Saving weights and logs of step 225000

checkpoint_225000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a241834d14e8ce32140cdf9151c8fdcaa7b79908747ded93e38f41d4ff7959
+size 1530270447

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": ".",
   "architectures": [
     "BigBirdForMaskedLM"
   ],
@@ -24,7 +23,6 @@
   "position_embedding_type": "absolute",
   "rescale_embeddings": false,
   "sep_token_id": 66,
-  "torch_dtype": "float32",
   "transformers_version": "4.9.0.dev0",
   "type_vocab_size": 2,
   "use_bias": true,

events.out.tfevents.1626397185.t1v-n-f5c06ea1-w-0.760449.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75d98147922b932dd6939ba021778b95c1ec799a8036630bffff4b749c5f07e9
-size 10830402
+oid sha256:55333c246f74b2c84620675b6048997ae79474af6bfdd07693a18bed98c164cc
+size 11281744

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baac2faaefa281dd0212650164a6b61ed52f9de5369418f02fe29cd52b3f08cd
+oid sha256:e8f5ca7b60c5e4b03edfdde3f172ec2572f02f5753f13fe7a658c57c2fc9bae5
 size 510090043

wandb/run-20210716_005946-3bte92ft/files/output.log

@@ -8246,3 +8246,365 @@ Training...: 71999it [8:23:42,  2.67it/s]█████████████
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...: 72049it [8:24:53,  2.68it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72099it [8:25:13,  2.72it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72149it [8:25:33,  2.67it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72199it [8:25:53,  2.71it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72249it [8:26:13,  2.68it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72299it [8:26:33,  2.69it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 72350it [8:27:06,  4.07s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 72400it [8:27:26,  4.01s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72449it [8:27:33,  2.72it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72499it [8:27:53,  2.68it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 72550it [8:28:27,  4.01s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 72600it [8:28:47,  4.07s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 72652it [8:29:07,  2.24s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72699it [8:29:13,  2.76it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72749it [8:29:33,  2.69it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 72800it [8:30:07,  4.01s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 72850it [8:30:27,  4.01s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 72902it [8:30:47,  2.24s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72949it [8:30:54,  2.71it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 72999it [8:31:14,  2.68it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73050it [8:31:47,  4.01s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73102it [8:32:07,  2.25s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73152it [8:32:27,  2.25s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 73199it [8:32:34,  2.76it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 73249it [8:32:54,  2.69it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 73299it [8:33:14,  2.70it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73350it [8:33:47,  4.01s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73400it [8:34:07,  4.01s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73452it [8:34:27,  2.22s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73502it [8:34:47,  2.24s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73556it [8:35:08,  1.09it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73606it [8:35:28,  1.09it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73652it [8:35:48,  2.24s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73702it [8:36:08,  2.25s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73754it [8:36:28,  1.40s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73804it [8:36:48,  1.40s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73856it [8:37:08,  1.09it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73908it [8:37:28,  1.59it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 73952it [8:37:48,  2.24s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74002it [8:38:08,  2.25s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74052it [8:38:28,  2.24s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74104it [8:38:48,  1.40s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74154it [8:39:08,  1.39s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74204it [8:39:28,  1.40s/it]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 74249it [8:39:35,  2.69it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+
+Training...: 74308it [8:40:09,  1.59it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74358it [8:40:29,  1.58it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74410it [8:40:49,  2.25it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74460it [8:41:09,  2.24it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74506it [8:41:29,  1.04it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74562it [8:41:49,  3.08it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+Training...: 74599it [8:41:55,  2.68it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74649it [8:42:15,  2.70it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+
+Training...: 74708it [8:42:49,  1.58it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 74749it [8:42:55,  2.69it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+
+Training...: 74808it [8:43:29,  1.58it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 74849it [8:43:36,  2.68it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74899it [8:43:56,  2.73it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74949it [8:44:16,  2.68it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 74999it [8:44:36,  2.69it/s]████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+tcmalloc: large alloc 2715181056 bytes == 0x41e66a000 @  0x7f779c64f680 0x7f779c66fbdd 0x7f7782c0920d 0x7f7782c17340 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c16e87 0x7f7782c12bd3 0x7f7782c131fe 0x504d56 0x56acb6 0x568d9a 0x5f5b33 0x56bc9b 0x5f5956 0x56aadf 0x5f5956 0x56fb87 0x568d9a 0x5f5b33 0x56bc9b 0x568d9a
+[09:50:33] - INFO - absl - Saved checkpoint at checkpoint_225000
+[09:50:34] - INFO - huggingface_hub.repository - git version 2.25.1
+git-lfs/2.9.2 (GitHub; linux amd64; go 1.13.5)

wandb/run-20210716_005946-3bte92ft/files/wandb-summary.json

@@ -1 +1 @@
-{"training_step": 222000, "learning_rate": 2.393302202108316e-05, "train_loss": 2.2153563499450684, "_runtime": 30573, "_timestamp": 1626427759, "_step": 1450, "eval_step": 216000, "eval_accuracy": 0.6142588257789612, "eval_loss": 1.9934282302856445}
+{"training_step": 225000, "learning_rate": 2.3847169359214604e-05, "train_loss": 2.061807155609131, "_runtime": 31840, "_timestamp": 1626429026, "_step": 1511, "eval_step": 222000, "eval_accuracy": 0.6153644919395447, "eval_loss": 1.9865816831588745}