Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0"
+}

latest

@@ -0,0 +1 @@
+global_step259

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00945a958ceb370a03d47a618c8f115cfefe535e5d943d101cbe4e11bca7b67
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80fb1a33b6f81e14651b4277ff6a1f75302c7d51091973898c268ece96b271ab
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30bdd1ccb3236d92f23948c04e0b17ec6ec532ed25fb8daf2721f51fb19444c1
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "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-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-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-00002-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-00002-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-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-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-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-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-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-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"
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1575 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 259,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 1.7394,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 1.7697,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.6e-07,
+      "loss": 1.7627,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 1.735,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.7082,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.2e-07,
+      "loss": 1.6211,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 1.6883,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 1.5584,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.08e-06,
+      "loss": 1.5924,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.5434,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.32e-06,
+      "loss": 1.5874,
+      "step": 11
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.44e-06,
+      "loss": 1.5128,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.56e-06,
+      "loss": 1.476,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 1.4491,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8e-06,
+      "loss": 1.4457,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 1.5084,
+      "step": 16
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.0400000000000004e-06,
+      "loss": 1.4479,
+      "step": 17
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.16e-06,
+      "loss": 1.4411,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.28e-06,
+      "loss": 1.4247,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.4575,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.52e-06,
+      "loss": 1.4149,
+      "step": 21
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.64e-06,
+      "loss": 1.3653,
+      "step": 22
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.7600000000000003e-06,
+      "loss": 1.38,
+      "step": 23
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.88e-06,
+      "loss": 1.3726,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3e-06,
+      "loss": 1.3391,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.12e-06,
+      "loss": 1.3389,
+      "step": 26
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.2400000000000003e-06,
+      "loss": 1.3534,
+      "step": 27
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.3600000000000004e-06,
+      "loss": 1.3254,
+      "step": 28
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.4799999999999997e-06,
+      "loss": 1.3376,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.6e-06,
+      "loss": 1.3301,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.72e-06,
+      "loss": 1.2873,
+      "step": 31
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.8400000000000005e-06,
+      "loss": 1.3017,
+      "step": 32
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.96e-06,
+      "loss": 1.2682,
+      "step": 33
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.080000000000001e-06,
+      "loss": 1.2898,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.2e-06,
+      "loss": 1.3131,
+      "step": 35
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.32e-06,
+      "loss": 1.2749,
+      "step": 36
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.44e-06,
+      "loss": 1.2548,
+      "step": 37
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.56e-06,
+      "loss": 1.3048,
+      "step": 38
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.68e-06,
+      "loss": 1.2622,
+      "step": 39
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.2622,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.9199999999999995e-06,
+      "loss": 1.2856,
+      "step": 41
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5.04e-06,
+      "loss": 1.2536,
+      "step": 42
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 5.16e-06,
+      "loss": 1.2843,
+      "step": 43
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 5.28e-06,
+      "loss": 1.2241,
+      "step": 44
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 5.4e-06,
+      "loss": 1.2465,
+      "step": 45
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 5.5200000000000005e-06,
+      "loss": 1.2621,
+      "step": 46
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 5.64e-06,
+      "loss": 1.2394,
+      "step": 47
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.76e-06,
+      "loss": 1.2315,
+      "step": 48
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.8800000000000005e-06,
+      "loss": 1.1924,
+      "step": 49
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 6e-06,
+      "loss": 1.2384,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.9999719894583576e-06,
+      "loss": 1.2289,
+      "step": 51
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.9998879583564896e-06,
+      "loss": 1.241,
+      "step": 52
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5.999747908263568e-06,
+      "loss": 1.1919,
+      "step": 53
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 5.999551841794844e-06,
+      "loss": 1.2528,
+      "step": 54
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 5.999299762611606e-06,
+      "loss": 1.2073,
+      "step": 55
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5.998991675421101e-06,
+      "loss": 1.256,
+      "step": 56
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5.998627585976455e-06,
+      "loss": 1.256,
+      "step": 57
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5.998207501076565e-06,
+      "loss": 1.2178,
+      "step": 58
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5.997731428565966e-06,
+      "loss": 1.226,
+      "step": 59
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5.99719937733469e-06,
+      "loss": 1.2135,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.996611357318102e-06,
+      "loss": 1.2189,
+      "step": 61
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.995967379496706e-06,
+      "loss": 1.2547,
+      "step": 62
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.9952674558959485e-06,
+      "loss": 1.1776,
+      "step": 63
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.994511599585988e-06,
+      "loss": 1.1828,
+      "step": 64
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.993699824681454e-06,
+      "loss": 1.2118,
+      "step": 65
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.992832146341183e-06,
+      "loss": 1.2142,
+      "step": 66
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.991908580767936e-06,
+      "loss": 1.1621,
+      "step": 67
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.990929145208094e-06,
+      "loss": 1.1942,
+      "step": 68
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5.989893857951337e-06,
+      "loss": 1.22,
+      "step": 69
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5.988802738330303e-06,
+      "loss": 1.1666,
+      "step": 70
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5.9876558067202265e-06,
+      "loss": 1.2408,
+      "step": 71
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.986453084538559e-06,
+      "loss": 1.1819,
+      "step": 72
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.985194594244564e-06,
+      "loss": 1.183,
+      "step": 73
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.983880359338908e-06,
+      "loss": 1.2063,
+      "step": 74
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.982510404363209e-06,
+      "loss": 1.168,
+      "step": 75
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.981084754899591e-06,
+      "loss": 1.2035,
+      "step": 76
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.979603437570195e-06,
+      "loss": 1.1778,
+      "step": 77
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.978066480036686e-06,
+      "loss": 1.2116,
+      "step": 78
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5.976473910999742e-06,
+      "loss": 1.1549,
+      "step": 79
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5.974825760198511e-06,
+      "loss": 1.1782,
+      "step": 80
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5.973122058410054e-06,
+      "loss": 1.2074,
+      "step": 81
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 5.971362837448781e-06,
+      "loss": 1.208,
+      "step": 82
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 5.969548130165845e-06,
+      "loss": 1.1907,
+      "step": 83
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 5.967677970448536e-06,
+      "loss": 1.1988,
+      "step": 84
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 5.965752393219645e-06,
+      "loss": 1.17,
+      "step": 85
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 5.963771434436812e-06,
+      "loss": 1.1714,
+      "step": 86
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 5.961735131091857e-06,
+      "loss": 1.1543,
+      "step": 87
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 5.959643521210085e-06,
+      "loss": 1.226,
+      "step": 88
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 5.957496643849582e-06,
+      "loss": 1.1877,
+      "step": 89
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 5.955294539100477e-06,
+      "loss": 1.1982,
+      "step": 90
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 5.953037248084204e-06,
+      "loss": 1.1428,
+      "step": 91
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 5.950724812952725e-06,
+      "loss": 1.1791,
+      "step": 92
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 5.948357276887745e-06,
+      "loss": 1.1913,
+      "step": 93
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 5.945934684099912e-06,
+      "loss": 1.1774,
+      "step": 94
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 5.94345707982798e-06,
+      "loss": 1.1502,
+      "step": 95
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 5.9409245103379775e-06,
+      "loss": 1.1519,
+      "step": 96
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 5.938337022922332e-06,
+      "loss": 1.1538,
+      "step": 97
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 5.935694665898992e-06,
+      "loss": 1.1838,
+      "step": 98
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 5.932997488610526e-06,
+      "loss": 1.1512,
+      "step": 99
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5.9302455414231975e-06,
+      "loss": 1.1567,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5.927438875726029e-06,
+      "loss": 1.1236,
+      "step": 101
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5.924577543929837e-06,
+      "loss": 1.1731,
+      "step": 102
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 5.921661599466257e-06,
+      "loss": 1.1685,
+      "step": 103
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 5.918691096786745e-06,
+      "loss": 1.1885,
+      "step": 104
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5.915666091361561e-06,
+      "loss": 1.2044,
+      "step": 105
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5.912586639678732e-06,
+      "loss": 1.1825,
+      "step": 106
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5.909452799242996e-06,
+      "loss": 1.1341,
+      "step": 107
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 5.906264628574734e-06,
+      "loss": 1.1393,
+      "step": 108
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 5.90302218720887e-06,
+      "loss": 1.1612,
+      "step": 109
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 5.899725535693762e-06,
+      "loss": 1.1081,
+      "step": 110
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 5.896374735590074e-06,
+      "loss": 1.1474,
+      "step": 111
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 5.892969849469624e-06,
+      "loss": 1.2151,
+      "step": 112
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5.889510940914214e-06,
+      "loss": 1.1313,
+      "step": 113
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5.885998074514447e-06,
+      "loss": 1.1518,
+      "step": 114
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5.882431315868514e-06,
+      "loss": 1.1827,
+      "step": 115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 5.878810731580978e-06,
+      "loss": 1.1554,
+      "step": 116
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 5.875136389261522e-06,
+      "loss": 1.1353,
+      "step": 117
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.871408357523693e-06,
+      "loss": 1.2146,
+      "step": 118
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.867626705983617e-06,
+      "loss": 1.1441,
+      "step": 119
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.863791505258699e-06,
+      "loss": 1.1537,
+      "step": 120
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.859902826966304e-06,
+      "loss": 1.1486,
+      "step": 121
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.855960743722423e-06,
+      "loss": 1.1022,
+      "step": 122
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.851965329140315e-06,
+      "loss": 1.1632,
+      "step": 123
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.847916657829129e-06,
+      "loss": 1.1447,
+      "step": 124
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.8438148053925185e-06,
+      "loss": 1.1589,
+      "step": 125
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.839659848427221e-06,
+      "loss": 1.1597,
+      "step": 126
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.835451864521632e-06,
+      "loss": 1.1661,
+      "step": 127
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.831190932254359e-06,
+      "loss": 1.1426,
+      "step": 128
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.826877131192748e-06,
+      "loss": 1.1405,
+      "step": 129
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.822510541891403e-06,
+      "loss": 1.1292,
+      "step": 130
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.818091245890677e-06,
+      "loss": 1.1677,
+      "step": 131
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.8136193257151535e-06,
+      "loss": 1.1283,
+      "step": 132
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.809094864872104e-06,
+      "loss": 1.1596,
+      "step": 133
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5.804517947849927e-06,
+      "loss": 1.1647,
+      "step": 134
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5.799888660116573e-06,
+      "loss": 1.1448,
+      "step": 135
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 5.795207088117946e-06,
+      "loss": 1.1514,
+      "step": 136
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 5.790473319276292e-06,
+      "loss": 1.1466,
+      "step": 137
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 5.785687441988563e-06,
+      "loss": 1.15,
+      "step": 138
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.780849545624768e-06,
+      "loss": 1.1518,
+      "step": 139
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.775959720526308e-06,
+      "loss": 1.0718,
+      "step": 140
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.7710180580042804e-06,
+      "loss": 1.1932,
+      "step": 141
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.766024650337782e-06,
+      "loss": 1.1303,
+      "step": 142
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.760979590772182e-06,
+      "loss": 1.141,
+      "step": 143
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.75588297351738e-06,
+      "loss": 1.1325,
+      "step": 144
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.750734893746051e-06,
+      "loss": 1.1484,
+      "step": 145
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.7455354475918615e-06,
+      "loss": 1.1534,
+      "step": 146
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.740284732147681e-06,
+      "loss": 1.15,
+      "step": 147
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.7349828454637654e-06,
+      "loss": 1.0994,
+      "step": 148
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.7296298865459275e-06,
+      "loss": 1.1786,
+      "step": 149
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.724225955353685e-06,
+      "loss": 1.1118,
+      "step": 150
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.718771152798398e-06,
+      "loss": 1.1282,
+      "step": 151
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5.713265580741383e-06,
+      "loss": 1.0907,
+      "step": 152
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5.70770934199201e-06,
+      "loss": 1.1562,
+      "step": 153
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5.7021025403057835e-06,
+      "loss": 1.182,
+      "step": 154
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 5.696445280382404e-06,
+      "loss": 1.1148,
+      "step": 155
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 5.690737667863816e-06,
+      "loss": 1.1172,
+      "step": 156
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.684979809332232e-06,
+      "loss": 1.1513,
+      "step": 157
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.6791718123081425e-06,
+      "loss": 1.1334,
+      "step": 158
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.673313785248308e-06,
+      "loss": 1.118,
+      "step": 159
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5.667405837543736e-06,
+      "loss": 1.1427,
+      "step": 160
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5.661448079517636e-06,
+      "loss": 1.1403,
+      "step": 161
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.6554406224233634e-06,
+      "loss": 1.1438,
+      "step": 162
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.649383578442334e-06,
+      "loss": 1.1738,
+      "step": 163
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.643277060681938e-06,
+      "loss": 1.1444,
+      "step": 164
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.63712118317342e-06,
+      "loss": 1.0963,
+      "step": 165
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.630916060869758e-06,
+      "loss": 1.1497,
+      "step": 166
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.624661809643507e-06,
+      "loss": 1.1658,
+      "step": 167
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.618358546284646e-06,
+      "loss": 1.1281,
+      "step": 168
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.612006388498386e-06,
+      "loss": 1.124,
+      "step": 169
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.605605454902983e-06,
+      "loss": 1.0731,
+      "step": 170
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.599155865027513e-06,
+      "loss": 1.1296,
+      "step": 171
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.592657739309649e-06,
+      "loss": 1.1144,
+      "step": 172
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.5861111990934034e-06,
+      "loss": 1.1359,
+      "step": 173
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.579516366626867e-06,
+      "loss": 1.1321,
+      "step": 174
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.572873365059928e-06,
+      "loss": 1.1087,
+      "step": 175
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.5661823184419655e-06,
+      "loss": 1.0883,
+      "step": 176
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.559443351719542e-06,
+      "loss": 1.1151,
+      "step": 177
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.5526565907340604e-06,
+      "loss": 1.1163,
+      "step": 178
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.545822162219423e-06,
+      "loss": 1.1344,
+      "step": 179
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.538940193799659e-06,
+      "loss": 1.1188,
+      "step": 180
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.532010813986544e-06,
+      "loss": 1.084,
+      "step": 181
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.5250341521772e-06,
+      "loss": 1.1209,
+      "step": 182
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.518010338651676e-06,
+      "loss": 1.1116,
+      "step": 183
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.51093950457052e-06,
+      "loss": 1.1396,
+      "step": 184
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.5038217819723285e-06,
+      "loss": 1.1254,
+      "step": 185
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.496657303771276e-06,
+      "loss": 1.1158,
+      "step": 186
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.489446203754641e-06,
+      "loss": 1.162,
+      "step": 187
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.482188616580301e-06,
+      "loss": 1.1284,
+      "step": 188
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.4748846777742195e-06,
+      "loss": 1.1187,
+      "step": 189
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.467534523727921e-06,
+      "loss": 1.1254,
+      "step": 190
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.4601382916959355e-06,
+      "loss": 1.1071,
+      "step": 191
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.452696119793238e-06,
+      "loss": 1.1149,
+      "step": 192
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.445208146992674e-06,
+      "loss": 1.1392,
+      "step": 193
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.437674513122359e-06,
+      "loss": 1.1233,
+      "step": 194
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.43009535886307e-06,
+      "loss": 1.0951,
+      "step": 195
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.422470825745617e-06,
+      "loss": 1.0691,
+      "step": 196
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.414801056148203e-06,
+      "loss": 1.0983,
+      "step": 197
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.407086193293761e-06,
+      "loss": 1.1608,
+      "step": 198
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 5.399326381247282e-06,
+      "loss": 1.1355,
+      "step": 199
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 5.391521764913127e-06,
+      "loss": 1.1247,
+      "step": 200
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.383672490032313e-06,
+      "loss": 1.0917,
+      "step": 201
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.375778703179803e-06,
+      "loss": 1.1515,
+      "step": 202
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.3678405517617595e-06,
+      "loss": 1.1357,
+      "step": 203
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.359858184012799e-06,
+      "loss": 1.1481,
+      "step": 204
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.3518317489932144e-06,
+      "loss": 1.1765,
+      "step": 205
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.343761396586203e-06,
+      "loss": 1.1124,
+      "step": 206
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.335647277495057e-06,
+      "loss": 1.1391,
+      "step": 207
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.327489543240359e-06,
+      "loss": 1.113,
+      "step": 208
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5.3192883461571465e-06,
+      "loss": 1.1074,
+      "step": 209
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5.311043839392064e-06,
+      "loss": 1.1039,
+      "step": 210
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5.302756176900516e-06,
+      "loss": 1.1237,
+      "step": 211
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 5.294425513443777e-06,
+      "loss": 1.1101,
+      "step": 212
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 5.2860520045861104e-06,
+      "loss": 1.0947,
+      "step": 213
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.277635806691863e-06,
+      "loss": 1.1155,
+      "step": 214
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.2691770769225414e-06,
+      "loss": 1.1326,
+      "step": 215
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.260675973233882e-06,
+      "loss": 1.1411,
+      "step": 216
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 5.252132654372897e-06,
+      "loss": 1.112,
+      "step": 217
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 5.243547279874911e-06,
+      "loss": 1.1079,
+      "step": 218
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.234920010060586e-06,
+      "loss": 1.0891,
+      "step": 219
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.22625100603292e-06,
+      "loss": 1.1221,
+      "step": 220
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.217540429674246e-06,
+      "loss": 1.1151,
+      "step": 221
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.208788443643207e-06,
+      "loss": 1.1116,
+      "step": 222
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.1999952113717135e-06,
+      "loss": 1.0972,
+      "step": 223
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.191160897061898e-06,
+      "loss": 1.124,
+      "step": 224
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.1822856656830485e-06,
+      "loss": 1.1053,
+      "step": 225
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.173369682968522e-06,
+      "loss": 1.1473,
+      "step": 226
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.1644131154126544e-06,
+      "loss": 1.1131,
+      "step": 227
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.1554161302676544e-06,
+      "loss": 1.0935,
+      "step": 228
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.146378895540472e-06,
+      "loss": 1.0677,
+      "step": 229
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.137301579989665e-06,
+      "loss": 1.1269,
+      "step": 230
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.128184353122252e-06,
+      "loss": 1.0783,
+      "step": 231
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.119027385190542e-06,
+      "loss": 1.1059,
+      "step": 232
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.109830847188955e-06,
+      "loss": 1.0468,
+      "step": 233
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.100594910850832e-06,
+      "loss": 1.0851,
+      "step": 234
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.091319748645226e-06,
+      "loss": 1.0387,
+      "step": 235
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.082005533773682e-06,
+      "loss": 1.1361,
+      "step": 236
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.072652440167001e-06,
+      "loss": 1.1285,
+      "step": 237
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.063260642481997e-06,
+      "loss": 1.0934,
+      "step": 238
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.053830316098228e-06,
+      "loss": 1.1059,
+      "step": 239
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.044361637114729e-06,
+      "loss": 1.1031,
+      "step": 240
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.034854782346716e-06,
+      "loss": 1.0757,
+      "step": 241
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.0253099293222925e-06,
+      "loss": 1.1218,
+      "step": 242
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.015727256279126e-06,
+      "loss": 1.12,
+      "step": 243
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.0061069421611245e-06,
+      "loss": 1.0985,
+      "step": 244
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.996449166615094e-06,
+      "loss": 1.1192,
+      "step": 245
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.986754109987384e-06,
+      "loss": 1.0662,
+      "step": 246
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.97702195332052e-06,
+      "loss": 1.0671,
+      "step": 247
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.967252878349821e-06,
+      "loss": 1.1043,
+      "step": 248
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.9574470675000085e-06,
+      "loss": 1.1036,
+      "step": 249
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.947604703881797e-06,
+      "loss": 1.0729,
+      "step": 250
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.937725971288479e-06,
+      "loss": 1.1265,
+      "step": 251
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.927811054192486e-06,
+      "loss": 1.0854,
+      "step": 252
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.9178601377419506e-06,
+      "loss": 1.1334,
+      "step": 253
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.907873407757248e-06,
+      "loss": 1.1184,
+      "step": 254
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.89785105072752e-06,
+      "loss": 1.105,
+      "step": 255
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.8877932538072e-06,
+      "loss": 1.1124,
+      "step": 256
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.877700204812516e-06,
+      "loss": 1.0862,
+      "step": 257
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.867572092217977e-06,
+      "loss": 1.0856,
+      "step": 258
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.857409105152865e-06,
+      "loss": 1.0905,
+      "step": 259
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 777,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5.793364463679701e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153981e57a389e250d6774adce5af3d4ccd1412dc7f4b7a036cb0efa5434e600
+size 6584

zero_to_fp32.py

@@ -0,0 +1,587 @@
+#!/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):
+    """
+    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)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+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 _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()
+            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):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _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):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _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):
+    """
+    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``
+
+    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)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    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``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    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("-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)