4123
+ "loss": 0.135,
4124
+ "step": 16550
4125
+ },
4126
+ {
4127
+ "epoch": 0.58,
4128
+ "learning_rate": 3.443265306122449e-06,
4129
+ "loss": 0.1683,
4130
+ "step": 16575
4131
+ },
4132
+ {
4133
+ "epoch": 0.58,
4134
+ "learning_rate": 3.433061224489796e-06,
4135
+ "loss": 0.1449,
4136
+ "step": 16600
4137
+ },
4138
+ {
4139
+ "epoch": 0.58,
4140
+ "learning_rate": 3.422857142857143e-06,
4141
+ "loss": 0.1593,
4142
+ "step": 16625
4143
+ },
4144
+ {
4145
+ "epoch": 0.58,
4146
+ "learning_rate": 3.4126530612244902e-06,
4147
+ "loss": 0.1336,
4148
+ "step": 16650
4149
+ },
4150
+ {
4151
+ "epoch": 0.58,
4152
+ "learning_rate": 3.402448979591837e-06,
4153
+ "loss": 0.1527,
4154
+ "step": 16675
4155
+ },
4156
+ {
4157
+ "epoch": 0.58,
4158
+ "learning_rate": 3.392244897959184e-06,
4159
+ "loss": 0.1499,
4160
+ "step": 16700
4161
+ },
4162
+ {
4163
+ "epoch": 0.58,
4164
+ "learning_rate": 3.382040816326531e-06,
4165
+ "loss": 0.1686,
4166
+ "step": 16725
4167
+ },
4168
+ {
4169
+ "epoch": 0.58,
4170
+ "learning_rate": 3.371836734693878e-06,
4171
+ "loss": 0.124,
4172
+ "step": 16750
4173
+ },
4174
+ {
4175
+ "epoch": 0.58,
4176
+ "learning_rate": 3.3616326530612247e-06,
4177
+ "loss": 0.143,
4178
+ "step": 16775
4179
+ },
4180
+ {
4181
+ "epoch": 0.58,
4182
+ "learning_rate": 3.3514285714285718e-06,
4183
+ "loss": 0.1338,
4184
+ "step": 16800
4185
+ },
4186
+ {
4187
+ "epoch": 0.58,
4188
+ "learning_rate": 3.3412244897959184e-06,
4189
+ "loss": 0.1613,
4190
+ "step": 16825
4191
+ },
4192
+ {
4193
+ "epoch": 0.58,
4194
+ "learning_rate": 3.331020408163266e-06,
4195
+ "loss": 0.1334,
4196
+ "step": 16850
4197
+ },
4198
+ {
4199
+ "epoch": 0.59,
4200
+ "learning_rate": 3.3208163265306125e-06,
4201
+ "loss": 0.1633,
4202
+ "step": 16875
4203
+ },
4204
+ {
4205
+ "epoch": 0.59,
4206
+ "learning_rate": 3.3106122448979596e-06,
4207
+ "loss": 0.1399,
4208
+ "step": 16900
4209
+ },
4210
+ {
4211
+ "epoch": 0.59,
4212
+ "learning_rate": 3.3004081632653062e-06,
4213
+ "loss": 0.1783,
4214
+ "step": 16925
4215
+ },
4216
+ {
4217
+ "epoch": 0.59,
4218
+ "learning_rate": 3.2902040816326537e-06,
4219
+ "loss": 0.1448,
4220
+ "step": 16950
4221
+ },
4222
+ {
4223
+ "epoch": 0.59,
4224
+ "learning_rate": 3.2800000000000004e-06,
4225
+ "loss": 0.167,
4226
+ "step": 16975
4227
+ },
4228
+ {
4229
+ "epoch": 0.59,
4230
+ "learning_rate": 3.2697959183673474e-06,
4231
+ "loss": 0.117,
4232
+ "step": 17000
4233
+ },
4234
+ {
4235
+ "epoch": 0.59,
4236
+ "eval_loss": 0.16128729283809662,
4237
+ "eval_runtime": 31248.2115,
4238
+ "eval_samples_per_second": 0.993,
4239
+ "eval_steps_per_second": 0.062,
4240
+ "eval_wer": 0.09140322894892396,
4241
+ "step": 17000
4242
  }
4243
  ],
4244
  "max_steps": 25000,
4245
  "num_train_epochs": 1,
4246
+ "total_flos": 5.775025176576e+20,
4247
  "trial_name": null,
4248
  "trial_params": null
4249
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ddc7f21fd5cb7cbeac420cbf26556fe05d0d0276c5d96c3c5d572508243cc6
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46b6b71b47c9b3cdde4a1d39cea580e81a6bbf969d5738793f41c7f51939ad5
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 sha256:75cd60efea19799c78e56543455f4479b2c2960615ec3453f56a3b9470094bf2
3
- size 109957
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78bc9cee84c391c8ae997316cec7200e593d160d602a2fd280af39d860d9f6a
3
+ size 116636