Outer Step 69. Inner Step 0. Batch Size 0

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "distributed/optimized-gpt2-1b-vtestnet-v2",
+  "activation_function": "gelu_new",
+  "all_reduce_scores": {
+    "0": "NON_PARTICIPATING",
+    "1": "NON_PARTICIPATING",
+    "2": "SUCCESS",
+    "3": "NON_PARTICIPATING",
+    "4": "NON_PARTICIPATING",
+    "5": "NON_PARTICIPATING",
+    "6": "NON_PARTICIPATING",
+    "7": "NON_PARTICIPATING",
+    "8": "NON_PARTICIPATING",
+    "9": "NON_PARTICIPATING"
+  },
+  "architectures": [
+    "GPTOptim"
+  ],
+  "attn_pdrop": 0.1,
+  "auto_map": {
+    "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
+    "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
+  },
+  "block_list": [],
+  "block_size": 1024,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "inner_step": 0,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt_optimized",
+  "n_embd": 1280,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e943a767df4ce292b2328b8896a16a7e4153c9c65ce38acb48ff67a894683328
+size 4040701744