Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "arcee-ai/Llama-3.1-SuperNova-Lite",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "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": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.47.1"
+}

global_step324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1817ded6685be8fb549573e9ab25af1232a12ce53c69f1f92700e6c84c9745
+size 12108989031

global_step324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c4861ad826ec66356097c3f48e9bd1c053f3e7c8b1d1dc2dab1fb61ba33b14
+size 12108989031

global_step324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2503e19e0d32fe82569fdaaadb7ea7ba63746f94d4657ea1fe510af64fd4d576
+size 12108989031

global_step324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c76500efecaeaf81a41d21206eb6a1dcbde65f52fe5d19c3c0022677ab92bc
+size 12108989031

global_step324/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eeef17365a151ce4ca2647d76e8e1ca38d7dc6d64382a55c9047f3a892a08d6
+size 152165

global_step324/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499551dc2c6777cab8525a98cd3a47630edc335bcf9f11fc1da3c95c73cf5078
+size 152165

global_step324/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c3ec972b0753775c22dcd1132fdf695b4c141bbe0bcfda137612c83ff4dc42
+size 152165

global_step324/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a052e64663d0dbcdd175dfc94c718be59cb635f3d2333692d0fff84a4c1daa
+size 152165

latest

@@ -0,0 +1 @@
+global_step324

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3a0266bde6eac1b8d3d130a92166e8a4ffd5b0d26e63013d98f94eaf715a44
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd1ef294292b11078f7e5999d6478ab89d80e964a7d7aab33f0174d9f9f885e
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517ffd0ecedccd3fa38fcf05ef99704f479fa13c61ea5b1d4147952e9b495cdc
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a00d4577187ca4f8372bdffe17724e249aa6e3adb515020baeaf373485b9ee
+size 1168138808

model.safetensors.index.json

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

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418a5f105ae834c3075024076916b2a9475918fe034c12d0dd5b6d91f1aba467
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e07ace389d24bc1307b74f42a1e7b8f0117b0db853e2df64ff3f15cb92916a2
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6a990f346d7014dffb28fa2bc7d3b890bd3c53712503fce3656da48d3d6e50
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95f356ca38179b05993f55daece0223e96fa10b9a1b9ea2102a739211333f63
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02efb87663fa59a8ff631d8065648c110e216fdd6d5eb19b4f186d11adbf1f90
+size 1064

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade1dac458f86f9bea8bf35b713f14e1bbed24228429534038e9f7e54ea3e8b6
+size 17208712

tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "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": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "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": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,2301 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.925925925925926,
+  "eval_steps": 500,
+  "global_step": 324,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018518518518518517,
+      "grad_norm": 11.543508930958351,
+      "learning_rate": 1.3333333333333334e-07,
+      "loss": 2.5502,
+      "step": 1
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 11.036573442393484,
+      "learning_rate": 2.6666666666666667e-07,
+      "loss": 2.524,
+      "step": 2
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 10.633243381981275,
+      "learning_rate": 4e-07,
+      "loss": 2.204,
+      "step": 3
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 10.844156107788931,
+      "learning_rate": 5.333333333333333e-07,
+      "loss": 2.6556,
+      "step": 4
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 10.31689604512179,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 2.3083,
+      "step": 5
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 9.817262372273788,
+      "learning_rate": 8e-07,
+      "loss": 2.4079,
+      "step": 6
+    },
+    {
+      "epoch": 0.12962962962962962,
+      "grad_norm": 9.116167654173315,
+      "learning_rate": 9.333333333333333e-07,
+      "loss": 2.3343,
+      "step": 7
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 7.891190287353295,
+      "learning_rate": 1.0666666666666667e-06,
+      "loss": 2.3883,
+      "step": 8
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 8.42233222280676,
+      "learning_rate": 1.2e-06,
+      "loss": 2.4733,
+      "step": 9
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 6.5902867588718825,
+      "learning_rate": 1.3333333333333332e-06,
+      "loss": 2.2598,
+      "step": 10
+    },
+    {
+      "epoch": 0.2037037037037037,
+      "grad_norm": 7.468618276890062,
+      "learning_rate": 1.4666666666666665e-06,
+      "loss": 2.6818,
+      "step": 11
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 6.524430399848726,
+      "learning_rate": 1.6e-06,
+      "loss": 2.0609,
+      "step": 12
+    },
+    {
+      "epoch": 0.24074074074074073,
+      "grad_norm": 15.819198637332978,
+      "learning_rate": 1.7333333333333334e-06,
+      "loss": 1.8734,
+      "step": 13
+    },
+    {
+      "epoch": 0.25925925925925924,
+      "grad_norm": 12.251404296601525,
+      "learning_rate": 1.8666666666666667e-06,
+      "loss": 2.3952,
+      "step": 14
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 12.014341658055084,
+      "learning_rate": 2e-06,
+      "loss": 2.0763,
+      "step": 15
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 9.119171460936416,
+      "learning_rate": 1.999948316841124e-06,
+      "loss": 2.2581,
+      "step": 16
+    },
+    {
+      "epoch": 0.3148148148148148,
+      "grad_norm": 7.0075699362300785,
+      "learning_rate": 1.999793272706794e-06,
+      "loss": 2.3189,
+      "step": 17
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 8.434551205593468,
+      "learning_rate": 1.9995348836233515e-06,
+      "loss": 2.2956,
+      "step": 18
+    },
+    {
+      "epoch": 0.35185185185185186,
+      "grad_norm": 9.802253199544783,
+      "learning_rate": 1.999173176299524e-06,
+      "loss": 2.1106,
+      "step": 19
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 7.364889431202562,
+      "learning_rate": 1.9987081881236665e-06,
+      "loss": 2.4001,
+      "step": 20
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 5.5030313904087995,
+      "learning_rate": 1.9981399671598938e-06,
+      "loss": 2.0534,
+      "step": 21
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 4.022498450217217,
+      "learning_rate": 1.997468572143115e-06,
+      "loss": 1.9262,
+      "step": 22
+    },
+    {
+      "epoch": 0.42592592592592593,
+      "grad_norm": 4.237115597250525,
+      "learning_rate": 1.9966940724729603e-06,
+      "loss": 2.2743,
+      "step": 23
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 4.300566273621826,
+      "learning_rate": 1.995816548206609e-06,
+      "loss": 2.028,
+      "step": 24
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 4.157703163471443,
+      "learning_rate": 1.994836090050514e-06,
+      "loss": 2.2021,
+      "step": 25
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 4.59475590188255,
+      "learning_rate": 1.993752799351023e-06,
+      "loss": 2.1409,
+      "step": 26
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.553829762084,
+      "learning_rate": 1.992566788083908e-06,
+      "loss": 2.1277,
+      "step": 27
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 2.808767466788676,
+      "learning_rate": 1.9912781788427856e-06,
+      "loss": 2.074,
+      "step": 28
+    },
+    {
+      "epoch": 0.5370370370370371,
+      "grad_norm": 2.945994143903197,
+      "learning_rate": 1.989887104826449e-06,
+      "loss": 1.9894,
+      "step": 29
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 2.9859402190241,
+      "learning_rate": 1.988393709825096e-06,
+      "loss": 2.1096,
+      "step": 30
+    },
+    {
+      "epoch": 0.5740740740740741,
+      "grad_norm": 2.788646179800959,
+      "learning_rate": 1.9867981482054697e-06,
+      "loss": 2.315,
+      "step": 31
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 2.428878990731119,
+      "learning_rate": 1.9851005848948986e-06,
+      "loss": 2.1129,
+      "step": 32
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 2.326070514005508,
+      "learning_rate": 1.983301195364252e-06,
+      "loss": 2.3507,
+      "step": 33
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": 2.2448623338584524,
+      "learning_rate": 1.9814001656098e-06,
+      "loss": 2.2176,
+      "step": 34
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 3.345489216172997,
+      "learning_rate": 1.9793976921339876e-06,
+      "loss": 2.0352,
+      "step": 35
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.454245882780074,
+      "learning_rate": 1.9772939819251245e-06,
+      "loss": 1.7644,
+      "step": 36
+    },
+    {
+      "epoch": 0.6851851851851852,
+      "grad_norm": 2.2823601110851115,
+      "learning_rate": 1.9750892524359894e-06,
+      "loss": 2.0044,
+      "step": 37
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": 2.378703420397497,
+      "learning_rate": 1.9727837315613503e-06,
+      "loss": 1.9992,
+      "step": 38
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 2.2038000284491392,
+      "learning_rate": 1.9703776576144106e-06,
+      "loss": 2.1248,
+      "step": 39
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.6625652175528476,
+      "learning_rate": 1.9678712793021747e-06,
+      "loss": 1.7908,
+      "step": 40
+    },
+    {
+      "epoch": 0.7592592592592593,
+      "grad_norm": 1.649500064167637,
+      "learning_rate": 1.9652648556997396e-06,
+      "loss": 2.0346,
+      "step": 41
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 2.127402784391995,
+      "learning_rate": 1.962558656223516e-06,
+      "loss": 2.1544,
+      "step": 42
+    },
+    {
+      "epoch": 0.7962962962962963,
+      "grad_norm": 2.4572023559040668,
+      "learning_rate": 1.959752960603378e-06,
+      "loss": 1.9295,
+      "step": 43
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 1.511188510592738,
+      "learning_rate": 1.956848058853751e-06,
+      "loss": 2.1473,
+      "step": 44
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.6425186462750276,
+      "learning_rate": 1.9538442512436325e-06,
+      "loss": 1.7632,
+      "step": 45
+    },
+    {
+      "epoch": 0.8518518518518519,
+      "grad_norm": 2.528104013708182,
+      "learning_rate": 1.9507418482655546e-06,
+      "loss": 1.9125,
+      "step": 46
+    },
+    {
+      "epoch": 0.8703703703703703,
+      "grad_norm": 2.660072260955662,
+      "learning_rate": 1.947541170603488e-06,
+      "loss": 1.9839,
+      "step": 47
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.303424321729968,
+      "learning_rate": 1.9442425490996984e-06,
+      "loss": 1.8381,
+      "step": 48
+    },
+    {
+      "epoch": 0.9074074074074074,
+      "grad_norm": 1.7413263437826438,
+      "learning_rate": 1.940846324720544e-06,
+      "loss": 2.2322,
+      "step": 49
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 3.681741007928878,
+      "learning_rate": 1.9373528485212327e-06,
+      "loss": 2.1221,
+      "step": 50
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 2.729258330107977,
+      "learning_rate": 1.9337624816095357e-06,
+      "loss": 1.8567,
+      "step": 51
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 1.9607649593150183,
+      "learning_rate": 1.9300755951084592e-06,
+      "loss": 2.0553,
+      "step": 52
+    },
+    {
+      "epoch": 0.9814814814814815,
+      "grad_norm": 2.119362131138027,
+      "learning_rate": 1.9262925701178863e-06,
+      "loss": 1.936,
+      "step": 53
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.057082578120893,
+      "learning_rate": 1.9224137976751793e-06,
+      "loss": 1.9584,
+      "step": 54
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 2.0207421134902708,
+      "learning_rate": 1.918439678714763e-06,
+      "loss": 1.9837,
+      "step": 55
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 1.938684997881939,
+      "learning_rate": 1.9143706240266807e-06,
+      "loss": 1.9354,
+      "step": 56
+    },
+    {
+      "epoch": 1.037037037037037,
+      "grad_norm": 2.0601195298871398,
+      "learning_rate": 1.910207054214133e-06,
+      "loss": 2.0174,
+      "step": 57
+    },
+    {
+      "epoch": 1.0555555555555556,
+      "grad_norm": 2.041620934780644,
+      "learning_rate": 1.9059493996499985e-06,
+      "loss": 1.7447,
+      "step": 58
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 1.5682604954979573,
+      "learning_rate": 1.9015981004323534e-06,
+      "loss": 2.0106,
+      "step": 59
+    },
+    {
+      "epoch": 1.0925925925925926,
+      "grad_norm": 2.865965004078874,
+      "learning_rate": 1.8971536063389742e-06,
+      "loss": 2.2393,
+      "step": 60
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 2.7462581398678787,
+      "learning_rate": 1.89261637678085e-06,
+      "loss": 1.7421,
+      "step": 61
+    },
+    {
+      "epoch": 1.1296296296296295,
+      "grad_norm": 3.120548437283878,
+      "learning_rate": 1.8879868807546932e-06,
+      "loss": 1.9877,
+      "step": 62
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "grad_norm": 3.242255359642735,
+      "learning_rate": 1.8832655967944605e-06,
+      "loss": 1.9799,
+      "step": 63
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 2.2159733738020275,
+      "learning_rate": 1.8784530129218907e-06,
+      "loss": 2.0581,
+      "step": 64
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 2.08989006018966,
+      "learning_rate": 1.873549626596057e-06,
+      "loss": 1.8653,
+      "step": 65
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 1.4837874153680628,
+      "learning_rate": 1.8685559446619487e-06,
+      "loss": 1.9734,
+      "step": 66
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 2.1071721482630403,
+      "learning_rate": 1.863472483298079e-06,
+      "loss": 1.7762,
+      "step": 67
+    },
+    {
+      "epoch": 1.2407407407407407,
+      "grad_norm": 2.6554851825477646,
+      "learning_rate": 1.858299767963131e-06,
+      "loss": 2.2267,
+      "step": 68
+    },
+    {
+      "epoch": 1.2592592592592593,
+      "grad_norm": 2.135758261049139,
+      "learning_rate": 1.8530383333416415e-06,
+      "loss": 2.0624,
+      "step": 69
+    },
+    {
+      "epoch": 1.2777777777777777,
+      "grad_norm": 2.256153463268274,
+      "learning_rate": 1.847688723288733e-06,
+      "loss": 2.0254,
+      "step": 70
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 1.9270711341308566,
+      "learning_rate": 1.8422514907738986e-06,
+      "loss": 2.0873,
+      "step": 71
+    },
+    {
+      "epoch": 1.3148148148148149,
+      "grad_norm": 1.3698407936967985,
+      "learning_rate": 1.8367271978238418e-06,
+      "loss": 1.5655,
+      "step": 72
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.7934950271719698,
+      "learning_rate": 1.8311164154643833e-06,
+      "loss": 2.1081,
+      "step": 73
+    },
+    {
+      "epoch": 1.3518518518518519,
+      "grad_norm": 1.7554770045810462,
+      "learning_rate": 1.8254197236614353e-06,
+      "loss": 1.6326,
+      "step": 74
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 1.7910726004582642,
+      "learning_rate": 1.8196377112610524e-06,
+      "loss": 1.9896,
+      "step": 75
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 1.43155366985165,
+      "learning_rate": 1.8137709759285662e-06,
+      "loss": 1.8557,
+      "step": 76
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "grad_norm": 1.816009532890727,
+      "learning_rate": 1.8078201240868048e-06,
+      "loss": 1.7878,
+      "step": 77
+    },
+    {
+      "epoch": 1.425925925925926,
+      "grad_norm": 1.612331881267257,
+      "learning_rate": 1.8017857708534106e-06,
+      "loss": 1.982,
+      "step": 78
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 1.8628647966869196,
+      "learning_rate": 1.7956685399772576e-06,
+      "loss": 1.9704,
+      "step": 79
+    },
+    {
+      "epoch": 1.462962962962963,
+      "grad_norm": 1.9936817464029801,
+      "learning_rate": 1.7894690637739762e-06,
+      "loss": 1.8299,
+      "step": 80
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 2.463393533692339,
+      "learning_rate": 1.7831879830605936e-06,
+      "loss": 2.0444,
+      "step": 81
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.4979859149192305,
+      "learning_rate": 1.776825947089294e-06,
+      "loss": 2.0278,
+      "step": 82
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 2.7584711281071606,
+      "learning_rate": 1.7703836134803102e-06,
+      "loss": 1.8715,
+      "step": 83
+    },
+    {
+      "epoch": 1.5370370370370372,
+      "grad_norm": 1.9266117476771798,
+      "learning_rate": 1.7638616481539448e-06,
+      "loss": 2.3658,
+      "step": 84
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 2.7609401761288908,
+      "learning_rate": 1.7572607252617377e-06,
+      "loss": 1.9736,
+      "step": 85
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 2.114937054090088,
+      "learning_rate": 1.7505815271167822e-06,
+      "loss": 2.0398,
+      "step": 86
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 2.0664911123203513,
+      "learning_rate": 1.743824744123196e-06,
+      "loss": 2.1056,
+      "step": 87
+    },
+    {
+      "epoch": 1.6111111111111112,
+      "grad_norm": 2.5153483082090213,
+      "learning_rate": 1.7369910747047571e-06,
+      "loss": 1.8765,
+      "step": 88
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 1.8949983903048848,
+      "learning_rate": 1.7300812252327102e-06,
+      "loss": 2.1245,
+      "step": 89
+    },
+    {
+      "epoch": 1.6481481481481481,
+      "grad_norm": 2.7037983362018565,
+      "learning_rate": 1.723095909952751e-06,
+      "loss": 1.5174,
+      "step": 90
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.3396050215927673,
+      "learning_rate": 1.7160358509111989e-06,
+      "loss": 2.0559,
+      "step": 91
+    },
+    {
+      "epoch": 1.6851851851851851,
+      "grad_norm": 2.1357187531056976,
+      "learning_rate": 1.7089017778803595e-06,
+      "loss": 1.8264,
+      "step": 92
+    },
+    {
+      "epoch": 1.7037037037037037,
+      "grad_norm": 2.5298502653457358,
+      "learning_rate": 1.701694428283093e-06,
+      "loss": 2.1282,
+      "step": 93
+    },
+    {
+      "epoch": 1.7222222222222223,
+      "grad_norm": 2.0789215851330343,
+      "learning_rate": 1.6944145471165881e-06,
+      "loss": 2.1829,
+      "step": 94
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 1.8110067836025452,
+      "learning_rate": 1.6870628868753545e-06,
+      "loss": 1.7584,
+      "step": 95
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 2.7069181555694666,
+      "learning_rate": 1.6796402074734402e-06,
+      "loss": 1.897,
+      "step": 96
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 2.3956521553142176,
+      "learning_rate": 1.6721472761658836e-06,
+      "loss": 1.9119,
+      "step": 97
+    },
+    {
+      "epoch": 1.7962962962962963,
+      "grad_norm": 1.3732811625669847,
+      "learning_rate": 1.664584867469403e-06,
+      "loss": 1.6848,
+      "step": 98
+    },
+    {
+      "epoch": 1.8148148148148149,
+      "grad_norm": 1.9512817035138257,
+      "learning_rate": 1.6569537630823382e-06,
+      "loss": 2.0185,
+      "step": 99
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 1.864374052494234,
+      "learning_rate": 1.6492547518038503e-06,
+      "loss": 1.925,
+      "step": 100
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 1.7728078338576356,
+      "learning_rate": 1.6414886294523857e-06,
+      "loss": 1.8965,
+      "step": 101
+    },
+    {
+      "epoch": 1.8703703703703702,
+      "grad_norm": 1.8362690886038369,
+      "learning_rate": 1.6336561987834151e-06,
+      "loss": 1.8881,
+      "step": 102
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 3.120191999390615,
+      "learning_rate": 1.6257582694064556e-06,
+      "loss": 1.7192,
+      "step": 103
+    },
+    {
+      "epoch": 1.9074074074074074,
+      "grad_norm": 2.3586839267066044,
+      "learning_rate": 1.6177956577013846e-06,
+      "loss": 1.9387,
+      "step": 104
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": 2.779686602481001,
+      "learning_rate": 1.6097691867340543e-06,
+      "loss": 1.9497,
+      "step": 105
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 2.321935224272705,
+      "learning_rate": 1.6016796861712125e-06,
+      "loss": 1.9367,
+      "step": 106
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 2.3211469537338276,
+      "learning_rate": 1.5935279921947451e-06,
+      "loss": 1.9765,
+      "step": 107
+    },
+    {
+      "epoch": 1.9814814814814814,
+      "grad_norm": 1.8048838385036454,
+      "learning_rate": 1.585314947415242e-06,
+      "loss": 2.1524,
+      "step": 108
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.2432536623121866,
+      "learning_rate": 1.5770414007848994e-06,
+      "loss": 1.7596,
+      "step": 109
+    },
+    {
+      "epoch": 2.0185185185185186,
+      "grad_norm": 2.1527401042322984,
+      "learning_rate": 1.5687082075097674e-06,
+      "loss": 2.1903,
+      "step": 110
+    },
+    {
+      "epoch": 2.0185185185185186,
+      "grad_norm": 2.822074512897879,
+      "learning_rate": 1.5603162289613501e-06,
+      "loss": 2.0324,
+      "step": 111
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 1.9685786022400997,
+      "learning_rate": 1.551866332587568e-06,
+      "loss": 1.8009,
+      "step": 112
+    },
+    {
+      "epoch": 2.0555555555555554,
+      "grad_norm": 2.515751939304619,
+      "learning_rate": 1.5433593918230955e-06,
+      "loss": 1.9487,
+      "step": 113
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 2.349862710312166,
+      "learning_rate": 1.5347962859990742e-06,
+      "loss": 1.9967,
+      "step": 114
+    },
+    {
+      "epoch": 2.0925925925925926,
+      "grad_norm": 3.1803776539735233,
+      "learning_rate": 1.5261779002522216e-06,
+      "loss": 2.0633,
+      "step": 115
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 2.6762686321709372,
+      "learning_rate": 1.517505125433338e-06,
+      "loss": 2.1631,
+      "step": 116
+    },
+    {
+      "epoch": 2.1296296296296298,
+      "grad_norm": 3.17350275984332,
+      "learning_rate": 1.5087788580152206e-06,
+      "loss": 1.7666,
+      "step": 117
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 2.7374508335058128,
+      "learning_rate": 1.5e-06,
+      "loss": 1.6363,
+      "step": 118
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 2.518836889589819,
+      "learning_rate": 1.4911694588259037e-06,
+      "loss": 2.0306,
+      "step": 119
+    },
+    {
+      "epoch": 2.185185185185185,
+      "grad_norm": 2.0516490709057438,
+      "learning_rate": 1.482288147273456e-06,
+      "loss": 1.7322,
+      "step": 120
+    },
+    {
+      "epoch": 2.2037037037037037,
+      "grad_norm": 2.143653181079979,
+      "learning_rate": 1.4733569833711299e-06,
+      "loss": 1.9715,
+      "step": 121
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.5702663497071736,
+      "learning_rate": 1.4643768903004504e-06,
+      "loss": 1.6725,
+      "step": 122
+    },
+    {
+      "epoch": 2.240740740740741,
+      "grad_norm": 2.1780515590527045,
+      "learning_rate": 1.455348796300571e-06,
+      "loss": 1.8871,
+      "step": 123
+    },
+    {
+      "epoch": 2.259259259259259,
+      "grad_norm": 1.7384200856334007,
+      "learning_rate": 1.4462736345723259e-06,
+      "loss": 1.8607,
+      "step": 124
+    },
+    {
+      "epoch": 2.2777777777777777,
+      "grad_norm": 2.602970978377197,
+      "learning_rate": 1.437152343181765e-06,
+      "loss": 2.0933,
+      "step": 125
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 2.2409639030493516,
+      "learning_rate": 1.4279858649631928e-06,
+      "loss": 2.1028,
+      "step": 126
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 2.083427934167806,
+      "learning_rate": 1.4187751474217096e-06,
+      "loss": 1.7588,
+      "step": 127
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 1.710343556502238,
+      "learning_rate": 1.4095211426352718e-06,
+      "loss": 1.8985,
+      "step": 128
+    },
+    {
+      "epoch": 2.351851851851852,
+      "grad_norm": 2.4282958584597645,
+      "learning_rate": 1.4002248071562778e-06,
+      "loss": 1.8267,
+      "step": 129
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 2.2052175185263936,
+      "learning_rate": 1.3908871019126954e-06,
+      "loss": 2.254,
+      "step": 130
+    },
+    {
+      "epoch": 2.388888888888889,
+      "grad_norm": 2.4962771616425745,
+      "learning_rate": 1.3815089921087315e-06,
+      "loss": 1.8375,
+      "step": 131
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 2.420921240604477,
+      "learning_rate": 1.3720914471250642e-06,
+      "loss": 1.9705,
+      "step": 132
+    },
+    {
+      "epoch": 2.425925925925926,
+      "grad_norm": 1.6871014164962779,
+      "learning_rate": 1.3626354404186404e-06,
+      "loss": 1.866,
+      "step": 133
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.5220778910671986,
+      "learning_rate": 1.3531419494220545e-06,
+      "loss": 2.0116,
+      "step": 134
+    },
+    {
+      "epoch": 2.462962962962963,
+      "grad_norm": 1.9736590287767704,
+      "learning_rate": 1.343611955442513e-06,
+      "loss": 1.7881,
+      "step": 135
+    },
+    {
+      "epoch": 2.4814814814814814,
+      "grad_norm": 1.357453526449638,
+      "learning_rate": 1.334046443560402e-06,
+      "loss": 1.7624,
+      "step": 136
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.7906511346102865,
+      "learning_rate": 1.324446402527462e-06,
+      "loss": 1.7147,
+      "step": 137
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 2.0256913340352,
+      "learning_rate": 1.3148128246645848e-06,
+      "loss": 1.657,
+      "step": 138
+    },
+    {
+      "epoch": 2.537037037037037,
+      "grad_norm": 2.4368648915605786,
+      "learning_rate": 1.3051467057592413e-06,
+      "loss": 1.848,
+      "step": 139
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 1.7920760208344662,
+      "learning_rate": 1.2954490449625491e-06,
+      "loss": 2.2794,
+      "step": 140
+    },
+    {
+      "epoch": 2.574074074074074,
+      "grad_norm": 2.5934703428783115,
+      "learning_rate": 1.2857208446859957e-06,
+      "loss": 2.1465,
+      "step": 141
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 1.788260906958661,
+      "learning_rate": 1.2759631104978224e-06,
+      "loss": 2.067,
+      "step": 142
+    },
+    {
+      "epoch": 2.611111111111111,
+      "grad_norm": 2.7522723362234474,
+      "learning_rate": 1.2661768510190816e-06,
+      "loss": 1.8176,
+      "step": 143
+    },
+    {
+      "epoch": 2.6296296296296298,
+      "grad_norm": 2.43143502900473,
+      "learning_rate": 1.2563630778193802e-06,
+      "loss": 2.3366,
+      "step": 144
+    },
+    {
+      "epoch": 2.648148148148148,
+      "grad_norm": 1.7241238478367036,
+      "learning_rate": 1.2465228053123172e-06,
+      "loss": 1.9895,
+      "step": 145
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 2.0266143160589802,
+      "learning_rate": 1.2366570506506268e-06,
+      "loss": 1.7781,
+      "step": 146
+    },
+    {
+      "epoch": 2.685185185185185,
+      "grad_norm": 1.9459670874156856,
+      "learning_rate": 1.226766833621041e-06,
+      "loss": 2.3116,
+      "step": 147
+    },
+    {
+      "epoch": 2.7037037037037037,
+      "grad_norm": 2.248556130449579,
+      "learning_rate": 1.2168531765388755e-06,
+      "loss": 1.8032,
+      "step": 148
+    },
+    {
+      "epoch": 2.7222222222222223,
+      "grad_norm": 1.711136470727862,
+      "learning_rate": 1.2069171041423583e-06,
+      "loss": 1.6228,
+      "step": 149
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 2.4614425382704352,
+      "learning_rate": 1.1969596434867062e-06,
+      "loss": 1.9709,
+      "step": 150
+    },
+    {
+      "epoch": 2.7592592592592595,
+      "grad_norm": 2.3445742482429788,
+      "learning_rate": 1.186981823837961e-06,
+      "loss": 2.0597,
+      "step": 151
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 1.6706837512637804,
+      "learning_rate": 1.1769846765665992e-06,
+      "loss": 1.6263,
+      "step": 152
+    },
+    {
+      "epoch": 2.7962962962962963,
+      "grad_norm": 1.6603060271536991,
+      "learning_rate": 1.1669692350409222e-06,
+      "loss": 1.8723,
+      "step": 153
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 1.7552257393882156,
+      "learning_rate": 1.1569365345202413e-06,
+      "loss": 2.224,
+      "step": 154
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 1.3677514217091091,
+      "learning_rate": 1.1468876120478662e-06,
+      "loss": 1.897,
+      "step": 155
+    },
+    {
+      "epoch": 2.851851851851852,
+      "grad_norm": 1.4681588115995392,
+      "learning_rate": 1.1368235063439102e-06,
+      "loss": 1.7654,
+      "step": 156
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 1.4166676047405766,
+      "learning_rate": 1.1267452576979218e-06,
+      "loss": 1.7817,
+      "step": 157
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 1.5999665116208726,
+      "learning_rate": 1.1166539078613525e-06,
+      "loss": 1.814,
+      "step": 158
+    },
+    {
+      "epoch": 2.9074074074074074,
+      "grad_norm": 1.8734358713251535,
+      "learning_rate": 1.106550499939876e-06,
+      "loss": 2.0783,
+      "step": 159
+    },
+    {
+      "epoch": 2.925925925925926,
+      "grad_norm": 1.7212322982329384,
+      "learning_rate": 1.0964360782855666e-06,
+      "loss": 2.0753,
+      "step": 160
+    },
+    {
+      "epoch": 2.9444444444444446,
+      "grad_norm": 2.144799198000555,
+      "learning_rate": 1.086311688388946e-06,
+      "loss": 1.8936,
+      "step": 161
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 1.578076988317517,
+      "learning_rate": 1.076178376770918e-06,
+      "loss": 1.8926,
+      "step": 162
+    },
+    {
+      "epoch": 2.9814814814814814,
+      "grad_norm": 2.092387225323448,
+      "learning_rate": 1.0660371908745908e-06,
+      "loss": 1.8244,
+      "step": 163
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.91051937209127,
+      "learning_rate": 1.0558891789570082e-06,
+      "loss": 1.8447,
+      "step": 164
+    },
+    {
+      "epoch": 3.0185185185185186,
+      "grad_norm": 2.011878655711519,
+      "learning_rate": 1.0457353899807946e-06,
+      "loss": 1.6429,
+      "step": 165
+    },
+    {
+      "epoch": 3.0185185185185186,
+      "grad_norm": 1.501437779159261,
+      "learning_rate": 1.0355768735057273e-06,
+      "loss": 1.8726,
+      "step": 166
+    },
+    {
+      "epoch": 3.037037037037037,
+      "grad_norm": 2.2762397392089597,
+      "learning_rate": 1.0254146795802495e-06,
+      "loss": 1.8501,
+      "step": 167
+    },
+    {
+      "epoch": 3.0555555555555554,
+      "grad_norm": 1.711019377794848,
+      "learning_rate": 1.015249858632926e-06,
+      "loss": 1.9443,
+      "step": 168
+    },
+    {
+      "epoch": 3.074074074074074,
+      "grad_norm": 2.1218173803583733,
+      "learning_rate": 1.0050834613638694e-06,
+      "loss": 1.5682,
+      "step": 169
+    },
+    {
+      "epoch": 3.0925925925925926,
+      "grad_norm": 2.2421674612074383,
+      "learning_rate": 9.949165386361303e-07,
+      "loss": 1.8014,
+      "step": 170
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 2.0898372243057706,
+      "learning_rate": 9.847501413670742e-07,
+      "loss": 1.8711,
+      "step": 171
+    },
+    {
+      "epoch": 3.1296296296296298,
+      "grad_norm": 2.367436693252952,
+      "learning_rate": 9.745853204197508e-07,
+      "loss": 1.9004,
+      "step": 172
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 1.756679866289546,
+      "learning_rate": 9.644231264942724e-07,
+      "loss": 1.8121,
+      "step": 173
+    },
+    {
+      "epoch": 3.1666666666666665,
+      "grad_norm": 1.8172318892802939,
+      "learning_rate": 9.542646100192055e-07,
+      "loss": 1.9013,
+      "step": 174
+    },
+    {
+      "epoch": 3.185185185185185,
+      "grad_norm": 1.7124997061951257,
+      "learning_rate": 9.441108210429921e-07,
+      "loss": 1.7851,
+      "step": 175
+    },
+    {
+      "epoch": 3.2037037037037037,
+      "grad_norm": 1.4438554381375786,
+      "learning_rate": 9.339628091254091e-07,
+      "loss": 1.5955,
+      "step": 176
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 1.4447841103018684,
+      "learning_rate": 9.238216232290821e-07,
+      "loss": 2.0907,
+      "step": 177
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 1.6937928047736799,
+      "learning_rate": 9.136883116110541e-07,
+      "loss": 1.915,
+      "step": 178
+    },
+    {
+      "epoch": 3.259259259259259,
+      "grad_norm": 1.306322824987709,
+      "learning_rate": 9.035639217144334e-07,
+      "loss": 2.0679,
+      "step": 179
+    },
+    {
+      "epoch": 3.2777777777777777,
+      "grad_norm": 1.850877358174252,
+      "learning_rate": 8.93449500060124e-07,
+      "loss": 2.024,
+      "step": 180
+    },
+    {
+      "epoch": 3.2962962962962963,
+      "grad_norm": 1.5601775038920753,
+      "learning_rate": 8.833460921386477e-07,
+      "loss": 1.9335,
+      "step": 181
+    },
+    {
+      "epoch": 3.314814814814815,
+      "grad_norm": 2.270038996895677,
+      "learning_rate": 8.732547423020784e-07,
+      "loss": 2.3019,
+      "step": 182
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.3421300711986788,
+      "learning_rate": 8.631764936560899e-07,
+      "loss": 1.8503,
+      "step": 183
+    },
+    {
+      "epoch": 3.351851851851852,
+      "grad_norm": 2.071755001265988,
+      "learning_rate": 8.53112387952134e-07,
+      "loss": 1.838,
+      "step": 184
+    },
+    {
+      "epoch": 3.3703703703703702,
+      "grad_norm": 1.6174575169544287,
+      "learning_rate": 8.430634654797588e-07,
+      "loss": 2.2364,
+      "step": 185
+    },
+    {
+      "epoch": 3.388888888888889,
+      "grad_norm": 1.801580774474325,
+      "learning_rate": 8.330307649590779e-07,
+      "loss": 1.7633,
+      "step": 186
+    },
+    {
+      "epoch": 3.4074074074074074,
+      "grad_norm": 2.058657705709402,
+      "learning_rate": 8.230153234334007e-07,
+      "loss": 2.2177,
+      "step": 187
+    },
+    {
+      "epoch": 3.425925925925926,
+      "grad_norm": 1.5267427939756337,
+      "learning_rate": 8.130181761620392e-07,
+      "loss": 1.8588,
+      "step": 188
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 1.8491296560891988,
+      "learning_rate": 8.030403565132942e-07,
+      "loss": 2.0561,
+      "step": 189
+    },
+    {
+      "epoch": 3.462962962962963,
+      "grad_norm": 1.1987453530026493,
+      "learning_rate": 7.930828958576417e-07,
+      "loss": 2.0565,
+      "step": 190
+    },
+    {
+      "epoch": 3.4814814814814814,
+      "grad_norm": 1.7195298906541316,
+      "learning_rate": 7.831468234611247e-07,
+      "loss": 2.0798,
+      "step": 191
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 1.20797833272688,
+      "learning_rate": 7.73233166378959e-07,
+      "loss": 1.8627,
+      "step": 192
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 1.5640684128902402,
+      "learning_rate": 7.633429493493729e-07,
+      "loss": 2.0137,
+      "step": 193
+    },
+    {
+      "epoch": 3.537037037037037,
+      "grad_norm": 1.6824510280578688,
+      "learning_rate": 7.53477194687683e-07,
+      "loss": 2.1517,
+      "step": 194
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 1.4155640553151332,
+      "learning_rate": 7.4363692218062e-07,
+      "loss": 1.9426,
+      "step": 195
+    },
+    {
+      "epoch": 3.574074074074074,
+      "grad_norm": 1.3939742232946681,
+      "learning_rate": 7.338231489809182e-07,
+      "loss": 1.7207,
+      "step": 196
+    },
+    {
+      "epoch": 3.5925925925925926,
+      "grad_norm": 1.4589160544776356,
+      "learning_rate": 7.240368895021775e-07,
+      "loss": 1.8217,
+      "step": 197
+    },
+    {
+      "epoch": 3.611111111111111,
+      "grad_norm": 1.3991775241667967,
+      "learning_rate": 7.142791553140044e-07,
+      "loss": 1.9021,
+      "step": 198
+    },
+    {
+      "epoch": 3.6296296296296298,
+      "grad_norm": 1.5300112446112555,
+      "learning_rate": 7.045509550374509e-07,
+      "loss": 1.9647,
+      "step": 199
+    },
+    {
+      "epoch": 3.648148148148148,
+      "grad_norm": 1.449273309005635,
+      "learning_rate": 6.948532942407587e-07,
+      "loss": 1.9613,
+      "step": 200
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 1.069899380500529,
+      "learning_rate": 6.851871753354153e-07,
+      "loss": 1.7452,
+      "step": 201
+    },
+    {
+      "epoch": 3.685185185185185,
+      "grad_norm": 1.5579308530316032,
+      "learning_rate": 6.755535974725379e-07,
+      "loss": 1.9134,
+      "step": 202
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 1.0814459794670248,
+      "learning_rate": 6.659535564395982e-07,
+      "loss": 1.6609,
+      "step": 203
+    },
+    {
+      "epoch": 3.7222222222222223,
+      "grad_norm": 1.8876967693657951,
+      "learning_rate": 6.563880445574872e-07,
+      "loss": 2.0948,
+      "step": 204
+    },
+    {
+      "epoch": 3.7407407407407405,
+      "grad_norm": 1.6093595543167938,
+      "learning_rate": 6.468580505779455e-07,
+      "loss": 1.6327,
+      "step": 205
+    },
+    {
+      "epoch": 3.7592592592592595,
+      "grad_norm": 1.9559640817344714,
+      "learning_rate": 6.373645595813596e-07,
+      "loss": 1.6376,
+      "step": 206
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 2.0405778845643288,
+      "learning_rate": 6.27908552874936e-07,
+      "loss": 2.1409,
+      "step": 207
+    },
+    {
+      "epoch": 3.7962962962962963,
+      "grad_norm": 1.230340254163767,
+      "learning_rate": 6.184910078912686e-07,
+      "loss": 1.686,
+      "step": 208
+    },
+    {
+      "epoch": 3.814814814814815,
+      "grad_norm": 2.171420345125834,
+      "learning_rate": 6.091128980873045e-07,
+      "loss": 1.9347,
+      "step": 209
+    },
+    {
+      "epoch": 3.8333333333333335,
+      "grad_norm": 1.8008532771859842,
+      "learning_rate": 5.997751928437219e-07,
+      "loss": 2.1292,
+      "step": 210
+    },
+    {
+      "epoch": 3.851851851851852,
+      "grad_norm": 1.502892647903443,
+      "learning_rate": 5.904788573647282e-07,
+      "loss": 1.7302,
+      "step": 211
+    },
+    {
+      "epoch": 3.8703703703703702,
+      "grad_norm": 1.4720170454603325,
+      "learning_rate": 5.812248525782901e-07,
+      "loss": 1.6652,
+      "step": 212
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 1.4078435809618528,
+      "learning_rate": 5.720141350368072e-07,
+      "loss": 1.7847,
+      "step": 213
+    },
+    {
+      "epoch": 3.9074074074074074,
+      "grad_norm": 1.2860107867972834,
+      "learning_rate": 5.628476568182349e-07,
+      "loss": 1.818,
+      "step": 214
+    },
+    {
+      "epoch": 3.925925925925926,
+      "grad_norm": 1.5761560916907795,
+      "learning_rate": 5.537263654276743e-07,
+      "loss": 1.787,
+      "step": 215
+    },
+    {
+      "epoch": 3.9444444444444446,
+      "grad_norm": 1.463921943518727,
+      "learning_rate": 5.446512036994286e-07,
+      "loss": 1.9223,
+      "step": 216
+    },
+    {
+      "epoch": 3.962962962962963,
+      "grad_norm": 1.2770391505323755,
+      "learning_rate": 5.356231096995499e-07,
+      "loss": 1.5593,
+      "step": 217
+    },
+    {
+      "epoch": 3.9814814814814814,
+      "grad_norm": 1.4711865688844035,
+      "learning_rate": 5.266430166288704e-07,
+      "loss": 2.0863,
+      "step": 218
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.1447313661292717,
+      "learning_rate": 5.177118527265437e-07,
+      "loss": 1.9428,
+      "step": 219
+    },
+    {
+      "epoch": 4.018518518518519,
+      "grad_norm": 1.6196943319397998,
+      "learning_rate": 5.088305411740965e-07,
+      "loss": 2.2068,
+      "step": 220
+    },
+    {
+      "epoch": 4.018518518518518,
+      "grad_norm": 1.2766493962889875,
+      "learning_rate": 5.000000000000002e-07,
+      "loss": 1.7437,
+      "step": 221
+    },
+    {
+      "epoch": 4.037037037037037,
+      "grad_norm": 1.594306405599087,
+      "learning_rate": 4.912211419847793e-07,
+      "loss": 2.0219,
+      "step": 222
+    },
+    {
+      "epoch": 4.055555555555555,
+      "grad_norm": 1.227716475966799,
+      "learning_rate": 4.82494874566662e-07,
+      "loss": 2.187,
+      "step": 223
+    },
+    {
+      "epoch": 4.074074074074074,
+      "grad_norm": 1.2852396998354376,
+      "learning_rate": 4.738220997477784e-07,
+      "loss": 1.8363,
+      "step": 224
+    },
+    {
+      "epoch": 4.092592592592593,
+      "grad_norm": 1.0923893050000644,
+      "learning_rate": 4.6520371400092584e-07,
+      "loss": 1.7177,
+      "step": 225
+    },
+    {
+      "epoch": 4.111111111111111,
+      "grad_norm": 1.1495819987216884,
+      "learning_rate": 4.5664060817690476e-07,
+      "loss": 2.0734,
+      "step": 226
+    },
+    {
+      "epoch": 4.12962962962963,
+      "grad_norm": 1.1120083230916684,
+      "learning_rate": 4.481336674124323e-07,
+      "loss": 1.7847,
+      "step": 227
+    },
+    {
+      "epoch": 4.148148148148148,
+      "grad_norm": 0.9789098979808262,
+      "learning_rate": 4.3968377103865016e-07,
+      "loss": 1.7989,
+      "step": 228
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.9342477457439083,
+      "learning_rate": 4.3129179249023274e-07,
+      "loss": 1.6785,
+      "step": 229
+    },
+    {
+      "epoch": 4.185185185185185,
+      "grad_norm": 1.0718449337061247,
+      "learning_rate": 4.229585992151006e-07,
+      "loss": 1.7953,
+      "step": 230
+    },
+    {
+      "epoch": 4.203703703703703,
+      "grad_norm": 1.1500516991492213,
+      "learning_rate": 4.1468505258475784e-07,
+      "loss": 1.3975,
+      "step": 231
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 0.9650831232767911,
+      "learning_rate": 4.0647200780525483e-07,
+      "loss": 1.8603,
+      "step": 232
+    },
+    {
+      "epoch": 4.2407407407407405,
+      "grad_norm": 1.0207088687244406,
+      "learning_rate": 3.983203138287876e-07,
+      "loss": 1.9807,
+      "step": 233
+    },
+    {
+      "epoch": 4.2592592592592595,
+      "grad_norm": 1.1991752171611891,
+      "learning_rate": 3.9023081326594564e-07,
+      "loss": 2.2322,
+      "step": 234
+    },
+    {
+      "epoch": 4.277777777777778,
+      "grad_norm": 1.0807801212200088,
+      "learning_rate": 3.822043422986153e-07,
+      "loss": 1.6295,
+      "step": 235
+    },
+    {
+      "epoch": 4.296296296296296,
+      "grad_norm": 1.0103392155699495,
+      "learning_rate": 3.742417305935442e-07,
+      "loss": 1.7882,
+      "step": 236
+    },
+    {
+      "epoch": 4.314814814814815,
+      "grad_norm": 1.0657639750720669,
+      "learning_rate": 3.663438012165848e-07,
+      "loss": 1.6027,
+      "step": 237
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.9495451533397854,
+      "learning_rate": 3.5851137054761426e-07,
+      "loss": 1.8212,
+      "step": 238
+    },
+    {
+      "epoch": 4.351851851851852,
+      "grad_norm": 1.0780389016215326,
+      "learning_rate": 3.507452481961495e-07,
+      "loss": 1.6304,
+      "step": 239
+    },
+    {
+      "epoch": 4.37037037037037,
+      "grad_norm": 1.0244203325558825,
+      "learning_rate": 3.430462369176619e-07,
+      "loss": 1.9347,
+      "step": 240
+    },
+    {
+      "epoch": 4.388888888888889,
+      "grad_norm": 0.9762810523750869,
+      "learning_rate": 3.3541513253059726e-07,
+      "loss": 2.0351,
+      "step": 241
+    },
+    {
+      "epoch": 4.407407407407407,
+      "grad_norm": 0.8894982063199672,
+      "learning_rate": 3.278527238341163e-07,
+      "loss": 1.7788,
+      "step": 242
+    },
+    {
+      "epoch": 4.425925925925926,
+      "grad_norm": 0.9573443483478868,
+      "learning_rate": 3.2035979252655976e-07,
+      "loss": 1.6824,
+      "step": 243
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.878347387417952,
+      "learning_rate": 3.129371131246459e-07,
+      "loss": 1.7893,
+      "step": 244
+    },
+    {
+      "epoch": 4.462962962962963,
+      "grad_norm": 1.2131347174643223,
+      "learning_rate": 3.05585452883412e-07,
+      "loss": 2.4755,
+      "step": 245
+    },
+    {
+      "epoch": 4.481481481481482,
+      "grad_norm": 0.9278993006726863,
+      "learning_rate": 2.9830557171690693e-07,
+      "loss": 2.051,
+      "step": 246
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.9769923688632531,
+      "learning_rate": 2.910982221196404e-07,
+      "loss": 1.8307,
+      "step": 247
+    },
+    {
+      "epoch": 4.518518518518518,
+      "grad_norm": 1.0084007217465136,
+      "learning_rate": 2.8396414908880095e-07,
+      "loss": 2.0386,
+      "step": 248
+    },
+    {
+      "epoch": 4.537037037037037,
+      "grad_norm": 1.0273787706173494,
+      "learning_rate": 2.769040900472488e-07,
+      "loss": 1.9072,
+      "step": 249
+    },
+    {
+      "epoch": 4.555555555555555,
+      "grad_norm": 0.8621559648712259,
+      "learning_rate": 2.6991877476728985e-07,
+      "loss": 1.706,
+      "step": 250
+    },
+    {
+      "epoch": 4.574074074074074,
+      "grad_norm": 0.8247377172080764,
+      "learning_rate": 2.6300892529524264e-07,
+      "loss": 1.8414,
+      "step": 251
+    },
+    {
+      "epoch": 4.592592592592593,
+      "grad_norm": 0.8925073470001154,
+      "learning_rate": 2.56175255876804e-07,
+      "loss": 1.9007,
+      "step": 252
+    },
+    {
+      "epoch": 4.611111111111111,
+      "grad_norm": 0.7860274094152706,
+      "learning_rate": 2.494184728832179e-07,
+      "loss": 1.8654,
+      "step": 253
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 0.8936613069940655,
+      "learning_rate": 2.427392747382623e-07,
+      "loss": 1.6996,
+      "step": 254
+    },
+    {
+      "epoch": 4.648148148148148,
+      "grad_norm": 1.0827181264619206,
+      "learning_rate": 2.3613835184605523e-07,
+      "loss": 1.9413,
+      "step": 255
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.8918696543620299,
+      "learning_rate": 2.2961638651968974e-07,
+      "loss": 1.856,
+      "step": 256
+    },
+    {
+      "epoch": 4.685185185185185,
+      "grad_norm": 0.9976782397503938,
+      "learning_rate": 2.2317405291070567e-07,
+      "loss": 1.8228,
+      "step": 257
+    },
+    {
+      "epoch": 4.703703703703704,
+      "grad_norm": 1.021922767232776,
+      "learning_rate": 2.1681201693940666e-07,
+      "loss": 2.0057,
+      "step": 258
+    },
+    {
+      "epoch": 4.722222222222222,
+      "grad_norm": 1.1673943142630625,
+      "learning_rate": 2.1053093622602402e-07,
+      "loss": 1.9204,
+      "step": 259
+    },
+    {
+      "epoch": 4.7407407407407405,
+      "grad_norm": 1.0912049168909328,
+      "learning_rate": 2.043314600227425e-07,
+      "loss": 1.8173,
+      "step": 260
+    },
+    {
+      "epoch": 4.7592592592592595,
+      "grad_norm": 0.9358084522077252,
+      "learning_rate": 1.9821422914658957e-07,
+      "loss": 2.0846,
+      "step": 261
+    },
+    {
+      "epoch": 4.777777777777778,
+      "grad_norm": 1.0481784665647413,
+      "learning_rate": 1.921798759131953e-07,
+      "loss": 1.9789,
+      "step": 262
+    },
+    {
+      "epoch": 4.796296296296296,
+      "grad_norm": 0.983048254792995,
+      "learning_rate": 1.8622902407143392e-07,
+      "loss": 1.9294,
+      "step": 263
+    },
+    {
+      "epoch": 4.814814814814815,
+      "grad_norm": 0.8359638487960833,
+      "learning_rate": 1.8036228873894744e-07,
+      "loss": 1.7806,
+      "step": 264
+    },
+    {
+      "epoch": 4.833333333333333,
+      "grad_norm": 1.1295927764034195,
+      "learning_rate": 1.7458027633856475e-07,
+      "loss": 1.9495,
+      "step": 265
+    },
+    {
+      "epoch": 4.851851851851852,
+      "grad_norm": 1.1032897990848558,
+      "learning_rate": 1.6888358453561646e-07,
+      "loss": 2.0724,
+      "step": 266
+    },
+    {
+      "epoch": 4.87037037037037,
+      "grad_norm": 0.855002738874884,
+      "learning_rate": 1.632728021761579e-07,
+      "loss": 2.102,
+      "step": 267
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 1.0646161730662291,
+      "learning_rate": 1.5774850922610116e-07,
+      "loss": 1.9046,
+      "step": 268
+    },
+    {
+      "epoch": 4.907407407407407,
+      "grad_norm": 1.0109654313968932,
+      "learning_rate": 1.5231127671126676e-07,
+      "loss": 2.0854,
+      "step": 269
+    },
+    {
+      "epoch": 4.925925925925926,
+      "grad_norm": 0.9390534047671891,
+      "learning_rate": 1.4696166665835852e-07,
+      "loss": 2.1436,
+      "step": 270
+    },
+    {
+      "epoch": 4.944444444444445,
+      "grad_norm": 0.9838446669064714,
+      "learning_rate": 1.4170023203686875e-07,
+      "loss": 1.9317,
+      "step": 271
+    },
+    {
+      "epoch": 4.962962962962963,
+      "grad_norm": 1.0678273880700424,
+      "learning_rate": 1.3652751670192075e-07,
+      "loss": 1.8309,
+      "step": 272
+    },
+    {
+      "epoch": 4.981481481481482,
+      "grad_norm": 1.1853311551704062,
+      "learning_rate": 1.3144405533805136e-07,
+      "loss": 1.948,
+      "step": 273
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.0844767215232378,
+      "learning_rate": 1.2645037340394281e-07,
+      "loss": 2.1066,
+      "step": 274
+    },
+    {
+      "epoch": 5.018518518518518,
+      "grad_norm": 0.8509695959322425,
+      "learning_rate": 1.2154698707810928e-07,
+      "loss": 1.9217,
+      "step": 275
+    },
+    {
+      "epoch": 5.037037037037037,
+      "grad_norm": 0.9599815386335595,
+      "learning_rate": 1.167344032055394e-07,
+      "loss": 1.9898,
+      "step": 276
+    },
+    {
+      "epoch": 5.055555555555555,
+      "grad_norm": 0.9561022219351966,
+      "learning_rate": 1.1201311924530688e-07,
+      "loss": 1.6967,
+      "step": 277
+    },
+    {
+      "epoch": 5.074074074074074,
+      "grad_norm": 0.8614534074294055,
+      "learning_rate": 1.0738362321914995e-07,
+      "loss": 1.7586,
+      "step": 278
+    },
+    {
+      "epoch": 5.092592592592593,
+      "grad_norm": 0.884706815883145,
+      "learning_rate": 1.0284639366102598e-07,
+      "loss": 1.8692,
+      "step": 279
+    },
+    {
+      "epoch": 5.111111111111111,
+      "grad_norm": 0.8641496604329509,
+      "learning_rate": 9.840189956764677e-08,
+      "loss": 2.1101,
+      "step": 280
+    },
+    {
+      "epoch": 5.12962962962963,
+      "grad_norm": 0.8465414034017087,
+      "learning_rate": 9.405060035000134e-08,
+      "loss": 1.7827,
+      "step": 281
+    },
+    {
+      "epoch": 5.148148148148148,
+      "grad_norm": 0.6966794157650356,
+      "learning_rate": 8.979294578586738e-08,
+      "loss": 1.6446,
+      "step": 282
+    },
+    {
+      "epoch": 5.166666666666667,
+      "grad_norm": 0.8581271311276034,
+      "learning_rate": 8.562937597331898e-08,
+      "loss": 1.7243,
+      "step": 283
+    },
+    {
+      "epoch": 5.185185185185185,
+      "grad_norm": 0.9976947326325505,
+      "learning_rate": 8.156032128523694e-08,
+      "loss": 1.8994,
+      "step": 284
+    },
+    {
+      "epoch": 5.203703703703703,
+      "grad_norm": 0.9786757162446749,
+      "learning_rate": 7.758620232482083e-08,
+      "loss": 1.8625,
+      "step": 285
+    },
+    {
+      "epoch": 5.222222222222222,
+      "grad_norm": 0.7563393752170862,
+      "learning_rate": 7.370742988211364e-08,
+      "loss": 1.7512,
+      "step": 286
+    },
+    {
+      "epoch": 5.2407407407407405,
+      "grad_norm": 0.7955178168012043,
+      "learning_rate": 6.99244048915405e-08,
+      "loss": 2.2105,
+      "step": 287
+    },
+    {
+      "epoch": 5.2592592592592595,
+      "grad_norm": 0.8951178929520269,
+      "learning_rate": 6.623751839046455e-08,
+      "loss": 1.8276,
+      "step": 288
+    },
+    {
+      "epoch": 5.277777777777778,
+      "grad_norm": 0.9912120605663316,
+      "learning_rate": 6.264715147876742e-08,
+      "loss": 2.2784,
+      "step": 289
+    },
+    {
+      "epoch": 5.296296296296296,
+      "grad_norm": 0.759976000502015,
+      "learning_rate": 5.915367527945614e-08,
+      "loss": 1.9346,
+      "step": 290
+    },
+    {
+      "epoch": 5.314814814814815,
+      "grad_norm": 0.7423091105639062,
+      "learning_rate": 5.575745090030137e-08,
+      "loss": 1.8795,
+      "step": 291
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.7811530255930925,
+      "learning_rate": 5.245882939651181e-08,
+      "loss": 2.0584,
+      "step": 292
+    },
+    {
+      "epoch": 5.351851851851852,
+      "grad_norm": 0.9202352755672565,
+      "learning_rate": 4.9258151734445694e-08,
+      "loss": 2.0563,
+      "step": 293
+    },
+    {
+      "epoch": 5.37037037037037,
+      "grad_norm": 0.7972657702760176,
+      "learning_rate": 4.6155748756367294e-08,
+      "loss": 1.8333,
+      "step": 294
+    },
+    {
+      "epoch": 5.388888888888889,
+      "grad_norm": 0.6829451582697305,
+      "learning_rate": 4.3151941146248873e-08,
+      "loss": 1.9896,
+      "step": 295
+    },
+    {
+      "epoch": 5.407407407407407,
+      "grad_norm": 0.7886670762082094,
+      "learning_rate": 4.0247039396622e-08,
+      "loss": 1.8183,
+      "step": 296
+    },
+    {
+      "epoch": 5.425925925925926,
+      "grad_norm": 0.8840244220041553,
+      "learning_rate": 3.7441343776484113e-08,
+      "loss": 1.9354,
+      "step": 297
+    },
+    {
+      "epoch": 5.444444444444445,
+      "grad_norm": 0.71587738270711,
+      "learning_rate": 3.4735144300260255e-08,
+      "loss": 2.0167,
+      "step": 298
+    },
+    {
+      "epoch": 5.462962962962963,
+      "grad_norm": 0.7108094024246895,
+      "learning_rate": 3.212872069782513e-08,
+      "loss": 1.7169,
+      "step": 299
+    },
+    {
+      "epoch": 5.481481481481482,
+      "grad_norm": 0.6662930242485889,
+      "learning_rate": 2.962234238558925e-08,
+      "loss": 2.2062,
+      "step": 300
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.7122621954506775,
+      "learning_rate": 2.721626843864977e-08,
+      "loss": 2.0591,
+      "step": 301
+    },
+    {
+      "epoch": 5.518518518518518,
+      "grad_norm": 0.626318180659774,
+      "learning_rate": 2.491074756401068e-08,
+      "loss": 1.5866,
+      "step": 302
+    },
+    {
+      "epoch": 5.537037037037037,
+      "grad_norm": 0.6909592708288532,
+      "learning_rate": 2.2706018074875043e-08,
+      "loss": 1.9005,
+      "step": 303
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 0.7144569439769612,
+      "learning_rate": 2.0602307866012246e-08,
+      "loss": 2.0294,
+      "step": 304
+    },
+    {
+      "epoch": 5.574074074074074,
+      "grad_norm": 0.684647174393133,
+      "learning_rate": 1.8599834390199853e-08,
+      "loss": 1.6046,
+      "step": 305
+    },
+    {
+      "epoch": 5.592592592592593,
+      "grad_norm": 0.7752801436279185,
+      "learning_rate": 1.6698804635747576e-08,
+      "loss": 1.7937,
+      "step": 306
+    },
+    {
+      "epoch": 5.611111111111111,
+      "grad_norm": 0.6862611972609113,
+      "learning_rate": 1.4899415105101066e-08,
+      "loss": 1.7256,
+      "step": 307
+    },
+    {
+      "epoch": 5.62962962962963,
+      "grad_norm": 0.6608135193001434,
+      "learning_rate": 1.3201851794530371e-08,
+      "loss": 1.7763,
+      "step": 308
+    },
+    {
+      "epoch": 5.648148148148148,
+      "grad_norm": 0.7625095579861546,
+      "learning_rate": 1.1606290174903888e-08,
+      "loss": 2.0082,
+      "step": 309
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 0.6914220267730987,
+      "learning_rate": 1.0112895173551183e-08,
+      "loss": 1.9359,
+      "step": 310
+    },
+    {
+      "epoch": 5.685185185185185,
+      "grad_norm": 0.6505975431309626,
+      "learning_rate": 8.721821157214316e-09,
+      "loss": 1.9317,
+      "step": 311
+    },
+    {
+      "epoch": 5.703703703703704,
+      "grad_norm": 0.6947915176450158,
+      "learning_rate": 7.433211916092141e-09,
+      "loss": 1.6243,
+      "step": 312
+    },
+    {
+      "epoch": 5.722222222222222,
+      "grad_norm": 0.6360099423433963,
+      "learning_rate": 6.247200648976991e-09,
+      "loss": 1.9931,
+      "step": 313
+    },
+    {
+      "epoch": 5.7407407407407405,
+      "grad_norm": 0.6796797146249973,
+      "learning_rate": 5.163909949486233e-09,
+      "loss": 1.9858,
+      "step": 314
+    },
+    {
+      "epoch": 5.7592592592592595,
+      "grad_norm": 0.7636965994787633,
+      "learning_rate": 4.183451793390747e-09,
+      "loss": 1.8201,
+      "step": 315
+    },
+    {
+      "epoch": 5.777777777777778,
+      "grad_norm": 0.6434704456483539,
+      "learning_rate": 3.30592752703962e-09,
+      "loss": 1.5983,
+      "step": 316
+    },
+    {
+      "epoch": 5.796296296296296,
+      "grad_norm": 0.6697682736960676,
+      "learning_rate": 2.531427856885093e-09,
+      "loss": 1.985,
+      "step": 317
+    },
+    {
+      "epoch": 5.814814814814815,
+      "grad_norm": 0.657234650874368,
+      "learning_rate": 1.8600328401061627e-09,
+      "loss": 2.0918,
+      "step": 318
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 0.6249721935624161,
+      "learning_rate": 1.2918118763335372e-09,
+      "loss": 2.1123,
+      "step": 319
+    },
+    {
+      "epoch": 5.851851851851852,
+      "grad_norm": 0.7274585554347512,
+      "learning_rate": 8.268237004757095e-10,
+      "loss": 2.2962,
+      "step": 320
+    },
+    {
+      "epoch": 5.87037037037037,
+      "grad_norm": 0.6060864357328691,
+      "learning_rate": 4.651163766484778e-10,
+      "loss": 1.6461,
+      "step": 321
+    },
+    {
+      "epoch": 5.888888888888889,
+      "grad_norm": 0.6626618247650778,
+      "learning_rate": 2.0672729320581063e-10,
+      "loss": 2.0178,
+      "step": 322
+    },
+    {
+      "epoch": 5.907407407407407,
+      "grad_norm": 0.5905608542721459,
+      "learning_rate": 5.1683158875936994e-11,
+      "loss": 1.7269,
+      "step": 323
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.7138681736753105,
+      "learning_rate": 0.0,
+      "loss": 2.11,
+      "step": 324
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 324,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 54,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 128024720179200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444f31a52dc244c723586aec7f0e2f3b527599a865d311708a904c42d249ef10
+size 8248

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)