Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "albert-xxlarge-v2",
+  "architectures": [
+    "AlbertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-12,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 64,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23266d12c16bbb236b4806edbb43c8ce80131ff583746b5b0dd5c26e322e486c
+size 825489230

runs/Jun19_12-49-28_0bc610c6d45b/1655643346.2834032/events.out.tfevents.1655643346.0bc610c6d45b.78.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2057f0ae20b8af4650f714925fa752cdc8d25048a30fdf267e042b1130706afe
+size 5372

runs/Jun19_12-49-28_0bc610c6d45b/events.out.tfevents.1655643346.0bc610c6d45b.78.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421a4d665250e21c74ba280486ab545b40fcff630d83a4d99c6e51932a5f24b6
+size 4053

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7aeb365ccc4f1f8f8b10575f2b68a3f0a314c8329c7f94d90774f7864c74bd
+size 3311