Training in progress, step 420, checkpoint

checkpoint-420/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-420/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-420/global_step420/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:c813ca5704b3a55af21c2461ca46836ec1c7116c106667f29e63a1c0d9734bd8
+size 3402782855

checkpoint-420/global_step420/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:e214f5c76d81c63f597899ebdb6976644c2e75b7b412f489abf77a34da75e2f1
+size 3402782855

checkpoint-420/global_step420/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:cdbc53dcbe659794e602c4132ec1070afb10ae22f1c67217de68f681dad9033e
+size 3402782855

checkpoint-420/global_step420/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bdf9d812329d973f47c8ace5d099087eabf549ba32ec82ab385d8d6fa98417
+size 3402782855

checkpoint-420/global_step420/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6996cfd857f6011d6f2fe7784a0b98c2c695bce8d370406996145fa39d8fc01e
+size 3402782855

checkpoint-420/global_step420/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e198ca76899c328a5cf7028893c3418da0bd87d4aa1c2bb3334d5f1e18266cc0
+size 3402782855

checkpoint-420/global_step420/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e489615b9b4d022385c4b19565bb84d3e5135228a5833548e8527316cd79727b
+size 3402782855

checkpoint-420/global_step420/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c654aaa4e131d919ca9017fe76607aa7ba735e08e4491cb315ae1480ed853667
+size 3402782855

checkpoint-420/global_step420/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fbeadb39e83fd65423591c961a16686fd21c9cd5e2f3f81d939375861eeb22
+size 150245

checkpoint-420/global_step420/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd05af6e45ddba65500463600db0779648befb8f3d3e14b7ef70e38cb3eb08f7
+size 150245

checkpoint-420/global_step420/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ce2cffabee9954a963bcae6ffbb7a19c3c6c54c60547a3269264ccf9a032be
+size 150245

checkpoint-420/global_step420/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6143bf6a894e4f305f0f5a17ea69f2a55dd697db2c58f5eaef5fd981476bdb30
+size 150245

checkpoint-420/global_step420/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b84314532016a14d32c0011f4d737bb839b6d30501c49da1eb65db9c9318905
+size 150245

checkpoint-420/global_step420/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9d8b1ed7bd9c8dd6d112c28e94ecc4aa0eb007ac8cc825aca3f6191f839d35
+size 150245

checkpoint-420/global_step420/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f0873d4488beb0536ee4ec32b3df8aa91c36c58d61b88bd21c8bbdd036e4060
+size 150245

checkpoint-420/global_step420/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70ce5d6377fcde6d0accda733718ce14c09ad09d5678d26afa280470013ffd7
+size 150245

checkpoint-420/latest

@@ -0,0 +1 @@
+global_step420

checkpoint-420/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea48ffc540582401d1ec4465410ae43dd0884bc7429ca74bb660f8518ae0dc2
+size 4978354640

checkpoint-420/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4307b5a04e38aec5ef0b575f645e8064d538ad4efad47242d5cd8f325691f2
+size 4047172128

checkpoint-420/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-420/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0628a9017696045a3a29e9eaffc71e9262d855716e773c0c3be760a1fe85bc8
+size 15984

checkpoint-420/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df342004a4d8e3626bf2a9f689fde7c8bfd6d995e14931f5496eda1f456cb6f2
+size 15984

checkpoint-420/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02096eb4e8850b91490e80e4a042e2e60f71bd2abc6a269d62c271649cb77d2
+size 15984

checkpoint-420/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326c778d3d0e7e3d5665fa0a9ecd92986609c430da08b41611d6c05dc19815a8
+size 15984

checkpoint-420/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d978dcb0c34e022ee6750e9d86814b8c82e4965d7e07662f35f06eeac12938f3
+size 15984

checkpoint-420/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e83399aed1d9d173c3e07b2efa8530c956b62b2b68394c2ed0d43bd8bba9d1
+size 15984

checkpoint-420/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606ab3ca92e3d20c327c69fdcce7f7e39bec2f2c3538b036088b255f917e3ba4
+size 15984

checkpoint-420/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1276a987dd22c9093fec58921ba19f340a28f18bff635cc01324e09a3c37ac3a
+size 15984

checkpoint-420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335005782133f2fef2103c44db766999f6f6e1286ba705b565f67132fdf71586
+size 1064

checkpoint-420/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-420/tokenizer.json

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

checkpoint-420/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-420/trainer_state.json

@@ -0,0 +1,3014 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9988109393579072,
+  "eval_steps": 105,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023781212841854932,
+      "grad_norm": 32.74397118558861,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.9478,
+      "step": 1
+    },
+    {
+      "epoch": 0.0023781212841854932,
+      "eval_loss": 3.373392343521118,
+      "eval_runtime": 78.9756,
+      "eval_samples_per_second": 8.091,
+      "eval_steps_per_second": 1.013,
+      "step": 1
+    },
+    {
+      "epoch": 0.0047562425683709865,
+      "grad_norm": 37.080911592721954,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.8264,
+      "step": 2
+    },
+    {
+      "epoch": 0.007134363852556481,
+      "grad_norm": 31.107267997702266,
+      "learning_rate": 1.5e-06,
+      "loss": 2.9936,
+      "step": 3
+    },
+    {
+      "epoch": 0.009512485136741973,
+      "grad_norm": 27.574905774161167,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.8944,
+      "step": 4
+    },
+    {
+      "epoch": 0.011890606420927468,
+      "grad_norm": 13.643957484299273,
+      "learning_rate": 2.5e-06,
+      "loss": 2.7687,
+      "step": 5
+    },
+    {
+      "epoch": 0.014268727705112961,
+      "grad_norm": 15.077028980653411,
+      "learning_rate": 3e-06,
+      "loss": 2.6623,
+      "step": 6
+    },
+    {
+      "epoch": 0.016646848989298454,
+      "grad_norm": 14.569557474559408,
+      "learning_rate": 3.5e-06,
+      "loss": 2.9007,
+      "step": 7
+    },
+    {
+      "epoch": 0.019024970273483946,
+      "grad_norm": 13.894984550517007,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.8359,
+      "step": 8
+    },
+    {
+      "epoch": 0.02140309155766944,
+      "grad_norm": 13.546442233583257,
+      "learning_rate": 4.5e-06,
+      "loss": 2.7583,
+      "step": 9
+    },
+    {
+      "epoch": 0.023781212841854936,
+      "grad_norm": 11.166476039936938,
+      "learning_rate": 5e-06,
+      "loss": 2.518,
+      "step": 10
+    },
+    {
+      "epoch": 0.026159334126040427,
+      "grad_norm": 7.787448179397784,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 2.6494,
+      "step": 11
+    },
+    {
+      "epoch": 0.028537455410225922,
+      "grad_norm": 4.72349822440695,
+      "learning_rate": 6e-06,
+      "loss": 2.4022,
+      "step": 12
+    },
+    {
+      "epoch": 0.030915576694411414,
+      "grad_norm": 4.100722460414476,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 2.3933,
+      "step": 13
+    },
+    {
+      "epoch": 0.03329369797859691,
+      "grad_norm": 4.193151112965372,
+      "learning_rate": 7e-06,
+      "loss": 2.5468,
+      "step": 14
+    },
+    {
+      "epoch": 0.0356718192627824,
+      "grad_norm": 5.502246954578136,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 2.5126,
+      "step": 15
+    },
+    {
+      "epoch": 0.03804994054696789,
+      "grad_norm": 5.716937946349337,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.6761,
+      "step": 16
+    },
+    {
+      "epoch": 0.04042806183115339,
+      "grad_norm": 3.008867017303434,
+      "learning_rate": 8.5e-06,
+      "loss": 2.4264,
+      "step": 17
+    },
+    {
+      "epoch": 0.04280618311533888,
+      "grad_norm": 3.6016120293217178,
+      "learning_rate": 9e-06,
+      "loss": 2.3836,
+      "step": 18
+    },
+    {
+      "epoch": 0.04518430439952437,
+      "grad_norm": 2.1431386543975908,
+      "learning_rate": 9.5e-06,
+      "loss": 2.4879,
+      "step": 19
+    },
+    {
+      "epoch": 0.04756242568370987,
+      "grad_norm": 3.838539096237921,
+      "learning_rate": 1e-05,
+      "loss": 2.4116,
+      "step": 20
+    },
+    {
+      "epoch": 0.04994054696789536,
+      "grad_norm": 1.9119200890173822,
+      "learning_rate": 1.0500000000000001e-05,
+      "loss": 2.6716,
+      "step": 21
+    },
+    {
+      "epoch": 0.052318668252080855,
+      "grad_norm": 2.0853737807318904,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 2.4523,
+      "step": 22
+    },
+    {
+      "epoch": 0.054696789536266346,
+      "grad_norm": 1.6109539551135528,
+      "learning_rate": 1.15e-05,
+      "loss": 2.3086,
+      "step": 23
+    },
+    {
+      "epoch": 0.057074910820451845,
+      "grad_norm": 2.575933824126331,
+      "learning_rate": 1.2e-05,
+      "loss": 2.5576,
+      "step": 24
+    },
+    {
+      "epoch": 0.059453032104637336,
+      "grad_norm": 1.4827660467902501,
+      "learning_rate": 1.25e-05,
+      "loss": 2.264,
+      "step": 25
+    },
+    {
+      "epoch": 0.06183115338882283,
+      "grad_norm": 2.1022593224903128,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 2.8781,
+      "step": 26
+    },
+    {
+      "epoch": 0.06420927467300833,
+      "grad_norm": 2.756765764204405,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 2.5071,
+      "step": 27
+    },
+    {
+      "epoch": 0.06658739595719382,
+      "grad_norm": 1.6249455774563617,
+      "learning_rate": 1.4e-05,
+      "loss": 2.5085,
+      "step": 28
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 1.8653671914008603,
+      "learning_rate": 1.45e-05,
+      "loss": 2.4368,
+      "step": 29
+    },
+    {
+      "epoch": 0.0713436385255648,
+      "grad_norm": 1.867632087572305,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.1204,
+      "step": 30
+    },
+    {
+      "epoch": 0.07372175980975029,
+      "grad_norm": 1.2367329590346625,
+      "learning_rate": 1.55e-05,
+      "loss": 2.1118,
+      "step": 31
+    },
+    {
+      "epoch": 0.07609988109393578,
+      "grad_norm": 1.5969207000997636,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.4747,
+      "step": 32
+    },
+    {
+      "epoch": 0.07847800237812129,
+      "grad_norm": 1.5075133034220278,
+      "learning_rate": 1.65e-05,
+      "loss": 2.3349,
+      "step": 33
+    },
+    {
+      "epoch": 0.08085612366230678,
+      "grad_norm": 1.4803692479229955,
+      "learning_rate": 1.7e-05,
+      "loss": 2.3915,
+      "step": 34
+    },
+    {
+      "epoch": 0.08323424494649227,
+      "grad_norm": 2.692949771759104,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 2.6397,
+      "step": 35
+    },
+    {
+      "epoch": 0.08561236623067776,
+      "grad_norm": 1.3636512770329847,
+      "learning_rate": 1.8e-05,
+      "loss": 2.2944,
+      "step": 36
+    },
+    {
+      "epoch": 0.08799048751486326,
+      "grad_norm": 1.8310086696195464,
+      "learning_rate": 1.8500000000000002e-05,
+      "loss": 2.2614,
+      "step": 37
+    },
+    {
+      "epoch": 0.09036860879904875,
+      "grad_norm": 1.7765027708264853,
+      "learning_rate": 1.9e-05,
+      "loss": 2.3579,
+      "step": 38
+    },
+    {
+      "epoch": 0.09274673008323424,
+      "grad_norm": 1.4484769960901491,
+      "learning_rate": 1.95e-05,
+      "loss": 2.4548,
+      "step": 39
+    },
+    {
+      "epoch": 0.09512485136741974,
+      "grad_norm": 3.1520205275209414,
+      "learning_rate": 2e-05,
+      "loss": 2.5208,
+      "step": 40
+    },
+    {
+      "epoch": 0.09750297265160524,
+      "grad_norm": 1.5897739849482102,
+      "learning_rate": 1.9999981652287733e-05,
+      "loss": 2.4216,
+      "step": 41
+    },
+    {
+      "epoch": 0.09988109393579073,
+      "grad_norm": 2.4520591326987495,
+      "learning_rate": 1.999992660921826e-05,
+      "loss": 2.2326,
+      "step": 42
+    },
+    {
+      "epoch": 0.10225921521997622,
+      "grad_norm": 1.4817926319377914,
+      "learning_rate": 1.999983487099356e-05,
+      "loss": 2.541,
+      "step": 43
+    },
+    {
+      "epoch": 0.10463733650416171,
+      "grad_norm": 2.4022755616863956,
+      "learning_rate": 1.999970643795027e-05,
+      "loss": 2.3645,
+      "step": 44
+    },
+    {
+      "epoch": 0.1070154577883472,
+      "grad_norm": 2.476073007712477,
+      "learning_rate": 1.9999541310559686e-05,
+      "loss": 2.5051,
+      "step": 45
+    },
+    {
+      "epoch": 0.10939357907253269,
+      "grad_norm": 3.428213096316913,
+      "learning_rate": 1.9999339489427746e-05,
+      "loss": 2.3605,
+      "step": 46
+    },
+    {
+      "epoch": 0.1117717003567182,
+      "grad_norm": 2.464783346708793,
+      "learning_rate": 1.9999100975295046e-05,
+      "loss": 2.3785,
+      "step": 47
+    },
+    {
+      "epoch": 0.11414982164090369,
+      "grad_norm": 2.0686444585541754,
+      "learning_rate": 1.999882576903682e-05,
+      "loss": 2.6035,
+      "step": 48
+    },
+    {
+      "epoch": 0.11652794292508918,
+      "grad_norm": 2.30832669621963,
+      "learning_rate": 1.9998513871662945e-05,
+      "loss": 2.3982,
+      "step": 49
+    },
+    {
+      "epoch": 0.11890606420927467,
+      "grad_norm": 1.7443884357427357,
+      "learning_rate": 1.9998165284317944e-05,
+      "loss": 2.2344,
+      "step": 50
+    },
+    {
+      "epoch": 0.12128418549346016,
+      "grad_norm": 1.862498116501275,
+      "learning_rate": 1.999778000828098e-05,
+      "loss": 2.0631,
+      "step": 51
+    },
+    {
+      "epoch": 0.12366230677764566,
+      "grad_norm": 1.3054707043181313,
+      "learning_rate": 1.9997358044965833e-05,
+      "loss": 2.4434,
+      "step": 52
+    },
+    {
+      "epoch": 0.12604042806183116,
+      "grad_norm": 2.6645481874919583,
+      "learning_rate": 1.9996899395920915e-05,
+      "loss": 2.4647,
+      "step": 53
+    },
+    {
+      "epoch": 0.12841854934601665,
+      "grad_norm": 1.6884769054479885,
+      "learning_rate": 1.999640406282926e-05,
+      "loss": 2.2864,
+      "step": 54
+    },
+    {
+      "epoch": 0.13079667063020214,
+      "grad_norm": 2.281038989939936,
+      "learning_rate": 1.9995872047508516e-05,
+      "loss": 2.2999,
+      "step": 55
+    },
+    {
+      "epoch": 0.13317479191438764,
+      "grad_norm": 1.8457967068582515,
+      "learning_rate": 1.9995303351910934e-05,
+      "loss": 2.5117,
+      "step": 56
+    },
+    {
+      "epoch": 0.13555291319857313,
+      "grad_norm": 1.593901860141829,
+      "learning_rate": 1.9994697978123363e-05,
+      "loss": 2.1696,
+      "step": 57
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 2.168613470386471,
+      "learning_rate": 1.9994055928367256e-05,
+      "loss": 2.6852,
+      "step": 58
+    },
+    {
+      "epoch": 0.1403091557669441,
+      "grad_norm": 1.5398971278043392,
+      "learning_rate": 1.999337720499863e-05,
+      "loss": 2.396,
+      "step": 59
+    },
+    {
+      "epoch": 0.1426872770511296,
+      "grad_norm": 1.7618365641290346,
+      "learning_rate": 1.99926618105081e-05,
+      "loss": 2.047,
+      "step": 60
+    },
+    {
+      "epoch": 0.1450653983353151,
+      "grad_norm": 1.3935889380673343,
+      "learning_rate": 1.9991909747520835e-05,
+      "loss": 2.1071,
+      "step": 61
+    },
+    {
+      "epoch": 0.14744351961950058,
+      "grad_norm": 1.3063537354837544,
+      "learning_rate": 1.999112101879656e-05,
+      "loss": 2.3992,
+      "step": 62
+    },
+    {
+      "epoch": 0.14982164090368608,
+      "grad_norm": 1.025531260937785,
+      "learning_rate": 1.9990295627229544e-05,
+      "loss": 2.4764,
+      "step": 63
+    },
+    {
+      "epoch": 0.15219976218787157,
+      "grad_norm": 1.0662434476421614,
+      "learning_rate": 1.99894335758486e-05,
+      "loss": 2.0608,
+      "step": 64
+    },
+    {
+      "epoch": 0.1545778834720571,
+      "grad_norm": 1.335312659171346,
+      "learning_rate": 1.9988534867817065e-05,
+      "loss": 2.0345,
+      "step": 65
+    },
+    {
+      "epoch": 0.15695600475624258,
+      "grad_norm": 1.7866360477276542,
+      "learning_rate": 1.9987599506432785e-05,
+      "loss": 2.4781,
+      "step": 66
+    },
+    {
+      "epoch": 0.15933412604042807,
+      "grad_norm": 1.3661388854405736,
+      "learning_rate": 1.9986627495128105e-05,
+      "loss": 2.3895,
+      "step": 67
+    },
+    {
+      "epoch": 0.16171224732461356,
+      "grad_norm": 1.69413799763372,
+      "learning_rate": 1.9985618837469864e-05,
+      "loss": 2.415,
+      "step": 68
+    },
+    {
+      "epoch": 0.16409036860879905,
+      "grad_norm": 1.6458921632697698,
+      "learning_rate": 1.998457353715938e-05,
+      "loss": 2.4017,
+      "step": 69
+    },
+    {
+      "epoch": 0.16646848989298454,
+      "grad_norm": 1.705150979387567,
+      "learning_rate": 1.998349159803241e-05,
+      "loss": 2.317,
+      "step": 70
+    },
+    {
+      "epoch": 0.16884661117717004,
+      "grad_norm": 1.4786622132550975,
+      "learning_rate": 1.9982373024059195e-05,
+      "loss": 2.4046,
+      "step": 71
+    },
+    {
+      "epoch": 0.17122473246135553,
+      "grad_norm": 1.1257378401253821,
+      "learning_rate": 1.998121781934438e-05,
+      "loss": 2.196,
+      "step": 72
+    },
+    {
+      "epoch": 0.17360285374554102,
+      "grad_norm": 1.2450243917414825,
+      "learning_rate": 1.9980025988127037e-05,
+      "loss": 2.1235,
+      "step": 73
+    },
+    {
+      "epoch": 0.1759809750297265,
+      "grad_norm": 1.2574977788035384,
+      "learning_rate": 1.9978797534780646e-05,
+      "loss": 2.4466,
+      "step": 74
+    },
+    {
+      "epoch": 0.178359096313912,
+      "grad_norm": 1.390309850165232,
+      "learning_rate": 1.9977532463813064e-05,
+      "loss": 2.4469,
+      "step": 75
+    },
+    {
+      "epoch": 0.1807372175980975,
+      "grad_norm": 1.2146735833909619,
+      "learning_rate": 1.9976230779866527e-05,
+      "loss": 2.3705,
+      "step": 76
+    },
+    {
+      "epoch": 0.18311533888228299,
+      "grad_norm": 1.26356031715395,
+      "learning_rate": 1.9974892487717613e-05,
+      "loss": 2.4926,
+      "step": 77
+    },
+    {
+      "epoch": 0.18549346016646848,
+      "grad_norm": 1.3934309027656608,
+      "learning_rate": 1.997351759227725e-05,
+      "loss": 2.47,
+      "step": 78
+    },
+    {
+      "epoch": 0.187871581450654,
+      "grad_norm": 1.129998342751621,
+      "learning_rate": 1.9972106098590665e-05,
+      "loss": 2.3718,
+      "step": 79
+    },
+    {
+      "epoch": 0.1902497027348395,
+      "grad_norm": 1.3957720808228478,
+      "learning_rate": 1.9970658011837404e-05,
+      "loss": 2.2057,
+      "step": 80
+    },
+    {
+      "epoch": 0.19262782401902498,
+      "grad_norm": 1.5835508346410572,
+      "learning_rate": 1.9969173337331283e-05,
+      "loss": 2.2551,
+      "step": 81
+    },
+    {
+      "epoch": 0.19500594530321047,
+      "grad_norm": 1.0726363834452401,
+      "learning_rate": 1.996765208052037e-05,
+      "loss": 1.9962,
+      "step": 82
+    },
+    {
+      "epoch": 0.19738406658739596,
+      "grad_norm": 1.5380248440103288,
+      "learning_rate": 1.9966094246986983e-05,
+      "loss": 2.1986,
+      "step": 83
+    },
+    {
+      "epoch": 0.19976218787158145,
+      "grad_norm": 1.2953387209833067,
+      "learning_rate": 1.9964499842447665e-05,
+      "loss": 2.5842,
+      "step": 84
+    },
+    {
+      "epoch": 0.20214030915576695,
+      "grad_norm": 1.0712033116668103,
+      "learning_rate": 1.9962868872753144e-05,
+      "loss": 2.1298,
+      "step": 85
+    },
+    {
+      "epoch": 0.20451843043995244,
+      "grad_norm": 1.095761902776689,
+      "learning_rate": 1.996120134388834e-05,
+      "loss": 2.3641,
+      "step": 86
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 1.186679631328553,
+      "learning_rate": 1.995949726197231e-05,
+      "loss": 2.4801,
+      "step": 87
+    },
+    {
+      "epoch": 0.20927467300832342,
+      "grad_norm": 1.1887498108170933,
+      "learning_rate": 1.9957756633258264e-05,
+      "loss": 2.2866,
+      "step": 88
+    },
+    {
+      "epoch": 0.2116527942925089,
+      "grad_norm": 1.0909023774872124,
+      "learning_rate": 1.9955979464133515e-05,
+      "loss": 2.2916,
+      "step": 89
+    },
+    {
+      "epoch": 0.2140309155766944,
+      "grad_norm": 1.1077175360558418,
+      "learning_rate": 1.995416576111945e-05,
+      "loss": 2.1077,
+      "step": 90
+    },
+    {
+      "epoch": 0.2164090368608799,
+      "grad_norm": 1.1526064687436712,
+      "learning_rate": 1.9952315530871537e-05,
+      "loss": 2.2723,
+      "step": 91
+    },
+    {
+      "epoch": 0.21878715814506539,
+      "grad_norm": 1.1818210038912647,
+      "learning_rate": 1.9950428780179274e-05,
+      "loss": 2.2338,
+      "step": 92
+    },
+    {
+      "epoch": 0.2211652794292509,
+      "grad_norm": 1.164942154271255,
+      "learning_rate": 1.994850551596617e-05,
+      "loss": 2.3817,
+      "step": 93
+    },
+    {
+      "epoch": 0.2235434007134364,
+      "grad_norm": 1.339398993177121,
+      "learning_rate": 1.9946545745289727e-05,
+      "loss": 2.5508,
+      "step": 94
+    },
+    {
+      "epoch": 0.2259215219976219,
+      "grad_norm": 1.3267763052855093,
+      "learning_rate": 1.9944549475341404e-05,
+      "loss": 2.247,
+      "step": 95
+    },
+    {
+      "epoch": 0.22829964328180738,
+      "grad_norm": 1.1953250811556597,
+      "learning_rate": 1.99425167134466e-05,
+      "loss": 2.3373,
+      "step": 96
+    },
+    {
+      "epoch": 0.23067776456599287,
+      "grad_norm": 1.4321452409301854,
+      "learning_rate": 1.9940447467064624e-05,
+      "loss": 2.4776,
+      "step": 97
+    },
+    {
+      "epoch": 0.23305588585017836,
+      "grad_norm": 1.0224444212683161,
+      "learning_rate": 1.9938341743788658e-05,
+      "loss": 2.1837,
+      "step": 98
+    },
+    {
+      "epoch": 0.23543400713436385,
+      "grad_norm": 1.0977574950238398,
+      "learning_rate": 1.9936199551345744e-05,
+      "loss": 2.1478,
+      "step": 99
+    },
+    {
+      "epoch": 0.23781212841854935,
+      "grad_norm": 1.0660069054078747,
+      "learning_rate": 1.9934020897596752e-05,
+      "loss": 2.2816,
+      "step": 100
+    },
+    {
+      "epoch": 0.24019024970273484,
+      "grad_norm": 1.0312993672336248,
+      "learning_rate": 1.9931805790536342e-05,
+      "loss": 2.2468,
+      "step": 101
+    },
+    {
+      "epoch": 0.24256837098692033,
+      "grad_norm": 1.1278898252066067,
+      "learning_rate": 1.9929554238292944e-05,
+      "loss": 2.0526,
+      "step": 102
+    },
+    {
+      "epoch": 0.24494649227110582,
+      "grad_norm": 1.288343002944789,
+      "learning_rate": 1.992726624912872e-05,
+      "loss": 2.512,
+      "step": 103
+    },
+    {
+      "epoch": 0.2473246135552913,
+      "grad_norm": 1.1840020386119305,
+      "learning_rate": 1.992494183143955e-05,
+      "loss": 2.6356,
+      "step": 104
+    },
+    {
+      "epoch": 0.2497027348394768,
+      "grad_norm": 1.1014678408276726,
+      "learning_rate": 1.9922580993754985e-05,
+      "loss": 2.3521,
+      "step": 105
+    },
+    {
+      "epoch": 0.2497027348394768,
+      "eval_loss": 2.5365779399871826,
+      "eval_runtime": 66.0796,
+      "eval_samples_per_second": 9.67,
+      "eval_steps_per_second": 1.211,
+      "step": 105
+    },
+    {
+      "epoch": 0.2520808561236623,
+      "grad_norm": 0.9957844757920508,
+      "learning_rate": 1.9920183744738208e-05,
+      "loss": 2.355,
+      "step": 106
+    },
+    {
+      "epoch": 0.2544589774078478,
+      "grad_norm": 1.0070598447313825,
+      "learning_rate": 1.9917750093186036e-05,
+      "loss": 2.1747,
+      "step": 107
+    },
+    {
+      "epoch": 0.2568370986920333,
+      "grad_norm": 1.2463453868295562,
+      "learning_rate": 1.9915280048028853e-05,
+      "loss": 2.4131,
+      "step": 108
+    },
+    {
+      "epoch": 0.25921521997621877,
+      "grad_norm": 1.158558292534161,
+      "learning_rate": 1.9912773618330595e-05,
+      "loss": 2.4527,
+      "step": 109
+    },
+    {
+      "epoch": 0.2615933412604043,
+      "grad_norm": 1.1875643459332377,
+      "learning_rate": 1.9910230813288713e-05,
+      "loss": 2.1523,
+      "step": 110
+    },
+    {
+      "epoch": 0.26397146254458975,
+      "grad_norm": 0.892269173897758,
+      "learning_rate": 1.9907651642234138e-05,
+      "loss": 1.9606,
+      "step": 111
+    },
+    {
+      "epoch": 0.26634958382877527,
+      "grad_norm": 1.181952902180908,
+      "learning_rate": 1.9905036114631247e-05,
+      "loss": 2.3201,
+      "step": 112
+    },
+    {
+      "epoch": 0.26872770511296074,
+      "grad_norm": 0.9689153704257877,
+      "learning_rate": 1.990238424007783e-05,
+      "loss": 2.2329,
+      "step": 113
+    },
+    {
+      "epoch": 0.27110582639714625,
+      "grad_norm": 1.3665918769424286,
+      "learning_rate": 1.989969602830505e-05,
+      "loss": 2.2387,
+      "step": 114
+    },
+    {
+      "epoch": 0.2734839476813318,
+      "grad_norm": 1.0478434719151144,
+      "learning_rate": 1.9896971489177417e-05,
+      "loss": 2.2798,
+      "step": 115
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 1.5752154316391798,
+      "learning_rate": 1.9894210632692745e-05,
+      "loss": 2.201,
+      "step": 116
+    },
+    {
+      "epoch": 0.27824019024970276,
+      "grad_norm": 1.0264277011384757,
+      "learning_rate": 1.9891413468982112e-05,
+      "loss": 2.2756,
+      "step": 117
+    },
+    {
+      "epoch": 0.2806183115338882,
+      "grad_norm": 1.1750703393359614,
+      "learning_rate": 1.988858000830983e-05,
+      "loss": 2.1907,
+      "step": 118
+    },
+    {
+      "epoch": 0.28299643281807374,
+      "grad_norm": 0.9456957190962577,
+      "learning_rate": 1.9885710261073402e-05,
+      "loss": 2.2993,
+      "step": 119
+    },
+    {
+      "epoch": 0.2853745541022592,
+      "grad_norm": 1.37591692336223,
+      "learning_rate": 1.9882804237803487e-05,
+      "loss": 2.0751,
+      "step": 120
+    },
+    {
+      "epoch": 0.2877526753864447,
+      "grad_norm": 0.991181263305241,
+      "learning_rate": 1.9879861949163863e-05,
+      "loss": 2.1946,
+      "step": 121
+    },
+    {
+      "epoch": 0.2901307966706302,
+      "grad_norm": 1.2826616603092615,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 2.3084,
+      "step": 122
+    },
+    {
+      "epoch": 0.2925089179548157,
+      "grad_norm": 1.3162982027829009,
+      "learning_rate": 1.987386861909593e-05,
+      "loss": 2.294,
+      "step": 123
+    },
+    {
+      "epoch": 0.29488703923900117,
+      "grad_norm": 1.086311999313279,
+      "learning_rate": 1.98708175996604e-05,
+      "loss": 2.3025,
+      "step": 124
+    },
+    {
+      "epoch": 0.2972651605231867,
+      "grad_norm": 1.10683170372015,
+      "learning_rate": 1.986773035884064e-05,
+      "loss": 2.3447,
+      "step": 125
+    },
+    {
+      "epoch": 0.29964328180737215,
+      "grad_norm": 1.090568761480393,
+      "learning_rate": 1.9864606907965407e-05,
+      "loss": 2.4104,
+      "step": 126
+    },
+    {
+      "epoch": 0.30202140309155767,
+      "grad_norm": 1.4024759238343605,
+      "learning_rate": 1.986144725849634e-05,
+      "loss": 2.298,
+      "step": 127
+    },
+    {
+      "epoch": 0.30439952437574314,
+      "grad_norm": 0.9324914520062791,
+      "learning_rate": 1.9858251422027903e-05,
+      "loss": 2.1123,
+      "step": 128
+    },
+    {
+      "epoch": 0.30677764565992865,
+      "grad_norm": 1.3818136151492852,
+      "learning_rate": 1.9855019410287355e-05,
+      "loss": 2.2786,
+      "step": 129
+    },
+    {
+      "epoch": 0.3091557669441142,
+      "grad_norm": 0.9879756737720099,
+      "learning_rate": 1.98517512351347e-05,
+      "loss": 2.2735,
+      "step": 130
+    },
+    {
+      "epoch": 0.31153388822829964,
+      "grad_norm": 1.4107106057474024,
+      "learning_rate": 1.9848446908562647e-05,
+      "loss": 2.2421,
+      "step": 131
+    },
+    {
+      "epoch": 0.31391200951248516,
+      "grad_norm": 0.978862094447652,
+      "learning_rate": 1.9845106442696563e-05,
+      "loss": 2.4152,
+      "step": 132
+    },
+    {
+      "epoch": 0.3162901307966706,
+      "grad_norm": 1.3714074038447606,
+      "learning_rate": 1.9841729849794427e-05,
+      "loss": 2.4567,
+      "step": 133
+    },
+    {
+      "epoch": 0.31866825208085614,
+      "grad_norm": 1.030641093673837,
+      "learning_rate": 1.983831714224679e-05,
+      "loss": 2.3015,
+      "step": 134
+    },
+    {
+      "epoch": 0.3210463733650416,
+      "grad_norm": 1.1744699755999302,
+      "learning_rate": 1.9834868332576727e-05,
+      "loss": 2.2878,
+      "step": 135
+    },
+    {
+      "epoch": 0.3234244946492271,
+      "grad_norm": 0.9733999816490441,
+      "learning_rate": 1.9831383433439798e-05,
+      "loss": 2.1571,
+      "step": 136
+    },
+    {
+      "epoch": 0.3258026159334126,
+      "grad_norm": 1.0470367999253474,
+      "learning_rate": 1.982786245762398e-05,
+      "loss": 2.0943,
+      "step": 137
+    },
+    {
+      "epoch": 0.3281807372175981,
+      "grad_norm": 1.0748276455064096,
+      "learning_rate": 1.9824305418049645e-05,
+      "loss": 2.4156,
+      "step": 138
+    },
+    {
+      "epoch": 0.33055885850178357,
+      "grad_norm": 1.0220509349947084,
+      "learning_rate": 1.9820712327769503e-05,
+      "loss": 2.1898,
+      "step": 139
+    },
+    {
+      "epoch": 0.3329369797859691,
+      "grad_norm": 0.9811166423920332,
+      "learning_rate": 1.9817083199968552e-05,
+      "loss": 2.3449,
+      "step": 140
+    },
+    {
+      "epoch": 0.33531510107015455,
+      "grad_norm": 1.0664757695722766,
+      "learning_rate": 1.9813418047964025e-05,
+      "loss": 2.1514,
+      "step": 141
+    },
+    {
+      "epoch": 0.3376932223543401,
+      "grad_norm": 1.1228830278366924,
+      "learning_rate": 1.9809716885205363e-05,
+      "loss": 2.3371,
+      "step": 142
+    },
+    {
+      "epoch": 0.3400713436385256,
+      "grad_norm": 1.0703957613617774,
+      "learning_rate": 1.980597972527413e-05,
+      "loss": 2.2577,
+      "step": 143
+    },
+    {
+      "epoch": 0.34244946492271106,
+      "grad_norm": 0.9971842999532138,
+      "learning_rate": 1.9802206581883992e-05,
+      "loss": 2.2048,
+      "step": 144
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.9969712850303254,
+      "learning_rate": 1.979839746888067e-05,
+      "loss": 2.1725,
+      "step": 145
+    },
+    {
+      "epoch": 0.34720570749108204,
+      "grad_norm": 0.9782490093980141,
+      "learning_rate": 1.979455240024186e-05,
+      "loss": 2.1598,
+      "step": 146
+    },
+    {
+      "epoch": 0.34958382877526756,
+      "grad_norm": 1.1595035293528873,
+      "learning_rate": 1.97906713900772e-05,
+      "loss": 2.1812,
+      "step": 147
+    },
+    {
+      "epoch": 0.351961950059453,
+      "grad_norm": 1.0488323565717943,
+      "learning_rate": 1.9786754452628226e-05,
+      "loss": 2.126,
+      "step": 148
+    },
+    {
+      "epoch": 0.35434007134363854,
+      "grad_norm": 1.0236205683546673,
+      "learning_rate": 1.9782801602268306e-05,
+      "loss": 1.9399,
+      "step": 149
+    },
+    {
+      "epoch": 0.356718192627824,
+      "grad_norm": 0.983049547537296,
+      "learning_rate": 1.9778812853502592e-05,
+      "loss": 2.0336,
+      "step": 150
+    },
+    {
+      "epoch": 0.3590963139120095,
+      "grad_norm": 1.0856474713800959,
+      "learning_rate": 1.9774788220967968e-05,
+      "loss": 2.2103,
+      "step": 151
+    },
+    {
+      "epoch": 0.361474435196195,
+      "grad_norm": 1.098143269144179,
+      "learning_rate": 1.9770727719432994e-05,
+      "loss": 2.1425,
+      "step": 152
+    },
+    {
+      "epoch": 0.3638525564803805,
+      "grad_norm": 1.1908904777112574,
+      "learning_rate": 1.9766631363797852e-05,
+      "loss": 2.2516,
+      "step": 153
+    },
+    {
+      "epoch": 0.36623067776456597,
+      "grad_norm": 1.1823343263781934,
+      "learning_rate": 1.9762499169094288e-05,
+      "loss": 2.0991,
+      "step": 154
+    },
+    {
+      "epoch": 0.3686087990487515,
+      "grad_norm": 1.1543274307271654,
+      "learning_rate": 1.9758331150485576e-05,
+      "loss": 2.2917,
+      "step": 155
+    },
+    {
+      "epoch": 0.37098692033293695,
+      "grad_norm": 1.1828452156246019,
+      "learning_rate": 1.9754127323266426e-05,
+      "loss": 2.3577,
+      "step": 156
+    },
+    {
+      "epoch": 0.3733650416171225,
+      "grad_norm": 1.2458434785978698,
+      "learning_rate": 1.9749887702862972e-05,
+      "loss": 2.2291,
+      "step": 157
+    },
+    {
+      "epoch": 0.375743162901308,
+      "grad_norm": 1.0632348458757013,
+      "learning_rate": 1.9745612304832672e-05,
+      "loss": 2.495,
+      "step": 158
+    },
+    {
+      "epoch": 0.37812128418549346,
+      "grad_norm": 1.2413557275846534,
+      "learning_rate": 1.9741301144864284e-05,
+      "loss": 2.3006,
+      "step": 159
+    },
+    {
+      "epoch": 0.380499405469679,
+      "grad_norm": 1.068837985332943,
+      "learning_rate": 1.9736954238777793e-05,
+      "loss": 2.2228,
+      "step": 160
+    },
+    {
+      "epoch": 0.38287752675386444,
+      "grad_norm": 1.181973772137545,
+      "learning_rate": 1.9732571602524353e-05,
+      "loss": 2.3419,
+      "step": 161
+    },
+    {
+      "epoch": 0.38525564803804996,
+      "grad_norm": 0.9361759344356807,
+      "learning_rate": 1.972815325218624e-05,
+      "loss": 2.2727,
+      "step": 162
+    },
+    {
+      "epoch": 0.3876337693222354,
+      "grad_norm": 1.2300672941710984,
+      "learning_rate": 1.9723699203976768e-05,
+      "loss": 2.3947,
+      "step": 163
+    },
+    {
+      "epoch": 0.39001189060642094,
+      "grad_norm": 0.9647921025871186,
+      "learning_rate": 1.9719209474240263e-05,
+      "loss": 1.8388,
+      "step": 164
+    },
+    {
+      "epoch": 0.3923900118906064,
+      "grad_norm": 1.1390311715526416,
+      "learning_rate": 1.971468407945198e-05,
+      "loss": 2.4054,
+      "step": 165
+    },
+    {
+      "epoch": 0.3947681331747919,
+      "grad_norm": 0.9830051867519547,
+      "learning_rate": 1.9710123036218044e-05,
+      "loss": 2.0355,
+      "step": 166
+    },
+    {
+      "epoch": 0.3971462544589774,
+      "grad_norm": 1.1244517585073737,
+      "learning_rate": 1.97055263612754e-05,
+      "loss": 2.0188,
+      "step": 167
+    },
+    {
+      "epoch": 0.3995243757431629,
+      "grad_norm": 1.0256020852263494,
+      "learning_rate": 1.9700894071491736e-05,
+      "loss": 2.0774,
+      "step": 168
+    },
+    {
+      "epoch": 0.40190249702734837,
+      "grad_norm": 1.011023720252716,
+      "learning_rate": 1.9696226183865436e-05,
+      "loss": 2.2592,
+      "step": 169
+    },
+    {
+      "epoch": 0.4042806183115339,
+      "grad_norm": 1.046975898884085,
+      "learning_rate": 1.969152271552552e-05,
+      "loss": 2.1791,
+      "step": 170
+    },
+    {
+      "epoch": 0.40665873959571935,
+      "grad_norm": 1.1800984480399852,
+      "learning_rate": 1.9686783683731557e-05,
+      "loss": 2.3941,
+      "step": 171
+    },
+    {
+      "epoch": 0.4090368608799049,
+      "grad_norm": 1.2459882622321672,
+      "learning_rate": 1.9682009105873633e-05,
+      "loss": 2.1522,
+      "step": 172
+    },
+    {
+      "epoch": 0.4114149821640904,
+      "grad_norm": 1.0732133381850257,
+      "learning_rate": 1.9677198999472257e-05,
+      "loss": 2.1233,
+      "step": 173
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 1.2405484917580802,
+      "learning_rate": 1.967235338217832e-05,
+      "loss": 2.3016,
+      "step": 174
+    },
+    {
+      "epoch": 0.4161712247324614,
+      "grad_norm": 1.0759940201219593,
+      "learning_rate": 1.9667472271773026e-05,
+      "loss": 2.2947,
+      "step": 175
+    },
+    {
+      "epoch": 0.41854934601664684,
+      "grad_norm": 1.2008734320661734,
+      "learning_rate": 1.9662555686167808e-05,
+      "loss": 2.2155,
+      "step": 176
+    },
+    {
+      "epoch": 0.42092746730083236,
+      "grad_norm": 0.9303619935178572,
+      "learning_rate": 1.965760364340429e-05,
+      "loss": 2.1234,
+      "step": 177
+    },
+    {
+      "epoch": 0.4233055885850178,
+      "grad_norm": 1.3884826767438652,
+      "learning_rate": 1.9652616161654204e-05,
+      "loss": 2.2539,
+      "step": 178
+    },
+    {
+      "epoch": 0.42568370986920334,
+      "grad_norm": 0.9947187673832885,
+      "learning_rate": 1.9647593259219328e-05,
+      "loss": 2.2052,
+      "step": 179
+    },
+    {
+      "epoch": 0.4280618311533888,
+      "grad_norm": 1.4655922792083054,
+      "learning_rate": 1.964253495453141e-05,
+      "loss": 2.1552,
+      "step": 180
+    },
+    {
+      "epoch": 0.4304399524375743,
+      "grad_norm": 1.1481294188693778,
+      "learning_rate": 1.963744126615212e-05,
+      "loss": 2.3942,
+      "step": 181
+    },
+    {
+      "epoch": 0.4328180737217598,
+      "grad_norm": 1.239760521409481,
+      "learning_rate": 1.9632312212772956e-05,
+      "loss": 2.3091,
+      "step": 182
+    },
+    {
+      "epoch": 0.4351961950059453,
+      "grad_norm": 1.0524654460411744,
+      "learning_rate": 1.9627147813215207e-05,
+      "loss": 2.302,
+      "step": 183
+    },
+    {
+      "epoch": 0.43757431629013077,
+      "grad_norm": 1.0231645108607732,
+      "learning_rate": 1.9621948086429847e-05,
+      "loss": 2.2334,
+      "step": 184
+    },
+    {
+      "epoch": 0.4399524375743163,
+      "grad_norm": 1.0600582051447691,
+      "learning_rate": 1.9616713051497496e-05,
+      "loss": 2.2044,
+      "step": 185
+    },
+    {
+      "epoch": 0.4423305588585018,
+      "grad_norm": 1.0861978175484295,
+      "learning_rate": 1.9611442727628344e-05,
+      "loss": 2.3267,
+      "step": 186
+    },
+    {
+      "epoch": 0.4447086801426873,
+      "grad_norm": 1.0122924353396487,
+      "learning_rate": 1.960613713416206e-05,
+      "loss": 2.2327,
+      "step": 187
+    },
+    {
+      "epoch": 0.4470868014268728,
+      "grad_norm": 1.1275635495135592,
+      "learning_rate": 1.9600796290567747e-05,
+      "loss": 2.2474,
+      "step": 188
+    },
+    {
+      "epoch": 0.44946492271105826,
+      "grad_norm": 1.0778906611663819,
+      "learning_rate": 1.9595420216443864e-05,
+      "loss": 2.2777,
+      "step": 189
+    },
+    {
+      "epoch": 0.4518430439952438,
+      "grad_norm": 1.0593499669893551,
+      "learning_rate": 1.9590008931518133e-05,
+      "loss": 2.4937,
+      "step": 190
+    },
+    {
+      "epoch": 0.45422116527942924,
+      "grad_norm": 1.0887914371115388,
+      "learning_rate": 1.9584562455647494e-05,
+      "loss": 2.2577,
+      "step": 191
+    },
+    {
+      "epoch": 0.45659928656361476,
+      "grad_norm": 1.0280779311785984,
+      "learning_rate": 1.9579080808818035e-05,
+      "loss": 2.2352,
+      "step": 192
+    },
+    {
+      "epoch": 0.4589774078478002,
+      "grad_norm": 1.1201705856067985,
+      "learning_rate": 1.9573564011144873e-05,
+      "loss": 2.1482,
+      "step": 193
+    },
+    {
+      "epoch": 0.46135552913198574,
+      "grad_norm": 1.0039435227655624,
+      "learning_rate": 1.9568012082872148e-05,
+      "loss": 2.1069,
+      "step": 194
+    },
+    {
+      "epoch": 0.4637336504161712,
+      "grad_norm": 1.0523831000821406,
+      "learning_rate": 1.9562425044372884e-05,
+      "loss": 1.9268,
+      "step": 195
+    },
+    {
+      "epoch": 0.4661117717003567,
+      "grad_norm": 1.0635880350342213,
+      "learning_rate": 1.9556802916148963e-05,
+      "loss": 2.2722,
+      "step": 196
+    },
+    {
+      "epoch": 0.4684898929845422,
+      "grad_norm": 2.4351848601787287,
+      "learning_rate": 1.955114571883102e-05,
+      "loss": 2.1402,
+      "step": 197
+    },
+    {
+      "epoch": 0.4708680142687277,
+      "grad_norm": 1.2199308274597462,
+      "learning_rate": 1.9545453473178384e-05,
+      "loss": 2.2599,
+      "step": 198
+    },
+    {
+      "epoch": 0.47324613555291317,
+      "grad_norm": 0.9936114796299212,
+      "learning_rate": 1.9539726200078987e-05,
+      "loss": 2.0662,
+      "step": 199
+    },
+    {
+      "epoch": 0.4756242568370987,
+      "grad_norm": 1.0692703333507547,
+      "learning_rate": 1.9533963920549307e-05,
+      "loss": 2.3739,
+      "step": 200
+    },
+    {
+      "epoch": 0.4780023781212842,
+      "grad_norm": 1.0406002686664542,
+      "learning_rate": 1.9528166655734267e-05,
+      "loss": 2.3611,
+      "step": 201
+    },
+    {
+      "epoch": 0.4803804994054697,
+      "grad_norm": 1.9375905536343168,
+      "learning_rate": 1.9522334426907185e-05,
+      "loss": 2.0971,
+      "step": 202
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 1.024548704059581,
+      "learning_rate": 1.951646725546966e-05,
+      "loss": 2.2498,
+      "step": 203
+    },
+    {
+      "epoch": 0.48513674197384066,
+      "grad_norm": 1.0033895284405978,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 2.299,
+      "step": 204
+    },
+    {
+      "epoch": 0.4875148632580262,
+      "grad_norm": 1.541631519071697,
+      "learning_rate": 1.950462817101079e-05,
+      "loss": 2.4076,
+      "step": 205
+    },
+    {
+      "epoch": 0.48989298454221164,
+      "grad_norm": 0.9499702987331401,
+      "learning_rate": 1.9498656301433466e-05,
+      "loss": 2.0754,
+      "step": 206
+    },
+    {
+      "epoch": 0.49227110582639716,
+      "grad_norm": 1.099383371761328,
+      "learning_rate": 1.9492649576133594e-05,
+      "loss": 2.2514,
+      "step": 207
+    },
+    {
+      "epoch": 0.4946492271105826,
+      "grad_norm": 0.9296431838496088,
+      "learning_rate": 1.94866080171531e-05,
+      "loss": 2.2308,
+      "step": 208
+    },
+    {
+      "epoch": 0.49702734839476814,
+      "grad_norm": 4.140796209905845,
+      "learning_rate": 1.9480531646661753e-05,
+      "loss": 2.4388,
+      "step": 209
+    },
+    {
+      "epoch": 0.4994054696789536,
+      "grad_norm": 1.011142238194789,
+      "learning_rate": 1.9474420486957045e-05,
+      "loss": 2.2414,
+      "step": 210
+    },
+    {
+      "epoch": 0.4994054696789536,
+      "eval_loss": 2.49302339553833,
+      "eval_runtime": 65.8636,
+      "eval_samples_per_second": 9.702,
+      "eval_steps_per_second": 1.215,
+      "step": 210
+    },
+    {
+      "epoch": 0.5017835909631391,
+      "grad_norm": 0.9941401750604694,
+      "learning_rate": 1.9468274560464134e-05,
+      "loss": 2.2182,
+      "step": 211
+    },
+    {
+      "epoch": 0.5041617122473246,
+      "grad_norm": 1.035068690961865,
+      "learning_rate": 1.9462093889735766e-05,
+      "loss": 2.3569,
+      "step": 212
+    },
+    {
+      "epoch": 0.5065398335315101,
+      "grad_norm": 1.5052185888965133,
+      "learning_rate": 1.945587849745217e-05,
+      "loss": 2.4474,
+      "step": 213
+    },
+    {
+      "epoch": 0.5089179548156956,
+      "grad_norm": 1.01730612362564,
+      "learning_rate": 1.944962840642099e-05,
+      "loss": 2.3912,
+      "step": 214
+    },
+    {
+      "epoch": 0.5112960760998811,
+      "grad_norm": 0.9513743221196854,
+      "learning_rate": 1.9443343639577206e-05,
+      "loss": 2.2842,
+      "step": 215
+    },
+    {
+      "epoch": 0.5136741973840666,
+      "grad_norm": 0.9759286606572132,
+      "learning_rate": 1.943702421998303e-05,
+      "loss": 2.3117,
+      "step": 216
+    },
+    {
+      "epoch": 0.5160523186682521,
+      "grad_norm": 0.9357816333722543,
+      "learning_rate": 1.9430670170827844e-05,
+      "loss": 2.1091,
+      "step": 217
+    },
+    {
+      "epoch": 0.5184304399524375,
+      "grad_norm": 1.1804547022456764,
+      "learning_rate": 1.94242815154281e-05,
+      "loss": 2.2333,
+      "step": 218
+    },
+    {
+      "epoch": 0.5208085612366231,
+      "grad_norm": 1.0289463651234612,
+      "learning_rate": 1.9417858277227244e-05,
+      "loss": 2.0495,
+      "step": 219
+    },
+    {
+      "epoch": 0.5231866825208086,
+      "grad_norm": 0.9297621773216459,
+      "learning_rate": 1.9411400479795618e-05,
+      "loss": 2.2102,
+      "step": 220
+    },
+    {
+      "epoch": 0.525564803804994,
+      "grad_norm": 0.9468558483075745,
+      "learning_rate": 1.9404908146830383e-05,
+      "loss": 2.2593,
+      "step": 221
+    },
+    {
+      "epoch": 0.5279429250891795,
+      "grad_norm": 1.03418169808611,
+      "learning_rate": 1.9398381302155435e-05,
+      "loss": 2.185,
+      "step": 222
+    },
+    {
+      "epoch": 0.5303210463733651,
+      "grad_norm": 0.84914434823741,
+      "learning_rate": 1.93918199697213e-05,
+      "loss": 1.8499,
+      "step": 223
+    },
+    {
+      "epoch": 0.5326991676575505,
+      "grad_norm": 1.0824133835143805,
+      "learning_rate": 1.9385224173605072e-05,
+      "loss": 2.2171,
+      "step": 224
+    },
+    {
+      "epoch": 0.535077288941736,
+      "grad_norm": 0.9478237708740055,
+      "learning_rate": 1.9378593938010302e-05,
+      "loss": 2.2397,
+      "step": 225
+    },
+    {
+      "epoch": 0.5374554102259215,
+      "grad_norm": 2.4277055664527065,
+      "learning_rate": 1.937192928726692e-05,
+      "loss": 2.2262,
+      "step": 226
+    },
+    {
+      "epoch": 0.539833531510107,
+      "grad_norm": 1.5223794932859396,
+      "learning_rate": 1.936523024583115e-05,
+      "loss": 2.2664,
+      "step": 227
+    },
+    {
+      "epoch": 0.5422116527942925,
+      "grad_norm": 1.2991334808397113,
+      "learning_rate": 1.9358496838285408e-05,
+      "loss": 2.1967,
+      "step": 228
+    },
+    {
+      "epoch": 0.544589774078478,
+      "grad_norm": 1.132823106642245,
+      "learning_rate": 1.9351729089338214e-05,
+      "loss": 2.2516,
+      "step": 229
+    },
+    {
+      "epoch": 0.5469678953626635,
+      "grad_norm": 1.0872118899678849,
+      "learning_rate": 1.9344927023824112e-05,
+      "loss": 2.3602,
+      "step": 230
+    },
+    {
+      "epoch": 0.549346016646849,
+      "grad_norm": 0.9596136441748024,
+      "learning_rate": 1.933809066670357e-05,
+      "loss": 2.3944,
+      "step": 231
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 1.3340981902899025,
+      "learning_rate": 1.9331220043062894e-05,
+      "loss": 1.8085,
+      "step": 232
+    },
+    {
+      "epoch": 0.5541022592152199,
+      "grad_norm": 0.9780209403031624,
+      "learning_rate": 1.9324315178114127e-05,
+      "loss": 2.2626,
+      "step": 233
+    },
+    {
+      "epoch": 0.5564803804994055,
+      "grad_norm": 0.8441113781121591,
+      "learning_rate": 1.9317376097194964e-05,
+      "loss": 1.904,
+      "step": 234
+    },
+    {
+      "epoch": 0.558858501783591,
+      "grad_norm": 0.9000708142025062,
+      "learning_rate": 1.9310402825768655e-05,
+      "loss": 2.1239,
+      "step": 235
+    },
+    {
+      "epoch": 0.5612366230677764,
+      "grad_norm": 0.9819927724537073,
+      "learning_rate": 1.9303395389423918e-05,
+      "loss": 2.2526,
+      "step": 236
+    },
+    {
+      "epoch": 0.5636147443519619,
+      "grad_norm": 0.9835396213176555,
+      "learning_rate": 1.9296353813874838e-05,
+      "loss": 2.1293,
+      "step": 237
+    },
+    {
+      "epoch": 0.5659928656361475,
+      "grad_norm": 0.8705520689865173,
+      "learning_rate": 1.9289278124960777e-05,
+      "loss": 1.9911,
+      "step": 238
+    },
+    {
+      "epoch": 0.5683709869203329,
+      "grad_norm": 1.0080028925541162,
+      "learning_rate": 1.9282168348646268e-05,
+      "loss": 2.0903,
+      "step": 239
+    },
+    {
+      "epoch": 0.5707491082045184,
+      "grad_norm": 1.0304202570689127,
+      "learning_rate": 1.927502451102095e-05,
+      "loss": 2.0784,
+      "step": 240
+    },
+    {
+      "epoch": 0.5731272294887039,
+      "grad_norm": 1.0836386452615874,
+      "learning_rate": 1.926784663829943e-05,
+      "loss": 2.2297,
+      "step": 241
+    },
+    {
+      "epoch": 0.5755053507728894,
+      "grad_norm": 0.972327672270083,
+      "learning_rate": 1.926063475682121e-05,
+      "loss": 2.2518,
+      "step": 242
+    },
+    {
+      "epoch": 0.5778834720570749,
+      "grad_norm": 1.1250553185490555,
+      "learning_rate": 1.9253388893050612e-05,
+      "loss": 2.2419,
+      "step": 243
+    },
+    {
+      "epoch": 0.5802615933412604,
+      "grad_norm": 1.6628057931903235,
+      "learning_rate": 1.924610907357663e-05,
+      "loss": 2.2409,
+      "step": 244
+    },
+    {
+      "epoch": 0.582639714625446,
+      "grad_norm": 1.3164993193299928,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 2.4277,
+      "step": 245
+    },
+    {
+      "epoch": 0.5850178359096314,
+      "grad_norm": 0.9607216662774912,
+      "learning_rate": 1.9231447674497444e-05,
+      "loss": 2.0357,
+      "step": 246
+    },
+    {
+      "epoch": 0.5873959571938169,
+      "grad_norm": 0.9753564233974246,
+      "learning_rate": 1.922406614869287e-05,
+      "loss": 2.1743,
+      "step": 247
+    },
+    {
+      "epoch": 0.5897740784780023,
+      "grad_norm": 0.9514731158004311,
+      "learning_rate": 1.9216650774785975e-05,
+      "loss": 2.2775,
+      "step": 248
+    },
+    {
+      "epoch": 0.5921521997621879,
+      "grad_norm": 1.1514073630104866,
+      "learning_rate": 1.9209201579987777e-05,
+      "loss": 2.0307,
+      "step": 249
+    },
+    {
+      "epoch": 0.5945303210463734,
+      "grad_norm": 1.0070268666833808,
+      "learning_rate": 1.9201718591633417e-05,
+      "loss": 2.405,
+      "step": 250
+    },
+    {
+      "epoch": 0.5969084423305588,
+      "grad_norm": 0.9724192667298419,
+      "learning_rate": 1.9194201837182045e-05,
+      "loss": 2.3375,
+      "step": 251
+    },
+    {
+      "epoch": 0.5992865636147443,
+      "grad_norm": 0.9184225452723915,
+      "learning_rate": 1.9186651344216703e-05,
+      "loss": 2.0576,
+      "step": 252
+    },
+    {
+      "epoch": 0.6016646848989299,
+      "grad_norm": 0.9277770597042948,
+      "learning_rate": 1.9179067140444246e-05,
+      "loss": 2.065,
+      "step": 253
+    },
+    {
+      "epoch": 0.6040428061831153,
+      "grad_norm": 0.9971241617303254,
+      "learning_rate": 1.9171449253695233e-05,
+      "loss": 2.0388,
+      "step": 254
+    },
+    {
+      "epoch": 0.6064209274673008,
+      "grad_norm": 0.968526625269074,
+      "learning_rate": 1.9163797711923822e-05,
+      "loss": 2.2154,
+      "step": 255
+    },
+    {
+      "epoch": 0.6087990487514863,
+      "grad_norm": 1.0974259939522593,
+      "learning_rate": 1.9156112543207674e-05,
+      "loss": 2.0897,
+      "step": 256
+    },
+    {
+      "epoch": 0.6111771700356718,
+      "grad_norm": 1.0661979784688387,
+      "learning_rate": 1.9148393775747842e-05,
+      "loss": 2.3986,
+      "step": 257
+    },
+    {
+      "epoch": 0.6135552913198573,
+      "grad_norm": 1.3741439020152701,
+      "learning_rate": 1.9140641437868664e-05,
+      "loss": 2.1249,
+      "step": 258
+    },
+    {
+      "epoch": 0.6159334126040428,
+      "grad_norm": 0.9207355567454468,
+      "learning_rate": 1.913285555801768e-05,
+      "loss": 2.2715,
+      "step": 259
+    },
+    {
+      "epoch": 0.6183115338882283,
+      "grad_norm": 1.0171260467381849,
+      "learning_rate": 1.9125036164765502e-05,
+      "loss": 2.2638,
+      "step": 260
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.9849622761444283,
+      "learning_rate": 1.9117183286805726e-05,
+      "loss": 2.148,
+      "step": 261
+    },
+    {
+      "epoch": 0.6230677764565993,
+      "grad_norm": 1.384730629468189,
+      "learning_rate": 1.9109296952954826e-05,
+      "loss": 2.2442,
+      "step": 262
+    },
+    {
+      "epoch": 0.6254458977407847,
+      "grad_norm": 1.066860211861379,
+      "learning_rate": 1.9101377192152033e-05,
+      "loss": 2.451,
+      "step": 263
+    },
+    {
+      "epoch": 0.6278240190249703,
+      "grad_norm": 1.1537333721148562,
+      "learning_rate": 1.909342403345925e-05,
+      "loss": 2.3076,
+      "step": 264
+    },
+    {
+      "epoch": 0.6302021403091558,
+      "grad_norm": 1.388798426336895,
+      "learning_rate": 1.9085437506060925e-05,
+      "loss": 2.3458,
+      "step": 265
+    },
+    {
+      "epoch": 0.6325802615933412,
+      "grad_norm": 1.057136103530956,
+      "learning_rate": 1.9077417639263966e-05,
+      "loss": 2.1901,
+      "step": 266
+    },
+    {
+      "epoch": 0.6349583828775267,
+      "grad_norm": 1.0267855180849,
+      "learning_rate": 1.906936446249761e-05,
+      "loss": 2.2597,
+      "step": 267
+    },
+    {
+      "epoch": 0.6373365041617123,
+      "grad_norm": 0.984822259782258,
+      "learning_rate": 1.906127800531333e-05,
+      "loss": 1.9602,
+      "step": 268
+    },
+    {
+      "epoch": 0.6397146254458977,
+      "grad_norm": 1.0914462759031294,
+      "learning_rate": 1.905315829738473e-05,
+      "loss": 2.4246,
+      "step": 269
+    },
+    {
+      "epoch": 0.6420927467300832,
+      "grad_norm": 1.007066333419377,
+      "learning_rate": 1.9045005368507418e-05,
+      "loss": 2.2638,
+      "step": 270
+    },
+    {
+      "epoch": 0.6444708680142688,
+      "grad_norm": 0.8517882887076221,
+      "learning_rate": 1.9036819248598914e-05,
+      "loss": 1.9905,
+      "step": 271
+    },
+    {
+      "epoch": 0.6468489892984542,
+      "grad_norm": 1.0217039586834744,
+      "learning_rate": 1.9028599967698533e-05,
+      "loss": 2.2177,
+      "step": 272
+    },
+    {
+      "epoch": 0.6492271105826397,
+      "grad_norm": 0.9930930260750681,
+      "learning_rate": 1.902034755596727e-05,
+      "loss": 2.093,
+      "step": 273
+    },
+    {
+      "epoch": 0.6516052318668252,
+      "grad_norm": 1.4476621256505835,
+      "learning_rate": 1.9012062043687713e-05,
+      "loss": 2.2535,
+      "step": 274
+    },
+    {
+      "epoch": 0.6539833531510107,
+      "grad_norm": 0.9679973366177126,
+      "learning_rate": 1.9003743461263887e-05,
+      "loss": 2.2304,
+      "step": 275
+    },
+    {
+      "epoch": 0.6563614744351962,
+      "grad_norm": 1.0576995279849084,
+      "learning_rate": 1.899539183922119e-05,
+      "loss": 2.0678,
+      "step": 276
+    },
+    {
+      "epoch": 0.6587395957193817,
+      "grad_norm": 0.9196543804308106,
+      "learning_rate": 1.8987007208206254e-05,
+      "loss": 2.1106,
+      "step": 277
+    },
+    {
+      "epoch": 0.6611177170035671,
+      "grad_norm": 1.0412924135468502,
+      "learning_rate": 1.8978589598986838e-05,
+      "loss": 2.3659,
+      "step": 278
+    },
+    {
+      "epoch": 0.6634958382877527,
+      "grad_norm": 1.1221322457101093,
+      "learning_rate": 1.8970139042451712e-05,
+      "loss": 2.0853,
+      "step": 279
+    },
+    {
+      "epoch": 0.6658739595719382,
+      "grad_norm": 0.8927332524290843,
+      "learning_rate": 1.8961655569610557e-05,
+      "loss": 2.2388,
+      "step": 280
+    },
+    {
+      "epoch": 0.6682520808561236,
+      "grad_norm": 1.0304293869359518,
+      "learning_rate": 1.8953139211593838e-05,
+      "loss": 2.381,
+      "step": 281
+    },
+    {
+      "epoch": 0.6706302021403091,
+      "grad_norm": 1.0508469543032843,
+      "learning_rate": 1.8944589999652687e-05,
+      "loss": 2.214,
+      "step": 282
+    },
+    {
+      "epoch": 0.6730083234244947,
+      "grad_norm": 0.8545452252368634,
+      "learning_rate": 1.8936007965158806e-05,
+      "loss": 2.0308,
+      "step": 283
+    },
+    {
+      "epoch": 0.6753864447086801,
+      "grad_norm": 1.3101079437708238,
+      "learning_rate": 1.8927393139604327e-05,
+      "loss": 2.3389,
+      "step": 284
+    },
+    {
+      "epoch": 0.6777645659928656,
+      "grad_norm": 0.8257605335721794,
+      "learning_rate": 1.8918745554601726e-05,
+      "loss": 1.9511,
+      "step": 285
+    },
+    {
+      "epoch": 0.6801426872770512,
+      "grad_norm": 0.9918391764529991,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 2.3694,
+      "step": 286
+    },
+    {
+      "epoch": 0.6825208085612366,
+      "grad_norm": 0.8841124075255721,
+      "learning_rate": 1.8901352233302964e-05,
+      "loss": 2.1977,
+      "step": 287
+    },
+    {
+      "epoch": 0.6848989298454221,
+      "grad_norm": 0.8100832981740426,
+      "learning_rate": 1.8892606560832335e-05,
+      "loss": 1.9161,
+      "step": 288
+    },
+    {
+      "epoch": 0.6872770511296076,
+      "grad_norm": 0.8738803349826288,
+      "learning_rate": 1.8883828256564413e-05,
+      "loss": 2.2419,
+      "step": 289
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.8961748350433363,
+      "learning_rate": 1.8875017352711547e-05,
+      "loss": 2.1639,
+      "step": 290
+    },
+    {
+      "epoch": 0.6920332936979786,
+      "grad_norm": 1.0902732587802257,
+      "learning_rate": 1.886617388160573e-05,
+      "loss": 2.4486,
+      "step": 291
+    },
+    {
+      "epoch": 0.6944114149821641,
+      "grad_norm": 0.9653296144522788,
+      "learning_rate": 1.8857297875698455e-05,
+      "loss": 2.0904,
+      "step": 292
+    },
+    {
+      "epoch": 0.6967895362663495,
+      "grad_norm": 1.0898489125890396,
+      "learning_rate": 1.8848389367560604e-05,
+      "loss": 2.2726,
+      "step": 293
+    },
+    {
+      "epoch": 0.6991676575505351,
+      "grad_norm": 0.8892982592369411,
+      "learning_rate": 1.883944838988232e-05,
+      "loss": 1.8982,
+      "step": 294
+    },
+    {
+      "epoch": 0.7015457788347206,
+      "grad_norm": 0.9481426246994946,
+      "learning_rate": 1.8830474975472904e-05,
+      "loss": 2.1466,
+      "step": 295
+    },
+    {
+      "epoch": 0.703923900118906,
+      "grad_norm": 0.8426682151678768,
+      "learning_rate": 1.8821469157260687e-05,
+      "loss": 2.1086,
+      "step": 296
+    },
+    {
+      "epoch": 0.7063020214030915,
+      "grad_norm": 1.0388273479050054,
+      "learning_rate": 1.8812430968292888e-05,
+      "loss": 2.3994,
+      "step": 297
+    },
+    {
+      "epoch": 0.7086801426872771,
+      "grad_norm": 0.9544054737799986,
+      "learning_rate": 1.8803360441735533e-05,
+      "loss": 2.0918,
+      "step": 298
+    },
+    {
+      "epoch": 0.7110582639714625,
+      "grad_norm": 0.9333443425947632,
+      "learning_rate": 1.8794257610873307e-05,
+      "loss": 2.2388,
+      "step": 299
+    },
+    {
+      "epoch": 0.713436385255648,
+      "grad_norm": 0.9411120276164652,
+      "learning_rate": 1.8785122509109425e-05,
+      "loss": 2.1787,
+      "step": 300
+    },
+    {
+      "epoch": 0.7158145065398336,
+      "grad_norm": 0.899942759501507,
+      "learning_rate": 1.877595516996554e-05,
+      "loss": 2.2007,
+      "step": 301
+    },
+    {
+      "epoch": 0.718192627824019,
+      "grad_norm": 0.952238040187914,
+      "learning_rate": 1.8766755627081586e-05,
+      "loss": 2.1491,
+      "step": 302
+    },
+    {
+      "epoch": 0.7205707491082045,
+      "grad_norm": 1.0704167928673332,
+      "learning_rate": 1.875752391421568e-05,
+      "loss": 2.4306,
+      "step": 303
+    },
+    {
+      "epoch": 0.72294887039239,
+      "grad_norm": 1.0126343580756334,
+      "learning_rate": 1.8748260065243985e-05,
+      "loss": 2.3258,
+      "step": 304
+    },
+    {
+      "epoch": 0.7253269916765755,
+      "grad_norm": 0.9203276329051738,
+      "learning_rate": 1.8738964114160586e-05,
+      "loss": 2.0469,
+      "step": 305
+    },
+    {
+      "epoch": 0.727705112960761,
+      "grad_norm": 1.0298534605384366,
+      "learning_rate": 1.8729636095077368e-05,
+      "loss": 2.3807,
+      "step": 306
+    },
+    {
+      "epoch": 0.7300832342449465,
+      "grad_norm": 0.9102516225979571,
+      "learning_rate": 1.8720276042223896e-05,
+      "loss": 2.0705,
+      "step": 307
+    },
+    {
+      "epoch": 0.7324613555291319,
+      "grad_norm": 0.8450936687346169,
+      "learning_rate": 1.8710883989947278e-05,
+      "loss": 1.9468,
+      "step": 308
+    },
+    {
+      "epoch": 0.7348394768133175,
+      "grad_norm": 10.37449210680128,
+      "learning_rate": 1.870145997271206e-05,
+      "loss": 2.2267,
+      "step": 309
+    },
+    {
+      "epoch": 0.737217598097503,
+      "grad_norm": 0.9380258905092027,
+      "learning_rate": 1.8692004025100054e-05,
+      "loss": 2.2396,
+      "step": 310
+    },
+    {
+      "epoch": 0.7395957193816884,
+      "grad_norm": 0.9949249727532327,
+      "learning_rate": 1.868251618181028e-05,
+      "loss": 2.2737,
+      "step": 311
+    },
+    {
+      "epoch": 0.7419738406658739,
+      "grad_norm": 0.8650417909396523,
+      "learning_rate": 1.8672996477658767e-05,
+      "loss": 2.2057,
+      "step": 312
+    },
+    {
+      "epoch": 0.7443519619500595,
+      "grad_norm": 0.9963224791105781,
+      "learning_rate": 1.866344494757848e-05,
+      "loss": 2.3958,
+      "step": 313
+    },
+    {
+      "epoch": 0.746730083234245,
+      "grad_norm": 0.9782743745256545,
+      "learning_rate": 1.8653861626619166e-05,
+      "loss": 2.105,
+      "step": 314
+    },
+    {
+      "epoch": 0.7491082045184304,
+      "grad_norm": 0.9991591823799537,
+      "learning_rate": 1.8644246549947226e-05,
+      "loss": 2.3339,
+      "step": 315
+    },
+    {
+      "epoch": 0.7491082045184304,
+      "eval_loss": 2.453089952468872,
+      "eval_runtime": 65.8189,
+      "eval_samples_per_second": 9.708,
+      "eval_steps_per_second": 1.215,
+      "step": 315
+    },
+    {
+      "epoch": 0.751486325802616,
+      "grad_norm": 0.8595275246052216,
+      "learning_rate": 1.8634599752845594e-05,
+      "loss": 2.2405,
+      "step": 316
+    },
+    {
+      "epoch": 0.7538644470868014,
+      "grad_norm": 0.9508091435584168,
+      "learning_rate": 1.86249212707136e-05,
+      "loss": 2.0259,
+      "step": 317
+    },
+    {
+      "epoch": 0.7562425683709869,
+      "grad_norm": 1.007143450486727,
+      "learning_rate": 1.861521113906684e-05,
+      "loss": 2.2581,
+      "step": 318
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.8694388672608973,
+      "learning_rate": 1.8605469393537062e-05,
+      "loss": 2.1028,
+      "step": 319
+    },
+    {
+      "epoch": 0.760998810939358,
+      "grad_norm": 1.1523113038633086,
+      "learning_rate": 1.8595696069872013e-05,
+      "loss": 2.5605,
+      "step": 320
+    },
+    {
+      "epoch": 0.7633769322235434,
+      "grad_norm": 1.0752431273595597,
+      "learning_rate": 1.8585891203935315e-05,
+      "loss": 2.179,
+      "step": 321
+    },
+    {
+      "epoch": 0.7657550535077289,
+      "grad_norm": 1.4087896659381576,
+      "learning_rate": 1.8576054831706348e-05,
+      "loss": 2.3727,
+      "step": 322
+    },
+    {
+      "epoch": 0.7681331747919143,
+      "grad_norm": 1.0235487680455349,
+      "learning_rate": 1.856618698928009e-05,
+      "loss": 2.0918,
+      "step": 323
+    },
+    {
+      "epoch": 0.7705112960760999,
+      "grad_norm": 0.9904332707712578,
+      "learning_rate": 1.8556287712867006e-05,
+      "loss": 2.2627,
+      "step": 324
+    },
+    {
+      "epoch": 0.7728894173602854,
+      "grad_norm": 0.9900875612198691,
+      "learning_rate": 1.8546357038792918e-05,
+      "loss": 2.2281,
+      "step": 325
+    },
+    {
+      "epoch": 0.7752675386444708,
+      "grad_norm": 0.8882946865776852,
+      "learning_rate": 1.8536395003498857e-05,
+      "loss": 2.2966,
+      "step": 326
+    },
+    {
+      "epoch": 0.7776456599286563,
+      "grad_norm": 0.9917259649244573,
+      "learning_rate": 1.8526401643540924e-05,
+      "loss": 2.2903,
+      "step": 327
+    },
+    {
+      "epoch": 0.7800237812128419,
+      "grad_norm": 1.0110335104954997,
+      "learning_rate": 1.8516376995590185e-05,
+      "loss": 2.2732,
+      "step": 328
+    },
+    {
+      "epoch": 0.7824019024970273,
+      "grad_norm": 1.0613748791083453,
+      "learning_rate": 1.8506321096432516e-05,
+      "loss": 2.1801,
+      "step": 329
+    },
+    {
+      "epoch": 0.7847800237812128,
+      "grad_norm": 0.8280074594268549,
+      "learning_rate": 1.849623398296846e-05,
+      "loss": 2.0413,
+      "step": 330
+    },
+    {
+      "epoch": 0.7871581450653984,
+      "grad_norm": 1.061771296332105,
+      "learning_rate": 1.84861156922131e-05,
+      "loss": 2.3187,
+      "step": 331
+    },
+    {
+      "epoch": 0.7895362663495838,
+      "grad_norm": 1.003700059201312,
+      "learning_rate": 1.8475966261295947e-05,
+      "loss": 2.2117,
+      "step": 332
+    },
+    {
+      "epoch": 0.7919143876337693,
+      "grad_norm": 1.0346094081558943,
+      "learning_rate": 1.8465785727460763e-05,
+      "loss": 2.35,
+      "step": 333
+    },
+    {
+      "epoch": 0.7942925089179548,
+      "grad_norm": 1.0628441168006169,
+      "learning_rate": 1.845557412806545e-05,
+      "loss": 2.2907,
+      "step": 334
+    },
+    {
+      "epoch": 0.7966706302021404,
+      "grad_norm": 0.9035239279839531,
+      "learning_rate": 1.8445331500581905e-05,
+      "loss": 2.3114,
+      "step": 335
+    },
+    {
+      "epoch": 0.7990487514863258,
+      "grad_norm": 0.8520631758698989,
+      "learning_rate": 1.8435057882595885e-05,
+      "loss": 2.236,
+      "step": 336
+    },
+    {
+      "epoch": 0.8014268727705113,
+      "grad_norm": 0.9909579691053704,
+      "learning_rate": 1.8424753311806867e-05,
+      "loss": 2.164,
+      "step": 337
+    },
+    {
+      "epoch": 0.8038049940546967,
+      "grad_norm": 1.3497517322085937,
+      "learning_rate": 1.8414417826027907e-05,
+      "loss": 2.1371,
+      "step": 338
+    },
+    {
+      "epoch": 0.8061831153388823,
+      "grad_norm": 0.9733174734597209,
+      "learning_rate": 1.840405146318552e-05,
+      "loss": 2.2605,
+      "step": 339
+    },
+    {
+      "epoch": 0.8085612366230678,
+      "grad_norm": 0.991877145495908,
+      "learning_rate": 1.8393654261319504e-05,
+      "loss": 2.2597,
+      "step": 340
+    },
+    {
+      "epoch": 0.8109393579072532,
+      "grad_norm": 0.8567918308119495,
+      "learning_rate": 1.8383226258582833e-05,
+      "loss": 2.0034,
+      "step": 341
+    },
+    {
+      "epoch": 0.8133174791914387,
+      "grad_norm": 1.065116900935523,
+      "learning_rate": 1.837276749324151e-05,
+      "loss": 2.3297,
+      "step": 342
+    },
+    {
+      "epoch": 0.8156956004756243,
+      "grad_norm": 0.945929516741479,
+      "learning_rate": 1.8362278003674417e-05,
+      "loss": 2.1654,
+      "step": 343
+    },
+    {
+      "epoch": 0.8180737217598097,
+      "grad_norm": 1.2321854339549771,
+      "learning_rate": 1.8351757828373183e-05,
+      "loss": 2.3218,
+      "step": 344
+    },
+    {
+      "epoch": 0.8204518430439952,
+      "grad_norm": 0.8769538008656999,
+      "learning_rate": 1.8341207005942033e-05,
+      "loss": 1.9733,
+      "step": 345
+    },
+    {
+      "epoch": 0.8228299643281808,
+      "grad_norm": 0.9563552488015744,
+      "learning_rate": 1.8330625575097663e-05,
+      "loss": 1.8932,
+      "step": 346
+    },
+    {
+      "epoch": 0.8252080856123662,
+      "grad_norm": 0.9405864126962645,
+      "learning_rate": 1.8320013574669083e-05,
+      "loss": 2.2498,
+      "step": 347
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.910096309278826,
+      "learning_rate": 1.8309371043597472e-05,
+      "loss": 2.0247,
+      "step": 348
+    },
+    {
+      "epoch": 0.8299643281807372,
+      "grad_norm": 0.8784633584470368,
+      "learning_rate": 1.829869802093606e-05,
+      "loss": 1.9894,
+      "step": 349
+    },
+    {
+      "epoch": 0.8323424494649228,
+      "grad_norm": 0.8541120126588495,
+      "learning_rate": 1.8287994545849948e-05,
+      "loss": 2.0511,
+      "step": 350
+    },
+    {
+      "epoch": 0.8347205707491082,
+      "grad_norm": 0.9979547733824415,
+      "learning_rate": 1.8277260657615993e-05,
+      "loss": 2.0893,
+      "step": 351
+    },
+    {
+      "epoch": 0.8370986920332937,
+      "grad_norm": 1.0836986822911394,
+      "learning_rate": 1.826649639562266e-05,
+      "loss": 2.3076,
+      "step": 352
+    },
+    {
+      "epoch": 0.8394768133174791,
+      "grad_norm": 1.035582585906488,
+      "learning_rate": 1.825570179936986e-05,
+      "loss": 2.2928,
+      "step": 353
+    },
+    {
+      "epoch": 0.8418549346016647,
+      "grad_norm": 0.8458996980228227,
+      "learning_rate": 1.8244876908468826e-05,
+      "loss": 2.0421,
+      "step": 354
+    },
+    {
+      "epoch": 0.8442330558858502,
+      "grad_norm": 0.9377520676275963,
+      "learning_rate": 1.8234021762641946e-05,
+      "loss": 2.2872,
+      "step": 355
+    },
+    {
+      "epoch": 0.8466111771700356,
+      "grad_norm": 0.9662487818099018,
+      "learning_rate": 1.8223136401722648e-05,
+      "loss": 2.2357,
+      "step": 356
+    },
+    {
+      "epoch": 0.8489892984542212,
+      "grad_norm": 0.9373837869014561,
+      "learning_rate": 1.8212220865655224e-05,
+      "loss": 2.3807,
+      "step": 357
+    },
+    {
+      "epoch": 0.8513674197384067,
+      "grad_norm": 0.8767072116092074,
+      "learning_rate": 1.8201275194494695e-05,
+      "loss": 2.0453,
+      "step": 358
+    },
+    {
+      "epoch": 0.8537455410225921,
+      "grad_norm": 0.9164578385360742,
+      "learning_rate": 1.8190299428406667e-05,
+      "loss": 2.1177,
+      "step": 359
+    },
+    {
+      "epoch": 0.8561236623067776,
+      "grad_norm": 2.207352437074081,
+      "learning_rate": 1.8179293607667177e-05,
+      "loss": 2.2001,
+      "step": 360
+    },
+    {
+      "epoch": 0.8585017835909632,
+      "grad_norm": 0.983155025111798,
+      "learning_rate": 1.8168257772662556e-05,
+      "loss": 2.3009,
+      "step": 361
+    },
+    {
+      "epoch": 0.8608799048751486,
+      "grad_norm": 0.9734880504382539,
+      "learning_rate": 1.8157191963889265e-05,
+      "loss": 2.3093,
+      "step": 362
+    },
+    {
+      "epoch": 0.8632580261593341,
+      "grad_norm": 0.8887247626382502,
+      "learning_rate": 1.8146096221953767e-05,
+      "loss": 2.1673,
+      "step": 363
+    },
+    {
+      "epoch": 0.8656361474435196,
+      "grad_norm": 0.9468700496948975,
+      "learning_rate": 1.8134970587572345e-05,
+      "loss": 2.2193,
+      "step": 364
+    },
+    {
+      "epoch": 0.8680142687277052,
+      "grad_norm": 0.9774148680996411,
+      "learning_rate": 1.8123815101570996e-05,
+      "loss": 2.2185,
+      "step": 365
+    },
+    {
+      "epoch": 0.8703923900118906,
+      "grad_norm": 1.0377594097114105,
+      "learning_rate": 1.8112629804885248e-05,
+      "loss": 2.1385,
+      "step": 366
+    },
+    {
+      "epoch": 0.8727705112960761,
+      "grad_norm": 0.9257473414011718,
+      "learning_rate": 1.8101414738560018e-05,
+      "loss": 2.309,
+      "step": 367
+    },
+    {
+      "epoch": 0.8751486325802615,
+      "grad_norm": 0.8751605326561603,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 2.0981,
+      "step": 368
+    },
+    {
+      "epoch": 0.8775267538644471,
+      "grad_norm": 0.8318450854470809,
+      "learning_rate": 1.8078895461716867e-05,
+      "loss": 2.0499,
+      "step": 369
+    },
+    {
+      "epoch": 0.8799048751486326,
+      "grad_norm": 0.9229990617872996,
+      "learning_rate": 1.8067591333834382e-05,
+      "loss": 2.0931,
+      "step": 370
+    },
+    {
+      "epoch": 0.882282996432818,
+      "grad_norm": 0.8885903764744792,
+      "learning_rate": 1.8056257601583004e-05,
+      "loss": 2.1094,
+      "step": 371
+    },
+    {
+      "epoch": 0.8846611177170036,
+      "grad_norm": 0.8862767802235494,
+      "learning_rate": 1.8044894306552338e-05,
+      "loss": 2.1633,
+      "step": 372
+    },
+    {
+      "epoch": 0.8870392390011891,
+      "grad_norm": 0.8644263027922633,
+      "learning_rate": 1.8033501490440478e-05,
+      "loss": 2.1869,
+      "step": 373
+    },
+    {
+      "epoch": 0.8894173602853745,
+      "grad_norm": 0.8908757391357947,
+      "learning_rate": 1.802207919505385e-05,
+      "loss": 2.0867,
+      "step": 374
+    },
+    {
+      "epoch": 0.89179548156956,
+      "grad_norm": 0.9706439808339724,
+      "learning_rate": 1.801062746230705e-05,
+      "loss": 2.2817,
+      "step": 375
+    },
+    {
+      "epoch": 0.8941736028537456,
+      "grad_norm": 0.9665648406193532,
+      "learning_rate": 1.79991463342227e-05,
+      "loss": 2.109,
+      "step": 376
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.8628669010410803,
+      "learning_rate": 1.798763585293128e-05,
+      "loss": 2.0049,
+      "step": 377
+    },
+    {
+      "epoch": 0.8989298454221165,
+      "grad_norm": 0.9905082003227874,
+      "learning_rate": 1.7976096060671e-05,
+      "loss": 2.3004,
+      "step": 378
+    },
+    {
+      "epoch": 0.901307966706302,
+      "grad_norm": 0.9857769539636477,
+      "learning_rate": 1.7964526999787606e-05,
+      "loss": 2.2076,
+      "step": 379
+    },
+    {
+      "epoch": 0.9036860879904876,
+      "grad_norm": 0.9874365687027726,
+      "learning_rate": 1.7952928712734266e-05,
+      "loss": 2.2918,
+      "step": 380
+    },
+    {
+      "epoch": 0.906064209274673,
+      "grad_norm": 0.8854059768194814,
+      "learning_rate": 1.7941301242071384e-05,
+      "loss": 2.1416,
+      "step": 381
+    },
+    {
+      "epoch": 0.9084423305588585,
+      "grad_norm": 0.8891010909161526,
+      "learning_rate": 1.792964463046646e-05,
+      "loss": 2.2335,
+      "step": 382
+    },
+    {
+      "epoch": 0.9108204518430439,
+      "grad_norm": 0.8836139495461457,
+      "learning_rate": 1.7917958920693923e-05,
+      "loss": 2.0156,
+      "step": 383
+    },
+    {
+      "epoch": 0.9131985731272295,
+      "grad_norm": 0.862309723766035,
+      "learning_rate": 1.790624415563498e-05,
+      "loss": 2.2668,
+      "step": 384
+    },
+    {
+      "epoch": 0.915576694411415,
+      "grad_norm": 0.8736380448815635,
+      "learning_rate": 1.7894500378277463e-05,
+      "loss": 2.1338,
+      "step": 385
+    },
+    {
+      "epoch": 0.9179548156956004,
+      "grad_norm": 0.8450572821559386,
+      "learning_rate": 1.7882727631715655e-05,
+      "loss": 2.0142,
+      "step": 386
+    },
+    {
+      "epoch": 0.920332936979786,
+      "grad_norm": 0.9862096866699867,
+      "learning_rate": 1.7870925959150155e-05,
+      "loss": 1.9915,
+      "step": 387
+    },
+    {
+      "epoch": 0.9227110582639715,
+      "grad_norm": 1.0092700839816597,
+      "learning_rate": 1.7859095403887697e-05,
+      "loss": 2.0294,
+      "step": 388
+    },
+    {
+      "epoch": 0.925089179548157,
+      "grad_norm": 1.1074789492464077,
+      "learning_rate": 1.7847236009341007e-05,
+      "loss": 2.2817,
+      "step": 389
+    },
+    {
+      "epoch": 0.9274673008323424,
+      "grad_norm": 1.1905201839698938,
+      "learning_rate": 1.7835347819028642e-05,
+      "loss": 2.1793,
+      "step": 390
+    },
+    {
+      "epoch": 0.929845422116528,
+      "grad_norm": 0.9783879172577963,
+      "learning_rate": 1.7823430876574815e-05,
+      "loss": 2.0936,
+      "step": 391
+    },
+    {
+      "epoch": 0.9322235434007135,
+      "grad_norm": 0.8747590280954227,
+      "learning_rate": 1.7811485225709255e-05,
+      "loss": 2.0459,
+      "step": 392
+    },
+    {
+      "epoch": 0.9346016646848989,
+      "grad_norm": 0.9379273246769285,
+      "learning_rate": 1.7799510910267032e-05,
+      "loss": 2.3024,
+      "step": 393
+    },
+    {
+      "epoch": 0.9369797859690844,
+      "grad_norm": 1.0154785871015584,
+      "learning_rate": 1.778750797418841e-05,
+      "loss": 2.2336,
+      "step": 394
+    },
+    {
+      "epoch": 0.93935790725327,
+      "grad_norm": 2.334020052582292,
+      "learning_rate": 1.7775476461518668e-05,
+      "loss": 2.2146,
+      "step": 395
+    },
+    {
+      "epoch": 0.9417360285374554,
+      "grad_norm": 1.028424946167679,
+      "learning_rate": 1.7763416416407953e-05,
+      "loss": 2.148,
+      "step": 396
+    },
+    {
+      "epoch": 0.9441141498216409,
+      "grad_norm": 0.9939249719466411,
+      "learning_rate": 1.7751327883111117e-05,
+      "loss": 2.3384,
+      "step": 397
+    },
+    {
+      "epoch": 0.9464922711058263,
+      "grad_norm": 0.9622526498121815,
+      "learning_rate": 1.773921090598754e-05,
+      "loss": 2.2333,
+      "step": 398
+    },
+    {
+      "epoch": 0.9488703923900119,
+      "grad_norm": 0.9627114271614428,
+      "learning_rate": 1.7727065529500986e-05,
+      "loss": 2.0078,
+      "step": 399
+    },
+    {
+      "epoch": 0.9512485136741974,
+      "grad_norm": 1.0739248368345071,
+      "learning_rate": 1.7714891798219432e-05,
+      "loss": 2.431,
+      "step": 400
+    },
+    {
+      "epoch": 0.9536266349583828,
+      "grad_norm": 0.9459448330629742,
+      "learning_rate": 1.7702689756814898e-05,
+      "loss": 2.195,
+      "step": 401
+    },
+    {
+      "epoch": 0.9560047562425684,
+      "grad_norm": 0.985098727152756,
+      "learning_rate": 1.7690459450063297e-05,
+      "loss": 2.378,
+      "step": 402
+    },
+    {
+      "epoch": 0.9583828775267539,
+      "grad_norm": 0.9004480308740594,
+      "learning_rate": 1.7678200922844256e-05,
+      "loss": 2.0375,
+      "step": 403
+    },
+    {
+      "epoch": 0.9607609988109393,
+      "grad_norm": 1.0816635115771127,
+      "learning_rate": 1.7665914220140964e-05,
+      "loss": 2.2932,
+      "step": 404
+    },
+    {
+      "epoch": 0.9631391200951248,
+      "grad_norm": 0.856817467594963,
+      "learning_rate": 1.7653599387039993e-05,
+      "loss": 2.1395,
+      "step": 405
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.9816466176158317,
+      "learning_rate": 1.764125646873115e-05,
+      "loss": 2.2032,
+      "step": 406
+    },
+    {
+      "epoch": 0.9678953626634959,
+      "grad_norm": 1.0159180902253635,
+      "learning_rate": 1.7628885510507295e-05,
+      "loss": 2.3814,
+      "step": 407
+    },
+    {
+      "epoch": 0.9702734839476813,
+      "grad_norm": 0.8765185622300491,
+      "learning_rate": 1.7616486557764187e-05,
+      "loss": 2.1377,
+      "step": 408
+    },
+    {
+      "epoch": 0.9726516052318668,
+      "grad_norm": 0.8581340453429611,
+      "learning_rate": 1.7604059656000313e-05,
+      "loss": 2.1687,
+      "step": 409
+    },
+    {
+      "epoch": 0.9750297265160524,
+      "grad_norm": 1.0106580156311586,
+      "learning_rate": 1.7591604850816705e-05,
+      "loss": 2.4389,
+      "step": 410
+    },
+    {
+      "epoch": 0.9774078478002378,
+      "grad_norm": 0.9102932420528898,
+      "learning_rate": 1.757912218791681e-05,
+      "loss": 2.1774,
+      "step": 411
+    },
+    {
+      "epoch": 0.9797859690844233,
+      "grad_norm": 0.8897815759878576,
+      "learning_rate": 1.7566611713106287e-05,
+      "loss": 2.0938,
+      "step": 412
+    },
+    {
+      "epoch": 0.9821640903686087,
+      "grad_norm": 0.8151179975871685,
+      "learning_rate": 1.7554073472292854e-05,
+      "loss": 2.0923,
+      "step": 413
+    },
+    {
+      "epoch": 0.9845422116527943,
+      "grad_norm": 0.9325421154931588,
+      "learning_rate": 1.7541507511486114e-05,
+      "loss": 2.2798,
+      "step": 414
+    },
+    {
+      "epoch": 0.9869203329369798,
+      "grad_norm": 0.9169184208068022,
+      "learning_rate": 1.75289138767974e-05,
+      "loss": 2.2266,
+      "step": 415
+    },
+    {
+      "epoch": 0.9892984542211652,
+      "grad_norm": 0.9539647094698775,
+      "learning_rate": 1.7516292614439586e-05,
+      "loss": 2.3459,
+      "step": 416
+    },
+    {
+      "epoch": 0.9916765755053508,
+      "grad_norm": 1.0372921455846975,
+      "learning_rate": 1.7503643770726924e-05,
+      "loss": 2.2152,
+      "step": 417
+    },
+    {
+      "epoch": 0.9940546967895363,
+      "grad_norm": 0.8903926236033542,
+      "learning_rate": 1.7490967392074897e-05,
+      "loss": 2.1959,
+      "step": 418
+    },
+    {
+      "epoch": 0.9964328180737217,
+      "grad_norm": 0.8491943369235393,
+      "learning_rate": 1.7478263525000003e-05,
+      "loss": 2.265,
+      "step": 419
+    },
+    {
+      "epoch": 0.9988109393579072,
+      "grad_norm": 0.9138223778798192,
+      "learning_rate": 1.7465532216119628e-05,
+      "loss": 2.2167,
+      "step": 420
+    },
+    {
+      "epoch": 0.9988109393579072,
+      "eval_loss": 2.4223339557647705,
+      "eval_runtime": 65.3623,
+      "eval_samples_per_second": 9.776,
+      "eval_steps_per_second": 1.224,
+      "step": 420
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 210,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6054264560287744e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4afa27d1a40ecd661f9724785c2e34f68177e49c01784ff719ada5cf02a780
+size 8504

checkpoint-420/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)