Step... (24000/50000 | Loss: 1.6508632898330688, Acc: 0.6671841740608215): 48%|█████████████ | 24215/50000 [9:36:14<10:45:10, 1.50s/it]

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba1daf7b1dad5bf7c386bc7b53d5537a8f26b3cfee5b0fc009a750ad077eab0
+oid sha256:b22d22612dd38ad92ffdda4b0cf432e201d6c90dd5386d04a2cdf4d19cdfd1ed
 size 249750019

outputs/checkpoints/checkpoint-17000/training_state.json

@@ -1 +0,0 @@
-{"step": 17001}

outputs/checkpoints/checkpoint-18000/training_state.json

@@ -1 +0,0 @@
-{"step": 18001}

outputs/checkpoints/checkpoint-19000/training_state.json

@@ -1 +0,0 @@
-{"step": 19001}

outputs/checkpoints/{checkpoint-17000 → checkpoint-22000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6453368e8fd0e3c80ecb0b3dd860a84293d6cc3788ee6f32b9a7cb9a77fa001a
+oid sha256:ce6736afa967315a5ccac23ff15ab3d3f2f90881f2858be1c86b98b60e0fa764
 size 249750019

outputs/checkpoints/{checkpoint-19000 → checkpoint-22000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd17bbca5658a6226151a6f85c1c6b4064b42b9ce32213f96be1f4b4993a48c
+oid sha256:02cabdf326b00115bc75530d1d7bc3f9a82e57d038202548c3edee7d57c661ae
 size 499500278

outputs/checkpoints/checkpoint-22000/training_state.json

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

outputs/checkpoints/{checkpoint-19000 → checkpoint-23000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0ae4178820ed8ec84d010dda13f1c110189fa19d49afd4d14283cf09774bee
+oid sha256:559baf67a4fa12f4ddb4ea45aaf285d2e5d700ac5aa0e7ffb854af49e075634d
 size 249750019

outputs/checkpoints/{checkpoint-17000 → checkpoint-23000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b05dc72072a294b97d7184e57ba9c0046b55665a7eb760f5ff414d319abe87
+oid sha256:6bcd19d800843747a4fd81108e8654c0d431e94bacbd45321125f28f4eda9857
 size 499500278

outputs/checkpoints/checkpoint-23000/training_state.json

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

outputs/checkpoints/{checkpoint-18000 → checkpoint-24000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a36a0b75be789eed389d6d8014081085f305abe5ca5007d4fd9bf9decf73d2
+oid sha256:b22d22612dd38ad92ffdda4b0cf432e201d6c90dd5386d04a2cdf4d19cdfd1ed
 size 249750019

outputs/checkpoints/{checkpoint-18000 → checkpoint-24000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472de67734e639ea41e43bd17705bf1c8e3ce22ee74865cab8ef338731f0cf9f
+oid sha256:bcac7bac463ddd6530546523b0141118f658d528e0d7ec682da2661fe2a0f7df
 size 499500278

outputs/checkpoints/checkpoint-24000/training_state.json

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

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3cc46840b5336c96adfc10b39ed6dd9d36d3759fb574ca64e28191207730bfb
-size 3176589
+oid sha256:187bfd40e3dd6f12ab8cd6df2018b0fef55ab1ab89a973e1cc1b5427620d8135
+size 3549865

outputs/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba1daf7b1dad5bf7c386bc7b53d5537a8f26b3cfee5b0fc009a750ad077eab0
+oid sha256:b22d22612dd38ad92ffdda4b0cf432e201d6c90dd5386d04a2cdf4d19cdfd1ed
 size 249750019

outputs/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd862c6893d8672a836d674b5ef9d3eaab357c385ad5b064b7202eccc581ff05
+oid sha256:bcac7bac463ddd6530546523b0141118f658d528e0d7ec682da2661fe2a0f7df
 size 499500278

outputs/training_state.json

@@ -1 +1 @@
-{"step": 21001}
+{"step": 24001}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ddc0bfdddad2ca72308b9edd1fc42a1a815c78826b2a838c898083e3d5041e
+oid sha256:d50ca6bc265a7b18cee3972966e847d1c5891e5fec62a6e912bbbe885e2e82da
 size 498858859

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

@@ -14630,6 +14630,1723 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (21000/50000 | Loss: 1.669716238975525, Acc: 0.6647850275039673):  44%|████████████▎               | 22000/50000 [8:40:53<13:14:50,  1.70s/it]
+Step... (21500 | Loss: 1.764472484588623, Learning Rate: 0.00034545455127954483)
+Step... (21000/50000 | Loss: 1.669716238975525, Acc: 0.6647850275039673):  44%|████████████▎               | 22000/50000 [8:40:55<13:14:50,  1.70s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+[10:49:19] - INFO - __main__ - Saving checkpoint at 22000 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... (22000/50000 | Loss: 1.6613430976867676, Acc: 0.6655245423316956):  46%|████████████▍              | 23000/50000 [9:05:24<10:18:31,  1.37s/it]
+Evaluating ...:   3%|██▉                                                                                              | 4/130 [00:00<00:08, 14.65it/s]
+Step... (22500 | Loss: 1.9999163150787354, Learning Rate: 0.0003333333588670939)
+
+
+
+
+
+
+
+
+
+
+
+
+[11:13:47] - INFO - __main__ - Saving checkpoint at 23000 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... (23000/50000 | Loss: 1.6572293043136597, Acc: 0.6663545966148376):  48%|████████████▉              | 24000/50000 [9:30:12<11:34:04,  1.60s/it]
+Step... (23500 | Loss: 1.7666906118392944, Learning Rate: 0.00032121213735081255)
+Step... (24000 | Loss: 1.657638430595398, Learning Rate: 0.00031515152659267187)
+
+
+
+
+
+
+
+
+
+
+
+[11:38:36] - INFO - __main__ - Saving checkpoint at 24000 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": 21500, "_timestamp": 1627295817.37153, "train_time": 957886.375, "train_learning_rate": 0.00034545455127954483, "_step": 42871, "train_loss": 1.6961593627929688, "eval_accuracy": 0.6647850275039673, "eval_loss": 1.669716238975525}
+{"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}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efeb439af32e6eb761cd222b4de30fb8c299ae62524e09ab6574d273aa9ccb62
-size 16987693
+oid sha256:e82989e4b19c6c0abd610b0181219b8926bc8d5e7d84c1812150b24b6b6a4d6e
+size 18951993

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0563d981cabfb744be4dba9411f8759967f5c165cc116bd1736d9615afb67aa9
-size 8433368
+oid sha256:0c32d64082b6ac9a729c131c88cc2d56813251ca3d7cc69eb10cf688204a79ff
+size 9437234