Step... (21000/50000 | Loss: 1.669716238975525, Acc: 0.6647850275039673): 44%|████████████▏ | 21775/50000 [8:35:31<11:59:11, 1.53s/it]

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0ae4178820ed8ec84d010dda13f1c110189fa19d49afd4d14283cf09774bee
+oid sha256:7ba1daf7b1dad5bf7c386bc7b53d5537a8f26b3cfee5b0fc009a750ad077eab0
 size 249750019

outputs/checkpoints/checkpoint-15000/training_state.json

@@ -1 +0,0 @@
-{"step": 15001}

outputs/checkpoints/checkpoint-16000/training_state.json

@@ -1 +0,0 @@
-{"step": 16001}

outputs/checkpoints/{checkpoint-15000 → checkpoint-20000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fae57c94dac9999e94e22d5044434007f1f445ea6c1ed7eba59fea02de5db30
+oid sha256:a0bf6ec68f574b4af0a99a55d1d45aa7b0e1e57289109e4d7f5c9e5d83816424
 size 249750019

outputs/checkpoints/{checkpoint-15000 → checkpoint-20000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e466347b293d39a54146314ea173df2523a33930d651d708c67ac132dd5088
+oid sha256:cab56f5cbba1f1be7c19b45ad56f5c58ced35d8e3f342687638a6a00d3e1d292
 size 499500278

outputs/checkpoints/checkpoint-20000/training_state.json

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

outputs/checkpoints/{checkpoint-16000 → checkpoint-21000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c97577a048157d950d83272279ccc645289bcda0b3c1a4a714df7b8ef89ffa
+oid sha256:7ba1daf7b1dad5bf7c386bc7b53d5537a8f26b3cfee5b0fc009a750ad077eab0
 size 249750019

outputs/checkpoints/{checkpoint-16000 → checkpoint-21000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33826e22d38c2cec4b568afa016f47cb58598d04aaa49474922cfec9ede1b96b
+oid sha256:cd862c6893d8672a836d674b5ef9d3eaab357c385ad5b064b7202eccc581ff05
 size 499500278

outputs/checkpoints/checkpoint-21000/training_state.json

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

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d64128316db1be6b780146438299ca6d9e56a42d407935030bc80dd716161f5
-size 2803455
+oid sha256:c3cc46840b5336c96adfc10b39ed6dd9d36d3759fb574ca64e28191207730bfb
+size 3176589

outputs/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0ae4178820ed8ec84d010dda13f1c110189fa19d49afd4d14283cf09774bee
+oid sha256:7ba1daf7b1dad5bf7c386bc7b53d5537a8f26b3cfee5b0fc009a750ad077eab0
 size 249750019

outputs/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd17bbca5658a6226151a6f85c1c6b4064b42b9ce32213f96be1f4b4993a48c
+oid sha256:cd862c6893d8672a836d674b5ef9d3eaab357c385ad5b064b7202eccc581ff05
 size 499500278

outputs/training_state.json

@@ -1 +1 @@
-{"step": 19001}
+{"step": 21001}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e1c987c78ed3890e2c466fea8b433708a3e3c70c0d1d02e1b0cdab38c7ab56f
+oid sha256:56ddc0bfdddad2ca72308b9edd1fc42a1a815c78826b2a838c898083e3d5041e
 size 498858859

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

@@ -12910,6 +12910,1726 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (19000/50000 | Loss: 1.6823453903198242, Acc: 0.6625654101371765):  40%|██████████▊                | 20000/50000 [7:51:27<11:12:26,  1.34s/it]
+Step... (19500 | Loss: 1.7442021369934082, Learning Rate: 0.0003696969652082771)
+Step... (20000 | Loss: 1.6871428489685059, Learning Rate: 0.0003636363835539669)
+
+
+
+
+
+
+
+
+
+
+
+[09:59:50] - INFO - __main__ - Saving checkpoint at 20000 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... (20000/50000 | Loss: 1.6746032238006592, Acc: 0.6636187434196472):  42%|███████████▎               | 21000/50000 [8:16:08<11:06:45,  1.38s/it]
+Step... (20500 | Loss: 1.8593541383743286, Learning Rate: 0.0003575757727958262)
+Step... (20000/50000 | Loss: 1.6746032238006592, Acc: 0.6636187434196472):  42%|███████████▎               | 21000/50000 [8:16:10<11:06:45,  1.38s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+[10:24:33] - INFO - __main__ - Saving checkpoint at 21000 steps█████████████████████████████████████████████████████| 130/130 [00:21<00:00,  4.59it/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": 19000, "_timestamp": 1627292083.608254, "train_time": 778139.25, "train_learning_rate": 0.00037575760507024825, "_step": 37886, "train_loss": 1.8002192974090576, "eval_accuracy": 0.6613297462463379, "eval_loss": 1.6918002367019653}
+{"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}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5735b88f7fe8d8de75852323f4e472b4ff32a198dfcd9c4aa9b6b77935cfe7a3
-size 15022911
+oid sha256:efeb439af32e6eb761cd222b4de30fb8c299ae62524e09ab6574d273aa9ccb62
+size 16987693

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ba593b01d33851355b3d3d6b7ed6ce7fd160ce6e024522afb8bfc04d32aa8c
-size 7433980
+oid sha256:0563d981cabfb744be4dba9411f8759967f5c165cc116bd1736d9615afb67aa9
+size 8433368