Upload folder using huggingface_hub

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/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_lr1e-5/checkpoint-468/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_lr1e-5/checkpoint-468/latest

@@ -0,0 +1 @@
+global_step468

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778ffbb201fb5d8b34007ce9beb7aa6ee27b9fdf93afb9487335ae5034a6207a
+size 4961502800

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be4d447ccde89310586ac3366847644ae24227df9d270989188081dc8dc267e
+size 4970422232

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33eb02446aedff576515cc4179a78f6d30a3c5bb745c5c03cd11f9f5d9bbb298
+size 4881272584

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccec4caa4064809e0139917bf9414ea9d96b0ca2f4da139699f16b1e7800c11
+size 4933722216

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c785c30346bea7c9755de83f431c1275ee4402418149151173e23164ed817b86
+size 4933722208

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1aa84eeeb3bd2d7c69abb80ec962a9a8b1976ce4cf60cdacd5127376eb120c
+size 1422460712

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/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_lr1e-5/checkpoint-468/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2509d80b2f762431b21d8b2c0c505ad9466727f26605d6289b24caab9e57d598
+size 15984

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d007e5981734d70061da15efdb1a39099608c994c62c0738b7f2a638c356d81
+size 15984

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357c4b48f9bb8f2836e53e08200cd2708d7bf7452bc78487820e53dba5c27bfa
+size 15984

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a1639367b5cd82b6484fda514185cedc094e11dece2ca3a73315ce86bb26de
+size 15984

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a77cc4bc0f599af40e9f903af6ac08f0ae8fef97d94a88f48f641a3713f4f1
+size 15984

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03a7773b00d4512901ae179ba5ed5663a6b3cbedf9f220e73ae3eb4c302cd67
+size 15984

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ca7c993e1a6bbf092680f5b2852fee8060d9c838ce0d2a6c9562a2784e5069
+size 15984

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a649cc11674a37b0d4fa80a9f131068b7297e43d745bf8b76d0dac3c4db6a7b
+size 15984

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac05d6263d9cededc202227cd6bb80549724eb1af63b29dc951d4d30bd4930a1
+size 1064

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/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_lr1e-5/checkpoint-468/tokenizer.model

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

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/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_lr1e-5/checkpoint-468/trainer_state.json

@@ -0,0 +1,1678 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9936102236421727,
+  "eval_steps": 500,
+  "global_step": 468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006389776357827476,
+      "grad_norm": 2.055807172999327,
+      "learning_rate": 1.282051282051282e-07,
+      "loss": 1.695,
+      "step": 1
+    },
+    {
+      "epoch": 0.012779552715654952,
+      "grad_norm": 2.0619830708339495,
+      "learning_rate": 2.564102564102564e-07,
+      "loss": 1.6748,
+      "step": 2
+    },
+    {
+      "epoch": 0.025559105431309903,
+      "grad_norm": 2.713640119093072,
+      "learning_rate": 5.128205128205128e-07,
+      "loss": 1.7543,
+      "step": 4
+    },
+    {
+      "epoch": 0.038338658146964855,
+      "grad_norm": 2.7787517219371667,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.7052,
+      "step": 6
+    },
+    {
+      "epoch": 0.051118210862619806,
+      "grad_norm": 2.28188247274044,
+      "learning_rate": 1.0256410256410257e-06,
+      "loss": 1.7023,
+      "step": 8
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 2.4315142127580045,
+      "learning_rate": 1.282051282051282e-06,
+      "loss": 1.7215,
+      "step": 10
+    },
+    {
+      "epoch": 0.07667731629392971,
+      "grad_norm": 1.8730980445467513,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.6382,
+      "step": 12
+    },
+    {
+      "epoch": 0.08945686900958466,
+      "grad_norm": 1.350046171341438,
+      "learning_rate": 1.794871794871795e-06,
+      "loss": 1.5726,
+      "step": 14
+    },
+    {
+      "epoch": 0.10223642172523961,
+      "grad_norm": 0.9126399700382735,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 1.5539,
+      "step": 16
+    },
+    {
+      "epoch": 0.11501597444089456,
+      "grad_norm": 0.5310525834146045,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.4776,
+      "step": 18
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 0.3699817611010441,
+      "learning_rate": 2.564102564102564e-06,
+      "loss": 1.4255,
+      "step": 20
+    },
+    {
+      "epoch": 0.14057507987220447,
+      "grad_norm": 0.3578249477320206,
+      "learning_rate": 2.8205128205128207e-06,
+      "loss": 1.39,
+      "step": 22
+    },
+    {
+      "epoch": 0.15335463258785942,
+      "grad_norm": 0.29549280933458616,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.3752,
+      "step": 24
+    },
+    {
+      "epoch": 0.16613418530351437,
+      "grad_norm": 0.3738398649251706,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.3474,
+      "step": 26
+    },
+    {
+      "epoch": 0.17891373801916932,
+      "grad_norm": 0.375163024245781,
+      "learning_rate": 3.58974358974359e-06,
+      "loss": 1.321,
+      "step": 28
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 0.28197926317237565,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 1.2797,
+      "step": 30
+    },
+    {
+      "epoch": 0.20447284345047922,
+      "grad_norm": 0.20848720674536458,
+      "learning_rate": 4.102564102564103e-06,
+      "loss": 1.2788,
+      "step": 32
+    },
+    {
+      "epoch": 0.21725239616613418,
+      "grad_norm": 0.2061126173314709,
+      "learning_rate": 4.358974358974359e-06,
+      "loss": 1.2864,
+      "step": 34
+    },
+    {
+      "epoch": 0.23003194888178913,
+      "grad_norm": 0.1978997937482167,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 1.2748,
+      "step": 36
+    },
+    {
+      "epoch": 0.24281150159744408,
+      "grad_norm": 0.14694306639698337,
+      "learning_rate": 4.871794871794872e-06,
+      "loss": 1.2576,
+      "step": 38
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 0.148218022844095,
+      "learning_rate": 5.128205128205128e-06,
+      "loss": 1.2141,
+      "step": 40
+    },
+    {
+      "epoch": 0.268370607028754,
+      "grad_norm": 0.1468062532086508,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 1.2002,
+      "step": 42
+    },
+    {
+      "epoch": 0.28115015974440893,
+      "grad_norm": 0.1044672455499073,
+      "learning_rate": 5.641025641025641e-06,
+      "loss": 1.2066,
+      "step": 44
+    },
+    {
+      "epoch": 0.2939297124600639,
+      "grad_norm": 0.10230074959226108,
+      "learning_rate": 5.897435897435898e-06,
+      "loss": 1.2093,
+      "step": 46
+    },
+    {
+      "epoch": 0.30670926517571884,
+      "grad_norm": 0.10835321687062423,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 1.1781,
+      "step": 48
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 0.08591864999573447,
+      "learning_rate": 6.410256410256412e-06,
+      "loss": 1.1987,
+      "step": 50
+    },
+    {
+      "epoch": 0.33226837060702874,
+      "grad_norm": 0.10170463928385623,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.1597,
+      "step": 52
+    },
+    {
+      "epoch": 0.3450479233226837,
+      "grad_norm": 0.08703108140215988,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.1569,
+      "step": 54
+    },
+    {
+      "epoch": 0.35782747603833864,
+      "grad_norm": 0.09437727868865202,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 1.1461,
+      "step": 56
+    },
+    {
+      "epoch": 0.3706070287539936,
+      "grad_norm": 0.08627521436960119,
+      "learning_rate": 7.435897435897437e-06,
+      "loss": 1.1509,
+      "step": 58
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.16763960045834678,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 1.1816,
+      "step": 60
+    },
+    {
+      "epoch": 0.3961661341853035,
+      "grad_norm": 0.09148986628797769,
+      "learning_rate": 7.948717948717949e-06,
+      "loss": 1.1353,
+      "step": 62
+    },
+    {
+      "epoch": 0.40894568690095845,
+      "grad_norm": 0.08816273706390138,
+      "learning_rate": 8.205128205128205e-06,
+      "loss": 1.1144,
+      "step": 64
+    },
+    {
+      "epoch": 0.4217252396166134,
+      "grad_norm": 0.07490136953022462,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 1.1337,
+      "step": 66
+    },
+    {
+      "epoch": 0.43450479233226835,
+      "grad_norm": 0.0726514548363597,
+      "learning_rate": 8.717948717948719e-06,
+      "loss": 1.141,
+      "step": 68
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 0.07842873764946051,
+      "learning_rate": 8.974358974358976e-06,
+      "loss": 1.1426,
+      "step": 70
+    },
+    {
+      "epoch": 0.46006389776357826,
+      "grad_norm": 0.07307353878556878,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 1.1314,
+      "step": 72
+    },
+    {
+      "epoch": 0.4728434504792332,
+      "grad_norm": 0.07464837020208384,
+      "learning_rate": 9.487179487179487e-06,
+      "loss": 1.106,
+      "step": 74
+    },
+    {
+      "epoch": 0.48562300319488816,
+      "grad_norm": 0.07682927536881419,
+      "learning_rate": 9.743589743589744e-06,
+      "loss": 1.1146,
+      "step": 76
+    },
+    {
+      "epoch": 0.4984025559105431,
+      "grad_norm": 0.07349178847988343,
+      "learning_rate": 1e-05,
+      "loss": 1.1243,
+      "step": 78
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 0.0716279769265826,
+      "learning_rate": 9.99995506314361e-06,
+      "loss": 1.106,
+      "step": 80
+    },
+    {
+      "epoch": 0.5239616613418531,
+      "grad_norm": 0.07985106483800218,
+      "learning_rate": 9.99982025338217e-06,
+      "loss": 1.0953,
+      "step": 82
+    },
+    {
+      "epoch": 0.536741214057508,
+      "grad_norm": 0.07973069799195517,
+      "learning_rate": 9.999595573138845e-06,
+      "loss": 1.1047,
+      "step": 84
+    },
+    {
+      "epoch": 0.549520766773163,
+      "grad_norm": 0.07769113605735692,
+      "learning_rate": 9.99928102645221e-06,
+      "loss": 1.1049,
+      "step": 86
+    },
+    {
+      "epoch": 0.5623003194888179,
+      "grad_norm": 0.07650118671106154,
+      "learning_rate": 9.99887661897616e-06,
+      "loss": 1.0801,
+      "step": 88
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.0643603309848082,
+      "learning_rate": 9.99838235797981e-06,
+      "loss": 1.097,
+      "step": 90
+    },
+    {
+      "epoch": 0.5878594249201278,
+      "grad_norm": 0.07041897634176414,
+      "learning_rate": 9.997798252347382e-06,
+      "loss": 1.0842,
+      "step": 92
+    },
+    {
+      "epoch": 0.6006389776357828,
+      "grad_norm": 0.06665938409713099,
+      "learning_rate": 9.99712431257802e-06,
+      "loss": 1.0871,
+      "step": 94
+    },
+    {
+      "epoch": 0.6134185303514377,
+      "grad_norm": 0.07351270527817233,
+      "learning_rate": 9.996360550785619e-06,
+      "loss": 1.0905,
+      "step": 96
+    },
+    {
+      "epoch": 0.6261980830670927,
+      "grad_norm": 0.06482669705796376,
+      "learning_rate": 9.9955069806986e-06,
+      "loss": 1.0729,
+      "step": 98
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 0.06311878917729494,
+      "learning_rate": 9.994563617659665e-06,
+      "loss": 1.0608,
+      "step": 100
+    },
+    {
+      "epoch": 0.6517571884984026,
+      "grad_norm": 0.07132649561595898,
+      "learning_rate": 9.993530478625524e-06,
+      "loss": 1.0648,
+      "step": 102
+    },
+    {
+      "epoch": 0.6645367412140575,
+      "grad_norm": 0.06507293693787788,
+      "learning_rate": 9.992407582166582e-06,
+      "loss": 1.0428,
+      "step": 104
+    },
+    {
+      "epoch": 0.6773162939297125,
+      "grad_norm": 0.06495408671246342,
+      "learning_rate": 9.991194948466615e-06,
+      "loss": 1.0725,
+      "step": 106
+    },
+    {
+      "epoch": 0.6900958466453674,
+      "grad_norm": 0.06960119096523358,
+      "learning_rate": 9.989892599322404e-06,
+      "loss": 1.059,
+      "step": 108
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 0.06678653497671336,
+      "learning_rate": 9.988500558143337e-06,
+      "loss": 1.0645,
+      "step": 110
+    },
+    {
+      "epoch": 0.7156549520766773,
+      "grad_norm": 0.06356475510898561,
+      "learning_rate": 9.987018849950996e-06,
+      "loss": 1.0456,
+      "step": 112
+    },
+    {
+      "epoch": 0.7284345047923323,
+      "grad_norm": 0.06541109148868933,
+      "learning_rate": 9.985447501378706e-06,
+      "loss": 1.0664,
+      "step": 114
+    },
+    {
+      "epoch": 0.7412140575079872,
+      "grad_norm": 0.06677420023722364,
+      "learning_rate": 9.983786540671052e-06,
+      "loss": 1.0329,
+      "step": 116
+    },
+    {
+      "epoch": 0.7539936102236422,
+      "grad_norm": 0.06819775252703462,
+      "learning_rate": 9.982035997683372e-06,
+      "loss": 1.0374,
+      "step": 118
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.0629291663919797,
+      "learning_rate": 9.980195903881231e-06,
+      "loss": 1.0665,
+      "step": 120
+    },
+    {
+      "epoch": 0.7795527156549521,
+      "grad_norm": 0.06922951247948388,
+      "learning_rate": 9.978266292339838e-06,
+      "loss": 1.0258,
+      "step": 122
+    },
+    {
+      "epoch": 0.792332268370607,
+      "grad_norm": 0.06458224821875515,
+      "learning_rate": 9.976247197743465e-06,
+      "loss": 1.0368,
+      "step": 124
+    },
+    {
+      "epoch": 0.805111821086262,
+      "grad_norm": 0.06056072044117011,
+      "learning_rate": 9.974138656384815e-06,
+      "loss": 1.0368,
+      "step": 126
+    },
+    {
+      "epoch": 0.8178913738019169,
+      "grad_norm": 0.06218269287622606,
+      "learning_rate": 9.97194070616438e-06,
+      "loss": 1.0203,
+      "step": 128
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 0.07088500071993263,
+      "learning_rate": 9.969653386589749e-06,
+      "loss": 1.0401,
+      "step": 130
+    },
+    {
+      "epoch": 0.8434504792332268,
+      "grad_norm": 0.0793056560286898,
+      "learning_rate": 9.967276738774897e-06,
+      "loss": 1.033,
+      "step": 132
+    },
+    {
+      "epoch": 0.8562300319488818,
+      "grad_norm": 0.07124122803857391,
+      "learning_rate": 9.964810805439464e-06,
+      "loss": 1.0382,
+      "step": 134
+    },
+    {
+      "epoch": 0.8690095846645367,
+      "grad_norm": 0.06569660589004858,
+      "learning_rate": 9.962255630907964e-06,
+      "loss": 1.0142,
+      "step": 136
+    },
+    {
+      "epoch": 0.8817891373801917,
+      "grad_norm": 0.06473404088250143,
+      "learning_rate": 9.959611261108999e-06,
+      "loss": 1.0426,
+      "step": 138
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 0.07195889745904455,
+      "learning_rate": 9.956877743574437e-06,
+      "loss": 1.0205,
+      "step": 140
+    },
+    {
+      "epoch": 0.9073482428115016,
+      "grad_norm": 0.06898817679598546,
+      "learning_rate": 9.954055127438554e-06,
+      "loss": 1.0133,
+      "step": 142
+    },
+    {
+      "epoch": 0.9201277955271565,
+      "grad_norm": 0.07559846293275942,
+      "learning_rate": 9.951143463437145e-06,
+      "loss": 1.0168,
+      "step": 144
+    },
+    {
+      "epoch": 0.9329073482428115,
+      "grad_norm": 0.07117773396387629,
+      "learning_rate": 9.948142803906623e-06,
+      "loss": 1.0039,
+      "step": 146
+    },
+    {
+      "epoch": 0.9456869009584664,
+      "grad_norm": 0.06414039585607693,
+      "learning_rate": 9.94505320278307e-06,
+      "loss": 1.0281,
+      "step": 148
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 0.07046019347974852,
+      "learning_rate": 9.94187471560127e-06,
+      "loss": 1.0256,
+      "step": 150
+    },
+    {
+      "epoch": 0.9712460063897763,
+      "grad_norm": 0.06737566318066629,
+      "learning_rate": 9.938607399493714e-06,
+      "loss": 1.0266,
+      "step": 152
+    },
+    {
+      "epoch": 0.9840255591054313,
+      "grad_norm": 0.06699946284561666,
+      "learning_rate": 9.935251313189564e-06,
+      "loss": 1.018,
+      "step": 154
+    },
+    {
+      "epoch": 0.9968051118210862,
+      "grad_norm": 0.06425061877237022,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 1.0232,
+      "step": 156
+    },
+    {
+      "epoch": 1.011182108626198,
+      "grad_norm": 0.09907516110524082,
+      "learning_rate": 9.92827307288518e-06,
+      "loss": 1.3609,
+      "step": 158
+    },
+    {
+      "epoch": 1.023961661341853,
+      "grad_norm": 0.07415902760603522,
+      "learning_rate": 9.924651044317017e-06,
+      "loss": 0.9496,
+      "step": 160
+    },
+    {
+      "epoch": 1.036741214057508,
+      "grad_norm": 0.0662373551160772,
+      "learning_rate": 9.920940496414153e-06,
+      "loss": 0.9752,
+      "step": 162
+    },
+    {
+      "epoch": 1.049520766773163,
+      "grad_norm": 0.07089817007291226,
+      "learning_rate": 9.917141495872733e-06,
+      "loss": 0.9842,
+      "step": 164
+    },
+    {
+      "epoch": 1.0623003194888179,
+      "grad_norm": 0.07572146019295103,
+      "learning_rate": 9.913254110978812e-06,
+      "loss": 0.9634,
+      "step": 166
+    },
+    {
+      "epoch": 1.0750798722044728,
+      "grad_norm": 0.13090482009861787,
+      "learning_rate": 9.909278411607134e-06,
+      "loss": 0.9587,
+      "step": 168
+    },
+    {
+      "epoch": 1.0878594249201279,
+      "grad_norm": 0.07240483127809519,
+      "learning_rate": 9.90521446921987e-06,
+      "loss": 0.9451,
+      "step": 170
+    },
+    {
+      "epoch": 1.1006389776357828,
+      "grad_norm": 0.06956480741239271,
+      "learning_rate": 9.90106235686534e-06,
+      "loss": 0.9618,
+      "step": 172
+    },
+    {
+      "epoch": 1.1134185303514377,
+      "grad_norm": 0.06957125058770244,
+      "learning_rate": 9.896822149176695e-06,
+      "loss": 0.9488,
+      "step": 174
+    },
+    {
+      "epoch": 1.1261980830670926,
+      "grad_norm": 0.06928591522513586,
+      "learning_rate": 9.892493922370575e-06,
+      "loss": 0.9811,
+      "step": 176
+    },
+    {
+      "epoch": 1.1389776357827477,
+      "grad_norm": 0.07118250896901829,
+      "learning_rate": 9.888077754245741e-06,
+      "loss": 0.9453,
+      "step": 178
+    },
+    {
+      "epoch": 1.1517571884984026,
+      "grad_norm": 0.06924103852362032,
+      "learning_rate": 9.883573724181683e-06,
+      "loss": 0.9621,
+      "step": 180
+    },
+    {
+      "epoch": 1.1645367412140575,
+      "grad_norm": 0.07320566404171391,
+      "learning_rate": 9.878981913137178e-06,
+      "loss": 0.9592,
+      "step": 182
+    },
+    {
+      "epoch": 1.1773162939297124,
+      "grad_norm": 0.07834944252802674,
+      "learning_rate": 9.87430240364885e-06,
+      "loss": 0.9565,
+      "step": 184
+    },
+    {
+      "epoch": 1.1900958466453675,
+      "grad_norm": 0.06778631059512405,
+      "learning_rate": 9.869535279829674e-06,
+      "loss": 0.9532,
+      "step": 186
+    },
+    {
+      "epoch": 1.2028753993610224,
+      "grad_norm": 0.06492444701831263,
+      "learning_rate": 9.864680627367476e-06,
+      "loss": 0.9502,
+      "step": 188
+    },
+    {
+      "epoch": 1.2156549520766773,
+      "grad_norm": 0.07215071942019542,
+      "learning_rate": 9.859738533523384e-06,
+      "loss": 0.9334,
+      "step": 190
+    },
+    {
+      "epoch": 1.2284345047923322,
+      "grad_norm": 0.07692962165173596,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.9285,
+      "step": 192
+    },
+    {
+      "epoch": 1.2412140575079873,
+      "grad_norm": 0.07144733289845186,
+      "learning_rate": 9.849592378591113e-06,
+      "loss": 0.9553,
+      "step": 194
+    },
+    {
+      "epoch": 1.2539936102236422,
+      "grad_norm": 0.07083601337037776,
+      "learning_rate": 9.844388499877457e-06,
+      "loss": 0.9328,
+      "step": 196
+    },
+    {
+      "epoch": 1.266773162939297,
+      "grad_norm": 0.07316320243317584,
+      "learning_rate": 9.839097544527674e-06,
+      "loss": 0.935,
+      "step": 198
+    },
+    {
+      "epoch": 1.279552715654952,
+      "grad_norm": 0.0695208433301601,
+      "learning_rate": 9.833719607645325e-06,
+      "loss": 0.9359,
+      "step": 200
+    },
+    {
+      "epoch": 1.292332268370607,
+      "grad_norm": 0.06969390398034943,
+      "learning_rate": 9.82825478589744e-06,
+      "loss": 0.9253,
+      "step": 202
+    },
+    {
+      "epoch": 1.305111821086262,
+      "grad_norm": 0.07197337129595487,
+      "learning_rate": 9.822703177512783e-06,
+      "loss": 0.9279,
+      "step": 204
+    },
+    {
+      "epoch": 1.317891373801917,
+      "grad_norm": 0.07293955629391159,
+      "learning_rate": 9.817064882280085e-06,
+      "loss": 0.9113,
+      "step": 206
+    },
+    {
+      "epoch": 1.330670926517572,
+      "grad_norm": 0.0662084834618456,
+      "learning_rate": 9.811340001546252e-06,
+      "loss": 0.9412,
+      "step": 208
+    },
+    {
+      "epoch": 1.343450479233227,
+      "grad_norm": 0.06897239157709753,
+      "learning_rate": 9.805528638214543e-06,
+      "loss": 0.9138,
+      "step": 210
+    },
+    {
+      "epoch": 1.3562300319488818,
+      "grad_norm": 0.07764173779556026,
+      "learning_rate": 9.799630896742716e-06,
+      "loss": 0.9264,
+      "step": 212
+    },
+    {
+      "epoch": 1.3690095846645367,
+      "grad_norm": 0.06786942257491788,
+      "learning_rate": 9.793646883141155e-06,
+      "loss": 0.9132,
+      "step": 214
+    },
+    {
+      "epoch": 1.3817891373801916,
+      "grad_norm": 0.07299256618164499,
+      "learning_rate": 9.787576704970965e-06,
+      "loss": 0.9162,
+      "step": 216
+    },
+    {
+      "epoch": 1.3945686900958467,
+      "grad_norm": 0.07374519229160317,
+      "learning_rate": 9.781420471342035e-06,
+      "loss": 0.9175,
+      "step": 218
+    },
+    {
+      "epoch": 1.4073482428115016,
+      "grad_norm": 0.0714888166966269,
+      "learning_rate": 9.77517829291108e-06,
+      "loss": 0.9189,
+      "step": 220
+    },
+    {
+      "epoch": 1.4201277955271565,
+      "grad_norm": 0.07380307635726331,
+      "learning_rate": 9.768850281879651e-06,
+      "loss": 0.9004,
+      "step": 222
+    },
+    {
+      "epoch": 1.4329073482428116,
+      "grad_norm": 0.07384614438950858,
+      "learning_rate": 9.762436551992117e-06,
+      "loss": 0.9122,
+      "step": 224
+    },
+    {
+      "epoch": 1.4456869009584665,
+      "grad_norm": 0.07399395278257612,
+      "learning_rate": 9.755937218533622e-06,
+      "loss": 0.9239,
+      "step": 226
+    },
+    {
+      "epoch": 1.4584664536741214,
+      "grad_norm": 0.07112586882023823,
+      "learning_rate": 9.74935239832801e-06,
+      "loss": 0.9061,
+      "step": 228
+    },
+    {
+      "epoch": 1.4712460063897763,
+      "grad_norm": 0.07140106100598033,
+      "learning_rate": 9.742682209735727e-06,
+      "loss": 0.898,
+      "step": 230
+    },
+    {
+      "epoch": 1.4840255591054312,
+      "grad_norm": 0.06999739915996865,
+      "learning_rate": 9.735926772651703e-06,
+      "loss": 0.9094,
+      "step": 232
+    },
+    {
+      "epoch": 1.4968051118210863,
+      "grad_norm": 0.069142775225698,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 0.9216,
+      "step": 234
+    },
+    {
+      "epoch": 1.5095846645367412,
+      "grad_norm": 0.07208310321027284,
+      "learning_rate": 9.722160640247523e-06,
+      "loss": 0.9271,
+      "step": 236
+    },
+    {
+      "epoch": 1.5223642172523961,
+      "grad_norm": 0.06937923111300098,
+      "learning_rate": 9.715150192370054e-06,
+      "loss": 0.8998,
+      "step": 238
+    },
+    {
+      "epoch": 1.5351437699680512,
+      "grad_norm": 0.06912137074594725,
+      "learning_rate": 9.708054990881763e-06,
+      "loss": 0.9098,
+      "step": 240
+    },
+    {
+      "epoch": 1.547923322683706,
+      "grad_norm": 0.0716336159595822,
+      "learning_rate": 9.700875163317072e-06,
+      "loss": 0.8953,
+      "step": 242
+    },
+    {
+      "epoch": 1.560702875399361,
+      "grad_norm": 0.07031864221802098,
+      "learning_rate": 9.693610838731532e-06,
+      "loss": 0.9007,
+      "step": 244
+    },
+    {
+      "epoch": 1.573482428115016,
+      "grad_norm": 0.07029805178803208,
+      "learning_rate": 9.686262147699507e-06,
+      "loss": 0.8923,
+      "step": 246
+    },
+    {
+      "epoch": 1.5862619808306708,
+      "grad_norm": 0.06898824959435941,
+      "learning_rate": 9.678829222311827e-06,
+      "loss": 0.8955,
+      "step": 248
+    },
+    {
+      "epoch": 1.599041533546326,
+      "grad_norm": 0.07545525981677151,
+      "learning_rate": 9.671312196173413e-06,
+      "loss": 0.9088,
+      "step": 250
+    },
+    {
+      "epoch": 1.6118210862619808,
+      "grad_norm": 0.09583645803024936,
+      "learning_rate": 9.663711204400872e-06,
+      "loss": 0.8813,
+      "step": 252
+    },
+    {
+      "epoch": 1.6246006389776357,
+      "grad_norm": 0.07052803439311484,
+      "learning_rate": 9.656026383620076e-06,
+      "loss": 0.9021,
+      "step": 254
+    },
+    {
+      "epoch": 1.6373801916932909,
+      "grad_norm": 0.07174435305622688,
+      "learning_rate": 9.6482578719637e-06,
+      "loss": 0.8862,
+      "step": 256
+    },
+    {
+      "epoch": 1.6501597444089455,
+      "grad_norm": 0.07238748413283501,
+      "learning_rate": 9.640405809068743e-06,
+      "loss": 0.9023,
+      "step": 258
+    },
+    {
+      "epoch": 1.6629392971246006,
+      "grad_norm": 0.0693406974968129,
+      "learning_rate": 9.632470336074009e-06,
+      "loss": 0.8892,
+      "step": 260
+    },
+    {
+      "epoch": 1.6757188498402555,
+      "grad_norm": 0.07327624706245563,
+      "learning_rate": 9.624451595617588e-06,
+      "loss": 0.8723,
+      "step": 262
+    },
+    {
+      "epoch": 1.6884984025559104,
+      "grad_norm": 0.07963678227936324,
+      "learning_rate": 9.616349731834271e-06,
+      "loss": 0.8772,
+      "step": 264
+    },
+    {
+      "epoch": 1.7012779552715656,
+      "grad_norm": 0.10357279860244777,
+      "learning_rate": 9.608164890352977e-06,
+      "loss": 0.8886,
+      "step": 266
+    },
+    {
+      "epoch": 1.7140575079872205,
+      "grad_norm": 0.0778385786289741,
+      "learning_rate": 9.599897218294122e-06,
+      "loss": 0.8771,
+      "step": 268
+    },
+    {
+      "epoch": 1.7268370607028753,
+      "grad_norm": 0.12610777062933215,
+      "learning_rate": 9.591546864266983e-06,
+      "loss": 0.8696,
+      "step": 270
+    },
+    {
+      "epoch": 1.7396166134185305,
+      "grad_norm": 0.07770370992844734,
+      "learning_rate": 9.583113978367026e-06,
+      "loss": 0.8924,
+      "step": 272
+    },
+    {
+      "epoch": 1.7523961661341851,
+      "grad_norm": 0.0806612698044715,
+      "learning_rate": 9.574598712173202e-06,
+      "loss": 0.8785,
+      "step": 274
+    },
+    {
+      "epoch": 1.7651757188498403,
+      "grad_norm": 0.0788062028214947,
+      "learning_rate": 9.56600121874523e-06,
+      "loss": 0.8547,
+      "step": 276
+    },
+    {
+      "epoch": 1.7779552715654952,
+      "grad_norm": 0.07731947968487375,
+      "learning_rate": 9.557321652620839e-06,
+      "loss": 0.8627,
+      "step": 278
+    },
+    {
+      "epoch": 1.79073482428115,
+      "grad_norm": 0.08190803662055393,
+      "learning_rate": 9.548560169812997e-06,
+      "loss": 0.8604,
+      "step": 280
+    },
+    {
+      "epoch": 1.8035143769968052,
+      "grad_norm": 0.08260525401723899,
+      "learning_rate": 9.539716927807102e-06,
+      "loss": 0.8771,
+      "step": 282
+    },
+    {
+      "epoch": 1.81629392971246,
+      "grad_norm": 0.07784346527611156,
+      "learning_rate": 9.530792085558151e-06,
+      "loss": 0.886,
+      "step": 284
+    },
+    {
+      "epoch": 1.829073482428115,
+      "grad_norm": 0.07825987296583618,
+      "learning_rate": 9.521785803487888e-06,
+      "loss": 0.874,
+      "step": 286
+    },
+    {
+      "epoch": 1.84185303514377,
+      "grad_norm": 0.11504308003589604,
+      "learning_rate": 9.512698243481914e-06,
+      "loss": 0.8722,
+      "step": 288
+    },
+    {
+      "epoch": 1.854632587859425,
+      "grad_norm": 0.0706998555334881,
+      "learning_rate": 9.50352956888678e-06,
+      "loss": 0.8786,
+      "step": 290
+    },
+    {
+      "epoch": 1.8674121405750799,
+      "grad_norm": 0.08032750314446153,
+      "learning_rate": 9.49427994450705e-06,
+      "loss": 0.8665,
+      "step": 292
+    },
+    {
+      "epoch": 1.880191693290735,
+      "grad_norm": 0.12277701328436769,
+      "learning_rate": 9.484949536602343e-06,
+      "loss": 0.8569,
+      "step": 294
+    },
+    {
+      "epoch": 1.8929712460063897,
+      "grad_norm": 0.3133344539837911,
+      "learning_rate": 9.47553851288434e-06,
+      "loss": 0.8342,
+      "step": 296
+    },
+    {
+      "epoch": 1.9057507987220448,
+      "grad_norm": 0.07915849443417738,
+      "learning_rate": 9.466047042513767e-06,
+      "loss": 0.8722,
+      "step": 298
+    },
+    {
+      "epoch": 1.9185303514376997,
+      "grad_norm": 0.07388844698367664,
+      "learning_rate": 9.45647529609736e-06,
+      "loss": 0.8523,
+      "step": 300
+    },
+    {
+      "epoch": 1.9313099041533546,
+      "grad_norm": 0.07844075449799331,
+      "learning_rate": 9.4468234456848e-06,
+      "loss": 0.8684,
+      "step": 302
+    },
+    {
+      "epoch": 1.9440894568690097,
+      "grad_norm": 0.08117794295033834,
+      "learning_rate": 9.437091664765611e-06,
+      "loss": 0.8615,
+      "step": 304
+    },
+    {
+      "epoch": 1.9568690095846646,
+      "grad_norm": 0.0774054800449662,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 0.8519,
+      "step": 306
+    },
+    {
+      "epoch": 1.9696485623003195,
+      "grad_norm": 0.07348805569878705,
+      "learning_rate": 9.41738901254596e-06,
+      "loss": 0.838,
+      "step": 308
+    },
+    {
+      "epoch": 1.9824281150159746,
+      "grad_norm": 0.07814133587865683,
+      "learning_rate": 9.4074184953956e-06,
+      "loss": 0.8606,
+      "step": 310
+    },
+    {
+      "epoch": 1.9952076677316293,
+      "grad_norm": 0.07768240761269606,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 0.8363,
+      "step": 312
+    },
+    {
+      "epoch": 2.009584664536741,
+      "grad_norm": 0.08883201756641222,
+      "learning_rate": 9.38723997509798e-06,
+      "loss": 1.1054,
+      "step": 314
+    },
+    {
+      "epoch": 2.022364217252396,
+      "grad_norm": 0.09535044991933866,
+      "learning_rate": 9.37703233465443e-06,
+      "loss": 0.7809,
+      "step": 316
+    },
+    {
+      "epoch": 2.0351437699680512,
+      "grad_norm": 0.0899461173236908,
+      "learning_rate": 9.366746018181503e-06,
+      "loss": 0.7853,
+      "step": 318
+    },
+    {
+      "epoch": 2.047923322683706,
+      "grad_norm": 0.08699834395832293,
+      "learning_rate": 9.356381210573092e-06,
+      "loss": 0.7804,
+      "step": 320
+    },
+    {
+      "epoch": 2.060702875399361,
+      "grad_norm": 0.08621851686642173,
+      "learning_rate": 9.345938098133946e-06,
+      "loss": 0.7691,
+      "step": 322
+    },
+    {
+      "epoch": 2.073482428115016,
+      "grad_norm": 0.0878792614677104,
+      "learning_rate": 9.33541686857632e-06,
+      "loss": 0.7533,
+      "step": 324
+    },
+    {
+      "epoch": 2.086261980830671,
+      "grad_norm": 0.09394109098983003,
+      "learning_rate": 9.324817711016609e-06,
+      "loss": 0.7664,
+      "step": 326
+    },
+    {
+      "epoch": 2.099041533546326,
+      "grad_norm": 0.0852387489503167,
+      "learning_rate": 9.31414081597194e-06,
+      "loss": 0.7595,
+      "step": 328
+    },
+    {
+      "epoch": 2.1118210862619806,
+      "grad_norm": 0.08209521428452116,
+      "learning_rate": 9.303386375356752e-06,
+      "loss": 0.7343,
+      "step": 330
+    },
+    {
+      "epoch": 2.1246006389776357,
+      "grad_norm": 0.09206102053261545,
+      "learning_rate": 9.292554582479349e-06,
+      "loss": 0.7607,
+      "step": 332
+    },
+    {
+      "epoch": 2.137380191693291,
+      "grad_norm": 0.08213489385694336,
+      "learning_rate": 9.281645632038417e-06,
+      "loss": 0.7568,
+      "step": 334
+    },
+    {
+      "epoch": 2.1501597444089455,
+      "grad_norm": 0.08209078040215159,
+      "learning_rate": 9.270659720119533e-06,
+      "loss": 0.7521,
+      "step": 336
+    },
+    {
+      "epoch": 2.1629392971246006,
+      "grad_norm": 0.08511423465943413,
+      "learning_rate": 9.259597044191635e-06,
+      "loss": 0.7337,
+      "step": 338
+    },
+    {
+      "epoch": 2.1757188498402558,
+      "grad_norm": 0.10041875249218343,
+      "learning_rate": 9.248457803103476e-06,
+      "loss": 0.746,
+      "step": 340
+    },
+    {
+      "epoch": 2.1884984025559104,
+      "grad_norm": 0.08704563593245765,
+      "learning_rate": 9.237242197080045e-06,
+      "loss": 0.7353,
+      "step": 342
+    },
+    {
+      "epoch": 2.2012779552715656,
+      "grad_norm": 0.09348040659499997,
+      "learning_rate": 9.225950427718974e-06,
+      "loss": 0.7729,
+      "step": 344
+    },
+    {
+      "epoch": 2.2140575079872207,
+      "grad_norm": 0.08726341086333145,
+      "learning_rate": 9.21458269798691e-06,
+      "loss": 0.7517,
+      "step": 346
+    },
+    {
+      "epoch": 2.2268370607028753,
+      "grad_norm": 0.08436941838539416,
+      "learning_rate": 9.203139212215868e-06,
+      "loss": 0.7164,
+      "step": 348
+    },
+    {
+      "epoch": 2.2396166134185305,
+      "grad_norm": 0.0901609443354115,
+      "learning_rate": 9.191620176099559e-06,
+      "loss": 0.7407,
+      "step": 350
+    },
+    {
+      "epoch": 2.252396166134185,
+      "grad_norm": 0.08831943060441182,
+      "learning_rate": 9.180025796689692e-06,
+      "loss": 0.7323,
+      "step": 352
+    },
+    {
+      "epoch": 2.2651757188498403,
+      "grad_norm": 0.09564066419044027,
+      "learning_rate": 9.168356282392253e-06,
+      "loss": 0.7298,
+      "step": 354
+    },
+    {
+      "epoch": 2.2779552715654954,
+      "grad_norm": 0.08464582091102903,
+      "learning_rate": 9.156611842963753e-06,
+      "loss": 0.7314,
+      "step": 356
+    },
+    {
+      "epoch": 2.29073482428115,
+      "grad_norm": 0.08870915805306676,
+      "learning_rate": 9.144792689507471e-06,
+      "loss": 0.7217,
+      "step": 358
+    },
+    {
+      "epoch": 2.303514376996805,
+      "grad_norm": 0.08613473048448057,
+      "learning_rate": 9.132899034469648e-06,
+      "loss": 0.7402,
+      "step": 360
+    },
+    {
+      "epoch": 2.31629392971246,
+      "grad_norm": 0.08341988693841207,
+      "learning_rate": 9.120931091635669e-06,
+      "loss": 0.7467,
+      "step": 362
+    },
+    {
+      "epoch": 2.329073482428115,
+      "grad_norm": 0.08549945333901839,
+      "learning_rate": 9.108889076126226e-06,
+      "loss": 0.7207,
+      "step": 364
+    },
+    {
+      "epoch": 2.34185303514377,
+      "grad_norm": 0.08336828182020982,
+      "learning_rate": 9.09677320439345e-06,
+      "loss": 0.7385,
+      "step": 366
+    },
+    {
+      "epoch": 2.3546325878594248,
+      "grad_norm": 0.08408664059192321,
+      "learning_rate": 9.084583694217012e-06,
+      "loss": 0.7248,
+      "step": 368
+    },
+    {
+      "epoch": 2.36741214057508,
+      "grad_norm": 0.0886593849582559,
+      "learning_rate": 9.072320764700223e-06,
+      "loss": 0.7096,
+      "step": 370
+    },
+    {
+      "epoch": 2.380191693290735,
+      "grad_norm": 0.0839729222435562,
+      "learning_rate": 9.059984636266082e-06,
+      "loss": 0.7145,
+      "step": 372
+    },
+    {
+      "epoch": 2.3929712460063897,
+      "grad_norm": 0.08726323559997523,
+      "learning_rate": 9.047575530653324e-06,
+      "loss": 0.7418,
+      "step": 374
+    },
+    {
+      "epoch": 2.405750798722045,
+      "grad_norm": 0.08770732225914885,
+      "learning_rate": 9.035093670912424e-06,
+      "loss": 0.7196,
+      "step": 376
+    },
+    {
+      "epoch": 2.4185303514377,
+      "grad_norm": 0.08755818172663851,
+      "learning_rate": 9.022539281401601e-06,
+      "loss": 0.7061,
+      "step": 378
+    },
+    {
+      "epoch": 2.4313099041533546,
+      "grad_norm": 0.0854340041188233,
+      "learning_rate": 9.009912587782772e-06,
+      "loss": 0.6979,
+      "step": 380
+    },
+    {
+      "epoch": 2.4440894568690097,
+      "grad_norm": 0.09169828487884032,
+      "learning_rate": 8.997213817017508e-06,
+      "loss": 0.7157,
+      "step": 382
+    },
+    {
+      "epoch": 2.4568690095846644,
+      "grad_norm": 0.0901920345313963,
+      "learning_rate": 8.984443197362938e-06,
+      "loss": 0.7077,
+      "step": 384
+    },
+    {
+      "epoch": 2.4696485623003195,
+      "grad_norm": 0.09096539957366484,
+      "learning_rate": 8.971600958367668e-06,
+      "loss": 0.7035,
+      "step": 386
+    },
+    {
+      "epoch": 2.4824281150159746,
+      "grad_norm": 0.0873097187921073,
+      "learning_rate": 8.958687330867634e-06,
+      "loss": 0.694,
+      "step": 388
+    },
+    {
+      "epoch": 2.4952076677316293,
+      "grad_norm": 0.08516233809095139,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 0.7095,
+      "step": 390
+    },
+    {
+      "epoch": 2.5079872204472844,
+      "grad_norm": 0.08243863183194293,
+      "learning_rate": 8.932646840108818e-06,
+      "loss": 0.6915,
+      "step": 392
+    },
+    {
+      "epoch": 2.520766773162939,
+      "grad_norm": 0.09578242588929417,
+      "learning_rate": 8.919520444921153e-06,
+      "loss": 0.7267,
+      "step": 394
+    },
+    {
+      "epoch": 2.533546325878594,
+      "grad_norm": 0.08923574104867454,
+      "learning_rate": 8.906323597362547e-06,
+      "loss": 0.735,
+      "step": 396
+    },
+    {
+      "epoch": 2.5463258785942493,
+      "grad_norm": 0.08980929421634831,
+      "learning_rate": 8.893056534642938e-06,
+      "loss": 0.7079,
+      "step": 398
+    },
+    {
+      "epoch": 2.559105431309904,
+      "grad_norm": 0.09498992436734802,
+      "learning_rate": 8.879719495234363e-06,
+      "loss": 0.6925,
+      "step": 400
+    },
+    {
+      "epoch": 2.571884984025559,
+      "grad_norm": 0.0875701522095898,
+      "learning_rate": 8.866312718866669e-06,
+      "loss": 0.6902,
+      "step": 402
+    },
+    {
+      "epoch": 2.584664536741214,
+      "grad_norm": 0.09245786132330439,
+      "learning_rate": 8.852836446523213e-06,
+      "loss": 0.6992,
+      "step": 404
+    },
+    {
+      "epoch": 2.597444089456869,
+      "grad_norm": 0.09222422334070807,
+      "learning_rate": 8.83929092043652e-06,
+      "loss": 0.7156,
+      "step": 406
+    },
+    {
+      "epoch": 2.610223642172524,
+      "grad_norm": 0.09354657561723002,
+      "learning_rate": 8.825676384083936e-06,
+      "loss": 0.699,
+      "step": 408
+    },
+    {
+      "epoch": 2.623003194888179,
+      "grad_norm": 0.08392617333570597,
+      "learning_rate": 8.811993082183243e-06,
+      "loss": 0.6708,
+      "step": 410
+    },
+    {
+      "epoch": 2.635782747603834,
+      "grad_norm": 0.09563565262978453,
+      "learning_rate": 8.798241260688273e-06,
+      "loss": 0.6878,
+      "step": 412
+    },
+    {
+      "epoch": 2.648562300319489,
+      "grad_norm": 0.09071924557956357,
+      "learning_rate": 8.784421166784476e-06,
+      "loss": 0.6569,
+      "step": 414
+    },
+    {
+      "epoch": 2.661341853035144,
+      "grad_norm": 0.09189326542168455,
+      "learning_rate": 8.770533048884483e-06,
+      "loss": 0.6929,
+      "step": 416
+    },
+    {
+      "epoch": 2.6741214057507987,
+      "grad_norm": 0.08886131371026194,
+      "learning_rate": 8.756577156623636e-06,
+      "loss": 0.6775,
+      "step": 418
+    },
+    {
+      "epoch": 2.686900958466454,
+      "grad_norm": 0.0884759503364701,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.6647,
+      "step": 420
+    },
+    {
+      "epoch": 2.6996805111821085,
+      "grad_norm": 0.09138446256959393,
+      "learning_rate": 8.728463053647382e-06,
+      "loss": 0.6912,
+      "step": 422
+    },
+    {
+      "epoch": 2.7124600638977636,
+      "grad_norm": 0.09602956398461687,
+      "learning_rate": 8.71430534827574e-06,
+      "loss": 0.6915,
+      "step": 424
+    },
+    {
+      "epoch": 2.7252396166134183,
+      "grad_norm": 0.09546369455014705,
+      "learning_rate": 8.700080879221689e-06,
+      "loss": 0.6639,
+      "step": 426
+    },
+    {
+      "epoch": 2.7380191693290734,
+      "grad_norm": 0.09410029940427483,
+      "learning_rate": 8.685789902166395e-06,
+      "loss": 0.6582,
+      "step": 428
+    },
+    {
+      "epoch": 2.7507987220447285,
+      "grad_norm": 0.10031465100986502,
+      "learning_rate": 8.671432673986493e-06,
+      "loss": 0.6444,
+      "step": 430
+    },
+    {
+      "epoch": 2.763578274760383,
+      "grad_norm": 0.08567336248542835,
+      "learning_rate": 8.657009452749466e-06,
+      "loss": 0.6968,
+      "step": 432
+    },
+    {
+      "epoch": 2.7763578274760383,
+      "grad_norm": 0.09475186511369259,
+      "learning_rate": 8.642520497709001e-06,
+      "loss": 0.6916,
+      "step": 434
+    },
+    {
+      "epoch": 2.7891373801916934,
+      "grad_norm": 0.09385138382626645,
+      "learning_rate": 8.627966069300332e-06,
+      "loss": 0.6747,
+      "step": 436
+    },
+    {
+      "epoch": 2.801916932907348,
+      "grad_norm": 0.09246626511863794,
+      "learning_rate": 8.613346429135567e-06,
+      "loss": 0.6971,
+      "step": 438
+    },
+    {
+      "epoch": 2.8146964856230032,
+      "grad_norm": 0.0902896351493368,
+      "learning_rate": 8.598661839998972e-06,
+      "loss": 0.6456,
+      "step": 440
+    },
+    {
+      "epoch": 2.8274760383386583,
+      "grad_norm": 0.0974374236441883,
+      "learning_rate": 8.583912565842258e-06,
+      "loss": 0.6847,
+      "step": 442
+    },
+    {
+      "epoch": 2.840255591054313,
+      "grad_norm": 0.09028761990649814,
+      "learning_rate": 8.569098871779828e-06,
+      "loss": 0.6481,
+      "step": 444
+    },
+    {
+      "epoch": 2.853035143769968,
+      "grad_norm": 0.09094677152860932,
+      "learning_rate": 8.554221024084019e-06,
+      "loss": 0.6765,
+      "step": 446
+    },
+    {
+      "epoch": 2.8658146964856233,
+      "grad_norm": 0.09114673707540955,
+      "learning_rate": 8.539279290180315e-06,
+      "loss": 0.6537,
+      "step": 448
+    },
+    {
+      "epoch": 2.878594249201278,
+      "grad_norm": 0.08646200856678304,
+      "learning_rate": 8.524273938642539e-06,
+      "loss": 0.6584,
+      "step": 450
+    },
+    {
+      "epoch": 2.891373801916933,
+      "grad_norm": 0.09673722964818894,
+      "learning_rate": 8.509205239188017e-06,
+      "loss": 0.6852,
+      "step": 452
+    },
+    {
+      "epoch": 2.9041533546325877,
+      "grad_norm": 0.10123163649623611,
+      "learning_rate": 8.494073462672743e-06,
+      "loss": 0.6746,
+      "step": 454
+    },
+    {
+      "epoch": 2.916932907348243,
+      "grad_norm": 0.09584474326248778,
+      "learning_rate": 8.478878881086505e-06,
+      "loss": 0.6633,
+      "step": 456
+    },
+    {
+      "epoch": 2.9297124600638975,
+      "grad_norm": 0.08930310945740996,
+      "learning_rate": 8.463621767547998e-06,
+      "loss": 0.6362,
+      "step": 458
+    },
+    {
+      "epoch": 2.9424920127795526,
+      "grad_norm": 0.0871909024937303,
+      "learning_rate": 8.448302396299906e-06,
+      "loss": 0.6441,
+      "step": 460
+    },
+    {
+      "epoch": 2.9552715654952078,
+      "grad_norm": 0.09193009664136784,
+      "learning_rate": 8.432921042703985e-06,
+      "loss": 0.6594,
+      "step": 462
+    },
+    {
+      "epoch": 2.9680511182108624,
+      "grad_norm": 0.10151316130359724,
+      "learning_rate": 8.417477983236107e-06,
+      "loss": 0.6273,
+      "step": 464
+    },
+    {
+      "epoch": 2.9808306709265175,
+      "grad_norm": 0.09687677621564994,
+      "learning_rate": 8.401973495481289e-06,
+      "loss": 0.6466,
+      "step": 466
+    },
+    {
+      "epoch": 2.9936102236421727,
+      "grad_norm": 0.08818640172103377,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 0.6571,
+      "step": 468
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8977376755091767e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465bc2aa3a69c77edd4dd8329b8c5845f84192ba6d63456f03bac7f5907488ad
+size 7352

uccix_v2_instruct_191224_lr1e-5/checkpoint-468/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)