Delete move_cp20008

move_cp20008/config.json

@@ -1,29 +0,0 @@
-{
-  "_name_or_path": "/mnt/blob/no_token/llama-3-8b/desc_ep2_lr5e-6_g32_bs64_token/checkpoint-12352",
-  "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,
-  "mlp_bias": false,
-  "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": "bfloat16",
-  "transformers_version": "4.42.0.dev0",
-  "use_cache": false,
-  "vocab_size": 128320
-}

move_cp20008/generation_config.json

@@ -1,9 +0,0 @@
-{
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "max_length": 4096,
-  "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.42.0.dev0"
-}

move_cp20008/latest

@@ -1 +0,0 @@
-global_step20008

move_cp20008/model-00001-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5443762908cdfcafa6e0b76b2b29932adba9c3b83f41949647e0f590aa1f17ca
-size 4977222960

move_cp20008/model-00002-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:01dffd18613ba950e0d48f1b75d2af79f21510f1e2c403f86177674931d9c797
-size 4999802720

move_cp20008/model-00003-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e3b54989c6a927b01eac54b28c3303a49b0830f65d936d2d7c97ca344713d43a
-size 4915916176

move_cp20008/model-00004-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:88b63c0b4d05b6ee1bbec7f32ddca129339103693a7808345841e9379446d5f5
-size 1168663096

move_cp20008/model.safetensors.index.json

@@ -1,298 +0,0 @@
-{
-  "metadata": {
-    "total_size": 16061571072
-  },
-  "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"
-  }
-}

move_cp20008/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b525ed181af52bfa9b5f6f1351c85968bee21e7e725d7d6b55ef7104edef72c9
-size 15984

move_cp20008/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7d597c44a7934815266ed76440ccacec8655b590a06fa41a5f088f06466a78f9
-size 15984

move_cp20008/rng_state_10.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a49fd0ef07d22cefb2d112ec31b9853ac8edc197442ec5bd0bb156e7c372aedb
-size 15997

move_cp20008/rng_state_11.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:61ce7cfd0bb30203f3903bb8e9899fcbc9c008e64c4a719e7dce642ac4711164
-size 15997

move_cp20008/rng_state_12.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:059f90f7d0b7856fadfb69c04b66aef15ee2e76522f91c7d92081c4c22ec407d
-size 15997

move_cp20008/rng_state_13.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:df421c4e43665492ad76d818ddfee28b859a37043fde8b9c1a1f5b53c9b6fb3a
-size 15997

move_cp20008/rng_state_14.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:00c4b40b0da79cd5692165ed28cb75fafa9cf38d3e5621c29f95d84923a02627
-size 15997

move_cp20008/rng_state_15.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:02cdfa3a63e3b6592cac6cb16a86a54996afcd1c3bf7180bd0c5600c9fb5f0aa
-size 15997

move_cp20008/rng_state_16.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:71aed5d2d952e33ef37594a03684066f07f70a98f0674bcf6365b40bee46cd27
-size 15997

move_cp20008/rng_state_17.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e7800d997b5c7dbc4fa51f1b1a6be2427dcf6e841873be203a763a3c76252b62
-size 15997

move_cp20008/rng_state_18.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cd28deee6978d5f1076a6165fa45d63086a25ba5b157643f97ba7010cec40d08
-size 15997

move_cp20008/rng_state_19.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f2811500abf9205f099ff7c9003153c86e411bba324cc6cb3bf66345d7427269
-size 15997

move_cp20008/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dd0f37fcff72d8dd151cd68bbbc58309c978d203210530ac908a5f7b5cf21550
-size 15984

move_cp20008/rng_state_20.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8aae4c4506e2f07bffa7ee5a251103d0b643d9cf09f2968a22c9a2c46119a18f
-size 15997

move_cp20008/rng_state_21.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c4e428a4b5e0be52ae1f2b84781b18d3ad6d1e68d92ae0657803463ca62b0bc6
-size 15997

move_cp20008/rng_state_22.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de85bde5e9c0abb6befbb0422412e67352af98d1f005e7ed9d822606b00759c3
-size 15997

move_cp20008/rng_state_23.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cd743e9579765787abd8e2deffa2d3157035cb7b3dcdceea94ec3dba3d77d555
-size 15997

move_cp20008/rng_state_24.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4f5d3b7d034d1a337c9aaf01fdb6230604a8be75b6724ace61eb0204fee3aacd
-size 15997

move_cp20008/rng_state_25.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e94a891c014a26e7ae65f017a0809784b7ab41b6afb4b84b8d1bd7370f78bb85
-size 15997

move_cp20008/rng_state_26.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a6e5afd3aaee737b425422d1a1188421c15ca60bc6cbcfe4f15df5f0949c39e5
-size 15997

move_cp20008/rng_state_27.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c456e8637ddb872942d28eeb343f4c214e0d84aa28e2d86f2a75bfd775db3b66
-size 15997

move_cp20008/rng_state_28.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9df4941fec8e422903ad77bf5f44d9a70962e3fc8e48475d54adb7c6255e814b
-size 15997

move_cp20008/rng_state_29.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5b30e5129fa501cb0805975102c7fb0a539f12803fb50f4b6889ec466e74d6da
-size 15997

move_cp20008/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d6ca03a599a3c5bea8e20ea978c258f1a01dbdaf8dc144b889c627cef6f07610
-size 15984

move_cp20008/rng_state_30.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:63dc5fe36eb57f11dea08ded14cf81e224bdce594c094da74e6edce75f06d30d
-size 15997

move_cp20008/rng_state_31.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7c138ae90836288a30721dc1bd1fb326e2246b9a36de67f75ead124d3b84c222
-size 15997

move_cp20008/rng_state_4.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1d88434240324803a7f1a75423ac697d01c80c776c3ab93f79a354e01e103488
-size 15984

move_cp20008/rng_state_5.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8a563555ed94a1a4bc24658f111f3ca62b8185ef2174ae0f50f89949cb12a0ab
-size 15984

move_cp20008/rng_state_6.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ba7b95611bc3b135e50d38a67d6630d1a81bce8b2d1411d7af894f130f5e8717
-size 15984

move_cp20008/rng_state_7.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d7368d8c04dba8ce78f39b437df81648ab052fbaf92d1e22159d6454b58cf9d
-size 15984

move_cp20008/rng_state_8.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:898b448c51c7ff714aef690e6153c1130783a5a955f12f65f930f8e6309ca31b
-size 15984

move_cp20008/rng_state_9.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:96d413eacf06f23cde05292f82a01dd0d5204116bf9f21566acdd3c12f9373b0
-size 15984

move_cp20008/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:32573f3c6a3570d57b7661c7ddcaaf57d4577c4190bf413ac2b6ae663218b8b3
-size 1064

move_cp20008/special_tokens_map.json

@@ -1,23 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

move_cp20008/tokenizer_config.json

@@ -1,2105 +0,0 @@
-{
-  "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
-    },
-    "128256": {
-      "content": "<line>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "128257": {
-      "content": "<question>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "128258": {
-      "content": "<color>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "128259": {
-      "content": "<castle>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "128260": {
-      "content": "<enpassant>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|eot_id|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
-  "tokenizer_class": "PreTrainedTokenizerFast"
-}

move_cp20008/trainer_state.json

@@ -1,1593 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 4.0,
-  "eval_steps": 1000,
-  "global_step": 20008,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.019992003198720514,
-      "grad_norm": 3.2906418025602697,
-      "learning_rate": 8.319467554076539e-07,
-      "loss": 2.8478,
-      "step": 100
-    },
-    {
-      "epoch": 0.03998400639744103,
-      "grad_norm": 2.612188771411833,
-      "learning_rate": 1.6638935108153078e-06,
-      "loss": 0.2944,
-      "step": 200
-    },
-    {
-      "epoch": 0.059976009596161534,
-      "grad_norm": 1.709917815870727,
-      "learning_rate": 2.495840266222962e-06,
-      "loss": 0.2168,
-      "step": 300
-    },
-    {
-      "epoch": 0.07996801279488205,
-      "grad_norm": 2.259871031642651,
-      "learning_rate": 3.3277870216306156e-06,
-      "loss": 0.1858,
-      "step": 400
-    },
-    {
-      "epoch": 0.09996001599360256,
-      "grad_norm": 0.9215880977767715,
-      "learning_rate": 4.15973377703827e-06,
-      "loss": 0.1422,
-      "step": 500
-    },
-    {
-      "epoch": 0.11995201919232307,
-      "grad_norm": 1.0072778277609464,
-      "learning_rate": 4.991680532445924e-06,
-      "loss": 0.1008,
-      "step": 600
-    },
-    {
-      "epoch": 0.1399440223910436,
-      "grad_norm": 1.0911258381450193,
-      "learning_rate": 4.974493739372392e-06,
-      "loss": 0.0791,
-      "step": 700
-    },
-    {
-      "epoch": 0.1599360255897641,
-      "grad_norm": 0.626267425043489,
-      "learning_rate": 4.948729839748544e-06,
-      "loss": 0.0627,
-      "step": 800
-    },
-    {
-      "epoch": 0.1799280287884846,
-      "grad_norm": 0.5862003006285114,
-      "learning_rate": 4.9229659401246975e-06,
-      "loss": 0.0529,
-      "step": 900
-    },
-    {
-      "epoch": 0.19992003198720512,
-      "grad_norm": 0.8696329558011359,
-      "learning_rate": 4.897202040500851e-06,
-      "loss": 0.0463,
-      "step": 1000
-    },
-    {
-      "epoch": 0.19992003198720512,
-      "eval_loss": 0.035722002387046814,
-      "eval_runtime": 1158.0365,
-      "eval_samples_per_second": 1965.633,
-      "eval_steps_per_second": 0.48,
-      "step": 1000
-    },
-    {
-      "epoch": 0.21991203518592564,
-      "grad_norm": 0.62358371544167,
-      "learning_rate": 4.871438140877003e-06,
-      "loss": 0.0415,
-      "step": 1100
-    },
-    {
-      "epoch": 0.23990403838464613,
-      "grad_norm": 0.46764125348291113,
-      "learning_rate": 4.845674241253156e-06,
-      "loss": 0.0375,
-      "step": 1200
-    },
-    {
-      "epoch": 0.25989604158336665,
-      "grad_norm": 0.5030799455707828,
-      "learning_rate": 4.819910341629309e-06,
-      "loss": 0.0348,
-      "step": 1300
-    },
-    {
-      "epoch": 0.2798880447820872,
-      "grad_norm": 0.5817498641773395,
-      "learning_rate": 4.794146442005463e-06,
-      "loss": 0.0331,
-      "step": 1400
-    },
-    {
-      "epoch": 0.2998800479808077,
-      "grad_norm": 0.5076317594860285,
-      "learning_rate": 4.768382542381616e-06,
-      "loss": 0.0311,
-      "step": 1500
-    },
-    {
-      "epoch": 0.3198720511795282,
-      "grad_norm": 0.45084160209651897,
-      "learning_rate": 4.742618642757768e-06,
-      "loss": 0.029,
-      "step": 1600
-    },
-    {
-      "epoch": 0.3398640543782487,
-      "grad_norm": 0.539295413732545,
-      "learning_rate": 4.716854743133921e-06,
-      "loss": 0.0276,
-      "step": 1700
-    },
-    {
-      "epoch": 0.3598560575769692,
-      "grad_norm": 0.5368726004829203,
-      "learning_rate": 4.691090843510074e-06,
-      "loss": 0.0258,
-      "step": 1800
-    },
-    {
-      "epoch": 0.3798480607756897,
-      "grad_norm": 0.5065440217067927,
-      "learning_rate": 4.665326943886227e-06,
-      "loss": 0.0243,
-      "step": 1900
-    },
-    {
-      "epoch": 0.39984006397441024,
-      "grad_norm": 0.6222308594088681,
-      "learning_rate": 4.63956304426238e-06,
-      "loss": 0.0234,
-      "step": 2000
-    },
-    {
-      "epoch": 0.39984006397441024,
-      "eval_loss": 0.01707020029425621,
-      "eval_runtime": 1148.7811,
-      "eval_samples_per_second": 1981.47,
-      "eval_steps_per_second": 0.484,
-      "step": 2000
-    },
-    {
-      "epoch": 0.41983206717313076,
-      "grad_norm": 0.4846533449700183,
-      "learning_rate": 4.6137991446385325e-06,
-      "loss": 0.0225,
-      "step": 2100
-    },
-    {
-      "epoch": 0.4398240703718513,
-      "grad_norm": 0.45924196528031774,
-      "learning_rate": 4.588035245014686e-06,
-      "loss": 0.0211,
-      "step": 2200
-    },
-    {
-      "epoch": 0.45981607357057175,
-      "grad_norm": 0.4198728133739694,
-      "learning_rate": 4.562271345390839e-06,
-      "loss": 0.0201,
-      "step": 2300
-    },
-    {
-      "epoch": 0.47980807676929227,
-      "grad_norm": 0.43320867716253725,
-      "learning_rate": 4.536507445766992e-06,
-      "loss": 0.0191,
-      "step": 2400
-    },
-    {
-      "epoch": 0.4998000799680128,
-      "grad_norm": 0.4145934512072783,
-      "learning_rate": 4.510743546143144e-06,
-      "loss": 0.0181,
-      "step": 2500
-    },
-    {
-      "epoch": 0.5197920831667333,
-      "grad_norm": 0.4415066256936705,
-      "learning_rate": 4.484979646519298e-06,
-      "loss": 0.0175,
-      "step": 2600
-    },
-    {
-      "epoch": 0.5397840863654538,
-      "grad_norm": 0.4584351705324334,
-      "learning_rate": 4.459215746895451e-06,
-      "loss": 0.0171,
-      "step": 2700
-    },
-    {
-      "epoch": 0.5597760895641744,
-      "grad_norm": 0.43589491413943715,
-      "learning_rate": 4.433451847271603e-06,
-      "loss": 0.0163,
-      "step": 2800
-    },
-    {
-      "epoch": 0.5797680927628949,
-      "grad_norm": 0.3919816997022679,
-      "learning_rate": 4.407687947647756e-06,
-      "loss": 0.0155,
-      "step": 2900
-    },
-    {
-      "epoch": 0.5997600959616154,
-      "grad_norm": 0.3490072026794518,
-      "learning_rate": 4.3819240480239095e-06,
-      "loss": 0.0151,
-      "step": 3000
-    },
-    {
-      "epoch": 0.5997600959616154,
-      "eval_loss": 0.010557837784290314,
-      "eval_runtime": 1159.6719,
-      "eval_samples_per_second": 1962.861,
-      "eval_steps_per_second": 0.479,
-      "step": 3000
-    },
-    {
-      "epoch": 0.6197520991603359,
-      "grad_norm": 0.39976173846949037,
-      "learning_rate": 4.356160148400062e-06,
-      "loss": 0.0146,
-      "step": 3100
-    },
-    {
-      "epoch": 0.6397441023590564,
-      "grad_norm": 0.3686606922604611,
-      "learning_rate": 4.330396248776215e-06,
-      "loss": 0.0138,
-      "step": 3200
-    },
-    {
-      "epoch": 0.6597361055577768,
-      "grad_norm": 0.35778467966165745,
-      "learning_rate": 4.3046323491523674e-06,
-      "loss": 0.0134,
-      "step": 3300
-    },
-    {
-      "epoch": 0.6797281087564974,
-      "grad_norm": 0.4442927418718934,
-      "learning_rate": 4.278868449528521e-06,
-      "loss": 0.013,
-      "step": 3400
-    },
-    {
-      "epoch": 0.6997201119552179,
-      "grad_norm": 0.43308852994965336,
-      "learning_rate": 4.253104549904674e-06,
-      "loss": 0.0126,
-      "step": 3500
-    },
-    {
-      "epoch": 0.7197121151539384,
-      "grad_norm": 1.019254639188622,
-      "learning_rate": 4.227340650280827e-06,
-      "loss": 0.0125,
-      "step": 3600
-    },
-    {
-      "epoch": 0.7397041183526589,
-      "grad_norm": 0.36006157152672075,
-      "learning_rate": 4.20157675065698e-06,
-      "loss": 0.012,
-      "step": 3700
-    },
-    {
-      "epoch": 0.7596961215513794,
-      "grad_norm": 0.3731429313011076,
-      "learning_rate": 4.1758128510331326e-06,
-      "loss": 0.0117,
-      "step": 3800
-    },
-    {
-      "epoch": 0.7796881247501,
-      "grad_norm": 0.2863518237339844,
-      "learning_rate": 4.150048951409286e-06,
-      "loss": 0.0112,
-      "step": 3900
-    },
-    {
-      "epoch": 0.7996801279488205,
-      "grad_norm": 0.3216011950163523,
-      "learning_rate": 4.124285051785439e-06,
-      "loss": 0.0107,
-      "step": 4000
-    },
-    {
-      "epoch": 0.7996801279488205,
-      "eval_loss": 0.007380891125649214,
-      "eval_runtime": 1155.9611,
-      "eval_samples_per_second": 1969.162,
-      "eval_steps_per_second": 0.481,
-      "step": 4000
-    },
-    {
-      "epoch": 0.819672131147541,
-      "grad_norm": 0.44587188368998915,
-      "learning_rate": 4.098521152161591e-06,
-      "loss": 0.0103,
-      "step": 4100
-    },
-    {
-      "epoch": 0.8396641343462615,
-      "grad_norm": 0.3454382773343057,
-      "learning_rate": 4.0727572525377445e-06,
-      "loss": 0.0102,
-      "step": 4200
-    },
-    {
-      "epoch": 0.859656137544982,
-      "grad_norm": 0.3495069101038828,
-      "learning_rate": 4.046993352913897e-06,
-      "loss": 0.0098,
-      "step": 4300
-    },
-    {
-      "epoch": 0.8796481407437026,
-      "grad_norm": 0.3260402574229812,
-      "learning_rate": 4.02122945329005e-06,
-      "loss": 0.0095,
-      "step": 4400
-    },
-    {
-      "epoch": 0.899640143942423,
-      "grad_norm": 0.2892186356418927,
-      "learning_rate": 3.995465553666203e-06,
-      "loss": 0.0093,
-      "step": 4500
-    },
-    {
-      "epoch": 0.9196321471411435,
-      "grad_norm": 0.26994903201562426,
-      "learning_rate": 3.9697016540423565e-06,
-      "loss": 0.0093,
-      "step": 4600
-    },
-    {
-      "epoch": 0.939624150339864,
-      "grad_norm": 0.3313524103173336,
-      "learning_rate": 3.94393775441851e-06,
-      "loss": 0.0087,
-      "step": 4700
-    },
-    {
-      "epoch": 0.9596161535385845,
-      "grad_norm": 0.35432667473979634,
-      "learning_rate": 3.918173854794662e-06,
-      "loss": 0.0087,
-      "step": 4800
-    },
-    {
-      "epoch": 0.9796081567373051,
-      "grad_norm": 0.313845062033794,
-      "learning_rate": 3.892409955170815e-06,
-      "loss": 0.0084,
-      "step": 4900
-    },
-    {
-      "epoch": 0.9996001599360256,
-      "grad_norm": 0.26966046757470574,
-      "learning_rate": 3.866646055546968e-06,
-      "loss": 0.0081,
-      "step": 5000
-    },
-    {
-      "epoch": 0.9996001599360256,
-      "eval_loss": 0.0059196543879806995,
-      "eval_runtime": 1143.8848,
-      "eval_samples_per_second": 1989.951,
-      "eval_steps_per_second": 0.486,
-      "step": 5000
-    },
-    {
-      "epoch": 1.0195921631347462,
-      "grad_norm": 0.19657349130959176,
-      "learning_rate": 3.840882155923121e-06,
-      "loss": 0.0069,
-      "step": 5100
-    },
-    {
-      "epoch": 1.0395841663334666,
-      "grad_norm": 0.16149383470986645,
-      "learning_rate": 3.815118256299274e-06,
-      "loss": 0.0069,
-      "step": 5200
-    },
-    {
-      "epoch": 1.059576169532187,
-      "grad_norm": 0.17808659414609593,
-      "learning_rate": 3.7893543566754263e-06,
-      "loss": 0.0066,
-      "step": 5300
-    },
-    {
-      "epoch": 1.0795681727309077,
-      "grad_norm": 0.19769167653084443,
-      "learning_rate": 3.7635904570515795e-06,
-      "loss": 0.0066,
-      "step": 5400
-    },
-    {
-      "epoch": 1.099560175929628,
-      "grad_norm": 0.22190899844371975,
-      "learning_rate": 3.7378265574277327e-06,
-      "loss": 0.0064,
-      "step": 5500
-    },
-    {
-      "epoch": 1.1195521791283487,
-      "grad_norm": 0.20385395787887484,
-      "learning_rate": 3.7120626578038855e-06,
-      "loss": 0.0065,
-      "step": 5600
-    },
-    {
-      "epoch": 1.139544182327069,
-      "grad_norm": 0.17153152097279364,
-      "learning_rate": 3.6862987581800387e-06,
-      "loss": 0.0063,
-      "step": 5700
-    },
-    {
-      "epoch": 1.1595361855257897,
-      "grad_norm": 0.26310571695256085,
-      "learning_rate": 3.660534858556191e-06,
-      "loss": 0.0063,
-      "step": 5800
-    },
-    {
-      "epoch": 1.1795281887245102,
-      "grad_norm": 0.1766373303734902,
-      "learning_rate": 3.6347709589323442e-06,
-      "loss": 0.006,
-      "step": 5900
-    },
-    {
-      "epoch": 1.1995201919232308,
-      "grad_norm": 0.1433024740538582,
-      "learning_rate": 3.6090070593084974e-06,
-      "loss": 0.006,
-      "step": 6000
-    },
-    {
-      "epoch": 1.1995201919232308,
-      "eval_loss": 0.004465326201170683,
-      "eval_runtime": 1152.6448,
-      "eval_samples_per_second": 1974.828,
-      "eval_steps_per_second": 0.482,
-      "step": 6000
-    },
-    {
-      "epoch": 1.2195121951219512,
-      "grad_norm": 0.19682657592276392,
-      "learning_rate": 3.58324315968465e-06,
-      "loss": 0.0063,
-      "step": 6100
-    },
-    {
-      "epoch": 1.2395041983206718,
-      "grad_norm": 0.21594538200022467,
-      "learning_rate": 3.5574792600608034e-06,
-      "loss": 0.0058,
-      "step": 6200
-    },
-    {
-      "epoch": 1.2594962015193922,
-      "grad_norm": 0.1812127869687129,
-      "learning_rate": 3.5317153604369557e-06,
-      "loss": 0.0055,
-      "step": 6300
-    },
-    {
-      "epoch": 1.2794882047181129,
-      "grad_norm": 0.1438610940325648,
-      "learning_rate": 3.505951460813109e-06,
-      "loss": 0.0055,
-      "step": 6400
-    },
-    {
-      "epoch": 1.2994802079168333,
-      "grad_norm": 0.15088672988296747,
-      "learning_rate": 3.480187561189262e-06,
-      "loss": 0.0055,
-      "step": 6500
-    },
-    {
-      "epoch": 1.3194722111155537,
-      "grad_norm": 0.12082795146726928,
-      "learning_rate": 3.454423661565415e-06,
-      "loss": 0.0051,
-      "step": 6600
-    },
-    {
-      "epoch": 1.3394642143142743,
-      "grad_norm": 0.13445938749745928,
-      "learning_rate": 3.428659761941568e-06,
-      "loss": 0.0052,
-      "step": 6700
-    },
-    {
-      "epoch": 1.3594562175129947,
-      "grad_norm": 0.13753979874165334,
-      "learning_rate": 3.4028958623177205e-06,
-      "loss": 0.0053,
-      "step": 6800
-    },
-    {
-      "epoch": 1.3794482207117154,
-      "grad_norm": 0.201293244180889,
-      "learning_rate": 3.3771319626938737e-06,
-      "loss": 0.0051,
-      "step": 6900
-    },
-    {
-      "epoch": 1.3994402239104358,
-      "grad_norm": 0.17659284731298783,
-      "learning_rate": 3.351368063070027e-06,
-      "loss": 0.0049,
-      "step": 7000
-    },
-    {
-      "epoch": 1.3994402239104358,
-      "eval_loss": 0.003597887698560953,
-      "eval_runtime": 1147.8087,
-      "eval_samples_per_second": 1983.148,
-      "eval_steps_per_second": 0.484,
-      "step": 7000
-    },
-    {
-      "epoch": 1.4194322271091564,
-      "grad_norm": 0.17711208096950334,
-      "learning_rate": 3.3256041634461796e-06,
-      "loss": 0.0048,
-      "step": 7100
-    },
-    {
-      "epoch": 1.4394242303078768,
-      "grad_norm": 0.20822929942805718,
-      "learning_rate": 3.2998402638223324e-06,
-      "loss": 0.0048,
-      "step": 7200
-    },
-    {
-      "epoch": 1.4594162335065974,
-      "grad_norm": 0.15907431314922751,
-      "learning_rate": 3.274076364198485e-06,
-      "loss": 0.0047,
-      "step": 7300
-    },
-    {
-      "epoch": 1.4794082367053178,
-      "grad_norm": 0.11765503368520981,
-      "learning_rate": 3.2483124645746384e-06,
-      "loss": 0.0047,
-      "step": 7400
-    },
-    {
-      "epoch": 1.4994002399040385,
-      "grad_norm": 0.13975828179718594,
-      "learning_rate": 3.2225485649507916e-06,
-      "loss": 0.0045,
-      "step": 7500
-    },
-    {
-      "epoch": 1.5193922431027589,
-      "grad_norm": 0.15547831220542083,
-      "learning_rate": 3.196784665326944e-06,
-      "loss": 0.0045,
-      "step": 7600
-    },
-    {
-      "epoch": 1.5393842463014793,
-      "grad_norm": 0.12126479392767976,
-      "learning_rate": 3.171020765703097e-06,
-      "loss": 0.0045,
-      "step": 7700
-    },
-    {
-      "epoch": 1.5593762495002,
-      "grad_norm": 0.1487065137945884,
-      "learning_rate": 3.14525686607925e-06,
-      "loss": 0.0043,
-      "step": 7800
-    },
-    {
-      "epoch": 1.5793682526989206,
-      "grad_norm": 0.14098209486666624,
-      "learning_rate": 3.119492966455403e-06,
-      "loss": 0.0041,
-      "step": 7900
-    },
-    {
-      "epoch": 1.599360255897641,
-      "grad_norm": 0.13792767122589517,
-      "learning_rate": 3.0937290668315554e-06,
-      "loss": 0.0041,
-      "step": 8000
-    },
-    {
-      "epoch": 1.599360255897641,
-      "eval_loss": 0.003024752950295806,
-      "eval_runtime": 1148.8025,
-      "eval_samples_per_second": 1981.433,
-      "eval_steps_per_second": 0.484,
-      "step": 8000
-    },
-    {
-      "epoch": 1.6193522590963614,
-      "grad_norm": 0.13726027178372066,
-      "learning_rate": 3.0679651672077086e-06,
-      "loss": 0.0042,
-      "step": 8100
-    },
-    {
-      "epoch": 1.639344262295082,
-      "grad_norm": 0.269356212971355,
-      "learning_rate": 3.042201267583862e-06,
-      "loss": 0.0039,
-      "step": 8200
-    },
-    {
-      "epoch": 1.6593362654938026,
-      "grad_norm": 0.1676278942097669,
-      "learning_rate": 3.0164373679600146e-06,
-      "loss": 0.0039,
-      "step": 8300
-    },
-    {
-      "epoch": 1.6793282686925228,
-      "grad_norm": 0.20272208559979238,
-      "learning_rate": 2.990673468336168e-06,
-      "loss": 0.0039,
-      "step": 8400
-    },
-    {
-      "epoch": 1.6993202718912435,
-      "grad_norm": 0.11297839801035961,
-      "learning_rate": 2.96490956871232e-06,
-      "loss": 0.0039,
-      "step": 8500
-    },
-    {
-      "epoch": 1.719312275089964,
-      "grad_norm": 0.14977765570615936,
-      "learning_rate": 2.9391456690884733e-06,
-      "loss": 0.0038,
-      "step": 8600
-    },
-    {
-      "epoch": 1.7393042782886845,
-      "grad_norm": 0.162014477342941,
-      "learning_rate": 2.9133817694646265e-06,
-      "loss": 0.0037,
-      "step": 8700
-    },
-    {
-      "epoch": 1.759296281487405,
-      "grad_norm": 0.1942632350764828,
-      "learning_rate": 2.8876178698407793e-06,
-      "loss": 0.0038,
-      "step": 8800
-    },
-    {
-      "epoch": 1.7792882846861255,
-      "grad_norm": 0.13246889598416928,
-      "learning_rate": 2.8618539702169325e-06,
-      "loss": 0.0035,
-      "step": 8900
-    },
-    {
-      "epoch": 1.7992802878848462,
-      "grad_norm": 0.1370764817313647,
-      "learning_rate": 2.836090070593085e-06,
-      "loss": 0.0034,
-      "step": 9000
-    },
-    {
-      "epoch": 1.7992802878848462,
-      "eval_loss": 0.0023648806381970644,
-      "eval_runtime": 1151.149,
-      "eval_samples_per_second": 1977.394,
-      "eval_steps_per_second": 0.483,
-      "step": 9000
-    },
-    {
-      "epoch": 1.8192722910835666,
-      "grad_norm": 0.1991830186402239,
-      "learning_rate": 2.810326170969238e-06,
-      "loss": 0.0035,
-      "step": 9100
-    },
-    {
-      "epoch": 1.839264294282287,
-      "grad_norm": 0.1150829148835746,
-      "learning_rate": 2.7845622713453913e-06,
-      "loss": 0.0034,
-      "step": 9200
-    },
-    {
-      "epoch": 1.8592562974810076,
-      "grad_norm": 0.15273064038769674,
-      "learning_rate": 2.758798371721544e-06,
-      "loss": 0.0035,
-      "step": 9300
-    },
-    {
-      "epoch": 1.8792483006797283,
-      "grad_norm": 0.17453861427084028,
-      "learning_rate": 2.733034472097697e-06,
-      "loss": 0.0034,
-      "step": 9400
-    },
-    {
-      "epoch": 1.8992403038784487,
-      "grad_norm": 0.09588198900746768,
-      "learning_rate": 2.7072705724738496e-06,
-      "loss": 0.0033,
-      "step": 9500
-    },
-    {
-      "epoch": 1.919232307077169,
-      "grad_norm": 0.14501234610352706,
-      "learning_rate": 2.6815066728500028e-06,
-      "loss": 0.0032,
-      "step": 9600
-    },
-    {
-      "epoch": 1.9392243102758897,
-      "grad_norm": 0.12932702465904403,
-      "learning_rate": 2.655742773226156e-06,
-      "loss": 0.0031,
-      "step": 9700
-    },
-    {
-      "epoch": 1.9592163134746101,
-      "grad_norm": 0.14310650821413762,
-      "learning_rate": 2.6299788736023083e-06,
-      "loss": 0.0031,
-      "step": 9800
-    },
-    {
-      "epoch": 1.9792083166733305,
-      "grad_norm": 0.14342874165458733,
-      "learning_rate": 2.6042149739784615e-06,
-      "loss": 0.0031,
-      "step": 9900
-    },
-    {
-      "epoch": 1.9992003198720512,
-      "grad_norm": 0.13884167411495685,
-      "learning_rate": 2.5784510743546143e-06,
-      "loss": 0.0029,
-      "step": 10000
-    },
-    {
-      "epoch": 1.9992003198720512,
-      "eval_loss": 0.0021491902880370617,
-      "eval_runtime": 1149.9886,
-      "eval_samples_per_second": 1979.389,
-      "eval_steps_per_second": 0.483,
-      "step": 10000
-    },
-    {
-      "epoch": 2.019192323070772,
-      "grad_norm": 0.19131721356471873,
-      "learning_rate": 2.5526871747307675e-06,
-      "loss": 0.0022,
-      "step": 10100
-    },
-    {
-      "epoch": 2.0391843262694924,
-      "grad_norm": 0.10579815660482608,
-      "learning_rate": 2.5269232751069207e-06,
-      "loss": 0.0021,
-      "step": 10200
-    },
-    {
-      "epoch": 2.0591763294682126,
-      "grad_norm": 0.1459096737501663,
-      "learning_rate": 2.501159375483073e-06,
-      "loss": 0.0021,
-      "step": 10300
-    },
-    {
-      "epoch": 2.0791683326669332,
-      "grad_norm": 0.2238325151379845,
-      "learning_rate": 2.4753954758592262e-06,
-      "loss": 0.002,
-      "step": 10400
-    },
-    {
-      "epoch": 2.099160335865654,
-      "grad_norm": 0.17935702910953022,
-      "learning_rate": 2.449631576235379e-06,
-      "loss": 0.002,
-      "step": 10500
-    },
-    {
-      "epoch": 2.119152339064374,
-      "grad_norm": 0.20520620272264029,
-      "learning_rate": 2.4238676766115322e-06,
-      "loss": 0.0023,
-      "step": 10600
-    },
-    {
-      "epoch": 2.1391443422630947,
-      "grad_norm": 0.1240921861957277,
-      "learning_rate": 2.398103776987685e-06,
-      "loss": 0.002,
-      "step": 10700
-    },
-    {
-      "epoch": 2.1591363454618153,
-      "grad_norm": 0.12023170309949173,
-      "learning_rate": 2.3723398773638378e-06,
-      "loss": 0.002,
-      "step": 10800
-    },
-    {
-      "epoch": 2.179128348660536,
-      "grad_norm": 0.1561297642336451,
-      "learning_rate": 2.346575977739991e-06,
-      "loss": 0.002,
-      "step": 10900
-    },
-    {
-      "epoch": 2.199120351859256,
-      "grad_norm": 0.16225575470431738,
-      "learning_rate": 2.3208120781161437e-06,
-      "loss": 0.002,
-      "step": 11000
-    },
-    {
-      "epoch": 2.199120351859256,
-      "eval_loss": 0.001861926051788032,
-      "eval_runtime": 1153.5745,
-      "eval_samples_per_second": 1973.236,
-      "eval_steps_per_second": 0.482,
-      "step": 11000
-    },
-    {
-      "epoch": 2.2191123550579768,
-      "grad_norm": 0.14986168305029213,
-      "learning_rate": 2.295048178492297e-06,
-      "loss": 0.0021,
-      "step": 11100
-    },
-    {
-      "epoch": 2.2391043582566974,
-      "grad_norm": 0.14893816160027404,
-      "learning_rate": 2.2692842788684497e-06,
-      "loss": 0.0019,
-      "step": 11200
-    },
-    {
-      "epoch": 2.259096361455418,
-      "grad_norm": 0.18837728320673752,
-      "learning_rate": 2.2435203792446025e-06,
-      "loss": 0.0019,
-      "step": 11300
-    },
-    {
-      "epoch": 2.279088364654138,
-      "grad_norm": 0.1813771564736812,
-      "learning_rate": 2.2177564796207557e-06,
-      "loss": 0.002,
-      "step": 11400
-    },
-    {
-      "epoch": 2.299080367852859,
-      "grad_norm": 0.14890142698478906,
-      "learning_rate": 2.1919925799969085e-06,
-      "loss": 0.0019,
-      "step": 11500
-    },
-    {
-      "epoch": 2.3190723710515795,
-      "grad_norm": 0.14120304591361144,
-      "learning_rate": 2.1662286803730617e-06,
-      "loss": 0.0018,
-      "step": 11600
-    },
-    {
-      "epoch": 2.3390643742502997,
-      "grad_norm": 0.11951772767901686,
-      "learning_rate": 2.1404647807492144e-06,
-      "loss": 0.0019,
-      "step": 11700
-    },
-    {
-      "epoch": 2.3590563774490203,
-      "grad_norm": 0.1309490308886904,
-      "learning_rate": 2.114700881125367e-06,
-      "loss": 0.0018,
-      "step": 11800
-    },
-    {
-      "epoch": 2.379048380647741,
-      "grad_norm": 0.13801443520886084,
-      "learning_rate": 2.0889369815015204e-06,
-      "loss": 0.0018,
-      "step": 11900
-    },
-    {
-      "epoch": 2.3990403838464616,
-      "grad_norm": 0.1377983040904713,
-      "learning_rate": 2.063173081877673e-06,
-      "loss": 0.0018,
-      "step": 12000
-    },
-    {
-      "epoch": 2.3990403838464616,
-      "eval_loss": 0.0016944886883720756,
-      "eval_runtime": 1148.5931,
-      "eval_samples_per_second": 1981.794,
-      "eval_steps_per_second": 0.484,
-      "step": 12000
-    },
-    {
-      "epoch": 2.4190323870451818,
-      "grad_norm": 0.15861747622264824,
-      "learning_rate": 2.037409182253826e-06,
-      "loss": 0.0017,
-      "step": 12100
-    },
-    {
-      "epoch": 2.4390243902439024,
-      "grad_norm": 0.12331870013555493,
-      "learning_rate": 2.011645282629979e-06,
-      "loss": 0.0017,
-      "step": 12200
-    },
-    {
-      "epoch": 2.459016393442623,
-      "grad_norm": 0.15911577091706341,
-      "learning_rate": 1.985881383006132e-06,
-      "loss": 0.0018,
-      "step": 12300
-    },
-    {
-      "epoch": 2.4790083966413436,
-      "grad_norm": 0.16548753836493896,
-      "learning_rate": 1.960117483382285e-06,
-      "loss": 0.0016,
-      "step": 12400
-    },
-    {
-      "epoch": 2.499000399840064,
-      "grad_norm": 0.11602256920808221,
-      "learning_rate": 1.934353583758438e-06,
-      "loss": 0.0016,
-      "step": 12500
-    },
-    {
-      "epoch": 2.5189924030387845,
-      "grad_norm": 0.14251019580139415,
-      "learning_rate": 1.9085896841345907e-06,
-      "loss": 0.0017,
-      "step": 12600
-    },
-    {
-      "epoch": 2.538984406237505,
-      "grad_norm": 0.169226398045584,
-      "learning_rate": 1.8828257845107436e-06,
-      "loss": 0.0017,
-      "step": 12700
-    },
-    {
-      "epoch": 2.5589764094362257,
-      "grad_norm": 0.13552219820990755,
-      "learning_rate": 1.8570618848868966e-06,
-      "loss": 0.0016,
-      "step": 12800
-    },
-    {
-      "epoch": 2.578968412634946,
-      "grad_norm": 0.14588875549640484,
-      "learning_rate": 1.8312979852630496e-06,
-      "loss": 0.0016,
-      "step": 12900
-    },
-    {
-      "epoch": 2.5989604158336665,
-      "grad_norm": 0.20595125909257264,
-      "learning_rate": 1.8055340856392026e-06,
-      "loss": 0.0016,
-      "step": 13000
-    },
-    {
-      "epoch": 2.5989604158336665,
-      "eval_loss": 0.0014449004083871841,
-      "eval_runtime": 1161.1376,
-      "eval_samples_per_second": 1960.384,
-      "eval_steps_per_second": 0.479,
-      "step": 13000
-    },
-    {
-      "epoch": 2.618952419032387,
-      "grad_norm": 0.1065984785896659,
-      "learning_rate": 1.7797701860153554e-06,
-      "loss": 0.0016,
-      "step": 13100
-    },
-    {
-      "epoch": 2.6389444222311074,
-      "grad_norm": 0.10639438336852645,
-      "learning_rate": 1.7540062863915084e-06,
-      "loss": 0.0016,
-      "step": 13200
-    },
-    {
-      "epoch": 2.658936425429828,
-      "grad_norm": 0.09098635003049371,
-      "learning_rate": 1.7282423867676611e-06,
-      "loss": 0.0015,
-      "step": 13300
-    },
-    {
-      "epoch": 2.6789284286285486,
-      "grad_norm": 0.157315122097513,
-      "learning_rate": 1.7024784871438143e-06,
-      "loss": 0.0014,
-      "step": 13400
-    },
-    {
-      "epoch": 2.6989204318272693,
-      "grad_norm": 0.11820399708006288,
-      "learning_rate": 1.6767145875199673e-06,
-      "loss": 0.0015,
-      "step": 13500
-    },
-    {
-      "epoch": 2.7189124350259894,
-      "grad_norm": 0.10172879528798195,
-      "learning_rate": 1.65095068789612e-06,
-      "loss": 0.0014,
-      "step": 13600
-    },
-    {
-      "epoch": 2.73890443822471,
-      "grad_norm": 0.16664553651334096,
-      "learning_rate": 1.625186788272273e-06,
-      "loss": 0.0015,
-      "step": 13700
-    },
-    {
-      "epoch": 2.7588964414234307,
-      "grad_norm": 0.10781015775436545,
-      "learning_rate": 1.5994228886484259e-06,
-      "loss": 0.0014,
-      "step": 13800
-    },
-    {
-      "epoch": 2.778888444622151,
-      "grad_norm": 0.16647409513753272,
-      "learning_rate": 1.5736589890245788e-06,
-      "loss": 0.0014,
-      "step": 13900
-    },
-    {
-      "epoch": 2.7988804478208715,
-      "grad_norm": 0.12382972993278037,
-      "learning_rate": 1.5478950894007318e-06,
-      "loss": 0.0014,
-      "step": 14000
-    },
-    {
-      "epoch": 2.7988804478208715,
-      "eval_loss": 0.001271539367735386,
-      "eval_runtime": 1155.6876,
-      "eval_samples_per_second": 1969.628,
-      "eval_steps_per_second": 0.481,
-      "step": 14000
-    },
-    {
-      "epoch": 2.818872451019592,
-      "grad_norm": 0.07729864026978665,
-      "learning_rate": 1.5221311897768848e-06,
-      "loss": 0.0013,
-      "step": 14100
-    },
-    {
-      "epoch": 2.838864454218313,
-      "grad_norm": 0.15724704193244626,
-      "learning_rate": 1.4963672901530376e-06,
-      "loss": 0.0014,
-      "step": 14200
-    },
-    {
-      "epoch": 2.8588564574170334,
-      "grad_norm": 0.15464785596732425,
-      "learning_rate": 1.4706033905291906e-06,
-      "loss": 0.0014,
-      "step": 14300
-    },
-    {
-      "epoch": 2.8788484606157536,
-      "grad_norm": 0.1469602680382028,
-      "learning_rate": 1.4448394909053433e-06,
-      "loss": 0.0014,
-      "step": 14400
-    },
-    {
-      "epoch": 2.8988404638144742,
-      "grad_norm": 0.11281007344165582,
-      "learning_rate": 1.4190755912814965e-06,
-      "loss": 0.0013,
-      "step": 14500
-    },
-    {
-      "epoch": 2.918832467013195,
-      "grad_norm": 0.14726624471120695,
-      "learning_rate": 1.3933116916576495e-06,
-      "loss": 0.0013,
-      "step": 14600
-    },
-    {
-      "epoch": 2.938824470211915,
-      "grad_norm": 0.14733117574775798,
-      "learning_rate": 1.3675477920338023e-06,
-      "loss": 0.0012,
-      "step": 14700
-    },
-    {
-      "epoch": 2.9588164734106357,
-      "grad_norm": 0.38118620984525436,
-      "learning_rate": 1.3417838924099553e-06,
-      "loss": 0.0011,
-      "step": 14800
-    },
-    {
-      "epoch": 2.9788084766093563,
-      "grad_norm": 0.08374852431168589,
-      "learning_rate": 1.316019992786108e-06,
-      "loss": 0.0012,
-      "step": 14900
-    },
-    {
-      "epoch": 2.998800479808077,
-      "grad_norm": 0.12709134182524984,
-      "learning_rate": 1.2902560931622613e-06,
-      "loss": 0.0011,
-      "step": 15000
-    },
-    {
-      "epoch": 2.998800479808077,
-      "eval_loss": 0.0011752103455364704,
-      "eval_runtime": 1164.8873,
-      "eval_samples_per_second": 1954.073,
-      "eval_steps_per_second": 0.477,
-      "step": 15000
-    },
-    {
-      "epoch": 3.018792483006797,
-      "grad_norm": 0.08381688672893102,
-      "learning_rate": 1.264492193538414e-06,
-      "loss": 0.0007,
-      "step": 15100
-    },
-    {
-      "epoch": 3.0387844862055178,
-      "grad_norm": 0.09710345048057636,
-      "learning_rate": 1.238728293914567e-06,
-      "loss": 0.0005,
-      "step": 15200
-    },
-    {
-      "epoch": 3.0587764894042384,
-      "grad_norm": 0.22385109684525908,
-      "learning_rate": 1.2129643942907198e-06,
-      "loss": 0.0006,
-      "step": 15300
-    },
-    {
-      "epoch": 3.0787684926029586,
-      "grad_norm": 0.1601770118752614,
-      "learning_rate": 1.187200494666873e-06,
-      "loss": 0.0006,
-      "step": 15400
-    },
-    {
-      "epoch": 3.0987604958016792,
-      "grad_norm": 0.16080588436491186,
-      "learning_rate": 1.1614365950430258e-06,
-      "loss": 0.0006,
-      "step": 15500
-    },
-    {
-      "epoch": 3.1187524990004,
-      "grad_norm": 0.13250025478577457,
-      "learning_rate": 1.1356726954191788e-06,
-      "loss": 0.0006,
-      "step": 15600
-    },
-    {
-      "epoch": 3.1387445021991205,
-      "grad_norm": 0.21986369421357652,
-      "learning_rate": 1.1099087957953317e-06,
-      "loss": 0.0006,
-      "step": 15700
-    },
-    {
-      "epoch": 3.1587365053978407,
-      "grad_norm": 0.0846389547777558,
-      "learning_rate": 1.0841448961714845e-06,
-      "loss": 0.0006,
-      "step": 15800
-    },
-    {
-      "epoch": 3.1787285085965613,
-      "grad_norm": 0.16537732926990753,
-      "learning_rate": 1.0583809965476375e-06,
-      "loss": 0.0006,
-      "step": 15900
-    },
-    {
-      "epoch": 3.198720511795282,
-      "grad_norm": 0.14320708980064725,
-      "learning_rate": 1.0326170969237905e-06,
-      "loss": 0.0006,
-      "step": 16000
-    },
-    {
-      "epoch": 3.198720511795282,
-      "eval_loss": 0.0011424524709582329,
-      "eval_runtime": 1160.0759,
-      "eval_samples_per_second": 1962.178,
-      "eval_steps_per_second": 0.479,
-      "step": 16000
-    },
-    {
-      "epoch": 3.2187125149940026,
-      "grad_norm": 0.12152352055677858,
-      "learning_rate": 1.0068531972999435e-06,
-      "loss": 0.0005,
-      "step": 16100
-    },
-    {
-      "epoch": 3.2387045181927228,
-      "grad_norm": 0.08979850548441953,
-      "learning_rate": 9.810892976760962e-07,
-      "loss": 0.0005,
-      "step": 16200
-    },
-    {
-      "epoch": 3.2586965213914434,
-      "grad_norm": 0.13248724505987958,
-      "learning_rate": 9.553253980522492e-07,
-      "loss": 0.0005,
-      "step": 16300
-    },
-    {
-      "epoch": 3.278688524590164,
-      "grad_norm": 0.17928305695165855,
-      "learning_rate": 9.295614984284022e-07,
-      "loss": 0.0005,
-      "step": 16400
-    },
-    {
-      "epoch": 3.2986805277888847,
-      "grad_norm": 0.11974187428101392,
-      "learning_rate": 9.037975988045551e-07,
-      "loss": 0.0005,
-      "step": 16500
-    },
-    {
-      "epoch": 3.318672530987605,
-      "grad_norm": 0.11749934971100777,
-      "learning_rate": 8.780336991807081e-07,
-      "loss": 0.0005,
-      "step": 16600
-    },
-    {
-      "epoch": 3.3386645341863255,
-      "grad_norm": 0.1261302652674093,
-      "learning_rate": 8.52269799556861e-07,
-      "loss": 0.0005,
-      "step": 16700
-    },
-    {
-      "epoch": 3.358656537385046,
-      "grad_norm": 0.11427762353703971,
-      "learning_rate": 8.265058999330138e-07,
-      "loss": 0.0005,
-      "step": 16800
-    },
-    {
-      "epoch": 3.3786485405837663,
-      "grad_norm": 0.1650136057485135,
-      "learning_rate": 8.007420003091669e-07,
-      "loss": 0.0005,
-      "step": 16900
-    },
-    {
-      "epoch": 3.398640543782487,
-      "grad_norm": 0.08229566695193702,
-      "learning_rate": 7.749781006853198e-07,
-      "loss": 0.0005,
-      "step": 17000
-    },
-    {
-      "epoch": 3.398640543782487,
-      "eval_loss": 0.0010600716341286898,
-      "eval_runtime": 1152.2546,
-      "eval_samples_per_second": 1975.497,
-      "eval_steps_per_second": 0.483,
-      "step": 17000
-    },
-    {
-      "epoch": 3.4186325469812076,
-      "grad_norm": 0.2044466929273688,
-      "learning_rate": 7.492142010614727e-07,
-      "loss": 0.0005,
-      "step": 17100
-    },
-    {
-      "epoch": 3.438624550179928,
-      "grad_norm": 0.07494444907583155,
-      "learning_rate": 7.234503014376257e-07,
-      "loss": 0.0005,
-      "step": 17200
-    },
-    {
-      "epoch": 3.4586165533786484,
-      "grad_norm": 0.16667119229981087,
-      "learning_rate": 6.976864018137786e-07,
-      "loss": 0.0005,
-      "step": 17300
-    },
-    {
-      "epoch": 3.478608556577369,
-      "grad_norm": 0.050436647584788406,
-      "learning_rate": 6.719225021899315e-07,
-      "loss": 0.0004,
-      "step": 17400
-    },
-    {
-      "epoch": 3.4986005597760896,
-      "grad_norm": 0.1103566981152097,
-      "learning_rate": 6.461586025660844e-07,
-      "loss": 0.0005,
-      "step": 17500
-    },
-    {
-      "epoch": 3.51859256297481,
-      "grad_norm": 0.10253704263588607,
-      "learning_rate": 6.203947029422374e-07,
-      "loss": 0.0005,
-      "step": 17600
-    },
-    {
-      "epoch": 3.5385845661735305,
-      "grad_norm": 0.09833384171173816,
-      "learning_rate": 5.946308033183904e-07,
-      "loss": 0.0004,
-      "step": 17700
-    },
-    {
-      "epoch": 3.558576569372251,
-      "grad_norm": 0.23793985241997176,
-      "learning_rate": 5.688669036945433e-07,
-      "loss": 0.0004,
-      "step": 17800
-    },
-    {
-      "epoch": 3.5785685725709717,
-      "grad_norm": 0.06702012945759417,
-      "learning_rate": 5.431030040706962e-07,
-      "loss": 0.0004,
-      "step": 17900
-    },
-    {
-      "epoch": 3.5985605757696923,
-      "grad_norm": 0.12144307064257012,
-      "learning_rate": 5.173391044468491e-07,
-      "loss": 0.0004,
-      "step": 18000
-    },
-    {
-      "epoch": 3.5985605757696923,
-      "eval_loss": 0.0009872900554910302,
-      "eval_runtime": 1150.5948,
-      "eval_samples_per_second": 1978.346,
-      "eval_steps_per_second": 0.483,
-      "step": 18000
-    },
-    {
-      "epoch": 3.6185525789684125,
-      "grad_norm": 0.15085542756004489,
-      "learning_rate": 4.91575204823002e-07,
-      "loss": 0.0004,
-      "step": 18100
-    },
-    {
-      "epoch": 3.638544582167133,
-      "grad_norm": 0.11281548293309303,
-      "learning_rate": 4.6581130519915495e-07,
-      "loss": 0.0004,
-      "step": 18200
-    },
-    {
-      "epoch": 3.658536585365854,
-      "grad_norm": 0.09926989527298706,
-      "learning_rate": 4.400474055753079e-07,
-      "loss": 0.0004,
-      "step": 18300
-    },
-    {
-      "epoch": 3.678528588564574,
-      "grad_norm": 0.14947986652047726,
-      "learning_rate": 4.142835059514608e-07,
-      "loss": 0.0004,
-      "step": 18400
-    },
-    {
-      "epoch": 3.6985205917632946,
-      "grad_norm": 0.06801833566776633,
-      "learning_rate": 3.885196063276138e-07,
-      "loss": 0.0004,
-      "step": 18500
-    },
-    {
-      "epoch": 3.7185125949620152,
-      "grad_norm": 0.1061544197534862,
-      "learning_rate": 3.6275570670376674e-07,
-      "loss": 0.0003,
-      "step": 18600
-    },
-    {
-      "epoch": 3.738504598160736,
-      "grad_norm": 0.09123620554862143,
-      "learning_rate": 3.369918070799196e-07,
-      "loss": 0.0004,
-      "step": 18700
-    },
-    {
-      "epoch": 3.758496601359456,
-      "grad_norm": 0.09155846956740325,
-      "learning_rate": 3.1122790745607255e-07,
-      "loss": 0.0003,
-      "step": 18800
-    },
-    {
-      "epoch": 3.7784886045581767,
-      "grad_norm": 0.11711396445856288,
-      "learning_rate": 2.8546400783222553e-07,
-      "loss": 0.0003,
-      "step": 18900
-    },
-    {
-      "epoch": 3.7984806077568973,
-      "grad_norm": 0.09806176989625397,
-      "learning_rate": 2.597001082083784e-07,
-      "loss": 0.0003,
-      "step": 19000
-    },
-    {
-      "epoch": 3.7984806077568973,
-      "eval_loss": 0.0009322697296738625,
-      "eval_runtime": 1160.9962,
-      "eval_samples_per_second": 1960.622,
-      "eval_steps_per_second": 0.479,
-      "step": 19000
-    },
-    {
-      "epoch": 3.8184726109556175,
-      "grad_norm": 0.10439625436846747,
-      "learning_rate": 2.3393620858453137e-07,
-      "loss": 0.0003,
-      "step": 19100
-    },
-    {
-      "epoch": 3.838464614154338,
-      "grad_norm": 0.12075153657265009,
-      "learning_rate": 2.0817230896068433e-07,
-      "loss": 0.0003,
-      "step": 19200
-    },
-    {
-      "epoch": 3.858456617353059,
-      "grad_norm": 0.10238786224831033,
-      "learning_rate": 1.8240840933683724e-07,
-      "loss": 0.0003,
-      "step": 19300
-    },
-    {
-      "epoch": 3.8784486205517794,
-      "grad_norm": 0.1341911348478737,
-      "learning_rate": 1.5664450971299017e-07,
-      "loss": 0.0003,
-      "step": 19400
-    },
-    {
-      "epoch": 3.8984406237505,
-      "grad_norm": 0.058901582357242764,
-      "learning_rate": 1.308806100891431e-07,
-      "loss": 0.0003,
-      "step": 19500
-    },
-    {
-      "epoch": 3.9184326269492202,
-      "grad_norm": 0.08130441166484537,
-      "learning_rate": 1.0511671046529604e-07,
-      "loss": 0.0003,
-      "step": 19600
-    },
-    {
-      "epoch": 3.938424630147941,
-      "grad_norm": 0.22931949885097863,
-      "learning_rate": 7.935281084144897e-08,
-      "loss": 0.0003,
-      "step": 19700
-    },
-    {
-      "epoch": 3.9584166333466615,
-      "grad_norm": 0.08058265664022546,
-      "learning_rate": 5.35889112176019e-08,
-      "loss": 0.0003,
-      "step": 19800
-    },
-    {
-      "epoch": 3.9784086365453817,
-      "grad_norm": 0.10117500275375008,
-      "learning_rate": 2.7825011593754832e-08,
-      "loss": 0.0003,
-      "step": 19900
-    },
-    {
-      "epoch": 3.9984006397441023,
-      "grad_norm": 0.07504730669729223,
-      "learning_rate": 2.0611119699077657e-09,
-      "loss": 0.0003,
-      "step": 20000
-    },
-    {
-      "epoch": 3.9984006397441023,
-      "eval_loss": 0.0008902106783352792,
-      "eval_runtime": 1170.0746,
-      "eval_samples_per_second": 1945.41,
-      "eval_steps_per_second": 0.475,
-      "step": 20000
-    }
-  ],
-  "logging_steps": 100,
-  "max_steps": 20008,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
-  "save_steps": 1000,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.6250799134867456e+16,
-  "train_batch_size": 64,
-  "trial_name": null,
-  "trial_params": null
-}

move_cp20008/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5d53daaff3479dcf40895b6aa0c279f0cd75349c0f606083ee0ff3b6656ab38f
-size 6968

move_cp20008/zero_to_fp32.py

@@ -1,604 +0,0 @@
-#!/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)