Upload folder using huggingface_hub

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/share/home/dwu/local_models/Llama-2-7b-chat-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

latest

@@ -0,0 +1 @@
+global_step1576

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3158a908c9897aeed7d5b4ed61642421a29d4d23d1edec7b27029af252367f1a
+size 4938985248

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378c8d1f8e2da10ba66505da851699dc910e52d8086e146761cef5591ee56f86
+size 4947390768

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e326499c3378fc67f063c1f3555227a6c572688c05b4f1cc4acfeabb29435a
+size 3590488736

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
+size 15024

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1132 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1576,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006345177664974619,
+      "grad_norm": 1.6225066184997559,
+      "learning_rate": 9.999889621822132e-06,
+      "loss": 0.9998,
+      "step": 10
+    },
+    {
+      "epoch": 0.012690355329949238,
+      "grad_norm": 1.652418613433838,
+      "learning_rate": 9.999558492161865e-06,
+      "loss": 0.9514,
+      "step": 20
+    },
+    {
+      "epoch": 0.01903553299492386,
+      "grad_norm": 1.589950680732727,
+      "learning_rate": 9.999006625638994e-06,
+      "loss": 0.9091,
+      "step": 30
+    },
+    {
+      "epoch": 0.025380710659898477,
+      "grad_norm": 1.3906126022338867,
+      "learning_rate": 9.998234046619128e-06,
+      "loss": 0.9221,
+      "step": 40
+    },
+    {
+      "epoch": 0.031725888324873094,
+      "grad_norm": 1.4328875541687012,
+      "learning_rate": 9.997240789212612e-06,
+      "loss": 0.9083,
+      "step": 50
+    },
+    {
+      "epoch": 0.03807106598984772,
+      "grad_norm": 1.682231068611145,
+      "learning_rate": 9.996026897273024e-06,
+      "loss": 0.884,
+      "step": 60
+    },
+    {
+      "epoch": 0.044416243654822336,
+      "grad_norm": 1.554661750793457,
+      "learning_rate": 9.994592424395235e-06,
+      "loss": 0.8974,
+      "step": 70
+    },
+    {
+      "epoch": 0.050761421319796954,
+      "grad_norm": 1.4692213535308838,
+      "learning_rate": 9.992937433913048e-06,
+      "loss": 0.9087,
+      "step": 80
+    },
+    {
+      "epoch": 0.05710659898477157,
+      "grad_norm": 1.7308210134506226,
+      "learning_rate": 9.991061998896395e-06,
+      "loss": 0.908,
+      "step": 90
+    },
+    {
+      "epoch": 0.06345177664974619,
+      "grad_norm": 1.3942962884902954,
+      "learning_rate": 9.988966202148115e-06,
+      "loss": 0.8783,
+      "step": 100
+    },
+    {
+      "epoch": 0.06979695431472081,
+      "grad_norm": 1.4834920167922974,
+      "learning_rate": 9.9866501362003e-06,
+      "loss": 0.8663,
+      "step": 110
+    },
+    {
+      "epoch": 0.07614213197969544,
+      "grad_norm": 1.572066068649292,
+      "learning_rate": 9.984113903310206e-06,
+      "loss": 0.8876,
+      "step": 120
+    },
+    {
+      "epoch": 0.08248730964467005,
+      "grad_norm": 1.412290096282959,
+      "learning_rate": 9.981357615455738e-06,
+      "loss": 0.8744,
+      "step": 130
+    },
+    {
+      "epoch": 0.08883248730964467,
+      "grad_norm": 1.4933444261550903,
+      "learning_rate": 9.978381394330509e-06,
+      "loss": 0.8877,
+      "step": 140
+    },
+    {
+      "epoch": 0.09517766497461928,
+      "grad_norm": 1.44158935546875,
+      "learning_rate": 9.975185371338464e-06,
+      "loss": 0.8683,
+      "step": 150
+    },
+    {
+      "epoch": 0.10152284263959391,
+      "grad_norm": 1.4896454811096191,
+      "learning_rate": 9.971769687588082e-06,
+      "loss": 0.8716,
+      "step": 160
+    },
+    {
+      "epoch": 0.10786802030456853,
+      "grad_norm": 1.7083044052124023,
+      "learning_rate": 9.968134493886143e-06,
+      "loss": 0.8689,
+      "step": 170
+    },
+    {
+      "epoch": 0.11421319796954314,
+      "grad_norm": 1.6805241107940674,
+      "learning_rate": 9.964279950731066e-06,
+      "loss": 0.8631,
+      "step": 180
+    },
+    {
+      "epoch": 0.12055837563451777,
+      "grad_norm": 1.469270944595337,
+      "learning_rate": 9.960206228305835e-06,
+      "loss": 0.8605,
+      "step": 190
+    },
+    {
+      "epoch": 0.12690355329949238,
+      "grad_norm": 1.587968349456787,
+      "learning_rate": 9.955913506470472e-06,
+      "loss": 0.8744,
+      "step": 200
+    },
+    {
+      "epoch": 0.13324873096446702,
+      "grad_norm": 1.3910565376281738,
+      "learning_rate": 9.951401974754103e-06,
+      "loss": 0.864,
+      "step": 210
+    },
+    {
+      "epoch": 0.13959390862944163,
+      "grad_norm": 1.3854566812515259,
+      "learning_rate": 9.946671832346588e-06,
+      "loss": 0.8605,
+      "step": 220
+    },
+    {
+      "epoch": 0.14593908629441624,
+      "grad_norm": 1.3671081066131592,
+      "learning_rate": 9.941723288089727e-06,
+      "loss": 0.8492,
+      "step": 230
+    },
+    {
+      "epoch": 0.15228426395939088,
+      "grad_norm": 1.5190922021865845,
+      "learning_rate": 9.936556560468037e-06,
+      "loss": 0.8479,
+      "step": 240
+    },
+    {
+      "epoch": 0.15862944162436549,
+      "grad_norm": 1.4076085090637207,
+      "learning_rate": 9.931171877599113e-06,
+      "loss": 0.8539,
+      "step": 250
+    },
+    {
+      "epoch": 0.1649746192893401,
+      "grad_norm": 1.3882677555084229,
+      "learning_rate": 9.925569477223549e-06,
+      "loss": 0.842,
+      "step": 260
+    },
+    {
+      "epoch": 0.1713197969543147,
+      "grad_norm": 1.4815824031829834,
+      "learning_rate": 9.91974960669444e-06,
+      "loss": 0.8368,
+      "step": 270
+    },
+    {
+      "epoch": 0.17766497461928935,
+      "grad_norm": 1.468481183052063,
+      "learning_rate": 9.91371252296647e-06,
+      "loss": 0.8573,
+      "step": 280
+    },
+    {
+      "epoch": 0.18401015228426396,
+      "grad_norm": 1.315491795539856,
+      "learning_rate": 9.907458492584561e-06,
+      "loss": 0.8546,
+      "step": 290
+    },
+    {
+      "epoch": 0.19035532994923857,
+      "grad_norm": 1.5127493143081665,
+      "learning_rate": 9.9009877916721e-06,
+      "loss": 0.865,
+      "step": 300
+    },
+    {
+      "epoch": 0.1967005076142132,
+      "grad_norm": 1.3773964643478394,
+      "learning_rate": 9.89430070591876e-06,
+      "loss": 0.8394,
+      "step": 310
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 1.3822346925735474,
+      "learning_rate": 9.888097563523227e-06,
+      "loss": 0.8332,
+      "step": 320
+    },
+    {
+      "epoch": 0.20939086294416243,
+      "grad_norm": 1.5273101329803467,
+      "learning_rate": 9.881000167853215e-06,
+      "loss": 0.863,
+      "step": 330
+    },
+    {
+      "epoch": 0.21573604060913706,
+      "grad_norm": 1.39267897605896,
+      "learning_rate": 9.873687269821322e-06,
+      "loss": 0.8677,
+      "step": 340
+    },
+    {
+      "epoch": 0.22208121827411167,
+      "grad_norm": 1.564704418182373,
+      "learning_rate": 9.866159192301294e-06,
+      "loss": 0.8336,
+      "step": 350
+    },
+    {
+      "epoch": 0.22842639593908629,
+      "grad_norm": 1.5593595504760742,
+      "learning_rate": 9.858416267667318e-06,
+      "loss": 0.8476,
+      "step": 360
+    },
+    {
+      "epoch": 0.23477157360406092,
+      "grad_norm": 1.5241975784301758,
+      "learning_rate": 9.850458837779366e-06,
+      "loss": 0.8521,
+      "step": 370
+    },
+    {
+      "epoch": 0.24111675126903553,
+      "grad_norm": 1.4592645168304443,
+      "learning_rate": 9.842287253968077e-06,
+      "loss": 0.8531,
+      "step": 380
+    },
+    {
+      "epoch": 0.24746192893401014,
+      "grad_norm": 1.327803373336792,
+      "learning_rate": 9.833901877019266e-06,
+      "loss": 0.8526,
+      "step": 390
+    },
+    {
+      "epoch": 0.25380710659898476,
+      "grad_norm": 1.351017713546753,
+      "learning_rate": 9.825303077157983e-06,
+      "loss": 0.8503,
+      "step": 400
+    },
+    {
+      "epoch": 0.26015228426395937,
+      "grad_norm": 1.6651396751403809,
+      "learning_rate": 9.816491234032175e-06,
+      "loss": 0.8758,
+      "step": 410
+    },
+    {
+      "epoch": 0.26649746192893403,
+      "grad_norm": 1.4911518096923828,
+      "learning_rate": 9.807466736695912e-06,
+      "loss": 0.8494,
+      "step": 420
+    },
+    {
+      "epoch": 0.27284263959390864,
+      "grad_norm": 1.34939706325531,
+      "learning_rate": 9.798229983592229e-06,
+      "loss": 0.8419,
+      "step": 430
+    },
+    {
+      "epoch": 0.27918781725888325,
+      "grad_norm": 1.4626591205596924,
+      "learning_rate": 9.788781382535512e-06,
+      "loss": 0.8479,
+      "step": 440
+    },
+    {
+      "epoch": 0.28553299492385786,
+      "grad_norm": 1.5620290040969849,
+      "learning_rate": 9.77912135069351e-06,
+      "loss": 0.8442,
+      "step": 450
+    },
+    {
+      "epoch": 0.2918781725888325,
+      "grad_norm": 1.3260949850082397,
+      "learning_rate": 9.769250314568907e-06,
+      "loss": 0.818,
+      "step": 460
+    },
+    {
+      "epoch": 0.2982233502538071,
+      "grad_norm": 1.3637892007827759,
+      "learning_rate": 9.7591687099805e-06,
+      "loss": 0.8404,
+      "step": 470
+    },
+    {
+      "epoch": 0.30456852791878175,
+      "grad_norm": 1.5293395519256592,
+      "learning_rate": 9.74887698204394e-06,
+      "loss": 0.8334,
+      "step": 480
+    },
+    {
+      "epoch": 0.31091370558375636,
+      "grad_norm": 1.3983063697814941,
+      "learning_rate": 9.738375585152103e-06,
+      "loss": 0.8225,
+      "step": 490
+    },
+    {
+      "epoch": 0.31725888324873097,
+      "grad_norm": 1.3531032800674438,
+      "learning_rate": 9.727664982955008e-06,
+      "loss": 0.8427,
+      "step": 500
+    },
+    {
+      "epoch": 0.3236040609137056,
+      "grad_norm": 1.5252591371536255,
+      "learning_rate": 9.716745648339356e-06,
+      "loss": 0.8625,
+      "step": 510
+    },
+    {
+      "epoch": 0.3299492385786802,
+      "grad_norm": 1.653649926185608,
+      "learning_rate": 9.705618063407653e-06,
+      "loss": 0.8305,
+      "step": 520
+    },
+    {
+      "epoch": 0.3362944162436548,
+      "grad_norm": 1.4992367029190063,
+      "learning_rate": 9.694282719456916e-06,
+      "loss": 0.8149,
+      "step": 530
+    },
+    {
+      "epoch": 0.3426395939086294,
+      "grad_norm": 1.431707739830017,
+      "learning_rate": 9.682740116956992e-06,
+      "loss": 0.8355,
+      "step": 540
+    },
+    {
+      "epoch": 0.3489847715736041,
+      "grad_norm": 1.31185781955719,
+      "learning_rate": 9.670990765528453e-06,
+      "loss": 0.8408,
+      "step": 550
+    },
+    {
+      "epoch": 0.3553299492385787,
+      "grad_norm": 1.550418734550476,
+      "learning_rate": 9.659035183920098e-06,
+      "loss": 0.8227,
+      "step": 560
+    },
+    {
+      "epoch": 0.3616751269035533,
+      "grad_norm": 1.4619323015213013,
+      "learning_rate": 9.646873899986054e-06,
+      "loss": 0.866,
+      "step": 570
+    },
+    {
+      "epoch": 0.3680203045685279,
+      "grad_norm": 1.4029253721237183,
+      "learning_rate": 9.634507450662463e-06,
+      "loss": 0.8411,
+      "step": 580
+    },
+    {
+      "epoch": 0.3743654822335025,
+      "grad_norm": 1.401058554649353,
+      "learning_rate": 9.621936381943787e-06,
+      "loss": 0.848,
+      "step": 590
+    },
+    {
+      "epoch": 0.38071065989847713,
+      "grad_norm": 1.3282866477966309,
+      "learning_rate": 9.609161248858684e-06,
+      "loss": 0.8391,
+      "step": 600
+    },
+    {
+      "epoch": 0.3870558375634518,
+      "grad_norm": 1.4488921165466309,
+      "learning_rate": 9.596182615445522e-06,
+      "loss": 0.8236,
+      "step": 610
+    },
+    {
+      "epoch": 0.3934010152284264,
+      "grad_norm": 1.3285187482833862,
+      "learning_rate": 9.583001054727463e-06,
+      "loss": 0.8439,
+      "step": 620
+    },
+    {
+      "epoch": 0.399746192893401,
+      "grad_norm": 1.5738445520401,
+      "learning_rate": 9.56961714868717e-06,
+      "loss": 0.8377,
+      "step": 630
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 1.4648795127868652,
+      "learning_rate": 9.556031488241107e-06,
+      "loss": 0.8337,
+      "step": 640
+    },
+    {
+      "epoch": 0.41243654822335024,
+      "grad_norm": 1.284525990486145,
+      "learning_rate": 9.54224467321345e-06,
+      "loss": 0.838,
+      "step": 650
+    },
+    {
+      "epoch": 0.41878172588832485,
+      "grad_norm": 1.3344087600708008,
+      "learning_rate": 9.528257312309608e-06,
+      "loss": 0.8242,
+      "step": 660
+    },
+    {
+      "epoch": 0.4251269035532995,
+      "grad_norm": 1.4964150190353394,
+      "learning_rate": 9.514070023089348e-06,
+      "loss": 0.8373,
+      "step": 670
+    },
+    {
+      "epoch": 0.43147208121827413,
+      "grad_norm": 1.324698805809021,
+      "learning_rate": 9.49968343193952e-06,
+      "loss": 0.8422,
+      "step": 680
+    },
+    {
+      "epoch": 0.43781725888324874,
+      "grad_norm": 1.2812756299972534,
+      "learning_rate": 9.485098174046412e-06,
+      "loss": 0.8341,
+      "step": 690
+    },
+    {
+      "epoch": 0.44416243654822335,
+      "grad_norm": 1.4059038162231445,
+      "learning_rate": 9.4703148933677e-06,
+      "loss": 0.8187,
+      "step": 700
+    },
+    {
+      "epoch": 0.45050761421319796,
+      "grad_norm": 1.5261121988296509,
+      "learning_rate": 9.455334242604018e-06,
+      "loss": 0.8298,
+      "step": 710
+    },
+    {
+      "epoch": 0.45685279187817257,
+      "grad_norm": 1.420009732246399,
+      "learning_rate": 9.440156883170137e-06,
+      "loss": 0.8347,
+      "step": 720
+    },
+    {
+      "epoch": 0.4631979695431472,
+      "grad_norm": 1.2983534336090088,
+      "learning_rate": 9.424783485165775e-06,
+      "loss": 0.8346,
+      "step": 730
+    },
+    {
+      "epoch": 0.46954314720812185,
+      "grad_norm": 1.2840627431869507,
+      "learning_rate": 9.409214727345987e-06,
+      "loss": 0.8151,
+      "step": 740
+    },
+    {
+      "epoch": 0.47588832487309646,
+      "grad_norm": 1.3696503639221191,
+      "learning_rate": 9.39345129709123e-06,
+      "loss": 0.8214,
+      "step": 750
+    },
+    {
+      "epoch": 0.48223350253807107,
+      "grad_norm": 1.370424509048462,
+      "learning_rate": 9.37749389037698e-06,
+      "loss": 0.8293,
+      "step": 760
+    },
+    {
+      "epoch": 0.4885786802030457,
+      "grad_norm": 1.4171712398529053,
+      "learning_rate": 9.361343211743033e-06,
+      "loss": 0.8235,
+      "step": 770
+    },
+    {
+      "epoch": 0.4949238578680203,
+      "grad_norm": 1.2537575960159302,
+      "learning_rate": 9.344999974262377e-06,
+      "loss": 0.8188,
+      "step": 780
+    },
+    {
+      "epoch": 0.501269035532995,
+      "grad_norm": 1.3169902563095093,
+      "learning_rate": 9.328464899509722e-06,
+      "loss": 0.8169,
+      "step": 790
+    },
+    {
+      "epoch": 0.5076142131979695,
+      "grad_norm": 1.2017827033996582,
+      "learning_rate": 9.31173871752964e-06,
+      "loss": 0.8175,
+      "step": 800
+    },
+    {
+      "epoch": 0.5139593908629442,
+      "grad_norm": 1.5057929754257202,
+      "learning_rate": 9.294822166804323e-06,
+      "loss": 0.8227,
+      "step": 810
+    },
+    {
+      "epoch": 0.5203045685279187,
+      "grad_norm": 1.4769108295440674,
+      "learning_rate": 9.277715994220989e-06,
+      "loss": 0.8137,
+      "step": 820
+    },
+    {
+      "epoch": 0.5266497461928934,
+      "grad_norm": 1.3442022800445557,
+      "learning_rate": 9.260420955038904e-06,
+      "loss": 0.8247,
+      "step": 830
+    },
+    {
+      "epoch": 0.5329949238578681,
+      "grad_norm": 1.2690612077713013,
+      "learning_rate": 9.242937812856034e-06,
+      "loss": 0.8087,
+      "step": 840
+    },
+    {
+      "epoch": 0.5393401015228426,
+      "grad_norm": 1.277985692024231,
+      "learning_rate": 9.225267339575325e-06,
+      "loss": 0.8089,
+      "step": 850
+    },
+    {
+      "epoch": 0.5456852791878173,
+      "grad_norm": 1.3761783838272095,
+      "learning_rate": 9.207410315370639e-06,
+      "loss": 0.8248,
+      "step": 860
+    },
+    {
+      "epoch": 0.5520304568527918,
+      "grad_norm": 1.3367259502410889,
+      "learning_rate": 9.18936752865229e-06,
+      "loss": 0.8253,
+      "step": 870
+    },
+    {
+      "epoch": 0.5583756345177665,
+      "grad_norm": 1.293145775794983,
+      "learning_rate": 9.17113977603225e-06,
+      "loss": 0.8077,
+      "step": 880
+    },
+    {
+      "epoch": 0.5647208121827412,
+      "grad_norm": 1.290528655052185,
+      "learning_rate": 9.152727862288963e-06,
+      "loss": 0.8216,
+      "step": 890
+    },
+    {
+      "epoch": 0.5710659898477157,
+      "grad_norm": 1.298192024230957,
+      "learning_rate": 9.134132600331829e-06,
+      "loss": 0.824,
+      "step": 900
+    },
+    {
+      "epoch": 0.5774111675126904,
+      "grad_norm": 1.313166856765747,
+      "learning_rate": 9.115354811165298e-06,
+      "loss": 0.8197,
+      "step": 910
+    },
+    {
+      "epoch": 0.583756345177665,
+      "grad_norm": 1.2986682653427124,
+      "learning_rate": 9.096395323852635e-06,
+      "loss": 0.8172,
+      "step": 920
+    },
+    {
+      "epoch": 0.5901015228426396,
+      "grad_norm": 1.3514500856399536,
+      "learning_rate": 9.0772549754793e-06,
+      "loss": 0.835,
+      "step": 930
+    },
+    {
+      "epoch": 0.5964467005076142,
+      "grad_norm": 1.1752053499221802,
+      "learning_rate": 9.057934611116008e-06,
+      "loss": 0.8113,
+      "step": 940
+    },
+    {
+      "epoch": 0.6027918781725888,
+      "grad_norm": 1.230542540550232,
+      "learning_rate": 9.038435083781401e-06,
+      "loss": 0.8115,
+      "step": 950
+    },
+    {
+      "epoch": 0.6091370558375635,
+      "grad_norm": 1.247090458869934,
+      "learning_rate": 9.0187572544044e-06,
+      "loss": 0.8202,
+      "step": 960
+    },
+    {
+      "epoch": 0.6154822335025381,
+      "grad_norm": 1.3615097999572754,
+      "learning_rate": 8.998901991786186e-06,
+      "loss": 0.8369,
+      "step": 970
+    },
+    {
+      "epoch": 0.6218274111675127,
+      "grad_norm": 1.3490197658538818,
+      "learning_rate": 8.978870172561842e-06,
+      "loss": 0.8084,
+      "step": 980
+    },
+    {
+      "epoch": 0.6281725888324873,
+      "grad_norm": 1.2877025604248047,
+      "learning_rate": 8.95866268116165e-06,
+      "loss": 0.7929,
+      "step": 990
+    },
+    {
+      "epoch": 0.6345177664974619,
+      "grad_norm": 1.5650062561035156,
+      "learning_rate": 8.938280409772038e-06,
+      "loss": 0.8263,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6408629441624365,
+      "grad_norm": 1.2181209325790405,
+      "learning_rate": 8.917724258296204e-06,
+      "loss": 0.8137,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6472081218274112,
+      "grad_norm": 1.4872324466705322,
+      "learning_rate": 8.896995134314361e-06,
+      "loss": 0.8097,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6535532994923858,
+      "grad_norm": 1.3156676292419434,
+      "learning_rate": 8.876093953043683e-06,
+      "loss": 0.8149,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6598984771573604,
+      "grad_norm": 1.358504295349121,
+      "learning_rate": 8.855021637297893e-06,
+      "loss": 0.8128,
+      "step": 1040
+    },
+    {
+      "epoch": 0.666243654822335,
+      "grad_norm": 1.4342836141586304,
+      "learning_rate": 8.833779117446515e-06,
+      "loss": 0.8101,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6725888324873096,
+      "grad_norm": 1.2380530834197998,
+      "learning_rate": 8.812367331373806e-06,
+      "loss": 0.8046,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6789340101522843,
+      "grad_norm": 1.253306269645691,
+      "learning_rate": 8.790787224437334e-06,
+      "loss": 0.8255,
+      "step": 1070
+    },
+    {
+      "epoch": 0.6852791878172588,
+      "grad_norm": 1.514151692390442,
+      "learning_rate": 8.769039749426256e-06,
+      "loss": 0.7946,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6916243654822335,
+      "grad_norm": 1.4850667715072632,
+      "learning_rate": 8.747125866519236e-06,
+      "loss": 0.8006,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6979695431472082,
+      "grad_norm": 1.4190680980682373,
+      "learning_rate": 8.725046543242061e-06,
+      "loss": 0.8243,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7043147208121827,
+      "grad_norm": 1.4006381034851074,
+      "learning_rate": 8.70280275442492e-06,
+      "loss": 0.829,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7106598984771574,
+      "grad_norm": 1.2715387344360352,
+      "learning_rate": 8.680395482159364e-06,
+      "loss": 0.806,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7170050761421319,
+      "grad_norm": 1.4159283638000488,
+      "learning_rate": 8.657825715754947e-06,
+      "loss": 0.8173,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7233502538071066,
+      "grad_norm": 1.368446946144104,
+      "learning_rate": 8.63509445169554e-06,
+      "loss": 0.8042,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7296954314720813,
+      "grad_norm": 1.3700900077819824,
+      "learning_rate": 8.612202693595356e-06,
+      "loss": 0.8016,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7360406091370558,
+      "grad_norm": 1.4008903503417969,
+      "learning_rate": 8.589151452154605e-06,
+      "loss": 0.8295,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7423857868020305,
+      "grad_norm": 1.2189836502075195,
+      "learning_rate": 8.565941745114901e-06,
+      "loss": 0.8234,
+      "step": 1170
+    },
+    {
+      "epoch": 0.748730964467005,
+      "grad_norm": 1.2055974006652832,
+      "learning_rate": 8.542574597214314e-06,
+      "loss": 0.8034,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7550761421319797,
+      "grad_norm": 1.2510757446289062,
+      "learning_rate": 8.519051040142128e-06,
+      "loss": 0.815,
+      "step": 1190
+    },
+    {
+      "epoch": 0.7614213197969543,
+      "grad_norm": 1.3542871475219727,
+      "learning_rate": 8.495372112493285e-06,
+      "loss": 0.8099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7677664974619289,
+      "grad_norm": 1.3265260457992554,
+      "learning_rate": 8.471538859722545e-06,
+      "loss": 0.7971,
+      "step": 1210
+    },
+    {
+      "epoch": 0.7741116751269036,
+      "grad_norm": 1.2787420749664307,
+      "learning_rate": 8.447552334098311e-06,
+      "loss": 0.8031,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7804568527918782,
+      "grad_norm": 1.2956528663635254,
+      "learning_rate": 8.42341359465618e-06,
+      "loss": 0.8252,
+      "step": 1230
+    },
+    {
+      "epoch": 0.7868020304568528,
+      "grad_norm": 1.6075105667114258,
+      "learning_rate": 8.399123707152182e-06,
+      "loss": 0.7794,
+      "step": 1240
+    },
+    {
+      "epoch": 0.7931472081218274,
+      "grad_norm": 1.4134018421173096,
+      "learning_rate": 8.374683744015728e-06,
+      "loss": 0.8111,
+      "step": 1250
+    },
+    {
+      "epoch": 0.799492385786802,
+      "grad_norm": 1.3463298082351685,
+      "learning_rate": 8.350094784302253e-06,
+      "loss": 0.818,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8058375634517766,
+      "grad_norm": 1.330447793006897,
+      "learning_rate": 8.325357913645589e-06,
+      "loss": 0.7955,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8121827411167513,
+      "grad_norm": 1.2311888933181763,
+      "learning_rate": 8.300474224210018e-06,
+      "loss": 0.8042,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8185279187817259,
+      "grad_norm": 1.2119029760360718,
+      "learning_rate": 8.27544481464206e-06,
+      "loss": 0.7754,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8248730964467005,
+      "grad_norm": 1.3066750764846802,
+      "learning_rate": 8.25027079002196e-06,
+      "loss": 0.7988,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8312182741116751,
+      "grad_norm": 1.4108072519302368,
+      "learning_rate": 8.224953261814912e-06,
+      "loss": 0.7966,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8375634517766497,
+      "grad_norm": 1.206554651260376,
+      "learning_rate": 8.199493347821963e-06,
+      "loss": 0.7973,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8439086294416244,
+      "grad_norm": 1.3971256017684937,
+      "learning_rate": 8.173892172130683e-06,
+      "loss": 0.7923,
+      "step": 1330
+    },
+    {
+      "epoch": 0.850253807106599,
+      "grad_norm": 1.3277279138565063,
+      "learning_rate": 8.148150865065514e-06,
+      "loss": 0.7894,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8565989847715736,
+      "grad_norm": 1.0922918319702148,
+      "learning_rate": 8.122270563137893e-06,
+      "loss": 0.8043,
+      "step": 1350
+    },
+    {
+      "epoch": 0.8629441624365483,
+      "grad_norm": 1.3102174997329712,
+      "learning_rate": 8.096252408996043e-06,
+      "loss": 0.7988,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8692893401015228,
+      "grad_norm": 1.36167311668396,
+      "learning_rate": 8.070097551374543e-06,
+      "loss": 0.8137,
+      "step": 1370
+    },
+    {
+      "epoch": 0.8756345177664975,
+      "grad_norm": 1.3062223196029663,
+      "learning_rate": 8.043807145043604e-06,
+      "loss": 0.8001,
+      "step": 1380
+    },
+    {
+      "epoch": 0.881979695431472,
+      "grad_norm": 1.3194143772125244,
+      "learning_rate": 8.017382350758085e-06,
+      "loss": 0.8137,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8883248730964467,
+      "grad_norm": 1.1782550811767578,
+      "learning_rate": 7.990824335206242e-06,
+      "loss": 0.7823,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8946700507614214,
+      "grad_norm": 1.4341142177581787,
+      "learning_rate": 7.964134270958222e-06,
+      "loss": 0.8075,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9010152284263959,
+      "grad_norm": 1.3810592889785767,
+      "learning_rate": 7.937313336414287e-06,
+      "loss": 0.8346,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9073604060913706,
+      "grad_norm": 1.2569160461425781,
+      "learning_rate": 7.910362715752792e-06,
+      "loss": 0.7885,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9137055837563451,
+      "grad_norm": 1.2901798486709595,
+      "learning_rate": 7.8832835988779e-06,
+      "loss": 0.7846,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9200507614213198,
+      "grad_norm": 1.369370460510254,
+      "learning_rate": 7.856077181367036e-06,
+      "loss": 0.796,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9263959390862944,
+      "grad_norm": 1.3031636476516724,
+      "learning_rate": 7.828744664418121e-06,
+      "loss": 0.82,
+      "step": 1460
+    },
+    {
+      "epoch": 0.932741116751269,
+      "grad_norm": 1.371850609779358,
+      "learning_rate": 7.801287254796522e-06,
+      "loss": 0.7746,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9390862944162437,
+      "grad_norm": 1.2887086868286133,
+      "learning_rate": 7.773706164781776e-06,
+      "loss": 0.7718,
+      "step": 1480
+    },
+    {
+      "epoch": 0.9454314720812182,
+      "grad_norm": 1.215701699256897,
+      "learning_rate": 7.746002612114064e-06,
+      "loss": 0.7974,
+      "step": 1490
+    },
+    {
+      "epoch": 0.9517766497461929,
+      "grad_norm": 1.3907893896102905,
+      "learning_rate": 7.718177819940455e-06,
+      "loss": 0.7891,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9581218274111675,
+      "grad_norm": 1.279998779296875,
+      "learning_rate": 7.690233016760891e-06,
+      "loss": 0.8199,
+      "step": 1510
+    },
+    {
+      "epoch": 0.9644670050761421,
+      "grad_norm": 1.2313257455825806,
+      "learning_rate": 7.662169436373954e-06,
+      "loss": 0.7825,
+      "step": 1520
+    },
+    {
+      "epoch": 0.9708121827411168,
+      "grad_norm": 1.3036500215530396,
+      "learning_rate": 7.633988317822394e-06,
+      "loss": 0.7927,
+      "step": 1530
+    },
+    {
+      "epoch": 0.9771573604060914,
+      "grad_norm": 1.4679865837097168,
+      "learning_rate": 7.605690905338413e-06,
+      "loss": 0.8148,
+      "step": 1540
+    },
+    {
+      "epoch": 0.983502538071066,
+      "grad_norm": 1.1727280616760254,
+      "learning_rate": 7.577278448288745e-06,
+      "loss": 0.8088,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9898477157360406,
+      "grad_norm": 1.4299554824829102,
+      "learning_rate": 7.548752201119484e-06,
+      "loss": 0.8154,
+      "step": 1560
+    },
+    {
+      "epoch": 0.9961928934010152,
+      "grad_norm": 1.2478923797607422,
+      "learning_rate": 7.520113423300706e-06,
+      "loss": 0.7988,
+      "step": 1570
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4728,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.066955944001798e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38910cc27a81dfe34946ec142e2ee6616bc16de0ca61d655dc667d70b3b810d8
+size 6904

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)