Transformers
PyTorch
English
pixel
pretraining
Inference Endpoints
plip commited on
Commit
a1f119e
1 Parent(s): 300740d

Training in progress, step 580000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a767a78fa4809e168b3ccdaca8245fdd800f92f9fb131a29e7c678020a7b2e1
3
  size 893439185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3c98677de897190cfb61fcdb47a41a233aacb3947cfaaf5565a6afc239a9e0
3
  size 893439185
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f451f7904b0f8403b186893bae5bf08f2c2acf369a21d50224d0be67c5692d4
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4bdcb08582dcc416cc4a3a9ae8bcb9040fe1e5dce27da0219c313edd1229bf9
3
  size 449471589
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28edfca80c69ce874f473f07c4b7e161b12e6d09912377717af008dd4d50a13b
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0acf92adb8fe29e7f8f300892a64ae6b1061f78cbc741a04875cceecbd7627bb
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 sha256:35b65d15b0a371107c6c614a483d347936ef1bc44210919862c9b83a7094116f
3
- size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989d83467172119d42cc5db629615122c0d05d39b97d6151f3073b83b05e95f1
3
+ size 14439
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:916d53efc24960a2419b0c56ff522c7980d4be4e94feb1e3f3194d2ea4a6489c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb6b551f6971cdac4e633aeb80c6604a5c29c6604766e95edb5b993ce689e66
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:eaddfaade81997be2461768daaef367db08e33d6fa1ca3618aadc35b99ca7474
3
  size 14439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7228d0f23743ac31eeebdd713de3352c2963513ff68c7b3a41fefd85d589e485
3
  size 14439
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e62e41706c3cdebd0963ceae6fb24ae079cf26e6452a67e31e4c02f3a80456e6
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2528712b13528834db613d1453dd7fb04ea3b7a1940fa3521b7d0be4a96c0a
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": 8.704017591277658,
5
- "global_step": 570000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -4224,11 +4224,85 @@
4224
  "eval_samples_per_second": 954.187,
4225
  "eval_steps_per_second": 15.267,
4226
  "step": 570000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4227
  }
4228
  ],
4229
  "max_steps": 1000000,
4230
  "num_train_epochs": 16,
4231
- "total_flos": 3.995709622184597e+22,
4232
  "trial_name": null,
4233
  "trial_params": null
4234
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 8.856719654282529,
5
+ "global_step": 580000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
4224
  "eval_samples_per_second": 954.187,
4225
  "eval_steps_per_second": 15.267,
4226
  "step": 570000
4227
+ },
4228
+ {
4229
+ "epoch": 8.72,
4230
+ "learning_rate": 6.939267446224418e-05,
4231
+ "loss": 0.2569,
4232
+ "step": 571000
4233
+ },
4234
+ {
4235
+ "epoch": 8.73,
4236
+ "learning_rate": 6.91639202643299e-05,
4237
+ "loss": 0.2569,
4238
+ "step": 572000
4239
+ },
4240
+ {
4241
+ "epoch": 8.75,
4242
+ "learning_rate": 6.893528456804756e-05,
4243
+ "loss": 0.2569,
4244
+ "step": 573000
4245
+ },
4246
+ {
4247
+ "epoch": 8.77,
4248
+ "learning_rate": 6.870676987372044e-05,
4249
+ "loss": 0.2568,
4250
+ "step": 574000
4251
+ },
4252
+ {
4253
+ "epoch": 8.78,
4254
+ "learning_rate": 6.847837868034861e-05,
4255
+ "loss": 0.257,
4256
+ "step": 575000
4257
+ },
4258
+ {
4259
+ "epoch": 8.78,
4260
+ "eval_runtime": 1.0002,
4261
+ "eval_samples_per_second": 999.79,
4262
+ "eval_steps_per_second": 15.997,
4263
+ "step": 575000
4264
+ },
4265
+ {
4266
+ "epoch": 8.8,
4267
+ "learning_rate": 6.825011348558167e-05,
4268
+ "loss": 0.2573,
4269
+ "step": 576000
4270
+ },
4271
+ {
4272
+ "epoch": 8.81,
4273
+ "learning_rate": 6.802197678569109e-05,
4274
+ "loss": 0.2566,
4275
+ "step": 577000
4276
+ },
4277
+ {
4278
+ "epoch": 8.83,
4279
+ "learning_rate": 6.779397107554339e-05,
4280
+ "loss": 0.2562,
4281
+ "step": 578000
4282
+ },
4283
+ {
4284
+ "epoch": 8.84,
4285
+ "learning_rate": 6.756609884857239e-05,
4286
+ "loss": 0.2566,
4287
+ "step": 579000
4288
+ },
4289
+ {
4290
+ "epoch": 8.86,
4291
+ "learning_rate": 6.733836259675233e-05,
4292
+ "loss": 0.2564,
4293
+ "step": 580000
4294
+ },
4295
+ {
4296
+ "epoch": 8.86,
4297
+ "eval_runtime": 1.0727,
4298
+ "eval_samples_per_second": 932.263,
4299
+ "eval_steps_per_second": 14.916,
4300
+ "step": 580000
4301
  }
4302
  ],
4303
  "max_steps": 1000000,
4304
  "num_train_epochs": 16,
4305
+ "total_flos": 4.065809883214944e+22,
4306
  "trial_name": null,
4307
  "trial_params": null
4308
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f451f7904b0f8403b186893bae5bf08f2c2acf369a21d50224d0be67c5692d4
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4bdcb08582dcc416cc4a3a9ae8bcb9040fe1e5dce27da0219c313edd1229bf9
3
  size 449471589