Delete checkpoint-224

checkpoint-224/config.json

@@ -1,36 +0,0 @@
-{
-  "_name_or_path": "jeiku/instructered4B",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128019,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "initializer_range": 0.02,
-  "intermediate_size": 9216,
-  "max_position_embeddings": 131072,
-  "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": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.1",
-  "use_cache": false,
-  "vocab_size": 128256
-}

checkpoint-224/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "transformers_version": "4.45.1"
-}

checkpoint-224/global_step224/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7c7fcfe685606e0b04223f51bd19add9979abf2cd6354f59ea3c446aba2f3e05
-size 13609806979

checkpoint-224/global_step224/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:413607e220cdce0b038f2ae026dd636994698eaab908a8559da38d0707ecf122
-size 13609806979

checkpoint-224/global_step224/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:856a6ec44ecedf5e27a5f77fe6ed05c9d95cd68ae9bcbb23c8445c4ed6ad5969
-size 152293

checkpoint-224/global_step224/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2ebe8e1787d3db2771380d322af7186942eacd8641e2d636c8c83cff795517b9
-size 152293

checkpoint-224/latest

@@ -1 +0,0 @@
-global_step224

checkpoint-224/model-00001-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c384928732ff1a2a0127bd30b464e66102692847ded7c98f09c5fa0f3f51ff04
-size 4978354640

checkpoint-224/model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a498da3a1dc2da409a1e82f94ed4028df397166fc457d7be1b7e07d1d7d2fe1e
-size 4047172128

checkpoint-224/model.safetensors.index.json

@@ -1,298 +0,0 @@
-{
-  "metadata": {
-    "total_size": 9025492992
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00002-of-00002.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors"
-  }
-}

checkpoint-224/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d5aeb0c54903210b6bb77aabf8f4802e4126d4bae40ff815b9d0b63767286cff
-size 14512

checkpoint-224/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2087fa1159897fc8e7870700fdb75275c4b88dbf7d3cd02c5397018e197c58f1
-size 14512

checkpoint-224/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1d90e1acb0addf826b67ce817354274df45a547fc1fc2d61aa91b5e34e71e956
-size 1064

checkpoint-224/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": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|finetune_right_pad_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

checkpoint-224/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
-size 17209884

checkpoint-224/tokenizer_config.json

@@ -1,2063 +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": "<|finetune_right_pad_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128005": {
-      "content": "<|reserved_special_token_2|>",
-      "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": "<|eom_id|>",
-      "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": "<|python_tag|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128011": {
-      "content": "<|reserved_special_token_3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128012": {
-      "content": "<|reserved_special_token_4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128013": {
-      "content": "<|reserved_special_token_5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128014": {
-      "content": "<|reserved_special_token_6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128015": {
-      "content": "<|reserved_special_token_7|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128016": {
-      "content": "<|reserved_special_token_8|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128017": {
-      "content": "<|reserved_special_token_9|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128018": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128019": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128020": {
-      "content": "<|reserved_special_token_12|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128021": {
-      "content": "<|reserved_special_token_13|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128022": {
-      "content": "<|reserved_special_token_14|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128023": {
-      "content": "<|reserved_special_token_15|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128024": {
-      "content": "<|reserved_special_token_16|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128025": {
-      "content": "<|reserved_special_token_17|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128026": {
-      "content": "<|reserved_special_token_18|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128027": {
-      "content": "<|reserved_special_token_19|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128028": {
-      "content": "<|reserved_special_token_20|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128029": {
-      "content": "<|reserved_special_token_21|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128030": {
-      "content": "<|reserved_special_token_22|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128031": {
-      "content": "<|reserved_special_token_23|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128032": {
-      "content": "<|reserved_special_token_24|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128033": {
-      "content": "<|reserved_special_token_25|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128034": {
-      "content": "<|reserved_special_token_26|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128035": {
-      "content": "<|reserved_special_token_27|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128036": {
-      "content": "<|reserved_special_token_28|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128037": {
-      "content": "<|reserved_special_token_29|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128038": {
-      "content": "<|reserved_special_token_30|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128039": {
-      "content": "<|reserved_special_token_31|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128040": {
-      "content": "<|reserved_special_token_32|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128041": {
-      "content": "<|reserved_special_token_33|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128042": {
-      "content": "<|reserved_special_token_34|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128043": {
-      "content": "<|reserved_special_token_35|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128044": {
-      "content": "<|reserved_special_token_36|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128045": {
-      "content": "<|reserved_special_token_37|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128046": {
-      "content": "<|reserved_special_token_38|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128047": {
-      "content": "<|reserved_special_token_39|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128048": {
-      "content": "<|reserved_special_token_40|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128049": {
-      "content": "<|reserved_special_token_41|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128050": {
-      "content": "<|reserved_special_token_42|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128051": {
-      "content": "<|reserved_special_token_43|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128052": {
-      "content": "<|reserved_special_token_44|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128053": {
-      "content": "<|reserved_special_token_45|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128054": {
-      "content": "<|reserved_special_token_46|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128055": {
-      "content": "<|reserved_special_token_47|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128056": {
-      "content": "<|reserved_special_token_48|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128057": {
-      "content": "<|reserved_special_token_49|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128058": {
-      "content": "<|reserved_special_token_50|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128059": {
-      "content": "<|reserved_special_token_51|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128060": {
-      "content": "<|reserved_special_token_52|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128061": {
-      "content": "<|reserved_special_token_53|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128062": {
-      "content": "<|reserved_special_token_54|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128063": {
-      "content": "<|reserved_special_token_55|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128064": {
-      "content": "<|reserved_special_token_56|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128065": {
-      "content": "<|reserved_special_token_57|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128066": {
-      "content": "<|reserved_special_token_58|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128067": {
-      "content": "<|reserved_special_token_59|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128068": {
-      "content": "<|reserved_special_token_60|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128069": {
-      "content": "<|reserved_special_token_61|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128070": {
-      "content": "<|reserved_special_token_62|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128071": {
-      "content": "<|reserved_special_token_63|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128072": {
-      "content": "<|reserved_special_token_64|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128073": {
-      "content": "<|reserved_special_token_65|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128074": {
-      "content": "<|reserved_special_token_66|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128075": {
-      "content": "<|reserved_special_token_67|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128076": {
-      "content": "<|reserved_special_token_68|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128077": {
-      "content": "<|reserved_special_token_69|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128078": {
-      "content": "<|reserved_special_token_70|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128079": {
-      "content": "<|reserved_special_token_71|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128080": {
-      "content": "<|reserved_special_token_72|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128081": {
-      "content": "<|reserved_special_token_73|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128082": {
-      "content": "<|reserved_special_token_74|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128083": {
-      "content": "<|reserved_special_token_75|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128084": {
-      "content": "<|reserved_special_token_76|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128085": {
-      "content": "<|reserved_special_token_77|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128086": {
-      "content": "<|reserved_special_token_78|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128087": {
-      "content": "<|reserved_special_token_79|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128088": {
-      "content": "<|reserved_special_token_80|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128089": {
-      "content": "<|reserved_special_token_81|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128090": {
-      "content": "<|reserved_special_token_82|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128091": {
-      "content": "<|reserved_special_token_83|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128092": {
-      "content": "<|reserved_special_token_84|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128093": {
-      "content": "<|reserved_special_token_85|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128094": {
-      "content": "<|reserved_special_token_86|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128095": {
-      "content": "<|reserved_special_token_87|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128096": {
-      "content": "<|reserved_special_token_88|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128097": {
-      "content": "<|reserved_special_token_89|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128098": {
-      "content": "<|reserved_special_token_90|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128099": {
-      "content": "<|reserved_special_token_91|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128100": {
-      "content": "<|reserved_special_token_92|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128101": {
-      "content": "<|reserved_special_token_93|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128102": {
-      "content": "<|reserved_special_token_94|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128103": {
-      "content": "<|reserved_special_token_95|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128104": {
-      "content": "<|reserved_special_token_96|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128105": {
-      "content": "<|reserved_special_token_97|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128106": {
-      "content": "<|reserved_special_token_98|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128107": {
-      "content": "<|reserved_special_token_99|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128108": {
-      "content": "<|reserved_special_token_100|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128109": {
-      "content": "<|reserved_special_token_101|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128110": {
-      "content": "<|reserved_special_token_102|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128111": {
-      "content": "<|reserved_special_token_103|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128112": {
-      "content": "<|reserved_special_token_104|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128113": {
-      "content": "<|reserved_special_token_105|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128114": {
-      "content": "<|reserved_special_token_106|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128115": {
-      "content": "<|reserved_special_token_107|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128116": {
-      "content": "<|reserved_special_token_108|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128117": {
-      "content": "<|reserved_special_token_109|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128118": {
-      "content": "<|reserved_special_token_110|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128119": {
-      "content": "<|reserved_special_token_111|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128120": {
-      "content": "<|reserved_special_token_112|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128121": {
-      "content": "<|reserved_special_token_113|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128122": {
-      "content": "<|reserved_special_token_114|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128123": {
-      "content": "<|reserved_special_token_115|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128124": {
-      "content": "<|reserved_special_token_116|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128125": {
-      "content": "<|reserved_special_token_117|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128126": {
-      "content": "<|reserved_special_token_118|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128127": {
-      "content": "<|reserved_special_token_119|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128128": {
-      "content": "<|reserved_special_token_120|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128129": {
-      "content": "<|reserved_special_token_121|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128130": {
-      "content": "<|reserved_special_token_122|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128131": {
-      "content": "<|reserved_special_token_123|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128132": {
-      "content": "<|reserved_special_token_124|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128133": {
-      "content": "<|reserved_special_token_125|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128134": {
-      "content": "<|reserved_special_token_126|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128135": {
-      "content": "<|reserved_special_token_127|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128136": {
-      "content": "<|reserved_special_token_128|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128137": {
-      "content": "<|reserved_special_token_129|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128138": {
-      "content": "<|reserved_special_token_130|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128139": {
-      "content": "<|reserved_special_token_131|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128140": {
-      "content": "<|reserved_special_token_132|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128141": {
-      "content": "<|reserved_special_token_133|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128142": {
-      "content": "<|reserved_special_token_134|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128143": {
-      "content": "<|reserved_special_token_135|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128144": {
-      "content": "<|reserved_special_token_136|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128145": {
-      "content": "<|reserved_special_token_137|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128146": {
-      "content": "<|reserved_special_token_138|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128147": {
-      "content": "<|reserved_special_token_139|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128148": {
-      "content": "<|reserved_special_token_140|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128149": {
-      "content": "<|reserved_special_token_141|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128150": {
-      "content": "<|reserved_special_token_142|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128151": {
-      "content": "<|reserved_special_token_143|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128152": {
-      "content": "<|reserved_special_token_144|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128153": {
-      "content": "<|reserved_special_token_145|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128154": {
-      "content": "<|reserved_special_token_146|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128155": {
-      "content": "<|reserved_special_token_147|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128156": {
-      "content": "<|reserved_special_token_148|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128157": {
-      "content": "<|reserved_special_token_149|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128158": {
-      "content": "<|reserved_special_token_150|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128159": {
-      "content": "<|reserved_special_token_151|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128160": {
-      "content": "<|reserved_special_token_152|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128161": {
-      "content": "<|reserved_special_token_153|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128162": {
-      "content": "<|reserved_special_token_154|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128163": {
-      "content": "<|reserved_special_token_155|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128164": {
-      "content": "<|reserved_special_token_156|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128165": {
-      "content": "<|reserved_special_token_157|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128166": {
-      "content": "<|reserved_special_token_158|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128167": {
-      "content": "<|reserved_special_token_159|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128168": {
-      "content": "<|reserved_special_token_160|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128169": {
-      "content": "<|reserved_special_token_161|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128170": {
-      "content": "<|reserved_special_token_162|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128171": {
-      "content": "<|reserved_special_token_163|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128172": {
-      "content": "<|reserved_special_token_164|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128173": {
-      "content": "<|reserved_special_token_165|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128174": {
-      "content": "<|reserved_special_token_166|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128175": {
-      "content": "<|reserved_special_token_167|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128176": {
-      "content": "<|reserved_special_token_168|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128177": {
-      "content": "<|reserved_special_token_169|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128178": {
-      "content": "<|reserved_special_token_170|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128179": {
-      "content": "<|reserved_special_token_171|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128180": {
-      "content": "<|reserved_special_token_172|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128181": {
-      "content": "<|reserved_special_token_173|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128182": {
-      "content": "<|reserved_special_token_174|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128183": {
-      "content": "<|reserved_special_token_175|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128184": {
-      "content": "<|reserved_special_token_176|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128185": {
-      "content": "<|reserved_special_token_177|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128186": {
-      "content": "<|reserved_special_token_178|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128187": {
-      "content": "<|reserved_special_token_179|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128188": {
-      "content": "<|reserved_special_token_180|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128189": {
-      "content": "<|reserved_special_token_181|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128190": {
-      "content": "<|reserved_special_token_182|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128191": {
-      "content": "<|reserved_special_token_183|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128192": {
-      "content": "<|reserved_special_token_184|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128193": {
-      "content": "<|reserved_special_token_185|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128194": {
-      "content": "<|reserved_special_token_186|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128195": {
-      "content": "<|reserved_special_token_187|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128196": {
-      "content": "<|reserved_special_token_188|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128197": {
-      "content": "<|reserved_special_token_189|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128198": {
-      "content": "<|reserved_special_token_190|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128199": {
-      "content": "<|reserved_special_token_191|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128200": {
-      "content": "<|reserved_special_token_192|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128201": {
-      "content": "<|reserved_special_token_193|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128202": {
-      "content": "<|reserved_special_token_194|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128203": {
-      "content": "<|reserved_special_token_195|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128204": {
-      "content": "<|reserved_special_token_196|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128205": {
-      "content": "<|reserved_special_token_197|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128206": {
-      "content": "<|reserved_special_token_198|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128207": {
-      "content": "<|reserved_special_token_199|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128208": {
-      "content": "<|reserved_special_token_200|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128209": {
-      "content": "<|reserved_special_token_201|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128210": {
-      "content": "<|reserved_special_token_202|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128211": {
-      "content": "<|reserved_special_token_203|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128212": {
-      "content": "<|reserved_special_token_204|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128213": {
-      "content": "<|reserved_special_token_205|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128214": {
-      "content": "<|reserved_special_token_206|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128215": {
-      "content": "<|reserved_special_token_207|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128216": {
-      "content": "<|reserved_special_token_208|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128217": {
-      "content": "<|reserved_special_token_209|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128218": {
-      "content": "<|reserved_special_token_210|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128219": {
-      "content": "<|reserved_special_token_211|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128220": {
-      "content": "<|reserved_special_token_212|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128221": {
-      "content": "<|reserved_special_token_213|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128222": {
-      "content": "<|reserved_special_token_214|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128223": {
-      "content": "<|reserved_special_token_215|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128224": {
-      "content": "<|reserved_special_token_216|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128225": {
-      "content": "<|reserved_special_token_217|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128226": {
-      "content": "<|reserved_special_token_218|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128227": {
-      "content": "<|reserved_special_token_219|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128228": {
-      "content": "<|reserved_special_token_220|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128229": {
-      "content": "<|reserved_special_token_221|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128230": {
-      "content": "<|reserved_special_token_222|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128231": {
-      "content": "<|reserved_special_token_223|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128232": {
-      "content": "<|reserved_special_token_224|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128233": {
-      "content": "<|reserved_special_token_225|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128234": {
-      "content": "<|reserved_special_token_226|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128235": {
-      "content": "<|reserved_special_token_227|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128236": {
-      "content": "<|reserved_special_token_228|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128237": {
-      "content": "<|reserved_special_token_229|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128238": {
-      "content": "<|reserved_special_token_230|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128239": {
-      "content": "<|reserved_special_token_231|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128240": {
-      "content": "<|reserved_special_token_232|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128241": {
-      "content": "<|reserved_special_token_233|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128242": {
-      "content": "<|reserved_special_token_234|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128243": {
-      "content": "<|reserved_special_token_235|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128244": {
-      "content": "<|reserved_special_token_236|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128245": {
-      "content": "<|reserved_special_token_237|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128246": {
-      "content": "<|reserved_special_token_238|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128247": {
-      "content": "<|reserved_special_token_239|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128248": {
-      "content": "<|reserved_special_token_240|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128249": {
-      "content": "<|reserved_special_token_241|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128250": {
-      "content": "<|reserved_special_token_242|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128251": {
-      "content": "<|reserved_special_token_243|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128252": {
-      "content": "<|reserved_special_token_244|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128253": {
-      "content": "<|reserved_special_token_245|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128254": {
-      "content": "<|reserved_special_token_246|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128255": {
-      "content": "<|reserved_special_token_247|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|im_end|>",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "pad_token": "<|finetune_right_pad_id|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
-}

checkpoint-224/trainer_state.json

@@ -1,1673 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.995539033457249,
-  "eval_steps": 28,
-  "global_step": 224,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.008895478131949592,
-      "grad_norm": 2.962439156483445,
-      "learning_rate": 4.5454545454545457e-07,
-      "loss": 1.8805,
-      "step": 1
-    },
-    {
-      "epoch": 0.008895478131949592,
-      "eval_loss": 2.7425005435943604,
-      "eval_runtime": 5.0857,
-      "eval_samples_per_second": 14.354,
-      "eval_steps_per_second": 2.556,
-      "step": 1
-    },
-    {
-      "epoch": 0.017790956263899184,
-      "grad_norm": 2.7396320345650156,
-      "learning_rate": 9.090909090909091e-07,
-      "loss": 1.8922,
-      "step": 2
-    },
-    {
-      "epoch": 0.026686434395848776,
-      "grad_norm": 2.8238110399477696,
-      "learning_rate": 1.3636363636363636e-06,
-      "loss": 1.8672,
-      "step": 3
-    },
-    {
-      "epoch": 0.03558191252779837,
-      "grad_norm": 2.825892310577778,
-      "learning_rate": 1.8181818181818183e-06,
-      "loss": 1.9474,
-      "step": 4
-    },
-    {
-      "epoch": 0.04447739065974796,
-      "grad_norm": 2.9182980055251515,
-      "learning_rate": 2.2727272727272728e-06,
-      "loss": 1.8873,
-      "step": 5
-    },
-    {
-      "epoch": 0.05337286879169755,
-      "grad_norm": 1.825111219165535,
-      "learning_rate": 2.7272727272727272e-06,
-      "loss": 1.8892,
-      "step": 6
-    },
-    {
-      "epoch": 0.06226834692364715,
-      "grad_norm": 1.603886963757723,
-      "learning_rate": 3.181818181818182e-06,
-      "loss": 1.8928,
-      "step": 7
-    },
-    {
-      "epoch": 0.07116382505559674,
-      "grad_norm": 1.9982114208239075,
-      "learning_rate": 3.6363636363636366e-06,
-      "loss": 1.8816,
-      "step": 8
-    },
-    {
-      "epoch": 0.08005930318754632,
-      "grad_norm": 2.2210111384360443,
-      "learning_rate": 4.0909090909090915e-06,
-      "loss": 1.814,
-      "step": 9
-    },
-    {
-      "epoch": 0.08895478131949593,
-      "grad_norm": 1.8833804876805869,
-      "learning_rate": 4.5454545454545455e-06,
-      "loss": 1.8789,
-      "step": 10
-    },
-    {
-      "epoch": 0.09785025945144551,
-      "grad_norm": 2.1696360746306986,
-      "learning_rate": 5e-06,
-      "loss": 1.8948,
-      "step": 11
-    },
-    {
-      "epoch": 0.1067457375833951,
-      "grad_norm": 1.9189154524725964,
-      "learning_rate": 5.4545454545454545e-06,
-      "loss": 1.8899,
-      "step": 12
-    },
-    {
-      "epoch": 0.1156412157153447,
-      "grad_norm": 1.5982373309558937,
-      "learning_rate": 5.90909090909091e-06,
-      "loss": 1.935,
-      "step": 13
-    },
-    {
-      "epoch": 0.1245366938472943,
-      "grad_norm": 1.2867259496282597,
-      "learning_rate": 6.363636363636364e-06,
-      "loss": 1.8012,
-      "step": 14
-    },
-    {
-      "epoch": 0.1334321719792439,
-      "grad_norm": 1.3487164419710964,
-      "learning_rate": 6.818181818181818e-06,
-      "loss": 1.8439,
-      "step": 15
-    },
-    {
-      "epoch": 0.14232765011119347,
-      "grad_norm": 1.4367061847474465,
-      "learning_rate": 7.272727272727273e-06,
-      "loss": 1.8463,
-      "step": 16
-    },
-    {
-      "epoch": 0.15122312824314307,
-      "grad_norm": 1.3999547484681398,
-      "learning_rate": 7.727272727272727e-06,
-      "loss": 1.8302,
-      "step": 17
-    },
-    {
-      "epoch": 0.16011860637509265,
-      "grad_norm": 1.0580202838750912,
-      "learning_rate": 8.181818181818183e-06,
-      "loss": 1.8602,
-      "step": 18
-    },
-    {
-      "epoch": 0.16901408450704225,
-      "grad_norm": 1.0918338120114914,
-      "learning_rate": 8.636363636363637e-06,
-      "loss": 1.7858,
-      "step": 19
-    },
-    {
-      "epoch": 0.17790956263899185,
-      "grad_norm": 1.0275858730350056,
-      "learning_rate": 9.090909090909091e-06,
-      "loss": 1.8628,
-      "step": 20
-    },
-    {
-      "epoch": 0.18680504077094143,
-      "grad_norm": 1.061639393901565,
-      "learning_rate": 9.545454545454547e-06,
-      "loss": 1.8227,
-      "step": 21
-    },
-    {
-      "epoch": 0.19570051890289103,
-      "grad_norm": 0.9240081464912561,
-      "learning_rate": 1e-05,
-      "loss": 1.7978,
-      "step": 22
-    },
-    {
-      "epoch": 0.20459599703484063,
-      "grad_norm": 0.9652630279266269,
-      "learning_rate": 9.999395316300748e-06,
-      "loss": 1.7734,
-      "step": 23
-    },
-    {
-      "epoch": 0.2134914751667902,
-      "grad_norm": 0.9039339352165564,
-      "learning_rate": 9.99758141145994e-06,
-      "loss": 1.849,
-      "step": 24
-    },
-    {
-      "epoch": 0.2223869532987398,
-      "grad_norm": 0.9643956642662512,
-      "learning_rate": 9.994558724213056e-06,
-      "loss": 1.825,
-      "step": 25
-    },
-    {
-      "epoch": 0.2312824314306894,
-      "grad_norm": 0.9167678356949895,
-      "learning_rate": 9.990327985667972e-06,
-      "loss": 1.7981,
-      "step": 26
-    },
-    {
-      "epoch": 0.24017790956263899,
-      "grad_norm": 0.8874816186232574,
-      "learning_rate": 9.984890219128148e-06,
-      "loss": 1.7821,
-      "step": 27
-    },
-    {
-      "epoch": 0.2490733876945886,
-      "grad_norm": 0.8787539356844203,
-      "learning_rate": 9.978246739845095e-06,
-      "loss": 1.7985,
-      "step": 28
-    },
-    {
-      "epoch": 0.2490733876945886,
-      "eval_loss": 2.290811777114868,
-      "eval_runtime": 4.938,
-      "eval_samples_per_second": 14.783,
-      "eval_steps_per_second": 2.633,
-      "step": 28
-    },
-    {
-      "epoch": 0.25796886582653816,
-      "grad_norm": 0.838340542158105,
-      "learning_rate": 9.970399154700264e-06,
-      "loss": 1.7882,
-      "step": 29
-    },
-    {
-      "epoch": 0.2668643439584878,
-      "grad_norm": 0.8285328505624969,
-      "learning_rate": 9.961349361816384e-06,
-      "loss": 1.8555,
-      "step": 30
-    },
-    {
-      "epoch": 0.27575982209043737,
-      "grad_norm": 0.9331640421116788,
-      "learning_rate": 9.951099550098349e-06,
-      "loss": 1.7626,
-      "step": 31
-    },
-    {
-      "epoch": 0.28465530022238694,
-      "grad_norm": 0.7822775533301098,
-      "learning_rate": 9.939652198703785e-06,
-      "loss": 1.7815,
-      "step": 32
-    },
-    {
-      "epoch": 0.2935507783543366,
-      "grad_norm": 0.8091655666026496,
-      "learning_rate": 9.927010076443408e-06,
-      "loss": 1.7973,
-      "step": 33
-    },
-    {
-      "epoch": 0.30244625648628615,
-      "grad_norm": 0.8067559509453439,
-      "learning_rate": 9.91317624111132e-06,
-      "loss": 1.7843,
-      "step": 34
-    },
-    {
-      "epoch": 0.3113417346182357,
-      "grad_norm": 0.791639209925201,
-      "learning_rate": 9.898154038745408e-06,
-      "loss": 1.8203,
-      "step": 35
-    },
-    {
-      "epoch": 0.3202372127501853,
-      "grad_norm": 0.8397439084797836,
-      "learning_rate": 9.881947102818036e-06,
-      "loss": 1.7982,
-      "step": 36
-    },
-    {
-      "epoch": 0.3291326908821349,
-      "grad_norm": 0.8069438258809916,
-      "learning_rate": 9.864559353357189e-06,
-      "loss": 1.7751,
-      "step": 37
-    },
-    {
-      "epoch": 0.3380281690140845,
-      "grad_norm": 0.8901339589432326,
-      "learning_rate": 9.845994995998332e-06,
-      "loss": 1.8393,
-      "step": 38
-    },
-    {
-      "epoch": 0.3469236471460341,
-      "grad_norm": 0.7778163619401842,
-      "learning_rate": 9.826258520967178e-06,
-      "loss": 1.6691,
-      "step": 39
-    },
-    {
-      "epoch": 0.3558191252779837,
-      "grad_norm": 0.8503632973674836,
-      "learning_rate": 9.805354701993624e-06,
-      "loss": 1.8385,
-      "step": 40
-    },
-    {
-      "epoch": 0.3647146034099333,
-      "grad_norm": 0.8510317916033313,
-      "learning_rate": 9.7832885951571e-06,
-      "loss": 1.7921,
-      "step": 41
-    },
-    {
-      "epoch": 0.37361008154188285,
-      "grad_norm": 0.8242453476305008,
-      "learning_rate": 9.76006553766365e-06,
-      "loss": 1.7588,
-      "step": 42
-    },
-    {
-      "epoch": 0.3825055596738325,
-      "grad_norm": 0.8490334887805663,
-      "learning_rate": 9.735691146555002e-06,
-      "loss": 1.7596,
-      "step": 43
-    },
-    {
-      "epoch": 0.39140103780578206,
-      "grad_norm": 0.940027149340783,
-      "learning_rate": 9.710171317349946e-06,
-      "loss": 1.7265,
-      "step": 44
-    },
-    {
-      "epoch": 0.40029651593773163,
-      "grad_norm": 0.7800160596846283,
-      "learning_rate": 9.683512222618376e-06,
-      "loss": 1.8351,
-      "step": 45
-    },
-    {
-      "epoch": 0.40919199406968126,
-      "grad_norm": 0.8750191358059531,
-      "learning_rate": 9.655720310488298e-06,
-      "loss": 1.7463,
-      "step": 46
-    },
-    {
-      "epoch": 0.41808747220163084,
-      "grad_norm": 0.7890987028235364,
-      "learning_rate": 9.62680230308621e-06,
-      "loss": 1.7175,
-      "step": 47
-    },
-    {
-      "epoch": 0.4269829503335804,
-      "grad_norm": 0.9776075848478134,
-      "learning_rate": 9.596765194911182e-06,
-      "loss": 1.7658,
-      "step": 48
-    },
-    {
-      "epoch": 0.43587842846553004,
-      "grad_norm": 0.8025568758744139,
-      "learning_rate": 9.565616251143094e-06,
-      "loss": 1.7425,
-      "step": 49
-    },
-    {
-      "epoch": 0.4447739065974796,
-      "grad_norm": 0.8932281966392491,
-      "learning_rate": 9.533363005885362e-06,
-      "loss": 1.7751,
-      "step": 50
-    },
-    {
-      "epoch": 0.4536693847294292,
-      "grad_norm": 0.8459501071139652,
-      "learning_rate": 9.50001326034265e-06,
-      "loss": 1.7298,
-      "step": 51
-    },
-    {
-      "epoch": 0.4625648628613788,
-      "grad_norm": 0.7921546527189047,
-      "learning_rate": 9.465575080933959e-06,
-      "loss": 1.7313,
-      "step": 52
-    },
-    {
-      "epoch": 0.4714603409933284,
-      "grad_norm": 0.8367967581956659,
-      "learning_rate": 9.430056797341574e-06,
-      "loss": 1.7492,
-      "step": 53
-    },
-    {
-      "epoch": 0.48035581912527797,
-      "grad_norm": 0.7931936215221228,
-      "learning_rate": 9.393467000496345e-06,
-      "loss": 1.7865,
-      "step": 54
-    },
-    {
-      "epoch": 0.4892512972572276,
-      "grad_norm": 0.984751704749124,
-      "learning_rate": 9.355814540499753e-06,
-      "loss": 1.7336,
-      "step": 55
-    },
-    {
-      "epoch": 0.4981467753891772,
-      "grad_norm": 0.8227951034631744,
-      "learning_rate": 9.317108524483319e-06,
-      "loss": 1.727,
-      "step": 56
-    },
-    {
-      "epoch": 0.4981467753891772,
-      "eval_loss": 2.1942620277404785,
-      "eval_runtime": 4.9502,
-      "eval_samples_per_second": 14.747,
-      "eval_steps_per_second": 2.626,
-      "step": 56
-    },
-    {
-      "epoch": 0.5070422535211268,
-      "grad_norm": 0.8411282879097969,
-      "learning_rate": 9.27735831440582e-06,
-      "loss": 1.7821,
-      "step": 57
-    },
-    {
-      "epoch": 0.5159377316530763,
-      "grad_norm": 0.7781618648296661,
-      "learning_rate": 9.236573524788888e-06,
-      "loss": 1.7347,
-      "step": 58
-    },
-    {
-      "epoch": 0.5248332097850259,
-      "grad_norm": 0.9088753275683533,
-      "learning_rate": 9.194764020391507e-06,
-      "loss": 1.7248,
-      "step": 59
-    },
-    {
-      "epoch": 0.5337286879169756,
-      "grad_norm": 0.8554987544215692,
-      "learning_rate": 9.151939913823988e-06,
-      "loss": 1.7127,
-      "step": 60
-    },
-    {
-      "epoch": 0.5426241660489252,
-      "grad_norm": 0.8266548000477859,
-      "learning_rate": 9.108111563102005e-06,
-      "loss": 1.7336,
-      "step": 61
-    },
-    {
-      "epoch": 0.5515196441808747,
-      "grad_norm": 0.8317314054903447,
-      "learning_rate": 9.063289569141251e-06,
-      "loss": 1.6577,
-      "step": 62
-    },
-    {
-      "epoch": 0.5604151223128243,
-      "grad_norm": 0.7907803326669282,
-      "learning_rate": 9.01748477319338e-06,
-      "loss": 1.7629,
-      "step": 63
-    },
-    {
-      "epoch": 0.5693106004447739,
-      "grad_norm": 0.9329359503827674,
-      "learning_rate": 8.970708254223768e-06,
-      "loss": 1.7681,
-      "step": 64
-    },
-    {
-      "epoch": 0.5782060785767235,
-      "grad_norm": 0.7480056903847685,
-      "learning_rate": 8.92297132623183e-06,
-      "loss": 1.7051,
-      "step": 65
-    },
-    {
-      "epoch": 0.5871015567086731,
-      "grad_norm": 0.9077672572079196,
-      "learning_rate": 8.87428553551445e-06,
-      "loss": 1.7093,
-      "step": 66
-    },
-    {
-      "epoch": 0.5959970348406227,
-      "grad_norm": 0.880358315923339,
-      "learning_rate": 8.82466265787324e-06,
-      "loss": 1.6933,
-      "step": 67
-    },
-    {
-      "epoch": 0.6048925129725723,
-      "grad_norm": 0.7941154116764113,
-      "learning_rate": 8.774114695766286e-06,
-      "loss": 1.7358,
-      "step": 68
-    },
-    {
-      "epoch": 0.6137879911045219,
-      "grad_norm": 0.8525197282856878,
-      "learning_rate": 8.722653875405077e-06,
-      "loss": 1.781,
-      "step": 69
-    },
-    {
-      "epoch": 0.6226834692364714,
-      "grad_norm": 0.8265406397838687,
-      "learning_rate": 8.670292643797302e-06,
-      "loss": 1.7098,
-      "step": 70
-    },
-    {
-      "epoch": 0.631578947368421,
-      "grad_norm": 0.7680796533145033,
-      "learning_rate": 8.61704366573625e-06,
-      "loss": 1.6796,
-      "step": 71
-    },
-    {
-      "epoch": 0.6404744255003706,
-      "grad_norm": 0.8042854169648783,
-      "learning_rate": 8.562919820737537e-06,
-      "loss": 1.6849,
-      "step": 72
-    },
-    {
-      "epoch": 0.6493699036323203,
-      "grad_norm": 0.821753341080785,
-      "learning_rate": 8.507934199923884e-06,
-      "loss": 1.6899,
-      "step": 73
-    },
-    {
-      "epoch": 0.6582653817642699,
-      "grad_norm": 0.8111947542056863,
-      "learning_rate": 8.452100102858734e-06,
-      "loss": 1.7003,
-      "step": 74
-    },
-    {
-      "epoch": 0.6671608598962194,
-      "grad_norm": 0.7818461027480149,
-      "learning_rate": 8.395431034329431e-06,
-      "loss": 1.7192,
-      "step": 75
-    },
-    {
-      "epoch": 0.676056338028169,
-      "grad_norm": 0.7685968932142347,
-      "learning_rate": 8.33794070108077e-06,
-      "loss": 1.7977,
-      "step": 76
-    },
-    {
-      "epoch": 0.6849518161601186,
-      "grad_norm": 0.8139919630919948,
-      "learning_rate": 8.2796430084997e-06,
-      "loss": 1.7318,
-      "step": 77
-    },
-    {
-      "epoch": 0.6938472942920682,
-      "grad_norm": 0.7794723242422334,
-      "learning_rate": 8.22055205725199e-06,
-      "loss": 1.7151,
-      "step": 78
-    },
-    {
-      "epoch": 0.7027427724240178,
-      "grad_norm": 0.728460212640379,
-      "learning_rate": 8.160682139871634e-06,
-      "loss": 1.7313,
-      "step": 79
-    },
-    {
-      "epoch": 0.7116382505559674,
-      "grad_norm": 0.7956691993406653,
-      "learning_rate": 8.100047737303877e-06,
-      "loss": 1.7096,
-      "step": 80
-    },
-    {
-      "epoch": 0.720533728687917,
-      "grad_norm": 0.711208685534124,
-      "learning_rate": 8.038663515402659e-06,
-      "loss": 1.7281,
-      "step": 81
-    },
-    {
-      "epoch": 0.7294292068198666,
-      "grad_norm": 0.775501063890523,
-      "learning_rate": 7.97654432138333e-06,
-      "loss": 1.6985,
-      "step": 82
-    },
-    {
-      "epoch": 0.7383246849518161,
-      "grad_norm": 0.7926863015669294,
-      "learning_rate": 7.913705180231505e-06,
-      "loss": 1.6493,
-      "step": 83
-    },
-    {
-      "epoch": 0.7472201630837657,
-      "grad_norm": 0.7646163799523064,
-      "learning_rate": 7.850161291068915e-06,
-      "loss": 1.7429,
-      "step": 84
-    },
-    {
-      "epoch": 0.7472201630837657,
-      "eval_loss": 2.166506052017212,
-      "eval_runtime": 5.0566,
-      "eval_samples_per_second": 14.436,
-      "eval_steps_per_second": 2.571,
-      "step": 84
-    },
-    {
-      "epoch": 0.7561156412157154,
-      "grad_norm": 0.7863441465872285,
-      "learning_rate": 7.785928023477142e-06,
-      "loss": 1.6836,
-      "step": 85
-    },
-    {
-      "epoch": 0.765011119347665,
-      "grad_norm": 0.8191984365366046,
-      "learning_rate": 7.721020913780137e-06,
-      "loss": 1.6842,
-      "step": 86
-    },
-    {
-      "epoch": 0.7739065974796145,
-      "grad_norm": 0.8006782198319303,
-      "learning_rate": 7.655455661286376e-06,
-      "loss": 1.6494,
-      "step": 87
-    },
-    {
-      "epoch": 0.7828020756115641,
-      "grad_norm": 0.7654197589814793,
-      "learning_rate": 7.589248124491627e-06,
-      "loss": 1.7664,
-      "step": 88
-    },
-    {
-      "epoch": 0.7916975537435137,
-      "grad_norm": 0.8599660274656371,
-      "learning_rate": 7.5224143172432e-06,
-      "loss": 1.7169,
-      "step": 89
-    },
-    {
-      "epoch": 0.8005930318754633,
-      "grad_norm": 0.7576298501441915,
-      "learning_rate": 7.454970404866612e-06,
-      "loss": 1.6947,
-      "step": 90
-    },
-    {
-      "epoch": 0.809488510007413,
-      "grad_norm": 0.8174817690479476,
-      "learning_rate": 7.386932700255635e-06,
-      "loss": 1.6878,
-      "step": 91
-    },
-    {
-      "epoch": 0.8183839881393625,
-      "grad_norm": 0.8235881096708558,
-      "learning_rate": 7.318317659926637e-06,
-      "loss": 1.7236,
-      "step": 92
-    },
-    {
-      "epoch": 0.8272794662713121,
-      "grad_norm": 0.8312635054795164,
-      "learning_rate": 7.249141880038181e-06,
-      "loss": 1.7094,
-      "step": 93
-    },
-    {
-      "epoch": 0.8361749444032617,
-      "grad_norm": 0.8883212124220771,
-      "learning_rate": 7.179422092376856e-06,
-      "loss": 1.6923,
-      "step": 94
-    },
-    {
-      "epoch": 0.8450704225352113,
-      "grad_norm": 0.8180549283263809,
-      "learning_rate": 7.109175160310312e-06,
-      "loss": 1.712,
-      "step": 95
-    },
-    {
-      "epoch": 0.8539659006671608,
-      "grad_norm": 0.7568720711350465,
-      "learning_rate": 7.038418074708444e-06,
-      "loss": 1.6887,
-      "step": 96
-    },
-    {
-      "epoch": 0.8628613787991104,
-      "grad_norm": 0.8561076366911579,
-      "learning_rate": 6.967167949833763e-06,
-      "loss": 1.7062,
-      "step": 97
-    },
-    {
-      "epoch": 0.8717568569310601,
-      "grad_norm": 0.8079541369639384,
-      "learning_rate": 6.895442019201898e-06,
-      "loss": 1.731,
-      "step": 98
-    },
-    {
-      "epoch": 0.8806523350630097,
-      "grad_norm": 0.7614430270741105,
-      "learning_rate": 6.8232576314132755e-06,
-      "loss": 1.7106,
-      "step": 99
-    },
-    {
-      "epoch": 0.8895478131949592,
-      "grad_norm": 0.7604432010057705,
-      "learning_rate": 6.750632245956954e-06,
-      "loss": 1.7534,
-      "step": 100
-    },
-    {
-      "epoch": 0.8984432913269088,
-      "grad_norm": 0.7782042216719071,
-      "learning_rate": 6.677583428987625e-06,
-      "loss": 1.6793,
-      "step": 101
-    },
-    {
-      "epoch": 0.9073387694588584,
-      "grad_norm": 0.7457350333389989,
-      "learning_rate": 6.6041288490768385e-06,
-      "loss": 1.6527,
-      "step": 102
-    },
-    {
-      "epoch": 0.916234247590808,
-      "grad_norm": 0.7714830457964388,
-      "learning_rate": 6.530286272939438e-06,
-      "loss": 1.7262,
-      "step": 103
-    },
-    {
-      "epoch": 0.9251297257227576,
-      "grad_norm": 0.7598538699042868,
-      "learning_rate": 6.456073561136261e-06,
-      "loss": 1.6938,
-      "step": 104
-    },
-    {
-      "epoch": 0.9340252038547072,
-      "grad_norm": 0.743820000982299,
-      "learning_rate": 6.381508663754152e-06,
-      "loss": 1.654,
-      "step": 105
-    },
-    {
-      "epoch": 0.9429206819866568,
-      "grad_norm": 0.7344076336222899,
-      "learning_rate": 6.306609616064304e-06,
-      "loss": 1.7266,
-      "step": 106
-    },
-    {
-      "epoch": 0.9518161601186064,
-      "grad_norm": 0.7846174979334468,
-      "learning_rate": 6.231394534160008e-06,
-      "loss": 1.7026,
-      "step": 107
-    },
-    {
-      "epoch": 0.9607116382505559,
-      "grad_norm": 0.7558875505010646,
-      "learning_rate": 6.15588161057485e-06,
-      "loss": 1.7292,
-      "step": 108
-    },
-    {
-      "epoch": 0.9696071163825055,
-      "grad_norm": 0.8255512223024366,
-      "learning_rate": 6.080089109882419e-06,
-      "loss": 1.6389,
-      "step": 109
-    },
-    {
-      "epoch": 0.9785025945144552,
-      "grad_norm": 0.7171315882558364,
-      "learning_rate": 6.004035364278593e-06,
-      "loss": 1.6367,
-      "step": 110
-    },
-    {
-      "epoch": 0.9873980726464048,
-      "grad_norm": 0.7524610234390072,
-      "learning_rate": 5.927738769147467e-06,
-      "loss": 1.6586,
-      "step": 111
-    },
-    {
-      "epoch": 0.9962935507783544,
-      "grad_norm": 0.776276543241556,
-      "learning_rate": 5.851217778611994e-06,
-      "loss": 1.6867,
-      "step": 112
-    },
-    {
-      "epoch": 0.9962935507783544,
-      "eval_loss": 2.1309382915496826,
-      "eval_runtime": 4.9289,
-      "eval_samples_per_second": 14.811,
-      "eval_steps_per_second": 2.638,
-      "step": 112
-    },
-    {
-      "epoch": 1.0052044609665427,
-      "grad_norm": 0.7949226363525317,
-      "learning_rate": 5.774490901070424e-06,
-      "loss": 1.6816,
-      "step": 113
-    },
-    {
-      "epoch": 1.0141263940520446,
-      "grad_norm": 0.8427527864276817,
-      "learning_rate": 5.697576694719616e-06,
-      "loss": 1.6729,
-      "step": 114
-    },
-    {
-      "epoch": 1.0230483271375466,
-      "grad_norm": 0.8391300041321513,
-      "learning_rate": 5.6204937630662974e-06,
-      "loss": 1.606,
-      "step": 115
-    },
-    {
-      "epoch": 1.0319702602230483,
-      "grad_norm": 0.860066136054114,
-      "learning_rate": 5.543260750427373e-06,
-      "loss": 1.6388,
-      "step": 116
-    },
-    {
-      "epoch": 1.0408921933085502,
-      "grad_norm": 0.7969614266629734,
-      "learning_rate": 5.465896337420359e-06,
-      "loss": 1.6474,
-      "step": 117
-    },
-    {
-      "epoch": 1.0498141263940521,
-      "grad_norm": 0.9025361781915455,
-      "learning_rate": 5.388419236445033e-06,
-      "loss": 1.5205,
-      "step": 118
-    },
-    {
-      "epoch": 1.0587360594795538,
-      "grad_norm": 0.8330236878373249,
-      "learning_rate": 5.310848187157404e-06,
-      "loss": 1.5675,
-      "step": 119
-    },
-    {
-      "epoch": 1.0676579925650558,
-      "grad_norm": 0.7616700634371533,
-      "learning_rate": 5.233201951937088e-06,
-      "loss": 1.6432,
-      "step": 120
-    },
-    {
-      "epoch": 1.0765799256505577,
-      "grad_norm": 0.8546223421581763,
-      "learning_rate": 5.155499311349185e-06,
-      "loss": 1.5784,
-      "step": 121
-    },
-    {
-      "epoch": 1.0855018587360594,
-      "grad_norm": 0.8166653392476256,
-      "learning_rate": 5.077759059601756e-06,
-      "loss": 1.5782,
-      "step": 122
-    },
-    {
-      "epoch": 1.0944237918215614,
-      "grad_norm": 0.8111532279560614,
-      "learning_rate": 5e-06,
-      "loss": 1.5873,
-      "step": 123
-    },
-    {
-      "epoch": 1.1033457249070633,
-      "grad_norm": 0.8158634269230521,
-      "learning_rate": 4.922240940398246e-06,
-      "loss": 1.5588,
-      "step": 124
-    },
-    {
-      "epoch": 1.112267657992565,
-      "grad_norm": 0.8210896404843728,
-      "learning_rate": 4.844500688650817e-06,
-      "loss": 1.6126,
-      "step": 125
-    },
-    {
-      "epoch": 1.121189591078067,
-      "grad_norm": 0.8000322873727128,
-      "learning_rate": 4.766798048062913e-06,
-      "loss": 1.5483,
-      "step": 126
-    },
-    {
-      "epoch": 1.1301115241635689,
-      "grad_norm": 0.7519469533082767,
-      "learning_rate": 4.689151812842598e-06,
-      "loss": 1.5701,
-      "step": 127
-    },
-    {
-      "epoch": 1.1390334572490706,
-      "grad_norm": 0.7800251310433457,
-      "learning_rate": 4.611580763554969e-06,
-      "loss": 1.5731,
-      "step": 128
-    },
-    {
-      "epoch": 1.1479553903345725,
-      "grad_norm": 0.8406348404872362,
-      "learning_rate": 4.534103662579643e-06,
-      "loss": 1.5307,
-      "step": 129
-    },
-    {
-      "epoch": 1.1568773234200744,
-      "grad_norm": 0.7654155312184125,
-      "learning_rate": 4.456739249572628e-06,
-      "loss": 1.547,
-      "step": 130
-    },
-    {
-      "epoch": 1.1657992565055761,
-      "grad_norm": 0.7463028643340174,
-      "learning_rate": 4.379506236933703e-06,
-      "loss": 1.5446,
-      "step": 131
-    },
-    {
-      "epoch": 1.174721189591078,
-      "grad_norm": 0.8062671750420662,
-      "learning_rate": 4.3024233052803855e-06,
-      "loss": 1.6141,
-      "step": 132
-    },
-    {
-      "epoch": 1.18364312267658,
-      "grad_norm": 0.815723178829378,
-      "learning_rate": 4.2255090989295765e-06,
-      "loss": 1.616,
-      "step": 133
-    },
-    {
-      "epoch": 1.1925650557620817,
-      "grad_norm": 0.7863478983348662,
-      "learning_rate": 4.148782221388007e-06,
-      "loss": 1.5959,
-      "step": 134
-    },
-    {
-      "epoch": 1.2014869888475836,
-      "grad_norm": 0.7864870983392745,
-      "learning_rate": 4.072261230852534e-06,
-      "loss": 1.6498,
-      "step": 135
-    },
-    {
-      "epoch": 1.2104089219330856,
-      "grad_norm": 0.7547272629847489,
-      "learning_rate": 3.995964635721409e-06,
-      "loss": 1.5999,
-      "step": 136
-    },
-    {
-      "epoch": 1.2193308550185873,
-      "grad_norm": 0.7673639108820794,
-      "learning_rate": 3.919910890117584e-06,
-      "loss": 1.5933,
-      "step": 137
-    },
-    {
-      "epoch": 1.2282527881040892,
-      "grad_norm": 0.7766205741224386,
-      "learning_rate": 3.844118389425154e-06,
-      "loss": 1.61,
-      "step": 138
-    },
-    {
-      "epoch": 1.2371747211895912,
-      "grad_norm": 0.7362112046628648,
-      "learning_rate": 3.768605465839994e-06,
-      "loss": 1.5712,
-      "step": 139
-    },
-    {
-      "epoch": 1.2460966542750929,
-      "grad_norm": 0.740953819543322,
-      "learning_rate": 3.6933903839356983e-06,
-      "loss": 1.6463,
-      "step": 140
-    },
-    {
-      "epoch": 1.2460966542750929,
-      "eval_loss": 2.126718044281006,
-      "eval_runtime": 5.0405,
-      "eval_samples_per_second": 14.483,
-      "eval_steps_per_second": 2.579,
-      "step": 140
-    },
-    {
-      "epoch": 1.2550185873605948,
-      "grad_norm": 0.7455906988345508,
-      "learning_rate": 3.6184913362458497e-06,
-      "loss": 1.5954,
-      "step": 141
-    },
-    {
-      "epoch": 1.2639405204460967,
-      "grad_norm": 0.7390172101050686,
-      "learning_rate": 3.5439264388637407e-06,
-      "loss": 1.5978,
-      "step": 142
-    },
-    {
-      "epoch": 1.2728624535315984,
-      "grad_norm": 0.7812295476595575,
-      "learning_rate": 3.469713727060564e-06,
-      "loss": 1.6303,
-      "step": 143
-    },
-    {
-      "epoch": 1.2817843866171004,
-      "grad_norm": 0.7556406155289581,
-      "learning_rate": 3.3958711509231627e-06,
-      "loss": 1.5518,
-      "step": 144
-    },
-    {
-      "epoch": 1.2907063197026023,
-      "grad_norm": 0.7468728606931369,
-      "learning_rate": 3.322416571012376e-06,
-      "loss": 1.6044,
-      "step": 145
-    },
-    {
-      "epoch": 1.299628252788104,
-      "grad_norm": 0.7191959471643807,
-      "learning_rate": 3.249367754043047e-06,
-      "loss": 1.6269,
-      "step": 146
-    },
-    {
-      "epoch": 1.308550185873606,
-      "grad_norm": 0.7664174797908729,
-      "learning_rate": 3.176742368586725e-06,
-      "loss": 1.5637,
-      "step": 147
-    },
-    {
-      "epoch": 1.3174721189591079,
-      "grad_norm": 0.7468906342438638,
-      "learning_rate": 3.104557980798104e-06,
-      "loss": 1.5446,
-      "step": 148
-    },
-    {
-      "epoch": 1.3263940520446096,
-      "grad_norm": 0.7451846473452862,
-      "learning_rate": 3.032832050166239e-06,
-      "loss": 1.5449,
-      "step": 149
-    },
-    {
-      "epoch": 1.3353159851301115,
-      "grad_norm": 0.7616087364880716,
-      "learning_rate": 2.961581925291557e-06,
-      "loss": 1.6044,
-      "step": 150
-    },
-    {
-      "epoch": 1.3442379182156134,
-      "grad_norm": 0.7445080222060676,
-      "learning_rate": 2.8908248396896893e-06,
-      "loss": 1.5702,
-      "step": 151
-    },
-    {
-      "epoch": 1.3531598513011152,
-      "grad_norm": 0.7210878474745228,
-      "learning_rate": 2.820577907623145e-06,
-      "loss": 1.5921,
-      "step": 152
-    },
-    {
-      "epoch": 1.362081784386617,
-      "grad_norm": 0.7554243231660402,
-      "learning_rate": 2.750858119961821e-06,
-      "loss": 1.5874,
-      "step": 153
-    },
-    {
-      "epoch": 1.371003717472119,
-      "grad_norm": 0.7671684721265511,
-      "learning_rate": 2.6816823400733628e-06,
-      "loss": 1.6214,
-      "step": 154
-    },
-    {
-      "epoch": 1.3799256505576207,
-      "grad_norm": 0.7107001153097623,
-      "learning_rate": 2.613067299744364e-06,
-      "loss": 1.6306,
-      "step": 155
-    },
-    {
-      "epoch": 1.3888475836431227,
-      "grad_norm": 0.7766434748408712,
-      "learning_rate": 2.5450295951333896e-06,
-      "loss": 1.6016,
-      "step": 156
-    },
-    {
-      "epoch": 1.3977695167286246,
-      "grad_norm": 0.7253668897149933,
-      "learning_rate": 2.4775856827568016e-06,
-      "loss": 1.5755,
-      "step": 157
-    },
-    {
-      "epoch": 1.4066914498141263,
-      "grad_norm": 0.7445577446601732,
-      "learning_rate": 2.410751875508373e-06,
-      "loss": 1.6057,
-      "step": 158
-    },
-    {
-      "epoch": 1.4156133828996282,
-      "grad_norm": 0.7388798176698108,
-      "learning_rate": 2.3445443387136247e-06,
-      "loss": 1.6085,
-      "step": 159
-    },
-    {
-      "epoch": 1.4245353159851302,
-      "grad_norm": 0.7528881371618414,
-      "learning_rate": 2.278979086219863e-06,
-      "loss": 1.5843,
-      "step": 160
-    },
-    {
-      "epoch": 1.4334572490706319,
-      "grad_norm": 0.7368231349073808,
-      "learning_rate": 2.2140719765228587e-06,
-      "loss": 1.5469,
-      "step": 161
-    },
-    {
-      "epoch": 1.4423791821561338,
-      "grad_norm": 0.7123568741875721,
-      "learning_rate": 2.149838708931087e-06,
-      "loss": 1.5725,
-      "step": 162
-    },
-    {
-      "epoch": 1.4513011152416357,
-      "grad_norm": 0.7410245476145694,
-      "learning_rate": 2.086294819768496e-06,
-      "loss": 1.5768,
-      "step": 163
-    },
-    {
-      "epoch": 1.4602230483271375,
-      "grad_norm": 0.7791011096821625,
-      "learning_rate": 2.0234556786166715e-06,
-      "loss": 1.5203,
-      "step": 164
-    },
-    {
-      "epoch": 1.4691449814126394,
-      "grad_norm": 0.756774717840047,
-      "learning_rate": 1.9613364845973433e-06,
-      "loss": 1.6617,
-      "step": 165
-    },
-    {
-      "epoch": 1.4780669144981413,
-      "grad_norm": 0.7162094806926552,
-      "learning_rate": 1.8999522626961254e-06,
-      "loss": 1.6116,
-      "step": 166
-    },
-    {
-      "epoch": 1.486988847583643,
-      "grad_norm": 0.7132743980586249,
-      "learning_rate": 1.8393178601283684e-06,
-      "loss": 1.5591,
-      "step": 167
-    },
-    {
-      "epoch": 1.495910780669145,
-      "grad_norm": 0.7683594146532297,
-      "learning_rate": 1.7794479427480115e-06,
-      "loss": 1.593,
-      "step": 168
-    },
-    {
-      "epoch": 1.495910780669145,
-      "eval_loss": 2.114826202392578,
-      "eval_runtime": 4.9368,
-      "eval_samples_per_second": 14.787,
-      "eval_steps_per_second": 2.633,
-      "step": 168
-    },
-    {
-      "epoch": 1.504832713754647,
-      "grad_norm": 0.7109602921298782,
-      "learning_rate": 1.7203569915003005e-06,
-      "loss": 1.5261,
-      "step": 169
-    },
-    {
-      "epoch": 1.5137546468401486,
-      "grad_norm": 0.7346220135576979,
-      "learning_rate": 1.6620592989192318e-06,
-      "loss": 1.594,
-      "step": 170
-    },
-    {
-      "epoch": 1.5226765799256505,
-      "grad_norm": 0.6734164312637153,
-      "learning_rate": 1.6045689656705715e-06,
-      "loss": 1.5471,
-      "step": 171
-    },
-    {
-      "epoch": 1.5315985130111525,
-      "grad_norm": 0.7409502781596998,
-      "learning_rate": 1.5478998971412669e-06,
-      "loss": 1.536,
-      "step": 172
-    },
-    {
-      "epoch": 1.5405204460966542,
-      "grad_norm": 0.7056300593485433,
-      "learning_rate": 1.4920658000761172e-06,
-      "loss": 1.5677,
-      "step": 173
-    },
-    {
-      "epoch": 1.549442379182156,
-      "grad_norm": 0.7032068699867184,
-      "learning_rate": 1.4370801792624656e-06,
-      "loss": 1.6057,
-      "step": 174
-    },
-    {
-      "epoch": 1.558364312267658,
-      "grad_norm": 0.7354693345583995,
-      "learning_rate": 1.3829563342637514e-06,
-      "loss": 1.6657,
-      "step": 175
-    },
-    {
-      "epoch": 1.5672862453531597,
-      "grad_norm": 0.7292297554209234,
-      "learning_rate": 1.3297073562026992e-06,
-      "loss": 1.6144,
-      "step": 176
-    },
-    {
-      "epoch": 1.5762081784386617,
-      "grad_norm": 0.689272475476711,
-      "learning_rate": 1.2773461245949249e-06,
-      "loss": 1.5528,
-      "step": 177
-    },
-    {
-      "epoch": 1.5851301115241636,
-      "grad_norm": 0.7354887342865115,
-      "learning_rate": 1.225885304233716e-06,
-      "loss": 1.6064,
-      "step": 178
-    },
-    {
-      "epoch": 1.5940520446096653,
-      "grad_norm": 0.7064194581763904,
-      "learning_rate": 1.1753373421267622e-06,
-      "loss": 1.6049,
-      "step": 179
-    },
-    {
-      "epoch": 1.6029739776951673,
-      "grad_norm": 0.7566228137505194,
-      "learning_rate": 1.125714464485551e-06,
-      "loss": 1.5472,
-      "step": 180
-    },
-    {
-      "epoch": 1.6118959107806692,
-      "grad_norm": 0.7068920541521109,
-      "learning_rate": 1.0770286737681701e-06,
-      "loss": 1.5112,
-      "step": 181
-    },
-    {
-      "epoch": 1.620817843866171,
-      "grad_norm": 0.6927990179758211,
-      "learning_rate": 1.0292917457762325e-06,
-      "loss": 1.614,
-      "step": 182
-    },
-    {
-      "epoch": 1.6297397769516728,
-      "grad_norm": 0.7004195144075062,
-      "learning_rate": 9.825152268066213e-07,
-      "loss": 1.6333,
-      "step": 183
-    },
-    {
-      "epoch": 1.6386617100371748,
-      "grad_norm": 0.7095189872060162,
-      "learning_rate": 9.367104308587493e-07,
-      "loss": 1.5678,
-      "step": 184
-    },
-    {
-      "epoch": 1.6475836431226765,
-      "grad_norm": 0.71255932263421,
-      "learning_rate": 8.918884368979969e-07,
-      "loss": 1.5812,
-      "step": 185
-    },
-    {
-      "epoch": 1.6565055762081784,
-      "grad_norm": 0.7111899621451707,
-      "learning_rate": 8.480600861760124e-07,
-      "loss": 1.5792,
-      "step": 186
-    },
-    {
-      "epoch": 1.6654275092936803,
-      "grad_norm": 0.6775823161513022,
-      "learning_rate": 8.052359796084952e-07,
-      "loss": 1.641,
-      "step": 187
-    },
-    {
-      "epoch": 1.674349442379182,
-      "grad_norm": 0.7246805658391949,
-      "learning_rate": 7.634264752111131e-07,
-      "loss": 1.5788,
-      "step": 188
-    },
-    {
-      "epoch": 1.683271375464684,
-      "grad_norm": 0.6857756197716095,
-      "learning_rate": 7.226416855941814e-07,
-      "loss": 1.5896,
-      "step": 189
-    },
-    {
-      "epoch": 1.692193308550186,
-      "grad_norm": 0.7126493923907314,
-      "learning_rate": 6.828914755166826e-07,
-      "loss": 1.5808,
-      "step": 190
-    },
-    {
-      "epoch": 1.7011152416356876,
-      "grad_norm": 0.6885954964525883,
-      "learning_rate": 6.441854595002478e-07,
-      "loss": 1.5641,
-      "step": 191
-    },
-    {
-      "epoch": 1.7100371747211895,
-      "grad_norm": 0.7047319405532964,
-      "learning_rate": 6.065329995036573e-07,
-      "loss": 1.5676,
-      "step": 192
-    },
-    {
-      "epoch": 1.7189591078066915,
-      "grad_norm": 0.6718035026523713,
-      "learning_rate": 5.699432026584267e-07,
-      "loss": 1.6242,
-      "step": 193
-    },
-    {
-      "epoch": 1.7278810408921932,
-      "grad_norm": 0.6981766400413105,
-      "learning_rate": 5.344249190660427e-07,
-      "loss": 1.482,
-      "step": 194
-    },
-    {
-      "epoch": 1.7368029739776951,
-      "grad_norm": 0.6893168999107806,
-      "learning_rate": 4.999867396573499e-07,
-      "loss": 1.6211,
-      "step": 195
-    },
-    {
-      "epoch": 1.745724907063197,
-      "grad_norm": 0.7107176396602818,
-      "learning_rate": 4.666369941146376e-07,
-      "loss": 1.604,
-      "step": 196
-    },
-    {
-      "epoch": 1.745724907063197,
-      "eval_loss": 2.112863779067993,
-      "eval_runtime": 5.0454,
-      "eval_samples_per_second": 14.469,
-      "eval_steps_per_second": 2.577,
-      "step": 196
-    },
-    {
-      "epoch": 1.7546468401486988,
-      "grad_norm": 0.6976263641639928,
-      "learning_rate": 4.343837488569058e-07,
-      "loss": 1.5392,
-      "step": 197
-    },
-    {
-      "epoch": 1.7635687732342007,
-      "grad_norm": 0.7174067662211165,
-      "learning_rate": 4.03234805088818e-07,
-      "loss": 1.5687,
-      "step": 198
-    },
-    {
-      "epoch": 1.7724907063197026,
-      "grad_norm": 0.6870219887534516,
-      "learning_rate": 3.7319769691379295e-07,
-      "loss": 1.551,
-      "step": 199
-    },
-    {
-      "epoch": 1.7814126394052043,
-      "grad_norm": 0.6983449018701221,
-      "learning_rate": 3.4427968951170287e-07,
-      "loss": 1.5828,
-      "step": 200
-    },
-    {
-      "epoch": 1.7903345724907063,
-      "grad_norm": 0.7183216870017771,
-      "learning_rate": 3.1648777738162496e-07,
-      "loss": 1.5435,
-      "step": 201
-    },
-    {
-      "epoch": 1.7992565055762082,
-      "grad_norm": 0.7185654549153709,
-      "learning_rate": 2.8982868265005457e-07,
-      "loss": 1.5457,
-      "step": 202
-    },
-    {
-      "epoch": 1.80817843866171,
-      "grad_norm": 0.7352379562150491,
-      "learning_rate": 2.6430885344499944e-07,
-      "loss": 1.5641,
-      "step": 203
-    },
-    {
-      "epoch": 1.817100371747212,
-      "grad_norm": 0.6976729455703554,
-      "learning_rate": 2.399344623363503e-07,
-      "loss": 1.5592,
-      "step": 204
-    },
-    {
-      "epoch": 1.8260223048327138,
-      "grad_norm": 0.7057792233242116,
-      "learning_rate": 2.1671140484290144e-07,
-      "loss": 1.598,
-      "step": 205
-    },
-    {
-      "epoch": 1.8349442379182155,
-      "grad_norm": 0.6884424303550053,
-      "learning_rate": 1.9464529800637731e-07,
-      "loss": 1.5715,
-      "step": 206
-    },
-    {
-      "epoch": 1.8438661710037176,
-      "grad_norm": 0.6928948603154073,
-      "learning_rate": 1.737414790328218e-07,
-      "loss": 1.6124,
-      "step": 207
-    },
-    {
-      "epoch": 1.8527881040892193,
-      "grad_norm": 0.6795496892846022,
-      "learning_rate": 1.540050040016694e-07,
-      "loss": 1.5935,
-      "step": 208
-    },
-    {
-      "epoch": 1.861710037174721,
-      "grad_norm": 0.6636706068104933,
-      "learning_rate": 1.3544064664281266e-07,
-      "loss": 1.6063,
-      "step": 209
-    },
-    {
-      "epoch": 1.8706319702602232,
-      "grad_norm": 0.7070367652211981,
-      "learning_rate": 1.1805289718196499e-07,
-      "loss": 1.5869,
-      "step": 210
-    },
-    {
-      "epoch": 1.879553903345725,
-      "grad_norm": 0.6856354556452025,
-      "learning_rate": 1.0184596125459134e-07,
-      "loss": 1.5154,
-      "step": 211
-    },
-    {
-      "epoch": 1.8884758364312266,
-      "grad_norm": 0.68093775252014,
-      "learning_rate": 8.682375888868167e-08,
-      "loss": 1.5594,
-      "step": 212
-    },
-    {
-      "epoch": 1.8973977695167288,
-      "grad_norm": 0.6485244056932311,
-      "learning_rate": 7.29899235565934e-08,
-      "loss": 1.5559,
-      "step": 213
-    },
-    {
-      "epoch": 1.9063197026022305,
-      "grad_norm": 0.6675593036944839,
-      "learning_rate": 6.034780129621664e-08,
-      "loss": 1.5156,
-      "step": 214
-    },
-    {
-      "epoch": 1.9152416356877322,
-      "grad_norm": 0.6872424052686473,
-      "learning_rate": 4.8900449901653214e-08,
-      "loss": 1.5674,
-      "step": 215
-    },
-    {
-      "epoch": 1.9241635687732344,
-      "grad_norm": 0.6924079214009966,
-      "learning_rate": 3.8650638183617695e-08,
-      "loss": 1.5574,
-      "step": 216
-    },
-    {
-      "epoch": 1.933085501858736,
-      "grad_norm": 0.7070912793422548,
-      "learning_rate": 2.960084529973706e-08,
-      "loss": 1.5807,
-      "step": 217
-    },
-    {
-      "epoch": 1.9420074349442378,
-      "grad_norm": 0.7050185875893417,
-      "learning_rate": 2.1753260154906973e-08,
-      "loss": 1.5965,
-      "step": 218
-    },
-    {
-      "epoch": 1.95092936802974,
-      "grad_norm": 0.6885302564214322,
-      "learning_rate": 1.5109780871853663e-08,
-      "loss": 1.6065,
-      "step": 219
-    },
-    {
-      "epoch": 1.9598513011152416,
-      "grad_norm": 0.6970811020575952,
-      "learning_rate": 9.672014332028357e-09,
-      "loss": 1.5348,
-      "step": 220
-    },
-    {
-      "epoch": 1.9687732342007433,
-      "grad_norm": 0.6899769194702832,
-      "learning_rate": 5.4412757869459765e-09,
-      "loss": 1.5395,
-      "step": 221
-    },
-    {
-      "epoch": 1.9776951672862455,
-      "grad_norm": 0.6839594718217513,
-      "learning_rate": 2.4185885400596076e-09,
-      "loss": 1.5979,
-      "step": 222
-    },
-    {
-      "epoch": 1.9866171003717472,
-      "grad_norm": 0.6685813594094444,
-      "learning_rate": 6.04683699252373e-10,
-      "loss": 1.613,
-      "step": 223
-    },
-    {
-      "epoch": 1.995539033457249,
-      "grad_norm": 0.6899032355777277,
-      "learning_rate": 0.0,
-      "loss": 1.6085,
-      "step": 224
-    },
-    {
-      "epoch": 1.995539033457249,
-      "eval_loss": 2.1147751808166504,
-      "eval_runtime": 4.9367,
-      "eval_samples_per_second": 14.787,
-      "eval_steps_per_second": 2.633,
-      "step": 224
-    }
-  ],
-  "logging_steps": 1,
-  "max_steps": 224,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 56,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 2.8644591172950426e+17,
-  "train_batch_size": 3,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-224/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a73ea13cdc4aa1f89e967406cd928d6a343ca4b05825deb19cc3ea1ef4d6f2e
-size 8376

checkpoint-224/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)