Upload checkpoint at step 2000

checkpoint-2000/config.json

@@ -0,0 +1,9 @@
+{
+  "d_model": 384,
+  "n_heads": 8,
+  "n_layers": 6,
+  "d_ff": 1536,
+  "max_seq_len": 512,
+  "vocab_size": 49152,
+  "dropout": 0.1
+}

checkpoint-2000/optimizer_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c429b6a8dd4e61fc19ef0b028f5996251ed59975f287d005c315a9a43fdae18a
+size 42475006

checkpoint-2000/optimizer_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c984f40ca164fdb8b5f87b928b9be063b07f37826ee649347dcaa83a719528b
+size 151047056

checkpoint-2000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea23d0e4dad8188e835456e8f052bf34c7d28b6e968765aea9833abc9c343182
+size 118002208

checkpoint-2000/scheduler_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcabad8d2df95b0633d682b66b7ca4a612e59a4a73b250344d50226d7c50429
+size 1008

checkpoint-2000/scheduler_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b10914e47e83d67685cbad8fe95817c83629b2fd218e21c6d3d2d565af5cbd
+size 1008

checkpoint-2000/training_args.json

@@ -0,0 +1,10 @@
+{
+  "step": 2000,
+  "metrics": {
+    "train_loss": 3.8291685581207275,
+    "train_accuracy": 0.3209635615348816,
+    "train_perplexity": 46.02425582786427,
+    "learning_rate": 0.006666666666666666
+  },
+  "total_steps": 15000
+}