Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "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": 131072,
+  "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": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.994994994994995,
+    "eval_loss": 1.367593765258789,
+    "eval_runtime": 17.9519,
+    "eval_samples_per_second": 6.183,
+    "eval_steps_per_second": 6.183
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.49.0"
+}

latest

@@ -0,0 +1 @@
+global_step1496

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b196524cbc421adf565c9cf6958ede2f61d43192e740f49526994bab4712443
+size 4865522496

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579a10a0d0a8660834f6afd2e52efe5b7cf5df85e65ba2695228f71528497eab
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ddf55ff614abb6401b8fb2eb14ac9c081b9ac26ce19ff239570965a9ccee81
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d904e73f3277ae743f97ccd7af2998c657c42529620dbebf4f5b148e8a5c6f6f
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6210a06a7c9787f01312bbaf0f6a0bcdbbf08266ef05675d40b9f0c726a12857
+size 4907496272

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "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"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c25e1b2d8ad42b7c8bd21cb9144fd371f9c347f00894a109bb865dcd893c82
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04fea7973d7269014fc457c2867d702a68b514f4362225b1a7efeba4a0a3d197
+size 1465

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

trainer_state.json

@@ -0,0 +1,1092 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.994994994994995,
+  "eval_steps": 500,
+  "global_step": 1497,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02002002002002002,
+      "grad_norm": 85.3724365234375,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 1.0542,
+      "step": 10
+    },
+    {
+      "epoch": 0.04004004004004004,
+      "grad_norm": 19.482826232910156,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.9033,
+      "step": 20
+    },
+    {
+      "epoch": 0.06006006006006006,
+      "grad_norm": 14.044015884399414,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.889,
+      "step": 30
+    },
+    {
+      "epoch": 0.08008008008008008,
+      "grad_norm": 16.23746681213379,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.8984,
+      "step": 40
+    },
+    {
+      "epoch": 0.1001001001001001,
+      "grad_norm": 19.264328002929688,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.076,
+      "step": 50
+    },
+    {
+      "epoch": 0.12012012012012012,
+      "grad_norm": 28.011310577392578,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.8041,
+      "step": 60
+    },
+    {
+      "epoch": 0.14014014014014015,
+      "grad_norm": 17.133804321289062,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.9156,
+      "step": 70
+    },
+    {
+      "epoch": 0.16016016016016016,
+      "grad_norm": 38.36112976074219,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.8373,
+      "step": 80
+    },
+    {
+      "epoch": 0.18018018018018017,
+      "grad_norm": 25.803749084472656,
+      "learning_rate": 6e-06,
+      "loss": 0.8105,
+      "step": 90
+    },
+    {
+      "epoch": 0.2002002002002002,
+      "grad_norm": 11.236152648925781,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9213,
+      "step": 100
+    },
+    {
+      "epoch": 0.22022022022022023,
+      "grad_norm": 11.80700397491455,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.8716,
+      "step": 110
+    },
+    {
+      "epoch": 0.24024024024024024,
+      "grad_norm": 46.683860778808594,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9531,
+      "step": 120
+    },
+    {
+      "epoch": 0.2602602602602603,
+      "grad_norm": 34.97478103637695,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.9266,
+      "step": 130
+    },
+    {
+      "epoch": 0.2802802802802803,
+      "grad_norm": 15.305174827575684,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 1.0951,
+      "step": 140
+    },
+    {
+      "epoch": 0.3003003003003003,
+      "grad_norm": 15.696242332458496,
+      "learning_rate": 1e-05,
+      "loss": 1.0434,
+      "step": 150
+    },
+    {
+      "epoch": 0.3203203203203203,
+      "grad_norm": 12.64402961730957,
+      "learning_rate": 9.998640169192487e-06,
+      "loss": 0.9082,
+      "step": 160
+    },
+    {
+      "epoch": 0.34034034034034033,
+      "grad_norm": 20.176891326904297,
+      "learning_rate": 9.994561416425877e-06,
+      "loss": 0.9433,
+      "step": 170
+    },
+    {
+      "epoch": 0.36036036036036034,
+      "grad_norm": 18.762786865234375,
+      "learning_rate": 9.987765960265639e-06,
+      "loss": 1.0805,
+      "step": 180
+    },
+    {
+      "epoch": 0.38038038038038036,
+      "grad_norm": 15.463565826416016,
+      "learning_rate": 9.978257496980025e-06,
+      "loss": 1.1743,
+      "step": 190
+    },
+    {
+      "epoch": 0.4004004004004004,
+      "grad_norm": 18.117294311523438,
+      "learning_rate": 9.966041198529562e-06,
+      "loss": 1.1714,
+      "step": 200
+    },
+    {
+      "epoch": 0.42042042042042044,
+      "grad_norm": 17.657556533813477,
+      "learning_rate": 9.95112370975384e-06,
+      "loss": 1.0502,
+      "step": 210
+    },
+    {
+      "epoch": 0.44044044044044045,
+      "grad_norm": 12.93178653717041,
+      "learning_rate": 9.933513144757187e-06,
+      "loss": 1.0316,
+      "step": 220
+    },
+    {
+      "epoch": 0.46046046046046046,
+      "grad_norm": 59.494056701660156,
+      "learning_rate": 9.913219082495128e-06,
+      "loss": 1.2795,
+      "step": 230
+    },
+    {
+      "epoch": 0.4804804804804805,
+      "grad_norm": 48.5118522644043,
+      "learning_rate": 9.890252561564094e-06,
+      "loss": 1.15,
+      "step": 240
+    },
+    {
+      "epoch": 0.5005005005005005,
+      "grad_norm": 11.185559272766113,
+      "learning_rate": 9.864626074197164e-06,
+      "loss": 1.3438,
+      "step": 250
+    },
+    {
+      "epoch": 0.5205205205205206,
+      "grad_norm": 15.397900581359863,
+      "learning_rate": 9.836353559469145e-06,
+      "loss": 1.1612,
+      "step": 260
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 15.821572303771973,
+      "learning_rate": 9.80545039571465e-06,
+      "loss": 1.5568,
+      "step": 270
+    },
+    {
+      "epoch": 0.5605605605605606,
+      "grad_norm": 15.897789001464844,
+      "learning_rate": 9.771933392163324e-06,
+      "loss": 1.0575,
+      "step": 280
+    },
+    {
+      "epoch": 0.5805805805805806,
+      "grad_norm": 9.421996116638184,
+      "learning_rate": 9.735820779796775e-06,
+      "loss": 1.1343,
+      "step": 290
+    },
+    {
+      "epoch": 0.6006006006006006,
+      "grad_norm": 16.344079971313477,
+      "learning_rate": 9.697132201432133e-06,
+      "loss": 1.1245,
+      "step": 300
+    },
+    {
+      "epoch": 0.6206206206206206,
+      "grad_norm": 18.52800178527832,
+      "learning_rate": 9.655888701037704e-06,
+      "loss": 1.2379,
+      "step": 310
+    },
+    {
+      "epoch": 0.6406406406406406,
+      "grad_norm": 18.442955017089844,
+      "learning_rate": 9.612112712286463e-06,
+      "loss": 0.9832,
+      "step": 320
+    },
+    {
+      "epoch": 0.6606606606606606,
+      "grad_norm": 15.195363998413086,
+      "learning_rate": 9.565828046353669e-06,
+      "loss": 1.115,
+      "step": 330
+    },
+    {
+      "epoch": 0.6806806806806807,
+      "grad_norm": 19.73291778564453,
+      "learning_rate": 9.517059878965177e-06,
+      "loss": 1.0119,
+      "step": 340
+    },
+    {
+      "epoch": 0.7007007007007007,
+      "grad_norm": 165.94976806640625,
+      "learning_rate": 9.465834736703565e-06,
+      "loss": 0.8088,
+      "step": 350
+    },
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 9.471101760864258,
+      "learning_rate": 9.41218048257946e-06,
+      "loss": 0.9265,
+      "step": 360
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 25.840486526489258,
+      "learning_rate": 9.356126300875947e-06,
+      "loss": 1.0758,
+      "step": 370
+    },
+    {
+      "epoch": 0.7607607607607607,
+      "grad_norm": 14.781391143798828,
+      "learning_rate": 9.297702681274294e-06,
+      "loss": 1.0414,
+      "step": 380
+    },
+    {
+      "epoch": 0.7807807807807807,
+      "grad_norm": 24.92754364013672,
+      "learning_rate": 9.23694140226963e-06,
+      "loss": 1.1561,
+      "step": 390
+    },
+    {
+      "epoch": 0.8008008008008008,
+      "grad_norm": 8.37315559387207,
+      "learning_rate": 9.173875513885592e-06,
+      "loss": 0.9872,
+      "step": 400
+    },
+    {
+      "epoch": 0.8208208208208209,
+      "grad_norm": 15.049481391906738,
+      "learning_rate": 9.10853931969735e-06,
+      "loss": 1.1482,
+      "step": 410
+    },
+    {
+      "epoch": 0.8408408408408409,
+      "grad_norm": 23.98802375793457,
+      "learning_rate": 9.040968358172787e-06,
+      "loss": 0.8824,
+      "step": 420
+    },
+    {
+      "epoch": 0.8608608608608609,
+      "grad_norm": 19.458723068237305,
+      "learning_rate": 8.971199383341972e-06,
+      "loss": 1.1417,
+      "step": 430
+    },
+    {
+      "epoch": 0.8808808808808809,
+      "grad_norm": 17.3590145111084,
+      "learning_rate": 8.89927034480546e-06,
+      "loss": 1.0421,
+      "step": 440
+    },
+    {
+      "epoch": 0.9009009009009009,
+      "grad_norm": 69.77664184570312,
+      "learning_rate": 8.82522036709227e-06,
+      "loss": 1.2733,
+      "step": 450
+    },
+    {
+      "epoch": 0.9209209209209209,
+      "grad_norm": 28.997215270996094,
+      "learning_rate": 8.7490897283788e-06,
+      "loss": 1.121,
+      "step": 460
+    },
+    {
+      "epoch": 0.9409409409409409,
+      "grad_norm": 10.64609146118164,
+      "learning_rate": 8.67091983858022e-06,
+      "loss": 1.2421,
+      "step": 470
+    },
+    {
+      "epoch": 0.960960960960961,
+      "grad_norm": 24.771728515625,
+      "learning_rate": 8.590753216826273e-06,
+      "loss": 1.1545,
+      "step": 480
+    },
+    {
+      "epoch": 0.980980980980981,
+      "grad_norm": 19.748878479003906,
+      "learning_rate": 8.50863346833376e-06,
+      "loss": 0.9979,
+      "step": 490
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 21.032365798950195,
+      "learning_rate": 8.42460526068824e-06,
+      "loss": 1.2302,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.2434757947921753,
+      "eval_runtime": 17.9994,
+      "eval_samples_per_second": 6.167,
+      "eval_steps_per_second": 6.167,
+      "step": 500
+    },
+    {
+      "epoch": 1.02002002002002,
+      "grad_norm": 8.104686737060547,
+      "learning_rate": 8.338714299547898e-06,
+      "loss": 0.5829,
+      "step": 510
+    },
+    {
+      "epoch": 1.04004004004004,
+      "grad_norm": 26.031190872192383,
+      "learning_rate": 8.251007303782754e-06,
+      "loss": 0.5962,
+      "step": 520
+    },
+    {
+      "epoch": 1.06006006006006,
+      "grad_norm": 10.554441452026367,
+      "learning_rate": 8.161531980062754e-06,
+      "loss": 0.5562,
+      "step": 530
+    },
+    {
+      "epoch": 1.08008008008008,
+      "grad_norm": 14.080601692199707,
+      "learning_rate": 8.070336996908585e-06,
+      "loss": 0.3213,
+      "step": 540
+    },
+    {
+      "epoch": 1.1001001001001,
+      "grad_norm": 8.222271919250488,
+      "learning_rate": 7.977471958219276e-06,
+      "loss": 0.4989,
+      "step": 550
+    },
+    {
+      "epoch": 1.12012012012012,
+      "grad_norm": 12.388670921325684,
+      "learning_rate": 7.882987376291051e-06,
+      "loss": 0.4506,
+      "step": 560
+    },
+    {
+      "epoch": 1.14014014014014,
+      "grad_norm": 13.545977592468262,
+      "learning_rate": 7.786934644342044e-06,
+      "loss": 0.3504,
+      "step": 570
+    },
+    {
+      "epoch": 1.16016016016016,
+      "grad_norm": 14.527294158935547,
+      "learning_rate": 7.689366008557879e-06,
+      "loss": 0.449,
+      "step": 580
+    },
+    {
+      "epoch": 1.1801801801801801,
+      "grad_norm": 15.87846851348877,
+      "learning_rate": 7.590334539673263e-06,
+      "loss": 0.6237,
+      "step": 590
+    },
+    {
+      "epoch": 1.2002002002002001,
+      "grad_norm": 34.297176361083984,
+      "learning_rate": 7.489894104105124e-06,
+      "loss": 0.4128,
+      "step": 600
+    },
+    {
+      "epoch": 1.2202202202202201,
+      "grad_norm": 27.035425186157227,
+      "learning_rate": 7.388099334652901e-06,
+      "loss": 0.5148,
+      "step": 610
+    },
+    {
+      "epoch": 1.2402402402402402,
+      "grad_norm": 28.68889045715332,
+      "learning_rate": 7.285005600782014e-06,
+      "loss": 0.499,
+      "step": 620
+    },
+    {
+      "epoch": 1.2602602602602602,
+      "grad_norm": 15.210294723510742,
+      "learning_rate": 7.180668978506613e-06,
+      "loss": 0.334,
+      "step": 630
+    },
+    {
+      "epoch": 1.2802802802802802,
+      "grad_norm": 10.216584205627441,
+      "learning_rate": 7.075146219888027e-06,
+      "loss": 0.5616,
+      "step": 640
+    },
+    {
+      "epoch": 1.3003003003003002,
+      "grad_norm": 5.705782413482666,
+      "learning_rate": 6.968494722165483e-06,
+      "loss": 0.5176,
+      "step": 650
+    },
+    {
+      "epoch": 1.3203203203203202,
+      "grad_norm": 14.276741027832031,
+      "learning_rate": 6.860772496535887e-06,
+      "loss": 0.3602,
+      "step": 660
+    },
+    {
+      "epoch": 1.3403403403403402,
+      "grad_norm": 33.196533203125,
+      "learning_rate": 6.752038136599663e-06,
+      "loss": 0.6254,
+      "step": 670
+    },
+    {
+      "epoch": 1.3603603603603602,
+      "grad_norm": 40.43268585205078,
+      "learning_rate": 6.642350786489809e-06,
+      "loss": 0.3451,
+      "step": 680
+    },
+    {
+      "epoch": 1.3803803803803802,
+      "grad_norm": 10.993099212646484,
+      "learning_rate": 6.531770108701467e-06,
+      "loss": 0.4373,
+      "step": 690
+    },
+    {
+      "epoch": 1.4004004004004005,
+      "grad_norm": 6.688507080078125,
+      "learning_rate": 6.42035625163959e-06,
+      "loss": 0.5468,
+      "step": 700
+    },
+    {
+      "epoch": 1.4204204204204205,
+      "grad_norm": 6.958929061889648,
+      "learning_rate": 6.3081698169022635e-06,
+      "loss": 0.4452,
+      "step": 710
+    },
+    {
+      "epoch": 1.4404404404404405,
+      "grad_norm": 5.645272731781006,
+      "learning_rate": 6.195271826317544e-06,
+      "loss": 0.4576,
+      "step": 720
+    },
+    {
+      "epoch": 1.4604604604604605,
+      "grad_norm": 7.839102268218994,
+      "learning_rate": 6.081723688751711e-06,
+      "loss": 0.5665,
+      "step": 730
+    },
+    {
+      "epoch": 1.4804804804804805,
+      "grad_norm": 13.920954704284668,
+      "learning_rate": 5.967587166707007e-06,
+      "loss": 0.3914,
+      "step": 740
+    },
+    {
+      "epoch": 1.5005005005005005,
+      "grad_norm": 5.867576599121094,
+      "learning_rate": 5.852924342727006e-06,
+      "loss": 0.651,
+      "step": 750
+    },
+    {
+      "epoch": 1.5205205205205206,
+      "grad_norm": 8.858614921569824,
+      "learning_rate": 5.737797585627918e-06,
+      "loss": 0.7602,
+      "step": 760
+    },
+    {
+      "epoch": 1.5405405405405406,
+      "grad_norm": 13.370222091674805,
+      "learning_rate": 5.62226951657417e-06,
+      "loss": 0.4655,
+      "step": 770
+    },
+    {
+      "epoch": 1.5605605605605606,
+      "grad_norm": 31.85508918762207,
+      "learning_rate": 5.506402975016738e-06,
+      "loss": 0.4276,
+      "step": 780
+    },
+    {
+      "epoch": 1.5805805805805806,
+      "grad_norm": 19.144956588745117,
+      "learning_rate": 5.390260984512728e-06,
+      "loss": 0.5327,
+      "step": 790
+    },
+    {
+      "epoch": 1.6006006006006006,
+      "grad_norm": 5.009524345397949,
+      "learning_rate": 5.273906718444834e-06,
+      "loss": 0.3488,
+      "step": 800
+    },
+    {
+      "epoch": 1.6206206206206206,
+      "grad_norm": 8.031986236572266,
+      "learning_rate": 5.15740346565929e-06,
+      "loss": 0.3583,
+      "step": 810
+    },
+    {
+      "epoch": 1.6406406406406406,
+      "grad_norm": 12.562287330627441,
+      "learning_rate": 5.0408145960410185e-06,
+      "loss": 0.3778,
+      "step": 820
+    },
+    {
+      "epoch": 1.6606606606606606,
+      "grad_norm": 15.383856773376465,
+      "learning_rate": 4.924203526044712e-06,
+      "loss": 0.4205,
+      "step": 830
+    },
+    {
+      "epoch": 1.6806806806806807,
+      "grad_norm": 37.331111907958984,
+      "learning_rate": 4.807633684200559e-06,
+      "loss": 0.4592,
+      "step": 840
+    },
+    {
+      "epoch": 1.7007007007007007,
+      "grad_norm": 3.9080111980438232,
+      "learning_rate": 4.691168476613426e-06,
+      "loss": 0.4791,
+      "step": 850
+    },
+    {
+      "epoch": 1.7207207207207207,
+      "grad_norm": 20.06818962097168,
+      "learning_rate": 4.574871252474227e-06,
+      "loss": 0.3267,
+      "step": 860
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 14.15330696105957,
+      "learning_rate": 4.458805269602245e-06,
+      "loss": 0.4908,
+      "step": 870
+    },
+    {
+      "epoch": 1.7607607607607607,
+      "grad_norm": 25.060203552246094,
+      "learning_rate": 4.34303366003717e-06,
+      "loss": 0.5989,
+      "step": 880
+    },
+    {
+      "epoch": 1.7807807807807807,
+      "grad_norm": 16.91396713256836,
+      "learning_rate": 4.227619395699523e-06,
+      "loss": 0.3807,
+      "step": 890
+    },
+    {
+      "epoch": 1.800800800800801,
+      "grad_norm": 9.745075225830078,
+      "learning_rate": 4.112625254138219e-06,
+      "loss": 0.4,
+      "step": 900
+    },
+    {
+      "epoch": 1.820820820820821,
+      "grad_norm": 26.580297470092773,
+      "learning_rate": 3.998113784383808e-06,
+      "loss": 0.3955,
+      "step": 910
+    },
+    {
+      "epoch": 1.840840840840841,
+      "grad_norm": 33.1876335144043,
+      "learning_rate": 3.8841472729260435e-06,
+      "loss": 0.6142,
+      "step": 920
+    },
+    {
+      "epoch": 1.860860860860861,
+      "grad_norm": 19.648466110229492,
+      "learning_rate": 3.7707877098342484e-06,
+      "loss": 0.4582,
+      "step": 930
+    },
+    {
+      "epoch": 1.880880880880881,
+      "grad_norm": 15.191150665283203,
+      "learning_rate": 3.65809675503891e-06,
+      "loss": 0.3308,
+      "step": 940
+    },
+    {
+      "epoch": 1.900900900900901,
+      "grad_norm": 23.23360252380371,
+      "learning_rate": 3.5461357047928522e-06,
+      "loss": 0.4302,
+      "step": 950
+    },
+    {
+      "epoch": 1.920920920920921,
+      "grad_norm": 4.980640888214111,
+      "learning_rate": 3.43496545833022e-06,
+      "loss": 0.4197,
+      "step": 960
+    },
+    {
+      "epoch": 1.940940940940941,
+      "grad_norm": 13.961352348327637,
+      "learning_rate": 3.3246464847414223e-06,
+      "loss": 0.3797,
+      "step": 970
+    },
+    {
+      "epoch": 1.960960960960961,
+      "grad_norm": 7.734709739685059,
+      "learning_rate": 3.2152387900820343e-06,
+      "loss": 0.3735,
+      "step": 980
+    },
+    {
+      "epoch": 1.980980980980981,
+      "grad_norm": 4.623331546783447,
+      "learning_rate": 3.106801884733566e-06,
+      "loss": 0.3805,
+      "step": 990
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 25.117450714111328,
+      "learning_rate": 2.9993947510338438e-06,
+      "loss": 0.3607,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.321751594543457,
+      "eval_runtime": 18.4065,
+      "eval_samples_per_second": 6.03,
+      "eval_steps_per_second": 6.03,
+      "step": 1000
+    },
+    {
+      "epoch": 2.02002002002002,
+      "grad_norm": 5.904636383056641,
+      "learning_rate": 2.8930758111946117e-06,
+      "loss": 0.2806,
+      "step": 1010
+    },
+    {
+      "epoch": 2.04004004004004,
+      "grad_norm": 32.370277404785156,
+      "learning_rate": 2.7879028955237887e-06,
+      "loss": 0.2025,
+      "step": 1020
+    },
+    {
+      "epoch": 2.06006006006006,
+      "grad_norm": 24.176109313964844,
+      "learning_rate": 2.683933210969718e-06,
+      "loss": 0.3624,
+      "step": 1030
+    },
+    {
+      "epoch": 2.08008008008008,
+      "grad_norm": 3.880007266998291,
+      "learning_rate": 2.58122331000444e-06,
+      "loss": 0.1176,
+      "step": 1040
+    },
+    {
+      "epoch": 2.1001001001001,
+      "grad_norm": 7.256086826324463,
+      "learning_rate": 2.4798290598629826e-06,
+      "loss": 0.121,
+      "step": 1050
+    },
+    {
+      "epoch": 2.12012012012012,
+      "grad_norm": 3.795654535293579,
+      "learning_rate": 2.3798056121553646e-06,
+      "loss": 0.1519,
+      "step": 1060
+    },
+    {
+      "epoch": 2.14014014014014,
+      "grad_norm": 16.733631134033203,
+      "learning_rate": 2.2812073728678525e-06,
+      "loss": 0.1601,
+      "step": 1070
+    },
+    {
+      "epoch": 2.16016016016016,
+      "grad_norm": 4.601969242095947,
+      "learning_rate": 2.184087972769786e-06,
+      "loss": 0.1254,
+      "step": 1080
+    },
+    {
+      "epoch": 2.18018018018018,
+      "grad_norm": 16.99506378173828,
+      "learning_rate": 2.0885002382420695e-06,
+      "loss": 0.2021,
+      "step": 1090
+    },
+    {
+      "epoch": 2.2002002002002,
+      "grad_norm": 3.1727092266082764,
+      "learning_rate": 1.9944961625431954e-06,
+      "loss": 0.1348,
+      "step": 1100
+    },
+    {
+      "epoch": 2.22022022022022,
+      "grad_norm": 4.597020626068115,
+      "learning_rate": 1.9021268775284301e-06,
+      "loss": 0.148,
+      "step": 1110
+    },
+    {
+      "epoch": 2.24024024024024,
+      "grad_norm": 25.738351821899414,
+      "learning_rate": 1.8114426258375473e-06,
+      "loss": 0.4416,
+      "step": 1120
+    },
+    {
+      "epoch": 2.26026026026026,
+      "grad_norm": 10.155012130737305,
+      "learning_rate": 1.722492733566226e-06,
+      "loss": 0.1879,
+      "step": 1130
+    },
+    {
+      "epoch": 2.28028028028028,
+      "grad_norm": 6.9975409507751465,
+      "learning_rate": 1.635325583436005e-06,
+      "loss": 0.1471,
+      "step": 1140
+    },
+    {
+      "epoch": 2.3003003003003,
+      "grad_norm": 7.446280002593994,
+      "learning_rate": 1.5499885884773436e-06,
+      "loss": 0.1164,
+      "step": 1150
+    },
+    {
+      "epoch": 2.32032032032032,
+      "grad_norm": 5.518588066101074,
+      "learning_rate": 1.4665281662401454e-06,
+      "loss": 0.1355,
+      "step": 1160
+    },
+    {
+      "epoch": 2.34034034034034,
+      "grad_norm": 6.030386924743652,
+      "learning_rate": 1.3849897135457574e-06,
+      "loss": 0.1302,
+      "step": 1170
+    },
+    {
+      "epoch": 2.3603603603603602,
+      "grad_norm": 4.593402862548828,
+      "learning_rate": 1.3054175817941677e-06,
+      "loss": 0.1307,
+      "step": 1180
+    },
+    {
+      "epoch": 2.3803803803803802,
+      "grad_norm": 10.065942764282227,
+      "learning_rate": 1.2278550528398486e-06,
+      "loss": 0.119,
+      "step": 1190
+    },
+    {
+      "epoch": 2.4004004004004003,
+      "grad_norm": 5.5326619148254395,
+      "learning_rate": 1.1523443154493509e-06,
+      "loss": 0.1194,
+      "step": 1200
+    },
+    {
+      "epoch": 2.4204204204204203,
+      "grad_norm": 13.280714988708496,
+      "learning_rate": 1.0789264423534757e-06,
+      "loss": 0.2006,
+      "step": 1210
+    },
+    {
+      "epoch": 2.4404404404404403,
+      "grad_norm": 2.77651309967041,
+      "learning_rate": 1.0076413679064857e-06,
+      "loss": 0.1594,
+      "step": 1220
+    },
+    {
+      "epoch": 2.4604604604604603,
+      "grad_norm": 5.999819278717041,
+      "learning_rate": 9.385278663645209e-07,
+      "loss": 0.3126,
+      "step": 1230
+    },
+    {
+      "epoch": 2.4804804804804803,
+      "grad_norm": 8.069478034973145,
+      "learning_rate": 8.716235307950255e-07,
+      "loss": 0.2226,
+      "step": 1240
+    },
+    {
+      "epoch": 2.5005005005005003,
+      "grad_norm": 12.986360549926758,
+      "learning_rate": 8.069647526286656e-07,
+      "loss": 0.1229,
+      "step": 1250
+    },
+    {
+      "epoch": 2.5205205205205203,
+      "grad_norm": 8.093034744262695,
+      "learning_rate": 7.445867018648517e-07,
+      "loss": 0.1374,
+      "step": 1260
+    },
+    {
+      "epoch": 2.5405405405405403,
+      "grad_norm": 3.4107353687286377,
+      "learning_rate": 6.845233079416397e-07,
+      "loss": 0.117,
+      "step": 1270
+    },
+    {
+      "epoch": 2.5605605605605604,
+      "grad_norm": 4.261966705322266,
+      "learning_rate": 6.268072412804138e-07,
+      "loss": 0.1725,
+      "step": 1280
+    },
+    {
+      "epoch": 2.5805805805805804,
+      "grad_norm": 5.60800838470459,
+      "learning_rate": 5.714698955153897e-07,
+      "loss": 0.1813,
+      "step": 1290
+    },
+    {
+      "epoch": 2.6006006006006004,
+      "grad_norm": 8.807952880859375,
+      "learning_rate": 5.185413704175963e-07,
+      "loss": 0.1745,
+      "step": 1300
+    },
+    {
+      "epoch": 2.6206206206206204,
+      "grad_norm": 5.851156234741211,
+      "learning_rate": 4.6805045552264397e-07,
+      "loss": 0.1793,
+      "step": 1310
+    },
+    {
+      "epoch": 2.6406406406406404,
+      "grad_norm": 22.0322322845459,
+      "learning_rate": 4.2002461447116174e-07,
+      "loss": 0.2279,
+      "step": 1320
+    },
+    {
+      "epoch": 2.6606606606606604,
+      "grad_norm": 6.453255653381348,
+      "learning_rate": 3.7448997007043684e-07,
+      "loss": 0.132,
+      "step": 1330
+    },
+    {
+      "epoch": 2.6806806806806804,
+      "grad_norm": 12.178539276123047,
+      "learning_rate": 3.314712900853767e-07,
+      "loss": 0.1058,
+      "step": 1340
+    },
+    {
+      "epoch": 2.7007007007007005,
+      "grad_norm": 10.403335571289062,
+      "learning_rate": 2.909919737665179e-07,
+      "loss": 0.1642,
+      "step": 1350
+    },
+    {
+      "epoch": 2.7207207207207205,
+      "grad_norm": 3.435100793838501,
+      "learning_rate": 2.53074039122419e-07,
+      "loss": 0.1115,
+      "step": 1360
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 12.800907135009766,
+      "learning_rate": 2.177381109433535e-07,
+      "loss": 0.1716,
+      "step": 1370
+    },
+    {
+      "epoch": 2.7607607607607605,
+      "grad_norm": 9.72323226928711,
+      "learning_rate": 1.8500340958282292e-07,
+      "loss": 0.1695,
+      "step": 1380
+    },
+    {
+      "epoch": 2.7807807807807805,
+      "grad_norm": 17.054372787475586,
+      "learning_rate": 1.5488774050298083e-07,
+      "loss": 0.2744,
+      "step": 1390
+    },
+    {
+      "epoch": 2.800800800800801,
+      "grad_norm": 8.085247993469238,
+      "learning_rate": 1.2740748458966834e-07,
+      "loss": 0.1364,
+      "step": 1400
+    },
+    {
+      "epoch": 2.820820820820821,
+      "grad_norm": 4.367096424102783,
+      "learning_rate": 1.0257758924232142e-07,
+      "loss": 0.2643,
+      "step": 1410
+    },
+    {
+      "epoch": 2.840840840840841,
+      "grad_norm": 3.3376331329345703,
+      "learning_rate": 8.04115602435962e-08,
+      "loss": 0.1234,
+      "step": 1420
+    },
+    {
+      "epoch": 2.860860860860861,
+      "grad_norm": 215.3577423095703,
+      "learning_rate": 6.092145441313757e-08,
+      "loss": 1.156,
+      "step": 1430
+    },
+    {
+      "epoch": 2.880880880880881,
+      "grad_norm": 2.81681489944458,
+      "learning_rate": 4.411787304948567e-08,
+      "loss": 0.1531,
+      "step": 1440
+    },
+    {
+      "epoch": 2.900900900900901,
+      "grad_norm": 15.65246295928955,
+      "learning_rate": 3.000995616368685e-08,
+      "loss": 0.1828,
+      "step": 1450
+    },
+    {
+      "epoch": 2.920920920920921,
+      "grad_norm": 8.164206504821777,
+      "learning_rate": 1.860537750774549e-08,
+      "loss": 0.1498,
+      "step": 1460
+    },
+    {
+      "epoch": 2.940940940940941,
+      "grad_norm": 3.0739083290100098,
+      "learning_rate": 9.910340400621777e-09,
+      "loss": 0.1659,
+      "step": 1470
+    },
+    {
+      "epoch": 2.960960960960961,
+      "grad_norm": 6.969380855560303,
+      "learning_rate": 3.929574354049614e-09,
+      "loss": 0.0964,
+      "step": 1480
+    },
+    {
+      "epoch": 2.980980980980981,
+      "grad_norm": 11.09949779510498,
+      "learning_rate": 6.663324999967024e-10,
+      "loss": 0.1811,
+      "step": 1490
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1497,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4689647124480.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ebdb802368b97aab5fa24a166376243f20077914e0e68821ec7b56f2c26d84
+size 8017

upload.py

@@ -0,0 +1,31 @@
+from huggingface_hub import HfApi
+import os
+
+# Set the correct repository name
+repo_id = "AlexCuadron/chai-sft-12b"  # Using the correct case
+model_path = "./"
+
+# Create API client
+api = HfApi()
+
+# First, create the repository if it doesn't exist
+print(f"Creating repository {repo_id}...")
+try:
+    api.create_repo(
+        repo_id=repo_id,
+        repo_type="model",
+        private=False  # Set to True if you want a private repository
+    )
+    print(f"Repository {repo_id} created successfully!")
+except Exception as e:
+    print(f"Note: {e}")
+    print("Continuing with upload as the repo might already exist...")
+
+# Then upload the model
+print(f"Starting upload to {repo_id}...")
+api.upload_folder(
+    folder_path=model_path,
+    repo_id=repo_id,
+    repo_type="model"
+)
+print("Upload completed successfully!")

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)