Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/models-pku/progressalign/shared_storage/downloaded_models/llama3-8b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.40.0"
+}

latest

@@ -0,0 +1 @@
+global_step155

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bff82a21ed1453cea78d67a378bd05880171c01c3ed2b723f91bf7ed3b5894b
+size 4976698592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcee6d9e9fc3673c95a5e23b0b7ce68d35c14211d84d5198c53d2deab1ce68a1
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed66f1f489f2c36ad450c84621e6761acb28bc69cbc56e873caeb19cd94a570
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cd45dfa234e7c41768491f79087839f3828dcd91bc55327b9953bec24ac8c0
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b304f4cf4b5141480605ee4261846b7767b05a1f9d6f10fc6e30f2d58fc004
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9998a65c4acb775f5fc4ce7aee3709a8fc457e5636a8402d2dea7ba06770c1
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccc635d988f8d366b514e533f286ed39c470a2ce64ced60bb701f2d2fe29c98
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552d73ec212ddad164c55ca069f86524d2633ac33016885486c8c12d4b07c7ac
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee8b4ba744a7b776e10f66b8d081a9b60035ed34e692467fee579b993f3192e
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68437801db591d108fc1279315667d18c803273753d9f3b9fc41fdd6c1e79439
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e4bfc719988be9cca5017a9c2e3e3b0dc9018db047e2f1f527321721e233e0
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50fcb35839935b929675237a883b92465bdda9a3e60b8573fe9cba155d6d325
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae086ce767da5cccc408b88e9f46a1e86e24bc37454f64a2d89c4cad7d672ff
+size 1064

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\\n' + content + '\\n\\n### Response:\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\\n\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_log.jsonl

@@ -0,0 +1,187 @@
+{"current_steps": 1, "total_steps": 616, "loss": 2.6141, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.006493506493506494, "percentage": 0.16, "elapsed_time": "0:00:22", "remaining_time": "3:48:17"}
+{"current_steps": 1, "total_steps": 616, "loss": null, "eval_loss": 2.635435104370117, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.006493506493506494, "percentage": 0.16, "elapsed_time": "0:00:22", "remaining_time": "3:48:17"}
+{"current_steps": 5, "total_steps": 616, "loss": 2.657, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.032467532467532464, "percentage": 0.81, "elapsed_time": "0:01:43", "remaining_time": "3:31:24"}
+{"current_steps": 5, "total_steps": 616, "loss": null, "eval_loss": 2.6205813884735107, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.032467532467532464, "percentage": 0.81, "elapsed_time": "0:01:43", "remaining_time": "3:31:24"}
+{"current_steps": 10, "total_steps": 616, "loss": 2.6337, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.25e-06, "epoch": 0.06493506493506493, "percentage": 1.62, "elapsed_time": "0:04:35", "remaining_time": "4:38:39"}
+{"current_steps": 10, "total_steps": 616, "loss": null, "eval_loss": 2.5846035480499268, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.06493506493506493, "percentage": 1.62, "elapsed_time": "0:04:35", "remaining_time": "4:38:39"}
+{"current_steps": 15, "total_steps": 616, "loss": 2.5268, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9e-06, "epoch": 0.09740259740259741, "percentage": 2.44, "elapsed_time": "0:07:29", "remaining_time": "5:00:19"}
+{"current_steps": 15, "total_steps": 616, "loss": null, "eval_loss": 2.5515594482421875, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.09740259740259741, "percentage": 2.44, "elapsed_time": "0:07:29", "remaining_time": "5:00:19"}
+{"current_steps": 20, "total_steps": 616, "loss": 2.5275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.275e-05, "epoch": 0.12987012987012986, "percentage": 3.25, "elapsed_time": "0:10:28", "remaining_time": "5:12:04"}
+{"current_steps": 20, "total_steps": 616, "loss": null, "eval_loss": 2.5321404933929443, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.12987012987012986, "percentage": 3.25, "elapsed_time": "0:10:28", "remaining_time": "5:12:04"}
+{"current_steps": 25, "total_steps": 616, "loss": 2.5005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4457320927100615e-05, "epoch": 0.16233766233766234, "percentage": 4.06, "elapsed_time": "0:13:27", "remaining_time": "5:18:06"}
+{"current_steps": 25, "total_steps": 616, "loss": null, "eval_loss": 2.513052225112915, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.16233766233766234, "percentage": 4.06, "elapsed_time": "0:13:27", "remaining_time": "5:18:06"}
+{"current_steps": 30, "total_steps": 616, "loss": 2.5339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3178060763055965e-05, "epoch": 0.19480519480519481, "percentage": 4.87, "elapsed_time": "0:16:21", "remaining_time": "5:19:38"}
+{"current_steps": 30, "total_steps": 616, "loss": null, "eval_loss": 2.496060609817505, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.19480519480519481, "percentage": 4.87, "elapsed_time": "0:16:21", "remaining_time": "5:19:38"}
+{"current_steps": 35, "total_steps": 616, "loss": 2.5335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.200291011775234e-05, "epoch": 0.22727272727272727, "percentage": 5.68, "elapsed_time": "0:19:14", "remaining_time": "5:19:30"}
+{"current_steps": 35, "total_steps": 616, "loss": null, "eval_loss": 2.4807701110839844, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.22727272727272727, "percentage": 5.68, "elapsed_time": "0:19:14", "remaining_time": "5:19:30"}
+{"current_steps": 40, "total_steps": 616, "loss": 2.4252, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.092418047398154e-05, "epoch": 0.2597402597402597, "percentage": 6.49, "elapsed_time": "0:22:05", "remaining_time": "5:18:09"}
+{"current_steps": 40, "total_steps": 616, "loss": null, "eval_loss": 2.464339256286621, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.2597402597402597, "percentage": 6.49, "elapsed_time": "0:22:05", "remaining_time": "5:18:09"}
+{"current_steps": 45, "total_steps": 616, "loss": 2.4445, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.934692235419926e-06, "epoch": 0.2922077922077922, "percentage": 7.31, "elapsed_time": "0:24:59", "remaining_time": "5:17:08"}
+{"current_steps": 45, "total_steps": 616, "loss": null, "eval_loss": 2.4518375396728516, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.2922077922077922, "percentage": 7.31, "elapsed_time": "0:24:59", "remaining_time": "5:17:08"}
+{"current_steps": 50, "total_steps": 616, "loss": 2.4594, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.02774500281382e-06, "epoch": 0.3246753246753247, "percentage": 8.12, "elapsed_time": "0:27:55", "remaining_time": "5:16:03"}
+{"current_steps": 50, "total_steps": 616, "loss": null, "eval_loss": 2.4393582344055176, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3246753246753247, "percentage": 8.12, "elapsed_time": "0:27:55", "remaining_time": "5:16:03"}
+{"current_steps": 55, "total_steps": 616, "loss": 2.4498, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.197089350822288e-06, "epoch": 0.35714285714285715, "percentage": 8.93, "elapsed_time": "0:30:50", "remaining_time": "5:14:32"}
+{"current_steps": 55, "total_steps": 616, "loss": null, "eval_loss": 2.4287211894989014, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.35714285714285715, "percentage": 8.93, "elapsed_time": "0:30:50", "remaining_time": "5:14:32"}
+{"current_steps": 60, "total_steps": 616, "loss": 2.3821, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.436900041840997e-06, "epoch": 0.38961038961038963, "percentage": 9.74, "elapsed_time": "0:33:43", "remaining_time": "5:12:30"}
+{"current_steps": 60, "total_steps": 616, "loss": null, "eval_loss": 2.4184141159057617, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.38961038961038963, "percentage": 9.74, "elapsed_time": "0:33:43", "remaining_time": "5:12:30"}
+{"current_steps": 65, "total_steps": 616, "loss": 2.4317, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.741750615310939e-06, "epoch": 0.42207792207792205, "percentage": 10.55, "elapsed_time": "0:36:37", "remaining_time": "5:10:31"}
+{"current_steps": 65, "total_steps": 616, "loss": null, "eval_loss": 2.4091267585754395, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.42207792207792205, "percentage": 10.55, "elapsed_time": "0:36:37", "remaining_time": "5:10:31"}
+{"current_steps": 70, "total_steps": 616, "loss": 2.3931, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.106589293139538e-06, "epoch": 0.45454545454545453, "percentage": 11.36, "elapsed_time": "0:39:31", "remaining_time": "5:08:19"}
+{"current_steps": 70, "total_steps": 616, "loss": null, "eval_loss": 2.40012788772583, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.45454545454545453, "percentage": 11.36, "elapsed_time": "0:39:31", "remaining_time": "5:08:19"}
+{"current_steps": 75, "total_steps": 616, "loss": 2.3695, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.526716143930102e-06, "epoch": 0.487012987012987, "percentage": 12.18, "elapsed_time": "0:42:25", "remaining_time": "5:06:04"}
+{"current_steps": 75, "total_steps": 616, "loss": null, "eval_loss": 2.3934359550476074, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.487012987012987, "percentage": 12.18, "elapsed_time": "0:42:25", "remaining_time": "5:06:04"}
+{"current_steps": 80, "total_steps": 616, "loss": 2.3981, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.997761450728939e-06, "epoch": 0.5194805194805194, "percentage": 12.99, "elapsed_time": "0:45:19", "remaining_time": "5:03:40"}
+{"current_steps": 80, "total_steps": 616, "loss": null, "eval_loss": 2.3855459690093994, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5194805194805194, "percentage": 12.99, "elapsed_time": "0:45:19", "remaining_time": "5:03:40"}
+{"current_steps": 85, "total_steps": 616, "loss": 2.3952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.515665228960038e-06, "epoch": 0.551948051948052, "percentage": 13.8, "elapsed_time": "0:48:14", "remaining_time": "5:01:22"}
+{"current_steps": 85, "total_steps": 616, "loss": null, "eval_loss": 2.37890887260437, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.551948051948052, "percentage": 13.8, "elapsed_time": "0:48:14", "remaining_time": "5:01:22"}
+{"current_steps": 90, "total_steps": 616, "loss": 2.4137, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0766578431245434e-06, "epoch": 0.5844155844155844, "percentage": 14.61, "elapsed_time": "0:51:09", "remaining_time": "4:59:01"}
+{"current_steps": 90, "total_steps": 616, "loss": null, "eval_loss": 2.3720638751983643, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5844155844155844, "percentage": 14.61, "elapsed_time": "0:51:09", "remaining_time": "4:59:01"}
+{"current_steps": 95, "total_steps": 616, "loss": 2.3614, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6772416726983343e-06, "epoch": 0.6168831168831169, "percentage": 15.42, "elapsed_time": "0:54:03", "remaining_time": "4:56:29"}
+{"current_steps": 95, "total_steps": 616, "loss": null, "eval_loss": 2.366936683654785, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6168831168831169, "percentage": 15.42, "elapsed_time": "0:54:03", "remaining_time": "4:56:29"}
+{"current_steps": 100, "total_steps": 616, "loss": 2.3467, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3141737794662055e-06, "epoch": 0.6493506493506493, "percentage": 16.23, "elapsed_time": "0:56:58", "remaining_time": "4:53:58"}
+{"current_steps": 100, "total_steps": 616, "loss": null, "eval_loss": 2.361203193664551, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6493506493506493, "percentage": 16.23, "elapsed_time": "0:56:58", "remaining_time": "4:53:58"}
+{"current_steps": 105, "total_steps": 616, "loss": 2.4012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.984449530286649e-06, "epoch": 0.6818181818181818, "percentage": 17.05, "elapsed_time": "0:59:52", "remaining_time": "4:51:25"}
+{"current_steps": 105, "total_steps": 616, "loss": null, "eval_loss": 2.3568994998931885, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6818181818181818, "percentage": 17.05, "elapsed_time": "0:59:52", "remaining_time": "4:51:25"}
+{"current_steps": 110, "total_steps": 616, "loss": 2.3224, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.685287130987944e-06, "epoch": 0.7142857142857143, "percentage": 17.86, "elapsed_time": "1:02:47", "remaining_time": "4:48:49"}
+{"current_steps": 110, "total_steps": 616, "loss": null, "eval_loss": 2.352806329727173, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7142857142857143, "percentage": 17.86, "elapsed_time": "1:02:47", "remaining_time": "4:48:49"}
+{"current_steps": 115, "total_steps": 616, "loss": 2.3348, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4141130287548048e-06, "epoch": 0.7467532467532467, "percentage": 18.67, "elapsed_time": "1:05:42", "remaining_time": "4:46:13"}
+{"current_steps": 115, "total_steps": 616, "loss": null, "eval_loss": 2.348268985748291, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7467532467532467, "percentage": 18.67, "elapsed_time": "1:05:42", "remaining_time": "4:46:13"}
+{"current_steps": 120, "total_steps": 616, "loss": 2.3573, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.168548141976706e-06, "epoch": 0.7792207792207793, "percentage": 19.48, "elapsed_time": "1:08:37", "remaining_time": "4:43:40"}
+{"current_steps": 120, "total_steps": 616, "loss": null, "eval_loss": 2.3447518348693848, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7792207792207793, "percentage": 19.48, "elapsed_time": "1:08:37", "remaining_time": "4:43:40"}
+{"current_steps": 125, "total_steps": 616, "loss": 2.306, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.946394878094437e-06, "epoch": 0.8116883116883117, "percentage": 20.29, "elapsed_time": "1:11:31", "remaining_time": "4:40:57"}
+{"current_steps": 125, "total_steps": 616, "loss": null, "eval_loss": 2.3411996364593506, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8116883116883117, "percentage": 20.29, "elapsed_time": "1:11:31", "remaining_time": "4:40:57"}
+{"current_steps": 130, "total_steps": 616, "loss": 2.342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.745624901501792e-06, "epoch": 0.8441558441558441, "percentage": 21.1, "elapsed_time": "1:14:25", "remaining_time": "4:38:14"}
+{"current_steps": 130, "total_steps": 616, "loss": null, "eval_loss": 2.338190793991089, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8441558441558441, "percentage": 21.1, "elapsed_time": "1:14:25", "remaining_time": "4:38:14"}
+{"current_steps": 135, "total_steps": 616, "loss": 2.3045, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.564367615035273e-06, "epoch": 0.8766233766233766, "percentage": 21.92, "elapsed_time": "1:17:19", "remaining_time": "4:35:29"}
+{"current_steps": 135, "total_steps": 616, "loss": null, "eval_loss": 2.3356211185455322, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8766233766233766, "percentage": 21.92, "elapsed_time": "1:17:19", "remaining_time": "4:35:29"}
+{"current_steps": 140, "total_steps": 616, "loss": 2.2959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4008993200171148e-06, "epoch": 0.9090909090909091, "percentage": 22.73, "elapsed_time": "1:20:12", "remaining_time": "4:32:43"}
+{"current_steps": 140, "total_steps": 616, "loss": null, "eval_loss": 2.3329813480377197, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9090909090909091, "percentage": 22.73, "elapsed_time": "1:20:12", "remaining_time": "4:32:43"}
+{"current_steps": 145, "total_steps": 616, "loss": 2.3545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.253633021206854e-06, "epoch": 0.9415584415584416, "percentage": 23.54, "elapsed_time": "1:23:08", "remaining_time": "4:30:03"}
+{"current_steps": 145, "total_steps": 616, "loss": null, "eval_loss": 2.330482006072998, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9415584415584416, "percentage": 23.54, "elapsed_time": "1:23:08", "remaining_time": "4:30:03"}
+{"current_steps": 150, "total_steps": 616, "loss": 2.3446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1211088443646446e-06, "epoch": 0.974025974025974, "percentage": 24.35, "elapsed_time": "1:26:03", "remaining_time": "4:27:21"}
+{"current_steps": 150, "total_steps": 616, "loss": null, "eval_loss": 2.3284924030303955, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.974025974025974, "percentage": 24.35, "elapsed_time": "1:26:03", "remaining_time": "4:27:21"}
+{"current_steps": 155, "total_steps": 616, "loss": 2.2502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0019850354367667e-06, "epoch": 1.0064935064935066, "percentage": 25.16, "elapsed_time": "1:28:58", "remaining_time": "4:24:36"}
+{"current_steps": 155, "total_steps": 616, "loss": null, "eval_loss": 2.326810598373413, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0064935064935066, "percentage": 25.16, "elapsed_time": "1:28:58", "remaining_time": "4:24:36"}
+{"current_steps": 160, "total_steps": 616, "loss": 2.0791, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.950295116407778e-07, "epoch": 1.0389610389610389, "percentage": 25.97, "elapsed_time": "1:31:51", "remaining_time": "4:21:48"}
+{"current_steps": 160, "total_steps": 616, "loss": null, "eval_loss": 2.3346893787384033, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0389610389610389, "percentage": 25.97, "elapsed_time": "1:31:51", "remaining_time": "4:21:48"}
+{"current_steps": 165, "total_steps": 616, "loss": 2.1034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.991119359555816e-07, "epoch": 1.0714285714285714, "percentage": 26.79, "elapsed_time": "1:34:45", "remaining_time": "4:18:59"}
+{"current_steps": 165, "total_steps": 616, "loss": null, "eval_loss": 2.3399083614349365, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0714285714285714, "percentage": 26.79, "elapsed_time": "1:34:45", "remaining_time": "4:18:59"}
+{"current_steps": 170, "total_steps": 616, "loss": 2.095, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.131962877110503e-07, "epoch": 1.103896103896104, "percentage": 27.6, "elapsed_time": "1:37:38", "remaining_time": "4:16:11"}
+{"current_steps": 170, "total_steps": 616, "loss": null, "eval_loss": 2.335786819458008, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.103896103896104, "percentage": 27.6, "elapsed_time": "1:37:38", "remaining_time": "4:16:11"}
+{"current_steps": 175, "total_steps": 616, "loss": 2.0627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.363339031235531e-07, "epoch": 1.1363636363636362, "percentage": 28.41, "elapsed_time": "1:40:33", "remaining_time": "4:13:23"}
+{"current_steps": 175, "total_steps": 616, "loss": null, "eval_loss": 2.3346118927001953, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1363636363636362, "percentage": 28.41, "elapsed_time": "1:40:33", "remaining_time": "4:13:23"}
+{"current_steps": 180, "total_steps": 616, "loss": 2.0408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.676569607386888e-07, "epoch": 1.1688311688311688, "percentage": 29.22, "elapsed_time": "1:43:26", "remaining_time": "4:10:33"}
+{"current_steps": 180, "total_steps": 616, "loss": null, "eval_loss": 2.3357036113739014, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1688311688311688, "percentage": 29.22, "elapsed_time": "1:43:26", "remaining_time": "4:10:33"}
+{"current_steps": 185, "total_steps": 616, "loss": 2.0575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.063723878213202e-07, "epoch": 1.2012987012987013, "percentage": 30.03, "elapsed_time": "1:46:19", "remaining_time": "4:07:43"}
+{"current_steps": 185, "total_steps": 616, "loss": null, "eval_loss": 2.336442708969116, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2012987012987013, "percentage": 30.03, "elapsed_time": "1:46:19", "remaining_time": "4:07:43"}
+{"current_steps": 190, "total_steps": 616, "loss": 2.0976, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5175616477672654e-07, "epoch": 1.2337662337662338, "percentage": 30.84, "elapsed_time": "1:49:14", "remaining_time": "4:04:55"}
+{"current_steps": 190, "total_steps": 616, "loss": null, "eval_loss": 2.3349287509918213, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2337662337662338, "percentage": 30.84, "elapsed_time": "1:49:14", "remaining_time": "4:04:55"}
+{"current_steps": 195, "total_steps": 616, "loss": 2.0668, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0314800569574653e-07, "epoch": 1.2662337662337662, "percentage": 31.66, "elapsed_time": "1:52:09", "remaining_time": "4:02:08"}
+{"current_steps": 195, "total_steps": 616, "loss": null, "eval_loss": 2.3336005210876465, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2662337662337662, "percentage": 31.66, "elapsed_time": "1:52:09", "remaining_time": "4:02:08"}
+{"current_steps": 200, "total_steps": 616, "loss": 2.0579, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5994639409229767e-07, "epoch": 1.2987012987012987, "percentage": 32.47, "elapsed_time": "1:55:02", "remaining_time": "3:59:17"}
+{"current_steps": 200, "total_steps": 616, "loss": null, "eval_loss": 2.3329007625579834, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2987012987012987, "percentage": 32.47, "elapsed_time": "1:55:02", "remaining_time": "3:59:17"}
+{"current_steps": 205, "total_steps": 616, "loss": 2.0756, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2160395384412303e-07, "epoch": 1.3311688311688312, "percentage": 33.28, "elapsed_time": "1:57:57", "remaining_time": "3:56:30"}
+{"current_steps": 205, "total_steps": 616, "loss": null, "eval_loss": 2.332624912261963, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.3311688311688312, "percentage": 33.28, "elapsed_time": "1:57:57", "remaining_time": "3:56:30"}
+{"current_steps": 210, "total_steps": 616, "loss": 2.1174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.87623136257929e-07, "epoch": 1.3636363636363638, "percentage": 34.09, "elapsed_time": "2:00:50", "remaining_time": "3:53:38"}
+{"current_steps": 210, "total_steps": 616, "loss": null, "eval_loss": 2.3325307369232178, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.3636363636363638, "percentage": 34.09, "elapsed_time": "2:00:50", "remaining_time": "3:53:38"}
+{"current_steps": 215, "total_steps": 616, "loss": 2.0663, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5755220505894177e-07, "epoch": 1.396103896103896, "percentage": 34.9, "elapsed_time": "2:03:44", "remaining_time": "3:50:48"}
+{"current_steps": 215, "total_steps": 616, "loss": null, "eval_loss": 2.332547664642334, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.396103896103896, "percentage": 34.9, "elapsed_time": "2:03:44", "remaining_time": "3:50:48"}
+{"current_steps": 220, "total_steps": 616, "loss": 2.0941, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3098150195300782e-07, "epoch": 1.4285714285714286, "percentage": 35.71, "elapsed_time": "2:06:39", "remaining_time": "3:47:58"}
+{"current_steps": 220, "total_steps": 616, "loss": null, "eval_loss": 2.332444190979004, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.4285714285714286, "percentage": 35.71, "elapsed_time": "2:06:39", "remaining_time": "3:47:58"}
+{"current_steps": 225, "total_steps": 616, "loss": 2.1074, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.075399762275433e-07, "epoch": 1.4610389610389611, "percentage": 36.53, "elapsed_time": "2:09:31", "remaining_time": "3:45:05"}
+{"current_steps": 225, "total_steps": 616, "loss": null, "eval_loss": 2.332444667816162, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.4610389610389611, "percentage": 36.53, "elapsed_time": "2:09:31", "remaining_time": "3:45:05"}
+{"current_steps": 230, "total_steps": 616, "loss": 2.1251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.868919626464468e-07, "epoch": 1.4935064935064934, "percentage": 37.34, "elapsed_time": "2:12:23", "remaining_time": "3:42:11"}
+{"current_steps": 230, "total_steps": 616, "loss": null, "eval_loss": 2.332214117050171, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.4935064935064934, "percentage": 37.34, "elapsed_time": "2:12:23", "remaining_time": "3:42:11"}
+{"current_steps": 235, "total_steps": 616, "loss": 2.0629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6873419265440147e-07, "epoch": 1.525974025974026, "percentage": 38.15, "elapsed_time": "2:15:17", "remaining_time": "3:39:21"}
+{"current_steps": 235, "total_steps": 616, "loss": null, "eval_loss": 2.3318090438842773, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.525974025974026, "percentage": 38.15, "elapsed_time": "2:15:17", "remaining_time": "3:39:21"}
+{"current_steps": 240, "total_steps": 616, "loss": 2.0872, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5279302463838363e-07, "epoch": 1.5584415584415585, "percentage": 38.96, "elapsed_time": "2:18:10", "remaining_time": "3:36:28"}
+{"current_steps": 240, "total_steps": 616, "loss": null, "eval_loss": 2.331209659576416, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.5584415584415585, "percentage": 38.96, "elapsed_time": "2:18:10", "remaining_time": "3:36:28"}
+{"current_steps": 245, "total_steps": 616, "loss": 2.0994, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3882187969941973e-07, "epoch": 1.5909090909090908, "percentage": 39.77, "elapsed_time": "2:21:03", "remaining_time": "3:33:35"}
+{"current_steps": 245, "total_steps": 616, "loss": null, "eval_loss": 2.3310420513153076, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.5909090909090908, "percentage": 39.77, "elapsed_time": "2:21:03", "remaining_time": "3:33:35"}
+{"current_steps": 250, "total_steps": 616, "loss": 2.0879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2659887006635567e-07, "epoch": 1.6233766233766234, "percentage": 40.58, "elapsed_time": "2:23:57", "remaining_time": "3:30:44"}
+{"current_steps": 250, "total_steps": 616, "loss": null, "eval_loss": 2.3307697772979736, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6233766233766234, "percentage": 40.58, "elapsed_time": "2:23:57", "remaining_time": "3:30:44"}
+{"current_steps": 255, "total_steps": 616, "loss": 2.0623, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.159246079362766e-07, "epoch": 1.655844155844156, "percentage": 41.4, "elapsed_time": "2:26:49", "remaining_time": "3:27:51"}
+{"current_steps": 255, "total_steps": 616, "loss": null, "eval_loss": 2.3305325508117676, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.655844155844156, "percentage": 41.4, "elapsed_time": "2:26:49", "remaining_time": "3:27:51"}
+{"current_steps": 260, "total_steps": 616, "loss": 2.1054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.066201831539531e-07, "epoch": 1.6883116883116882, "percentage": 42.21, "elapsed_time": "2:29:42", "remaining_time": "3:24:58"}
+{"current_steps": 260, "total_steps": 616, "loss": null, "eval_loss": 2.3303236961364746, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6883116883116882, "percentage": 42.21, "elapsed_time": "2:29:42", "remaining_time": "3:24:58"}
+{"current_steps": 265, "total_steps": 616, "loss": 2.0736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.852529874587936e-08, "epoch": 1.7207792207792207, "percentage": 43.02, "elapsed_time": "2:32:35", "remaining_time": "3:22:07"}
+{"current_steps": 265, "total_steps": 616, "loss": null, "eval_loss": 2.330125093460083, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.7207792207792207, "percentage": 43.02, "elapsed_time": "2:32:35", "remaining_time": "3:22:07"}
+{"current_steps": 270, "total_steps": 616, "loss": 2.1146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.149655390382344e-08, "epoch": 1.7532467532467533, "percentage": 43.83, "elapsed_time": "2:35:29", "remaining_time": "3:19:15"}
+{"current_steps": 270, "total_steps": 616, "loss": null, "eval_loss": 2.330049514770508, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.7532467532467533, "percentage": 43.83, "elapsed_time": "2:35:29", "remaining_time": "3:19:15"}
+{"current_steps": 275, "total_steps": 616, "loss": 2.0444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.540586456892e-08, "epoch": 1.7857142857142856, "percentage": 44.64, "elapsed_time": "2:38:21", "remaining_time": "3:16:21"}
+{"current_steps": 275, "total_steps": 616, "loss": null, "eval_loss": 2.330078125, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.7857142857142856, "percentage": 44.64, "elapsed_time": "2:38:21", "remaining_time": "3:16:21"}
+{"current_steps": 280, "total_steps": 616, "loss": 2.0541, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.013901230085373e-08, "epoch": 1.8181818181818183, "percentage": 45.45, "elapsed_time": "2:41:14", "remaining_time": "3:13:29"}
+{"current_steps": 280, "total_steps": 616, "loss": null, "eval_loss": 2.3301477432250977, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.8181818181818183, "percentage": 45.45, "elapsed_time": "2:41:14", "remaining_time": "3:13:29"}
+{"current_steps": 285, "total_steps": 616, "loss": 2.1333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.55943126282245e-08, "epoch": 1.8506493506493507, "percentage": 46.27, "elapsed_time": "2:44:08", "remaining_time": "3:10:37"}
+{"current_steps": 285, "total_steps": 616, "loss": null, "eval_loss": 2.3300485610961914, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.8506493506493507, "percentage": 46.27, "elapsed_time": "2:44:08", "remaining_time": "3:10:37"}
+{"current_steps": 290, "total_steps": 616, "loss": 2.1101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.168139456635546e-08, "epoch": 1.883116883116883, "percentage": 47.08, "elapsed_time": "2:47:01", "remaining_time": "3:07:45"}
+{"current_steps": 290, "total_steps": 616, "loss": null, "eval_loss": 2.3298966884613037, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.883116883116883, "percentage": 47.08, "elapsed_time": "2:47:01", "remaining_time": "3:07:45"}
+{"current_steps": 295, "total_steps": 616, "loss": 2.0234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.832008345822561e-08, "epoch": 1.9155844155844157, "percentage": 47.89, "elapsed_time": "2:49:55", "remaining_time": "3:04:54"}
+{"current_steps": 295, "total_steps": 616, "loss": null, "eval_loss": 2.3297622203826904, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.9155844155844157, "percentage": 47.89, "elapsed_time": "2:49:55", "remaining_time": "3:04:54"}
+{"current_steps": 300, "total_steps": 616, "loss": 2.0671, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.543937974344862e-08, "epoch": 1.948051948051948, "percentage": 48.7, "elapsed_time": "2:52:48", "remaining_time": "3:02:01"}
+{"current_steps": 300, "total_steps": 616, "loss": null, "eval_loss": 2.3298168182373047, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.948051948051948, "percentage": 48.7, "elapsed_time": "2:52:48", "remaining_time": "3:02:01"}
+{"current_steps": 305, "total_steps": 616, "loss": 2.083, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.297652668988982e-08, "epoch": 1.9805194805194806, "percentage": 49.51, "elapsed_time": "2:55:41", "remaining_time": "2:59:08"}
+{"current_steps": 305, "total_steps": 616, "loss": null, "eval_loss": 2.329840660095215, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.9805194805194806, "percentage": 49.51, "elapsed_time": "2:55:41", "remaining_time": "2:59:08"}
+{"current_steps": 310, "total_steps": 616, "loss": 2.0417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.087616053317391e-08, "epoch": 2.012987012987013, "percentage": 50.32, "elapsed_time": "2:58:34", "remaining_time": "2:56:15"}
+{"current_steps": 310, "total_steps": 616, "loss": null, "eval_loss": 2.329859972000122, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.012987012987013, "percentage": 50.32, "elapsed_time": "2:58:34", "remaining_time": "2:56:15"}
+{"current_steps": 315, "total_steps": 616, "loss": 2.0784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.908953686156436e-08, "epoch": 2.0454545454545454, "percentage": 51.14, "elapsed_time": "3:01:27", "remaining_time": "2:53:24"}
+{"current_steps": 315, "total_steps": 616, "loss": null, "eval_loss": 2.330275297164917, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0454545454545454, "percentage": 51.14, "elapsed_time": "3:01:27", "remaining_time": "2:53:24"}
+{"current_steps": 320, "total_steps": 616, "loss": 2.058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.757382745804978e-08, "epoch": 2.0779220779220777, "percentage": 51.95, "elapsed_time": "3:04:19", "remaining_time": "2:50:30"}
+{"current_steps": 320, "total_steps": 616, "loss": null, "eval_loss": 2.3307604789733887, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0779220779220777, "percentage": 51.95, "elapsed_time": "3:04:19", "remaining_time": "2:50:30"}
+{"current_steps": 325, "total_steps": 616, "loss": 2.0524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.629148216850244e-08, "epoch": 2.1103896103896105, "percentage": 52.76, "elapsed_time": "3:07:13", "remaining_time": "2:47:38"}
+{"current_steps": 325, "total_steps": 616, "loss": null, "eval_loss": 2.3312222957611084, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.1103896103896105, "percentage": 52.76, "elapsed_time": "3:07:13", "remaining_time": "2:47:38"}
+{"current_steps": 330, "total_steps": 616, "loss": 2.0318, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.5209650705026766e-08, "epoch": 2.142857142857143, "percentage": 53.57, "elapsed_time": "3:10:06", "remaining_time": "2:44:45"}
+{"current_steps": 330, "total_steps": 616, "loss": null, "eval_loss": 2.3315961360931396, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.142857142857143, "percentage": 53.57, "elapsed_time": "3:10:06", "remaining_time": "2:44:45"}
+{"current_steps": 335, "total_steps": 616, "loss": 2.0914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.429965961761988e-08, "epoch": 2.175324675324675, "percentage": 54.38, "elapsed_time": "3:13:00", "remaining_time": "2:41:53"}
+{"current_steps": 335, "total_steps": 616, "loss": null, "eval_loss": 2.3318288326263428, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.175324675324675, "percentage": 54.38, "elapsed_time": "3:13:00", "remaining_time": "2:41:53"}
+{"current_steps": 340, "total_steps": 616, "loss": 2.0319, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.353653997555268e-08, "epoch": 2.207792207792208, "percentage": 55.19, "elapsed_time": "3:15:53", "remaining_time": "2:39:00"}
+{"current_steps": 340, "total_steps": 616, "loss": null, "eval_loss": 2.3320202827453613, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.207792207792208, "percentage": 55.19, "elapsed_time": "3:15:53", "remaining_time": "2:39:00"}
+{"current_steps": 345, "total_steps": 616, "loss": 2.0099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.289860159296223e-08, "epoch": 2.24025974025974, "percentage": 56.01, "elapsed_time": "3:18:45", "remaining_time": "2:36:07"}
+{"current_steps": 345, "total_steps": 616, "loss": null, "eval_loss": 2.3321921825408936, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.24025974025974, "percentage": 56.01, "elapsed_time": "3:18:45", "remaining_time": "2:36:07"}
+{"current_steps": 350, "total_steps": 616, "loss": 2.075, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.236704991153409e-08, "epoch": 2.2727272727272725, "percentage": 56.82, "elapsed_time": "3:21:36", "remaining_time": "2:33:13"}
+{"current_steps": 350, "total_steps": 616, "loss": null, "eval_loss": 2.3322551250457764, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.2727272727272725, "percentage": 56.82, "elapsed_time": "3:21:36", "remaining_time": "2:33:13"}
+{"current_steps": 355, "total_steps": 616, "loss": 2.0444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.192564191734593e-08, "epoch": 2.3051948051948052, "percentage": 57.63, "elapsed_time": "3:24:31", "remaining_time": "2:30:21"}
+{"current_steps": 355, "total_steps": 616, "loss": null, "eval_loss": 2.3323724269866943, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.3051948051948052, "percentage": 57.63, "elapsed_time": "3:24:31", "remaining_time": "2:30:21"}
+{"current_steps": 360, "total_steps": 616, "loss": 2.0428, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.1560377719433e-08, "epoch": 2.3376623376623376, "percentage": 58.44, "elapsed_time": "3:27:24", "remaining_time": "2:27:29"}
+{"current_steps": 360, "total_steps": 616, "loss": null, "eval_loss": 2.332462787628174, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.3376623376623376, "percentage": 58.44, "elapsed_time": "3:27:24", "remaining_time": "2:27:29"}
+{"current_steps": 365, "total_steps": 616, "loss": 2.0612, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.12592246549025e-08, "epoch": 2.3701298701298703, "percentage": 59.25, "elapsed_time": "3:30:17", "remaining_time": "2:24:36"}
+{"current_steps": 365, "total_steps": 616, "loss": null, "eval_loss": 2.3325576782226562, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.3701298701298703, "percentage": 59.25, "elapsed_time": "3:30:17", "remaining_time": "2:24:36"}
+{"current_steps": 370, "total_steps": 616, "loss": 2.1078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.101187100994392e-08, "epoch": 2.4025974025974026, "percentage": 60.06, "elapsed_time": "3:33:11", "remaining_time": "2:21:44"}
+{"current_steps": 370, "total_steps": 616, "loss": null, "eval_loss": 2.3326776027679443, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.4025974025974026, "percentage": 60.06, "elapsed_time": "3:33:11", "remaining_time": "2:21:44"}
+{"current_steps": 375, "total_steps": 616, "loss": 2.0643, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0809506658318405e-08, "epoch": 2.435064935064935, "percentage": 60.88, "elapsed_time": "3:36:04", "remaining_time": "2:18:51"}
+{"current_steps": 375, "total_steps": 616, "loss": null, "eval_loss": 2.332730531692505, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.435064935064935, "percentage": 60.88, "elapsed_time": "3:36:04", "remaining_time": "2:18:51"}
+{"current_steps": 380, "total_steps": 616, "loss": 2.0667, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.06446281193206e-08, "epoch": 2.4675324675324677, "percentage": 61.69, "elapsed_time": "3:38:56", "remaining_time": "2:15:58"}
+{"current_steps": 380, "total_steps": 616, "loss": null, "eval_loss": 2.3326008319854736, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.4675324675324677, "percentage": 61.69, "elapsed_time": "3:38:56", "remaining_time": "2:15:58"}
+{"current_steps": 385, "total_steps": 616, "loss": 2.0285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.051086572623794e-08, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "3:41:49", "remaining_time": "2:13:05"}
+{"current_steps": 385, "total_steps": 616, "loss": null, "eval_loss": 2.3324227333068848, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "3:41:49", "remaining_time": "2:13:05"}
+{"current_steps": 390, "total_steps": 616, "loss": 2.0571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.040283077442462e-08, "epoch": 2.5324675324675323, "percentage": 63.31, "elapsed_time": "3:44:41", "remaining_time": "2:10:12"}
+{"current_steps": 390, "total_steps": 616, "loss": null, "eval_loss": 2.332240343093872, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5324675324675323, "percentage": 63.31, "elapsed_time": "3:44:41", "remaining_time": "2:10:12"}
+{"current_steps": 395, "total_steps": 616, "loss": 2.0209, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0315980685690885e-08, "epoch": 2.564935064935065, "percentage": 64.12, "elapsed_time": "3:47:33", "remaining_time": "2:07:19"}
+{"current_steps": 395, "total_steps": 616, "loss": null, "eval_loss": 2.332184076309204, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.564935064935065, "percentage": 64.12, "elapsed_time": "3:47:33", "remaining_time": "2:07:19"}
+{"current_steps": 400, "total_steps": 616, "loss": 2.0537, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.024650038320448e-08, "epoch": 2.5974025974025974, "percentage": 64.94, "elapsed_time": "3:50:26", "remaining_time": "2:04:26"}
+{"current_steps": 400, "total_steps": 616, "loss": null, "eval_loss": 2.3322784900665283, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5974025974025974, "percentage": 64.94, "elapsed_time": "3:50:26", "remaining_time": "2:04:26"}
+{"current_steps": 405, "total_steps": 616, "loss": 2.0138, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.019119821892392e-08, "epoch": 2.62987012987013, "percentage": 65.75, "elapsed_time": "3:53:17", "remaining_time": "2:01:32"}
+{"current_steps": 405, "total_steps": 616, "loss": null, "eval_loss": 2.3324267864227295, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.62987012987013, "percentage": 65.75, "elapsed_time": "3:53:17", "remaining_time": "2:01:32"}
+{"current_steps": 410, "total_steps": 616, "loss": 2.0772, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0147414934136414e-08, "epoch": 2.6623376623376624, "percentage": 66.56, "elapsed_time": "3:56:07", "remaining_time": "1:58:38"}
+{"current_steps": 410, "total_steps": 616, "loss": null, "eval_loss": 2.33242130279541, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.6623376623376624, "percentage": 66.56, "elapsed_time": "3:56:07", "remaining_time": "1:58:38"}
+{"current_steps": 415, "total_steps": 616, "loss": 2.039, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.011294426335357e-08, "epoch": 2.6948051948051948, "percentage": 67.37, "elapsed_time": "3:58:59", "remaining_time": "1:55:45"}
+{"current_steps": 415, "total_steps": 616, "loss": null, "eval_loss": 2.332331895828247, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.6948051948051948, "percentage": 67.37, "elapsed_time": "3:58:59", "remaining_time": "1:55:45"}
+{"current_steps": 420, "total_steps": 616, "loss": 2.0181, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.008596391301209e-08, "epoch": 2.7272727272727275, "percentage": 68.18, "elapsed_time": "4:01:51", "remaining_time": "1:52:52"}
+{"current_steps": 420, "total_steps": 616, "loss": null, "eval_loss": 2.3321642875671387, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.7272727272727275, "percentage": 68.18, "elapsed_time": "4:01:51", "remaining_time": "1:52:52"}
+{"current_steps": 425, "total_steps": 616, "loss": 2.0484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.006497575951353e-08, "epoch": 2.75974025974026, "percentage": 68.99, "elapsed_time": "4:04:43", "remaining_time": "1:49:59"}
+{"current_steps": 425, "total_steps": 616, "loss": null, "eval_loss": 2.3319947719573975, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.75974025974026, "percentage": 68.99, "elapsed_time": "4:04:43", "remaining_time": "1:49:59"}
+{"current_steps": 430, "total_steps": 616, "loss": 2.0224, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.004875421648668e-08, "epoch": 2.792207792207792, "percentage": 69.81, "elapsed_time": "4:07:35", "remaining_time": "1:47:05"}
+{"current_steps": 430, "total_steps": 616, "loss": null, "eval_loss": 2.3319504261016846, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.792207792207792, "percentage": 69.81, "elapsed_time": "4:07:35", "remaining_time": "1:47:05"}
+{"current_steps": 435, "total_steps": 616, "loss": 2.0732, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0036301819129696e-08, "epoch": 2.824675324675325, "percentage": 70.62, "elapsed_time": "4:10:27", "remaining_time": "1:44:12"}
+{"current_steps": 435, "total_steps": 616, "loss": null, "eval_loss": 2.332017421722412, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.824675324675325, "percentage": 70.62, "elapsed_time": "4:10:27", "remaining_time": "1:44:12"}
+{"current_steps": 440, "total_steps": 616, "loss": 2.0499, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.002681116443942e-08, "epoch": 2.857142857142857, "percentage": 71.43, "elapsed_time": "4:13:17", "remaining_time": "1:41:19"}
+{"current_steps": 440, "total_steps": 616, "loss": null, "eval_loss": 2.3320865631103516, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.857142857142857, "percentage": 71.43, "elapsed_time": "4:13:17", "remaining_time": "1:41:19"}
+{"current_steps": 445, "total_steps": 616, "loss": 2.0498, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.001963243040635e-08, "epoch": 2.8896103896103895, "percentage": 72.24, "elapsed_time": "4:16:10", "remaining_time": "1:38:26"}
+{"current_steps": 445, "total_steps": 616, "loss": null, "eval_loss": 2.332113742828369, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.8896103896103895, "percentage": 72.24, "elapsed_time": "4:16:10", "remaining_time": "1:38:26"}
+{"current_steps": 450, "total_steps": 616, "loss": 2.0472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0014245775181084e-08, "epoch": 2.9220779220779223, "percentage": 73.05, "elapsed_time": "4:19:01", "remaining_time": "1:35:33"}
+{"current_steps": 450, "total_steps": 616, "loss": null, "eval_loss": 2.33201003074646, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9220779220779223, "percentage": 73.05, "elapsed_time": "4:19:01", "remaining_time": "1:35:33"}
+{"current_steps": 455, "total_steps": 616, "loss": 2.1327, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0010237989128404e-08, "epoch": 2.9545454545454546, "percentage": 73.86, "elapsed_time": "4:21:53", "remaining_time": "1:32:40"}
+{"current_steps": 455, "total_steps": 616, "loss": null, "eval_loss": 2.3319180011749268, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9545454545454546, "percentage": 73.86, "elapsed_time": "4:21:53", "remaining_time": "1:32:40"}
+{"current_steps": 460, "total_steps": 616, "loss": 2.0642, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.00072828388965e-08, "epoch": 2.987012987012987, "percentage": 74.68, "elapsed_time": "4:24:43", "remaining_time": "1:29:46"}
+{"current_steps": 460, "total_steps": 616, "loss": null, "eval_loss": 2.3318610191345215, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.987012987012987, "percentage": 74.68, "elapsed_time": "4:24:43", "remaining_time": "1:29:46"}
+{"current_steps": 465, "total_steps": 616, "loss": 2.0654, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000512460345108e-08, "epoch": 3.0194805194805197, "percentage": 75.49, "elapsed_time": "4:27:33", "remaining_time": "1:26:53"}

trainer_state.json

@@ -0,0 +1,501 @@
+{
+  "best_metric": 2.326810598373413,
+  "best_model_checkpoint": "./output/training_results/C015_llama3-8b-base_pretrain_20240428_005832/checkpoint-155",
+  "epoch": 1.0064935064935066,
+  "eval_steps": 5,
+  "global_step": 155,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006493506493506494,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 2.6141,
+      "step": 1
+    },
+    {
+      "epoch": 0.006493506493506494,
+      "eval_loss": 2.635435104370117,
+      "eval_runtime": 13.3872,
+      "eval_samples_per_second": 81.421,
+      "eval_steps_per_second": 0.672,
+      "step": 1
+    },
+    {
+      "epoch": 0.032467532467532464,
+      "grad_norm": 3.736102227472634,
+      "learning_rate": 2.25e-06,
+      "loss": 2.657,
+      "step": 5
+    },
+    {
+      "epoch": 0.032467532467532464,
+      "eval_loss": 2.6205813884735107,
+      "eval_runtime": 13.3001,
+      "eval_samples_per_second": 81.955,
+      "eval_steps_per_second": 0.677,
+      "step": 5
+    },
+    {
+      "epoch": 0.06493506493506493,
+      "grad_norm": 2.9360680843951172,
+      "learning_rate": 5.25e-06,
+      "loss": 2.6337,
+      "step": 10
+    },
+    {
+      "epoch": 0.06493506493506493,
+      "eval_loss": 2.5846035480499268,
+      "eval_runtime": 13.3634,
+      "eval_samples_per_second": 81.566,
+      "eval_steps_per_second": 0.673,
+      "step": 10
+    },
+    {
+      "epoch": 0.09740259740259741,
+      "grad_norm": 2.4441290480949354,
+      "learning_rate": 9e-06,
+      "loss": 2.5268,
+      "step": 15
+    },
+    {
+      "epoch": 0.09740259740259741,
+      "eval_loss": 2.5515594482421875,
+      "eval_runtime": 13.3452,
+      "eval_samples_per_second": 81.677,
+      "eval_steps_per_second": 0.674,
+      "step": 15
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "grad_norm": 2.5052749297132455,
+      "learning_rate": 1.275e-05,
+      "loss": 2.5275,
+      "step": 20
+    },
+    {
+      "epoch": 0.12987012987012986,
+      "eval_loss": 2.5321404933929443,
+      "eval_runtime": 13.3665,
+      "eval_samples_per_second": 81.547,
+      "eval_steps_per_second": 0.673,
+      "step": 20
+    },
+    {
+      "epoch": 0.16233766233766234,
+      "grad_norm": 2.570439112365278,
+      "learning_rate": 1.4457320927100615e-05,
+      "loss": 2.5005,
+      "step": 25
+    },
+    {
+      "epoch": 0.16233766233766234,
+      "eval_loss": 2.513052225112915,
+      "eval_runtime": 13.3936,
+      "eval_samples_per_second": 81.382,
+      "eval_steps_per_second": 0.672,
+      "step": 25
+    },
+    {
+      "epoch": 0.19480519480519481,
+      "grad_norm": 2.1653661003420974,
+      "learning_rate": 1.3178060763055965e-05,
+      "loss": 2.5339,
+      "step": 30
+    },
+    {
+      "epoch": 0.19480519480519481,
+      "eval_loss": 2.496060609817505,
+      "eval_runtime": 13.4225,
+      "eval_samples_per_second": 81.207,
+      "eval_steps_per_second": 0.671,
+      "step": 30
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 2.4298156508230955,
+      "learning_rate": 1.200291011775234e-05,
+      "loss": 2.5335,
+      "step": 35
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "eval_loss": 2.4807701110839844,
+      "eval_runtime": 13.3964,
+      "eval_samples_per_second": 81.365,
+      "eval_steps_per_second": 0.672,
+      "step": 35
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 2.371474812035467,
+      "learning_rate": 1.092418047398154e-05,
+      "loss": 2.4252,
+      "step": 40
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "eval_loss": 2.464339256286621,
+      "eval_runtime": 13.3751,
+      "eval_samples_per_second": 81.495,
+      "eval_steps_per_second": 0.673,
+      "step": 40
+    },
+    {
+      "epoch": 0.2922077922077922,
+      "grad_norm": 2.233872363768768,
+      "learning_rate": 9.934692235419926e-06,
+      "loss": 2.4445,
+      "step": 45
+    },
+    {
+      "epoch": 0.2922077922077922,
+      "eval_loss": 2.4518375396728516,
+      "eval_runtime": 13.4165,
+      "eval_samples_per_second": 81.243,
+      "eval_steps_per_second": 0.671,
+      "step": 45
+    },
+    {
+      "epoch": 0.3246753246753247,
+      "grad_norm": 2.228351075418733,
+      "learning_rate": 9.02774500281382e-06,
+      "loss": 2.4594,
+      "step": 50
+    },
+    {
+      "epoch": 0.3246753246753247,
+      "eval_loss": 2.4393582344055176,
+      "eval_runtime": 13.3552,
+      "eval_samples_per_second": 81.616,
+      "eval_steps_per_second": 0.674,
+      "step": 50
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 2.2182357621988693,
+      "learning_rate": 8.197089350822288e-06,
+      "loss": 2.4498,
+      "step": 55
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "eval_loss": 2.4287211894989014,
+      "eval_runtime": 13.3236,
+      "eval_samples_per_second": 81.809,
+      "eval_steps_per_second": 0.675,
+      "step": 55
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 2.3864673038770854,
+      "learning_rate": 7.436900041840997e-06,
+      "loss": 2.3821,
+      "step": 60
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "eval_loss": 2.4184141159057617,
+      "eval_runtime": 13.3882,
+      "eval_samples_per_second": 81.415,
+      "eval_steps_per_second": 0.672,
+      "step": 60
+    },
+    {
+      "epoch": 0.42207792207792205,
+      "grad_norm": 1.9510161344368442,
+      "learning_rate": 6.741750615310939e-06,
+      "loss": 2.4317,
+      "step": 65
+    },
+    {
+      "epoch": 0.42207792207792205,
+      "eval_loss": 2.4091267585754395,
+      "eval_runtime": 13.358,
+      "eval_samples_per_second": 81.599,
+      "eval_steps_per_second": 0.674,
+      "step": 65
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.9482390057148204,
+      "learning_rate": 6.106589293139538e-06,
+      "loss": 2.3931,
+      "step": 70
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "eval_loss": 2.40012788772583,
+      "eval_runtime": 13.4261,
+      "eval_samples_per_second": 81.185,
+      "eval_steps_per_second": 0.67,
+      "step": 70
+    },
+    {
+      "epoch": 0.487012987012987,
+      "grad_norm": 2.112671713085814,
+      "learning_rate": 5.526716143930102e-06,
+      "loss": 2.3695,
+      "step": 75
+    },
+    {
+      "epoch": 0.487012987012987,
+      "eval_loss": 2.3934359550476074,
+      "eval_runtime": 13.3826,
+      "eval_samples_per_second": 81.449,
+      "eval_steps_per_second": 0.673,
+      "step": 75
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 2.0831282196798315,
+      "learning_rate": 4.997761450728939e-06,
+      "loss": 2.3981,
+      "step": 80
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "eval_loss": 2.3855459690093994,
+      "eval_runtime": 13.4481,
+      "eval_samples_per_second": 81.052,
+      "eval_steps_per_second": 0.669,
+      "step": 80
+    },
+    {
+      "epoch": 0.551948051948052,
+      "grad_norm": 1.850619691727126,
+      "learning_rate": 4.515665228960038e-06,
+      "loss": 2.3952,
+      "step": 85
+    },
+    {
+      "epoch": 0.551948051948052,
+      "eval_loss": 2.37890887260437,
+      "eval_runtime": 13.4148,
+      "eval_samples_per_second": 81.254,
+      "eval_steps_per_second": 0.671,
+      "step": 85
+    },
+    {
+      "epoch": 0.5844155844155844,
+      "grad_norm": 1.92650957243675,
+      "learning_rate": 4.0766578431245434e-06,
+      "loss": 2.4137,
+      "step": 90
+    },
+    {
+      "epoch": 0.5844155844155844,
+      "eval_loss": 2.3720638751983643,
+      "eval_runtime": 13.3735,
+      "eval_samples_per_second": 81.504,
+      "eval_steps_per_second": 0.673,
+      "step": 90
+    },
+    {
+      "epoch": 0.6168831168831169,
+      "grad_norm": 1.9166696037048836,
+      "learning_rate": 3.6772416726983343e-06,
+      "loss": 2.3614,
+      "step": 95
+    },
+    {
+      "epoch": 0.6168831168831169,
+      "eval_loss": 2.366936683654785,
+      "eval_runtime": 13.4784,
+      "eval_samples_per_second": 80.87,
+      "eval_steps_per_second": 0.668,
+      "step": 95
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "grad_norm": 1.9337017607143168,
+      "learning_rate": 3.3141737794662055e-06,
+      "loss": 2.3467,
+      "step": 100
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "eval_loss": 2.361203193664551,
+      "eval_runtime": 13.4232,
+      "eval_samples_per_second": 81.203,
+      "eval_steps_per_second": 0.67,
+      "step": 100
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 1.800114241259619,
+      "learning_rate": 2.984449530286649e-06,
+      "loss": 2.4012,
+      "step": 105
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "eval_loss": 2.3568994998931885,
+      "eval_runtime": 13.3387,
+      "eval_samples_per_second": 81.717,
+      "eval_steps_per_second": 0.675,
+      "step": 105
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.8774879479561137,
+      "learning_rate": 2.685287130987944e-06,
+      "loss": 2.3224,
+      "step": 110
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "eval_loss": 2.352806329727173,
+      "eval_runtime": 13.3565,
+      "eval_samples_per_second": 81.608,
+      "eval_steps_per_second": 0.674,
+      "step": 110
+    },
+    {
+      "epoch": 0.7467532467532467,
+      "grad_norm": 1.8730632952307495,
+      "learning_rate": 2.4141130287548048e-06,
+      "loss": 2.3348,
+      "step": 115
+    },
+    {
+      "epoch": 0.7467532467532467,
+      "eval_loss": 2.348268985748291,
+      "eval_runtime": 13.3814,
+      "eval_samples_per_second": 81.456,
+      "eval_steps_per_second": 0.673,
+      "step": 115
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 1.9700141360167842,
+      "learning_rate": 2.168548141976706e-06,
+      "loss": 2.3573,
+      "step": 120
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "eval_loss": 2.3447518348693848,
+      "eval_runtime": 13.3872,
+      "eval_samples_per_second": 81.421,
+      "eval_steps_per_second": 0.672,
+      "step": 120
+    },
+    {
+      "epoch": 0.8116883116883117,
+      "grad_norm": 1.8580210267921047,
+      "learning_rate": 1.946394878094437e-06,
+      "loss": 2.306,
+      "step": 125
+    },
+    {
+      "epoch": 0.8116883116883117,
+      "eval_loss": 2.3411996364593506,
+      "eval_runtime": 13.4315,
+      "eval_samples_per_second": 81.153,
+      "eval_steps_per_second": 0.67,
+      "step": 125
+    },
+    {
+      "epoch": 0.8441558441558441,
+      "grad_norm": 1.8818877549057513,
+      "learning_rate": 1.745624901501792e-06,
+      "loss": 2.342,
+      "step": 130
+    },
+    {
+      "epoch": 0.8441558441558441,
+      "eval_loss": 2.338190793991089,
+      "eval_runtime": 13.3467,
+      "eval_samples_per_second": 81.668,
+      "eval_steps_per_second": 0.674,
+      "step": 130
+    },
+    {
+      "epoch": 0.8766233766233766,
+      "grad_norm": 1.9087045844270383,
+      "learning_rate": 1.564367615035273e-06,
+      "loss": 2.3045,
+      "step": 135
+    },
+    {
+      "epoch": 0.8766233766233766,
+      "eval_loss": 2.3356211185455322,
+      "eval_runtime": 13.3981,
+      "eval_samples_per_second": 81.355,
+      "eval_steps_per_second": 0.672,
+      "step": 135
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.8238462929669437,
+      "learning_rate": 1.4008993200171148e-06,
+      "loss": 2.2959,
+      "step": 140
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "eval_loss": 2.3329813480377197,
+      "eval_runtime": 13.4034,
+      "eval_samples_per_second": 81.322,
+      "eval_steps_per_second": 0.671,
+      "step": 140
+    },
+    {
+      "epoch": 0.9415584415584416,
+      "grad_norm": 1.824603087231258,
+      "learning_rate": 1.253633021206854e-06,
+      "loss": 2.3545,
+      "step": 145
+    },
+    {
+      "epoch": 0.9415584415584416,
+      "eval_loss": 2.330482006072998,
+      "eval_runtime": 13.3871,
+      "eval_samples_per_second": 81.422,
+      "eval_steps_per_second": 0.672,
+      "step": 145
+    },
+    {
+      "epoch": 0.974025974025974,
+      "grad_norm": 1.7913666925001428,
+      "learning_rate": 1.1211088443646446e-06,
+      "loss": 2.3446,
+      "step": 150
+    },
+    {
+      "epoch": 0.974025974025974,
+      "eval_loss": 2.3284924030303955,
+      "eval_runtime": 13.3985,
+      "eval_samples_per_second": 81.353,
+      "eval_steps_per_second": 0.672,
+      "step": 150
+    },
+    {
+      "epoch": 1.0064935064935066,
+      "grad_norm": 3.0555751125596067,
+      "learning_rate": 1.0019850354367667e-06,
+      "loss": 2.2502,
+      "step": 155
+    },
+    {
+      "epoch": 1.0064935064935066,
+      "eval_loss": 2.326810598373413,
+      "eval_runtime": 13.3767,
+      "eval_samples_per_second": 81.485,
+      "eval_steps_per_second": 0.673,
+      "step": 155
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 616,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 5,
+  "total_flos": 15912853831680.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42b461f9885884c0238fd9e17e3474f943ec5c6d2512d0670ebd9983efd8b89
+size 6968

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)