Add files using upload-large-folder tool

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 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,
+    "type": "dynamic"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.39.3"
+}

global_step5102/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a73100674c39a883e880005902f0837adbe686691f4a7323e02f6e442764d1
+size 12045397436

global_step5102/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c32be903f56227d4e7b6d7263aa577d44d264871cd1169914d1769db5a8a930
+size 12045398460

global_step5102/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:de7e0aa36af7057b2ed0c473ac6da7dd98e1a096fb9d8331030b2f94bb589d03
+size 12045398844

global_step5102/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990031945a38b6e854bdae4600595750b2ae0a154c17427267da7e491cfd3850
+size 12045398716

global_step5102/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b77e5861e7758a10c7eadb8df4d2cde0601bc2dd75d0a18d3ac82b007633a70
+size 12045398716

global_step5102/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe09b2b6e02c01818fa4949ccbe23854682673f2be30b08c08bca88d3057308
+size 12045398972

global_step5102/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09339726b1840329b8135a6410fc1c121fc82d677930bdd13fd0c05831d354e4
+size 12045398524

global_step5102/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd25c54e99f6b19b8c4923d01e2eddb6c845521c18ae6a92ce89c25ea952542
+size 12045397372

global_step5102/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5604e0eb337aaa037c379895b1a43d163821976b1329fa4eb25f8aaacf82b4
+size 16060611168

latest

@@ -0,0 +1 @@
+global_step5102

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a8b2275f96a4e18c0fd299bdc6fa526ab48e6515e063ef102adcfded6f1f3f
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0623ffd0509a260c7017dcbfe23a7bf22a3a9a889e5d35bae6bdb1265e4834a5
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299790534de3d335926e670155fb13fb3e5a9baa95bcad9e69c80b3cee60a6e
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24aea5d2c00b65c5c9777f2a690559ed840945755572ab7b74d0b8e55c54763
+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:af2966519bc2bd5b140990b36ccff1e3f2464c393599f20e3d4f0fd65bf3ef99
+size 15920

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8553e9d157dbd23eaef7ca402d63273fefa7e1a15fa0ad8029b205c05463588d
+size 15920

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc971a50765f8d8cf415b82c5d13f70ddac495f2cf26090bc8646b95b5e44d2
+size 15920

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e098f87d6f8966bf47dd4ea457af8a39a52078075152b45a094e31710de7b8
+size 15920

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0a04bf84b31d39c9136be2c68f5daa5abb41bf539bbd49b933d3a6e38c7e4f
+size 15920

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3eae0bb1eb1653205429ac3362479ee71cfed4107e6eb108ee6a0e67b8b8f1
+size 15920

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc18e524aa41bde44d3839835eadb6c8f0cd46cbaf8a8365ec09140041cfa1e
+size 15920

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2db5ad63fdf69177572f605ce4afecb085550b16f60084c021ee4cdbdd05ebc
+size 15920

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "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|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 16000,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right"
+}

trainer_state.json

@@ -0,0 +1,3631 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1000,
+  "global_step": 5102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 6.812536716461182,
+      "learning_rate": 9.70873786407767e-08,
+      "loss": 1.4108,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 6.775967597961426,
+      "learning_rate": 1.941747572815534e-07,
+      "loss": 1.4065,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 6.67765998840332,
+      "learning_rate": 2.9126213592233014e-07,
+      "loss": 1.4145,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 6.1705145835876465,
+      "learning_rate": 3.883495145631068e-07,
+      "loss": 1.3955,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.644610404968262,
+      "learning_rate": 4.854368932038835e-07,
+      "loss": 1.3986,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 6.067681789398193,
+      "learning_rate": 5.825242718446603e-07,
+      "loss": 1.3721,
+      "step": 60
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.449668884277344,
+      "learning_rate": 6.79611650485437e-07,
+      "loss": 1.3672,
+      "step": 70
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.1965107917785645,
+      "learning_rate": 7.766990291262136e-07,
+      "loss": 1.3229,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.0556440353393555,
+      "learning_rate": 8.737864077669904e-07,
+      "loss": 1.2846,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.58712911605835,
+      "learning_rate": 9.70873786407767e-07,
+      "loss": 1.2561,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.737099647521973,
+      "learning_rate": 1.0679611650485437e-06,
+      "loss": 1.2511,
+      "step": 110
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.916423320770264,
+      "learning_rate": 1.1650485436893206e-06,
+      "loss": 1.2378,
+      "step": 120
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.898449420928955,
+      "learning_rate": 1.2621359223300972e-06,
+      "loss": 1.2263,
+      "step": 130
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.9001641273498535,
+      "learning_rate": 1.359223300970874e-06,
+      "loss": 1.228,
+      "step": 140
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.939080238342285,
+      "learning_rate": 1.4563106796116506e-06,
+      "loss": 1.2006,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.023560047149658,
+      "learning_rate": 1.5533980582524272e-06,
+      "loss": 1.1934,
+      "step": 160
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.546477317810059,
+      "learning_rate": 1.650485436893204e-06,
+      "loss": 1.1905,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.045153617858887,
+      "learning_rate": 1.7475728155339808e-06,
+      "loss": 1.1642,
+      "step": 180
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.5985870361328125,
+      "learning_rate": 1.8446601941747574e-06,
+      "loss": 1.1674,
+      "step": 190
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.283823490142822,
+      "learning_rate": 1.941747572815534e-06,
+      "loss": 1.157,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.753105640411377,
+      "learning_rate": 2.0388349514563107e-06,
+      "loss": 1.164,
+      "step": 210
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.330531597137451,
+      "learning_rate": 2.1359223300970874e-06,
+      "loss": 1.169,
+      "step": 220
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.404067516326904,
+      "learning_rate": 2.2330097087378645e-06,
+      "loss": 1.1493,
+      "step": 230
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.143772602081299,
+      "learning_rate": 2.330097087378641e-06,
+      "loss": 1.1388,
+      "step": 240
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.965195417404175,
+      "learning_rate": 2.427184466019418e-06,
+      "loss": 1.147,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.0882039070129395,
+      "learning_rate": 2.5242718446601945e-06,
+      "loss": 1.1487,
+      "step": 260
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.03162956237793,
+      "learning_rate": 2.621359223300971e-06,
+      "loss": 1.136,
+      "step": 270
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.2308855056762695,
+      "learning_rate": 2.718446601941748e-06,
+      "loss": 1.1378,
+      "step": 280
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.1606221199035645,
+      "learning_rate": 2.8155339805825245e-06,
+      "loss": 1.1471,
+      "step": 290
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.03283166885376,
+      "learning_rate": 2.912621359223301e-06,
+      "loss": 1.1185,
+      "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.2199859619140625,
+      "learning_rate": 3.0097087378640778e-06,
+      "loss": 1.1432,
+      "step": 310
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.150729656219482,
+      "learning_rate": 3.1067961165048544e-06,
+      "loss": 1.1155,
+      "step": 320
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.9178309440612793,
+      "learning_rate": 3.2038834951456315e-06,
+      "loss": 1.1219,
+      "step": 330
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.3575663566589355,
+      "learning_rate": 3.300970873786408e-06,
+      "loss": 1.108,
+      "step": 340
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.251282215118408,
+      "learning_rate": 3.398058252427185e-06,
+      "loss": 1.1052,
+      "step": 350
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.297124862670898,
+      "learning_rate": 3.4951456310679615e-06,
+      "loss": 1.112,
+      "step": 360
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.4219465255737305,
+      "learning_rate": 3.592233009708738e-06,
+      "loss": 1.12,
+      "step": 370
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.0326948165893555,
+      "learning_rate": 3.689320388349515e-06,
+      "loss": 1.1286,
+      "step": 380
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.3179030418396,
+      "learning_rate": 3.7864077669902915e-06,
+      "loss": 1.1255,
+      "step": 390
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.20508337020874,
+      "learning_rate": 3.883495145631068e-06,
+      "loss": 1.1116,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.361403942108154,
+      "learning_rate": 3.980582524271845e-06,
+      "loss": 1.1061,
+      "step": 410
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.279186248779297,
+      "learning_rate": 4.0776699029126215e-06,
+      "loss": 1.1031,
+      "step": 420
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.163991928100586,
+      "learning_rate": 4.1747572815533986e-06,
+      "loss": 1.1097,
+      "step": 430
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.068342685699463,
+      "learning_rate": 4.271844660194175e-06,
+      "loss": 1.1048,
+      "step": 440
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.233316421508789,
+      "learning_rate": 4.368932038834952e-06,
+      "loss": 1.11,
+      "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.018556594848633,
+      "learning_rate": 4.466019417475729e-06,
+      "loss": 1.1,
+      "step": 460
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.257734298706055,
+      "learning_rate": 4.563106796116505e-06,
+      "loss": 1.1102,
+      "step": 470
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.20249605178833,
+      "learning_rate": 4.660194174757282e-06,
+      "loss": 1.0938,
+      "step": 480
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.196409225463867,
+      "learning_rate": 4.7572815533980585e-06,
+      "loss": 1.1153,
+      "step": 490
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.7823269367218018,
+      "learning_rate": 4.854368932038836e-06,
+      "loss": 1.105,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.8932242393493652,
+      "learning_rate": 4.951456310679612e-06,
+      "loss": 1.0977,
+      "step": 510
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.169296741485596,
+      "learning_rate": 5.048543689320389e-06,
+      "loss": 1.1022,
+      "step": 520
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.110784530639648,
+      "learning_rate": 5.145631067961165e-06,
+      "loss": 1.0954,
+      "step": 530
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.476339340209961,
+      "learning_rate": 5.242718446601942e-06,
+      "loss": 1.104,
+      "step": 540
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.7383415699005127,
+      "learning_rate": 5.3398058252427185e-06,
+      "loss": 1.106,
+      "step": 550
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.040097236633301,
+      "learning_rate": 5.436893203883496e-06,
+      "loss": 1.1006,
+      "step": 560
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.430188179016113,
+      "learning_rate": 5.533980582524272e-06,
+      "loss": 1.1087,
+      "step": 570
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.724983215332031,
+      "learning_rate": 5.631067961165049e-06,
+      "loss": 1.1004,
+      "step": 580
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.040498733520508,
+      "learning_rate": 5.728155339805825e-06,
+      "loss": 1.0944,
+      "step": 590
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.504246234893799,
+      "learning_rate": 5.825242718446602e-06,
+      "loss": 1.0915,
+      "step": 600
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.28185510635376,
+      "learning_rate": 5.9223300970873785e-06,
+      "loss": 1.0951,
+      "step": 610
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.7988641262054443,
+      "learning_rate": 6.0194174757281556e-06,
+      "loss": 1.1052,
+      "step": 620
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.40338134765625,
+      "learning_rate": 6.116504854368932e-06,
+      "loss": 1.0931,
+      "step": 630
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.3256659507751465,
+      "learning_rate": 6.213592233009709e-06,
+      "loss": 1.0863,
+      "step": 640
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.146902561187744,
+      "learning_rate": 6.310679611650487e-06,
+      "loss": 1.0916,
+      "step": 650
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.871020317077637,
+      "learning_rate": 6.407766990291263e-06,
+      "loss": 1.0853,
+      "step": 660
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.6339454650878906,
+      "learning_rate": 6.50485436893204e-06,
+      "loss": 1.0907,
+      "step": 670
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.507898330688477,
+      "learning_rate": 6.601941747572816e-06,
+      "loss": 1.1049,
+      "step": 680
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.15292501449585,
+      "learning_rate": 6.6990291262135935e-06,
+      "loss": 1.0928,
+      "step": 690
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.081875324249268,
+      "learning_rate": 6.79611650485437e-06,
+      "loss": 1.1104,
+      "step": 700
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.9496753215789795,
+      "learning_rate": 6.893203883495147e-06,
+      "loss": 1.0916,
+      "step": 710
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.676784992218018,
+      "learning_rate": 6.990291262135923e-06,
+      "loss": 1.087,
+      "step": 720
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.889897584915161,
+      "learning_rate": 7.0873786407767e-06,
+      "loss": 1.0889,
+      "step": 730
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.654224157333374,
+      "learning_rate": 7.184466019417476e-06,
+      "loss": 1.0929,
+      "step": 740
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.457578182220459,
+      "learning_rate": 7.2815533980582534e-06,
+      "loss": 1.0855,
+      "step": 750
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.403715133666992,
+      "learning_rate": 7.37864077669903e-06,
+      "loss": 1.0793,
+      "step": 760
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.498962879180908,
+      "learning_rate": 7.475728155339807e-06,
+      "loss": 1.0946,
+      "step": 770
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.233016014099121,
+      "learning_rate": 7.572815533980583e-06,
+      "loss": 1.0753,
+      "step": 780
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.361231327056885,
+      "learning_rate": 7.66990291262136e-06,
+      "loss": 1.0865,
+      "step": 790
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.116058349609375,
+      "learning_rate": 7.766990291262136e-06,
+      "loss": 1.0874,
+      "step": 800
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.87738037109375,
+      "learning_rate": 7.864077669902913e-06,
+      "loss": 1.0897,
+      "step": 810
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.444067478179932,
+      "learning_rate": 7.96116504854369e-06,
+      "loss": 1.0926,
+      "step": 820
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.9490249156951904,
+      "learning_rate": 8.058252427184466e-06,
+      "loss": 1.0678,
+      "step": 830
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.674923896789551,
+      "learning_rate": 8.155339805825243e-06,
+      "loss": 1.0923,
+      "step": 840
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.707766056060791,
+      "learning_rate": 8.25242718446602e-06,
+      "loss": 1.0874,
+      "step": 850
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.693995475769043,
+      "learning_rate": 8.349514563106797e-06,
+      "loss": 1.0558,
+      "step": 860
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.561864376068115,
+      "learning_rate": 8.446601941747573e-06,
+      "loss": 1.0961,
+      "step": 870
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.7990922927856445,
+      "learning_rate": 8.54368932038835e-06,
+      "loss": 1.0877,
+      "step": 880
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 5.014951705932617,
+      "learning_rate": 8.640776699029127e-06,
+      "loss": 1.0866,
+      "step": 890
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.007348537445068,
+      "learning_rate": 8.737864077669904e-06,
+      "loss": 1.0795,
+      "step": 900
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.876419544219971,
+      "learning_rate": 8.834951456310681e-06,
+      "loss": 1.0826,
+      "step": 910
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.8001556396484375,
+      "learning_rate": 8.932038834951458e-06,
+      "loss": 1.0828,
+      "step": 920
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.761294364929199,
+      "learning_rate": 9.029126213592233e-06,
+      "loss": 1.0897,
+      "step": 930
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.832348346710205,
+      "learning_rate": 9.12621359223301e-06,
+      "loss": 1.0826,
+      "step": 940
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 5.325027942657471,
+      "learning_rate": 9.223300970873788e-06,
+      "loss": 1.0705,
+      "step": 950
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.859924554824829,
+      "learning_rate": 9.320388349514565e-06,
+      "loss": 1.0691,
+      "step": 960
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.8470637798309326,
+      "learning_rate": 9.41747572815534e-06,
+      "loss": 1.0808,
+      "step": 970
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 4.887052536010742,
+      "learning_rate": 9.514563106796117e-06,
+      "loss": 1.0688,
+      "step": 980
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.891918897628784,
+      "learning_rate": 9.611650485436894e-06,
+      "loss": 1.0748,
+      "step": 990
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.252170562744141,
+      "learning_rate": 9.708737864077671e-06,
+      "loss": 1.0889,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.0763322114944458,
+      "eval_runtime": 12.4536,
+      "eval_samples_per_second": 52.515,
+      "eval_steps_per_second": 6.584,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.76177453994751,
+      "learning_rate": 9.805825242718447e-06,
+      "loss": 1.0925,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.820517063140869,
+      "learning_rate": 9.902912621359224e-06,
+      "loss": 1.0879,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.241539478302002,
+      "learning_rate": 1e-05,
+      "loss": 1.0688,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.468598365783691,
+      "learning_rate": 9.999971286914108e-06,
+      "loss": 1.0782,
+      "step": 1040
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.580018043518066,
+      "learning_rate": 9.999885147986207e-06,
+      "loss": 1.0793,
+      "step": 1050
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.351871490478516,
+      "learning_rate": 9.999741584205621e-06,
+      "loss": 1.0746,
+      "step": 1060
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.939090251922607,
+      "learning_rate": 9.999540597221217e-06,
+      "loss": 1.0814,
+      "step": 1070
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.497158050537109,
+      "learning_rate": 9.999282189341374e-06,
+      "loss": 1.076,
+      "step": 1080
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.999101161956787,
+      "learning_rate": 9.998966363533972e-06,
+      "loss": 1.0826,
+      "step": 1090
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.041301727294922,
+      "learning_rate": 9.99859312342634e-06,
+      "loss": 1.0675,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.890156269073486,
+      "learning_rate": 9.998162473305229e-06,
+      "loss": 1.0724,
+      "step": 1110
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.730093955993652,
+      "learning_rate": 9.997674418116759e-06,
+      "loss": 1.0679,
+      "step": 1120
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.929831504821777,
+      "learning_rate": 9.997128963466355e-06,
+      "loss": 1.064,
+      "step": 1130
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.288021087646484,
+      "learning_rate": 9.996526115618694e-06,
+      "loss": 1.0895,
+      "step": 1140
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.647055149078369,
+      "learning_rate": 9.995865881497621e-06,
+      "loss": 1.0768,
+      "step": 1150
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 5.861464977264404,
+      "learning_rate": 9.995148268686086e-06,
+      "loss": 1.073,
+      "step": 1160
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 5.072396278381348,
+      "learning_rate": 9.994373285426034e-06,
+      "loss": 1.0679,
+      "step": 1170
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.59302282333374,
+      "learning_rate": 9.993540940618334e-06,
+      "loss": 1.0999,
+      "step": 1180
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.47246789932251,
+      "learning_rate": 9.992651243822658e-06,
+      "loss": 1.0797,
+      "step": 1190
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.917146682739258,
+      "learning_rate": 9.991704205257383e-06,
+      "loss": 1.0786,
+      "step": 1200
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.097021102905273,
+      "learning_rate": 9.99069983579947e-06,
+      "loss": 1.0709,
+      "step": 1210
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.385958671569824,
+      "learning_rate": 9.989638146984337e-06,
+      "loss": 1.0878,
+      "step": 1220
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.534526824951172,
+      "learning_rate": 9.988519151005728e-06,
+      "loss": 1.0753,
+      "step": 1230
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.479306697845459,
+      "learning_rate": 9.987342860715575e-06,
+      "loss": 1.0638,
+      "step": 1240
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.557966232299805,
+      "learning_rate": 9.986109289623848e-06,
+      "loss": 1.0841,
+      "step": 1250
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.882152080535889,
+      "learning_rate": 9.984818451898399e-06,
+      "loss": 1.0678,
+      "step": 1260
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.506185054779053,
+      "learning_rate": 9.983470362364803e-06,
+      "loss": 1.0766,
+      "step": 1270
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.027829170227051,
+      "learning_rate": 9.982065036506183e-06,
+      "loss": 1.0825,
+      "step": 1280
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.385190010070801,
+      "learning_rate": 9.980602490463037e-06,
+      "loss": 1.0709,
+      "step": 1290
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 6.701911449432373,
+      "learning_rate": 9.979082741033047e-06,
+      "loss": 1.0813,
+      "step": 1300
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.571600437164307,
+      "learning_rate": 9.977505805670895e-06,
+      "loss": 1.0678,
+      "step": 1310
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.041151523590088,
+      "learning_rate": 9.97587170248805e-06,
+      "loss": 1.08,
+      "step": 1320
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.1545729637146,
+      "learning_rate": 9.97418045025257e-06,
+      "loss": 1.071,
+      "step": 1330
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.163790702819824,
+      "learning_rate": 9.972432068388885e-06,
+      "loss": 1.068,
+      "step": 1340
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.824156284332275,
+      "learning_rate": 9.97062657697757e-06,
+      "loss": 1.0718,
+      "step": 1350
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 6.520030975341797,
+      "learning_rate": 9.968763996755115e-06,
+      "loss": 1.0779,
+      "step": 1360
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 4.418417453765869,
+      "learning_rate": 9.966844349113695e-06,
+      "loss": 1.0677,
+      "step": 1370
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 4.918398380279541,
+      "learning_rate": 9.96486765610091e-06,
+      "loss": 1.0942,
+      "step": 1380
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 5.05225944519043,
+      "learning_rate": 9.96283394041954e-06,
+      "loss": 1.0852,
+      "step": 1390
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 4.492018699645996,
+      "learning_rate": 9.96074322542729e-06,
+      "loss": 1.0728,
+      "step": 1400
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.9885711669921875,
+      "learning_rate": 9.958595535136511e-06,
+      "loss": 1.0618,
+      "step": 1410
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.547979831695557,
+      "learning_rate": 9.95639089421393e-06,
+      "loss": 1.0753,
+      "step": 1420
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.2231621742248535,
+      "learning_rate": 9.954129327980362e-06,
+      "loss": 1.0573,
+      "step": 1430
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.681105613708496,
+      "learning_rate": 9.951810862410426e-06,
+      "loss": 1.0833,
+      "step": 1440
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.339748382568359,
+      "learning_rate": 9.949435524132245e-06,
+      "loss": 1.0712,
+      "step": 1450
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.844823837280273,
+      "learning_rate": 9.947003340427134e-06,
+      "loss": 1.0803,
+      "step": 1460
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 3.774728536605835,
+      "learning_rate": 9.944514339229292e-06,
+      "loss": 1.0787,
+      "step": 1470
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.437483310699463,
+      "learning_rate": 9.941968549125481e-06,
+      "loss": 1.0757,
+      "step": 1480
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 5.675827503204346,
+      "learning_rate": 9.9393659993547e-06,
+      "loss": 1.0635,
+      "step": 1490
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 5.193900108337402,
+      "learning_rate": 9.936706719807839e-06,
+      "loss": 1.0527,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.871400833129883,
+      "learning_rate": 9.93399074102735e-06,
+      "loss": 1.0683,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.098533630371094,
+      "learning_rate": 9.931218094206882e-06,
+      "loss": 1.0704,
+      "step": 1520
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.03292989730835,
+      "learning_rate": 9.928388811190938e-06,
+      "loss": 1.0839,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.196811199188232,
+      "learning_rate": 9.925502924474495e-06,
+      "loss": 1.0749,
+      "step": 1540
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.939242362976074,
+      "learning_rate": 9.922560467202638e-06,
+      "loss": 1.0761,
+      "step": 1550
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.359401702880859,
+      "learning_rate": 9.919561473170178e-06,
+      "loss": 1.0625,
+      "step": 1560
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.799266338348389,
+      "learning_rate": 9.916505976821262e-06,
+      "loss": 1.0691,
+      "step": 1570
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 4.341587543487549,
+      "learning_rate": 9.913394013248987e-06,
+      "loss": 1.0737,
+      "step": 1580
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.106640815734863,
+      "learning_rate": 9.91022561819498e-06,
+      "loss": 1.0805,
+      "step": 1590
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 4.987344741821289,
+      "learning_rate": 9.907000828049001e-06,
+      "loss": 1.0569,
+      "step": 1600
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.510980606079102,
+      "learning_rate": 9.903719679848522e-06,
+      "loss": 1.078,
+      "step": 1610
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.564126968383789,
+      "learning_rate": 9.9003822112783e-06,
+      "loss": 1.0726,
+      "step": 1620
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.666530132293701,
+      "learning_rate": 9.89698846066994e-06,
+      "loss": 1.0635,
+      "step": 1630
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.472270488739014,
+      "learning_rate": 9.893538467001466e-06,
+      "loss": 1.0529,
+      "step": 1640
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.534265995025635,
+      "learning_rate": 9.890032269896862e-06,
+      "loss": 1.08,
+      "step": 1650
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.677114963531494,
+      "learning_rate": 9.886469909625624e-06,
+      "loss": 1.0719,
+      "step": 1660
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.84233283996582,
+      "learning_rate": 9.882851427102299e-06,
+      "loss": 1.0665,
+      "step": 1670
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.839110374450684,
+      "learning_rate": 9.879176863885997e-06,
+      "loss": 1.0635,
+      "step": 1680
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.322112560272217,
+      "learning_rate": 9.875446262179948e-06,
+      "loss": 1.0755,
+      "step": 1690
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.2779130935668945,
+      "learning_rate": 9.87165966483098e-06,
+      "loss": 1.0745,
+      "step": 1700
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.142566204071045,
+      "learning_rate": 9.867817115329055e-06,
+      "loss": 1.0725,
+      "step": 1710
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.487438678741455,
+      "learning_rate": 9.863918657806752e-06,
+      "loss": 1.0538,
+      "step": 1720
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.5258588790893555,
+      "learning_rate": 9.85996433703877e-06,
+      "loss": 1.0559,
+      "step": 1730
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.927529811859131,
+      "learning_rate": 9.855954198441411e-06,
+      "loss": 1.0661,
+      "step": 1740
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.9455795288085938,
+      "learning_rate": 9.851888288072053e-06,
+      "loss": 1.0769,
+      "step": 1750
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.094160556793213,
+      "learning_rate": 9.847766652628635e-06,
+      "loss": 1.0767,
+      "step": 1760
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.2093424797058105,
+      "learning_rate": 9.843589339449102e-06,
+      "loss": 1.0635,
+      "step": 1770
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.292007923126221,
+      "learning_rate": 9.839356396510875e-06,
+      "loss": 1.0593,
+      "step": 1780
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.241662502288818,
+      "learning_rate": 9.835067872430297e-06,
+      "loss": 1.0627,
+      "step": 1790
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.465583324432373,
+      "learning_rate": 9.830723816462071e-06,
+      "loss": 1.0551,
+      "step": 1800
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.395579814910889,
+      "learning_rate": 9.8263242784987e-06,
+      "loss": 1.0691,
+      "step": 1810
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.91081428527832,
+      "learning_rate": 9.821869309069907e-06,
+      "loss": 1.0632,
+      "step": 1820
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9647531509399414,
+      "learning_rate": 9.817358959342057e-06,
+      "loss": 1.0693,
+      "step": 1830
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.396968364715576,
+      "learning_rate": 9.81279328111758e-06,
+      "loss": 1.0869,
+      "step": 1840
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.095502853393555,
+      "learning_rate": 9.808172326834356e-06,
+      "loss": 1.0636,
+      "step": 1850
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.527934551239014,
+      "learning_rate": 9.80349614956513e-06,
+      "loss": 1.0679,
+      "step": 1860
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 5.237788200378418,
+      "learning_rate": 9.798764803016892e-06,
+      "loss": 1.05,
+      "step": 1870
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 4.45642614364624,
+      "learning_rate": 9.793978341530265e-06,
+      "loss": 1.0697,
+      "step": 1880
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.550489664077759,
+      "learning_rate": 9.789136820078884e-06,
+      "loss": 1.079,
+      "step": 1890
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.879551887512207,
+      "learning_rate": 9.784240294268756e-06,
+      "loss": 1.0649,
+      "step": 1900
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 4.333283424377441,
+      "learning_rate": 9.779288820337628e-06,
+      "loss": 1.0668,
+      "step": 1910
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.761474370956421,
+      "learning_rate": 9.774282455154338e-06,
+      "loss": 1.0738,
+      "step": 1920
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.7375967502593994,
+      "learning_rate": 9.769221256218165e-06,
+      "loss": 1.0574,
+      "step": 1930
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.852424144744873,
+      "learning_rate": 9.764105281658161e-06,
+      "loss": 1.0536,
+      "step": 1940
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.345045566558838,
+      "learning_rate": 9.758934590232495e-06,
+      "loss": 1.0898,
+      "step": 1950
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.355409622192383,
+      "learning_rate": 9.753709241327773e-06,
+      "loss": 1.0657,
+      "step": 1960
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.160512924194336,
+      "learning_rate": 9.748429294958345e-06,
+      "loss": 1.0699,
+      "step": 1970
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.259660243988037,
+      "learning_rate": 9.74309481176564e-06,
+      "loss": 1.0703,
+      "step": 1980
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.260087013244629,
+      "learning_rate": 9.737705853017442e-06,
+      "loss": 1.0816,
+      "step": 1990
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.026108264923096,
+      "learning_rate": 9.732262480607207e-06,
+      "loss": 1.0556,
+      "step": 2000
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.0583994388580322,
+      "eval_runtime": 12.5254,
+      "eval_samples_per_second": 52.214,
+      "eval_steps_per_second": 6.547,
+      "step": 2000
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.157490253448486,
+      "learning_rate": 9.726764757053343e-06,
+      "loss": 1.0735,
+      "step": 2010
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.293674468994141,
+      "learning_rate": 9.721212745498493e-06,
+      "loss": 1.0697,
+      "step": 2020
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.8046298027038574,
+      "learning_rate": 9.715606509708812e-06,
+      "loss": 1.0635,
+      "step": 2030
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.55698561668396,
+      "learning_rate": 9.709946114073231e-06,
+      "loss": 1.0685,
+      "step": 2040
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.9492263793945312,
+      "learning_rate": 9.704231623602721e-06,
+      "loss": 1.0692,
+      "step": 2050
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.995659351348877,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 1.069,
+      "step": 2060
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.452322483062744,
+      "learning_rate": 9.692640621306497e-06,
+      "loss": 1.0728,
+      "step": 2070
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.006470680236816,
+      "learning_rate": 9.686764242606164e-06,
+      "loss": 1.0616,
+      "step": 2080
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.041233539581299,
+      "learning_rate": 9.680834035320127e-06,
+      "loss": 1.0712,
+      "step": 2090
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 3.9690816402435303,
+      "learning_rate": 9.674850067558209e-06,
+      "loss": 1.0682,
+      "step": 2100
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.229337215423584,
+      "learning_rate": 9.66881240804768e-06,
+      "loss": 1.0734,
+      "step": 2110
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.3140339851379395,
+      "learning_rate": 9.662721126132473e-06,
+      "loss": 1.0665,
+      "step": 2120
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.23881721496582,
+      "learning_rate": 9.656576291772392e-06,
+      "loss": 1.0535,
+      "step": 2130
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.9377248287200928,
+      "learning_rate": 9.650377975542298e-06,
+      "loss": 1.068,
+      "step": 2140
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.9194915294647217,
+      "learning_rate": 9.644126248631306e-06,
+      "loss": 1.0803,
+      "step": 2150
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.5396149158477783,
+      "learning_rate": 9.637821182841965e-06,
+      "loss": 1.0574,
+      "step": 2160
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.14241361618042,
+      "learning_rate": 9.631462850589432e-06,
+      "loss": 1.0643,
+      "step": 2170
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.7068986892700195,
+      "learning_rate": 9.625051324900645e-06,
+      "loss": 1.0519,
+      "step": 2180
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.9636712074279785,
+      "learning_rate": 9.618586679413477e-06,
+      "loss": 1.054,
+      "step": 2190
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.6051032543182373,
+      "learning_rate": 9.612068988375898e-06,
+      "loss": 1.0534,
+      "step": 2200
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.969806671142578,
+      "learning_rate": 9.605498326645115e-06,
+      "loss": 1.0851,
+      "step": 2210
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.08690071105957,
+      "learning_rate": 9.598874769686721e-06,
+      "loss": 1.0645,
+      "step": 2220
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.7391505241394043,
+      "learning_rate": 9.592198393573816e-06,
+      "loss": 1.0693,
+      "step": 2230
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.053625583648682,
+      "learning_rate": 9.585469274986148e-06,
+      "loss": 1.0682,
+      "step": 2240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.923471212387085,
+      "learning_rate": 9.578687491209219e-06,
+      "loss": 1.0606,
+      "step": 2250
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.096630573272705,
+      "learning_rate": 9.571853120133406e-06,
+      "loss": 1.064,
+      "step": 2260
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.9412453174591064,
+      "learning_rate": 9.564966240253062e-06,
+      "loss": 1.0786,
+      "step": 2270
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.6600263118743896,
+      "learning_rate": 9.558026930665614e-06,
+      "loss": 1.0622,
+      "step": 2280
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.281722545623779,
+      "learning_rate": 9.551035271070665e-06,
+      "loss": 1.0542,
+      "step": 2290
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.6689794063568115,
+      "learning_rate": 9.543991341769057e-06,
+      "loss": 1.0496,
+      "step": 2300
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.148682594299316,
+      "learning_rate": 9.536895223661975e-06,
+      "loss": 1.0648,
+      "step": 2310
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.112921237945557,
+      "learning_rate": 9.529746998249994e-06,
+      "loss": 1.0632,
+      "step": 2320
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.144115447998047,
+      "learning_rate": 9.52254674763216e-06,
+      "loss": 1.0555,
+      "step": 2330
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.198709011077881,
+      "learning_rate": 9.515294554505039e-06,
+      "loss": 1.049,
+      "step": 2340
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.7727572917938232,
+      "learning_rate": 9.507990502161769e-06,
+      "loss": 1.0428,
+      "step": 2350
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.66112756729126,
+      "learning_rate": 9.500634674491099e-06,
+      "loss": 1.0666,
+      "step": 2360
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.313396453857422,
+      "learning_rate": 9.49322715597644e-06,
+      "loss": 1.0658,
+      "step": 2370
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.8979835510253906,
+      "learning_rate": 9.485768031694872e-06,
+      "loss": 1.0516,
+      "step": 2380
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 4.047280788421631,
+      "learning_rate": 9.478257387316189e-06,
+      "loss": 1.0708,
+      "step": 2390
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.9112637042999268,
+      "learning_rate": 9.470695309101903e-06,
+      "loss": 1.0576,
+      "step": 2400
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.9057672023773193,
+      "learning_rate": 9.463081883904251e-06,
+      "loss": 1.0653,
+      "step": 2410
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 4.1275105476379395,
+      "learning_rate": 9.455417199165209e-06,
+      "loss": 1.0454,
+      "step": 2420
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.834106922149658,
+      "learning_rate": 9.447701342915473e-06,
+      "loss": 1.0593,
+      "step": 2430
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.673773765563965,
+      "learning_rate": 9.439934403773468e-06,
+      "loss": 1.0543,
+      "step": 2440
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.011989593505859,
+      "learning_rate": 9.4321164709443e-06,
+      "loss": 1.0468,
+      "step": 2450
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.221887588500977,
+      "learning_rate": 9.42424763421877e-06,
+      "loss": 1.0699,
+      "step": 2460
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.603546142578125,
+      "learning_rate": 9.416327983972304e-06,
+      "loss": 1.0525,
+      "step": 2470
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.173734188079834,
+      "learning_rate": 9.408357611163945e-06,
+      "loss": 1.0678,
+      "step": 2480
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.5241010189056396,
+      "learning_rate": 9.400336607335294e-06,
+      "loss": 1.0536,
+      "step": 2490
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.8831429481506348,
+      "learning_rate": 9.392265064609455e-06,
+      "loss": 1.0367,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.8573215007781982,
+      "learning_rate": 9.384143075689992e-06,
+      "loss": 1.0474,
+      "step": 2510
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.8050475120544434,
+      "learning_rate": 9.375970733859848e-06,
+      "loss": 1.0508,
+      "step": 2520
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.164061546325684,
+      "learning_rate": 9.367748132980286e-06,
+      "loss": 1.0629,
+      "step": 2530
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.8858516216278076,
+      "learning_rate": 9.359475367489805e-06,
+      "loss": 1.0616,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.033576965332031,
+      "learning_rate": 9.351152532403054e-06,
+      "loss": 1.0687,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.06900691986084,
+      "learning_rate": 9.342779723309746e-06,
+      "loss": 1.0519,
+      "step": 2560
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.8570592403411865,
+      "learning_rate": 9.334357036373552e-06,
+      "loss": 1.0482,
+      "step": 2570
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 4.30549430847168,
+      "learning_rate": 9.32588456833101e-06,
+      "loss": 1.0714,
+      "step": 2580
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.6463634967803955,
+      "learning_rate": 9.317362416490396e-06,
+      "loss": 1.055,
+      "step": 2590
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 4.366295337677002,
+      "learning_rate": 9.308790678730627e-06,
+      "loss": 1.0502,
+      "step": 2600
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.8573434352874756,
+      "learning_rate": 9.300169453500117e-06,
+      "loss": 1.0597,
+      "step": 2610
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.8393239974975586,
+      "learning_rate": 9.291498839815658e-06,
+      "loss": 1.0553,
+      "step": 2620
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.246349334716797,
+      "learning_rate": 9.282778937261279e-06,
+      "loss": 1.0734,
+      "step": 2630
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.076491355895996,
+      "learning_rate": 9.274009845987106e-06,
+      "loss": 1.0643,
+      "step": 2640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.7121007442474365,
+      "learning_rate": 9.26519166670821e-06,
+      "loss": 1.0491,
+      "step": 2650
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.8223936557769775,
+      "learning_rate": 9.256324500703439e-06,
+      "loss": 1.0713,
+      "step": 2660
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.4132473468780518,
+      "learning_rate": 9.247408449814281e-06,
+      "loss": 1.0541,
+      "step": 2670
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 3.846742868423462,
+      "learning_rate": 9.238443616443666e-06,
+      "loss": 1.0573,
+      "step": 2680
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 4.1583123207092285,
+      "learning_rate": 9.229430103554808e-06,
+      "loss": 1.038,
+      "step": 2690
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 4.192993640899658,
+      "learning_rate": 9.22036801467001e-06,
+      "loss": 1.0645,
+      "step": 2700
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 4.137371063232422,
+      "learning_rate": 9.211257453869495e-06,
+      "loss": 1.058,
+      "step": 2710
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 4.091256618499756,
+      "learning_rate": 9.202098525790182e-06,
+      "loss": 1.0702,
+      "step": 2720
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.9540719985961914,
+      "learning_rate": 9.192891335624508e-06,
+      "loss": 1.0406,
+      "step": 2730
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.149806022644043,
+      "learning_rate": 9.183635989119211e-06,
+      "loss": 1.0558,
+      "step": 2740
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.950911045074463,
+      "learning_rate": 9.174332592574115e-06,
+      "loss": 1.0446,
+      "step": 2750
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.7937111854553223,
+      "learning_rate": 9.164981252840908e-06,
+      "loss": 1.0608,
+      "step": 2760
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.06609582901001,
+      "learning_rate": 9.155582077321918e-06,
+      "loss": 1.0653,
+      "step": 2770
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.201600074768066,
+      "learning_rate": 9.146135173968881e-06,
+      "loss": 1.0651,
+      "step": 2780
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.8813118934631348,
+      "learning_rate": 9.136640651281694e-06,
+      "loss": 1.0567,
+      "step": 2790
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.4754064083099365,
+      "learning_rate": 9.127098618307177e-06,
+      "loss": 1.0632,
+      "step": 2800
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.5580170154571533,
+      "learning_rate": 9.117509184637814e-06,
+      "loss": 1.057,
+      "step": 2810
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.7533814907073975,
+      "learning_rate": 9.107872460410496e-06,
+      "loss": 1.0398,
+      "step": 2820
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 4.086584091186523,
+      "learning_rate": 9.098188556305262e-06,
+      "loss": 1.0633,
+      "step": 2830
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.2910237312316895,
+      "learning_rate": 9.088457583544022e-06,
+      "loss": 1.0334,
+      "step": 2840
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.132745742797852,
+      "learning_rate": 9.078679653889273e-06,
+      "loss": 1.0595,
+      "step": 2850
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.9243948459625244,
+      "learning_rate": 9.068854879642833e-06,
+      "loss": 1.0641,
+      "step": 2860
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.943058490753174,
+      "learning_rate": 9.058983373644532e-06,
+      "loss": 1.0493,
+      "step": 2870
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.724886417388916,
+      "learning_rate": 9.049065249270936e-06,
+      "loss": 1.0374,
+      "step": 2880
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.8636670112609863,
+      "learning_rate": 9.039100620434025e-06,
+      "loss": 1.0634,
+      "step": 2890
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.841193675994873,
+      "learning_rate": 9.029089601579895e-06,
+      "loss": 1.0433,
+      "step": 2900
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.6147212982177734,
+      "learning_rate": 9.019032307687446e-06,
+      "loss": 1.0416,
+      "step": 2910
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.8550570011138916,
+      "learning_rate": 9.008928854267054e-06,
+      "loss": 1.064,
+      "step": 2920
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.5188698768615723,
+      "learning_rate": 8.99877935735925e-06,
+      "loss": 1.0472,
+      "step": 2930
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.188703536987305,
+      "learning_rate": 8.988583933533384e-06,
+      "loss": 1.0688,
+      "step": 2940
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.8695075511932373,
+      "learning_rate": 8.978342699886289e-06,
+      "loss": 1.0391,
+      "step": 2950
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.8634023666381836,
+      "learning_rate": 8.968055774040932e-06,
+      "loss": 1.0422,
+      "step": 2960
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.071281909942627,
+      "learning_rate": 8.95772327414507e-06,
+      "loss": 1.0442,
+      "step": 2970
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.14091157913208,
+      "learning_rate": 8.947345318869883e-06,
+      "loss": 1.0541,
+      "step": 2980
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.287483215332031,
+      "learning_rate": 8.936922027408618e-06,
+      "loss": 1.0391,
+      "step": 2990
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.207295894622803,
+      "learning_rate": 8.926453519475225e-06,
+      "loss": 1.0455,
+      "step": 3000
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.046447992324829,
+      "eval_runtime": 12.4637,
+      "eval_samples_per_second": 52.472,
+      "eval_steps_per_second": 6.579,
+      "step": 3000
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.189324855804443,
+      "learning_rate": 8.91593991530297e-06,
+      "loss": 1.0559,
+      "step": 3010
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.109393119812012,
+      "learning_rate": 8.905381335643056e-06,
+      "loss": 1.0524,
+      "step": 3020
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.9047772884368896,
+      "learning_rate": 8.89477790176325e-06,
+      "loss": 1.059,
+      "step": 3030
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.3157196044921875,
+      "learning_rate": 8.884129735446471e-06,
+      "loss": 1.0494,
+      "step": 3040
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.147355079650879,
+      "learning_rate": 8.873436958989409e-06,
+      "loss": 1.0517,
+      "step": 3050
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.453030586242676,
+      "learning_rate": 8.862699695201107e-06,
+      "loss": 1.0538,
+      "step": 3060
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.24041223526001,
+      "learning_rate": 8.851918067401552e-06,
+      "loss": 1.0425,
+      "step": 3070
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.6763038635253906,
+      "learning_rate": 8.84109219942027e-06,
+      "loss": 1.0558,
+      "step": 3080
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.736586093902588,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 1.0589,
+      "step": 3090
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.622150182723999,
+      "learning_rate": 8.819308240769726e-06,
+      "loss": 1.0428,
+      "step": 3100
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.96793794631958,
+      "learning_rate": 8.808350400294332e-06,
+      "loss": 1.0245,
+      "step": 3110
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.7367801666259766,
+      "learning_rate": 8.797348820022079e-06,
+      "loss": 1.0551,
+      "step": 3120
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.7123868465423584,
+      "learning_rate": 8.78630362630869e-06,
+      "loss": 1.0381,
+      "step": 3130
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.651548385620117,
+      "learning_rate": 8.775214946010806e-06,
+      "loss": 1.0428,
+      "step": 3140
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.124800205230713,
+      "learning_rate": 8.764082906484518e-06,
+      "loss": 1.0638,
+      "step": 3150
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.599874496459961,
+      "learning_rate": 8.752907635583911e-06,
+      "loss": 1.0441,
+      "step": 3160
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.769707441329956,
+      "learning_rate": 8.74168926165959e-06,
+      "loss": 1.0526,
+      "step": 3170
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.018752098083496,
+      "learning_rate": 8.730427913557205e-06,
+      "loss": 1.0672,
+      "step": 3180
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.963313341140747,
+      "learning_rate": 8.71912372061598e-06,
+      "loss": 1.0606,
+      "step": 3190
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 4.098948001861572,
+      "learning_rate": 8.707776812667224e-06,
+      "loss": 1.0383,
+      "step": 3200
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.441176652908325,
+      "learning_rate": 8.696387320032827e-06,
+      "loss": 1.0629,
+      "step": 3210
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.6925058364868164,
+      "learning_rate": 8.684955373523787e-06,
+      "loss": 1.0555,
+      "step": 3220
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.5602104663848877,
+      "learning_rate": 8.673481104438685e-06,
+      "loss": 1.0421,
+      "step": 3230
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.177275657653809,
+      "learning_rate": 8.661964644562194e-06,
+      "loss": 1.0504,
+      "step": 3240
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.9053499698638916,
+      "learning_rate": 8.650406126163553e-06,
+      "loss": 1.0508,
+      "step": 3250
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.4393839836120605,
+      "learning_rate": 8.638805681995052e-06,
+      "loss": 1.0375,
+      "step": 3260
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.890512228012085,
+      "learning_rate": 8.627163445290514e-06,
+      "loss": 1.0453,
+      "step": 3270
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.122755527496338,
+      "learning_rate": 8.615479549763756e-06,
+      "loss": 1.0427,
+      "step": 3280
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.3840408325195312,
+      "learning_rate": 8.603754129607055e-06,
+      "loss": 1.0454,
+      "step": 3290
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.196717262268066,
+      "learning_rate": 8.591987319489612e-06,
+      "loss": 1.0594,
+      "step": 3300
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.9698941707611084,
+      "learning_rate": 8.580179254555997e-06,
+      "loss": 1.0431,
+      "step": 3310
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.883592128753662,
+      "learning_rate": 8.5683300704246e-06,
+      "loss": 1.0257,
+      "step": 3320
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.783325672149658,
+      "learning_rate": 8.556439903186082e-06,
+      "loss": 1.0445,
+      "step": 3330
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.042956352233887,
+      "learning_rate": 8.544508889401799e-06,
+      "loss": 1.0507,
+      "step": 3340
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.7064452171325684,
+      "learning_rate": 8.53253716610224e-06,
+      "loss": 1.0604,
+      "step": 3350
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.835759401321411,
+      "learning_rate": 8.520524870785453e-06,
+      "loss": 1.0526,
+      "step": 3360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.9541969299316406,
+      "learning_rate": 8.508472141415468e-06,
+      "loss": 1.0365,
+      "step": 3370
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.182323932647705,
+      "learning_rate": 8.4963791164207e-06,
+      "loss": 1.0292,
+      "step": 3380
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.205846309661865,
+      "learning_rate": 8.484245934692379e-06,
+      "loss": 1.0236,
+      "step": 3390
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.628838300704956,
+      "learning_rate": 8.472072735582942e-06,
+      "loss": 1.0457,
+      "step": 3400
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.7961418628692627,
+      "learning_rate": 8.45985965890443e-06,
+      "loss": 1.0491,
+      "step": 3410
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.6906325817108154,
+      "learning_rate": 8.447606844926895e-06,
+      "loss": 1.0315,
+      "step": 3420
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 4.307608604431152,
+      "learning_rate": 8.435314434376773e-06,
+      "loss": 1.0498,
+      "step": 3430
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.8979074954986572,
+      "learning_rate": 8.422982568435283e-06,
+      "loss": 1.0637,
+      "step": 3440
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.03852653503418,
+      "learning_rate": 8.410611388736793e-06,
+      "loss": 1.06,
+      "step": 3450
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.238548994064331,
+      "learning_rate": 8.398201037367202e-06,
+      "loss": 1.0385,
+      "step": 3460
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.223562240600586,
+      "learning_rate": 8.385751656862305e-06,
+      "loss": 1.039,
+      "step": 3470
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.7112879753112793,
+      "learning_rate": 8.373263390206155e-06,
+      "loss": 1.0412,
+      "step": 3480
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.801882743835449,
+      "learning_rate": 8.36073638082942e-06,
+      "loss": 1.0455,
+      "step": 3490
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 4.619334697723389,
+      "learning_rate": 8.348170772607737e-06,
+      "loss": 1.054,
+      "step": 3500
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 3.967297077178955,
+      "learning_rate": 8.335566709860065e-06,
+      "loss": 1.0369,
+      "step": 3510
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 3.9955484867095947,
+      "learning_rate": 8.322924337347016e-06,
+      "loss": 1.0631,
+      "step": 3520
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 3.6488661766052246,
+      "learning_rate": 8.3102438002692e-06,
+      "loss": 1.0427,
+      "step": 3530
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 4.1679534912109375,
+      "learning_rate": 8.29752524426556e-06,
+      "loss": 1.0396,
+      "step": 3540
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.7516090869903564,
+      "learning_rate": 8.284768815411693e-06,
+      "loss": 1.0457,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.902599811553955,
+      "learning_rate": 8.27197466021817e-06,
+      "loss": 1.0354,
+      "step": 3560
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.828345775604248,
+      "learning_rate": 8.259142925628862e-06,
+      "loss": 1.0359,
+      "step": 3570
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.114760875701904,
+      "learning_rate": 8.246273759019252e-06,
+      "loss": 1.0346,
+      "step": 3580
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.289566993713379,
+      "learning_rate": 8.233367308194735e-06,
+      "loss": 1.038,
+      "step": 3590
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.713040828704834,
+      "learning_rate": 8.220423721388918e-06,
+      "loss": 1.0442,
+      "step": 3600
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 4.1226630210876465,
+      "learning_rate": 8.20744314726193e-06,
+      "loss": 1.0502,
+      "step": 3610
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.980717182159424,
+      "learning_rate": 8.19442573489871e-06,
+      "loss": 1.0398,
+      "step": 3620
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.998352527618408,
+      "learning_rate": 8.181371633807289e-06,
+      "loss": 1.0558,
+      "step": 3630
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 4.392803192138672,
+      "learning_rate": 8.168280993917078e-06,
+      "loss": 1.0508,
+      "step": 3640
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.483020305633545,
+      "learning_rate": 8.155153965577139e-06,
+      "loss": 1.028,
+      "step": 3650
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.593369960784912,
+      "learning_rate": 8.141990699554476e-06,
+      "loss": 1.0591,
+      "step": 3660
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.9365193843841553,
+      "learning_rate": 8.12879134703228e-06,
+      "loss": 1.0496,
+      "step": 3670
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.063488960266113,
+      "learning_rate": 8.115556059608208e-06,
+      "loss": 1.0554,
+      "step": 3680
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.916815996170044,
+      "learning_rate": 8.102284989292639e-06,
+      "loss": 1.0382,
+      "step": 3690
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.987957000732422,
+      "learning_rate": 8.088978288506923e-06,
+      "loss": 1.0668,
+      "step": 3700
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 4.158136367797852,
+      "learning_rate": 8.075636110081643e-06,
+      "loss": 1.0346,
+      "step": 3710
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.6939709186553955,
+      "learning_rate": 8.062258607254841e-06,
+      "loss": 1.0401,
+      "step": 3720
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 4.190096378326416,
+      "learning_rate": 8.048845933670274e-06,
+      "loss": 1.0285,
+      "step": 3730
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.59887957572937,
+      "learning_rate": 8.035398243375636e-06,
+      "loss": 1.036,
+      "step": 3740
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.9749696254730225,
+      "learning_rate": 8.021915690820808e-06,
+      "loss": 1.0555,
+      "step": 3750
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.9689297676086426,
+      "learning_rate": 8.008398430856064e-06,
+      "loss": 1.038,
+      "step": 3760
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.9846508502960205,
+      "learning_rate": 7.994846618730301e-06,
+      "loss": 1.0523,
+      "step": 3770
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.488775730133057,
+      "learning_rate": 7.981260410089258e-06,
+      "loss": 1.0244,
+      "step": 3780
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.135215759277344,
+      "learning_rate": 7.967639960973727e-06,
+      "loss": 1.0653,
+      "step": 3790
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.3885884284973145,
+      "learning_rate": 7.953985427817757e-06,
+      "loss": 1.0531,
+      "step": 3800
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.9444169998168945,
+      "learning_rate": 7.94029696744686e-06,
+      "loss": 1.04,
+      "step": 3810
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.401015758514404,
+      "learning_rate": 7.92657473707621e-06,
+      "loss": 1.0498,
+      "step": 3820
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.35683012008667,
+      "learning_rate": 7.912818894308845e-06,
+      "loss": 1.0288,
+      "step": 3830
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.314106464385986,
+      "learning_rate": 7.899029597133836e-06,
+      "loss": 1.0413,
+      "step": 3840
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.9266910552978516,
+      "learning_rate": 7.885207003924498e-06,
+      "loss": 1.0319,
+      "step": 3850
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.997091054916382,
+      "learning_rate": 7.87135127343655e-06,
+      "loss": 1.0324,
+      "step": 3860
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.264638423919678,
+      "learning_rate": 7.857462564806306e-06,
+      "loss": 1.0328,
+      "step": 3870
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.032344818115234,
+      "learning_rate": 7.84354103754884e-06,
+      "loss": 1.0415,
+      "step": 3880
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.569589614868164,
+      "learning_rate": 7.82958685155615e-06,
+      "loss": 1.0566,
+      "step": 3890
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.405215740203857,
+      "learning_rate": 7.815600167095338e-06,
+      "loss": 1.0508,
+      "step": 3900
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.7878050804138184,
+      "learning_rate": 7.801581144806752e-06,
+      "loss": 1.0365,
+      "step": 3910
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.773585319519043,
+      "learning_rate": 7.787529945702145e-06,
+      "loss": 1.0366,
+      "step": 3920
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 4.027467727661133,
+      "learning_rate": 7.773446731162835e-06,
+      "loss": 1.0285,
+      "step": 3930
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.831883430480957,
+      "learning_rate": 7.759331662937841e-06,
+      "loss": 1.0342,
+      "step": 3940
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 4.330446243286133,
+      "learning_rate": 7.745184903142029e-06,
+      "loss": 1.0398,
+      "step": 3950
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.389279842376709,
+      "learning_rate": 7.731006614254252e-06,
+      "loss": 1.017,
+      "step": 3960
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.518781661987305,
+      "learning_rate": 7.716796959115479e-06,
+      "loss": 1.0465,
+      "step": 3970
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.294104099273682,
+      "learning_rate": 7.70255610092693e-06,
+      "loss": 1.0328,
+      "step": 3980
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.937368154525757,
+      "learning_rate": 7.688284203248197e-06,
+      "loss": 1.0496,
+      "step": 3990
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.222658157348633,
+      "learning_rate": 7.673981429995372e-06,
+      "loss": 1.032,
+      "step": 4000
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 1.0327889919281006,
+      "eval_runtime": 12.4602,
+      "eval_samples_per_second": 52.487,
+      "eval_steps_per_second": 6.581,
+      "step": 4000
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 3.9882421493530273,
+      "learning_rate": 7.659647945439157e-06,
+      "loss": 1.0262,
+      "step": 4010
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.082265377044678,
+      "learning_rate": 7.645283914202981e-06,
+      "loss": 1.03,
+      "step": 4020
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.47793436050415,
+      "learning_rate": 7.63088950126111e-06,
+      "loss": 1.0402,
+      "step": 4030
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.539676189422607,
+      "learning_rate": 7.616464871936748e-06,
+      "loss": 1.0441,
+      "step": 4040
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.070407867431641,
+      "learning_rate": 7.602010191900147e-06,
+      "loss": 1.0298,
+      "step": 4050
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.478466510772705,
+      "learning_rate": 7.587525627166691e-06,
+      "loss": 1.0298,
+      "step": 4060
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.1451005935668945,
+      "learning_rate": 7.573011344095002e-06,
+      "loss": 1.0411,
+      "step": 4070
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.8588812351226807,
+      "learning_rate": 7.558467509385023e-06,
+      "loss": 1.0312,
+      "step": 4080
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.136762619018555,
+      "learning_rate": 7.5438942900761035e-06,
+      "loss": 1.0436,
+      "step": 4090
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.054186820983887,
+      "learning_rate": 7.529291853545082e-06,
+      "loss": 1.0421,
+      "step": 4100
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 4.862720012664795,
+      "learning_rate": 7.514660367504368e-06,
+      "loss": 1.0355,
+      "step": 4110
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 38.17692565917969,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.045,
+      "step": 4120
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 4.037071228027344,
+      "learning_rate": 7.485310919409742e-06,
+      "loss": 1.0382,
+      "step": 4130
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 4.044297218322754,
+      "learning_rate": 7.470593294441124e-06,
+      "loss": 1.0354,
+      "step": 4140
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 3.8578081130981445,
+      "learning_rate": 7.455847294129519e-06,
+      "loss": 1.0475,
+      "step": 4150
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.1042094230651855,
+      "learning_rate": 7.4410730878361936e-06,
+      "loss": 1.0302,
+      "step": 4160
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.391599178314209,
+      "learning_rate": 7.426270845246373e-06,
+      "loss": 1.0317,
+      "step": 4170
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.354910373687744,
+      "learning_rate": 7.411440736367281e-06,
+      "loss": 1.0291,
+      "step": 4180
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.061986923217773,
+      "learning_rate": 7.396582931526194e-06,
+      "loss": 1.0434,
+      "step": 4190
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.731538772583008,
+      "learning_rate": 7.381697601368481e-06,
+      "loss": 1.0472,
+      "step": 4200
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.0257887840271,
+      "learning_rate": 7.36678491685565e-06,
+      "loss": 1.0399,
+      "step": 4210
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.179793834686279,
+      "learning_rate": 7.351845049263374e-06,
+      "loss": 1.0518,
+      "step": 4220
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.212937355041504,
+      "learning_rate": 7.3368781701795365e-06,
+      "loss": 1.0381,
+      "step": 4230
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.426169395446777,
+      "learning_rate": 7.321884451502252e-06,
+      "loss": 1.0338,
+      "step": 4240
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.190229415893555,
+      "learning_rate": 7.30686406543789e-06,
+      "loss": 1.0482,
+      "step": 4250
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.897801160812378,
+      "learning_rate": 7.291817184499107e-06,
+      "loss": 1.0331,
+      "step": 4260
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.616969585418701,
+      "learning_rate": 7.276743981502856e-06,
+      "loss": 1.0515,
+      "step": 4270
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.8713490962982178,
+      "learning_rate": 7.2616446295684075e-06,
+      "loss": 1.0222,
+      "step": 4280
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.93888783454895,
+      "learning_rate": 7.246519302115355e-06,
+      "loss": 1.0355,
+      "step": 4290
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.489087104797363,
+      "learning_rate": 7.23136817286163e-06,
+      "loss": 1.0316,
+      "step": 4300
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.9029769897460938,
+      "learning_rate": 7.216191415821503e-06,
+      "loss": 1.0212,
+      "step": 4310
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.405784606933594,
+      "learning_rate": 7.200989205303583e-06,
+      "loss": 1.0421,
+      "step": 4320
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.0875701904296875,
+      "learning_rate": 7.185761715908826e-06,
+      "loss": 1.0468,
+      "step": 4330
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.10852575302124,
+      "learning_rate": 7.170509122528511e-06,
+      "loss": 1.0307,
+      "step": 4340
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.401843547821045,
+      "learning_rate": 7.15523160034225e-06,
+      "loss": 1.0265,
+      "step": 4350
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.106047630310059,
+      "learning_rate": 7.139929324815965e-06,
+      "loss": 1.021,
+      "step": 4360
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.1536407470703125,
+      "learning_rate": 7.124602471699878e-06,
+      "loss": 1.0409,
+      "step": 4370
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.14933443069458,
+      "learning_rate": 7.109251217026487e-06,
+      "loss": 1.0385,
+      "step": 4380
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.064835071563721,
+      "learning_rate": 7.0938757371085485e-06,
+      "loss": 1.0312,
+      "step": 4390
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.811549425125122,
+      "learning_rate": 7.078476208537057e-06,
+      "loss": 1.0359,
+      "step": 4400
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.325003623962402,
+      "learning_rate": 7.063052808179205e-06,
+      "loss": 1.0483,
+      "step": 4410
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 3.5266337394714355,
+      "learning_rate": 7.04760571317636e-06,
+      "loss": 1.0228,
+      "step": 4420
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.071694850921631,
+      "learning_rate": 7.032135100942027e-06,
+      "loss": 1.0353,
+      "step": 4430
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.121958255767822,
+      "learning_rate": 7.016641149159816e-06,
+      "loss": 1.049,
+      "step": 4440
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.714683532714844,
+      "learning_rate": 7.00112403578139e-06,
+      "loss": 1.0361,
+      "step": 4450
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.453790664672852,
+      "learning_rate": 6.985583939024436e-06,
+      "loss": 1.033,
+      "step": 4460
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.712753772735596,
+      "learning_rate": 6.970021037370609e-06,
+      "loss": 1.0462,
+      "step": 4470
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.329601287841797,
+      "learning_rate": 6.9544355095634775e-06,
+      "loss": 1.0459,
+      "step": 4480
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.669638156890869,
+      "learning_rate": 6.938827534606484e-06,
+      "loss": 1.0335,
+      "step": 4490
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.9964518547058105,
+      "learning_rate": 6.923197291760876e-06,
+      "loss": 1.0433,
+      "step": 4500
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.998533248901367,
+      "learning_rate": 6.907544960543659e-06,
+      "loss": 1.035,
+      "step": 4510
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.344484329223633,
+      "learning_rate": 6.891870720725522e-06,
+      "loss": 1.0405,
+      "step": 4520
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.392531871795654,
+      "learning_rate": 6.8761747523287845e-06,
+      "loss": 1.0339,
+      "step": 4530
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.274383544921875,
+      "learning_rate": 6.860457235625322e-06,
+      "loss": 1.0337,
+      "step": 4540
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.2484846115112305,
+      "learning_rate": 6.844718351134496e-06,
+      "loss": 1.0433,
+      "step": 4550
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.707181692123413,
+      "learning_rate": 6.828958279621085e-06,
+      "loss": 1.0497,
+      "step": 4560
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.188033103942871,
+      "learning_rate": 6.813177202093203e-06,
+      "loss": 1.0274,
+      "step": 4570
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.837230682373047,
+      "learning_rate": 6.797375299800224e-06,
+      "loss": 1.0395,
+      "step": 4580
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.9512484073638916,
+      "learning_rate": 6.7815527542307e-06,
+      "loss": 1.0516,
+      "step": 4590
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.2635297775268555,
+      "learning_rate": 6.765709747110274e-06,
+      "loss": 1.057,
+      "step": 4600
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.248997211456299,
+      "learning_rate": 6.749846460399594e-06,
+      "loss": 1.0296,
+      "step": 4610
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.210043430328369,
+      "learning_rate": 6.7339630762922295e-06,
+      "loss": 1.0291,
+      "step": 4620
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 3.8999147415161133,
+      "learning_rate": 6.7180597772125665e-06,
+      "loss": 1.0375,
+      "step": 4630
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.221770286560059,
+      "learning_rate": 6.702136745813721e-06,
+      "loss": 1.0206,
+      "step": 4640
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.14971399307251,
+      "learning_rate": 6.686194164975446e-06,
+      "loss": 1.0283,
+      "step": 4650
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 3.6616663932800293,
+      "learning_rate": 6.670232217802011e-06,
+      "loss": 1.0299,
+      "step": 4660
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.623802661895752,
+      "learning_rate": 6.654251087620125e-06,
+      "loss": 1.0325,
+      "step": 4670
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.6086490154266357,
+      "learning_rate": 6.638250957976813e-06,
+      "loss": 1.0299,
+      "step": 4680
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.8812456130981445,
+      "learning_rate": 6.6222320126373105e-06,
+      "loss": 1.0436,
+      "step": 4690
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.9015376567840576,
+      "learning_rate": 6.6061944355829634e-06,
+      "loss": 1.0093,
+      "step": 4700
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.15576171875,
+      "learning_rate": 6.590138411009099e-06,
+      "loss": 1.0378,
+      "step": 4710
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.204216957092285,
+      "learning_rate": 6.574064123322925e-06,
+      "loss": 1.032,
+      "step": 4720
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.158588409423828,
+      "learning_rate": 6.557971757141402e-06,
+      "loss": 1.0182,
+      "step": 4730
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.28289270401001,
+      "learning_rate": 6.541861497289126e-06,
+      "loss": 1.0324,
+      "step": 4740
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.406084060668945,
+      "learning_rate": 6.525733528796207e-06,
+      "loss": 1.0311,
+      "step": 4750
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.9430246353149414,
+      "learning_rate": 6.509588036896144e-06,
+      "loss": 1.0365,
+      "step": 4760
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.8312675952911377,
+      "learning_rate": 6.493425207023693e-06,
+      "loss": 1.0313,
+      "step": 4770
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.555315017700195,
+      "learning_rate": 6.477245224812746e-06,
+      "loss": 1.0336,
+      "step": 4780
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.399374961853027,
+      "learning_rate": 6.46104827609419e-06,
+      "loss": 1.0309,
+      "step": 4790
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.963261604309082,
+      "learning_rate": 6.444834546893773e-06,
+      "loss": 1.0401,
+      "step": 4800
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.5317559242248535,
+      "learning_rate": 6.42860422342998e-06,
+      "loss": 1.0287,
+      "step": 4810
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.08970308303833,
+      "learning_rate": 6.412357492111877e-06,
+      "loss": 1.0314,
+      "step": 4820
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.869360446929932,
+      "learning_rate": 6.396094539536981e-06,
+      "loss": 1.0426,
+      "step": 4830
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.279962539672852,
+      "learning_rate": 6.379815552489112e-06,
+      "loss": 1.044,
+      "step": 4840
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.379662990570068,
+      "learning_rate": 6.363520717936256e-06,
+      "loss": 1.022,
+      "step": 4850
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.329278469085693,
+      "learning_rate": 6.347210223028403e-06,
+      "loss": 1.0295,
+      "step": 4860
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.4202423095703125,
+      "learning_rate": 6.330884255095409e-06,
+      "loss": 1.0391,
+      "step": 4870
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.681463718414307,
+      "learning_rate": 6.3145430016448435e-06,
+      "loss": 1.0326,
+      "step": 4880
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.008312225341797,
+      "learning_rate": 6.298186650359832e-06,
+      "loss": 1.0459,
+      "step": 4890
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.1975884437561035,
+      "learning_rate": 6.281815389096903e-06,
+      "loss": 1.032,
+      "step": 4900
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.011014461517334,
+      "learning_rate": 6.265429405883825e-06,
+      "loss": 1.0537,
+      "step": 4910
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.628488063812256,
+      "learning_rate": 6.24902888891746e-06,
+      "loss": 1.0296,
+      "step": 4920
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 4.286167621612549,
+      "learning_rate": 6.232614026561586e-06,
+      "loss": 1.0251,
+      "step": 4930
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 4.162431240081787,
+      "learning_rate": 6.216185007344745e-06,
+      "loss": 1.0231,
+      "step": 4940
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 4.599613189697266,
+      "learning_rate": 6.199742019958074e-06,
+      "loss": 1.0259,
+      "step": 4950
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 3.7376463413238525,
+      "learning_rate": 6.183285253253135e-06,
+      "loss": 1.0308,
+      "step": 4960
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 4.396124362945557,
+      "learning_rate": 6.1668148962397525e-06,
+      "loss": 1.0383,
+      "step": 4970
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.382174015045166,
+      "learning_rate": 6.150331138083833e-06,
+      "loss": 1.0269,
+      "step": 4980
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.524794578552246,
+      "learning_rate": 6.133834168105206e-06,
+      "loss": 1.0381,
+      "step": 4990
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.226146221160889,
+      "learning_rate": 6.117324175775435e-06,
+      "loss": 1.0449,
+      "step": 5000
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 1.023166298866272,
+      "eval_runtime": 12.4375,
+      "eval_samples_per_second": 52.583,
+      "eval_steps_per_second": 6.593,
+      "step": 5000
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.120533466339111,
+      "learning_rate": 6.100801350715652e-06,
+      "loss": 1.0285,
+      "step": 5010
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9948532581329346,
+      "learning_rate": 6.084265882694378e-06,
+      "loss": 1.0411,
+      "step": 5020
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.175631999969482,
+      "learning_rate": 6.0677179616253345e-06,
+      "loss": 1.0347,
+      "step": 5030
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.19612455368042,
+      "learning_rate": 6.0511577775652744e-06,
+      "loss": 1.0367,
+      "step": 5040
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.379330158233643,
+      "learning_rate": 6.034585520711792e-06,
+      "loss": 1.0314,
+      "step": 5050
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.5682902336120605,
+      "learning_rate": 6.018001381401143e-06,
+      "loss": 1.0333,
+      "step": 5060
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.473631381988525,
+      "learning_rate": 6.001405550106052e-06,
+      "loss": 1.0397,
+      "step": 5070
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.200445175170898,
+      "learning_rate": 5.9847982174335314e-06,
+      "loss": 1.0262,
+      "step": 5080
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.9142019748687744,
+      "learning_rate": 5.96817957412269e-06,
+      "loss": 1.034,
+      "step": 5090
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.04217004776001,
+      "learning_rate": 5.951549811042539e-06,
+      "loss": 1.0466,
+      "step": 5100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1,
+  "total_flos": 1.9350228034513797e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568ebf0eb34d76cda9bc37319cd1c96c5b6f6ea9d7a5f79479001712c2590cb0
+size 6584

zero_to_fp32.py

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