Hugging Face's logo

Nadav
/
PretrainedPHD-v3

Transformers
PyTorch
pixel
Model card Files
xet
 Community
Nadav commited on
Commit
242a67d
·
1 Parent(s): 40371b4

Training in progress, step 85000

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +71 -3
  7. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f114d2b0773cada99ce881c4e22a2410886550308dc17b6c8e48e4e5a5387ce
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf938e63db77fb407ca47abed9e7a5b622550039846f9a1a0cc7d7854dbb2281
3
  size 893439185
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a9b5fb1dcfb7895228c2f4a730ed4edea1a215819024a4c0654968eea89946d
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5bcc93b2c675ac193323529f67e669dbfe2287137af0167133422edba34de4
3
  size 449471589
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2c5f0547efe6f38ef562914beec18a2f1351d0dbb968a034845dcfebc05fae2
3
  size 15523
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3655ec059c2901c4c797618f117c418550187bdda5cfab80dab7cfa4d45cc8
3
  size 15523
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5994f16dd9f02e200635d626b21258e19b080289a3a2044ab0c57ee033a8704e
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c4e080eeb88caf6658eef6af97f13224fe0c49f64a0c60f4f4bdea046def223
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43311d0b3c3eb1b18d444cfb5122f037db53b11eb8c47a5ba47de792dbb0736a
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a11653a0100092bd397f58122a7fff6e0777910c42ff21f17a4fb4b6f481092
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": 0.35,
5
- "global_step": 80000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1094,11 +1094,79 @@
1094
  "eval_samples_per_second": 86.675,
1095
  "eval_steps_per_second": 1.354,
1096
  "step": 80000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1097
  }
1098
  ],
1099
  "max_steps": 200000,
1100
  "num_train_epochs": 9223372036854775807,
1101
- "total_flos": 1.8839445389180928e+21,
1102
  "trial_name": null,
1103
  "trial_params": null
1104
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.375,
5
+ "global_step": 85000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1094
  "eval_samples_per_second": 86.675,
1095
  "eval_steps_per_second": 1.354,
1096
  "step": 80000
1097
+ },
1098
+ {
1099
+ "epoch": 0.35,
1100
+ "learning_rate": 6.9098014163495e-05,
1101
+ "loss": 0.4409,
1102
+ "step": 80500
1103
+ },
1104
+ {
1105
+ "epoch": 0.35,
1106
+ "learning_rate": 6.875774190311069e-05,
1107
+ "loss": 0.4412,
1108
+ "step": 81000
1109
+ },
1110
+ {
1111
+ "epoch": 0.36,
1112
+ "learning_rate": 6.841664509599106e-05,
1113
+ "loss": 0.4414,
1114
+ "step": 81500
1115
+ },
1116
+ {
1117
+ "epoch": 0.36,
1118
+ "learning_rate": 6.807474478259389e-05,
1119
+ "loss": 0.4416,
1120
+ "step": 82000
1121
+ },
1122
+ {
1123
+ "epoch": 0.36,
1124
+ "learning_rate": 6.773206205294097e-05,
1125
+ "loss": 0.4419,
1126
+ "step": 82500
1127
+ },
1128
+ {
1129
+ "epoch": 0.36,
1130
+ "learning_rate": 6.738930567901446e-05,
1131
+ "loss": 0.4411,
1132
+ "step": 83000
1133
+ },
1134
+ {
1135
+ "epoch": 0.37,
1136
+ "learning_rate": 6.704512303767616e-05,
1137
+ "loss": 0.4412,
1138
+ "step": 83500
1139
+ },
1140
+ {
1141
+ "epoch": 0.37,
1142
+ "learning_rate": 6.67002214920013e-05,
1143
+ "loss": 0.4416,
1144
+ "step": 84000
1145
+ },
1146
+ {
1147
+ "epoch": 0.37,
1148
+ "learning_rate": 6.635462231714186e-05,
1149
+ "loss": 0.4409,
1150
+ "step": 84500
1151
+ },
1152
+ {
1153
+ "epoch": 0.38,
1154
+ "learning_rate": 6.600834683128286e-05,
1155
+ "loss": 0.44,
1156
+ "step": 85000
1157
+ },
1158
+ {
1159
+ "epoch": 0.38,
1160
+ "eval_loss": 0.4143606424331665,
1161
+ "eval_runtime": 94.0695,
1162
+ "eval_samples_per_second": 68.035,
1163
+ "eval_steps_per_second": 1.063,
1164
+ "step": 85000
1165
  }
1166
  ],
1167
  "max_steps": 200000,
1168
  "num_train_epochs": 9223372036854775807,
1169
+ "total_flos": 2.0016910726004736e+21,
1170
  "trial_name": null,
1171
  "trial_params": null
1172
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a9b5fb1dcfb7895228c2f4a730ed4edea1a215819024a4c0654968eea89946d
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5bcc93b2c675ac193323529f67e669dbfe2287137af0167133422edba34de4
3
  size 449471589