Upload 15 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "avemio-digital/Mistral-Nemo-SFT-after-CPT-with-2-epochs-adjusted-config",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 131136
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.4"
+}

latest

@@ -0,0 +1 @@
+global_step720

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3296d415d0e2b2754257d87da185d9dff731987029b31ce0307774c8bafb246a
+size 4866177856

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348b74901e4d5c51bb4005101f4950105c55434fda2bdc1eeae8c4b9272fad14
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e07e57f24c193cb5c56fbbd6545b4a5925fecd6ebbf96bd8ee9e29204d8021
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6eb30db4d77024f9fd5a362d39c98f7c58ac306b0c92b28b7505df3b7660de2
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d70438639b120ae15dee5c1fb673b2d00a791e465500a316fc41831a55b2661
+size 4908151632

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24496875520
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,504 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.425531914893618,
+  "eval_steps": 300,
+  "global_step": 720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9078014184397163,
+      "grad_norm": 132.1505126953125,
+      "learning_rate": 2.222222222222222e-07,
+      "log_odds_chosen": 0.05492939054965973,
+      "log_odds_ratio": -0.7323614954948425,
+      "logits/chosen": -4.740067958831787,
+      "logits/rejected": -4.963461399078369,
+      "logps/chosen": -2.374514579772949,
+      "logps/rejected": -2.4533467292785645,
+      "loss": 2.8785,
+      "nll_loss": 2.7699854373931885,
+      "rewards/accuracies": 0.48828125,
+      "rewards/chosen": -0.3561772108078003,
+      "rewards/margins": 0.011824802495539188,
+      "rewards/rejected": -0.3680019676685333,
+      "step": 32
+    },
+    {
+      "epoch": 1.8156028368794326,
+      "grad_norm": 45.387813568115234,
+      "learning_rate": 4.444444444444444e-07,
+      "log_odds_chosen": 0.22124934196472168,
+      "log_odds_ratio": -0.6725601553916931,
+      "logits/chosen": -5.0936760902404785,
+      "logits/rejected": -5.33966588973999,
+      "logps/chosen": -1.732269287109375,
+      "logps/rejected": -1.9329001903533936,
+      "loss": 2.2151,
+      "nll_loss": 2.172783851623535,
+      "rewards/accuracies": 0.6015625,
+      "rewards/chosen": -0.2598403990268707,
+      "rewards/margins": 0.030094601213932037,
+      "rewards/rejected": -0.28993502259254456,
+      "step": 64
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 19.709226608276367,
+      "learning_rate": 4.983095894354857e-07,
+      "log_odds_chosen": 0.2306685447692871,
+      "log_odds_ratio": -0.658535361289978,
+      "logits/chosen": -4.936949729919434,
+      "logits/rejected": -5.155893802642822,
+      "logps/chosen": -1.4097586870193481,
+      "logps/rejected": -1.5965328216552734,
+      "loss": 1.8908,
+      "nll_loss": 1.8126921653747559,
+      "rewards/accuracies": 0.6171875,
+      "rewards/chosen": -0.2114638090133667,
+      "rewards/margins": 0.028016118332743645,
+      "rewards/rejected": -0.2394799143075943,
+      "step": 96
+    },
+    {
+      "epoch": 3.631205673758865,
+      "grad_norm": 20.5742130279541,
+      "learning_rate": 4.908427196539701e-07,
+      "log_odds_chosen": 0.3416966497898102,
+      "log_odds_ratio": -0.5978461503982544,
+      "logits/chosen": -4.871417999267578,
+      "logits/rejected": -5.006246566772461,
+      "logps/chosen": -1.3338335752487183,
+      "logps/rejected": -1.595802903175354,
+      "loss": 1.7492,
+      "nll_loss": 1.6234831809997559,
+      "rewards/accuracies": 0.66015625,
+      "rewards/chosen": -0.20007506012916565,
+      "rewards/margins": 0.039295390248298645,
+      "rewards/rejected": -0.2393704503774643,
+      "step": 128
+    },
+    {
+      "epoch": 4.539007092198582,
+      "grad_norm": 19.219451904296875,
+      "learning_rate": 4.775907352415367e-07,
+      "log_odds_chosen": 0.4098852872848511,
+      "log_odds_ratio": -0.5668885111808777,
+      "logits/chosen": -4.7395429611206055,
+      "logits/rejected": -4.919832229614258,
+      "logps/chosen": -1.251634955406189,
+      "logps/rejected": -1.5617362260818481,
+      "loss": 1.6591,
+      "nll_loss": 1.5759321451187134,
+      "rewards/accuracies": 0.72265625,
+      "rewards/chosen": -0.18774525821208954,
+      "rewards/margins": 0.04651518166065216,
+      "rewards/rejected": -0.2342604398727417,
+      "step": 160
+    },
+    {
+      "epoch": 5.446808510638298,
+      "grad_norm": 25.844369888305664,
+      "learning_rate": 4.588719528532341e-07,
+      "log_odds_chosen": 0.4376165568828583,
+      "log_odds_ratio": -0.5644897222518921,
+      "logits/chosen": -4.674585342407227,
+      "logits/rejected": -4.810555934906006,
+      "logps/chosen": -1.2456402778625488,
+      "logps/rejected": -1.5732855796813965,
+      "loss": 1.5996,
+      "nll_loss": 1.4974051713943481,
+      "rewards/accuracies": 0.73828125,
+      "rewards/chosen": -0.1868460476398468,
+      "rewards/margins": 0.04914678633213043,
+      "rewards/rejected": -0.23599283397197723,
+      "step": 192
+    },
+    {
+      "epoch": 6.3546099290780145,
+      "grad_norm": 23.09563636779785,
+      "learning_rate": 4.3513600327725117e-07,
+      "log_odds_chosen": 0.3738464415073395,
+      "log_odds_ratio": -0.5867234468460083,
+      "logits/chosen": -4.663087844848633,
+      "logits/rejected": -4.844013214111328,
+      "logps/chosen": -1.3138737678527832,
+      "logps/rejected": -1.5835403203964233,
+      "loss": 1.5411,
+      "nll_loss": 1.4685286283493042,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": -0.197081059217453,
+      "rewards/margins": 0.04045000299811363,
+      "rewards/rejected": -0.23753106594085693,
+      "step": 224
+    },
+    {
+      "epoch": 7.26241134751773,
+      "grad_norm": 23.646638870239258,
+      "learning_rate": 4.0695303116802467e-07,
+      "log_odds_chosen": 0.46367794275283813,
+      "log_odds_ratio": -0.547984778881073,
+      "logits/chosen": -4.620482921600342,
+      "logits/rejected": -4.765042781829834,
+      "logps/chosen": -1.307213544845581,
+      "logps/rejected": -1.65544593334198,
+      "loss": 1.498,
+      "nll_loss": 1.4461973905563354,
+      "rewards/accuracies": 0.75390625,
+      "rewards/chosen": -0.19608205556869507,
+      "rewards/margins": 0.05223485454916954,
+      "rewards/rejected": -0.2483169138431549,
+      "step": 256
+    },
+    {
+      "epoch": 8.170212765957446,
+      "grad_norm": 23.585857391357422,
+      "learning_rate": 3.75e-07,
+      "log_odds_chosen": 0.4542897343635559,
+      "log_odds_ratio": -0.5773134827613831,
+      "logits/chosen": -4.633105278015137,
+      "logits/rejected": -4.810471057891846,
+      "logps/chosen": -1.3886733055114746,
+      "logps/rejected": -1.7219102382659912,
+      "loss": 1.4686,
+      "nll_loss": 1.3969916105270386,
+      "rewards/accuracies": 0.7734375,
+      "rewards/chosen": -0.20830100774765015,
+      "rewards/margins": 0.049985550343990326,
+      "rewards/rejected": -0.2582865357398987,
+      "step": 288
+    },
+    {
+      "epoch": 8.51063829787234,
+      "eval_log_odds_chosen": 1.6898525953292847,
+      "eval_log_odds_ratio": -0.19230316579341888,
+      "eval_logits/chosen": -4.930749416351318,
+      "eval_logits/rejected": -4.758046627044678,
+      "eval_logps/chosen": -1.4714246988296509,
+      "eval_logps/rejected": -2.9621574878692627,
+      "eval_loss": 1.3246647119522095,
+      "eval_nll_loss": 1.4632530212402344,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": -0.22071371972560883,
+      "eval_rewards/margins": 0.22360996901988983,
+      "eval_rewards/rejected": -0.44432368874549866,
+      "eval_runtime": 0.6144,
+      "eval_samples_per_second": 222.965,
+      "eval_steps_per_second": 4.882,
+      "step": 300
+    },
+    {
+      "epoch": 9.078014184397164,
+      "grad_norm": 20.154146194458008,
+      "learning_rate": 3.400444312011776e-07,
+      "log_odds_chosen": 0.409349262714386,
+      "log_odds_ratio": -0.5844379663467407,
+      "logits/chosen": -4.599703311920166,
+      "logits/rejected": -4.766429901123047,
+      "logps/chosen": -1.3831363916397095,
+      "logps/rejected": -1.6733564138412476,
+      "loss": 1.4397,
+      "nll_loss": 1.4065345525741577,
+      "rewards/accuracies": 0.74609375,
+      "rewards/chosen": -0.20747046172618866,
+      "rewards/margins": 0.04353303089737892,
+      "rewards/rejected": -0.2510034739971161,
+      "step": 320
+    },
+    {
+      "epoch": 9.98581560283688,
+      "grad_norm": 23.09050750732422,
+      "learning_rate": 3.029259680573527e-07,
+      "log_odds_chosen": 0.43665847182273865,
+      "log_odds_ratio": -0.5905143618583679,
+      "logits/chosen": -4.58922815322876,
+      "logits/rejected": -4.685288906097412,
+      "logps/chosen": -1.458475112915039,
+      "logps/rejected": -1.7894960641860962,
+      "loss": 1.4285,
+      "nll_loss": 1.3732693195343018,
+      "rewards/accuracies": 0.73046875,
+      "rewards/chosen": -0.21877126395702362,
+      "rewards/margins": 0.04965316504240036,
+      "rewards/rejected": -0.26842445135116577,
+      "step": 352
+    },
+    {
+      "epoch": 10.893617021276595,
+      "grad_norm": 35.926055908203125,
+      "learning_rate": 2.6453620722761895e-07,
+      "log_odds_chosen": 0.6511461138725281,
+      "log_odds_ratio": -0.49195483326911926,
+      "logits/chosen": -4.608173370361328,
+      "logits/rejected": -4.685794830322266,
+      "logps/chosen": -1.3694053888320923,
+      "logps/rejected": -1.8711962699890137,
+      "loss": 1.4144,
+      "nll_loss": 1.374709129333496,
+      "rewards/accuracies": 0.8359375,
+      "rewards/chosen": -0.20541077852249146,
+      "rewards/margins": 0.07526866346597672,
+      "rewards/rejected": -0.28067946434020996,
+      "step": 384
+    },
+    {
+      "epoch": 11.801418439716311,
+      "grad_norm": 33.8105583190918,
+      "learning_rate": 2.2579728232420523e-07,
+      "log_odds_chosen": 0.5499828457832336,
+      "log_odds_ratio": -0.5233615040779114,
+      "logits/chosen": -4.537787437438965,
+      "logits/rejected": -4.662774085998535,
+      "logps/chosen": -1.3898181915283203,
+      "logps/rejected": -1.7920804023742676,
+      "loss": 1.4016,
+      "nll_loss": 1.3631547689437866,
+      "rewards/accuracies": 0.7890625,
+      "rewards/chosen": -0.20847272872924805,
+      "rewards/margins": 0.06033932417631149,
+      "rewards/rejected": -0.26881206035614014,
+      "step": 416
+    },
+    {
+      "epoch": 12.709219858156029,
+      "grad_norm": 25.557348251342773,
+      "learning_rate": 1.8763971398550467e-07,
+      "log_odds_chosen": 0.5377756357192993,
+      "log_odds_ratio": -0.5508320927619934,
+      "logits/chosen": -4.532352447509766,
+      "logits/rejected": -4.629130840301514,
+      "logps/chosen": -1.3977127075195312,
+      "logps/rejected": -1.7851612567901611,
+      "loss": 1.3943,
+      "nll_loss": 1.3304414749145508,
+      "rewards/accuracies": 0.77734375,
+      "rewards/chosen": -0.20965692400932312,
+      "rewards/margins": 0.05811727046966553,
+      "rewards/rejected": -0.26777422428131104,
+      "step": 448
+    },
+    {
+      "epoch": 13.617021276595745,
+      "grad_norm": 28.700815200805664,
+      "learning_rate": 1.5098005849021078e-07,
+      "log_odds_chosen": 0.5411101579666138,
+      "log_odds_ratio": -0.5445564985275269,
+      "logits/chosen": -4.501680850982666,
+      "logits/rejected": -4.677550315856934,
+      "logps/chosen": -1.3654242753982544,
+      "logps/rejected": -1.7541980743408203,
+      "loss": 1.401,
+      "nll_loss": 1.2766036987304688,
+      "rewards/accuracies": 0.8046875,
+      "rewards/chosen": -0.2048136293888092,
+      "rewards/margins": 0.05831605941057205,
+      "rewards/rejected": -0.26312971115112305,
+      "step": 480
+    },
+    {
+      "epoch": 14.52482269503546,
+      "grad_norm": 35.40031814575195,
+      "learning_rate": 1.1669889179957723e-07,
+      "log_odds_chosen": 0.7372524738311768,
+      "log_odds_ratio": -0.46363916993141174,
+      "logits/chosen": -4.513700485229492,
+      "logits/rejected": -4.619227886199951,
+      "logps/chosen": -1.3301138877868652,
+      "logps/rejected": -1.8859204053878784,
+      "loss": 1.3839,
+      "nll_loss": 1.219886302947998,
+      "rewards/accuracies": 0.87109375,
+      "rewards/chosen": -0.19951710104942322,
+      "rewards/margins": 0.08337096124887466,
+      "rewards/rejected": -0.2828880548477173,
+      "step": 512
+    },
+    {
+      "epoch": 15.432624113475176,
+      "grad_norm": 62.16829299926758,
+      "learning_rate": 8.561965785773412e-08,
+      "log_odds_chosen": 0.661382794380188,
+      "log_odds_ratio": -0.4891131520271301,
+      "logits/chosen": -4.506048202514648,
+      "logits/rejected": -4.587852478027344,
+      "logps/chosen": -1.3864898681640625,
+      "logps/rejected": -1.8775601387023926,
+      "loss": 1.3876,
+      "nll_loss": 1.2974672317504883,
+      "rewards/accuracies": 0.8359375,
+      "rewards/chosen": -0.20797351002693176,
+      "rewards/margins": 0.07366053014993668,
+      "rewards/rejected": -0.28163403272628784,
+      "step": 544
+    },
+    {
+      "epoch": 16.340425531914892,
+      "grad_norm": 29.107358932495117,
+      "learning_rate": 5.848888922025552e-08,
+      "log_odds_chosen": 0.6269708275794983,
+      "log_odds_ratio": -0.49757176637649536,
+      "logits/chosen": -4.460994243621826,
+      "logits/rejected": -4.661521911621094,
+      "logps/chosen": -1.3339214324951172,
+      "logps/rejected": -1.7924858331680298,
+      "loss": 1.3923,
+      "nll_loss": 1.2958626747131348,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.200088232755661,
+      "rewards/margins": 0.06878463923931122,
+      "rewards/rejected": -0.26887285709381104,
+      "step": 576
+    },
+    {
+      "epoch": 17.02127659574468,
+      "eval_log_odds_chosen": 1.7557824850082397,
+      "eval_log_odds_ratio": -0.18494771420955658,
+      "eval_logits/chosen": -4.790639400482178,
+      "eval_logits/rejected": -4.577674865722656,
+      "eval_logps/chosen": -1.626247763633728,
+      "eval_logps/rejected": -3.2115631103515625,
+      "eval_loss": 1.2619013786315918,
+      "eval_nll_loss": 1.4078196287155151,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": -0.2439371794462204,
+      "eval_rewards/margins": 0.2377973347902298,
+      "eval_rewards/rejected": -0.4817345142364502,
+      "eval_runtime": 0.6115,
+      "eval_samples_per_second": 224.05,
+      "eval_steps_per_second": 4.906,
+      "step": 600
+    },
+    {
+      "epoch": 17.24822695035461,
+      "grad_norm": 29.23589515686035,
+      "learning_rate": 3.5958275117433404e-08,
+      "log_odds_chosen": 0.5763309001922607,
+      "log_odds_ratio": -0.5261004567146301,
+      "logits/chosen": -4.398637294769287,
+      "logits/rejected": -4.560643672943115,
+      "logps/chosen": -1.3885968923568726,
+      "logps/rejected": -1.8019691705703735,
+      "loss": 1.3886,
+      "nll_loss": 1.3023698329925537,
+      "rewards/accuracies": 0.8046875,
+      "rewards/chosen": -0.20828954875469208,
+      "rewards/margins": 0.06200582906603813,
+      "rewards/rejected": -0.2702953815460205,
+      "step": 608
+    },
+    {
+      "epoch": 18.156028368794328,
+      "grad_norm": 27.693330764770508,
+      "learning_rate": 1.8569007682777415e-08,
+      "log_odds_chosen": 0.7424343824386597,
+      "log_odds_ratio": -0.46295538544654846,
+      "logits/chosen": -4.579552173614502,
+      "logits/rejected": -4.691650390625,
+      "logps/chosen": -1.3507909774780273,
+      "logps/rejected": -1.9150110483169556,
+      "loss": 1.3865,
+      "nll_loss": 1.3111711740493774,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.20261868834495544,
+      "rewards/margins": 0.084633007645607,
+      "rewards/rejected": -0.28725165128707886,
+      "step": 640
+    },
+    {
+      "epoch": 19.06382978723404,
+      "grad_norm": 37.925621032714844,
+      "learning_rate": 6.738782355044048e-09,
+      "log_odds_chosen": 0.6857459545135498,
+      "log_odds_ratio": -0.4916977882385254,
+      "logits/chosen": -4.52652645111084,
+      "logits/rejected": -4.689857482910156,
+      "logps/chosen": -1.341786503791809,
+      "logps/rejected": -1.8565285205841064,
+      "loss": 1.3794,
+      "nll_loss": 1.2754034996032715,
+      "rewards/accuracies": 0.8046875,
+      "rewards/chosen": -0.20126797258853912,
+      "rewards/margins": 0.07721129059791565,
+      "rewards/rejected": -0.27847927808761597,
+      "step": 672
+    },
+    {
+      "epoch": 19.97163120567376,
+      "grad_norm": 24.041799545288086,
+      "learning_rate": 7.51764708051994e-10,
+      "log_odds_chosen": 0.6411248445510864,
+      "log_odds_ratio": -0.5100895762443542,
+      "logits/chosen": -4.384097099304199,
+      "logits/rejected": -4.515219688415527,
+      "logps/chosen": -1.3920109272003174,
+      "logps/rejected": -1.8711614608764648,
+      "loss": 1.3805,
+      "nll_loss": 1.2700397968292236,
+      "rewards/accuracies": 0.8203125,
+      "rewards/chosen": -0.20880162715911865,
+      "rewards/margins": 0.07187257707118988,
+      "rewards/rejected": -0.2806742191314697,
+      "step": 704
+    },
+    {
+      "epoch": 20.425531914893618,
+      "grad_norm": 28.226720809936523,
+      "learning_rate": 0.0,
+      "log_odds_chosen": 0.6200518608093262,
+      "log_odds_ratio": -0.529932975769043,
+      "logits/chosen": -4.434691905975342,
+      "logits/rejected": -4.575813293457031,
+      "logps/chosen": -1.416117548942566,
+      "logps/rejected": -1.8715832233428955,
+      "loss": 1.3893,
+      "nll_loss": 1.2817054986953735,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.2124176323413849,
+      "rewards/margins": 0.0683198943734169,
+      "rewards/rejected": -0.2807375192642212,
+      "step": 720
+    },
+    {
+      "epoch": 20.425531914893618,
+      "eval_log_odds_chosen": 1.7479673624038696,
+      "eval_log_odds_ratio": -0.1867920309305191,
+      "eval_logits/chosen": -4.75565767288208,
+      "eval_logits/rejected": -4.538194179534912,
+      "eval_logps/chosen": -1.6300764083862305,
+      "eval_logps/rejected": -3.2087719440460205,
+      "eval_loss": 1.2522811889648438,
+      "eval_nll_loss": 1.4028778076171875,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": -0.24451148509979248,
+      "eval_rewards/margins": 0.23680436611175537,
+      "eval_rewards/rejected": -0.48131585121154785,
+      "eval_runtime": 0.615,
+      "eval_samples_per_second": 222.778,
+      "eval_steps_per_second": 4.878,
+      "step": 720
+    }
+  ],
+  "logging_steps": 32,
+  "max_steps": 720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 21,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

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)