Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/biogpt",
+  "activation_dropout": 0.0,
+  "architectures": [
+    "BioGptForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 1024,
+  "model_type": "biogpt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 42384
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b335b24501aaf963723fc4477764767b4192b6e7272d67a681a9928739fcba0
+size 1387181917

runs/Apr29_18-41-18_python-gpu-simple/1682793714.11331/events.out.tfevents.1682793714.python-gpu-simple

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424f315d867e78ba61b5335acb826d48a7646ff43fdb67a6cd3d00bdd447d3e9
+size 5596

runs/Apr29_18-41-18_python-gpu-simple/events.out.tfevents.1682793714.python-gpu-simple

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dfe72e30b9c98f593481d9a71d4db1f28e87c6059baba576693a6085a67d341
+size 3956

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e08b029e34751d2ebd0684ad010618f8a28f9a818310b915c8db3b02f22ce3
+size 3643