Training in progress, epoch 0, checkpoint

checkpoint-349/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128019,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-349/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "transformers_version": "4.46.0.dev0"
+}

checkpoint-349/global_step349/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd86fa04ff6d952ca217b0bd09b2a994bc04606cecd3e6df55c78cadc469e97
+size 13609807299

checkpoint-349/global_step349/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f77337897c2ef7ac910db06b40b4f2cc148889e46eefedba5b3adf54d1608d
+size 13609807299

checkpoint-349/global_step349/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1371c8566a47a5b24ac64632222d00667de734f496134b4fc95745cab876d2
+size 152293

checkpoint-349/global_step349/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c64fd086b7421efecee4c885a9fc90185230c17dfd2bc76e92b6c8bd60495d
+size 152293

checkpoint-349/latest

@@ -0,0 +1 @@
+global_step349

checkpoint-349/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35df2d99728a28b3a6b36b3b4c1bb0ed4c9e195b29e91026579d9758290f0f9d
+size 4978354640

checkpoint-349/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1dab55a2b124aa3dc2b6445dd424a9c958dc3fa0e94da40b2e86ff8e149a15
+size 4047172128

checkpoint-349/model.safetensors.index.json

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

checkpoint-349/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e52325e9d729519836af640f8f754a93ee06730fb2953b5309434b53b17562
+size 14512

checkpoint-349/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a93593cf0342eb47876986e1063102e1546354426a2324c46ddcf1cbecae803
+size 14512

checkpoint-349/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc330a705ce44b1f0f9876c7f0a8a61c09c1784350d40ae4b0288eb56fb556b
+size 1064

checkpoint-349/special_tokens_map.json

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

checkpoint-349/tokenizer.json

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

checkpoint-349/tokenizer_config.json

@@ -0,0 +1,2062 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-349/trainer_state.json

@@ -0,0 +1,2508 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9992841803865425,
+  "eval_steps": 88,
+  "global_step": 349,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002863278453829635,
+      "grad_norm": 1.7433022469392645,
+      "learning_rate": 2.9411764705882356e-07,
+      "loss": 2.5227,
+      "step": 1
+    },
+    {
+      "epoch": 0.002863278453829635,
+      "eval_loss": 2.9798059463500977,
+      "eval_runtime": 15.4107,
+      "eval_samples_per_second": 14.146,
+      "eval_steps_per_second": 2.401,
+      "step": 1
+    },
+    {
+      "epoch": 0.00572655690765927,
+      "grad_norm": 1.7260085141016746,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 2.5557,
+      "step": 2
+    },
+    {
+      "epoch": 0.008589835361488905,
+      "grad_norm": 1.6875415011788866,
+      "learning_rate": 8.823529411764707e-07,
+      "loss": 2.5153,
+      "step": 3
+    },
+    {
+      "epoch": 0.01145311381531854,
+      "grad_norm": 1.501231559534811,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 2.5383,
+      "step": 4
+    },
+    {
+      "epoch": 0.014316392269148175,
+      "grad_norm": 1.3386535922727172,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 2.5313,
+      "step": 5
+    },
+    {
+      "epoch": 0.01717967072297781,
+      "grad_norm": 1.4453252560511072,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 2.5023,
+      "step": 6
+    },
+    {
+      "epoch": 0.020042949176807445,
+      "grad_norm": 1.2649460157616863,
+      "learning_rate": 2.058823529411765e-06,
+      "loss": 2.516,
+      "step": 7
+    },
+    {
+      "epoch": 0.02290622763063708,
+      "grad_norm": 1.2272485421450576,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 2.4859,
+      "step": 8
+    },
+    {
+      "epoch": 0.025769506084466716,
+      "grad_norm": 0.9566083602405432,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 2.505,
+      "step": 9
+    },
+    {
+      "epoch": 0.02863278453829635,
+      "grad_norm": 0.9324778074733336,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 2.5398,
+      "step": 10
+    },
+    {
+      "epoch": 0.031496062992125984,
+      "grad_norm": 0.9121134598727566,
+      "learning_rate": 3.2352941176470594e-06,
+      "loss": 2.4925,
+      "step": 11
+    },
+    {
+      "epoch": 0.03435934144595562,
+      "grad_norm": 0.7810248065316661,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 2.5252,
+      "step": 12
+    },
+    {
+      "epoch": 0.03722261989978525,
+      "grad_norm": 0.7605027751280174,
+      "learning_rate": 3.8235294117647055e-06,
+      "loss": 2.4853,
+      "step": 13
+    },
+    {
+      "epoch": 0.04008589835361489,
+      "grad_norm": 0.7103184324186846,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 2.5164,
+      "step": 14
+    },
+    {
+      "epoch": 0.04294917680744453,
+      "grad_norm": 0.7150261519787532,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 2.5179,
+      "step": 15
+    },
+    {
+      "epoch": 0.04581245526127416,
+      "grad_norm": 0.6401893492590393,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 2.5337,
+      "step": 16
+    },
+    {
+      "epoch": 0.048675733715103794,
+      "grad_norm": 0.6382120155027352,
+      "learning_rate": 5e-06,
+      "loss": 2.4971,
+      "step": 17
+    },
+    {
+      "epoch": 0.05153901216893343,
+      "grad_norm": 0.638974871748697,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 2.5137,
+      "step": 18
+    },
+    {
+      "epoch": 0.05440229062276306,
+      "grad_norm": 0.6276417784569189,
+      "learning_rate": 5.588235294117647e-06,
+      "loss": 2.5221,
+      "step": 19
+    },
+    {
+      "epoch": 0.0572655690765927,
+      "grad_norm": 0.6267712807753728,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 2.4958,
+      "step": 20
+    },
+    {
+      "epoch": 0.06012884753042233,
+      "grad_norm": 0.6277644572158624,
+      "learning_rate": 6.176470588235295e-06,
+      "loss": 2.4878,
+      "step": 21
+    },
+    {
+      "epoch": 0.06299212598425197,
+      "grad_norm": 0.6127762919814617,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 2.4914,
+      "step": 22
+    },
+    {
+      "epoch": 0.0658554044380816,
+      "grad_norm": 0.6038751254503039,
+      "learning_rate": 6.764705882352942e-06,
+      "loss": 2.51,
+      "step": 23
+    },
+    {
+      "epoch": 0.06871868289191124,
+      "grad_norm": 0.6003698592486557,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 2.4906,
+      "step": 24
+    },
+    {
+      "epoch": 0.07158196134574088,
+      "grad_norm": 0.6282240768376209,
+      "learning_rate": 7.352941176470589e-06,
+      "loss": 2.5082,
+      "step": 25
+    },
+    {
+      "epoch": 0.0744452397995705,
+      "grad_norm": 0.6087841519965377,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 2.4878,
+      "step": 26
+    },
+    {
+      "epoch": 0.07730851825340014,
+      "grad_norm": 0.5860330254627644,
+      "learning_rate": 7.941176470588236e-06,
+      "loss": 2.5182,
+      "step": 27
+    },
+    {
+      "epoch": 0.08017179670722978,
+      "grad_norm": 0.5939132759806514,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 2.501,
+      "step": 28
+    },
+    {
+      "epoch": 0.08303507516105942,
+      "grad_norm": 0.6359589764914113,
+      "learning_rate": 8.529411764705883e-06,
+      "loss": 2.523,
+      "step": 29
+    },
+    {
+      "epoch": 0.08589835361488905,
+      "grad_norm": 0.6255572369664097,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 2.4931,
+      "step": 30
+    },
+    {
+      "epoch": 0.08876163206871868,
+      "grad_norm": 0.5910507560604619,
+      "learning_rate": 9.11764705882353e-06,
+      "loss": 2.4838,
+      "step": 31
+    },
+    {
+      "epoch": 0.09162491052254831,
+      "grad_norm": 0.581588749176898,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 2.4853,
+      "step": 32
+    },
+    {
+      "epoch": 0.09448818897637795,
+      "grad_norm": 0.6483321707461923,
+      "learning_rate": 9.705882352941177e-06,
+      "loss": 2.4944,
+      "step": 33
+    },
+    {
+      "epoch": 0.09735146743020759,
+      "grad_norm": 0.5987568368261761,
+      "learning_rate": 1e-05,
+      "loss": 2.4699,
+      "step": 34
+    },
+    {
+      "epoch": 0.10021474588403723,
+      "grad_norm": 0.6206579432531898,
+      "learning_rate": 9.999751334779716e-06,
+      "loss": 2.523,
+      "step": 35
+    },
+    {
+      "epoch": 0.10307802433786686,
+      "grad_norm": 0.6064407921800384,
+      "learning_rate": 9.999005363852619e-06,
+      "loss": 2.5203,
+      "step": 36
+    },
+    {
+      "epoch": 0.10594130279169649,
+      "grad_norm": 0.5721412252832796,
+      "learning_rate": 9.997762161417517e-06,
+      "loss": 2.5012,
+      "step": 37
+    },
+    {
+      "epoch": 0.10880458124552612,
+      "grad_norm": 0.5497451217796617,
+      "learning_rate": 9.996021851130897e-06,
+      "loss": 2.4914,
+      "step": 38
+    },
+    {
+      "epoch": 0.11166785969935576,
+      "grad_norm": 0.5470018162226529,
+      "learning_rate": 9.993784606094612e-06,
+      "loss": 2.501,
+      "step": 39
+    },
+    {
+      "epoch": 0.1145311381531854,
+      "grad_norm": 0.5866491336876943,
+      "learning_rate": 9.991050648838676e-06,
+      "loss": 2.48,
+      "step": 40
+    },
+    {
+      "epoch": 0.11739441660701504,
+      "grad_norm": 0.5438529330919207,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 2.4983,
+      "step": 41
+    },
+    {
+      "epoch": 0.12025769506084466,
+      "grad_norm": 0.5740915531654763,
+      "learning_rate": 9.984093734790955e-06,
+      "loss": 2.5182,
+      "step": 42
+    },
+    {
+      "epoch": 0.1231209735146743,
+      "grad_norm": 0.5664275625259377,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 2.4862,
+      "step": 43
+    },
+    {
+      "epoch": 0.12598425196850394,
+      "grad_norm": 0.5926385697048842,
+      "learning_rate": 9.975153876827008e-06,
+      "loss": 2.4896,
+      "step": 44
+    },
+    {
+      "epoch": 0.12884753042233357,
+      "grad_norm": 0.574391809445724,
+      "learning_rate": 9.969941424583926e-06,
+      "loss": 2.5367,
+      "step": 45
+    },
+    {
+      "epoch": 0.1317108088761632,
+      "grad_norm": 0.5397781778798922,
+      "learning_rate": 9.964234631709188e-06,
+      "loss": 2.5025,
+      "step": 46
+    },
+    {
+      "epoch": 0.13457408732999285,
+      "grad_norm": 0.5539122724303173,
+      "learning_rate": 9.958034065835151e-06,
+      "loss": 2.5278,
+      "step": 47
+    },
+    {
+      "epoch": 0.13743736578382248,
+      "grad_norm": 0.5818328936194783,
+      "learning_rate": 9.951340343707852e-06,
+      "loss": 2.5188,
+      "step": 48
+    },
+    {
+      "epoch": 0.14030064423765212,
+      "grad_norm": 0.7458319373172223,
+      "learning_rate": 9.944154131125643e-06,
+      "loss": 2.4617,
+      "step": 49
+    },
+    {
+      "epoch": 0.14316392269148176,
+      "grad_norm": 0.5661010380152568,
+      "learning_rate": 9.936476142872979e-06,
+      "loss": 2.4926,
+      "step": 50
+    },
+    {
+      "epoch": 0.14602720114531137,
+      "grad_norm": 0.5650834703916657,
+      "learning_rate": 9.928307142649315e-06,
+      "loss": 2.4848,
+      "step": 51
+    },
+    {
+      "epoch": 0.148890479599141,
+      "grad_norm": 0.548453507209605,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 2.4969,
+      "step": 52
+    },
+    {
+      "epoch": 0.15175375805297064,
+      "grad_norm": 0.5758188221734539,
+      "learning_rate": 9.910499405201195e-06,
+      "loss": 2.484,
+      "step": 53
+    },
+    {
+      "epoch": 0.15461703650680028,
+      "grad_norm": 0.5753520047837293,
+      "learning_rate": 9.900862439242719e-06,
+      "loss": 2.4941,
+      "step": 54
+    },
+    {
+      "epoch": 0.15748031496062992,
+      "grad_norm": 0.5769855830607382,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 2.4856,
+      "step": 55
+    },
+    {
+      "epoch": 0.16034359341445956,
+      "grad_norm": 0.5490460548187522,
+      "learning_rate": 9.880127105518122e-06,
+      "loss": 2.5226,
+      "step": 56
+    },
+    {
+      "epoch": 0.1632068718682892,
+      "grad_norm": 0.601542983516753,
+      "learning_rate": 9.869030800214531e-06,
+      "loss": 2.5096,
+      "step": 57
+    },
+    {
+      "epoch": 0.16607015032211883,
+      "grad_norm": 0.5613978478420705,
+      "learning_rate": 9.857450191464337e-06,
+      "loss": 2.5145,
+      "step": 58
+    },
+    {
+      "epoch": 0.16893342877594847,
+      "grad_norm": 0.5600847385523823,
+      "learning_rate": 9.84538643114539e-06,
+      "loss": 2.5111,
+      "step": 59
+    },
+    {
+      "epoch": 0.1717967072297781,
+      "grad_norm": 0.5401691538446458,
+      "learning_rate": 9.832840719192737e-06,
+      "loss": 2.498,
+      "step": 60
+    },
+    {
+      "epoch": 0.17465998568360774,
+      "grad_norm": 0.5520094893813158,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 2.494,
+      "step": 61
+    },
+    {
+      "epoch": 0.17752326413743735,
+      "grad_norm": 0.5497902576608895,
+      "learning_rate": 9.806308479691595e-06,
+      "loss": 2.5017,
+      "step": 62
+    },
+    {
+      "epoch": 0.180386542591267,
+      "grad_norm": 0.525740103564976,
+      "learning_rate": 9.792324591201179e-06,
+      "loss": 2.5068,
+      "step": 63
+    },
+    {
+      "epoch": 0.18324982104509663,
+      "grad_norm": 0.5544436996206911,
+      "learning_rate": 9.777864028930705e-06,
+      "loss": 2.4976,
+      "step": 64
+    },
+    {
+      "epoch": 0.18611309949892627,
+      "grad_norm": 0.555608149815371,
+      "learning_rate": 9.762928231215731e-06,
+      "loss": 2.5112,
+      "step": 65
+    },
+    {
+      "epoch": 0.1889763779527559,
+      "grad_norm": 0.5356931315907684,
+      "learning_rate": 9.747518683661632e-06,
+      "loss": 2.4967,
+      "step": 66
+    },
+    {
+      "epoch": 0.19183965640658554,
+      "grad_norm": 0.5603711133278504,
+      "learning_rate": 9.731636918995821e-06,
+      "loss": 2.5134,
+      "step": 67
+    },
+    {
+      "epoch": 0.19470293486041518,
+      "grad_norm": 0.5414742895107459,
+      "learning_rate": 9.715284516915303e-06,
+      "loss": 2.525,
+      "step": 68
+    },
+    {
+      "epoch": 0.19756621331424482,
+      "grad_norm": 0.5348649401490828,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 2.4903,
+      "step": 69
+    },
+    {
+      "epoch": 0.20042949176807445,
+      "grad_norm": 0.5179063198083461,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 2.5107,
+      "step": 70
+    },
+    {
+      "epoch": 0.2032927702219041,
+      "grad_norm": 0.5246232399143359,
+      "learning_rate": 9.663419984367139e-06,
+      "loss": 2.5203,
+      "step": 71
+    },
+    {
+      "epoch": 0.20615604867573373,
+      "grad_norm": 0.5289273463036179,
+      "learning_rate": 9.645201763392513e-06,
+      "loss": 2.5053,
+      "step": 72
+    },
+    {
+      "epoch": 0.20901932712956334,
+      "grad_norm": 0.5433820476794674,
+      "learning_rate": 9.626521502369984e-06,
+      "loss": 2.4764,
+      "step": 73
+    },
+    {
+      "epoch": 0.21188260558339297,
+      "grad_norm": 0.5505407639513397,
+      "learning_rate": 9.60738105935204e-06,
+      "loss": 2.4838,
+      "step": 74
+    },
+    {
+      "epoch": 0.2147458840372226,
+      "grad_norm": 0.5690742761627252,
+      "learning_rate": 9.58778233816367e-06,
+      "loss": 2.4774,
+      "step": 75
+    },
+    {
+      "epoch": 0.21760916249105225,
+      "grad_norm": 0.514161333996788,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 2.4778,
+      "step": 76
+    },
+    {
+      "epoch": 0.2204724409448819,
+      "grad_norm": 0.5512425303188625,
+      "learning_rate": 9.547217904297411e-06,
+      "loss": 2.488,
+      "step": 77
+    },
+    {
+      "epoch": 0.22333571939871152,
+      "grad_norm": 0.547345521950976,
+      "learning_rate": 9.526256226405075e-06,
+      "loss": 2.5231,
+      "step": 78
+    },
+    {
+      "epoch": 0.22619899785254116,
+      "grad_norm": 0.572668835030032,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 2.4904,
+      "step": 79
+    },
+    {
+      "epoch": 0.2290622763063708,
+      "grad_norm": 0.5586691177416543,
+      "learning_rate": 9.482984373375105e-06,
+      "loss": 2.5099,
+      "step": 80
+    },
+    {
+      "epoch": 0.23192555476020044,
+      "grad_norm": 0.5580296085776706,
+      "learning_rate": 9.460678502319419e-06,
+      "loss": 2.4894,
+      "step": 81
+    },
+    {
+      "epoch": 0.23478883321403007,
+      "grad_norm": 0.5485012119106963,
+      "learning_rate": 9.437928945022772e-06,
+      "loss": 2.4949,
+      "step": 82
+    },
+    {
+      "epoch": 0.2376521116678597,
+      "grad_norm": 0.543333232228658,
+      "learning_rate": 9.414737964294636e-06,
+      "loss": 2.4868,
+      "step": 83
+    },
+    {
+      "epoch": 0.24051539012168932,
+      "grad_norm": 0.5890968894329803,
+      "learning_rate": 9.391107866851143e-06,
+      "loss": 2.5089,
+      "step": 84
+    },
+    {
+      "epoch": 0.24337866857551896,
+      "grad_norm": 0.5506851813496826,
+      "learning_rate": 9.36704100308565e-06,
+      "loss": 2.4458,
+      "step": 85
+    },
+    {
+      "epoch": 0.2462419470293486,
+      "grad_norm": 0.5504307062507774,
+      "learning_rate": 9.342539766834945e-06,
+      "loss": 2.4797,
+      "step": 86
+    },
+    {
+      "epoch": 0.24910522548317823,
+      "grad_norm": 0.548732984699912,
+      "learning_rate": 9.317606595141156e-06,
+      "loss": 2.5029,
+      "step": 87
+    },
+    {
+      "epoch": 0.25196850393700787,
+      "grad_norm": 0.5505255392480715,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 2.5027,
+      "step": 88
+    },
+    {
+      "epoch": 0.25196850393700787,
+      "eval_loss": 2.9500625133514404,
+      "eval_runtime": 15.442,
+      "eval_samples_per_second": 14.117,
+      "eval_steps_per_second": 2.396,
+      "step": 88
+    },
+    {
+      "epoch": 0.25483178239083754,
+      "grad_norm": 0.5482944395523252,
+      "learning_rate": 9.266454408160779e-06,
+      "loss": 2.5322,
+      "step": 89
+    },
+    {
+      "epoch": 0.25769506084466715,
+      "grad_norm": 0.541771069630789,
+      "learning_rate": 9.24024048078213e-06,
+      "loss": 2.5155,
+      "step": 90
+    },
+    {
+      "epoch": 0.26055833929849676,
+      "grad_norm": 0.5325088342727101,
+      "learning_rate": 9.213604793270196e-06,
+      "loss": 2.4651,
+      "step": 91
+    },
+    {
+      "epoch": 0.2634216177523264,
+      "grad_norm": 0.5265061377076917,
+      "learning_rate": 9.186549994972618e-06,
+      "loss": 2.4755,
+      "step": 92
+    },
+    {
+      "epoch": 0.26628489620615603,
+      "grad_norm": 0.5466047048898959,
+      "learning_rate": 9.159078776924347e-06,
+      "loss": 2.4785,
+      "step": 93
+    },
+    {
+      "epoch": 0.2691481746599857,
+      "grad_norm": 0.5303191520111897,
+      "learning_rate": 9.131193871579975e-06,
+      "loss": 2.5137,
+      "step": 94
+    },
+    {
+      "epoch": 0.2720114531138153,
+      "grad_norm": 0.5517463944794626,
+      "learning_rate": 9.102898052541959e-06,
+      "loss": 2.4892,
+      "step": 95
+    },
+    {
+      "epoch": 0.27487473156764497,
+      "grad_norm": 0.5100270059915952,
+      "learning_rate": 9.074194134284726e-06,
+      "loss": 2.5048,
+      "step": 96
+    },
+    {
+      "epoch": 0.2777380100214746,
+      "grad_norm": 0.5278965930755488,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 2.4806,
+      "step": 97
+    },
+    {
+      "epoch": 0.28060128847530424,
+      "grad_norm": 0.5386440502957012,
+      "learning_rate": 9.01557346068651e-06,
+      "loss": 2.4637,
+      "step": 98
+    },
+    {
+      "epoch": 0.28346456692913385,
+      "grad_norm": 0.5424442293047355,
+      "learning_rate": 8.985662536114614e-06,
+      "loss": 2.4731,
+      "step": 99
+    },
+    {
+      "epoch": 0.2863278453829635,
+      "grad_norm": 0.5447548421095255,
+      "learning_rate": 8.955355173281709e-06,
+      "loss": 2.456,
+      "step": 100
+    },
+    {
+      "epoch": 0.28919112383679313,
+      "grad_norm": 0.5056892441431114,
+      "learning_rate": 8.924654386742613e-06,
+      "loss": 2.5027,
+      "step": 101
+    },
+    {
+      "epoch": 0.29205440229062274,
+      "grad_norm": 0.5577307275143056,
+      "learning_rate": 8.89356323018447e-06,
+      "loss": 2.5396,
+      "step": 102
+    },
+    {
+      "epoch": 0.2949176807444524,
+      "grad_norm": 0.5269321742421326,
+      "learning_rate": 8.862084796122998e-06,
+      "loss": 2.5348,
+      "step": 103
+    },
+    {
+      "epoch": 0.297780959198282,
+      "grad_norm": 0.573483487118278,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 2.5129,
+      "step": 104
+    },
+    {
+      "epoch": 0.3006442376521117,
+      "grad_norm": 0.5053757854271658,
+      "learning_rate": 8.797978657846391e-06,
+      "loss": 2.4992,
+      "step": 105
+    },
+    {
+      "epoch": 0.3035075161059413,
+      "grad_norm": 0.5463649574920005,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 2.4745,
+      "step": 106
+    },
+    {
+      "epoch": 0.30637079455977095,
+      "grad_norm": 0.5380399569585859,
+      "learning_rate": 8.732361476825752e-06,
+      "loss": 2.5305,
+      "step": 107
+    },
+    {
+      "epoch": 0.30923407301360056,
+      "grad_norm": 0.501404327425355,
+      "learning_rate": 8.698994380237921e-06,
+      "loss": 2.493,
+      "step": 108
+    },
+    {
+      "epoch": 0.31209735146743023,
+      "grad_norm": 0.5204332392598845,
+      "learning_rate": 8.665259359149132e-06,
+      "loss": 2.4834,
+      "step": 109
+    },
+    {
+      "epoch": 0.31496062992125984,
+      "grad_norm": 0.5172941461879834,
+      "learning_rate": 8.631159769049965e-06,
+      "loss": 2.4663,
+      "step": 110
+    },
+    {
+      "epoch": 0.3178239083750895,
+      "grad_norm": 0.5633507992944607,
+      "learning_rate": 8.596699001693257e-06,
+      "loss": 2.5106,
+      "step": 111
+    },
+    {
+      "epoch": 0.3206871868289191,
+      "grad_norm": 0.5111870840713941,
+      "learning_rate": 8.561880484756726e-06,
+      "loss": 2.4961,
+      "step": 112
+    },
+    {
+      "epoch": 0.3235504652827487,
+      "grad_norm": 0.5204943642446078,
+      "learning_rate": 8.526707681502045e-06,
+      "loss": 2.459,
+      "step": 113
+    },
+    {
+      "epoch": 0.3264137437365784,
+      "grad_norm": 0.5243848667219405,
+      "learning_rate": 8.491184090430365e-06,
+      "loss": 2.4847,
+      "step": 114
+    },
+    {
+      "epoch": 0.329277022190408,
+      "grad_norm": 0.5095475752397022,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 2.5041,
+      "step": 115
+    },
+    {
+      "epoch": 0.33214030064423766,
+      "grad_norm": 0.5324839977569346,
+      "learning_rate": 8.4190987129466e-06,
+      "loss": 2.4581,
+      "step": 116
+    },
+    {
+      "epoch": 0.3350035790980673,
+      "grad_norm": 0.537216858096812,
+      "learning_rate": 8.382544096585028e-06,
+      "loss": 2.4956,
+      "step": 117
+    },
+    {
+      "epoch": 0.33786685755189694,
+      "grad_norm": 0.5026214156562598,
+      "learning_rate": 8.345653031794292e-06,
+      "loss": 2.5109,
+      "step": 118
+    },
+    {
+      "epoch": 0.34073013600572655,
+      "grad_norm": 0.5589087292743029,
+      "learning_rate": 8.308429187984298e-06,
+      "loss": 2.4508,
+      "step": 119
+    },
+    {
+      "epoch": 0.3435934144595562,
+      "grad_norm": 0.5175402219605563,
+      "learning_rate": 8.270876267665173e-06,
+      "loss": 2.4915,
+      "step": 120
+    },
+    {
+      "epoch": 0.3464566929133858,
+      "grad_norm": 0.5228528180395297,
+      "learning_rate": 8.232998006078998e-06,
+      "loss": 2.4766,
+      "step": 121
+    },
+    {
+      "epoch": 0.3493199713672155,
+      "grad_norm": 0.5654685794544859,
+      "learning_rate": 8.19479817082828e-06,
+      "loss": 2.4669,
+      "step": 122
+    },
+    {
+      "epoch": 0.3521832498210451,
+      "grad_norm": 0.517826924265438,
+      "learning_rate": 8.156280561501196e-06,
+      "loss": 2.4913,
+      "step": 123
+    },
+    {
+      "epoch": 0.3550465282748747,
+      "grad_norm": 0.5546777654441133,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 2.4551,
+      "step": 124
+    },
+    {
+      "epoch": 0.35790980672870437,
+      "grad_norm": 0.5128294773578065,
+      "learning_rate": 8.078307376628292e-06,
+      "loss": 2.5143,
+      "step": 125
+    },
+    {
+      "epoch": 0.360773085182534,
+      "grad_norm": 0.5181572014660524,
+      "learning_rate": 8.038859556770152e-06,
+      "loss": 2.4918,
+      "step": 126
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.5580601606690623,
+      "learning_rate": 7.99910947343957e-06,
+      "loss": 2.4703,
+      "step": 127
+    },
+    {
+      "epoch": 0.36649964209019326,
+      "grad_norm": 0.5310828252758204,
+      "learning_rate": 7.95906108042184e-06,
+      "loss": 2.4942,
+      "step": 128
+    },
+    {
+      "epoch": 0.3693629205440229,
+      "grad_norm": 0.5572432262386191,
+      "learning_rate": 7.918718361173951e-06,
+      "loss": 2.5351,
+      "step": 129
+    },
+    {
+      "epoch": 0.37222619899785253,
+      "grad_norm": 0.5627081677105857,
+      "learning_rate": 7.87808532842837e-06,
+      "loss": 2.4636,
+      "step": 130
+    },
+    {
+      "epoch": 0.3750894774516822,
+      "grad_norm": 0.5613271800153685,
+      "learning_rate": 7.83716602379391e-06,
+      "loss": 2.4953,
+      "step": 131
+    },
+    {
+      "epoch": 0.3779527559055118,
+      "grad_norm": 0.5394988971278871,
+      "learning_rate": 7.795964517353734e-06,
+      "loss": 2.5189,
+      "step": 132
+    },
+    {
+      "epoch": 0.38081603435934147,
+      "grad_norm": 0.5313679498243665,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 2.4768,
+      "step": 133
+    },
+    {
+      "epoch": 0.3836793128131711,
+      "grad_norm": 0.5703379561975805,
+      "learning_rate": 7.712731319328798e-06,
+      "loss": 2.4659,
+      "step": 134
+    },
+    {
+      "epoch": 0.3865425912670007,
+      "grad_norm": 0.49255468232562744,
+      "learning_rate": 7.670707906624644e-06,
+      "loss": 2.4989,
+      "step": 135
+    },
+    {
+      "epoch": 0.38940586972083036,
+      "grad_norm": 0.5185698028962875,
+      "learning_rate": 7.628418849052523e-06,
+      "loss": 2.4941,
+      "step": 136
+    },
+    {
+      "epoch": 0.39226914817465997,
+      "grad_norm": 0.5378386670092136,
+      "learning_rate": 7.585868352939564e-06,
+      "loss": 2.4772,
+      "step": 137
+    },
+    {
+      "epoch": 0.39513242662848963,
+      "grad_norm": 0.5379669385240866,
+      "learning_rate": 7.543060650617159e-06,
+      "loss": 2.4902,
+      "step": 138
+    },
+    {
+      "epoch": 0.39799570508231924,
+      "grad_norm": 0.527227129367134,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 2.4898,
+      "step": 139
+    },
+    {
+      "epoch": 0.4008589835361489,
+      "grad_norm": 0.5185278503926084,
+      "learning_rate": 7.456690684162557e-06,
+      "loss": 2.479,
+      "step": 140
+    },
+    {
+      "epoch": 0.4037222619899785,
+      "grad_norm": 0.5028759823161459,
+      "learning_rate": 7.413137010913055e-06,
+      "loss": 2.5108,
+      "step": 141
+    },
+    {
+      "epoch": 0.4065855404438082,
+      "grad_norm": 0.5323427436694725,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 2.4895,
+      "step": 142
+    },
+    {
+      "epoch": 0.4094488188976378,
+      "grad_norm": 0.5303373348854972,
+      "learning_rate": 7.3253139445062535e-06,
+      "loss": 2.4831,
+      "step": 143
+    },
+    {
+      "epoch": 0.41231209735146745,
+      "grad_norm": 0.5171505606227076,
+      "learning_rate": 7.281053286765816e-06,
+      "loss": 2.4691,
+      "step": 144
+    },
+    {
+      "epoch": 0.41517537580529706,
+      "grad_norm": 0.5007625110632795,
+      "learning_rate": 7.236565741578163e-06,
+      "loss": 2.4864,
+      "step": 145
+    },
+    {
+      "epoch": 0.4180386542591267,
+      "grad_norm": 0.5192090084896421,
+      "learning_rate": 7.191855733945388e-06,
+      "loss": 2.5329,
+      "step": 146
+    },
+    {
+      "epoch": 0.42090193271295634,
+      "grad_norm": 0.5408008884476913,
+      "learning_rate": 7.146927710997047e-06,
+      "loss": 2.4846,
+      "step": 147
+    },
+    {
+      "epoch": 0.42376521116678595,
+      "grad_norm": 0.4927740392753858,
+      "learning_rate": 7.101786141547829e-06,
+      "loss": 2.458,
+      "step": 148
+    },
+    {
+      "epoch": 0.4266284896206156,
+      "grad_norm": 0.5063973450614866,
+      "learning_rate": 7.056435515653059e-06,
+      "loss": 2.4772,
+      "step": 149
+    },
+    {
+      "epoch": 0.4294917680744452,
+      "grad_norm": 0.5403619047312843,
+      "learning_rate": 7.010880344162087e-06,
+      "loss": 2.4837,
+      "step": 150
+    },
+    {
+      "epoch": 0.4323550465282749,
+      "grad_norm": 0.4922676337577914,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 2.4819,
+      "step": 151
+    },
+    {
+      "epoch": 0.4352183249821045,
+      "grad_norm": 0.521792840976189,
+      "learning_rate": 6.919174509065003e-06,
+      "loss": 2.5105,
+      "step": 152
+    },
+    {
+      "epoch": 0.43808160343593416,
+      "grad_norm": 0.5219763904404502,
+      "learning_rate": 6.873032967079562e-06,
+      "loss": 2.4779,
+      "step": 153
+    },
+    {
+      "epoch": 0.4409448818897638,
+      "grad_norm": 0.5154672827971456,
+      "learning_rate": 6.8267051218319766e-06,
+      "loss": 2.52,
+      "step": 154
+    },
+    {
+      "epoch": 0.44380816034359344,
+      "grad_norm": 0.5301945278339433,
+      "learning_rate": 6.780195581371785e-06,
+      "loss": 2.4721,
+      "step": 155
+    },
+    {
+      "epoch": 0.44667143879742305,
+      "grad_norm": 0.5014158054403869,
+      "learning_rate": 6.733508971821037e-06,
+      "loss": 2.4652,
+      "step": 156
+    },
+    {
+      "epoch": 0.44953471725125266,
+      "grad_norm": 0.5221719192401763,
+      "learning_rate": 6.686649936914151e-06,
+      "loss": 2.5095,
+      "step": 157
+    },
+    {
+      "epoch": 0.4523979957050823,
+      "grad_norm": 0.5633793319541605,
+      "learning_rate": 6.639623137536023e-06,
+      "loss": 2.5088,
+      "step": 158
+    },
+    {
+      "epoch": 0.45526127415891193,
+      "grad_norm": 0.503797400013898,
+      "learning_rate": 6.592433251258423e-06,
+      "loss": 2.4392,
+      "step": 159
+    },
+    {
+      "epoch": 0.4581245526127416,
+      "grad_norm": 0.5353571393146068,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 2.4806,
+      "step": 160
+    },
+    {
+      "epoch": 0.4609878310665712,
+      "grad_norm": 0.5394132569835262,
+      "learning_rate": 6.497583008933097e-06,
+      "loss": 2.4437,
+      "step": 161
+    },
+    {
+      "epoch": 0.4638511095204009,
+      "grad_norm": 0.49177737499930074,
+      "learning_rate": 6.449932087267932e-06,
+      "loss": 2.4602,
+      "step": 162
+    },
+    {
+      "epoch": 0.4667143879742305,
+      "grad_norm": 0.5299162942575597,
+      "learning_rate": 6.402136946530014e-06,
+      "loss": 2.458,
+      "step": 163
+    },
+    {
+      "epoch": 0.46957766642806015,
+      "grad_norm": 0.5268297730689246,
+      "learning_rate": 6.354202340715027e-06,
+      "loss": 2.4701,
+      "step": 164
+    },
+    {
+      "epoch": 0.47244094488188976,
+      "grad_norm": 0.5120064053501564,
+      "learning_rate": 6.306133037690693e-06,
+      "loss": 2.485,
+      "step": 165
+    },
+    {
+      "epoch": 0.4753042233357194,
+      "grad_norm": 0.5110676269579153,
+      "learning_rate": 6.257933818722544e-06,
+      "loss": 2.4721,
+      "step": 166
+    },
+    {
+      "epoch": 0.47816750178954903,
+      "grad_norm": 0.5476368667166479,
+      "learning_rate": 6.209609477998339e-06,
+      "loss": 2.4884,
+      "step": 167
+    },
+    {
+      "epoch": 0.48103078024337864,
+      "grad_norm": 0.4764530610045073,
+      "learning_rate": 6.161164822151213e-06,
+      "loss": 2.4384,
+      "step": 168
+    },
+    {
+      "epoch": 0.4838940586972083,
+      "grad_norm": 0.5083738885386776,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 2.5163,
+      "step": 169
+    },
+    {
+      "epoch": 0.4867573371510379,
+      "grad_norm": 0.5721234428494102,
+      "learning_rate": 6.063933850977811e-06,
+      "loss": 2.4187,
+      "step": 170
+    },
+    {
+      "epoch": 0.4896206156048676,
+      "grad_norm": 0.48356591072844135,
+      "learning_rate": 6.015157206835881e-06,
+      "loss": 2.4661,
+      "step": 171
+    },
+    {
+      "epoch": 0.4924838940586972,
+      "grad_norm": 0.5318155836725099,
+      "learning_rate": 5.9662795889777666e-06,
+      "loss": 2.4874,
+      "step": 172
+    },
+    {
+      "epoch": 0.49534717251252686,
+      "grad_norm": 0.532932583531948,
+      "learning_rate": 5.917305859068912e-06,
+      "loss": 2.4611,
+      "step": 173
+    },
+    {
+      "epoch": 0.49821045096635647,
+      "grad_norm": 0.4992558226313865,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 2.4847,
+      "step": 174
+    },
+    {
+      "epoch": 0.5010737294201861,
+      "grad_norm": 0.49892566334047106,
+      "learning_rate": 5.819089557075689e-06,
+      "loss": 2.4672,
+      "step": 175
+    },
+    {
+      "epoch": 0.5039370078740157,
+      "grad_norm": 0.5162760616236272,
+      "learning_rate": 5.769856754182668e-06,
+      "loss": 2.481,
+      "step": 176
+    },
+    {
+      "epoch": 0.5039370078740157,
+      "eval_loss": 2.939789295196533,
+      "eval_runtime": 15.4591,
+      "eval_samples_per_second": 14.102,
+      "eval_steps_per_second": 2.393,
+      "step": 176
+    },
+    {
+      "epoch": 0.5068002863278454,
+      "grad_norm": 0.5155049998342655,
+      "learning_rate": 5.720547376649901e-06,
+      "loss": 2.4383,
+      "step": 177
+    },
+    {
+      "epoch": 0.5096635647816751,
+      "grad_norm": 0.49383297653530694,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 2.4963,
+      "step": 178
+    },
+    {
+      "epoch": 0.5125268432355047,
+      "grad_norm": 0.5451897427189254,
+      "learning_rate": 5.621718523237427e-06,
+      "loss": 2.458,
+      "step": 179
+    },
+    {
+      "epoch": 0.5153901216893343,
+      "grad_norm": 0.5067050740905722,
+      "learning_rate": 5.57220887747716e-06,
+      "loss": 2.4615,
+      "step": 180
+    },
+    {
+      "epoch": 0.5182534001431639,
+      "grad_norm": 0.5118844197490995,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 2.4782,
+      "step": 181
+    },
+    {
+      "epoch": 0.5211166785969935,
+      "grad_norm": 0.49843713068761214,
+      "learning_rate": 5.473023770012686e-06,
+      "loss": 2.4639,
+      "step": 182
+    },
+    {
+      "epoch": 0.5239799570508232,
+      "grad_norm": 0.49039624756309863,
+      "learning_rate": 5.423358173863117e-06,
+      "loss": 2.5034,
+      "step": 183
+    },
+    {
+      "epoch": 0.5268432355046528,
+      "grad_norm": 0.5397522237987987,
+      "learning_rate": 5.373650467932122e-06,
+      "loss": 2.4828,
+      "step": 184
+    },
+    {
+      "epoch": 0.5297065139584825,
+      "grad_norm": 0.46938500048241816,
+      "learning_rate": 5.323905596450759e-06,
+      "loss": 2.4896,
+      "step": 185
+    },
+    {
+      "epoch": 0.5325697924123121,
+      "grad_norm": 0.46678391598361535,
+      "learning_rate": 5.274128507346801e-06,
+      "loss": 2.513,
+      "step": 186
+    },
+    {
+      "epoch": 0.5354330708661418,
+      "grad_norm": 0.497328791756282,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 2.4681,
+      "step": 187
+    },
+    {
+      "epoch": 0.5382963493199714,
+      "grad_norm": 0.49519258041200537,
+      "learning_rate": 5.174497483512506e-06,
+      "loss": 2.5165,
+      "step": 188
+    },
+    {
+      "epoch": 0.541159627773801,
+      "grad_norm": 0.51742332377377,
+      "learning_rate": 5.1246534586903655e-06,
+      "loss": 2.5054,
+      "step": 189
+    },
+    {
+      "epoch": 0.5440229062276306,
+      "grad_norm": 0.47861405099169874,
+      "learning_rate": 5.074797035076319e-06,
+      "loss": 2.4731,
+      "step": 190
+    },
+    {
+      "epoch": 0.5468861846814602,
+      "grad_norm": 0.49802176173801116,
+      "learning_rate": 5.024933171693791e-06,
+      "loss": 2.4637,
+      "step": 191
+    },
+    {
+      "epoch": 0.5497494631352899,
+      "grad_norm": 0.4840967047698607,
+      "learning_rate": 4.9750668283062104e-06,
+      "loss": 2.4968,
+      "step": 192
+    },
+    {
+      "epoch": 0.5526127415891195,
+      "grad_norm": 0.47135451227221825,
+      "learning_rate": 4.9252029649236835e-06,
+      "loss": 2.4511,
+      "step": 193
+    },
+    {
+      "epoch": 0.5554760200429492,
+      "grad_norm": 0.48895069084444304,
+      "learning_rate": 4.875346541309637e-06,
+      "loss": 2.4481,
+      "step": 194
+    },
+    {
+      "epoch": 0.5583392984967788,
+      "grad_norm": 0.4965170322744245,
+      "learning_rate": 4.825502516487497e-06,
+      "loss": 2.4937,
+      "step": 195
+    },
+    {
+      "epoch": 0.5612025769506085,
+      "grad_norm": 0.4978261261637217,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 2.479,
+      "step": 196
+    },
+    {
+      "epoch": 0.5640658554044381,
+      "grad_norm": 0.4773588207221208,
+      "learning_rate": 4.7258714926532e-06,
+      "loss": 2.492,
+      "step": 197
+    },
+    {
+      "epoch": 0.5669291338582677,
+      "grad_norm": 0.4759022046084612,
+      "learning_rate": 4.676094403549241e-06,
+      "loss": 2.4585,
+      "step": 198
+    },
+    {
+      "epoch": 0.5697924123120973,
+      "grad_norm": 0.48965996741234036,
+      "learning_rate": 4.626349532067879e-06,
+      "loss": 2.4761,
+      "step": 199
+    },
+    {
+      "epoch": 0.572655690765927,
+      "grad_norm": 0.46747661270431873,
+      "learning_rate": 4.576641826136884e-06,
+      "loss": 2.4748,
+      "step": 200
+    },
+    {
+      "epoch": 0.5755189692197566,
+      "grad_norm": 0.47493437805144983,
+      "learning_rate": 4.526976229987315e-06,
+      "loss": 2.4631,
+      "step": 201
+    },
+    {
+      "epoch": 0.5783822476735863,
+      "grad_norm": 0.4915217558336455,
+      "learning_rate": 4.477357683661734e-06,
+      "loss": 2.4768,
+      "step": 202
+    },
+    {
+      "epoch": 0.5812455261274159,
+      "grad_norm": 0.4793297296845006,
+      "learning_rate": 4.427791122522841e-06,
+      "loss": 2.4861,
+      "step": 203
+    },
+    {
+      "epoch": 0.5841088045812455,
+      "grad_norm": 0.4847288969292467,
+      "learning_rate": 4.3782814767625755e-06,
+      "loss": 2.4528,
+      "step": 204
+    },
+    {
+      "epoch": 0.5869720830350752,
+      "grad_norm": 0.46840483063360394,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 2.4844,
+      "step": 205
+    },
+    {
+      "epoch": 0.5898353614889048,
+      "grad_norm": 0.49201004049650826,
+      "learning_rate": 4.279452623350101e-06,
+      "loss": 2.4908,
+      "step": 206
+    },
+    {
+      "epoch": 0.5926986399427344,
+      "grad_norm": 0.49621336600388116,
+      "learning_rate": 4.230143245817332e-06,
+      "loss": 2.4997,
+      "step": 207
+    },
+    {
+      "epoch": 0.595561918396564,
+      "grad_norm": 0.4922422256843438,
+      "learning_rate": 4.180910442924312e-06,
+      "loss": 2.4725,
+      "step": 208
+    },
+    {
+      "epoch": 0.5984251968503937,
+      "grad_norm": 0.49243609704503866,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 2.4525,
+      "step": 209
+    },
+    {
+      "epoch": 0.6012884753042234,
+      "grad_norm": 0.5310002493376136,
+      "learning_rate": 4.0826941409310885e-06,
+      "loss": 2.4959,
+      "step": 210
+    },
+    {
+      "epoch": 0.604151753758053,
+      "grad_norm": 0.485979098182275,
+      "learning_rate": 4.033720411022235e-06,
+      "loss": 2.4817,
+      "step": 211
+    },
+    {
+      "epoch": 0.6070150322118826,
+      "grad_norm": 0.4893545713811437,
+      "learning_rate": 3.98484279316412e-06,
+      "loss": 2.4926,
+      "step": 212
+    },
+    {
+      "epoch": 0.6098783106657122,
+      "grad_norm": 0.5177988359519327,
+      "learning_rate": 3.936066149022191e-06,
+      "loss": 2.5085,
+      "step": 213
+    },
+    {
+      "epoch": 0.6127415891195419,
+      "grad_norm": 0.49306653272715745,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 2.473,
+      "step": 214
+    },
+    {
+      "epoch": 0.6156048675733715,
+      "grad_norm": 0.47728344715096344,
+      "learning_rate": 3.8388351778487884e-06,
+      "loss": 2.4729,
+      "step": 215
+    },
+    {
+      "epoch": 0.6184681460272011,
+      "grad_norm": 0.47456363408410085,
+      "learning_rate": 3.790390522001662e-06,
+      "loss": 2.4628,
+      "step": 216
+    },
+    {
+      "epoch": 0.6213314244810307,
+      "grad_norm": 0.4914122331915044,
+      "learning_rate": 3.7420661812774577e-06,
+      "loss": 2.479,
+      "step": 217
+    },
+    {
+      "epoch": 0.6241947029348605,
+      "grad_norm": 0.4835020063832526,
+      "learning_rate": 3.6938669623093086e-06,
+      "loss": 2.4775,
+      "step": 218
+    },
+    {
+      "epoch": 0.6270579813886901,
+      "grad_norm": 0.4819963834404957,
+      "learning_rate": 3.6457976592849753e-06,
+      "loss": 2.4627,
+      "step": 219
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 0.48578165660736744,
+      "learning_rate": 3.5978630534699873e-06,
+      "loss": 2.4921,
+      "step": 220
+    },
+    {
+      "epoch": 0.6327845382963493,
+      "grad_norm": 0.4946223923765296,
+      "learning_rate": 3.550067912732069e-06,
+      "loss": 2.4802,
+      "step": 221
+    },
+    {
+      "epoch": 0.635647816750179,
+      "grad_norm": 0.47731930944616413,
+      "learning_rate": 3.502416991066904e-06,
+      "loss": 2.4862,
+      "step": 222
+    },
+    {
+      "epoch": 0.6385110952040086,
+      "grad_norm": 0.46672416010636814,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 2.4746,
+      "step": 223
+    },
+    {
+      "epoch": 0.6413743736578382,
+      "grad_norm": 0.47432031556982895,
+      "learning_rate": 3.4075667487415785e-06,
+      "loss": 2.4461,
+      "step": 224
+    },
+    {
+      "epoch": 0.6442376521116678,
+      "grad_norm": 0.4613340476214188,
+      "learning_rate": 3.3603768624639786e-06,
+      "loss": 2.4734,
+      "step": 225
+    },
+    {
+      "epoch": 0.6471009305654974,
+      "grad_norm": 0.4879808421776038,
+      "learning_rate": 3.3133500630858507e-06,
+      "loss": 2.4458,
+      "step": 226
+    },
+    {
+      "epoch": 0.6499642090193272,
+      "grad_norm": 0.49504385746210705,
+      "learning_rate": 3.266491028178964e-06,
+      "loss": 2.4931,
+      "step": 227
+    },
+    {
+      "epoch": 0.6528274874731568,
+      "grad_norm": 0.46696567892600954,
+      "learning_rate": 3.219804418628216e-06,
+      "loss": 2.4582,
+      "step": 228
+    },
+    {
+      "epoch": 0.6556907659269864,
+      "grad_norm": 0.46371322697466877,
+      "learning_rate": 3.173294878168025e-06,
+      "loss": 2.4688,
+      "step": 229
+    },
+    {
+      "epoch": 0.658554044380816,
+      "grad_norm": 0.45817247273224015,
+      "learning_rate": 3.12696703292044e-06,
+      "loss": 2.4942,
+      "step": 230
+    },
+    {
+      "epoch": 0.6614173228346457,
+      "grad_norm": 0.47446326987653453,
+      "learning_rate": 3.0808254909349987e-06,
+      "loss": 2.4717,
+      "step": 231
+    },
+    {
+      "epoch": 0.6642806012884753,
+      "grad_norm": 0.46895233817717097,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 2.4737,
+      "step": 232
+    },
+    {
+      "epoch": 0.6671438797423049,
+      "grad_norm": 0.47218853082979256,
+      "learning_rate": 2.989119655837913e-06,
+      "loss": 2.4635,
+      "step": 233
+    },
+    {
+      "epoch": 0.6700071581961345,
+      "grad_norm": 0.4704459933176104,
+      "learning_rate": 2.9435644843469434e-06,
+      "loss": 2.4932,
+      "step": 234
+    },
+    {
+      "epoch": 0.6728704366499642,
+      "grad_norm": 0.4649089431955579,
+      "learning_rate": 2.8982138584521734e-06,
+      "loss": 2.4827,
+      "step": 235
+    },
+    {
+      "epoch": 0.6757337151037939,
+      "grad_norm": 0.47709482926494806,
+      "learning_rate": 2.853072289002954e-06,
+      "loss": 2.465,
+      "step": 236
+    },
+    {
+      "epoch": 0.6785969935576235,
+      "grad_norm": 0.4637487649689432,
+      "learning_rate": 2.8081442660546126e-06,
+      "loss": 2.4768,
+      "step": 237
+    },
+    {
+      "epoch": 0.6814602720114531,
+      "grad_norm": 0.46866785131238103,
+      "learning_rate": 2.7634342584218364e-06,
+      "loss": 2.4784,
+      "step": 238
+    },
+    {
+      "epoch": 0.6843235504652827,
+      "grad_norm": 0.4894597393103176,
+      "learning_rate": 2.718946713234185e-06,
+      "loss": 2.5016,
+      "step": 239
+    },
+    {
+      "epoch": 0.6871868289191124,
+      "grad_norm": 0.4667475078124399,
+      "learning_rate": 2.674686055493748e-06,
+      "loss": 2.5086,
+      "step": 240
+    },
+    {
+      "epoch": 0.690050107372942,
+      "grad_norm": 0.4696416005150825,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 2.4469,
+      "step": 241
+    },
+    {
+      "epoch": 0.6929133858267716,
+      "grad_norm": 0.46824017819944164,
+      "learning_rate": 2.5868629890869467e-06,
+      "loss": 2.4876,
+      "step": 242
+    },
+    {
+      "epoch": 0.6957766642806013,
+      "grad_norm": 0.46557559754046707,
+      "learning_rate": 2.543309315837444e-06,
+      "loss": 2.4287,
+      "step": 243
+    },
+    {
+      "epoch": 0.698639942734431,
+      "grad_norm": 0.4762974026954119,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 2.5047,
+      "step": 244
+    },
+    {
+      "epoch": 0.7015032211882606,
+      "grad_norm": 0.4644049626901058,
+      "learning_rate": 2.4569393493828433e-06,
+      "loss": 2.457,
+      "step": 245
+    },
+    {
+      "epoch": 0.7043664996420902,
+      "grad_norm": 0.4731570583945912,
+      "learning_rate": 2.4141316470604362e-06,
+      "loss": 2.4875,
+      "step": 246
+    },
+    {
+      "epoch": 0.7072297780959198,
+      "grad_norm": 0.4652373549525223,
+      "learning_rate": 2.371581150947476e-06,
+      "loss": 2.501,
+      "step": 247
+    },
+    {
+      "epoch": 0.7100930565497494,
+      "grad_norm": 0.46149990291747417,
+      "learning_rate": 2.3292920933753566e-06,
+      "loss": 2.4767,
+      "step": 248
+    },
+    {
+      "epoch": 0.7129563350035791,
+      "grad_norm": 0.45894170076752305,
+      "learning_rate": 2.2872686806712037e-06,
+      "loss": 2.466,
+      "step": 249
+    },
+    {
+      "epoch": 0.7158196134574087,
+      "grad_norm": 0.4587340338845331,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 2.4843,
+      "step": 250
+    },
+    {
+      "epoch": 0.7186828919112384,
+      "grad_norm": 0.4568306102089786,
+      "learning_rate": 2.204035482646267e-06,
+      "loss": 2.4452,
+      "step": 251
+    },
+    {
+      "epoch": 0.721546170365068,
+      "grad_norm": 0.45503692900873527,
+      "learning_rate": 2.162833976206092e-06,
+      "loss": 2.4854,
+      "step": 252
+    },
+    {
+      "epoch": 0.7244094488188977,
+      "grad_norm": 0.45864934324739526,
+      "learning_rate": 2.1219146715716332e-06,
+      "loss": 2.5048,
+      "step": 253
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.4616476773972489,
+      "learning_rate": 2.081281638826052e-06,
+      "loss": 2.4602,
+      "step": 254
+    },
+    {
+      "epoch": 0.7301360057265569,
+      "grad_norm": 0.4691408422165569,
+      "learning_rate": 2.0409389195781627e-06,
+      "loss": 2.4943,
+      "step": 255
+    },
+    {
+      "epoch": 0.7329992841803865,
+      "grad_norm": 0.46727999266440634,
+      "learning_rate": 2.0008905265604316e-06,
+      "loss": 2.4899,
+      "step": 256
+    },
+    {
+      "epoch": 0.7358625626342162,
+      "grad_norm": 0.4751400894854323,
+      "learning_rate": 1.9611404432298505e-06,
+      "loss": 2.4554,
+      "step": 257
+    },
+    {
+      "epoch": 0.7387258410880458,
+      "grad_norm": 0.47283617833966596,
+      "learning_rate": 1.9216926233717087e-06,
+      "loss": 2.4631,
+      "step": 258
+    },
+    {
+      "epoch": 0.7415891195418755,
+      "grad_norm": 0.4579533439995314,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 2.4794,
+      "step": 259
+    },
+    {
+      "epoch": 0.7444523979957051,
+      "grad_norm": 0.46285462884634804,
+      "learning_rate": 1.843719438498806e-06,
+      "loss": 2.4447,
+      "step": 260
+    },
+    {
+      "epoch": 0.7473156764495347,
+      "grad_norm": 0.45609200392812344,
+      "learning_rate": 1.8052018291717216e-06,
+      "loss": 2.5097,
+      "step": 261
+    },
+    {
+      "epoch": 0.7501789549033644,
+      "grad_norm": 0.4736752845679603,
+      "learning_rate": 1.7670019939210025e-06,
+      "loss": 2.4632,
+      "step": 262
+    },
+    {
+      "epoch": 0.753042233357194,
+      "grad_norm": 0.47156563387390643,
+      "learning_rate": 1.7291237323348287e-06,
+      "loss": 2.4749,
+      "step": 263
+    },
+    {
+      "epoch": 0.7559055118110236,
+      "grad_norm": 0.46047471823042235,
+      "learning_rate": 1.6915708120157042e-06,
+      "loss": 2.4313,
+      "step": 264
+    },
+    {
+      "epoch": 0.7559055118110236,
+      "eval_loss": 2.936035633087158,
+      "eval_runtime": 15.4546,
+      "eval_samples_per_second": 14.106,
+      "eval_steps_per_second": 2.394,
+      "step": 264
+    },
+    {
+      "epoch": 0.7587687902648532,
+      "grad_norm": 0.46741816845331546,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 2.4685,
+      "step": 265
+    },
+    {
+      "epoch": 0.7616320687186829,
+      "grad_norm": 0.44870053167803253,
+      "learning_rate": 1.617455903414974e-06,
+      "loss": 2.4712,
+      "step": 266
+    },
+    {
+      "epoch": 0.7644953471725126,
+      "grad_norm": 0.4561531748512701,
+      "learning_rate": 1.5809012870533996e-06,
+      "loss": 2.4874,
+      "step": 267
+    },
+    {
+      "epoch": 0.7673586256263422,
+      "grad_norm": 0.45480554069330664,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 2.443,
+      "step": 268
+    },
+    {
+      "epoch": 0.7702219040801718,
+      "grad_norm": 0.46600032777395256,
+      "learning_rate": 1.5088159095696365e-06,
+      "loss": 2.5145,
+      "step": 269
+    },
+    {
+      "epoch": 0.7730851825340014,
+      "grad_norm": 0.48866030251102854,
+      "learning_rate": 1.4732923184979563e-06,
+      "loss": 2.4231,
+      "step": 270
+    },
+    {
+      "epoch": 0.7759484609878311,
+      "grad_norm": 0.48186026098585555,
+      "learning_rate": 1.438119515243277e-06,
+      "loss": 2.4738,
+      "step": 271
+    },
+    {
+      "epoch": 0.7788117394416607,
+      "grad_norm": 0.4589872555488135,
+      "learning_rate": 1.4033009983067454e-06,
+      "loss": 2.4859,
+      "step": 272
+    },
+    {
+      "epoch": 0.7816750178954903,
+      "grad_norm": 0.4459291232495709,
+      "learning_rate": 1.3688402309500353e-06,
+      "loss": 2.5005,
+      "step": 273
+    },
+    {
+      "epoch": 0.7845382963493199,
+      "grad_norm": 0.4513699250772011,
+      "learning_rate": 1.3347406408508695e-06,
+      "loss": 2.487,
+      "step": 274
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "grad_norm": 0.4567378969589174,
+      "learning_rate": 1.3010056197620813e-06,
+      "loss": 2.4573,
+      "step": 275
+    },
+    {
+      "epoch": 0.7902648532569793,
+      "grad_norm": 0.4692124594286597,
+      "learning_rate": 1.2676385231742493e-06,
+      "loss": 2.4628,
+      "step": 276
+    },
+    {
+      "epoch": 0.7931281317108089,
+      "grad_norm": 0.457853009198463,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 2.4425,
+      "step": 277
+    },
+    {
+      "epoch": 0.7959914101646385,
+      "grad_norm": 0.46355613438320215,
+      "learning_rate": 1.2020213421536103e-06,
+      "loss": 2.5078,
+      "step": 278
+    },
+    {
+      "epoch": 0.7988546886184682,
+      "grad_norm": 0.4560209731740047,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 2.4658,
+      "step": 279
+    },
+    {
+      "epoch": 0.8017179670722978,
+      "grad_norm": 0.45676904584836525,
+      "learning_rate": 1.137915203877003e-06,
+      "loss": 2.456,
+      "step": 280
+    },
+    {
+      "epoch": 0.8045812455261274,
+      "grad_norm": 0.454564657506919,
+      "learning_rate": 1.1064367698155303e-06,
+      "loss": 2.4476,
+      "step": 281
+    },
+    {
+      "epoch": 0.807444523979957,
+      "grad_norm": 0.46526091929632524,
+      "learning_rate": 1.0753456132573886e-06,
+      "loss": 2.478,
+      "step": 282
+    },
+    {
+      "epoch": 0.8103078024337866,
+      "grad_norm": 0.4552190309373214,
+      "learning_rate": 1.044644826718295e-06,
+      "loss": 2.4653,
+      "step": 283
+    },
+    {
+      "epoch": 0.8131710808876164,
+      "grad_norm": 0.46555915439648266,
+      "learning_rate": 1.0143374638853892e-06,
+      "loss": 2.4766,
+      "step": 284
+    },
+    {
+      "epoch": 0.816034359341446,
+      "grad_norm": 0.4572802006505305,
+      "learning_rate": 9.844265393134927e-07,
+      "loss": 2.4569,
+      "step": 285
+    },
+    {
+      "epoch": 0.8188976377952756,
+      "grad_norm": 0.4458605895386478,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 2.4695,
+      "step": 286
+    },
+    {
+      "epoch": 0.8217609162491052,
+      "grad_norm": 0.4591574303861129,
+      "learning_rate": 9.258058657152763e-07,
+      "loss": 2.4416,
+      "step": 287
+    },
+    {
+      "epoch": 0.8246241947029349,
+      "grad_norm": 0.45928170428426124,
+      "learning_rate": 8.971019474580428e-07,
+      "loss": 2.4722,
+      "step": 288
+    },
+    {
+      "epoch": 0.8274874731567645,
+      "grad_norm": 0.4546308467235846,
+      "learning_rate": 8.688061284200266e-07,
+      "loss": 2.4638,
+      "step": 289
+    },
+    {
+      "epoch": 0.8303507516105941,
+      "grad_norm": 0.46135706461175,
+      "learning_rate": 8.409212230756564e-07,
+      "loss": 2.4896,
+      "step": 290
+    },
+    {
+      "epoch": 0.8332140300644237,
+      "grad_norm": 0.4357442522497734,
+      "learning_rate": 8.134500050273841e-07,
+      "loss": 2.4886,
+      "step": 291
+    },
+    {
+      "epoch": 0.8360773085182533,
+      "grad_norm": 0.4563872305836051,
+      "learning_rate": 7.863952067298042e-07,
+      "loss": 2.4891,
+      "step": 292
+    },
+    {
+      "epoch": 0.8389405869720831,
+      "grad_norm": 0.4598435875124808,
+      "learning_rate": 7.597595192178702e-07,
+      "loss": 2.4513,
+      "step": 293
+    },
+    {
+      "epoch": 0.8418038654259127,
+      "grad_norm": 0.44658046634222204,
+      "learning_rate": 7.33545591839222e-07,
+      "loss": 2.4831,
+      "step": 294
+    },
+    {
+      "epoch": 0.8446671438797423,
+      "grad_norm": 0.44490014330370886,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 2.4633,
+      "step": 295
+    },
+    {
+      "epoch": 0.8475304223335719,
+      "grad_norm": 0.45416636123029175,
+      "learning_rate": 6.82393404858846e-07,
+      "loss": 2.4548,
+      "step": 296
+    },
+    {
+      "epoch": 0.8503937007874016,
+      "grad_norm": 0.49083956893955283,
+      "learning_rate": 6.574602331650559e-07,
+      "loss": 2.4829,
+      "step": 297
+    },
+    {
+      "epoch": 0.8532569792412312,
+      "grad_norm": 0.45761237430081714,
+      "learning_rate": 6.329589969143518e-07,
+      "loss": 2.4761,
+      "step": 298
+    },
+    {
+      "epoch": 0.8561202576950608,
+      "grad_norm": 0.46149826051853654,
+      "learning_rate": 6.088921331488568e-07,
+      "loss": 2.4669,
+      "step": 299
+    },
+    {
+      "epoch": 0.8589835361488904,
+      "grad_norm": 0.44852500170386056,
+      "learning_rate": 5.852620357053651e-07,
+      "loss": 2.4889,
+      "step": 300
+    },
+    {
+      "epoch": 0.8618468146027202,
+      "grad_norm": 0.44535055340755936,
+      "learning_rate": 5.620710549772295e-07,
+      "loss": 2.454,
+      "step": 301
+    },
+    {
+      "epoch": 0.8647100930565498,
+      "grad_norm": 0.4523724462946578,
+      "learning_rate": 5.393214976805833e-07,
+      "loss": 2.4829,
+      "step": 302
+    },
+    {
+      "epoch": 0.8675733715103794,
+      "grad_norm": 0.4512432935032381,
+      "learning_rate": 5.17015626624896e-07,
+      "loss": 2.4964,
+      "step": 303
+    },
+    {
+      "epoch": 0.870436649964209,
+      "grad_norm": 0.4502752764610012,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 2.4652,
+      "step": 304
+    },
+    {
+      "epoch": 0.8732999284180386,
+      "grad_norm": 0.4418666890355134,
+      "learning_rate": 4.737437735949263e-07,
+      "loss": 2.4771,
+      "step": 305
+    },
+    {
+      "epoch": 0.8761632068718683,
+      "grad_norm": 0.4661160898935762,
+      "learning_rate": 4.5278209570258914e-07,
+      "loss": 2.4867,
+      "step": 306
+    },
+    {
+      "epoch": 0.8790264853256979,
+      "grad_norm": 0.4611073292882843,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 2.4746,
+      "step": 307
+    },
+    {
+      "epoch": 0.8818897637795275,
+      "grad_norm": 0.4446102922832806,
+      "learning_rate": 4.122176618363305e-07,
+      "loss": 2.4695,
+      "step": 308
+    },
+    {
+      "epoch": 0.8847530422333572,
+      "grad_norm": 0.44729778668314735,
+      "learning_rate": 3.9261894064796136e-07,
+      "loss": 2.4678,
+      "step": 309
+    },
+    {
+      "epoch": 0.8876163206871869,
+      "grad_norm": 0.45295141361260305,
+      "learning_rate": 3.734784976300165e-07,
+      "loss": 2.4926,
+      "step": 310
+    },
+    {
+      "epoch": 0.8904795991410165,
+      "grad_norm": 0.46930631413078255,
+      "learning_rate": 3.5479823660748703e-07,
+      "loss": 2.4514,
+      "step": 311
+    },
+    {
+      "epoch": 0.8933428775948461,
+      "grad_norm": 0.4417853093677557,
+      "learning_rate": 3.365800156328619e-07,
+      "loss": 2.4905,
+      "step": 312
+    },
+    {
+      "epoch": 0.8962061560486757,
+      "grad_norm": 0.4440433821954867,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 2.4864,
+      "step": 313
+    },
+    {
+      "epoch": 0.8990694345025053,
+      "grad_norm": 0.45330282639589614,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 2.4328,
+      "step": 314
+    },
+    {
+      "epoch": 0.901932712956335,
+      "grad_norm": 0.44590581999226264,
+      "learning_rate": 2.847154830846971e-07,
+      "loss": 2.501,
+      "step": 315
+    },
+    {
+      "epoch": 0.9047959914101646,
+      "grad_norm": 0.4534475837301284,
+      "learning_rate": 2.6836308100417874e-07,
+      "loss": 2.4455,
+      "step": 316
+    },
+    {
+      "epoch": 0.9076592698639943,
+      "grad_norm": 0.4448096353367094,
+      "learning_rate": 2.524813163383683e-07,
+      "loss": 2.4311,
+      "step": 317
+    },
+    {
+      "epoch": 0.9105225483178239,
+      "grad_norm": 0.44389847976222563,
+      "learning_rate": 2.3707176878426886e-07,
+      "loss": 2.4872,
+      "step": 318
+    },
+    {
+      "epoch": 0.9133858267716536,
+      "grad_norm": 0.44380665859676643,
+      "learning_rate": 2.2213597106929608e-07,
+      "loss": 2.4491,
+      "step": 319
+    },
+    {
+      "epoch": 0.9162491052254832,
+      "grad_norm": 0.44824967084915274,
+      "learning_rate": 2.0767540879882143e-07,
+      "loss": 2.4336,
+      "step": 320
+    },
+    {
+      "epoch": 0.9191123836793128,
+      "grad_norm": 0.4615916047912525,
+      "learning_rate": 1.9369152030840553e-07,
+      "loss": 2.4893,
+      "step": 321
+    },
+    {
+      "epoch": 0.9219756621331424,
+      "grad_norm": 0.44637662830765845,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 2.4488,
+      "step": 322
+    },
+    {
+      "epoch": 0.9248389405869721,
+      "grad_norm": 0.446240721408501,
+      "learning_rate": 1.6715928080726417e-07,
+      "loss": 2.4527,
+      "step": 323
+    },
+    {
+      "epoch": 0.9277022190408017,
+      "grad_norm": 0.4560572613231896,
+      "learning_rate": 1.5461356885461077e-07,
+      "loss": 2.4604,
+      "step": 324
+    },
+    {
+      "epoch": 0.9305654974946314,
+      "grad_norm": 0.4314293357419993,
+      "learning_rate": 1.4254980853566248e-07,
+      "loss": 2.479,
+      "step": 325
+    },
+    {
+      "epoch": 0.933428775948461,
+      "grad_norm": 0.44433384067807596,
+      "learning_rate": 1.3096919978546842e-07,
+      "loss": 2.4698,
+      "step": 326
+    },
+    {
+      "epoch": 0.9362920544022906,
+      "grad_norm": 0.43730852720830754,
+      "learning_rate": 1.1987289448187777e-07,
+      "loss": 2.4865,
+      "step": 327
+    },
+    {
+      "epoch": 0.9391553328561203,
+      "grad_norm": 0.4284159960564044,
+      "learning_rate": 1.0926199633097156e-07,
+      "loss": 2.4316,
+      "step": 328
+    },
+    {
+      "epoch": 0.9420186113099499,
+      "grad_norm": 0.44571916504011744,
+      "learning_rate": 9.913756075728088e-08,
+      "loss": 2.5041,
+      "step": 329
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 0.45304237672597053,
+      "learning_rate": 8.950059479880591e-08,
+      "loss": 2.5114,
+      "step": 330
+    },
+    {
+      "epoch": 0.9477451682176091,
+      "grad_norm": 0.43598348530628495,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 2.5127,
+      "step": 331
+    },
+    {
+      "epoch": 0.9506084466714388,
+      "grad_norm": 0.4356879074001767,
+      "learning_rate": 7.169285735068531e-08,
+      "loss": 2.4692,
+      "step": 332
+    },
+    {
+      "epoch": 0.9534717251252685,
+      "grad_norm": 0.44682377084462166,
+      "learning_rate": 6.352385712702191e-08,
+      "loss": 2.4778,
+      "step": 333
+    },
+    {
+      "epoch": 0.9563350035790981,
+      "grad_norm": 0.4474749989010966,
+      "learning_rate": 5.584586887435739e-08,
+      "loss": 2.4738,
+      "step": 334
+    },
+    {
+      "epoch": 0.9591982820329277,
+      "grad_norm": 0.44254145584508675,
+      "learning_rate": 4.865965629214819e-08,
+      "loss": 2.4445,
+      "step": 335
+    },
+    {
+      "epoch": 0.9620615604867573,
+      "grad_norm": 0.4814270534171316,
+      "learning_rate": 4.196593416484873e-08,
+      "loss": 2.5038,
+      "step": 336
+    },
+    {
+      "epoch": 0.964924838940587,
+      "grad_norm": 0.4449207768038768,
+      "learning_rate": 3.576536829081323e-08,
+      "loss": 2.4704,
+      "step": 337
+    },
+    {
+      "epoch": 0.9677881173944166,
+      "grad_norm": 0.44401542703062347,
+      "learning_rate": 3.005857541607371e-08,
+      "loss": 2.5191,
+      "step": 338
+    },
+    {
+      "epoch": 0.9706513958482462,
+      "grad_norm": 0.43424375987912595,
+      "learning_rate": 2.4846123172992953e-08,
+      "loss": 2.4885,
+      "step": 339
+    },
+    {
+      "epoch": 0.9735146743020758,
+      "grad_norm": 0.4473592208860157,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 2.4681,
+      "step": 340
+    },
+    {
+      "epoch": 0.9763779527559056,
+      "grad_norm": 0.45638058238294077,
+      "learning_rate": 1.590626520904526e-08,
+      "loss": 2.4722,
+      "step": 341
+    },
+    {
+      "epoch": 0.9792412312097352,
+      "grad_norm": 0.4442471751823356,
+      "learning_rate": 1.2179748700879013e-08,
+      "loss": 2.4685,
+      "step": 342
+    },
+    {
+      "epoch": 0.9821045096635648,
+      "grad_norm": 0.44699422552952645,
+      "learning_rate": 8.949351161324227e-09,
+      "loss": 2.4736,
+      "step": 343
+    },
+    {
+      "epoch": 0.9849677881173944,
+      "grad_norm": 0.44843427084177795,
+      "learning_rate": 6.215393905388278e-09,
+      "loss": 2.4758,
+      "step": 344
+    },
+    {
+      "epoch": 0.9878310665712241,
+      "grad_norm": 0.4430207903952749,
+      "learning_rate": 3.978148869103748e-09,
+      "loss": 2.4823,
+      "step": 345
+    },
+    {
+      "epoch": 0.9906943450250537,
+      "grad_norm": 0.44535966484744366,
+      "learning_rate": 2.237838582483387e-09,
+      "loss": 2.4529,
+      "step": 346
+    },
+    {
+      "epoch": 0.9935576234788833,
+      "grad_norm": 0.43129364144349974,
+      "learning_rate": 9.946361473822664e-10,
+      "loss": 2.4717,
+      "step": 347
+    },
+    {
+      "epoch": 0.9964209019327129,
+      "grad_norm": 0.44688887849751735,
+      "learning_rate": 2.486652202848827e-10,
+      "loss": 2.4743,
+      "step": 348
+    },
+    {
+      "epoch": 0.9992841803865425,
+      "grad_norm": 0.44578455043995546,
+      "learning_rate": 0.0,
+      "loss": 2.5218,
+      "step": 349
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 349,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.4632318176290406e+17,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-349/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592fa413ce36c00588c414891e8d44bffe7432823a442a999ac046d72a5df0aa
+size 8120

checkpoint-349/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)