Silemo commited on
Commit
eed004b
1 Parent(s): e714fad

Training in progress, step 3400, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d1c2e4ed987aee90e725ecff305fed01d3e4cec3c313446fbf4acd8456b8756
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c20757676a83e9b79b55197874149746ed730a010a68d7587e7a7a8797e4af1
3
  size 966995080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d53577f76fdefe8556c65117e1ab17e94a9394b496e89807249258044e5ec7e
3
  size 1925064044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8502d4c8fda153d19bf8f43fc8963d5f83d32afabe6587e68b89400a1db97099
3
  size 1925064044
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b41d2e987cb5c78d26dab771fe721c2da517630b617af0cac6deeb8db36562a9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e965350b0250570f0290355734c648f6a779f3eafb0bec172682cdf9092f567d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ea257fad0fa492e3a9fc46adc164d21d7f8ad016c3f3e68a0c6df4900fed1ab
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069be83226f429c691ea9e58c35ae52310d302cf0b73d3f098f087a042d5fe52
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 70.1955074875208,
3
  "best_model_checkpoint": "./whisper-it/checkpoint-300",
4
- "epoch": 5.916030534351145,
5
  "eval_steps": 100,
6
- "global_step": 3100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1030,6 +1030,105 @@
1030
  "eval_steps_per_second": 0.112,
1031
  "eval_wer": 184.29007210205214,
1032
  "step": 3100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1033
  }
1034
  ],
1035
  "logging_steps": 25,
@@ -1037,7 +1136,7 @@
1037
  "num_input_tokens_seen": 0,
1038
  "num_train_epochs": 8,
1039
  "save_steps": 100,
1040
- "total_flos": 2.86175712227328e+19,
1041
  "trial_name": null,
1042
  "trial_params": null
1043
  }
 
1
  {
2
  "best_metric": 70.1955074875208,
3
  "best_model_checkpoint": "./whisper-it/checkpoint-300",
4
+ "epoch": 6.488549618320611,
5
  "eval_steps": 100,
6
+ "global_step": 3400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1030
  "eval_steps_per_second": 0.112,
1031
  "eval_wer": 184.29007210205214,
1032
  "step": 3100
1033
+ },
1034
+ {
1035
+ "epoch": 5.96,
1036
+ "learning_rate": 2.5171428571428575e-06,
1037
+ "loss": 0.0084,
1038
+ "step": 3125
1039
+ },
1040
+ {
1041
+ "epoch": 6.01,
1042
+ "learning_rate": 2.445714285714286e-06,
1043
+ "loss": 0.009,
1044
+ "step": 3150
1045
+ },
1046
+ {
1047
+ "epoch": 6.06,
1048
+ "learning_rate": 2.3742857142857147e-06,
1049
+ "loss": 0.0062,
1050
+ "step": 3175
1051
+ },
1052
+ {
1053
+ "epoch": 6.11,
1054
+ "learning_rate": 2.302857142857143e-06,
1055
+ "loss": 0.0063,
1056
+ "step": 3200
1057
+ },
1058
+ {
1059
+ "epoch": 6.11,
1060
+ "eval_loss": 0.4454270899295807,
1061
+ "eval_runtime": 1613.5382,
1062
+ "eval_samples_per_second": 0.93,
1063
+ "eval_steps_per_second": 0.117,
1064
+ "eval_wer": 166.01497504159735,
1065
+ "step": 3200
1066
+ },
1067
+ {
1068
+ "epoch": 6.15,
1069
+ "learning_rate": 2.2314285714285715e-06,
1070
+ "loss": 0.0053,
1071
+ "step": 3225
1072
+ },
1073
+ {
1074
+ "epoch": 6.2,
1075
+ "learning_rate": 2.16e-06,
1076
+ "loss": 0.0056,
1077
+ "step": 3250
1078
+ },
1079
+ {
1080
+ "epoch": 6.25,
1081
+ "learning_rate": 2.0885714285714287e-06,
1082
+ "loss": 0.0065,
1083
+ "step": 3275
1084
+ },
1085
+ {
1086
+ "epoch": 6.3,
1087
+ "learning_rate": 2.0171428571428573e-06,
1088
+ "loss": 0.0059,
1089
+ "step": 3300
1090
+ },
1091
+ {
1092
+ "epoch": 6.3,
1093
+ "eval_loss": 0.44759225845336914,
1094
+ "eval_runtime": 1648.9449,
1095
+ "eval_samples_per_second": 0.91,
1096
+ "eval_steps_per_second": 0.114,
1097
+ "eval_wer": 179.18746533555185,
1098
+ "step": 3300
1099
+ },
1100
+ {
1101
+ "epoch": 6.35,
1102
+ "learning_rate": 1.945714285714286e-06,
1103
+ "loss": 0.006,
1104
+ "step": 3325
1105
+ },
1106
+ {
1107
+ "epoch": 6.39,
1108
+ "learning_rate": 1.8742857142857142e-06,
1109
+ "loss": 0.0058,
1110
+ "step": 3350
1111
+ },
1112
+ {
1113
+ "epoch": 6.44,
1114
+ "learning_rate": 1.8028571428571432e-06,
1115
+ "loss": 0.0056,
1116
+ "step": 3375
1117
+ },
1118
+ {
1119
+ "epoch": 6.49,
1120
+ "learning_rate": 1.7314285714285716e-06,
1121
+ "loss": 0.0058,
1122
+ "step": 3400
1123
+ },
1124
+ {
1125
+ "epoch": 6.49,
1126
+ "eval_loss": 0.4489666819572449,
1127
+ "eval_runtime": 1678.248,
1128
+ "eval_samples_per_second": 0.894,
1129
+ "eval_steps_per_second": 0.112,
1130
+ "eval_wer": 189.57986688851912,
1131
+ "step": 3400
1132
  }
1133
  ],
1134
  "logging_steps": 25,
 
1136
  "num_input_tokens_seen": 0,
1137
  "num_train_epochs": 8,
1138
  "save_steps": 100,
1139
+ "total_flos": 3.138597096800256e+19,
1140
  "trial_name": null,
1141
  "trial_params": null
1142
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41aeb0de3cf3c068ad356f23e2a4d52e468d71a8f1523974035aff9cc867de12
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6dbc4dfe40c6e33f03f512f01526c1128aacac99b0beb33850a3ef004ff4c98
3
  size 4856