Training in progress, step 100, checkpoint

checkpoint-100/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97aadced9c8bae535b719e6a5bcd67870ed967d312636d63b9fc328683399735
+oid sha256:4c9a5c8eae560953cb2afb2b3bf5d1330d089af788edaa1bf1d3f77b218837bc
 size 324662984

checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3ffb54c2862b62f7911b7e3fefbfb93500faa82b32d51f6592fa06f5b20ddd
+oid sha256:36ce7ab48fa86ef42491eaad3583773d2b60353997a5e7b6fb4ffc1414828749
 size 6520

checkpoint-75/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 1024,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

checkpoint-75/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b257dcf6c7ab062da763314d5ac648ac7e0a2c99289dc786c8b399a83efd0d8e
+size 324662984

checkpoint-75/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3ffb54c2862b62f7911b7e3fefbfb93500faa82b32d51f6592fa06f5b20ddd
+oid sha256:36ce7ab48fa86ef42491eaad3583773d2b60353997a5e7b6fb4ffc1414828749
 size 6520