Step... (19000/50000 | Loss: 1.6823453903198242, Acc: 0.6625654101371765): 39%|██████████▍ | 19301/50000 [7:34:52<11:40:44, 1.37s/it]

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c97577a048157d950d83272279ccc645289bcda0b3c1a4a714df7b8ef89ffa
+oid sha256:2d0ae4178820ed8ec84d010dda13f1c110189fa19d49afd4d14283cf09774bee
 size 249750019

outputs/checkpoints/checkpoint-12000/training_state.json

@@ -1 +0,0 @@
-{"step": 12001}

outputs/checkpoints/checkpoint-13000/training_state.json

@@ -1 +0,0 @@
-{"step": 13001}

outputs/checkpoints/checkpoint-14000/training_state.json

@@ -1 +0,0 @@
-{"step": 14001}

outputs/checkpoints/{checkpoint-12000 → checkpoint-17000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4df1917f93cb5be75e1a67299b85e14508ce6d594537be9e03fa1ea0d5c451b
+oid sha256:6453368e8fd0e3c80ecb0b3dd860a84293d6cc3788ee6f32b9a7cb9a77fa001a
 size 249750019

outputs/checkpoints/{checkpoint-14000 → checkpoint-17000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b657f7303349384c5ab4bd1d5226d2f8dbc1b641fc9355b1d5d4d2825ce382
+oid sha256:77b05dc72072a294b97d7184e57ba9c0046b55665a7eb760f5ff414d319abe87
 size 499500278

outputs/checkpoints/checkpoint-17000/training_state.json

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

outputs/checkpoints/{checkpoint-14000 → checkpoint-18000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b18e55e7e0e173646f5693cf8c145dd0ec756f12776cb671210c598dafdb45
+oid sha256:e5a36a0b75be789eed389d6d8014081085f305abe5ca5007d4fd9bf9decf73d2
 size 249750019

outputs/checkpoints/{checkpoint-12000 → checkpoint-18000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5ef9d9909e0225cdfdb08ba23fd64c8a8a881103ca5b932bc2206768a7e920b
+oid sha256:472de67734e639ea41e43bd17705bf1c8e3ce22ee74865cab8ef338731f0cf9f
 size 499500278

outputs/checkpoints/checkpoint-18000/training_state.json

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

outputs/checkpoints/{checkpoint-13000 → checkpoint-19000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7781249560c15a41eb883214ab5f6613f40b42c1ae0886c52a020bbfa19f76fb
+oid sha256:2d0ae4178820ed8ec84d010dda13f1c110189fa19d49afd4d14283cf09774bee
 size 249750019

outputs/checkpoints/{checkpoint-13000 → checkpoint-19000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c37a1e738b919e689e3c653244d8a680235541f5d91c99fb41edd65340a91d
+oid sha256:6fd17bbca5658a6226151a6f85c1c6b4064b42b9ce32213f96be1f4b4993a48c
 size 499500278

outputs/checkpoints/checkpoint-19000/training_state.json

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

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a36b6088bbbd059f09c03e927f62dc0250503de8e49e98bf4f6dc280b68fb259
-size 2430179
+oid sha256:2d64128316db1be6b780146438299ca6d9e56a42d407935030bc80dd716161f5
+size 2803455

outputs/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c97577a048157d950d83272279ccc645289bcda0b3c1a4a714df7b8ef89ffa
+oid sha256:2d0ae4178820ed8ec84d010dda13f1c110189fa19d49afd4d14283cf09774bee
 size 249750019

outputs/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33826e22d38c2cec4b568afa016f47cb58598d04aaa49474922cfec9ede1b96b
+oid sha256:6fd17bbca5658a6226151a6f85c1c6b4064b42b9ce32213f96be1f4b4993a48c
 size 499500278

outputs/training_state.json

@@ -1 +1 @@
-{"step": 16001}
+{"step": 19001}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0278c9ca522b31b01aa1a3b0b84a53e34020e5991c1693d5fede18cc38aaca
+oid sha256:6e1c987c78ed3890e2c466fea8b433708a3e3c70c0d1d02e1b0cdab38c7ab56f
 size 498858859

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

@@ -11188,6 +11188,1728 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (16000/50000 | Loss: 1.6991859674453735, Acc: 0.659552812576294):  34%|█████████▌                  | 17000/50000 [6:37:47<11:32:41,  1.26s/it]
+Step... (16500 | Loss: 1.7835588455200195, Learning Rate: 0.0004060606297571212)
+Step... (17000 | Loss: 1.692732572555542, Learning Rate: 0.00039999998989515007)
+
+
+
+
+
+
+
+
+
+
+
+[08:46:11] - INFO - __main__ - Saving checkpoint at 17000 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... (17000/50000 | Loss: 1.6971577405929565, Acc: 0.6604305505752563):  36%|█████████▋                 | 18000/50000 [7:02:23<12:10:56,  1.37s/it]
+Step... (17500 | Loss: 1.9012951850891113, Learning Rate: 0.00039393940824083984)
+Step... (17000/50000 | Loss: 1.6971577405929565, Acc: 0.6604305505752563):  36%|█████████▋                 | 18000/50000 [7:02:27<12:10:56,  1.37s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+[09:10:50] - INFO - __main__ - Saving checkpoint at 18000 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... (18000/50000 | Loss: 1.6918002367019653, Acc: 0.6613297462463379):  38%|██████████▎                | 19000/50000 [7:26:48<11:49:37,  1.37s/it]
+Evaluating ...:   3%|██▉                                                                                              | 4/130 [00:00<00:08, 15.60it/s]
+Step... (18500 | Loss: 1.7828737497329712, Learning Rate: 0.00038181818672455847)
+
+
+
+
+
+
+
+
+
+
+
+
+[09:35:12] - INFO - __main__ - Saving checkpoint at 19000 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": 16500, "_timestamp": 1627288441.057746, "train_time": 616863.8125, "train_learning_rate": 0.0004060606297571212, "_step": 32901, "train_loss": 1.7374286651611328, "eval_accuracy": 0.659552812576294, "eval_loss": 1.6991859674453735}
+{"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}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f35d9a9ad3688b7e2e04122606d3ef735831cd7d3b8cb484a6915984c95ff551
-size 13058395
+oid sha256:5735b88f7fe8d8de75852323f4e472b4ff32a198dfcd9c4aa9b6b77935cfe7a3
+size 15022911

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb882315e6f15ca6a3b1cd312b6599d77c0978d9421a510e09007e241cde953c
-size 6438750
+oid sha256:65ba593b01d33851355b3d3d6b7ed6ce7fd160ce6e024522afb8bfc04d32aa8c
+size 7433980