Upload folder using huggingface_hub

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/mnt/data/tungtran/output_model/irish_llama2_data_v3/checkpoint-2200",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 35483
+}

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/latest

@@ -0,0 +1 @@
+global_step320

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e5a044356bbdf5774eb8eb2e18dde92a4c6508c08042e51af2387a635e0746
+size 4961502800

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfbb2285fb8b265a194d459e5b9a345114eee6f859829305c7c5ab23baad94b6
+size 4970422232

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce465f343e4d6c21ae15d503cb49a7539500cd406f860109ffb1bdacce216db1
+size 4881272584

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec73ea6a98693f367005f19b9abb6765d2683c4ee74bce0e7e68a1fc84fdd83
+size 4933722216

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f560502c24eab89c10e578b6366d47b29c4ced093e5c606ecc750c97cab7f1
+size 4933722208

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603be40781db4a014228ab0bd322b619ea341cbdd637c7f167c7882fd31bea2a
+size 1422460712

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26103060480
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4639c63dd87ac33e45e3023adf278d225bcd84f3716bdf300ca937d7c28411
+size 15920

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98634ab74d1b6c3b107bd223d174aa7e02fd4a2b2d6101ecebdd4176f2c84f5
+size 15920

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4f75d8f1f8239b80b7fbf53b019cce45e362f7b71af64e66d404070bc686bf
+size 15920

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9404b8ac4a720bcb8b487c880ce34d3ff2b170ed00e374f27c80aef144a04a
+size 15920

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc4dd7a62d55ce80ab99ebc1759af8a1c5eb33377a107a7f9165349321b7d10
+size 15920

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:769d4f3f169a4b113287ed32b16e0940c67525bc8f3f98a0880e7404af13a165
+size 15920

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c8b24910d22e122e4179c4725875248c943a60476d9e2f4ffc14d84853698f
+size 15920

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a18f30295c7ca7ec4d2dc6672effd06c2fc171a24d9333361d84ca8bab9f91
+size 15920

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72be698b9c4e40fb7b67b10930efb49013ddcd75caaf62453ef62aa652244b7e
+size 1064

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/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
+  }
+}

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1f5d0342153f3e3bbb37b2026ba64d0b25583df351345f87cd8b9a5658c2fb
+size 558602

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/trainer_state.json

@@ -0,0 +1,1160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 320,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0125,
+      "grad_norm": 1.001694627324715,
+      "learning_rate": 6.25e-06,
+      "loss": 1.636,
+      "step": 1
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 1.1232886991122528,
+      "learning_rate": 1.25e-05,
+      "loss": 1.6567,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.30256479728273195,
+      "learning_rate": 2.5e-05,
+      "loss": 1.5177,
+      "step": 4
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.4658390417272426,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.3463,
+      "step": 6
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.21524068836984556,
+      "learning_rate": 5e-05,
+      "loss": 1.2869,
+      "step": 8
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.1290773408678012,
+      "learning_rate": 6.25e-05,
+      "loss": 1.2252,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1305532990433957,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.2042,
+      "step": 12
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.10470705468003734,
+      "learning_rate": 8.75e-05,
+      "loss": 1.1671,
+      "step": 14
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.09317869840175187,
+      "learning_rate": 0.0001,
+      "loss": 1.1348,
+      "step": 16
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.09202927639770621,
+      "learning_rate": 9.998932083939656e-05,
+      "loss": 1.0887,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.09563130912564372,
+      "learning_rate": 9.995728791936504e-05,
+      "loss": 1.0863,
+      "step": 20
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.09781477340327718,
+      "learning_rate": 9.990391492329341e-05,
+      "loss": 1.0505,
+      "step": 22
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.10054753783481035,
+      "learning_rate": 9.98292246503335e-05,
+      "loss": 1.038,
+      "step": 24
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.11771731267013749,
+      "learning_rate": 9.973324900566213e-05,
+      "loss": 1.0093,
+      "step": 26
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.07920039599178107,
+      "learning_rate": 9.961602898685226e-05,
+      "loss": 0.9599,
+      "step": 28
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.08754297025513495,
+      "learning_rate": 9.947761466636014e-05,
+      "loss": 0.9471,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.09077767050752232,
+      "learning_rate": 9.931806517013612e-05,
+      "loss": 0.9325,
+      "step": 32
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.07971857143163262,
+      "learning_rate": 9.913744865236798e-05,
+      "loss": 0.9195,
+      "step": 34
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.09330919417037573,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.8926,
+      "step": 36
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.09091187419808079,
+      "learning_rate": 9.871333213161438e-05,
+      "loss": 0.8811,
+      "step": 38
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.07814948556942038,
+      "learning_rate": 9.847001329696653e-05,
+      "loss": 0.8259,
+      "step": 40
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.0885696745070737,
+      "learning_rate": 9.820598970006069e-05,
+      "loss": 0.8208,
+      "step": 42
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.11527129492074112,
+      "learning_rate": 9.792137412291265e-05,
+      "loss": 0.7918,
+      "step": 44
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.11420680118812855,
+      "learning_rate": 9.761628814374073e-05,
+      "loss": 0.7764,
+      "step": 46
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.11627802945679176,
+      "learning_rate": 9.729086208503174e-05,
+      "loss": 0.7509,
+      "step": 48
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.09434304905330852,
+      "learning_rate": 9.694523495787149e-05,
+      "loss": 0.7338,
+      "step": 50
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.09146753352106175,
+      "learning_rate": 9.657955440256395e-05,
+      "loss": 0.6889,
+      "step": 52
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.11646616606039249,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6962,
+      "step": 54
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.1114311656394847,
+      "learning_rate": 9.578866633275288e-05,
+      "loss": 0.6692,
+      "step": 56
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.0987205616293445,
+      "learning_rate": 9.5363796659078e-05,
+      "loss": 0.6304,
+      "step": 58
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.10525188568247712,
+      "learning_rate": 9.491954909459895e-05,
+      "loss": 0.6277,
+      "step": 60
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.10335096582160389,
+      "learning_rate": 9.445611340695926e-05,
+      "loss": 0.5979,
+      "step": 62
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.09601224680804481,
+      "learning_rate": 9.397368756032445e-05,
+      "loss": 0.5705,
+      "step": 64
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.11665075197978235,
+      "learning_rate": 9.347247763081835e-05,
+      "loss": 0.5553,
+      "step": 66
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.17718968531566173,
+      "learning_rate": 9.295269771849427e-05,
+      "loss": 0.5239,
+      "step": 68
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.12563855755365627,
+      "learning_rate": 9.241456985587868e-05,
+      "loss": 0.5232,
+      "step": 70
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.16275531232300422,
+      "learning_rate": 9.185832391312644e-05,
+      "loss": 0.4977,
+      "step": 72
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.15831678407865832,
+      "learning_rate": 9.12841974998278e-05,
+      "loss": 0.4823,
+      "step": 74
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.13418888602939597,
+      "learning_rate": 9.069243586350975e-05,
+      "loss": 0.4665,
+      "step": 76
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.14029302212481656,
+      "learning_rate": 9.008329178487442e-05,
+      "loss": 0.4309,
+      "step": 78
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13080984306217305,
+      "learning_rate": 8.945702546981969e-05,
+      "loss": 0.4144,
+      "step": 80
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 0.1716051837075901,
+      "learning_rate": 8.881390443828787e-05,
+      "loss": 0.2687,
+      "step": 82
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.12051065792645782,
+      "learning_rate": 8.815420340999033e-05,
+      "loss": 0.2484,
+      "step": 84
+    },
+    {
+      "epoch": 1.075,
+      "grad_norm": 0.1331773298071305,
+      "learning_rate": 8.74782041870563e-05,
+      "loss": 0.2316,
+      "step": 86
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.09086971507936274,
+      "learning_rate": 8.678619553365659e-05,
+      "loss": 0.2152,
+      "step": 88
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.10120733178425682,
+      "learning_rate": 8.60784730526531e-05,
+      "loss": 0.2195,
+      "step": 90
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.07559304119756692,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.2092,
+      "step": 92
+    },
+    {
+      "epoch": 1.175,
+      "grad_norm": 0.0700251183868583,
+      "learning_rate": 8.461710245224148e-05,
+      "loss": 0.2087,
+      "step": 94
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.07733361851858198,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 0.2003,
+      "step": 96
+    },
+    {
+      "epoch": 1.225,
+      "grad_norm": 0.06936595290783064,
+      "learning_rate": 8.309658911297834e-05,
+      "loss": 0.205,
+      "step": 98
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.07214457895226337,
+      "learning_rate": 8.231496189304704e-05,
+      "loss": 0.1916,
+      "step": 100
+    },
+    {
+      "epoch": 1.275,
+      "grad_norm": 0.07972049863157102,
+      "learning_rate": 8.151953080639775e-05,
+      "loss": 0.1842,
+      "step": 102
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.0678370243606489,
+      "learning_rate": 8.07106356344834e-05,
+      "loss": 0.2015,
+      "step": 104
+    },
+    {
+      "epoch": 1.325,
+      "grad_norm": 0.06355327798399048,
+      "learning_rate": 7.988862191016205e-05,
+      "loss": 0.1739,
+      "step": 106
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.06793476682915373,
+      "learning_rate": 7.905384077009693e-05,
+      "loss": 0.1979,
+      "step": 108
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.06479689090271346,
+      "learning_rate": 7.820664880476256e-05,
+      "loss": 0.1722,
+      "step": 110
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.06872666246517939,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 0.1639,
+      "step": 112
+    },
+    {
+      "epoch": 1.425,
+      "grad_norm": 0.06601551408324573,
+      "learning_rate": 7.647648511303544e-05,
+      "loss": 0.1574,
+      "step": 114
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.06324892382211052,
+      "learning_rate": 7.559425245448006e-05,
+      "loss": 0.1609,
+      "step": 116
+    },
+    {
+      "epoch": 1.475,
+      "grad_norm": 0.056937237831200214,
+      "learning_rate": 7.470108679062521e-05,
+      "loss": 0.1589,
+      "step": 118
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.05372959808134079,
+      "learning_rate": 7.379736965185368e-05,
+      "loss": 0.165,
+      "step": 120
+    },
+    {
+      "epoch": 1.525,
+      "grad_norm": 0.050807581441291834,
+      "learning_rate": 7.288348707578408e-05,
+      "loss": 0.1655,
+      "step": 122
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.05154835426969918,
+      "learning_rate": 7.195982944236851e-05,
+      "loss": 0.1576,
+      "step": 124
+    },
+    {
+      "epoch": 1.575,
+      "grad_norm": 0.058296170975419254,
+      "learning_rate": 7.102679130713537e-05,
+      "loss": 0.1474,
+      "step": 126
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.047503910224261196,
+      "learning_rate": 7.008477123264848e-05,
+      "loss": 0.15,
+      "step": 128
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.04885400630069184,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1398,
+      "step": 130
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.056761777137180336,
+      "learning_rate": 6.817539852819149e-05,
+      "loss": 0.1642,
+      "step": 132
+    },
+    {
+      "epoch": 1.675,
+      "grad_norm": 0.045569753914067236,
+      "learning_rate": 6.720886151813194e-05,
+      "loss": 0.1381,
+      "step": 134
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.04690592784785931,
+      "learning_rate": 6.623497346023418e-05,
+      "loss": 0.1435,
+      "step": 136
+    },
+    {
+      "epoch": 1.725,
+      "grad_norm": 0.04713745634435082,
+      "learning_rate": 6.525415036677744e-05,
+      "loss": 0.1319,
+      "step": 138
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.04503944493700146,
+      "learning_rate": 6.426681121245527e-05,
+      "loss": 0.128,
+      "step": 140
+    },
+    {
+      "epoch": 1.775,
+      "grad_norm": 0.04747702878359576,
+      "learning_rate": 6.327337775540362e-05,
+      "loss": 0.1366,
+      "step": 142
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.04364714218227801,
+      "learning_rate": 6.227427435703997e-05,
+      "loss": 0.13,
+      "step": 144
+    },
+    {
+      "epoch": 1.825,
+      "grad_norm": 0.04395461532437832,
+      "learning_rate": 6.126992780079031e-05,
+      "loss": 0.1373,
+      "step": 146
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.04928547488841982,
+      "learning_rate": 6.026076710978171e-05,
+      "loss": 0.1221,
+      "step": 148
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.043656495356946795,
+      "learning_rate": 5.924722336357793e-05,
+      "loss": 0.1157,
+      "step": 150
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.0456896816676112,
+      "learning_rate": 5.8229729514036705e-05,
+      "loss": 0.1334,
+      "step": 152
+    },
+    {
+      "epoch": 1.925,
+      "grad_norm": 0.9649846981742741,
+      "learning_rate": 5.720872020036734e-05,
+      "loss": 0.1512,
+      "step": 154
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.042819929229098184,
+      "learning_rate": 5.618463156346739e-05,
+      "loss": 0.1183,
+      "step": 156
+    },
+    {
+      "epoch": 1.975,
+      "grad_norm": 0.04425179814586883,
+      "learning_rate": 5.515790105961786e-05,
+      "loss": 0.1169,
+      "step": 158
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1568815116859502,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 0.1398,
+      "step": 160
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 0.04736859283207987,
+      "learning_rate": 5.3098269731429736e-05,
+      "loss": 0.0649,
+      "step": 162
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 1.0009419802762844,
+      "learning_rate": 5.2066248712440656e-05,
+      "loss": 0.0676,
+      "step": 164
+    },
+    {
+      "epoch": 2.075,
+      "grad_norm": 0.10084215910400005,
+      "learning_rate": 5.103334506137772e-05,
+      "loss": 0.0729,
+      "step": 166
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.05492736250059767,
+      "learning_rate": 5e-05,
+      "loss": 0.0652,
+      "step": 168
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.041812562536590804,
+      "learning_rate": 4.8966654938622295e-05,
+      "loss": 0.0687,
+      "step": 170
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.05580872609288073,
+      "learning_rate": 4.7933751287559335e-05,
+      "loss": 0.0667,
+      "step": 172
+    },
+    {
+      "epoch": 2.175,
+      "grad_norm": 0.056542636206061606,
+      "learning_rate": 4.6901730268570275e-05,
+      "loss": 0.068,
+      "step": 174
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.04274229535119481,
+      "learning_rate": 4.5871032726383386e-05,
+      "loss": 0.0646,
+      "step": 176
+    },
+    {
+      "epoch": 2.225,
+      "grad_norm": 0.03831634022116529,
+      "learning_rate": 4.4842098940382155e-05,
+      "loss": 0.0649,
+      "step": 178
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.03778729638405323,
+      "learning_rate": 4.381536843653262e-05,
+      "loss": 0.0694,
+      "step": 180
+    },
+    {
+      "epoch": 2.275,
+      "grad_norm": 0.037105014536606744,
+      "learning_rate": 4.2791279799632666e-05,
+      "loss": 0.0678,
+      "step": 182
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.15684820491799406,
+      "learning_rate": 4.17702704859633e-05,
+      "loss": 0.103,
+      "step": 184
+    },
+    {
+      "epoch": 2.325,
+      "grad_norm": 0.03508902044155104,
+      "learning_rate": 4.075277663642208e-05,
+      "loss": 0.0643,
+      "step": 186
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.03348567296124864,
+      "learning_rate": 3.973923289021829e-05,
+      "loss": 0.0625,
+      "step": 188
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.03377745940251335,
+      "learning_rate": 3.87300721992097e-05,
+      "loss": 0.0674,
+      "step": 190
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.0351480774964804,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.0703,
+      "step": 192
+    },
+    {
+      "epoch": 2.425,
+      "grad_norm": 0.03389355898841613,
+      "learning_rate": 3.67266222445964e-05,
+      "loss": 0.0651,
+      "step": 194
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.030418411095335357,
+      "learning_rate": 3.5733188787544745e-05,
+      "loss": 0.0632,
+      "step": 196
+    },
+    {
+      "epoch": 2.475,
+      "grad_norm": 0.03464427979939839,
+      "learning_rate": 3.474584963322257e-05,
+      "loss": 0.0644,
+      "step": 198
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.030643080647599654,
+      "learning_rate": 3.3765026539765834e-05,
+      "loss": 0.0679,
+      "step": 200
+    },
+    {
+      "epoch": 2.525,
+      "grad_norm": 0.03319708430316191,
+      "learning_rate": 3.279113848186808e-05,
+      "loss": 0.0649,
+      "step": 202
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.03190646162558671,
+      "learning_rate": 3.18246014718085e-05,
+      "loss": 0.0694,
+      "step": 204
+    },
+    {
+      "epoch": 2.575,
+      "grad_norm": 0.03746679307525109,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0719,
+      "step": 206
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.029716218419465028,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 0.0604,
+      "step": 208
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.035100514903198446,
+      "learning_rate": 2.8973208692864624e-05,
+      "loss": 0.0692,
+      "step": 210
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.03413102367589507,
+      "learning_rate": 2.804017055763149e-05,
+      "loss": 0.0692,
+      "step": 212
+    },
+    {
+      "epoch": 2.675,
+      "grad_norm": 0.03636401730461719,
+      "learning_rate": 2.711651292421593e-05,
+      "loss": 0.0679,
+      "step": 214
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.03107466842244076,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 0.0621,
+      "step": 216
+    },
+    {
+      "epoch": 2.725,
+      "grad_norm": 0.036834702525337576,
+      "learning_rate": 2.529891320937481e-05,
+      "loss": 0.0698,
+      "step": 218
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.04645751316114215,
+      "learning_rate": 2.4405747545519963e-05,
+      "loss": 0.0648,
+      "step": 220
+    },
+    {
+      "epoch": 2.775,
+      "grad_norm": 0.028015969012530832,
+      "learning_rate": 2.352351488696457e-05,
+      "loss": 0.0588,
+      "step": 222
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.03525853228544041,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.0631,
+      "step": 224
+    },
+    {
+      "epoch": 2.825,
+      "grad_norm": 0.028959437202259703,
+      "learning_rate": 2.179335119523745e-05,
+      "loss": 0.0619,
+      "step": 226
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.027213618352209,
+      "learning_rate": 2.094615922990309e-05,
+      "loss": 0.0609,
+      "step": 228
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.02956846014413412,
+      "learning_rate": 2.0111378089837956e-05,
+      "loss": 0.0602,
+      "step": 230
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.028745535223261443,
+      "learning_rate": 1.928936436551661e-05,
+      "loss": 0.059,
+      "step": 232
+    },
+    {
+      "epoch": 2.925,
+      "grad_norm": 0.025725337055887934,
+      "learning_rate": 1.848046919360225e-05,
+      "loss": 0.0558,
+      "step": 234
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.03383514185440608,
+      "learning_rate": 1.768503810695295e-05,
+      "loss": 0.0614,
+      "step": 236
+    },
+    {
+      "epoch": 2.975,
+      "grad_norm": 0.02889459674020087,
+      "learning_rate": 1.6903410887021676e-05,
+      "loss": 0.0605,
+      "step": 238
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.025519223360493788,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 0.0595,
+      "step": 240
+    },
+    {
+      "epoch": 3.025,
+      "grad_norm": 0.027927636643276393,
+      "learning_rate": 1.5382897547758514e-05,
+      "loss": 0.0402,
+      "step": 242
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.024727586967036863,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0407,
+      "step": 244
+    },
+    {
+      "epoch": 3.075,
+      "grad_norm": 0.023660905030289225,
+      "learning_rate": 1.3921526947346902e-05,
+      "loss": 0.0392,
+      "step": 246
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.027883658494279227,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 0.0392,
+      "step": 248
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.0331184112060815,
+      "learning_rate": 1.2521795812943704e-05,
+      "loss": 0.0414,
+      "step": 250
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.02639223340759259,
+      "learning_rate": 1.1845796590009683e-05,
+      "loss": 0.0375,
+      "step": 252
+    },
+    {
+      "epoch": 3.175,
+      "grad_norm": 0.021297372430376865,
+      "learning_rate": 1.118609556171213e-05,
+      "loss": 0.0384,
+      "step": 254
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.02148458164678564,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.0363,
+      "step": 256
+    },
+    {
+      "epoch": 3.225,
+      "grad_norm": 0.026799613113537294,
+      "learning_rate": 9.916708215125587e-06,
+      "loss": 0.0374,
+      "step": 258
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.08445918521522447,
+      "learning_rate": 9.307564136490254e-06,
+      "loss": 0.0401,
+      "step": 260
+    },
+    {
+      "epoch": 3.275,
+      "grad_norm": 0.03221306732202585,
+      "learning_rate": 8.715802500172216e-06,
+      "loss": 0.0395,
+      "step": 262
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.023029085003687944,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.0384,
+      "step": 264
+    },
+    {
+      "epoch": 3.325,
+      "grad_norm": 0.019998138698183607,
+      "learning_rate": 7.585430144121319e-06,
+      "loss": 0.0354,
+      "step": 266
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 0.02806105420500808,
+      "learning_rate": 7.047302281505736e-06,
+      "loss": 0.0398,
+      "step": 268
+    },
+    {
+      "epoch": 3.375,
+      "grad_norm": 0.045720757721426676,
+      "learning_rate": 6.527522369181655e-06,
+      "loss": 0.0373,
+      "step": 270
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.032592835358184045,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.0376,
+      "step": 272
+    },
+    {
+      "epoch": 3.425,
+      "grad_norm": 0.025399293703522046,
+      "learning_rate": 5.543886593040737e-06,
+      "loss": 0.0404,
+      "step": 274
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 0.05341087943488079,
+      "learning_rate": 5.080450905401057e-06,
+      "loss": 0.0398,
+      "step": 276
+    },
+    {
+      "epoch": 3.475,
+      "grad_norm": 0.0289631047529844,
+      "learning_rate": 4.636203340922008e-06,
+      "loss": 0.0375,
+      "step": 278
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.02709048305851346,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 0.0356,
+      "step": 280
+    },
+    {
+      "epoch": 3.525,
+      "grad_norm": 0.02037186044242612,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0367,
+      "step": 282
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 0.03308570159891134,
+      "learning_rate": 3.420445597436056e-06,
+      "loss": 0.0381,
+      "step": 284
+    },
+    {
+      "epoch": 3.575,
+      "grad_norm": 0.025075251343593716,
+      "learning_rate": 3.054765042128521e-06,
+      "loss": 0.0366,
+      "step": 286
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.0639014175317484,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.06,
+      "step": 288
+    },
+    {
+      "epoch": 3.625,
+      "grad_norm": 0.020830003570237125,
+      "learning_rate": 2.3837118562592797e-06,
+      "loss": 0.0366,
+      "step": 290
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 0.022798627138582706,
+      "learning_rate": 2.0786258770873647e-06,
+      "loss": 0.0393,
+      "step": 292
+    },
+    {
+      "epoch": 3.675,
+      "grad_norm": 0.02044812017228562,
+      "learning_rate": 1.7940102999393194e-06,
+      "loss": 0.0387,
+      "step": 294
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.019781078187417544,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 0.0361,
+      "step": 296
+    },
+    {
+      "epoch": 3.725,
+      "grad_norm": 0.020539504396652995,
+      "learning_rate": 1.286667868385627e-06,
+      "loss": 0.0366,
+      "step": 298
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.035707356385659146,
+      "learning_rate": 1.064157733632276e-06,
+      "loss": 0.037,
+      "step": 300
+    },
+    {
+      "epoch": 3.775,
+      "grad_norm": 0.024574906458661484,
+      "learning_rate": 8.62551347632029e-07,
+      "loss": 0.04,
+      "step": 302
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.024927909984958394,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 0.0395,
+      "step": 304
+    },
+    {
+      "epoch": 3.825,
+      "grad_norm": 0.026646647916283364,
+      "learning_rate": 5.223853336398632e-07,
+      "loss": 0.0365,
+      "step": 306
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 0.021669244982966636,
+      "learning_rate": 3.839710131477492e-07,
+      "loss": 0.0387,
+      "step": 308
+    },
+    {
+      "epoch": 3.875,
+      "grad_norm": 0.02298012350769106,
+      "learning_rate": 2.667509943378721e-07,
+      "loss": 0.0397,
+      "step": 310
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.024765800330226025,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.0368,
+      "step": 312
+    },
+    {
+      "epoch": 3.925,
+      "grad_norm": 0.033654190885992814,
+      "learning_rate": 9.60850767065924e-08,
+      "loss": 0.0396,
+      "step": 314
+    },
+    {
+      "epoch": 3.95,
+      "grad_norm": 0.022813003291182403,
+      "learning_rate": 4.2712080634949024e-08,
+      "loss": 0.0391,
+      "step": 316
+    },
+    {
+      "epoch": 3.975,
+      "grad_norm": 0.02382187484626563,
+      "learning_rate": 1.0679160603449534e-08,
+      "loss": 0.0364,
+      "step": 318
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.021880026968572035,
+      "learning_rate": 0.0,
+      "loss": 0.035,
+      "step": 320
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 320,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1.2955222528543949e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc564678565627570649dab4c4b53ff32ab56b48ceac3010e490127231b29063
+size 7800

uccix_v2_instruct_191224_no_english_mixture_lr1e-4/checkpoint-320/zero_to_fp32.py

@@ -0,0 +1,592 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _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):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)