Step... (16000/50000 | Loss: 1.6991859674453735, Acc: 0.659552812576294): 34%|█████████▍ | 16847/50000 [6:34:07<17:05:58, 1.86s/it]

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b18e55e7e0e173646f5693cf8c145dd0ec756f12776cb671210c598dafdb45
+oid sha256:e1c97577a048157d950d83272279ccc645289bcda0b3c1a4a714df7b8ef89ffa
 size 249750019

outputs/checkpoints/checkpoint-10000/training_state.json

@@ -1 +0,0 @@
-{"step": 10001}

outputs/checkpoints/checkpoint-11000/training_state.json

@@ -1 +0,0 @@
-{"step": 11001}

outputs/checkpoints/{checkpoint-10000 → checkpoint-15000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3471d2de3797fdad00939cfed3c119d97a102b86aab17beb39d8ebf37259b497
+oid sha256:4fae57c94dac9999e94e22d5044434007f1f445ea6c1ed7eba59fea02de5db30
 size 249750019

outputs/checkpoints/{checkpoint-10000 → checkpoint-15000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd556fdff51c3980e0d8c551f647a5d5ee9ec23fd987b892a16e1032647149a5
+oid sha256:a5e466347b293d39a54146314ea173df2523a33930d651d708c67ac132dd5088
 size 499500278

outputs/checkpoints/checkpoint-15000/training_state.json

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

outputs/checkpoints/{checkpoint-11000 → checkpoint-16000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165a80d10b493e4117c19ffeb7cbc1d340e88d14e329eb9be3ab1d32f050f973
+oid sha256:e1c97577a048157d950d83272279ccc645289bcda0b3c1a4a714df7b8ef89ffa
 size 249750019

outputs/checkpoints/{checkpoint-11000 → checkpoint-16000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17907ad9f925f7ff5210c836be64cf4f0b87dea575a17582ec3bce13447deb03
+oid sha256:33826e22d38c2cec4b568afa016f47cb58598d04aaa49474922cfec9ede1b96b
 size 499500278

outputs/checkpoints/checkpoint-16000/training_state.json

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

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4576e5515e6cf1926a9625e2db3778c06552a27d5a56f4b306bfdc6dec02245d
-size 2061819
+oid sha256:a36b6088bbbd059f09c03e927f62dc0250503de8e49e98bf4f6dc280b68fb259
+size 2430179

outputs/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b18e55e7e0e173646f5693cf8c145dd0ec756f12776cb671210c598dafdb45
+oid sha256:e1c97577a048157d950d83272279ccc645289bcda0b3c1a4a714df7b8ef89ffa
 size 249750019

outputs/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b657f7303349384c5ab4bd1d5226d2f8dbc1b641fc9355b1d5d4d2825ce382
+oid sha256:33826e22d38c2cec4b568afa016f47cb58598d04aaa49474922cfec9ede1b96b
 size 499500278

outputs/training_state.json

@@ -1 +1 @@
-{"step": 14001}
+{"step": 16001}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0290d7d4fc3d31d587881870f70299d2262836ee8bad199236e57b27fd504a0
+oid sha256:cf0278c9ca522b31b01aa1a3b0b84a53e34020e5991c1693d5fede18cc38aaca
 size 498858859

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

@@ -9463,6 +9463,1731 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (14000/50000 | Loss: 1.7139594554901123, Acc: 0.6574689745903015):  30%|████████                   | 15000/50000 [5:48:39<11:57:48,  1.23s/it]
+Evaluating ...:   2%|█▍                                                                                               | 2/130 [00:00<00:08, 14.51it/s]
+Step... (14500 | Loss: 1.901540994644165, Learning Rate: 0.0004303030436858535)
+
+
+
+
+
+
+
+
+
+
+
+
+[07:57:02] - INFO - __main__ - Saving checkpoint at 15000 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.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (15000/50000 | Loss: 1.709453821182251, Acc: 0.6586650609970093):  32%|████████▉                   | 16000/50000 [6:13:24<13:18:57,  1.41s/it]
+Evaluating ...:   0%|                                                                                                         | 0/130 [00:00<?, ?it/s]
+Step... (15500 | Loss: 1.768535852432251, Learning Rate: 0.0004181818221695721)
+
+
+
+
+
+
+
+
+
+
+
+
+[08:21:47] - INFO - __main__ - Saving checkpoint at 16000 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": 14000, "_timestamp": 1627284744.890835, "train_time": 473944.03125, "train_learning_rate": 0.0004363636835478246, "_step": 27916, "train_loss": 1.866248369216919, "eval_accuracy": 0.6557744741439819, "eval_loss": 1.725870966911316}
+{"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}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e6271a5aebdb0a82b320da3c45ba34bbe503e95144d5ba49806fc88d8a7cba3
-size 11092265
+oid sha256:f35d9a9ad3688b7e2e04122606d3ef735831cd7d3b8cb484a6915984c95ff551
+size 13058395

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd71f592091748dfcbe49a2bde4aab4c1c7e018a8eb1ee1e528775a51a6409d6
-size 5451547
+oid sha256:cb882315e6f15ca6a3b1cd312b6599d77c0978d9421a510e09007e241cde953c
+size 6438750