Training in progress, step 438, checkpoint

checkpoint-438/config.json

@@ -0,0 +1,35 @@
+{
+  "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": "4.50.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-438/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "transformers_version": "4.50.0"
+}

checkpoint-438/global_step438/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:a43769814a3308b584f132a572e22e2240646f5a317ad51d579e41b64add4a24
+size 6805132103

checkpoint-438/global_step438/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:e4526ce1be7a2dc39ab229450496672bc4c987e40c749a88f4b31403c1a0c0ab
+size 6805132103

checkpoint-438/global_step438/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc92ba273c0c912edc3c76f109a4c5d98caec9e09e7ae7e47fae5638a75bd308
+size 6805132103

checkpoint-438/global_step438/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ed836a039e0cddd869c06cf2566e73f1fba175258d9279954e3e2f41d7ee9b
+size 6805132103

checkpoint-438/global_step438/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac87b6c03870f087abdfab5b940f98290b3840938024a47a63c00a4d7ec50a08
+size 150245

checkpoint-438/global_step438/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f822abd1ade4efcb3a9caf5912613de4a9b11f8bb4fd9fc20d253403561265
+size 150245

checkpoint-438/global_step438/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2a6a9e6ca37b7de0111ff45b084aa8e6125d967c087387a18d090262e06ecc
+size 150245

checkpoint-438/global_step438/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd27ff62e3e79879f9b7ce183a56fe075b45d195dc13c1f9591bd24b12f1e696
+size 150245

checkpoint-438/latest

@@ -0,0 +1 @@
+global_step438

checkpoint-438/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221aa63db9c76391304ca725a72267401004695f7ec8ec4d6da33e6863b2f954
+size 4978354640

checkpoint-438/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d988f3434667798f2bc8a032d408fbc4c23887388481dcfc66df311421e4d8e
+size 4047172128

checkpoint-438/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-438/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d74de51245105e1fbf57a6707ef3538b353952485508f6e2f8f74dc5d479d4
+size 15024

checkpoint-438/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0617c9eb6cf7df57b2e0bb53cfe17c05f0910de56fe5b14427fe39ab54a44782
+size 15024

checkpoint-438/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed68a365057022897d9645ee60902a77102f43215dcdf2ddd5d3842b6a8446d8
+size 15024

checkpoint-438/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ebaa0c302cadbdfcd9f8ee2289e35ecf9c9fc8c9968fc0c05f100dac20c6b9
+size 15024

checkpoint-438/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30206bce991f7e89d3a39d1bea06326a1ac48bb7993c6d1e53747b612a1696f6
+size 1064

checkpoint-438/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-438/tokenizer.json

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

checkpoint-438/tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

checkpoint-438/trainer_state.json

@@ -0,0 +1,3196 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 37,
+  "global_step": 438,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00684931506849315,
+      "grad_norm": 6.781628733365755,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.5668,
+      "step": 1
+    },
+    {
+      "epoch": 0.00684931506849315,
+      "eval_loss": 2.5806074142456055,
+      "eval_runtime": 6.5651,
+      "eval_samples_per_second": 47.524,
+      "eval_steps_per_second": 3.046,
+      "step": 1
+    },
+    {
+      "epoch": 0.0136986301369863,
+      "grad_norm": 6.86619348498488,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.6025,
+      "step": 2
+    },
+    {
+      "epoch": 0.02054794520547945,
+      "grad_norm": 6.661187717958318,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.6316,
+      "step": 3
+    },
+    {
+      "epoch": 0.0273972602739726,
+      "grad_norm": 6.861551727845244,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.5801,
+      "step": 4
+    },
+    {
+      "epoch": 0.03424657534246575,
+      "grad_norm": 6.69117874797922,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.5335,
+      "step": 5
+    },
+    {
+      "epoch": 0.0410958904109589,
+      "grad_norm": 5.875380376726272,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 2.5241,
+      "step": 6
+    },
+    {
+      "epoch": 0.04794520547945205,
+      "grad_norm": 5.7978399687358255,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 2.4675,
+      "step": 7
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "grad_norm": 3.954765219007858,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 2.5811,
+      "step": 8
+    },
+    {
+      "epoch": 0.06164383561643835,
+      "grad_norm": 3.8615688857265162,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 2.4886,
+      "step": 9
+    },
+    {
+      "epoch": 0.0684931506849315,
+      "grad_norm": 3.1019873404806138,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.5337,
+      "step": 10
+    },
+    {
+      "epoch": 0.07534246575342465,
+      "grad_norm": 1.653000190239802,
+      "learning_rate": 2.2e-06,
+      "loss": 2.493,
+      "step": 11
+    },
+    {
+      "epoch": 0.0821917808219178,
+      "grad_norm": 1.6653405065701912,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 2.4862,
+      "step": 12
+    },
+    {
+      "epoch": 0.08904109589041095,
+      "grad_norm": 1.9193066268748051,
+      "learning_rate": 2.6e-06,
+      "loss": 2.5172,
+      "step": 13
+    },
+    {
+      "epoch": 0.0958904109589041,
+      "grad_norm": 1.4108595092412395,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 2.4411,
+      "step": 14
+    },
+    {
+      "epoch": 0.10273972602739725,
+      "grad_norm": 2.0335186868451713,
+      "learning_rate": 3e-06,
+      "loss": 2.5062,
+      "step": 15
+    },
+    {
+      "epoch": 0.1095890410958904,
+      "grad_norm": 1.9834579085161663,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 2.406,
+      "step": 16
+    },
+    {
+      "epoch": 0.11643835616438356,
+      "grad_norm": 1.7772826080066895,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 2.4608,
+      "step": 17
+    },
+    {
+      "epoch": 0.1232876712328767,
+      "grad_norm": 1.3962245609921142,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 2.3551,
+      "step": 18
+    },
+    {
+      "epoch": 0.13013698630136986,
+      "grad_norm": 1.190039563451697,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.4188,
+      "step": 19
+    },
+    {
+      "epoch": 0.136986301369863,
+      "grad_norm": 1.0109005845053234,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.4981,
+      "step": 20
+    },
+    {
+      "epoch": 0.14383561643835616,
+      "grad_norm": 1.1671978967591745,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 2.319,
+      "step": 21
+    },
+    {
+      "epoch": 0.1506849315068493,
+      "grad_norm": 1.0658877053683267,
+      "learning_rate": 4.4e-06,
+      "loss": 2.3067,
+      "step": 22
+    },
+    {
+      "epoch": 0.15753424657534246,
+      "grad_norm": 1.0578186226484172,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 2.4644,
+      "step": 23
+    },
+    {
+      "epoch": 0.1643835616438356,
+      "grad_norm": 0.9493987331518986,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 2.4179,
+      "step": 24
+    },
+    {
+      "epoch": 0.17123287671232876,
+      "grad_norm": 0.8876721262354197,
+      "learning_rate": 5e-06,
+      "loss": 2.4548,
+      "step": 25
+    },
+    {
+      "epoch": 0.1780821917808219,
+      "grad_norm": 0.9016648720831166,
+      "learning_rate": 4.999960519285878e-06,
+      "loss": 2.4203,
+      "step": 26
+    },
+    {
+      "epoch": 0.18493150684931506,
+      "grad_norm": 0.8594911221513131,
+      "learning_rate": 4.999842078390492e-06,
+      "loss": 2.4445,
+      "step": 27
+    },
+    {
+      "epoch": 0.1917808219178082,
+      "grad_norm": 0.8294185847621298,
+      "learning_rate": 4.9996446810547464e-06,
+      "loss": 2.4286,
+      "step": 28
+    },
+    {
+      "epoch": 0.19863013698630136,
+      "grad_norm": 0.829981358086145,
+      "learning_rate": 4.999368333513354e-06,
+      "loss": 2.3941,
+      "step": 29
+    },
+    {
+      "epoch": 0.2054794520547945,
+      "grad_norm": 0.8259390860771237,
+      "learning_rate": 4.99901304449463e-06,
+      "loss": 2.2873,
+      "step": 30
+    },
+    {
+      "epoch": 0.21232876712328766,
+      "grad_norm": 0.7780493406506134,
+      "learning_rate": 4.998578825220228e-06,
+      "loss": 2.4414,
+      "step": 31
+    },
+    {
+      "epoch": 0.2191780821917808,
+      "grad_norm": 0.8139739891431346,
+      "learning_rate": 4.9980656894047776e-06,
+      "loss": 2.426,
+      "step": 32
+    },
+    {
+      "epoch": 0.22602739726027396,
+      "grad_norm": 0.7967892569249858,
+      "learning_rate": 4.9974736532554525e-06,
+      "loss": 2.436,
+      "step": 33
+    },
+    {
+      "epoch": 0.2328767123287671,
+      "grad_norm": 0.7428657720222388,
+      "learning_rate": 4.996802735471461e-06,
+      "loss": 2.3185,
+      "step": 34
+    },
+    {
+      "epoch": 0.23972602739726026,
+      "grad_norm": 0.7499845773485214,
+      "learning_rate": 4.996052957243455e-06,
+      "loss": 2.4402,
+      "step": 35
+    },
+    {
+      "epoch": 0.2465753424657534,
+      "grad_norm": 0.7359931004513611,
+      "learning_rate": 4.995224342252856e-06,
+      "loss": 2.3618,
+      "step": 36
+    },
+    {
+      "epoch": 0.2534246575342466,
+      "grad_norm": 0.7073950294074208,
+      "learning_rate": 4.994316916671115e-06,
+      "loss": 2.455,
+      "step": 37
+    },
+    {
+      "epoch": 0.2534246575342466,
+      "eval_loss": 2.4449844360351562,
+      "eval_runtime": 5.9369,
+      "eval_samples_per_second": 52.553,
+      "eval_steps_per_second": 3.369,
+      "step": 37
+    },
+    {
+      "epoch": 0.2602739726027397,
+      "grad_norm": 0.6796375355430841,
+      "learning_rate": 4.993330709158879e-06,
+      "loss": 2.4065,
+      "step": 38
+    },
+    {
+      "epoch": 0.2671232876712329,
+      "grad_norm": 0.7250510771173403,
+      "learning_rate": 4.992265750865091e-06,
+      "loss": 2.4527,
+      "step": 39
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 0.739133472992406,
+      "learning_rate": 4.991122075426001e-06,
+      "loss": 2.4787,
+      "step": 40
+    },
+    {
+      "epoch": 0.2808219178082192,
+      "grad_norm": 0.7026481518003141,
+      "learning_rate": 4.989899718964108e-06,
+      "loss": 2.4464,
+      "step": 41
+    },
+    {
+      "epoch": 0.2876712328767123,
+      "grad_norm": 0.7034188124515799,
+      "learning_rate": 4.988598720087015e-06,
+      "loss": 2.4366,
+      "step": 42
+    },
+    {
+      "epoch": 0.2945205479452055,
+      "grad_norm": 0.7114177997700272,
+      "learning_rate": 4.9872191198862166e-06,
+      "loss": 2.3954,
+      "step": 43
+    },
+    {
+      "epoch": 0.3013698630136986,
+      "grad_norm": 0.7489678406861063,
+      "learning_rate": 4.985760961935791e-06,
+      "loss": 2.4092,
+      "step": 44
+    },
+    {
+      "epoch": 0.3082191780821918,
+      "grad_norm": 0.721624023056601,
+      "learning_rate": 4.984224292291035e-06,
+      "loss": 2.395,
+      "step": 45
+    },
+    {
+      "epoch": 0.3150684931506849,
+      "grad_norm": 0.6976242893548902,
+      "learning_rate": 4.982609159486998e-06,
+      "loss": 2.3621,
+      "step": 46
+    },
+    {
+      "epoch": 0.3219178082191781,
+      "grad_norm": 0.6979047705556364,
+      "learning_rate": 4.980915614536957e-06,
+      "loss": 2.3956,
+      "step": 47
+    },
+    {
+      "epoch": 0.3287671232876712,
+      "grad_norm": 0.6638188971561942,
+      "learning_rate": 4.979143710930805e-06,
+      "loss": 2.4447,
+      "step": 48
+    },
+    {
+      "epoch": 0.3356164383561644,
+      "grad_norm": 0.6550861221813643,
+      "learning_rate": 4.977293504633357e-06,
+      "loss": 2.3803,
+      "step": 49
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 0.6637160251936499,
+      "learning_rate": 4.975365054082586e-06,
+      "loss": 2.5123,
+      "step": 50
+    },
+    {
+      "epoch": 0.3493150684931507,
+      "grad_norm": 0.6657032864997552,
+      "learning_rate": 4.973358420187776e-06,
+      "loss": 2.4373,
+      "step": 51
+    },
+    {
+      "epoch": 0.3561643835616438,
+      "grad_norm": 0.6671449801461397,
+      "learning_rate": 4.971273666327598e-06,
+      "loss": 2.4515,
+      "step": 52
+    },
+    {
+      "epoch": 0.363013698630137,
+      "grad_norm": 0.6574174542409758,
+      "learning_rate": 4.969110858348108e-06,
+      "loss": 2.3797,
+      "step": 53
+    },
+    {
+      "epoch": 0.3698630136986301,
+      "grad_norm": 0.7037780907575699,
+      "learning_rate": 4.96687006456067e-06,
+      "loss": 2.4465,
+      "step": 54
+    },
+    {
+      "epoch": 0.3767123287671233,
+      "grad_norm": 0.7244746896553337,
+      "learning_rate": 4.964551355739796e-06,
+      "loss": 2.4265,
+      "step": 55
+    },
+    {
+      "epoch": 0.3835616438356164,
+      "grad_norm": 0.6581463626850778,
+      "learning_rate": 4.962154805120908e-06,
+      "loss": 2.4168,
+      "step": 56
+    },
+    {
+      "epoch": 0.3904109589041096,
+      "grad_norm": 0.6289298559777078,
+      "learning_rate": 4.959680488398031e-06,
+      "loss": 2.3328,
+      "step": 57
+    },
+    {
+      "epoch": 0.3972602739726027,
+      "grad_norm": 0.724536921071452,
+      "learning_rate": 4.957128483721398e-06,
+      "loss": 2.4319,
+      "step": 58
+    },
+    {
+      "epoch": 0.4041095890410959,
+      "grad_norm": 0.7119106876660016,
+      "learning_rate": 4.9544988716949825e-06,
+      "loss": 2.4339,
+      "step": 59
+    },
+    {
+      "epoch": 0.410958904109589,
+      "grad_norm": 0.6561228716087687,
+      "learning_rate": 4.951791735373953e-06,
+      "loss": 2.4057,
+      "step": 60
+    },
+    {
+      "epoch": 0.4178082191780822,
+      "grad_norm": 0.7138586667149742,
+      "learning_rate": 4.949007160262049e-06,
+      "loss": 2.3573,
+      "step": 61
+    },
+    {
+      "epoch": 0.4246575342465753,
+      "grad_norm": 0.6884519352750037,
+      "learning_rate": 4.946145234308884e-06,
+      "loss": 2.3747,
+      "step": 62
+    },
+    {
+      "epoch": 0.4315068493150685,
+      "grad_norm": 0.7403756155139569,
+      "learning_rate": 4.943206047907159e-06,
+      "loss": 2.2729,
+      "step": 63
+    },
+    {
+      "epoch": 0.4383561643835616,
+      "grad_norm": 0.6656934708441304,
+      "learning_rate": 4.940189693889819e-06,
+      "loss": 2.3805,
+      "step": 64
+    },
+    {
+      "epoch": 0.4452054794520548,
+      "grad_norm": 0.7251476112884715,
+      "learning_rate": 4.937096267527111e-06,
+      "loss": 2.3104,
+      "step": 65
+    },
+    {
+      "epoch": 0.4520547945205479,
+      "grad_norm": 0.6921252166237588,
+      "learning_rate": 4.9339258665235815e-06,
+      "loss": 2.3499,
+      "step": 66
+    },
+    {
+      "epoch": 0.4589041095890411,
+      "grad_norm": 0.685877730442195,
+      "learning_rate": 4.930678591014986e-06,
+      "loss": 2.4331,
+      "step": 67
+    },
+    {
+      "epoch": 0.4657534246575342,
+      "grad_norm": 0.6641111783418014,
+      "learning_rate": 4.927354543565131e-06,
+      "loss": 2.3789,
+      "step": 68
+    },
+    {
+      "epoch": 0.4726027397260274,
+      "grad_norm": 0.6657747916085803,
+      "learning_rate": 4.9239538291626285e-06,
+      "loss": 2.4542,
+      "step": 69
+    },
+    {
+      "epoch": 0.4794520547945205,
+      "grad_norm": 0.6544468951826022,
+      "learning_rate": 4.920476555217586e-06,
+      "loss": 2.4277,
+      "step": 70
+    },
+    {
+      "epoch": 0.4863013698630137,
+      "grad_norm": 0.6670629357129911,
+      "learning_rate": 4.91692283155821e-06,
+      "loss": 2.3881,
+      "step": 71
+    },
+    {
+      "epoch": 0.4931506849315068,
+      "grad_norm": 0.6559422824562596,
+      "learning_rate": 4.913292770427338e-06,
+      "loss": 2.4225,
+      "step": 72
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6786459570539399,
+      "learning_rate": 4.909586486478897e-06,
+      "loss": 2.4963,
+      "step": 73
+    },
+    {
+      "epoch": 0.5068493150684932,
+      "grad_norm": 0.6892419553245916,
+      "learning_rate": 4.905804096774274e-06,
+      "loss": 2.4115,
+      "step": 74
+    },
+    {
+      "epoch": 0.5068493150684932,
+      "eval_loss": 2.4323267936706543,
+      "eval_runtime": 6.0665,
+      "eval_samples_per_second": 51.43,
+      "eval_steps_per_second": 3.297,
+      "step": 74
+    },
+    {
+      "epoch": 0.5136986301369864,
+      "grad_norm": 0.6768758807890537,
+      "learning_rate": 4.901945720778627e-06,
+      "loss": 2.3938,
+      "step": 75
+    },
+    {
+      "epoch": 0.5205479452054794,
+      "grad_norm": 0.7339799079732157,
+      "learning_rate": 4.898011480357109e-06,
+      "loss": 2.2883,
+      "step": 76
+    },
+    {
+      "epoch": 0.5273972602739726,
+      "grad_norm": 0.7397662592480156,
+      "learning_rate": 4.894001499771015e-06,
+      "loss": 2.4598,
+      "step": 77
+    },
+    {
+      "epoch": 0.5342465753424658,
+      "grad_norm": 0.6819769884160725,
+      "learning_rate": 4.889915905673865e-06,
+      "loss": 2.4188,
+      "step": 78
+    },
+    {
+      "epoch": 0.541095890410959,
+      "grad_norm": 0.6772539201070739,
+      "learning_rate": 4.885754827107395e-06,
+      "loss": 2.4142,
+      "step": 79
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 0.659763812226515,
+      "learning_rate": 4.88151839549749e-06,
+      "loss": 2.298,
+      "step": 80
+    },
+    {
+      "epoch": 0.5547945205479452,
+      "grad_norm": 0.7286093280405468,
+      "learning_rate": 4.877206744650024e-06,
+      "loss": 2.3898,
+      "step": 81
+    },
+    {
+      "epoch": 0.5616438356164384,
+      "grad_norm": 0.6986932306550346,
+      "learning_rate": 4.8728200107466415e-06,
+      "loss": 2.3598,
+      "step": 82
+    },
+    {
+      "epoch": 0.5684931506849316,
+      "grad_norm": 0.6842367412456468,
+      "learning_rate": 4.868358332340451e-06,
+      "loss": 2.3763,
+      "step": 83
+    },
+    {
+      "epoch": 0.5753424657534246,
+      "grad_norm": 0.6724304892107736,
+      "learning_rate": 4.863821850351655e-06,
+      "loss": 2.4028,
+      "step": 84
+    },
+    {
+      "epoch": 0.5821917808219178,
+      "grad_norm": 0.6674281958373836,
+      "learning_rate": 4.859210708063091e-06,
+      "loss": 2.4226,
+      "step": 85
+    },
+    {
+      "epoch": 0.589041095890411,
+      "grad_norm": 0.6761850508539816,
+      "learning_rate": 4.854525051115711e-06,
+      "loss": 2.2755,
+      "step": 86
+    },
+    {
+      "epoch": 0.5958904109589042,
+      "grad_norm": 0.7049437160925219,
+      "learning_rate": 4.8497650275039795e-06,
+      "loss": 2.3633,
+      "step": 87
+    },
+    {
+      "epoch": 0.6027397260273972,
+      "grad_norm": 0.6675473282240035,
+      "learning_rate": 4.844930787571204e-06,
+      "loss": 2.4161,
+      "step": 88
+    },
+    {
+      "epoch": 0.6095890410958904,
+      "grad_norm": 0.6893380001896178,
+      "learning_rate": 4.84002248400478e-06,
+      "loss": 2.3261,
+      "step": 89
+    },
+    {
+      "epoch": 0.6164383561643836,
+      "grad_norm": 0.6557076444481973,
+      "learning_rate": 4.835040271831371e-06,
+      "loss": 2.4113,
+      "step": 90
+    },
+    {
+      "epoch": 0.6232876712328768,
+      "grad_norm": 0.7106326693649547,
+      "learning_rate": 4.829984308412011e-06,
+      "loss": 2.3468,
+      "step": 91
+    },
+    {
+      "epoch": 0.6301369863013698,
+      "grad_norm": 0.6780886154634945,
+      "learning_rate": 4.82485475343714e-06,
+      "loss": 2.4227,
+      "step": 92
+    },
+    {
+      "epoch": 0.636986301369863,
+      "grad_norm": 0.6848177542457299,
+      "learning_rate": 4.819651768921552e-06,
+      "loss": 2.4455,
+      "step": 93
+    },
+    {
+      "epoch": 0.6438356164383562,
+      "grad_norm": 0.6537386212526299,
+      "learning_rate": 4.814375519199281e-06,
+      "loss": 2.359,
+      "step": 94
+    },
+    {
+      "epoch": 0.6506849315068494,
+      "grad_norm": 0.692282068736651,
+      "learning_rate": 4.809026170918414e-06,
+      "loss": 2.4523,
+      "step": 95
+    },
+    {
+      "epoch": 0.6575342465753424,
+      "grad_norm": 0.6623529936148479,
+      "learning_rate": 4.803603893035822e-06,
+      "loss": 2.4321,
+      "step": 96
+    },
+    {
+      "epoch": 0.6643835616438356,
+      "grad_norm": 0.6842008308899095,
+      "learning_rate": 4.798108856811828e-06,
+      "loss": 2.415,
+      "step": 97
+    },
+    {
+      "epoch": 0.6712328767123288,
+      "grad_norm": 0.6761407885852002,
+      "learning_rate": 4.7925412358047965e-06,
+      "loss": 2.4099,
+      "step": 98
+    },
+    {
+      "epoch": 0.678082191780822,
+      "grad_norm": 0.695106737467069,
+      "learning_rate": 4.786901205865647e-06,
+      "loss": 2.3944,
+      "step": 99
+    },
+    {
+      "epoch": 0.684931506849315,
+      "grad_norm": 0.7154498681645167,
+      "learning_rate": 4.781188945132311e-06,
+      "loss": 2.4261,
+      "step": 100
+    },
+    {
+      "epoch": 0.6917808219178082,
+      "grad_norm": 0.708416595063437,
+      "learning_rate": 4.775404634024093e-06,
+      "loss": 2.4236,
+      "step": 101
+    },
+    {
+      "epoch": 0.6986301369863014,
+      "grad_norm": 0.6561586213988884,
+      "learning_rate": 4.769548455235979e-06,
+      "loss": 2.2712,
+      "step": 102
+    },
+    {
+      "epoch": 0.7054794520547946,
+      "grad_norm": 0.710907523788328,
+      "learning_rate": 4.763620593732867e-06,
+      "loss": 2.3401,
+      "step": 103
+    },
+    {
+      "epoch": 0.7123287671232876,
+      "grad_norm": 0.6765968692107874,
+      "learning_rate": 4.75762123674372e-06,
+      "loss": 2.4381,
+      "step": 104
+    },
+    {
+      "epoch": 0.7191780821917808,
+      "grad_norm": 0.9946667705374828,
+      "learning_rate": 4.751550573755658e-06,
+      "loss": 2.4825,
+      "step": 105
+    },
+    {
+      "epoch": 0.726027397260274,
+      "grad_norm": 0.6808703038492471,
+      "learning_rate": 4.745408796507968e-06,
+      "loss": 2.4417,
+      "step": 106
+    },
+    {
+      "epoch": 0.7328767123287672,
+      "grad_norm": 0.6511402815615133,
+      "learning_rate": 4.73919609898605e-06,
+      "loss": 2.412,
+      "step": 107
+    },
+    {
+      "epoch": 0.7397260273972602,
+      "grad_norm": 0.6806168774586489,
+      "learning_rate": 4.7329126774152945e-06,
+      "loss": 2.4047,
+      "step": 108
+    },
+    {
+      "epoch": 0.7465753424657534,
+      "grad_norm": 0.6581235881106364,
+      "learning_rate": 4.726558730254876e-06,
+      "loss": 2.3624,
+      "step": 109
+    },
+    {
+      "epoch": 0.7534246575342466,
+      "grad_norm": 0.6858279965463718,
+      "learning_rate": 4.720134458191494e-06,
+      "loss": 2.4046,
+      "step": 110
+    },
+    {
+      "epoch": 0.7602739726027398,
+      "grad_norm": 0.7044328584380498,
+      "learning_rate": 4.7136400641330245e-06,
+      "loss": 2.3298,
+      "step": 111
+    },
+    {
+      "epoch": 0.7602739726027398,
+      "eval_loss": 2.422318935394287,
+      "eval_runtime": 6.1327,
+      "eval_samples_per_second": 50.874,
+      "eval_steps_per_second": 3.261,
+      "step": 111
+    },
+    {
+      "epoch": 0.7671232876712328,
+      "grad_norm": 0.6949341182078216,
+      "learning_rate": 4.707075753202123e-06,
+      "loss": 2.4219,
+      "step": 112
+    },
+    {
+      "epoch": 0.773972602739726,
+      "grad_norm": 0.6883254066631505,
+      "learning_rate": 4.700441732729733e-06,
+      "loss": 2.4841,
+      "step": 113
+    },
+    {
+      "epoch": 0.7808219178082192,
+      "grad_norm": 0.688766337379056,
+      "learning_rate": 4.693738212248549e-06,
+      "loss": 2.3722,
+      "step": 114
+    },
+    {
+      "epoch": 0.7876712328767124,
+      "grad_norm": 0.6887580535922757,
+      "learning_rate": 4.68696540348639e-06,
+      "loss": 2.3637,
+      "step": 115
+    },
+    {
+      "epoch": 0.7945205479452054,
+      "grad_norm": 0.6719005239018524,
+      "learning_rate": 4.68012352035952e-06,
+      "loss": 2.4465,
+      "step": 116
+    },
+    {
+      "epoch": 0.8013698630136986,
+      "grad_norm": 0.6327678432767432,
+      "learning_rate": 4.673212778965881e-06,
+      "loss": 2.4219,
+      "step": 117
+    },
+    {
+      "epoch": 0.8082191780821918,
+      "grad_norm": 0.6572338268581427,
+      "learning_rate": 4.66623339757828e-06,
+      "loss": 2.4384,
+      "step": 118
+    },
+    {
+      "epoch": 0.815068493150685,
+      "grad_norm": 0.6774201762455547,
+      "learning_rate": 4.659185596637485e-06,
+      "loss": 2.4289,
+      "step": 119
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 0.6765522988548955,
+      "learning_rate": 4.652069598745267e-06,
+      "loss": 2.3849,
+      "step": 120
+    },
+    {
+      "epoch": 0.8287671232876712,
+      "grad_norm": 0.6553606050310139,
+      "learning_rate": 4.644885628657369e-06,
+      "loss": 2.3953,
+      "step": 121
+    },
+    {
+      "epoch": 0.8356164383561644,
+      "grad_norm": 0.6817645269442179,
+      "learning_rate": 4.637633913276406e-06,
+      "loss": 2.4534,
+      "step": 122
+    },
+    {
+      "epoch": 0.8424657534246576,
+      "grad_norm": 0.6842353980823837,
+      "learning_rate": 4.630314681644701e-06,
+      "loss": 2.3376,
+      "step": 123
+    },
+    {
+      "epoch": 0.8493150684931506,
+      "grad_norm": 0.6938393939968492,
+      "learning_rate": 4.622928164937046e-06,
+      "loss": 2.3795,
+      "step": 124
+    },
+    {
+      "epoch": 0.8561643835616438,
+      "grad_norm": 0.6503903813017006,
+      "learning_rate": 4.615474596453406e-06,
+      "loss": 2.3801,
+      "step": 125
+    },
+    {
+      "epoch": 0.863013698630137,
+      "grad_norm": 0.6690065166974256,
+      "learning_rate": 4.607954211611543e-06,
+      "loss": 2.4771,
+      "step": 126
+    },
+    {
+      "epoch": 0.8698630136986302,
+      "grad_norm": 0.6565369111054283,
+      "learning_rate": 4.600367247939592e-06,
+      "loss": 2.4468,
+      "step": 127
+    },
+    {
+      "epoch": 0.8767123287671232,
+      "grad_norm": 0.6590600861747526,
+      "learning_rate": 4.5927139450685455e-06,
+      "loss": 2.2973,
+      "step": 128
+    },
+    {
+      "epoch": 0.8835616438356164,
+      "grad_norm": 0.6642768664806619,
+      "learning_rate": 4.584994544724695e-06,
+      "loss": 2.4463,
+      "step": 129
+    },
+    {
+      "epoch": 0.8904109589041096,
+      "grad_norm": 0.7254289901639452,
+      "learning_rate": 4.577209290721991e-06,
+      "loss": 2.2925,
+      "step": 130
+    },
+    {
+      "epoch": 0.8972602739726028,
+      "grad_norm": 0.6264601593599859,
+      "learning_rate": 4.569358428954343e-06,
+      "loss": 2.3624,
+      "step": 131
+    },
+    {
+      "epoch": 0.9041095890410958,
+      "grad_norm": 0.6932555262208767,
+      "learning_rate": 4.561442207387854e-06,
+      "loss": 2.3315,
+      "step": 132
+    },
+    {
+      "epoch": 0.910958904109589,
+      "grad_norm": 0.6857220601161248,
+      "learning_rate": 4.55346087605299e-06,
+      "loss": 2.372,
+      "step": 133
+    },
+    {
+      "epoch": 0.9178082191780822,
+      "grad_norm": 0.701001912101975,
+      "learning_rate": 4.5454146870366775e-06,
+      "loss": 2.4026,
+      "step": 134
+    },
+    {
+      "epoch": 0.9246575342465754,
+      "grad_norm": 0.6340272298295848,
+      "learning_rate": 4.537303894474349e-06,
+      "loss": 2.4131,
+      "step": 135
+    },
+    {
+      "epoch": 0.9315068493150684,
+      "grad_norm": 0.6136778043717291,
+      "learning_rate": 4.529128754541909e-06,
+      "loss": 2.297,
+      "step": 136
+    },
+    {
+      "epoch": 0.9383561643835616,
+      "grad_norm": 0.6322021005066626,
+      "learning_rate": 4.5208895254476495e-06,
+      "loss": 2.4084,
+      "step": 137
+    },
+    {
+      "epoch": 0.9452054794520548,
+      "grad_norm": 0.6445887057946764,
+      "learning_rate": 4.512586467424087e-06,
+      "loss": 2.3645,
+      "step": 138
+    },
+    {
+      "epoch": 0.952054794520548,
+      "grad_norm": 0.7062860383104262,
+      "learning_rate": 4.504219842719752e-06,
+      "loss": 2.3655,
+      "step": 139
+    },
+    {
+      "epoch": 0.958904109589041,
+      "grad_norm": 0.6781212322165483,
+      "learning_rate": 4.4957899155908954e-06,
+      "loss": 2.4285,
+      "step": 140
+    },
+    {
+      "epoch": 0.9657534246575342,
+      "grad_norm": 0.6678298874200482,
+      "learning_rate": 4.487296952293156e-06,
+      "loss": 2.38,
+      "step": 141
+    },
+    {
+      "epoch": 0.9726027397260274,
+      "grad_norm": 0.6575931921755482,
+      "learning_rate": 4.478741221073136e-06,
+      "loss": 2.4094,
+      "step": 142
+    },
+    {
+      "epoch": 0.9794520547945206,
+      "grad_norm": 0.6868011511324458,
+      "learning_rate": 4.470122992159938e-06,
+      "loss": 2.4096,
+      "step": 143
+    },
+    {
+      "epoch": 0.9863013698630136,
+      "grad_norm": 0.6854773154104912,
+      "learning_rate": 4.461442537756629e-06,
+      "loss": 2.4249,
+      "step": 144
+    },
+    {
+      "epoch": 0.9931506849315068,
+      "grad_norm": 0.708510432833667,
+      "learning_rate": 4.452700132031639e-06,
+      "loss": 2.3724,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6566297487438831,
+      "learning_rate": 4.443896051110105e-06,
+      "loss": 2.391,
+      "step": 146
+    },
+    {
+      "epoch": 1.0068493150684932,
+      "grad_norm": 0.7629369425964684,
+      "learning_rate": 4.435030573065148e-06,
+      "loss": 2.3448,
+      "step": 147
+    },
+    {
+      "epoch": 1.0136986301369864,
+      "grad_norm": 0.7384812144528767,
+      "learning_rate": 4.426103977909094e-06,
+      "loss": 2.322,
+      "step": 148
+    },
+    {
+      "epoch": 1.0136986301369864,
+      "eval_loss": 2.417771339416504,
+      "eval_runtime": 53.3919,
+      "eval_samples_per_second": 5.844,
+      "eval_steps_per_second": 0.375,
+      "step": 148
+    },
+    {
+      "epoch": 1.0205479452054795,
+      "grad_norm": 0.6662500395219653,
+      "learning_rate": 4.417116547584621e-06,
+      "loss": 2.35,
+      "step": 149
+    },
+    {
+      "epoch": 1.0273972602739727,
+      "grad_norm": 0.6789888617564587,
+      "learning_rate": 4.408068565955864e-06,
+      "loss": 2.3845,
+      "step": 150
+    },
+    {
+      "epoch": 1.0342465753424657,
+      "grad_norm": 0.6998134909721523,
+      "learning_rate": 4.398960318799446e-06,
+      "loss": 2.35,
+      "step": 151
+    },
+    {
+      "epoch": 1.0410958904109588,
+      "grad_norm": 0.7216093013270933,
+      "learning_rate": 4.389792093795444e-06,
+      "loss": 2.3223,
+      "step": 152
+    },
+    {
+      "epoch": 1.047945205479452,
+      "grad_norm": 0.7403493735812074,
+      "learning_rate": 4.380564180518318e-06,
+      "loss": 2.3253,
+      "step": 153
+    },
+    {
+      "epoch": 1.0547945205479452,
+      "grad_norm": 0.7218865625666383,
+      "learning_rate": 4.3712768704277535e-06,
+      "loss": 2.3106,
+      "step": 154
+    },
+    {
+      "epoch": 1.0616438356164384,
+      "grad_norm": 0.7197974746780744,
+      "learning_rate": 4.361930456859455e-06,
+      "loss": 2.3033,
+      "step": 155
+    },
+    {
+      "epoch": 1.0684931506849316,
+      "grad_norm": 0.7249006057182749,
+      "learning_rate": 4.35252523501589e-06,
+      "loss": 2.3888,
+      "step": 156
+    },
+    {
+      "epoch": 1.0753424657534247,
+      "grad_norm": 0.7037919961575326,
+      "learning_rate": 4.343061501956959e-06,
+      "loss": 2.3402,
+      "step": 157
+    },
+    {
+      "epoch": 1.0821917808219177,
+      "grad_norm": 0.6996471940866854,
+      "learning_rate": 4.3335395565906115e-06,
+      "loss": 2.3194,
+      "step": 158
+    },
+    {
+      "epoch": 1.0890410958904109,
+      "grad_norm": 0.717826362193492,
+      "learning_rate": 4.323959699663412e-06,
+      "loss": 2.3852,
+      "step": 159
+    },
+    {
+      "epoch": 1.095890410958904,
+      "grad_norm": 0.708765230517044,
+      "learning_rate": 4.314322233751034e-06,
+      "loss": 2.3206,
+      "step": 160
+    },
+    {
+      "epoch": 1.1027397260273972,
+      "grad_norm": 0.6776217729604187,
+      "learning_rate": 4.304627463248706e-06,
+      "loss": 2.3081,
+      "step": 161
+    },
+    {
+      "epoch": 1.1095890410958904,
+      "grad_norm": 0.6853081994090057,
+      "learning_rate": 4.294875694361599e-06,
+      "loss": 2.3176,
+      "step": 162
+    },
+    {
+      "epoch": 1.1164383561643836,
+      "grad_norm": 0.6830768891525606,
+      "learning_rate": 4.285067235095152e-06,
+      "loss": 2.3364,
+      "step": 163
+    },
+    {
+      "epoch": 1.1232876712328768,
+      "grad_norm": 0.7089445206356011,
+      "learning_rate": 4.275202395245346e-06,
+      "loss": 2.3418,
+      "step": 164
+    },
+    {
+      "epoch": 1.13013698630137,
+      "grad_norm": 0.7823709313759815,
+      "learning_rate": 4.26528148638892e-06,
+      "loss": 2.3798,
+      "step": 165
+    },
+    {
+      "epoch": 1.1369863013698631,
+      "grad_norm": 0.6709932434280309,
+      "learning_rate": 4.255304821873526e-06,
+      "loss": 2.2267,
+      "step": 166
+    },
+    {
+      "epoch": 1.143835616438356,
+      "grad_norm": 0.6628107638339615,
+      "learning_rate": 4.245272716807834e-06,
+      "loss": 2.3308,
+      "step": 167
+    },
+    {
+      "epoch": 1.1506849315068493,
+      "grad_norm": 0.7184114487855815,
+      "learning_rate": 4.2351854880515856e-06,
+      "loss": 2.3017,
+      "step": 168
+    },
+    {
+      "epoch": 1.1575342465753424,
+      "grad_norm": 0.7166834764618115,
+      "learning_rate": 4.225043454205573e-06,
+      "loss": 2.3551,
+      "step": 169
+    },
+    {
+      "epoch": 1.1643835616438356,
+      "grad_norm": 0.7234116110718222,
+      "learning_rate": 4.2148469356015895e-06,
+      "loss": 2.3205,
+      "step": 170
+    },
+    {
+      "epoch": 1.1712328767123288,
+      "grad_norm": 0.6873414003582445,
+      "learning_rate": 4.204596254292303e-06,
+      "loss": 2.3675,
+      "step": 171
+    },
+    {
+      "epoch": 1.178082191780822,
+      "grad_norm": 0.7161572137012578,
+      "learning_rate": 4.194291734041088e-06,
+      "loss": 2.2708,
+      "step": 172
+    },
+    {
+      "epoch": 1.1849315068493151,
+      "grad_norm": 0.7142712637206968,
+      "learning_rate": 4.183933700311801e-06,
+      "loss": 2.2617,
+      "step": 173
+    },
+    {
+      "epoch": 1.191780821917808,
+      "grad_norm": 0.698584695168926,
+      "learning_rate": 4.173522480258494e-06,
+      "loss": 2.3686,
+      "step": 174
+    },
+    {
+      "epoch": 1.1986301369863013,
+      "grad_norm": 0.7275575279831493,
+      "learning_rate": 4.163058402715092e-06,
+      "loss": 2.3088,
+      "step": 175
+    },
+    {
+      "epoch": 1.2054794520547945,
+      "grad_norm": 0.7066892597231554,
+      "learning_rate": 4.152541798184995e-06,
+      "loss": 2.3273,
+      "step": 176
+    },
+    {
+      "epoch": 1.2123287671232876,
+      "grad_norm": 0.6692377666271583,
+      "learning_rate": 4.141972998830651e-06,
+      "loss": 2.368,
+      "step": 177
+    },
+    {
+      "epoch": 1.2191780821917808,
+      "grad_norm": 0.7519738253706634,
+      "learning_rate": 4.1313523384630565e-06,
+      "loss": 2.2878,
+      "step": 178
+    },
+    {
+      "epoch": 1.226027397260274,
+      "grad_norm": 0.7029718569317863,
+      "learning_rate": 4.120680152531214e-06,
+      "loss": 2.2833,
+      "step": 179
+    },
+    {
+      "epoch": 1.2328767123287672,
+      "grad_norm": 0.7334026090190444,
+      "learning_rate": 4.109956778111544e-06,
+      "loss": 2.3322,
+      "step": 180
+    },
+    {
+      "epoch": 1.2397260273972603,
+      "grad_norm": 0.6951014303600972,
+      "learning_rate": 4.099182553897228e-06,
+      "loss": 2.2781,
+      "step": 181
+    },
+    {
+      "epoch": 1.2465753424657535,
+      "grad_norm": 0.6885637550568241,
+      "learning_rate": 4.088357820187521e-06,
+      "loss": 2.2814,
+      "step": 182
+    },
+    {
+      "epoch": 1.2534246575342465,
+      "grad_norm": 0.6917922559068629,
+      "learning_rate": 4.077482918876995e-06,
+      "loss": 2.378,
+      "step": 183
+    },
+    {
+      "epoch": 1.2602739726027397,
+      "grad_norm": 0.6912354421485389,
+      "learning_rate": 4.066558193444746e-06,
+      "loss": 2.3087,
+      "step": 184
+    },
+    {
+      "epoch": 1.2671232876712328,
+      "grad_norm": 0.7423647896303166,
+      "learning_rate": 4.0555839889435444e-06,
+      "loss": 2.2661,
+      "step": 185
+    },
+    {
+      "epoch": 1.2671232876712328,
+      "eval_loss": 2.4178218841552734,
+      "eval_runtime": 5.9059,
+      "eval_samples_per_second": 52.828,
+      "eval_steps_per_second": 3.386,
+      "step": 185
+    },
+    {
+      "epoch": 1.273972602739726,
+      "grad_norm": 0.7478496634954042,
+      "learning_rate": 4.044560651988933e-06,
+      "loss": 2.3361,
+      "step": 186
+    },
+    {
+      "epoch": 1.2808219178082192,
+      "grad_norm": 0.7065399264251201,
+      "learning_rate": 4.033488530748285e-06,
+      "loss": 2.2644,
+      "step": 187
+    },
+    {
+      "epoch": 1.2876712328767124,
+      "grad_norm": 0.726480536340863,
+      "learning_rate": 4.022367974929803e-06,
+      "loss": 2.1882,
+      "step": 188
+    },
+    {
+      "epoch": 1.2945205479452055,
+      "grad_norm": 0.6827946001097096,
+      "learning_rate": 4.0111993357714755e-06,
+      "loss": 2.2887,
+      "step": 189
+    },
+    {
+      "epoch": 1.3013698630136985,
+      "grad_norm": 0.6814103107109724,
+      "learning_rate": 3.999982966029981e-06,
+      "loss": 2.3315,
+      "step": 190
+    },
+    {
+      "epoch": 1.308219178082192,
+      "grad_norm": 0.65846390651437,
+      "learning_rate": 3.98871921996955e-06,
+      "loss": 2.2595,
+      "step": 191
+    },
+    {
+      "epoch": 1.3150684931506849,
+      "grad_norm": 0.6664034822825207,
+      "learning_rate": 3.977408453350774e-06,
+      "loss": 2.3524,
+      "step": 192
+    },
+    {
+      "epoch": 1.321917808219178,
+      "grad_norm": 0.7146251642801748,
+      "learning_rate": 3.966051023419366e-06,
+      "loss": 2.3562,
+      "step": 193
+    },
+    {
+      "epoch": 1.3287671232876712,
+      "grad_norm": 0.7013378563213172,
+      "learning_rate": 3.9546472888948825e-06,
+      "loss": 2.2865,
+      "step": 194
+    },
+    {
+      "epoch": 1.3356164383561644,
+      "grad_norm": 0.6884022789569789,
+      "learning_rate": 3.943197609959389e-06,
+      "loss": 2.3293,
+      "step": 195
+    },
+    {
+      "epoch": 1.3424657534246576,
+      "grad_norm": 0.7263022758504937,
+      "learning_rate": 3.931702348246087e-06,
+      "loss": 2.2485,
+      "step": 196
+    },
+    {
+      "epoch": 1.3493150684931507,
+      "grad_norm": 0.6879494874948079,
+      "learning_rate": 3.92016186682789e-06,
+      "loss": 2.2652,
+      "step": 197
+    },
+    {
+      "epoch": 1.356164383561644,
+      "grad_norm": 0.7035221618072612,
+      "learning_rate": 3.9085765302059556e-06,
+      "loss": 2.3413,
+      "step": 198
+    },
+    {
+      "epoch": 1.3630136986301369,
+      "grad_norm": 0.7042222964511125,
+      "learning_rate": 3.8969467042981725e-06,
+      "loss": 2.3202,
+      "step": 199
+    },
+    {
+      "epoch": 1.36986301369863,
+      "grad_norm": 0.6961599428087603,
+      "learning_rate": 3.885272756427609e-06,
+      "loss": 2.2134,
+      "step": 200
+    },
+    {
+      "epoch": 1.3767123287671232,
+      "grad_norm": 0.7445990308351226,
+      "learning_rate": 3.873555055310902e-06,
+      "loss": 2.3083,
+      "step": 201
+    },
+    {
+      "epoch": 1.3835616438356164,
+      "grad_norm": 0.7272556327744341,
+      "learning_rate": 3.86179397104662e-06,
+      "loss": 2.2611,
+      "step": 202
+    },
+    {
+      "epoch": 1.3904109589041096,
+      "grad_norm": 0.6734004584059651,
+      "learning_rate": 3.849989875103566e-06,
+      "loss": 2.3396,
+      "step": 203
+    },
+    {
+      "epoch": 1.3972602739726028,
+      "grad_norm": 0.702149629138006,
+      "learning_rate": 3.83814314030905e-06,
+      "loss": 2.2206,
+      "step": 204
+    },
+    {
+      "epoch": 1.404109589041096,
+      "grad_norm": 0.7668660946577405,
+      "learning_rate": 3.826254140837111e-06,
+      "loss": 2.3745,
+      "step": 205
+    },
+    {
+      "epoch": 1.410958904109589,
+      "grad_norm": 0.6972264397617832,
+      "learning_rate": 3.8143232521967023e-06,
+      "loss": 2.2376,
+      "step": 206
+    },
+    {
+      "epoch": 1.4178082191780823,
+      "grad_norm": 0.6802719750908277,
+      "learning_rate": 3.802350851219826e-06,
+      "loss": 2.3348,
+      "step": 207
+    },
+    {
+      "epoch": 1.4246575342465753,
+      "grad_norm": 0.679939282001721,
+      "learning_rate": 3.7903373160496342e-06,
+      "loss": 2.3184,
+      "step": 208
+    },
+    {
+      "epoch": 1.4315068493150684,
+      "grad_norm": 0.708335225525305,
+      "learning_rate": 3.778283026128485e-06,
+      "loss": 2.2065,
+      "step": 209
+    },
+    {
+      "epoch": 1.4383561643835616,
+      "grad_norm": 0.6821337057973484,
+      "learning_rate": 3.7661883621859584e-06,
+      "loss": 2.3815,
+      "step": 210
+    },
+    {
+      "epoch": 1.4452054794520548,
+      "grad_norm": 0.6864170898125791,
+      "learning_rate": 3.754053706226829e-06,
+      "loss": 2.2901,
+      "step": 211
+    },
+    {
+      "epoch": 1.452054794520548,
+      "grad_norm": 0.690989555098226,
+      "learning_rate": 3.741879441519004e-06,
+      "loss": 2.3053,
+      "step": 212
+    },
+    {
+      "epoch": 1.4589041095890412,
+      "grad_norm": 0.7326752735961912,
+      "learning_rate": 3.729665952581415e-06,
+      "loss": 2.2915,
+      "step": 213
+    },
+    {
+      "epoch": 1.4657534246575343,
+      "grad_norm": 0.6795313294527453,
+      "learning_rate": 3.7174136251718735e-06,
+      "loss": 2.3548,
+      "step": 214
+    },
+    {
+      "epoch": 1.4726027397260273,
+      "grad_norm": 0.7026030269068815,
+      "learning_rate": 3.705122846274889e-06,
+      "loss": 2.339,
+      "step": 215
+    },
+    {
+      "epoch": 1.4794520547945205,
+      "grad_norm": 0.6968149329541087,
+      "learning_rate": 3.6927940040894427e-06,
+      "loss": 2.324,
+      "step": 216
+    },
+    {
+      "epoch": 1.4863013698630136,
+      "grad_norm": 0.681949385138759,
+      "learning_rate": 3.680427488016731e-06,
+      "loss": 2.2522,
+      "step": 217
+    },
+    {
+      "epoch": 1.4931506849315068,
+      "grad_norm": 0.7101393810809886,
+      "learning_rate": 3.6680236886478627e-06,
+      "loss": 2.3273,
+      "step": 218
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.681265285699898,
+      "learning_rate": 3.6555829977515213e-06,
+      "loss": 2.3807,
+      "step": 219
+    },
+    {
+      "epoch": 1.5068493150684932,
+      "grad_norm": 0.6714546516939787,
+      "learning_rate": 3.6431058082615966e-06,
+      "loss": 2.3566,
+      "step": 220
+    },
+    {
+      "epoch": 1.5136986301369864,
+      "grad_norm": 0.677995114165458,
+      "learning_rate": 3.6305925142647704e-06,
+      "loss": 2.3523,
+      "step": 221
+    },
+    {
+      "epoch": 1.5205479452054793,
+      "grad_norm": 0.6347599230305153,
+      "learning_rate": 3.6180435109880677e-06,
+      "loss": 2.2482,
+      "step": 222
+    },
+    {
+      "epoch": 1.5205479452054793,
+      "eval_loss": 2.4155406951904297,
+      "eval_runtime": 5.9256,
+      "eval_samples_per_second": 52.653,
+      "eval_steps_per_second": 3.375,
+      "step": 222
+    },
+    {
+      "epoch": 1.5273972602739727,
+      "grad_norm": 0.7076904051784869,
+      "learning_rate": 3.6054591947863782e-06,
+      "loss": 2.3036,
+      "step": 223
+    },
+    {
+      "epoch": 1.5342465753424657,
+      "grad_norm": 0.6907845815242056,
+      "learning_rate": 3.592839963129934e-06,
+      "loss": 2.3765,
+      "step": 224
+    },
+    {
+      "epoch": 1.541095890410959,
+      "grad_norm": 0.698669011142619,
+      "learning_rate": 3.5801862145917565e-06,
+      "loss": 2.3535,
+      "step": 225
+    },
+    {
+      "epoch": 1.547945205479452,
+      "grad_norm": 0.6660369882110091,
+      "learning_rate": 3.5674983488350695e-06,
+      "loss": 2.3089,
+      "step": 226
+    },
+    {
+      "epoch": 1.5547945205479452,
+      "grad_norm": 0.6870900476918825,
+      "learning_rate": 3.5547767666006735e-06,
+      "loss": 2.1687,
+      "step": 227
+    },
+    {
+      "epoch": 1.5616438356164384,
+      "grad_norm": 0.6973754014334647,
+      "learning_rate": 3.542021869694289e-06,
+      "loss": 2.3408,
+      "step": 228
+    },
+    {
+      "epoch": 1.5684931506849316,
+      "grad_norm": 0.6883965513486622,
+      "learning_rate": 3.5292340609738667e-06,
+      "loss": 2.2992,
+      "step": 229
+    },
+    {
+      "epoch": 1.5753424657534247,
+      "grad_norm": 0.6818556003782501,
+      "learning_rate": 3.516413744336863e-06,
+      "loss": 2.3865,
+      "step": 230
+    },
+    {
+      "epoch": 1.5821917808219177,
+      "grad_norm": 0.702979144019098,
+      "learning_rate": 3.503561324707484e-06,
+      "loss": 2.2278,
+      "step": 231
+    },
+    {
+      "epoch": 1.589041095890411,
+      "grad_norm": 0.6806404665338951,
+      "learning_rate": 3.4906772080238925e-06,
+      "loss": 2.3231,
+      "step": 232
+    },
+    {
+      "epoch": 1.595890410958904,
+      "grad_norm": 0.685606147526874,
+      "learning_rate": 3.47776180122539e-06,
+      "loss": 2.3128,
+      "step": 233
+    },
+    {
+      "epoch": 1.6027397260273972,
+      "grad_norm": 0.6332716110587268,
+      "learning_rate": 3.4648155122395653e-06,
+      "loss": 2.3087,
+      "step": 234
+    },
+    {
+      "epoch": 1.6095890410958904,
+      "grad_norm": 0.7202386902926047,
+      "learning_rate": 3.4518387499694038e-06,
+      "loss": 2.3599,
+      "step": 235
+    },
+    {
+      "epoch": 1.6164383561643836,
+      "grad_norm": 0.6832286968858357,
+      "learning_rate": 3.438831924280381e-06,
+      "loss": 2.335,
+      "step": 236
+    },
+    {
+      "epoch": 1.6232876712328768,
+      "grad_norm": 0.6520482069071943,
+      "learning_rate": 3.425795445987508e-06,
+      "loss": 2.3355,
+      "step": 237
+    },
+    {
+      "epoch": 1.6301369863013697,
+      "grad_norm": 0.7019446668563534,
+      "learning_rate": 3.4127297268423637e-06,
+      "loss": 2.3111,
+      "step": 238
+    },
+    {
+      "epoch": 1.6369863013698631,
+      "grad_norm": 0.677088641753582,
+      "learning_rate": 3.3996351795200865e-06,
+      "loss": 2.3463,
+      "step": 239
+    },
+    {
+      "epoch": 1.643835616438356,
+      "grad_norm": 0.7234982640691922,
+      "learning_rate": 3.386512217606339e-06,
+      "loss": 2.3195,
+      "step": 240
+    },
+    {
+      "epoch": 1.6506849315068495,
+      "grad_norm": 0.6944442709324709,
+      "learning_rate": 3.373361255584249e-06,
+      "loss": 2.4005,
+      "step": 241
+    },
+    {
+      "epoch": 1.6575342465753424,
+      "grad_norm": 0.7269476410749787,
+      "learning_rate": 3.3601827088213124e-06,
+      "loss": 2.2849,
+      "step": 242
+    },
+    {
+      "epoch": 1.6643835616438356,
+      "grad_norm": 0.6933396138061356,
+      "learning_rate": 3.3469769935562798e-06,
+      "loss": 2.3302,
+      "step": 243
+    },
+    {
+      "epoch": 1.6712328767123288,
+      "grad_norm": 0.6951788312862931,
+      "learning_rate": 3.3337445268860065e-06,
+      "loss": 2.3419,
+      "step": 244
+    },
+    {
+      "epoch": 1.678082191780822,
+      "grad_norm": 0.7102864990853207,
+      "learning_rate": 3.3204857267522782e-06,
+      "loss": 2.2889,
+      "step": 245
+    },
+    {
+      "epoch": 1.6849315068493151,
+      "grad_norm": 0.6734448441851548,
+      "learning_rate": 3.3072010119286156e-06,
+      "loss": 2.3191,
+      "step": 246
+    },
+    {
+      "epoch": 1.691780821917808,
+      "grad_norm": 0.710004987174813,
+      "learning_rate": 3.2938908020070403e-06,
+      "loss": 2.2627,
+      "step": 247
+    },
+    {
+      "epoch": 1.6986301369863015,
+      "grad_norm": 0.7011446050991217,
+      "learning_rate": 3.280555517384825e-06,
+      "loss": 2.3647,
+      "step": 248
+    },
+    {
+      "epoch": 1.7054794520547945,
+      "grad_norm": 0.7319541321421087,
+      "learning_rate": 3.267195579251219e-06,
+      "loss": 2.3177,
+      "step": 249
+    },
+    {
+      "epoch": 1.7123287671232876,
+      "grad_norm": 0.6626335956989253,
+      "learning_rate": 3.2538114095741412e-06,
+      "loss": 2.3775,
+      "step": 250
+    },
+    {
+      "epoch": 1.7191780821917808,
+      "grad_norm": 0.6662336469102511,
+      "learning_rate": 3.2404034310868524e-06,
+      "loss": 2.3887,
+      "step": 251
+    },
+    {
+      "epoch": 1.726027397260274,
+      "grad_norm": 0.6904872645618079,
+      "learning_rate": 3.2269720672746045e-06,
+      "loss": 2.2411,
+      "step": 252
+    },
+    {
+      "epoch": 1.7328767123287672,
+      "grad_norm": 0.6786858149868691,
+      "learning_rate": 3.2135177423612668e-06,
+      "loss": 2.3343,
+      "step": 253
+    },
+    {
+      "epoch": 1.7397260273972601,
+      "grad_norm": 0.8070210101589392,
+      "learning_rate": 3.200040881295922e-06,
+      "loss": 2.3579,
+      "step": 254
+    },
+    {
+      "epoch": 1.7465753424657535,
+      "grad_norm": 0.6859306383539353,
+      "learning_rate": 3.186541909739452e-06,
+      "loss": 2.371,
+      "step": 255
+    },
+    {
+      "epoch": 1.7534246575342465,
+      "grad_norm": 0.6853782148050659,
+      "learning_rate": 3.1730212540510835e-06,
+      "loss": 2.117,
+      "step": 256
+    },
+    {
+      "epoch": 1.7602739726027399,
+      "grad_norm": 0.9960196249104211,
+      "learning_rate": 3.1594793412749316e-06,
+      "loss": 2.3843,
+      "step": 257
+    },
+    {
+      "epoch": 1.7671232876712328,
+      "grad_norm": 0.6757685094130473,
+      "learning_rate": 3.145916599126506e-06,
+      "loss": 2.3745,
+      "step": 258
+    },
+    {
+      "epoch": 1.773972602739726,
+      "grad_norm": 0.7253543893242833,
+      "learning_rate": 3.132333455979202e-06,
+      "loss": 2.3707,
+      "step": 259
+    },
+    {
+      "epoch": 1.773972602739726,
+      "eval_loss": 2.4115374088287354,
+      "eval_runtime": 6.1962,
+      "eval_samples_per_second": 50.354,
+      "eval_steps_per_second": 3.228,
+      "step": 259
+    },
+    {
+      "epoch": 1.7808219178082192,
+      "grad_norm": 0.6634255128578609,
+      "learning_rate": 3.118730340850774e-06,
+      "loss": 2.2806,
+      "step": 260
+    },
+    {
+      "epoch": 1.7876712328767124,
+      "grad_norm": 0.6969726139618965,
+      "learning_rate": 3.1051076833897814e-06,
+      "loss": 2.3148,
+      "step": 261
+    },
+    {
+      "epoch": 1.7945205479452055,
+      "grad_norm": 0.7393377224615634,
+      "learning_rate": 3.091465913862019e-06,
+      "loss": 2.3359,
+      "step": 262
+    },
+    {
+      "epoch": 1.8013698630136985,
+      "grad_norm": 0.6900014881921968,
+      "learning_rate": 3.077805463136931e-06,
+      "loss": 2.2974,
+      "step": 263
+    },
+    {
+      "epoch": 1.808219178082192,
+      "grad_norm": 0.6902244001587043,
+      "learning_rate": 3.0641267626739946e-06,
+      "loss": 2.3219,
+      "step": 264
+    },
+    {
+      "epoch": 1.8150684931506849,
+      "grad_norm": 0.6810057389366492,
+      "learning_rate": 3.050430244509103e-06,
+      "loss": 2.3185,
+      "step": 265
+    },
+    {
+      "epoch": 1.821917808219178,
+      "grad_norm": 0.7557527768095192,
+      "learning_rate": 3.0367163412409084e-06,
+      "loss": 2.2613,
+      "step": 266
+    },
+    {
+      "epoch": 1.8287671232876712,
+      "grad_norm": 0.7085704364858588,
+      "learning_rate": 3.0229854860171666e-06,
+      "loss": 2.3049,
+      "step": 267
+    },
+    {
+      "epoch": 1.8356164383561644,
+      "grad_norm": 0.7044887748838028,
+      "learning_rate": 3.009238112521054e-06,
+      "loss": 2.3123,
+      "step": 268
+    },
+    {
+      "epoch": 1.8424657534246576,
+      "grad_norm": 0.6900781076774555,
+      "learning_rate": 2.9954746549574696e-06,
+      "loss": 2.2775,
+      "step": 269
+    },
+    {
+      "epoch": 1.8493150684931505,
+      "grad_norm": 0.71668864808382,
+      "learning_rate": 2.981695548039319e-06,
+      "loss": 2.3295,
+      "step": 270
+    },
+    {
+      "epoch": 1.856164383561644,
+      "grad_norm": 0.667887574033749,
+      "learning_rate": 2.967901226973787e-06,
+      "loss": 2.3287,
+      "step": 271
+    },
+    {
+      "epoch": 1.8630136986301369,
+      "grad_norm": 0.6819433212131332,
+      "learning_rate": 2.9540921274485913e-06,
+      "loss": 2.3693,
+      "step": 272
+    },
+    {
+      "epoch": 1.8698630136986303,
+      "grad_norm": 0.9698629158570198,
+      "learning_rate": 2.9402686856182204e-06,
+      "loss": 2.2706,
+      "step": 273
+    },
+    {
+      "epoch": 1.8767123287671232,
+      "grad_norm": 0.6898650487034594,
+      "learning_rate": 2.9264313380901586e-06,
+      "loss": 2.3726,
+      "step": 274
+    },
+    {
+      "epoch": 1.8835616438356164,
+      "grad_norm": 0.6770885016618345,
+      "learning_rate": 2.912580521911095e-06,
+      "loss": 2.3218,
+      "step": 275
+    },
+    {
+      "epoch": 1.8904109589041096,
+      "grad_norm": 0.697939657290891,
+      "learning_rate": 2.898716674553121e-06,
+      "loss": 2.4074,
+      "step": 276
+    },
+    {
+      "epoch": 1.8972602739726028,
+      "grad_norm": 0.7048161669777684,
+      "learning_rate": 2.8848402338999116e-06,
+      "loss": 2.3547,
+      "step": 277
+    },
+    {
+      "epoch": 1.904109589041096,
+      "grad_norm": 0.7550887476234565,
+      "learning_rate": 2.870951638232896e-06,
+      "loss": 2.3242,
+      "step": 278
+    },
+    {
+      "epoch": 1.910958904109589,
+      "grad_norm": 0.674336958631372,
+      "learning_rate": 2.8570513262174155e-06,
+      "loss": 2.3511,
+      "step": 279
+    },
+    {
+      "epoch": 1.9178082191780823,
+      "grad_norm": 0.7168968714166564,
+      "learning_rate": 2.843139736888864e-06,
+      "loss": 2.3232,
+      "step": 280
+    },
+    {
+      "epoch": 1.9246575342465753,
+      "grad_norm": 0.7236665241621988,
+      "learning_rate": 2.829217309638828e-06,
+      "loss": 2.3281,
+      "step": 281
+    },
+    {
+      "epoch": 1.9315068493150684,
+      "grad_norm": 0.6931721284135243,
+      "learning_rate": 2.8152844842012034e-06,
+      "loss": 2.3643,
+      "step": 282
+    },
+    {
+      "epoch": 1.9383561643835616,
+      "grad_norm": 0.6928469669838125,
+      "learning_rate": 2.8013417006383078e-06,
+      "loss": 2.2855,
+      "step": 283
+    },
+    {
+      "epoch": 1.9452054794520548,
+      "grad_norm": 0.6982709588867243,
+      "learning_rate": 2.787389399326984e-06,
+      "loss": 2.2552,
+      "step": 284
+    },
+    {
+      "epoch": 1.952054794520548,
+      "grad_norm": 0.6890157309338247,
+      "learning_rate": 2.773428020944687e-06,
+      "loss": 2.1769,
+      "step": 285
+    },
+    {
+      "epoch": 1.958904109589041,
+      "grad_norm": 0.6890167227071454,
+      "learning_rate": 2.7594580064555664e-06,
+      "loss": 2.2975,
+      "step": 286
+    },
+    {
+      "epoch": 1.9657534246575343,
+      "grad_norm": 0.6603722163357953,
+      "learning_rate": 2.745479797096543e-06,
+      "loss": 2.3294,
+      "step": 287
+    },
+    {
+      "epoch": 1.9726027397260273,
+      "grad_norm": 0.673631868721191,
+      "learning_rate": 2.7314938343633656e-06,
+      "loss": 2.3338,
+      "step": 288
+    },
+    {
+      "epoch": 1.9794520547945207,
+      "grad_norm": 0.6838024849491231,
+      "learning_rate": 2.717500559996672e-06,
+      "loss": 2.2469,
+      "step": 289
+    },
+    {
+      "epoch": 1.9863013698630136,
+      "grad_norm": 0.6915378189577142,
+      "learning_rate": 2.7035004159680332e-06,
+      "loss": 2.3446,
+      "step": 290
+    },
+    {
+      "epoch": 1.9931506849315068,
+      "grad_norm": 0.7308967059013186,
+      "learning_rate": 2.6894938444659972e-06,
+      "loss": 2.3048,
+      "step": 291
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6670727912036851,
+      "learning_rate": 2.675481287882121e-06,
+      "loss": 2.3657,
+      "step": 292
+    },
+    {
+      "epoch": 2.006849315068493,
+      "grad_norm": 0.7842325057992966,
+      "learning_rate": 2.661463188796996e-06,
+      "loss": 2.2781,
+      "step": 293
+    },
+    {
+      "epoch": 2.0136986301369864,
+      "grad_norm": 0.7703049180632918,
+      "learning_rate": 2.647439989966272e-06,
+      "loss": 2.2511,
+      "step": 294
+    },
+    {
+      "epoch": 2.0205479452054793,
+      "grad_norm": 0.7618588659706208,
+      "learning_rate": 2.633412134306672e-06,
+      "loss": 2.3002,
+      "step": 295
+    },
+    {
+      "epoch": 2.0273972602739727,
+      "grad_norm": 0.7698611238860366,
+      "learning_rate": 2.6193800648820056e-06,
+      "loss": 2.293,
+      "step": 296
+    },
+    {
+      "epoch": 2.0273972602739727,
+      "eval_loss": 2.413179397583008,
+      "eval_runtime": 5.9465,
+      "eval_samples_per_second": 52.468,
+      "eval_steps_per_second": 3.363,
+      "step": 296
+    },
+    {
+      "epoch": 2.0342465753424657,
+      "grad_norm": 0.744217752384927,
+      "learning_rate": 2.605344224889167e-06,
+      "loss": 2.2864,
+      "step": 297
+    },
+    {
+      "epoch": 2.041095890410959,
+      "grad_norm": 0.7308267298605848,
+      "learning_rate": 2.591305057644148e-06,
+      "loss": 2.2549,
+      "step": 298
+    },
+    {
+      "epoch": 2.047945205479452,
+      "grad_norm": 0.7364683383887598,
+      "learning_rate": 2.5772630065680247e-06,
+      "loss": 2.2634,
+      "step": 299
+    },
+    {
+      "epoch": 2.0547945205479454,
+      "grad_norm": 0.6947110181620351,
+      "learning_rate": 2.563218515172962e-06,
+      "loss": 2.2756,
+      "step": 300
+    },
+    {
+      "epoch": 2.0616438356164384,
+      "grad_norm": 0.7441894255170367,
+      "learning_rate": 2.5491720270481995e-06,
+      "loss": 2.2196,
+      "step": 301
+    },
+    {
+      "epoch": 2.0684931506849313,
+      "grad_norm": 0.7308523751420212,
+      "learning_rate": 2.5351239858460425e-06,
+      "loss": 2.1325,
+      "step": 302
+    },
+    {
+      "epoch": 2.0753424657534247,
+      "grad_norm": 0.723559375401077,
+      "learning_rate": 2.521074835267851e-06,
+      "loss": 2.2826,
+      "step": 303
+    },
+    {
+      "epoch": 2.0821917808219177,
+      "grad_norm": 0.7107824928376044,
+      "learning_rate": 2.507025019050022e-06,
+      "loss": 2.3009,
+      "step": 304
+    },
+    {
+      "epoch": 2.089041095890411,
+      "grad_norm": 0.7407695595687628,
+      "learning_rate": 2.4929749809499788e-06,
+      "loss": 2.294,
+      "step": 305
+    },
+    {
+      "epoch": 2.095890410958904,
+      "grad_norm": 0.9861121146811986,
+      "learning_rate": 2.4789251647321498e-06,
+      "loss": 2.3456,
+      "step": 306
+    },
+    {
+      "epoch": 2.1027397260273974,
+      "grad_norm": 0.7154622282506935,
+      "learning_rate": 2.464876014153958e-06,
+      "loss": 2.3047,
+      "step": 307
+    },
+    {
+      "epoch": 2.1095890410958904,
+      "grad_norm": 0.764573333314849,
+      "learning_rate": 2.4508279729518013e-06,
+      "loss": 2.2963,
+      "step": 308
+    },
+    {
+      "epoch": 2.1164383561643834,
+      "grad_norm": 0.7200447494905048,
+      "learning_rate": 2.4367814848270386e-06,
+      "loss": 2.3017,
+      "step": 309
+    },
+    {
+      "epoch": 2.1232876712328768,
+      "grad_norm": 0.7331208423596353,
+      "learning_rate": 2.422736993431976e-06,
+      "loss": 2.2193,
+      "step": 310
+    },
+    {
+      "epoch": 2.1301369863013697,
+      "grad_norm": 0.7181268238018352,
+      "learning_rate": 2.408694942355853e-06,
+      "loss": 2.2816,
+      "step": 311
+    },
+    {
+      "epoch": 2.136986301369863,
+      "grad_norm": 0.71696981098615,
+      "learning_rate": 2.3946557751108333e-06,
+      "loss": 2.2556,
+      "step": 312
+    },
+    {
+      "epoch": 2.143835616438356,
+      "grad_norm": 0.7496868820684847,
+      "learning_rate": 2.3806199351179948e-06,
+      "loss": 2.2647,
+      "step": 313
+    },
+    {
+      "epoch": 2.1506849315068495,
+      "grad_norm": 0.7170898258087575,
+      "learning_rate": 2.3665878656933285e-06,
+      "loss": 2.2258,
+      "step": 314
+    },
+    {
+      "epoch": 2.1575342465753424,
+      "grad_norm": 0.7349227307009416,
+      "learning_rate": 2.3525600100337294e-06,
+      "loss": 2.3019,
+      "step": 315
+    },
+    {
+      "epoch": 2.1643835616438354,
+      "grad_norm": 0.7339023774015392,
+      "learning_rate": 2.3385368112030054e-06,
+      "loss": 2.2243,
+      "step": 316
+    },
+    {
+      "epoch": 2.171232876712329,
+      "grad_norm": 0.7094170245428788,
+      "learning_rate": 2.3245187121178804e-06,
+      "loss": 2.2296,
+      "step": 317
+    },
+    {
+      "epoch": 2.1780821917808217,
+      "grad_norm": 0.7201765979542566,
+      "learning_rate": 2.310506155534003e-06,
+      "loss": 2.3034,
+      "step": 318
+    },
+    {
+      "epoch": 2.184931506849315,
+      "grad_norm": 0.6843911581159334,
+      "learning_rate": 2.296499584031967e-06,
+      "loss": 2.3191,
+      "step": 319
+    },
+    {
+      "epoch": 2.191780821917808,
+      "grad_norm": 0.715427807427916,
+      "learning_rate": 2.282499440003329e-06,
+      "loss": 2.2465,
+      "step": 320
+    },
+    {
+      "epoch": 2.1986301369863015,
+      "grad_norm": 0.7344624489275093,
+      "learning_rate": 2.268506165636635e-06,
+      "loss": 2.2288,
+      "step": 321
+    },
+    {
+      "epoch": 2.2054794520547945,
+      "grad_norm": 0.7296105473696515,
+      "learning_rate": 2.254520202903458e-06,
+      "loss": 2.237,
+      "step": 322
+    },
+    {
+      "epoch": 2.212328767123288,
+      "grad_norm": 0.7740678634111837,
+      "learning_rate": 2.240541993544434e-06,
+      "loss": 2.2005,
+      "step": 323
+    },
+    {
+      "epoch": 2.219178082191781,
+      "grad_norm": 0.6876899720253623,
+      "learning_rate": 2.2265719790553147e-06,
+      "loss": 2.0113,
+      "step": 324
+    },
+    {
+      "epoch": 2.2260273972602738,
+      "grad_norm": 0.7385389732044396,
+      "learning_rate": 2.212610600673017e-06,
+      "loss": 2.2027,
+      "step": 325
+    },
+    {
+      "epoch": 2.232876712328767,
+      "grad_norm": 0.7237738352415183,
+      "learning_rate": 2.1986582993616926e-06,
+      "loss": 2.3329,
+      "step": 326
+    },
+    {
+      "epoch": 2.23972602739726,
+      "grad_norm": 0.7224811508262542,
+      "learning_rate": 2.1847155157987975e-06,
+      "loss": 2.3061,
+      "step": 327
+    },
+    {
+      "epoch": 2.2465753424657535,
+      "grad_norm": 0.7141960930180122,
+      "learning_rate": 2.170782690361173e-06,
+      "loss": 2.249,
+      "step": 328
+    },
+    {
+      "epoch": 2.2534246575342465,
+      "grad_norm": 0.7210265725669223,
+      "learning_rate": 2.1568602631111362e-06,
+      "loss": 2.3222,
+      "step": 329
+    },
+    {
+      "epoch": 2.26027397260274,
+      "grad_norm": 0.7622124004386663,
+      "learning_rate": 2.1429486737825857e-06,
+      "loss": 2.2205,
+      "step": 330
+    },
+    {
+      "epoch": 2.267123287671233,
+      "grad_norm": 0.7131919831150063,
+      "learning_rate": 2.129048361767104e-06,
+      "loss": 2.2562,
+      "step": 331
+    },
+    {
+      "epoch": 2.2739726027397262,
+      "grad_norm": 0.716232761563867,
+      "learning_rate": 2.1151597661000884e-06,
+      "loss": 2.1547,
+      "step": 332
+    },
+    {
+      "epoch": 2.280821917808219,
+      "grad_norm": 0.7370885639371628,
+      "learning_rate": 2.1012833254468803e-06,
+      "loss": 2.3085,
+      "step": 333
+    },
+    {
+      "epoch": 2.280821917808219,
+      "eval_loss": 2.413699150085449,
+      "eval_runtime": 5.9363,
+      "eval_samples_per_second": 52.558,
+      "eval_steps_per_second": 3.369,
+      "step": 333
+    },
+    {
+      "epoch": 2.287671232876712,
+      "grad_norm": 0.6858773863616128,
+      "learning_rate": 2.087419478088906e-06,
+      "loss": 2.1914,
+      "step": 334
+    },
+    {
+      "epoch": 2.2945205479452055,
+      "grad_norm": 0.7071367211538865,
+      "learning_rate": 2.073568661909842e-06,
+      "loss": 2.2382,
+      "step": 335
+    },
+    {
+      "epoch": 2.3013698630136985,
+      "grad_norm": 0.7099731184047182,
+      "learning_rate": 2.0597313143817804e-06,
+      "loss": 2.2705,
+      "step": 336
+    },
+    {
+      "epoch": 2.308219178082192,
+      "grad_norm": 0.7132760269247956,
+      "learning_rate": 2.045907872551409e-06,
+      "loss": 2.2967,
+      "step": 337
+    },
+    {
+      "epoch": 2.315068493150685,
+      "grad_norm": 0.7026265666695738,
+      "learning_rate": 2.0320987730262136e-06,
+      "loss": 2.1903,
+      "step": 338
+    },
+    {
+      "epoch": 2.3219178082191783,
+      "grad_norm": 0.7121256173220049,
+      "learning_rate": 2.018304451960682e-06,
+      "loss": 2.2352,
+      "step": 339
+    },
+    {
+      "epoch": 2.328767123287671,
+      "grad_norm": 0.716016616197666,
+      "learning_rate": 2.0045253450425308e-06,
+      "loss": 2.2246,
+      "step": 340
+    },
+    {
+      "epoch": 2.3356164383561646,
+      "grad_norm": 0.702268794797935,
+      "learning_rate": 1.9907618874789463e-06,
+      "loss": 2.1513,
+      "step": 341
+    },
+    {
+      "epoch": 2.3424657534246576,
+      "grad_norm": 0.7211508092099944,
+      "learning_rate": 1.9770145139828334e-06,
+      "loss": 2.2313,
+      "step": 342
+    },
+    {
+      "epoch": 2.3493150684931505,
+      "grad_norm": 0.6875475522410895,
+      "learning_rate": 1.963283658759093e-06,
+      "loss": 2.1937,
+      "step": 343
+    },
+    {
+      "epoch": 2.356164383561644,
+      "grad_norm": 0.7100032015503472,
+      "learning_rate": 1.9495697554908984e-06,
+      "loss": 2.2032,
+      "step": 344
+    },
+    {
+      "epoch": 2.363013698630137,
+      "grad_norm": 0.7090312927179646,
+      "learning_rate": 1.935873237326006e-06,
+      "loss": 2.3233,
+      "step": 345
+    },
+    {
+      "epoch": 2.3698630136986303,
+      "grad_norm": 0.7321348941655884,
+      "learning_rate": 1.9221945368630703e-06,
+      "loss": 2.3082,
+      "step": 346
+    },
+    {
+      "epoch": 2.3767123287671232,
+      "grad_norm": 0.7176395955608619,
+      "learning_rate": 1.9085340861379815e-06,
+      "loss": 2.2542,
+      "step": 347
+    },
+    {
+      "epoch": 2.383561643835616,
+      "grad_norm": 0.7470287281593275,
+      "learning_rate": 1.8948923166102192e-06,
+      "loss": 2.2732,
+      "step": 348
+    },
+    {
+      "epoch": 2.3904109589041096,
+      "grad_norm": 0.7438948749235669,
+      "learning_rate": 1.8812696591492265e-06,
+      "loss": 2.2342,
+      "step": 349
+    },
+    {
+      "epoch": 2.3972602739726026,
+      "grad_norm": 0.7307563711082086,
+      "learning_rate": 1.8676665440207982e-06,
+      "loss": 2.3099,
+      "step": 350
+    },
+    {
+      "epoch": 2.404109589041096,
+      "grad_norm": 0.7505670286099257,
+      "learning_rate": 1.8540834008734944e-06,
+      "loss": 2.1853,
+      "step": 351
+    },
+    {
+      "epoch": 2.410958904109589,
+      "grad_norm": 0.7136239479111697,
+      "learning_rate": 1.840520658725069e-06,
+      "loss": 2.2143,
+      "step": 352
+    },
+    {
+      "epoch": 2.4178082191780823,
+      "grad_norm": 0.7027371598115614,
+      "learning_rate": 1.8269787459489174e-06,
+      "loss": 2.2046,
+      "step": 353
+    },
+    {
+      "epoch": 2.4246575342465753,
+      "grad_norm": 0.707254420656309,
+      "learning_rate": 1.8134580902605491e-06,
+      "loss": 2.29,
+      "step": 354
+    },
+    {
+      "epoch": 2.4315068493150687,
+      "grad_norm": 0.7170888804392873,
+      "learning_rate": 1.7999591187040782e-06,
+      "loss": 2.2643,
+      "step": 355
+    },
+    {
+      "epoch": 2.4383561643835616,
+      "grad_norm": 0.6639457176222473,
+      "learning_rate": 1.786482257638734e-06,
+      "loss": 2.2946,
+      "step": 356
+    },
+    {
+      "epoch": 2.4452054794520546,
+      "grad_norm": 0.6791585701285383,
+      "learning_rate": 1.7730279327253964e-06,
+      "loss": 2.3087,
+      "step": 357
+    },
+    {
+      "epoch": 2.452054794520548,
+      "grad_norm": 0.6825147247611417,
+      "learning_rate": 1.7595965689131484e-06,
+      "loss": 2.2252,
+      "step": 358
+    },
+    {
+      "epoch": 2.458904109589041,
+      "grad_norm": 0.7066098521292989,
+      "learning_rate": 1.7461885904258592e-06,
+      "loss": 2.2848,
+      "step": 359
+    },
+    {
+      "epoch": 2.4657534246575343,
+      "grad_norm": 0.7168260488520454,
+      "learning_rate": 1.732804420748781e-06,
+      "loss": 2.2381,
+      "step": 360
+    },
+    {
+      "epoch": 2.4726027397260273,
+      "grad_norm": 0.6940716557572651,
+      "learning_rate": 1.7194444826151753e-06,
+      "loss": 2.229,
+      "step": 361
+    },
+    {
+      "epoch": 2.4794520547945207,
+      "grad_norm": 0.6907305923666783,
+      "learning_rate": 1.7061091979929611e-06,
+      "loss": 2.2814,
+      "step": 362
+    },
+    {
+      "epoch": 2.4863013698630136,
+      "grad_norm": 0.7177474380488151,
+      "learning_rate": 1.6927989880713852e-06,
+      "loss": 2.2602,
+      "step": 363
+    },
+    {
+      "epoch": 2.493150684931507,
+      "grad_norm": 0.7581488681368201,
+      "learning_rate": 1.6795142732477222e-06,
+      "loss": 2.317,
+      "step": 364
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.7320361051298075,
+      "learning_rate": 1.6662554731139945e-06,
+      "loss": 2.2549,
+      "step": 365
+    },
+    {
+      "epoch": 2.506849315068493,
+      "grad_norm": 0.686393513195622,
+      "learning_rate": 1.6530230064437213e-06,
+      "loss": 2.2856,
+      "step": 366
+    },
+    {
+      "epoch": 2.5136986301369864,
+      "grad_norm": 0.7545957049643752,
+      "learning_rate": 1.6398172911786883e-06,
+      "loss": 2.2899,
+      "step": 367
+    },
+    {
+      "epoch": 2.5205479452054793,
+      "grad_norm": 0.7106340176915894,
+      "learning_rate": 1.6266387444157519e-06,
+      "loss": 2.2894,
+      "step": 368
+    },
+    {
+      "epoch": 2.5273972602739727,
+      "grad_norm": 0.7389989197034765,
+      "learning_rate": 1.613487782393661e-06,
+      "loss": 2.2875,
+      "step": 369
+    },
+    {
+      "epoch": 2.5342465753424657,
+      "grad_norm": 0.7649624949493309,
+      "learning_rate": 1.600364820479914e-06,
+      "loss": 2.1902,
+      "step": 370
+    },
+    {
+      "epoch": 2.5342465753424657,
+      "eval_loss": 2.4123480319976807,
+      "eval_runtime": 6.0173,
+      "eval_samples_per_second": 51.85,
+      "eval_steps_per_second": 3.324,
+      "step": 370
+    },
+    {
+      "epoch": 2.541095890410959,
+      "grad_norm": 0.7223441929466774,
+      "learning_rate": 1.5872702731576374e-06,
+      "loss": 2.269,
+      "step": 371
+    },
+    {
+      "epoch": 2.547945205479452,
+      "grad_norm": 0.7067038601638844,
+      "learning_rate": 1.5742045540124932e-06,
+      "loss": 2.2439,
+      "step": 372
+    },
+    {
+      "epoch": 2.5547945205479454,
+      "grad_norm": 0.7198264845513052,
+      "learning_rate": 1.5611680757196198e-06,
+      "loss": 2.3084,
+      "step": 373
+    },
+    {
+      "epoch": 2.5616438356164384,
+      "grad_norm": 0.7048209878339,
+      "learning_rate": 1.5481612500305964e-06,
+      "loss": 2.2518,
+      "step": 374
+    },
+    {
+      "epoch": 2.5684931506849313,
+      "grad_norm": 0.7345257609929702,
+      "learning_rate": 1.5351844877604356e-06,
+      "loss": 2.2796,
+      "step": 375
+    },
+    {
+      "epoch": 2.5753424657534247,
+      "grad_norm": 0.713666987740628,
+      "learning_rate": 1.5222381987746104e-06,
+      "loss": 2.2713,
+      "step": 376
+    },
+    {
+      "epoch": 2.5821917808219177,
+      "grad_norm": 0.7150783105673093,
+      "learning_rate": 1.5093227919761084e-06,
+      "loss": 2.2099,
+      "step": 377
+    },
+    {
+      "epoch": 2.589041095890411,
+      "grad_norm": 0.704487566383048,
+      "learning_rate": 1.4964386752925165e-06,
+      "loss": 2.3054,
+      "step": 378
+    },
+    {
+      "epoch": 2.595890410958904,
+      "grad_norm": 0.7522139473067558,
+      "learning_rate": 1.4835862556631369e-06,
+      "loss": 2.2186,
+      "step": 379
+    },
+    {
+      "epoch": 2.602739726027397,
+      "grad_norm": 0.6891880183627714,
+      "learning_rate": 1.4707659390261337e-06,
+      "loss": 2.3112,
+      "step": 380
+    },
+    {
+      "epoch": 2.6095890410958904,
+      "grad_norm": 0.7087422764378963,
+      "learning_rate": 1.4579781303057123e-06,
+      "loss": 2.2926,
+      "step": 381
+    },
+    {
+      "epoch": 2.616438356164384,
+      "grad_norm": 0.8486535470180528,
+      "learning_rate": 1.4452232333993272e-06,
+      "loss": 2.2778,
+      "step": 382
+    },
+    {
+      "epoch": 2.6232876712328768,
+      "grad_norm": 0.7768366805945564,
+      "learning_rate": 1.4325016511649315e-06,
+      "loss": 2.2441,
+      "step": 383
+    },
+    {
+      "epoch": 2.6301369863013697,
+      "grad_norm": 0.759828305906503,
+      "learning_rate": 1.4198137854082443e-06,
+      "loss": 2.2788,
+      "step": 384
+    },
+    {
+      "epoch": 2.636986301369863,
+      "grad_norm": 0.6859934839331832,
+      "learning_rate": 1.4071600368700669e-06,
+      "loss": 2.2792,
+      "step": 385
+    },
+    {
+      "epoch": 2.643835616438356,
+      "grad_norm": 0.7385417901666564,
+      "learning_rate": 1.3945408052136222e-06,
+      "loss": 2.2977,
+      "step": 386
+    },
+    {
+      "epoch": 2.6506849315068495,
+      "grad_norm": 0.7287504655916882,
+      "learning_rate": 1.3819564890119325e-06,
+      "loss": 2.2535,
+      "step": 387
+    },
+    {
+      "epoch": 2.6575342465753424,
+      "grad_norm": 0.6590047061716495,
+      "learning_rate": 1.3694074857352306e-06,
+      "loss": 2.2968,
+      "step": 388
+    },
+    {
+      "epoch": 2.6643835616438354,
+      "grad_norm": 0.6943988283660237,
+      "learning_rate": 1.3568941917384038e-06,
+      "loss": 2.2821,
+      "step": 389
+    },
+    {
+      "epoch": 2.671232876712329,
+      "grad_norm": 0.715573529250739,
+      "learning_rate": 1.3444170022484803e-06,
+      "loss": 2.2114,
+      "step": 390
+    },
+    {
+      "epoch": 2.678082191780822,
+      "grad_norm": 0.7016875788114846,
+      "learning_rate": 1.331976311352139e-06,
+      "loss": 2.2775,
+      "step": 391
+    },
+    {
+      "epoch": 2.684931506849315,
+      "grad_norm": 0.7436040372608549,
+      "learning_rate": 1.3195725119832693e-06,
+      "loss": 2.1983,
+      "step": 392
+    },
+    {
+      "epoch": 2.691780821917808,
+      "grad_norm": 0.6959008156370489,
+      "learning_rate": 1.307205995910557e-06,
+      "loss": 2.2541,
+      "step": 393
+    },
+    {
+      "epoch": 2.6986301369863015,
+      "grad_norm": 0.6701075429596892,
+      "learning_rate": 1.294877153725112e-06,
+      "loss": 2.2895,
+      "step": 394
+    },
+    {
+      "epoch": 2.7054794520547945,
+      "grad_norm": 0.7133265486183699,
+      "learning_rate": 1.2825863748281269e-06,
+      "loss": 2.311,
+      "step": 395
+    },
+    {
+      "epoch": 2.712328767123288,
+      "grad_norm": 0.731649203575663,
+      "learning_rate": 1.2703340474185856e-06,
+      "loss": 2.214,
+      "step": 396
+    },
+    {
+      "epoch": 2.719178082191781,
+      "grad_norm": 0.6951302895005032,
+      "learning_rate": 1.258120558480996e-06,
+      "loss": 2.2798,
+      "step": 397
+    },
+    {
+      "epoch": 2.7260273972602738,
+      "grad_norm": 0.7342864394765313,
+      "learning_rate": 1.245946293773171e-06,
+      "loss": 2.2428,
+      "step": 398
+    },
+    {
+      "epoch": 2.732876712328767,
+      "grad_norm": 0.6748430142696247,
+      "learning_rate": 1.2338116378140424e-06,
+      "loss": 2.1684,
+      "step": 399
+    },
+    {
+      "epoch": 2.73972602739726,
+      "grad_norm": 0.706147657425132,
+      "learning_rate": 1.2217169738715162e-06,
+      "loss": 2.2685,
+      "step": 400
+    },
+    {
+      "epoch": 2.7465753424657535,
+      "grad_norm": 0.7029833217334348,
+      "learning_rate": 1.2096626839503666e-06,
+      "loss": 2.257,
+      "step": 401
+    },
+    {
+      "epoch": 2.7534246575342465,
+      "grad_norm": 0.6915579514085184,
+      "learning_rate": 1.1976491487801747e-06,
+      "loss": 2.3553,
+      "step": 402
+    },
+    {
+      "epoch": 2.76027397260274,
+      "grad_norm": 0.6935009825915379,
+      "learning_rate": 1.1856767478032978e-06,
+      "loss": 2.3177,
+      "step": 403
+    },
+    {
+      "epoch": 2.767123287671233,
+      "grad_norm": 0.776510135143567,
+      "learning_rate": 1.1737458591628898e-06,
+      "loss": 2.1945,
+      "step": 404
+    },
+    {
+      "epoch": 2.7739726027397262,
+      "grad_norm": 0.6785739385871513,
+      "learning_rate": 1.1618568596909514e-06,
+      "loss": 2.3425,
+      "step": 405
+    },
+    {
+      "epoch": 2.780821917808219,
+      "grad_norm": 0.7244494372149703,
+      "learning_rate": 1.150010124896435e-06,
+      "loss": 2.3191,
+      "step": 406
+    },
+    {
+      "epoch": 2.787671232876712,
+      "grad_norm": 0.723165620037459,
+      "learning_rate": 1.1382060289533805e-06,
+      "loss": 2.216,
+      "step": 407
+    },
+    {
+      "epoch": 2.787671232876712,
+      "eval_loss": 2.4112062454223633,
+      "eval_runtime": 6.0106,
+      "eval_samples_per_second": 51.908,
+      "eval_steps_per_second": 3.327,
+      "step": 407
+    },
+    {
+      "epoch": 2.7945205479452055,
+      "grad_norm": 0.716573732956154,
+      "learning_rate": 1.1264449446890976e-06,
+      "loss": 2.3031,
+      "step": 408
+    },
+    {
+      "epoch": 2.8013698630136985,
+      "grad_norm": 0.6990575425388178,
+      "learning_rate": 1.114727243572392e-06,
+      "loss": 2.2865,
+      "step": 409
+    },
+    {
+      "epoch": 2.808219178082192,
+      "grad_norm": 0.7033064610318523,
+      "learning_rate": 1.1030532957018288e-06,
+      "loss": 2.2547,
+      "step": 410
+    },
+    {
+      "epoch": 2.815068493150685,
+      "grad_norm": 0.7066376790442048,
+      "learning_rate": 1.0914234697940465e-06,
+      "loss": 2.2383,
+      "step": 411
+    },
+    {
+      "epoch": 2.821917808219178,
+      "grad_norm": 0.7220557474397004,
+      "learning_rate": 1.079838133172111e-06,
+      "loss": 2.18,
+      "step": 412
+    },
+    {
+      "epoch": 2.828767123287671,
+      "grad_norm": 0.710206848234572,
+      "learning_rate": 1.068297651753913e-06,
+      "loss": 2.2733,
+      "step": 413
+    },
+    {
+      "epoch": 2.8356164383561646,
+      "grad_norm": 0.7327379146961583,
+      "learning_rate": 1.0568023900406108e-06,
+      "loss": 2.1961,
+      "step": 414
+    },
+    {
+      "epoch": 2.8424657534246576,
+      "grad_norm": 0.6842961302424317,
+      "learning_rate": 1.0453527111051183e-06,
+      "loss": 2.1984,
+      "step": 415
+    },
+    {
+      "epoch": 2.8493150684931505,
+      "grad_norm": 0.7658479578627203,
+      "learning_rate": 1.0339489765806347e-06,
+      "loss": 2.2618,
+      "step": 416
+    },
+    {
+      "epoch": 2.856164383561644,
+      "grad_norm": 0.6961196544731081,
+      "learning_rate": 1.0225915466492268e-06,
+      "loss": 2.2644,
+      "step": 417
+    },
+    {
+      "epoch": 2.863013698630137,
+      "grad_norm": 0.6960320474171482,
+      "learning_rate": 1.0112807800304499e-06,
+      "loss": 2.1823,
+      "step": 418
+    },
+    {
+      "epoch": 2.8698630136986303,
+      "grad_norm": 0.7327958977392377,
+      "learning_rate": 1.00001703397002e-06,
+      "loss": 2.2894,
+      "step": 419
+    },
+    {
+      "epoch": 2.8767123287671232,
+      "grad_norm": 0.7175112056018497,
+      "learning_rate": 9.888006642285255e-07,
+      "loss": 2.3192,
+      "step": 420
+    },
+    {
+      "epoch": 2.883561643835616,
+      "grad_norm": 0.6951758710131047,
+      "learning_rate": 9.776320250701983e-07,
+      "loss": 2.2736,
+      "step": 421
+    },
+    {
+      "epoch": 2.8904109589041096,
+      "grad_norm": 0.8651114201507224,
+      "learning_rate": 9.665114692517157e-07,
+      "loss": 2.1695,
+      "step": 422
+    },
+    {
+      "epoch": 2.897260273972603,
+      "grad_norm": 0.7095105670222126,
+      "learning_rate": 9.554393480110678e-07,
+      "loss": 2.3053,
+      "step": 423
+    },
+    {
+      "epoch": 2.904109589041096,
+      "grad_norm": 0.721617667719065,
+      "learning_rate": 9.444160110564563e-07,
+      "loss": 2.2036,
+      "step": 424
+    },
+    {
+      "epoch": 2.910958904109589,
+      "grad_norm": 0.7086651454995305,
+      "learning_rate": 9.334418065552539e-07,
+      "loss": 2.3177,
+      "step": 425
+    },
+    {
+      "epoch": 2.9178082191780823,
+      "grad_norm": 0.725835606196638,
+      "learning_rate": 9.225170811230058e-07,
+      "loss": 2.3067,
+      "step": 426
+    },
+    {
+      "epoch": 2.9246575342465753,
+      "grad_norm": 0.6776112672757169,
+      "learning_rate": 9.116421798124794e-07,
+      "loss": 2.2832,
+      "step": 427
+    },
+    {
+      "epoch": 2.9315068493150687,
+      "grad_norm": 0.7033324367359345,
+      "learning_rate": 9.008174461027724e-07,
+      "loss": 2.1292,
+      "step": 428
+    },
+    {
+      "epoch": 2.9383561643835616,
+      "grad_norm": 0.6838016967986851,
+      "learning_rate": 8.900432218884567e-07,
+      "loss": 2.2064,
+      "step": 429
+    },
+    {
+      "epoch": 2.9452054794520546,
+      "grad_norm": 0.7010714046350294,
+      "learning_rate": 8.793198474687861e-07,
+      "loss": 2.2926,
+      "step": 430
+    },
+    {
+      "epoch": 2.952054794520548,
+      "grad_norm": 0.7329321374936051,
+      "learning_rate": 8.686476615369452e-07,
+      "loss": 2.1508,
+      "step": 431
+    },
+    {
+      "epoch": 2.958904109589041,
+      "grad_norm": 0.7131247907500139,
+      "learning_rate": 8.580270011693498e-07,
+      "loss": 2.2816,
+      "step": 432
+    },
+    {
+      "epoch": 2.9657534246575343,
+      "grad_norm": 0.7307979149023858,
+      "learning_rate": 8.474582018150054e-07,
+      "loss": 2.2547,
+      "step": 433
+    },
+    {
+      "epoch": 2.9726027397260273,
+      "grad_norm": 0.72846919982668,
+      "learning_rate": 8.369415972849087e-07,
+      "loss": 2.2389,
+      "step": 434
+    },
+    {
+      "epoch": 2.9794520547945207,
+      "grad_norm": 0.7303659540542966,
+      "learning_rate": 8.264775197415054e-07,
+      "loss": 2.2541,
+      "step": 435
+    },
+    {
+      "epoch": 2.9863013698630136,
+      "grad_norm": 0.7122425099335468,
+      "learning_rate": 8.160662996881996e-07,
+      "loss": 2.1782,
+      "step": 436
+    },
+    {
+      "epoch": 2.993150684931507,
+      "grad_norm": 0.7278886861085458,
+      "learning_rate": 8.057082659589116e-07,
+      "loss": 2.2729,
+      "step": 437
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6862919290272542,
+      "learning_rate": 7.95403745707698e-07,
+      "loss": 2.26,
+      "step": 438
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 73,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 275124867563520.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-438/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d934e26af3264e6d7e311644e8dc78b1ed7ce7e5e06d3f478fb3f9146974b7
+size 8440

checkpoint-438/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)