Step... (29000/50000 | Loss: 1.6177186965942383, Acc: 0.67269366979599): 58%|████████████████▊ | 29067/50000 [11:37:39<7:29:53, 1.29s/it]

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ceb7903825a5802361e2abfa48cc22549619333ade477fa0502eca94fff7518
+oid sha256:ab9e1ec9fe5381c6cd01fb75c25867879a3e432dfaf4960054ef157b5e52d406
 size 249750019

outputs/checkpoints/checkpoint-22000/training_state.json

@@ -1 +0,0 @@
-{"step": 22001}

outputs/checkpoints/checkpoint-23000/training_state.json

@@ -1 +0,0 @@
-{"step": 23001}

outputs/checkpoints/checkpoint-24000/training_state.json

@@ -1 +0,0 @@
-{"step": 24001}

outputs/checkpoints/{checkpoint-22000 → checkpoint-27000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6736afa967315a5ccac23ff15ab3d3f2f90881f2858be1c86b98b60e0fa764
+oid sha256:b3ab5739e776f02370c13f8fea2309cb8ca0ed3a123eae940e7afdb05a7bef05
 size 249750019

outputs/checkpoints/{checkpoint-24000 → checkpoint-27000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcac7bac463ddd6530546523b0141118f658d528e0d7ec682da2661fe2a0f7df
+oid sha256:61a747cb65ecae47682216a9acae813b1c986f07969e392fec94655708af0c9d
 size 499500278

outputs/checkpoints/checkpoint-27000/training_state.json

@@ -0,0 +1 @@
+{"step": 27001}

outputs/checkpoints/{checkpoint-24000 → checkpoint-28000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b22d22612dd38ad92ffdda4b0cf432e201d6c90dd5386d04a2cdf4d19cdfd1ed
+oid sha256:d58a98de8c35c88d685164db5fe4129857b5bcb473789b009556e5c1739a2c4c
 size 249750019

outputs/checkpoints/{checkpoint-22000 → checkpoint-28000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02cabdf326b00115bc75530d1d7bc3f9a82e57d038202548c3edee7d57c661ae
+oid sha256:be66fa7e148ce2b9d6c3645265528720ff474cf68ea20817c379b14fca3fc646
 size 499500278

outputs/checkpoints/checkpoint-28000/training_state.json

@@ -0,0 +1 @@
+{"step": 28001}

outputs/checkpoints/{checkpoint-23000 → checkpoint-29000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:559baf67a4fa12f4ddb4ea45aaf285d2e5d700ac5aa0e7ffb854af49e075634d
+oid sha256:ab9e1ec9fe5381c6cd01fb75c25867879a3e432dfaf4960054ef157b5e52d406
 size 249750019

outputs/checkpoints/{checkpoint-23000 → checkpoint-29000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bcd19d800843747a4fd81108e8654c0d431e94bacbd45321125f28f4eda9857
+oid sha256:54e623bbd0f1873163b786ac2b8889bdc078c9a03f02878216a3a20fb1d27569
 size 499500278

outputs/checkpoints/checkpoint-29000/training_state.json

@@ -0,0 +1 @@
+{"step": 29001}

outputs/events.out.tfevents.1627258355.tablespoon.3000110.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c07c9e738eed842b50ab4e82610a59b50a7f87c6b9aeeff615946beccf6da7a2
-size 3922999
+oid sha256:d4371c0c54c365271287a80d90ab3836df6db4026abad278a225bc389a870e17
+size 4296275

outputs/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ceb7903825a5802361e2abfa48cc22549619333ade477fa0502eca94fff7518
+oid sha256:ab9e1ec9fe5381c6cd01fb75c25867879a3e432dfaf4960054ef157b5e52d406
 size 249750019

outputs/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22861588524628232613a207d4ef751ae2280267840c912f9817827bd0747a14
+oid sha256:54e623bbd0f1873163b786ac2b8889bdc078c9a03f02878216a3a20fb1d27569
 size 499500278

outputs/training_state.json

@@ -1 +1 @@
-{"step": 26001}
+{"step": 29001}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b4d4ba780e464164915cfe3081ea36a32c7f31487d8cc141e99fe4a4e44171
+oid sha256:9d7187b7156584b95e4c067f8b7d04c6f66b165d9d934533bd83dc404dc48c81
 size 498858859

wandb/run-20210726_001233-17u6inbn/files/output.log

@@ -18053,6 +18053,1695 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (26000/50000 | Loss: 1.6362030506134033, Acc: 0.6691190600395203):  54%|██████████████            | 27000/50000 [10:45:19<10:31:50,  1.65s/it]
+Step... (26500 | Loss: 1.707963228225708, Learning Rate: 0.0002848485019057989)
+Step... (27000 | Loss: 1.7799105644226074, Learning Rate: 0.00027878789114765823)
+
+
+
+
+
+
+
+
+
+
+
+
+[12:53:43] - INFO - __main__ - Saving checkpoint at 27000 steps█████████████████████████████████████████████████████| 130/130 [00:21<00:00,  4.60it/s]
+All Flax model weights were used when initializing RobertaForMaskedLM.
+Some weights of RobertaForMaskedLM were not initialized from the Flax model and are newly initialized: ['lm_head.decoder.weight', 'roberta.embeddings.position_ids', 'lm_head.decoder.bias']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (27000/50000 | Loss: 1.6304749250411987, Acc: 0.670651376247406):  56%|███████████████▋            | 28000/50000 [11:10:01<8:36:13,  1.41s/it]
+Step... (27500 | Loss: 1.8015278577804565, Learning Rate: 0.00027272728038951755)
+Step... (27000/50000 | Loss: 1.6304749250411987, Acc: 0.670651376247406):  56%|███████████████▋            | 28000/50000 [11:10:04<8:36:13,  1.41s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+[13:18:28] - INFO - __main__ - Saving checkpoint at 28000 steps█████████████████████████████████████████████████████| 130/130 [00:21<00:00,  4.60it/s]
+All Flax model weights were used when initializing RobertaForMaskedLM.
+Some weights of RobertaForMaskedLM were not initialized from the Flax model and are newly initialized: ['lm_head.decoder.weight', 'roberta.embeddings.position_ids', 'lm_head.decoder.bias']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (28000/50000 | Loss: 1.627186894416809, Acc: 0.671392560005188):  58%|████████████████▊            | 29000/50000 [11:35:03<8:36:33,  1.48s/it]
+Step... (28500 | Loss: 1.738811731338501, Learning Rate: 0.00026060608797706664)
+Step... (29000 | Loss: 1.5798612833023071, Learning Rate: 0.00025454547721892595)
+
+
+
+
+
+
+
+
+
+
+
+
+[13:43:27] - INFO - __main__ - Saving checkpoint at 29000 steps█████████████████████████████████████████████████████| 130/130 [00:21<00:00,  4.60it/s]
+All Flax model weights were used when initializing RobertaForMaskedLM.
+Some weights of RobertaForMaskedLM were not initialized from the Flax model and are newly initialized: ['lm_head.decoder.weight', 'roberta.embeddings.position_ids', 'lm_head.decoder.bias']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 
 
 

wandb/run-20210726_001233-17u6inbn/files/wandb-summary.json

@@ -1 +1 @@
-{"global_step": 26500, "_timestamp": 1627303266.586647, "train_time": 1372972.75, "train_learning_rate": 0.0002848485019057989, "_step": 52841, "train_loss": 1.730733036994934, "eval_accuracy": 0.6691190600395203, "eval_loss": 1.6362030506134033}
+{"global_step": 29000, "_timestamp": 1627306978.644497, "train_time": 1608587.125, "train_learning_rate": 0.00025454547721892595, "_step": 57826, "train_loss": 1.61568021774292, "eval_accuracy": 0.671392560005188, "eval_loss": 1.627186894416809}

wandb/run-20210726_001233-17u6inbn/logs/debug-internal.log

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d92a70b4478861c91b2901d46e09c9d061fd6a02da2c0ff8ca5335c33cfde8
-size 20913336
+oid sha256:94c5b08086a46b44790fad9ed823f1a906f51889fca276b7086bf41d20a3a8ce
+size 22872190

wandb/run-20210726_001233-17u6inbn/run-17u6inbn.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1343d0ef55818f25efb5ed042e2cf55bb6c6f3440aba38c3b2f266129989e652
-size 10444427
+oid sha256:f83135fb6bd2b5e62d5771f3ca67b4afa426518c31fb39f682e6d326f6393e00
+size 11452146