Step... (26000/50000 | Loss: 1.6362030506134033, Acc: 0.6691190600395203): 53%|█████████████▊ | 26656/50000 [10:36:57<11:06:38, 1.71s/it]

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b22d22612dd38ad92ffdda4b0cf432e201d6c90dd5386d04a2cdf4d19cdfd1ed
+oid sha256:5ceb7903825a5802361e2abfa48cc22549619333ade477fa0502eca94fff7518
 size 249750019

outputs/checkpoints/checkpoint-20000/training_state.json

@@ -1 +0,0 @@
-{"step": 20001}

outputs/checkpoints/checkpoint-21000/training_state.json

@@ -1 +0,0 @@
-{"step": 21001}

outputs/checkpoints/{checkpoint-20000 → checkpoint-25000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0bf6ec68f574b4af0a99a55d1d45aa7b0e1e57289109e4d7f5c9e5d83816424
+oid sha256:3f01f7bd9dc37008fe586042d0858630facb5e28a5aabe227d941a460b9dac62
 size 249750019

outputs/checkpoints/{checkpoint-20000 → checkpoint-25000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab56f5cbba1f1be7c19b45ad56f5c58ced35d8e3f342687638a6a00d3e1d292
+oid sha256:fd4e308d24cbf75134aac7314daf08bd6739fe89d8e0c1dc9de2428e0a4a588a
 size 499500278

outputs/checkpoints/checkpoint-25000/training_state.json

@@ -0,0 +1 @@
+{"step": 25001}

outputs/checkpoints/{checkpoint-21000 → checkpoint-26000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba1daf7b1dad5bf7c386bc7b53d5537a8f26b3cfee5b0fc009a750ad077eab0
+oid sha256:5ceb7903825a5802361e2abfa48cc22549619333ade477fa0502eca94fff7518
 size 249750019

outputs/checkpoints/{checkpoint-21000 → checkpoint-26000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd862c6893d8672a836d674b5ef9d3eaab357c385ad5b064b7202eccc581ff05
+oid sha256:22861588524628232613a207d4ef751ae2280267840c912f9817827bd0747a14
 size 499500278

outputs/checkpoints/checkpoint-26000/training_state.json

@@ -0,0 +1 @@
+{"step": 26001}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:187bfd40e3dd6f12ab8cd6df2018b0fef55ab1ab89a973e1cc1b5427620d8135
-size 3549865
+oid sha256:c07c9e738eed842b50ab4e82610a59b50a7f87c6b9aeeff615946beccf6da7a2
+size 3922999

outputs/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b22d22612dd38ad92ffdda4b0cf432e201d6c90dd5386d04a2cdf4d19cdfd1ed
+oid sha256:5ceb7903825a5802361e2abfa48cc22549619333ade477fa0502eca94fff7518
 size 249750019

outputs/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcac7bac463ddd6530546523b0141118f658d528e0d7ec682da2661fe2a0f7df
+oid sha256:22861588524628232613a207d4ef751ae2280267840c912f9817827bd0747a14
 size 499500278

outputs/training_state.json

@@ -1 +1 @@
-{"step": 24001}
+{"step": 26001}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d50ca6bc265a7b18cee3972966e847d1c5891e5fec62a6e912bbbe885e2e82da
+oid sha256:17b4d4ba780e464164915cfe3081ea36a32c7f31487d8cc141e99fe4a4e44171
 size 498858859

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

@@ -16347,6 +16347,1710 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (24000/50000 | Loss: 1.6508632898330688, Acc: 0.6671841740608215):  50%|█████████████▌             | 25000/50000 [9:54:56<11:05:00,  1.60s/it]
+Evaluating ...:   5%|████▍                                                                                            | 6/130 [00:00<00:07, 15.90it/s]
+Step... (24500 | Loss: 1.7519614696502686, Learning Rate: 0.0003090909158345312)
+
+
+
+
+
+
+
+
+
+
+
+
+[12:03:19] - INFO - __main__ - Saving checkpoint at 25000 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... (25000/50000 | Loss: 1.6436606645584106, Acc: 0.668701171875):  52%|████████████████               | 26000/50000 [10:20:04<8:52:22,  1.33s/it]
+Step... (25500 | Loss: 1.6520822048187256, Learning Rate: 0.0002969697234220803)
+Step... (26000 | Loss: 1.7167686223983765, Learning Rate: 0.0002909091126639396)
+
+
+
+
+
+
+
+
+
+
+
+[12:28:28] - INFO - __main__ - Saving checkpoint at 26000 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": 24000, "_timestamp": 1627299487.452405, "train_time": 1156106.125, "train_learning_rate": 0.00031515152659267187, "_step": 47856, "train_loss": 1.7166345119476318, "eval_accuracy": 0.6663545966148376, "eval_loss": 1.6572293043136597}
+{"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}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82989e4b19c6c0abd610b0181219b8926bc8d5e7d84c1812150b24b6b6a4d6e
-size 18951993
+oid sha256:45d92a70b4478861c91b2901d46e09c9d061fd6a02da2c0ff8ca5335c33cfde8
+size 20913336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c32d64082b6ac9a729c131c88cc2d56813251ca3d7cc69eb10cf688204a79ff
-size 9437234
+oid sha256:1343d0ef55818f25efb5ed042e2cf55bb6c6f3440aba38c3b2f266129989e652
+size 10444427