Upload folder using huggingface_hub

.gitattributes

@@ -39,3 +39,4 @@ llama31_8b_300125_subsample_mixture/checkpoint-1005/tokenizer.json filter=lfs di
 llama31_8b_300125_subsample_mixture/checkpoint-2011/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 merged_models/ties_deepseek_irish-sft-llama3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 llama31_8b_instruct_translated_dolphin_r1_reasoning_flash_merged_0_to_11_out_of_100_half_English/checkpoint-1311/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/tokenizer.json filter=lfs diff=lfs merge=lfs -text

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.1"
+}

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/latest

@@ -0,0 +1 @@
+global_step548

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b7eac9a271191ead646f62b0e5d07bfb21640fcf2b8f7b8b6460e8adbefe15
+size 4976717314

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0bf4aeb23c758ecd5daeccca3aecf719c9d4ed23c95818e629e97cd28ce0a6c
+size 4999826246

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd5aa81bc1bd604fa5acb16038e916ef1364f7aea6bda81bcc6a6b51c007a6d
+size 4915938762

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ff421226f1309ec48d83f6d1103e07e019ac3c68f8a2f2f294f062a2825c3d
+size 1168140873

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/pytorch_model.bin.index.json

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

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808ee7eda4a18c906fa919978a7f42962c4977c093c976df9a277ced7d133d98
+size 14244

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d8d52581132d604ac3d2c6194a7e312871d4711c81ca02c7ba5e7a04384f27
+size 1064

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<｜end▁of▁sentence｜>"
+}

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
+size 17209530

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/tokenizer_config.json

@@ -0,0 +1,2066 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "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": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128012": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128013": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128014": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128015": {
+      "content": "<｜▁pad▁｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/trainer_state.json

@@ -0,0 +1,1958 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9996959562176954,
+  "eval_steps": 500,
+  "global_step": 548,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018242626938279112,
+      "grad_norm": 8.592140197753906,
+      "learning_rate": 1.204819277108434e-07,
+      "loss": 1.3113,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036485253876558225,
+      "grad_norm": 8.295819282531738,
+      "learning_rate": 2.409638554216868e-07,
+      "loss": 1.2671,
+      "step": 2
+    },
+    {
+      "epoch": 0.007297050775311645,
+      "grad_norm": 9.391046524047852,
+      "learning_rate": 4.819277108433736e-07,
+      "loss": 1.2857,
+      "step": 4
+    },
+    {
+      "epoch": 0.010945576162967468,
+      "grad_norm": 7.095087051391602,
+      "learning_rate": 7.228915662650602e-07,
+      "loss": 1.2067,
+      "step": 6
+    },
+    {
+      "epoch": 0.01459410155062329,
+      "grad_norm": 8.843668937683105,
+      "learning_rate": 9.638554216867472e-07,
+      "loss": 1.3509,
+      "step": 8
+    },
+    {
+      "epoch": 0.018242626938279112,
+      "grad_norm": 10.585760116577148,
+      "learning_rate": 1.2048192771084338e-06,
+      "loss": 1.1964,
+      "step": 10
+    },
+    {
+      "epoch": 0.021891152325934936,
+      "grad_norm": 7.215892791748047,
+      "learning_rate": 1.4457831325301204e-06,
+      "loss": 1.2249,
+      "step": 12
+    },
+    {
+      "epoch": 0.025539677713590756,
+      "grad_norm": 5.175631046295166,
+      "learning_rate": 1.6867469879518073e-06,
+      "loss": 1.182,
+      "step": 14
+    },
+    {
+      "epoch": 0.02918820310124658,
+      "grad_norm": 6.034592151641846,
+      "learning_rate": 1.9277108433734943e-06,
+      "loss": 1.1873,
+      "step": 16
+    },
+    {
+      "epoch": 0.0328367284889024,
+      "grad_norm": 4.697737693786621,
+      "learning_rate": 2.168674698795181e-06,
+      "loss": 1.0638,
+      "step": 18
+    },
+    {
+      "epoch": 0.036485253876558224,
+      "grad_norm": 5.241036891937256,
+      "learning_rate": 2.4096385542168676e-06,
+      "loss": 1.0815,
+      "step": 20
+    },
+    {
+      "epoch": 0.04013377926421405,
+      "grad_norm": 4.05128812789917,
+      "learning_rate": 2.6506024096385547e-06,
+      "loss": 0.9343,
+      "step": 22
+    },
+    {
+      "epoch": 0.04378230465186987,
+      "grad_norm": 2.4777638912200928,
+      "learning_rate": 2.891566265060241e-06,
+      "loss": 0.9977,
+      "step": 24
+    },
+    {
+      "epoch": 0.04743083003952569,
+      "grad_norm": 2.8077099323272705,
+      "learning_rate": 3.132530120481928e-06,
+      "loss": 0.9534,
+      "step": 26
+    },
+    {
+      "epoch": 0.05107935542718151,
+      "grad_norm": 1.8399295806884766,
+      "learning_rate": 3.3734939759036146e-06,
+      "loss": 0.9016,
+      "step": 28
+    },
+    {
+      "epoch": 0.054727880814837336,
+      "grad_norm": 1.6265225410461426,
+      "learning_rate": 3.6144578313253016e-06,
+      "loss": 0.9041,
+      "step": 30
+    },
+    {
+      "epoch": 0.05837640620249316,
+      "grad_norm": 1.7064011096954346,
+      "learning_rate": 3.855421686746989e-06,
+      "loss": 0.9486,
+      "step": 32
+    },
+    {
+      "epoch": 0.062024931590148984,
+      "grad_norm": 1.425864815711975,
+      "learning_rate": 4.096385542168675e-06,
+      "loss": 0.8463,
+      "step": 34
+    },
+    {
+      "epoch": 0.0656734569778048,
+      "grad_norm": 1.1896415948867798,
+      "learning_rate": 4.337349397590362e-06,
+      "loss": 0.7976,
+      "step": 36
+    },
+    {
+      "epoch": 0.06932198236546062,
+      "grad_norm": 1.3058383464813232,
+      "learning_rate": 4.578313253012049e-06,
+      "loss": 0.8497,
+      "step": 38
+    },
+    {
+      "epoch": 0.07297050775311645,
+      "grad_norm": 1.321593999862671,
+      "learning_rate": 4.819277108433735e-06,
+      "loss": 0.822,
+      "step": 40
+    },
+    {
+      "epoch": 0.07661903314077227,
+      "grad_norm": 5.552907943725586,
+      "learning_rate": 5.060240963855422e-06,
+      "loss": 0.7931,
+      "step": 42
+    },
+    {
+      "epoch": 0.0802675585284281,
+      "grad_norm": 1.1037073135375977,
+      "learning_rate": 5.301204819277109e-06,
+      "loss": 0.7707,
+      "step": 44
+    },
+    {
+      "epoch": 0.08391608391608392,
+      "grad_norm": 1.1386008262634277,
+      "learning_rate": 5.542168674698796e-06,
+      "loss": 0.7802,
+      "step": 46
+    },
+    {
+      "epoch": 0.08756460930373974,
+      "grad_norm": 0.9155784845352173,
+      "learning_rate": 5.783132530120482e-06,
+      "loss": 0.7317,
+      "step": 48
+    },
+    {
+      "epoch": 0.09121313469139557,
+      "grad_norm": 0.9841786026954651,
+      "learning_rate": 6.02409638554217e-06,
+      "loss": 0.6851,
+      "step": 50
+    },
+    {
+      "epoch": 0.09486166007905138,
+      "grad_norm": 1.21662175655365,
+      "learning_rate": 6.265060240963856e-06,
+      "loss": 0.7872,
+      "step": 52
+    },
+    {
+      "epoch": 0.0985101854667072,
+      "grad_norm": 0.9381082057952881,
+      "learning_rate": 6.5060240963855425e-06,
+      "loss": 0.7722,
+      "step": 54
+    },
+    {
+      "epoch": 0.10215871085436302,
+      "grad_norm": 1.130147933959961,
+      "learning_rate": 6.746987951807229e-06,
+      "loss": 0.6851,
+      "step": 56
+    },
+    {
+      "epoch": 0.10580723624201885,
+      "grad_norm": 0.9588335752487183,
+      "learning_rate": 6.987951807228917e-06,
+      "loss": 0.7067,
+      "step": 58
+    },
+    {
+      "epoch": 0.10945576162967467,
+      "grad_norm": 3.1881303787231445,
+      "learning_rate": 7.228915662650603e-06,
+      "loss": 0.7472,
+      "step": 60
+    },
+    {
+      "epoch": 0.1131042870173305,
+      "grad_norm": 1.1993156671524048,
+      "learning_rate": 7.469879518072289e-06,
+      "loss": 0.7773,
+      "step": 62
+    },
+    {
+      "epoch": 0.11675281240498632,
+      "grad_norm": 0.952839732170105,
+      "learning_rate": 7.710843373493977e-06,
+      "loss": 0.6838,
+      "step": 64
+    },
+    {
+      "epoch": 0.12040133779264214,
+      "grad_norm": 1.2836329936981201,
+      "learning_rate": 7.951807228915663e-06,
+      "loss": 0.761,
+      "step": 66
+    },
+    {
+      "epoch": 0.12404986318029797,
+      "grad_norm": 0.9141722321510315,
+      "learning_rate": 8.19277108433735e-06,
+      "loss": 0.6943,
+      "step": 68
+    },
+    {
+      "epoch": 0.1276983885679538,
+      "grad_norm": 1.0482511520385742,
+      "learning_rate": 8.433734939759038e-06,
+      "loss": 0.6896,
+      "step": 70
+    },
+    {
+      "epoch": 0.1313469139556096,
+      "grad_norm": 0.9622248411178589,
+      "learning_rate": 8.674698795180724e-06,
+      "loss": 0.667,
+      "step": 72
+    },
+    {
+      "epoch": 0.13499543934326544,
+      "grad_norm": 0.9998468160629272,
+      "learning_rate": 8.91566265060241e-06,
+      "loss": 0.7102,
+      "step": 74
+    },
+    {
+      "epoch": 0.13864396473092125,
+      "grad_norm": 1.114218831062317,
+      "learning_rate": 9.156626506024097e-06,
+      "loss": 0.707,
+      "step": 76
+    },
+    {
+      "epoch": 0.1422924901185771,
+      "grad_norm": 0.9857527017593384,
+      "learning_rate": 9.397590361445785e-06,
+      "loss": 0.6797,
+      "step": 78
+    },
+    {
+      "epoch": 0.1459410155062329,
+      "grad_norm": 0.9165706038475037,
+      "learning_rate": 9.63855421686747e-06,
+      "loss": 0.6712,
+      "step": 80
+    },
+    {
+      "epoch": 0.1495895408938887,
+      "grad_norm": 0.9506673812866211,
+      "learning_rate": 9.879518072289156e-06,
+      "loss": 0.6996,
+      "step": 82
+    },
+    {
+      "epoch": 0.15323806628154454,
+      "grad_norm": 0.9897269010543823,
+      "learning_rate": 9.999989874096101e-06,
+      "loss": 0.6752,
+      "step": 84
+    },
+    {
+      "epoch": 0.15688659166920035,
+      "grad_norm": 1.1789156198501587,
+      "learning_rate": 9.999908867110992e-06,
+      "loss": 0.6852,
+      "step": 86
+    },
+    {
+      "epoch": 0.1605351170568562,
+      "grad_norm": 0.8242220282554626,
+      "learning_rate": 9.9997468544532e-06,
+      "loss": 0.6163,
+      "step": 88
+    },
+    {
+      "epoch": 0.164183642444512,
+      "grad_norm": 1.0809637308120728,
+      "learning_rate": 9.999503838747564e-06,
+      "loss": 0.6952,
+      "step": 90
+    },
+    {
+      "epoch": 0.16783216783216784,
+      "grad_norm": 1.2057223320007324,
+      "learning_rate": 9.999179823931286e-06,
+      "loss": 0.6622,
+      "step": 92
+    },
+    {
+      "epoch": 0.17148069321982365,
+      "grad_norm": 0.8252416253089905,
+      "learning_rate": 9.998774815253869e-06,
+      "loss": 0.6548,
+      "step": 94
+    },
+    {
+      "epoch": 0.1751292186074795,
+      "grad_norm": 0.8368967175483704,
+      "learning_rate": 9.99828881927703e-06,
+      "loss": 0.6426,
+      "step": 96
+    },
+    {
+      "epoch": 0.1787777439951353,
+      "grad_norm": 1.2186616659164429,
+      "learning_rate": 9.997721843874604e-06,
+      "loss": 0.6827,
+      "step": 98
+    },
+    {
+      "epoch": 0.18242626938279113,
+      "grad_norm": 0.9738035798072815,
+      "learning_rate": 9.997073898232398e-06,
+      "loss": 0.6766,
+      "step": 100
+    },
+    {
+      "epoch": 0.18607479477044694,
+      "grad_norm": 0.9566294550895691,
+      "learning_rate": 9.996344992848063e-06,
+      "loss": 0.6704,
+      "step": 102
+    },
+    {
+      "epoch": 0.18972332015810275,
+      "grad_norm": 0.9457056522369385,
+      "learning_rate": 9.995535139530904e-06,
+      "loss": 0.6415,
+      "step": 104
+    },
+    {
+      "epoch": 0.1933718455457586,
+      "grad_norm": 1.1034765243530273,
+      "learning_rate": 9.994644351401704e-06,
+      "loss": 0.6747,
+      "step": 106
+    },
+    {
+      "epoch": 0.1970203709334144,
+      "grad_norm": 0.9405321478843689,
+      "learning_rate": 9.993672642892505e-06,
+      "loss": 0.6473,
+      "step": 108
+    },
+    {
+      "epoch": 0.20066889632107024,
+      "grad_norm": 0.8974522352218628,
+      "learning_rate": 9.992620029746375e-06,
+      "loss": 0.6647,
+      "step": 110
+    },
+    {
+      "epoch": 0.20431742170872605,
+      "grad_norm": 0.8799972534179688,
+      "learning_rate": 9.991486529017149e-06,
+      "loss": 0.6101,
+      "step": 112
+    },
+    {
+      "epoch": 0.2079659470963819,
+      "grad_norm": 1.0081822872161865,
+      "learning_rate": 9.990272159069164e-06,
+      "loss": 0.6686,
+      "step": 114
+    },
+    {
+      "epoch": 0.2116144724840377,
+      "grad_norm": 1.1524714231491089,
+      "learning_rate": 9.988976939576945e-06,
+      "loss": 0.681,
+      "step": 116
+    },
+    {
+      "epoch": 0.21526299787169353,
+      "grad_norm": 0.9791584610939026,
+      "learning_rate": 9.987600891524902e-06,
+      "loss": 0.6646,
+      "step": 118
+    },
+    {
+      "epoch": 0.21891152325934934,
+      "grad_norm": 0.8090513944625854,
+      "learning_rate": 9.98614403720698e-06,
+      "loss": 0.6632,
+      "step": 120
+    },
+    {
+      "epoch": 0.22256004864700518,
+      "grad_norm": 0.9401625394821167,
+      "learning_rate": 9.984606400226304e-06,
+      "loss": 0.6618,
+      "step": 122
+    },
+    {
+      "epoch": 0.226208574034661,
+      "grad_norm": 0.9542201161384583,
+      "learning_rate": 9.98298800549479e-06,
+      "loss": 0.6435,
+      "step": 124
+    },
+    {
+      "epoch": 0.2298570994223168,
+      "grad_norm": 1.0500489473342896,
+      "learning_rate": 9.981288879232746e-06,
+      "loss": 0.6476,
+      "step": 126
+    },
+    {
+      "epoch": 0.23350562480997264,
+      "grad_norm": 1.0309292078018188,
+      "learning_rate": 9.97950904896845e-06,
+      "loss": 0.6439,
+      "step": 128
+    },
+    {
+      "epoch": 0.23715415019762845,
+      "grad_norm": 0.8687788844108582,
+      "learning_rate": 9.977648543537694e-06,
+      "loss": 0.6448,
+      "step": 130
+    },
+    {
+      "epoch": 0.2408026755852843,
+      "grad_norm": 0.8222269415855408,
+      "learning_rate": 9.975707393083328e-06,
+      "loss": 0.6336,
+      "step": 132
+    },
+    {
+      "epoch": 0.2444512009729401,
+      "grad_norm": 0.9232620596885681,
+      "learning_rate": 9.973685629054761e-06,
+      "loss": 0.6299,
+      "step": 134
+    },
+    {
+      "epoch": 0.24809972636059593,
+      "grad_norm": 42.93293380737305,
+      "learning_rate": 9.971583284207467e-06,
+      "loss": 0.6368,
+      "step": 136
+    },
+    {
+      "epoch": 0.2517482517482518,
+      "grad_norm": 0.8836601376533508,
+      "learning_rate": 9.969400392602436e-06,
+      "loss": 0.6316,
+      "step": 138
+    },
+    {
+      "epoch": 0.2553967771359076,
+      "grad_norm": 0.9281610250473022,
+      "learning_rate": 9.967136989605631e-06,
+      "loss": 0.6751,
+      "step": 140
+    },
+    {
+      "epoch": 0.2590453025235634,
+      "grad_norm": 0.9172906279563904,
+      "learning_rate": 9.96479311188742e-06,
+      "loss": 0.629,
+      "step": 142
+    },
+    {
+      "epoch": 0.2626938279112192,
+      "grad_norm": 0.828248143196106,
+      "learning_rate": 9.962368797421972e-06,
+      "loss": 0.6096,
+      "step": 144
+    },
+    {
+      "epoch": 0.266342353298875,
+      "grad_norm": 0.8610714673995972,
+      "learning_rate": 9.959864085486649e-06,
+      "loss": 0.6564,
+      "step": 146
+    },
+    {
+      "epoch": 0.2699908786865309,
+      "grad_norm": 1.1389037370681763,
+      "learning_rate": 9.957279016661361e-06,
+      "loss": 0.6528,
+      "step": 148
+    },
+    {
+      "epoch": 0.2736394040741867,
+      "grad_norm": 0.9322584271430969,
+      "learning_rate": 9.954613632827925e-06,
+      "loss": 0.6035,
+      "step": 150
+    },
+    {
+      "epoch": 0.2772879294618425,
+      "grad_norm": 1.0046380758285522,
+      "learning_rate": 9.95186797716937e-06,
+      "loss": 0.655,
+      "step": 152
+    },
+    {
+      "epoch": 0.2809364548494983,
+      "grad_norm": 0.8859027624130249,
+      "learning_rate": 9.949042094169236e-06,
+      "loss": 0.6405,
+      "step": 154
+    },
+    {
+      "epoch": 0.2845849802371542,
+      "grad_norm": 0.9578436613082886,
+      "learning_rate": 9.946136029610877e-06,
+      "loss": 0.6662,
+      "step": 156
+    },
+    {
+      "epoch": 0.28823350562481,
+      "grad_norm": 0.9982143044471741,
+      "learning_rate": 9.94314983057669e-06,
+      "loss": 0.6446,
+      "step": 158
+    },
+    {
+      "epoch": 0.2918820310124658,
+      "grad_norm": 1.0939911603927612,
+      "learning_rate": 9.94008354544737e-06,
+      "loss": 0.6476,
+      "step": 160
+    },
+    {
+      "epoch": 0.2955305564001216,
+      "grad_norm": 1.0458049774169922,
+      "learning_rate": 9.936937223901119e-06,
+      "loss": 0.6427,
+      "step": 162
+    },
+    {
+      "epoch": 0.2991790817877774,
+      "grad_norm": 1.1223981380462646,
+      "learning_rate": 9.933710916912847e-06,
+      "loss": 0.663,
+      "step": 164
+    },
+    {
+      "epoch": 0.3028276071754333,
+      "grad_norm": 1.3451194763183594,
+      "learning_rate": 9.930404676753338e-06,
+      "loss": 0.6635,
+      "step": 166
+    },
+    {
+      "epoch": 0.3064761325630891,
+      "grad_norm": 1.32749605178833,
+      "learning_rate": 9.927018556988413e-06,
+      "loss": 0.6475,
+      "step": 168
+    },
+    {
+      "epoch": 0.3101246579507449,
+      "grad_norm": 0.7651606202125549,
+      "learning_rate": 9.923552612478048e-06,
+      "loss": 0.5907,
+      "step": 170
+    },
+    {
+      "epoch": 0.3137731833384007,
+      "grad_norm": 0.8623411655426025,
+      "learning_rate": 9.920006899375507e-06,
+      "loss": 0.6272,
+      "step": 172
+    },
+    {
+      "epoch": 0.3174217087260566,
+      "grad_norm": 6.449504375457764,
+      "learning_rate": 9.916381475126406e-06,
+      "loss": 0.6907,
+      "step": 174
+    },
+    {
+      "epoch": 0.3210702341137124,
+      "grad_norm": 1.2437793016433716,
+      "learning_rate": 9.912676398467807e-06,
+      "loss": 0.6325,
+      "step": 176
+    },
+    {
+      "epoch": 0.3247187595013682,
+      "grad_norm": 0.8467330932617188,
+      "learning_rate": 9.908891729427245e-06,
+      "loss": 0.6178,
+      "step": 178
+    },
+    {
+      "epoch": 0.328367284889024,
+      "grad_norm": 0.8577013611793518,
+      "learning_rate": 9.905027529321771e-06,
+      "loss": 0.6048,
+      "step": 180
+    },
+    {
+      "epoch": 0.33201581027667987,
+      "grad_norm": 0.845434308052063,
+      "learning_rate": 9.901083860756954e-06,
+      "loss": 0.6177,
+      "step": 182
+    },
+    {
+      "epoch": 0.3356643356643357,
+      "grad_norm": 0.7583611011505127,
+      "learning_rate": 9.89706078762586e-06,
+      "loss": 0.5888,
+      "step": 184
+    },
+    {
+      "epoch": 0.3393128610519915,
+      "grad_norm": 0.9179339408874512,
+      "learning_rate": 9.892958375108031e-06,
+      "loss": 0.6216,
+      "step": 186
+    },
+    {
+      "epoch": 0.3429613864396473,
+      "grad_norm": 0.8592986464500427,
+      "learning_rate": 9.88877668966841e-06,
+      "loss": 0.611,
+      "step": 188
+    },
+    {
+      "epoch": 0.3466099118273031,
+      "grad_norm": 1.0181283950805664,
+      "learning_rate": 9.884515799056284e-06,
+      "loss": 0.6174,
+      "step": 190
+    },
+    {
+      "epoch": 0.350258437214959,
+      "grad_norm": 0.7851302623748779,
+      "learning_rate": 9.880175772304173e-06,
+      "loss": 0.5936,
+      "step": 192
+    },
+    {
+      "epoch": 0.3539069626026148,
+      "grad_norm": 0.7657840251922607,
+      "learning_rate": 9.875756679726714e-06,
+      "loss": 0.5997,
+      "step": 194
+    },
+    {
+      "epoch": 0.3575554879902706,
+      "grad_norm": 1.089402437210083,
+      "learning_rate": 9.871258592919524e-06,
+      "loss": 0.6162,
+      "step": 196
+    },
+    {
+      "epoch": 0.3612040133779264,
+      "grad_norm": 0.9028885960578918,
+      "learning_rate": 9.866681584758046e-06,
+      "loss": 0.6279,
+      "step": 198
+    },
+    {
+      "epoch": 0.36485253876558227,
+      "grad_norm": 0.8105641007423401,
+      "learning_rate": 9.862025729396352e-06,
+      "loss": 0.6212,
+      "step": 200
+    },
+    {
+      "epoch": 0.3685010641532381,
+      "grad_norm": 0.8687553405761719,
+      "learning_rate": 9.85729110226596e-06,
+      "loss": 0.6361,
+      "step": 202
+    },
+    {
+      "epoch": 0.3721495895408939,
+      "grad_norm": 0.7712480425834656,
+      "learning_rate": 9.852477780074596e-06,
+      "loss": 0.619,
+      "step": 204
+    },
+    {
+      "epoch": 0.3757981149285497,
+      "grad_norm": 0.7695804238319397,
+      "learning_rate": 9.84758584080496e-06,
+      "loss": 0.6077,
+      "step": 206
+    },
+    {
+      "epoch": 0.3794466403162055,
+      "grad_norm": 0.7548947334289551,
+      "learning_rate": 9.84261536371347e-06,
+      "loss": 0.5898,
+      "step": 208
+    },
+    {
+      "epoch": 0.3830951657038614,
+      "grad_norm": 0.7162324786186218,
+      "learning_rate": 9.837566429328953e-06,
+      "loss": 0.6237,
+      "step": 210
+    },
+    {
+      "epoch": 0.3867436910915172,
+      "grad_norm": 1.5595295429229736,
+      "learning_rate": 9.832439119451372e-06,
+      "loss": 0.6137,
+      "step": 212
+    },
+    {
+      "epoch": 0.390392216479173,
+      "grad_norm": 0.7806109189987183,
+      "learning_rate": 9.827233517150475e-06,
+      "loss": 0.5901,
+      "step": 214
+    },
+    {
+      "epoch": 0.3940407418668288,
+      "grad_norm": 0.7377996444702148,
+      "learning_rate": 9.821949706764463e-06,
+      "loss": 0.643,
+      "step": 216
+    },
+    {
+      "epoch": 0.39768926725448467,
+      "grad_norm": 0.7791337966918945,
+      "learning_rate": 9.81658777389862e-06,
+      "loss": 0.5872,
+      "step": 218
+    },
+    {
+      "epoch": 0.4013377926421405,
+      "grad_norm": 0.7520440816879272,
+      "learning_rate": 9.811147805423924e-06,
+      "loss": 0.5711,
+      "step": 220
+    },
+    {
+      "epoch": 0.4049863180297963,
+      "grad_norm": 0.8312076330184937,
+      "learning_rate": 9.805629889475641e-06,
+      "loss": 0.6397,
+      "step": 222
+    },
+    {
+      "epoch": 0.4086348434174521,
+      "grad_norm": 0.6981707811355591,
+      "learning_rate": 9.800034115451904e-06,
+      "loss": 0.5765,
+      "step": 224
+    },
+    {
+      "epoch": 0.4122833688051079,
+      "grad_norm": 0.9388242959976196,
+      "learning_rate": 9.794360574012249e-06,
+      "loss": 0.606,
+      "step": 226
+    },
+    {
+      "epoch": 0.4159318941927638,
+      "grad_norm": 1.5727872848510742,
+      "learning_rate": 9.788609357076159e-06,
+      "loss": 0.5848,
+      "step": 228
+    },
+    {
+      "epoch": 0.4195804195804196,
+      "grad_norm": 0.787630558013916,
+      "learning_rate": 9.782780557821576e-06,
+      "loss": 0.5848,
+      "step": 230
+    },
+    {
+      "epoch": 0.4232289449680754,
+      "grad_norm": 0.7875147461891174,
+      "learning_rate": 9.776874270683378e-06,
+      "loss": 0.5712,
+      "step": 232
+    },
+    {
+      "epoch": 0.4268774703557312,
+      "grad_norm": 0.6882831454277039,
+      "learning_rate": 9.770890591351865e-06,
+      "loss": 0.5804,
+      "step": 234
+    },
+    {
+      "epoch": 0.43052599574338707,
+      "grad_norm": 0.856640100479126,
+      "learning_rate": 9.764829616771194e-06,
+      "loss": 0.6282,
+      "step": 236
+    },
+    {
+      "epoch": 0.4341745211310429,
+      "grad_norm": 0.7834499478340149,
+      "learning_rate": 9.758691445137822e-06,
+      "loss": 0.5872,
+      "step": 238
+    },
+    {
+      "epoch": 0.4378230465186987,
+      "grad_norm": 0.8516238331794739,
+      "learning_rate": 9.752476175898905e-06,
+      "loss": 0.6049,
+      "step": 240
+    },
+    {
+      "epoch": 0.4414715719063545,
+      "grad_norm": 0.8098310828208923,
+      "learning_rate": 9.746183909750692e-06,
+      "loss": 0.6276,
+      "step": 242
+    },
+    {
+      "epoch": 0.44512009729401036,
+      "grad_norm": 0.8648990392684937,
+      "learning_rate": 9.739814748636892e-06,
+      "loss": 0.6254,
+      "step": 244
+    },
+    {
+      "epoch": 0.4487686226816662,
+      "grad_norm": 0.8435967564582825,
+      "learning_rate": 9.73336879574702e-06,
+      "loss": 0.6099,
+      "step": 246
+    },
+    {
+      "epoch": 0.452417148069322,
+      "grad_norm": 0.7823182344436646,
+      "learning_rate": 9.726846155514731e-06,
+      "loss": 0.571,
+      "step": 248
+    },
+    {
+      "epoch": 0.4560656734569778,
+      "grad_norm": 0.84818434715271,
+      "learning_rate": 9.720246933616125e-06,
+      "loss": 0.5939,
+      "step": 250
+    },
+    {
+      "epoch": 0.4597141988446336,
+      "grad_norm": 0.8617188930511475,
+      "learning_rate": 9.713571236968026e-06,
+      "loss": 0.6102,
+      "step": 252
+    },
+    {
+      "epoch": 0.46336272423228947,
+      "grad_norm": 0.7632100582122803,
+      "learning_rate": 9.706819173726273e-06,
+      "loss": 0.5874,
+      "step": 254
+    },
+    {
+      "epoch": 0.4670112496199453,
+      "grad_norm": 0.7862482070922852,
+      "learning_rate": 9.69999085328394e-06,
+      "loss": 0.6042,
+      "step": 256
+    },
+    {
+      "epoch": 0.4706597750076011,
+      "grad_norm": 1.2909066677093506,
+      "learning_rate": 9.693086386269581e-06,
+      "loss": 0.6243,
+      "step": 258
+    },
+    {
+      "epoch": 0.4743083003952569,
+      "grad_norm": 0.7482678890228271,
+      "learning_rate": 9.686105884545435e-06,
+      "loss": 0.6056,
+      "step": 260
+    },
+    {
+      "epoch": 0.47795682578291276,
+      "grad_norm": 0.9162628650665283,
+      "learning_rate": 9.679049461205614e-06,
+      "loss": 0.5943,
+      "step": 262
+    },
+    {
+      "epoch": 0.4816053511705686,
+      "grad_norm": 1.1275169849395752,
+      "learning_rate": 9.671917230574262e-06,
+      "loss": 0.635,
+      "step": 264
+    },
+    {
+      "epoch": 0.4852538765582244,
+      "grad_norm": 0.904468297958374,
+      "learning_rate": 9.664709308203713e-06,
+      "loss": 0.599,
+      "step": 266
+    },
+    {
+      "epoch": 0.4889024019458802,
+      "grad_norm": 0.7175026535987854,
+      "learning_rate": 9.657425810872616e-06,
+      "loss": 0.5455,
+      "step": 268
+    },
+    {
+      "epoch": 0.492550927333536,
+      "grad_norm": 0.7503458857536316,
+      "learning_rate": 9.650066856584045e-06,
+      "loss": 0.5903,
+      "step": 270
+    },
+    {
+      "epoch": 0.49619945272119187,
+      "grad_norm": 0.8808678984642029,
+      "learning_rate": 9.642632564563576e-06,
+      "loss": 0.5982,
+      "step": 272
+    },
+    {
+      "epoch": 0.4998479781088477,
+      "grad_norm": 0.9144216179847717,
+      "learning_rate": 9.635123055257373e-06,
+      "loss": 0.5781,
+      "step": 274
+    },
+    {
+      "epoch": 0.5034965034965035,
+      "grad_norm": 1.0071049928665161,
+      "learning_rate": 9.627538450330224e-06,
+      "loss": 0.6302,
+      "step": 276
+    },
+    {
+      "epoch": 0.5071450288841594,
+      "grad_norm": 0.7271871566772461,
+      "learning_rate": 9.619878872663572e-06,
+      "loss": 0.5632,
+      "step": 278
+    },
+    {
+      "epoch": 0.5107935542718152,
+      "grad_norm": 0.7123481631278992,
+      "learning_rate": 9.612144446353532e-06,
+      "loss": 0.5849,
+      "step": 280
+    },
+    {
+      "epoch": 0.514442079659471,
+      "grad_norm": 0.668262243270874,
+      "learning_rate": 9.604335296708861e-06,
+      "loss": 0.5687,
+      "step": 282
+    },
+    {
+      "epoch": 0.5180906050471268,
+      "grad_norm": 0.872313916683197,
+      "learning_rate": 9.596451550248955e-06,
+      "loss": 0.5906,
+      "step": 284
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.8018190264701843,
+      "learning_rate": 9.588493334701778e-06,
+      "loss": 0.5893,
+      "step": 286
+    },
+    {
+      "epoch": 0.5253876558224384,
+      "grad_norm": 0.7583948373794556,
+      "learning_rate": 9.580460779001802e-06,
+      "loss": 0.5778,
+      "step": 288
+    },
+    {
+      "epoch": 0.5290361812100942,
+      "grad_norm": 0.7148042321205139,
+      "learning_rate": 9.57235401328791e-06,
+      "loss": 0.586,
+      "step": 290
+    },
+    {
+      "epoch": 0.53268470659775,
+      "grad_norm": 0.793960690498352,
+      "learning_rate": 9.564173168901302e-06,
+      "loss": 0.5996,
+      "step": 292
+    },
+    {
+      "epoch": 0.536333231985406,
+      "grad_norm": 0.7752788662910461,
+      "learning_rate": 9.555918378383353e-06,
+      "loss": 0.5904,
+      "step": 294
+    },
+    {
+      "epoch": 0.5399817573730618,
+      "grad_norm": 0.7369986176490784,
+      "learning_rate": 9.54758977547347e-06,
+      "loss": 0.6031,
+      "step": 296
+    },
+    {
+      "epoch": 0.5436302827607176,
+      "grad_norm": 0.6657317876815796,
+      "learning_rate": 9.539187495106936e-06,
+      "loss": 0.5762,
+      "step": 298
+    },
+    {
+      "epoch": 0.5472788081483734,
+      "grad_norm": 0.7155686616897583,
+      "learning_rate": 9.530711673412698e-06,
+      "loss": 0.5715,
+      "step": 300
+    },
+    {
+      "epoch": 0.5509273335360292,
+      "grad_norm": 0.821488618850708,
+      "learning_rate": 9.522162447711192e-06,
+      "loss": 0.5641,
+      "step": 302
+    },
+    {
+      "epoch": 0.554575858923685,
+      "grad_norm": 0.7769792675971985,
+      "learning_rate": 9.513539956512096e-06,
+      "loss": 0.5996,
+      "step": 304
+    },
+    {
+      "epoch": 0.5582243843113408,
+      "grad_norm": 0.738440215587616,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.5765,
+      "step": 306
+    },
+    {
+      "epoch": 0.5618729096989966,
+      "grad_norm": 0.7775160670280457,
+      "learning_rate": 9.496075737592623e-06,
+      "loss": 0.5576,
+      "step": 308
+    },
+    {
+      "epoch": 0.5655214350866524,
+      "grad_norm": 0.773650586605072,
+      "learning_rate": 9.487234292817563e-06,
+      "loss": 0.5955,
+      "step": 310
+    },
+    {
+      "epoch": 0.5691699604743083,
+      "grad_norm": 0.6792920231819153,
+      "learning_rate": 9.478320148430965e-06,
+      "loss": 0.5612,
+      "step": 312
+    },
+    {
+      "epoch": 0.5728184858619642,
+      "grad_norm": 0.795219898223877,
+      "learning_rate": 9.469333448854713e-06,
+      "loss": 0.5886,
+      "step": 314
+    },
+    {
+      "epoch": 0.57646701124962,
+      "grad_norm": 0.7756664752960205,
+      "learning_rate": 9.460274339686189e-06,
+      "loss": 0.6012,
+      "step": 316
+    },
+    {
+      "epoch": 0.5801155366372758,
+      "grad_norm": 0.6775463223457336,
+      "learning_rate": 9.451142967695916e-06,
+      "loss": 0.5483,
+      "step": 318
+    },
+    {
+      "epoch": 0.5837640620249316,
+      "grad_norm": 0.7596588134765625,
+      "learning_rate": 9.441939480825176e-06,
+      "loss": 0.5683,
+      "step": 320
+    },
+    {
+      "epoch": 0.5874125874125874,
+      "grad_norm": 0.703626811504364,
+      "learning_rate": 9.432664028183615e-06,
+      "loss": 0.5724,
+      "step": 322
+    },
+    {
+      "epoch": 0.5910611128002432,
+      "grad_norm": 0.7344934344291687,
+      "learning_rate": 9.42331676004683e-06,
+      "loss": 0.5934,
+      "step": 324
+    },
+    {
+      "epoch": 0.594709638187899,
+      "grad_norm": 0.7058429718017578,
+      "learning_rate": 9.413897827853929e-06,
+      "loss": 0.5582,
+      "step": 326
+    },
+    {
+      "epoch": 0.5983581635755548,
+      "grad_norm": 0.7114812135696411,
+      "learning_rate": 9.404407384205078e-06,
+      "loss": 0.592,
+      "step": 328
+    },
+    {
+      "epoch": 0.6020066889632107,
+      "grad_norm": 3.259948253631592,
+      "learning_rate": 9.394845582859038e-06,
+      "loss": 0.6054,
+      "step": 330
+    },
+    {
+      "epoch": 0.6056552143508666,
+      "grad_norm": 0.7661309242248535,
+      "learning_rate": 9.38521257873066e-06,
+      "loss": 0.56,
+      "step": 332
+    },
+    {
+      "epoch": 0.6093037397385224,
+      "grad_norm": 0.899976909160614,
+      "learning_rate": 9.375508527888389e-06,
+      "loss": 0.5968,
+      "step": 334
+    },
+    {
+      "epoch": 0.6129522651261782,
+      "grad_norm": 0.7192819714546204,
+      "learning_rate": 9.365733587551717e-06,
+      "loss": 0.6015,
+      "step": 336
+    },
+    {
+      "epoch": 0.616600790513834,
+      "grad_norm": 0.7547832131385803,
+      "learning_rate": 9.355887916088658e-06,
+      "loss": 0.582,
+      "step": 338
+    },
+    {
+      "epoch": 0.6202493159014898,
+      "grad_norm": 0.683064341545105,
+      "learning_rate": 9.345971673013166e-06,
+      "loss": 0.5854,
+      "step": 340
+    },
+    {
+      "epoch": 0.6238978412891456,
+      "grad_norm": 0.7966418862342834,
+      "learning_rate": 9.33598501898256e-06,
+      "loss": 0.5778,
+      "step": 342
+    },
+    {
+      "epoch": 0.6275463666768014,
+      "grad_norm": 0.7256126999855042,
+      "learning_rate": 9.325928115794911e-06,
+      "loss": 0.5832,
+      "step": 344
+    },
+    {
+      "epoch": 0.6311948920644573,
+      "grad_norm": 0.6923336386680603,
+      "learning_rate": 9.315801126386432e-06,
+      "loss": 0.586,
+      "step": 346
+    },
+    {
+      "epoch": 0.6348434174521131,
+      "grad_norm": 0.7444384694099426,
+      "learning_rate": 9.305604214828833e-06,
+      "loss": 0.6072,
+      "step": 348
+    },
+    {
+      "epoch": 0.638491942839769,
+      "grad_norm": 0.7712548971176147,
+      "learning_rate": 9.295337546326658e-06,
+      "loss": 0.5934,
+      "step": 350
+    },
+    {
+      "epoch": 0.6421404682274248,
+      "grad_norm": 0.7229786515235901,
+      "learning_rate": 9.28500128721462e-06,
+      "loss": 0.5688,
+      "step": 352
+    },
+    {
+      "epoch": 0.6457889936150806,
+      "grad_norm": 0.6662163138389587,
+      "learning_rate": 9.27459560495489e-06,
+      "loss": 0.5473,
+      "step": 354
+    },
+    {
+      "epoch": 0.6494375190027364,
+      "grad_norm": 0.7679241299629211,
+      "learning_rate": 9.264120668134405e-06,
+      "loss": 0.5947,
+      "step": 356
+    },
+    {
+      "epoch": 0.6530860443903922,
+      "grad_norm": 0.7818153500556946,
+      "learning_rate": 9.253576646462115e-06,
+      "loss": 0.5697,
+      "step": 358
+    },
+    {
+      "epoch": 0.656734569778048,
+      "grad_norm": 0.7283984422683716,
+      "learning_rate": 9.242963710766249e-06,
+      "loss": 0.5676,
+      "step": 360
+    },
+    {
+      "epoch": 0.6603830951657038,
+      "grad_norm": 0.6908257603645325,
+      "learning_rate": 9.232282032991539e-06,
+      "loss": 0.5802,
+      "step": 362
+    },
+    {
+      "epoch": 0.6640316205533597,
+      "grad_norm": 0.6994187831878662,
+      "learning_rate": 9.22153178619644e-06,
+      "loss": 0.5792,
+      "step": 364
+    },
+    {
+      "epoch": 0.6676801459410155,
+      "grad_norm": 0.7992912530899048,
+      "learning_rate": 9.210713144550318e-06,
+      "loss": 0.5839,
+      "step": 366
+    },
+    {
+      "epoch": 0.6713286713286714,
+      "grad_norm": 0.7373973727226257,
+      "learning_rate": 9.199826283330641e-06,
+      "loss": 0.5671,
+      "step": 368
+    },
+    {
+      "epoch": 0.6749771967163272,
+      "grad_norm": 0.7272558212280273,
+      "learning_rate": 9.188871378920123e-06,
+      "loss": 0.5568,
+      "step": 370
+    },
+    {
+      "epoch": 0.678625722103983,
+      "grad_norm": 0.6657068133354187,
+      "learning_rate": 9.17784860880388e-06,
+      "loss": 0.5284,
+      "step": 372
+    },
+    {
+      "epoch": 0.6822742474916388,
+      "grad_norm": 0.7878971099853516,
+      "learning_rate": 9.16675815156655e-06,
+      "loss": 0.6024,
+      "step": 374
+    },
+    {
+      "epoch": 0.6859227728792946,
+      "grad_norm": 0.7263739109039307,
+      "learning_rate": 9.155600186889396e-06,
+      "loss": 0.5926,
+      "step": 376
+    },
+    {
+      "epoch": 0.6895712982669504,
+      "grad_norm": 0.7257018089294434,
+      "learning_rate": 9.1443748955474e-06,
+      "loss": 0.5746,
+      "step": 378
+    },
+    {
+      "epoch": 0.6932198236546062,
+      "grad_norm": 0.7777044773101807,
+      "learning_rate": 9.133082459406335e-06,
+      "loss": 0.5908,
+      "step": 380
+    },
+    {
+      "epoch": 0.6968683490422621,
+      "grad_norm": 2.0082859992980957,
+      "learning_rate": 9.12172306141981e-06,
+      "loss": 0.5901,
+      "step": 382
+    },
+    {
+      "epoch": 0.700516874429918,
+      "grad_norm": 0.6709379553794861,
+      "learning_rate": 9.110296885626315e-06,
+      "loss": 0.5731,
+      "step": 384
+    },
+    {
+      "epoch": 0.7041653998175738,
+      "grad_norm": 0.684029757976532,
+      "learning_rate": 9.098804117146233e-06,
+      "loss": 0.5962,
+      "step": 386
+    },
+    {
+      "epoch": 0.7078139252052296,
+      "grad_norm": 0.6345304250717163,
+      "learning_rate": 9.087244942178852e-06,
+      "loss": 0.567,
+      "step": 388
+    },
+    {
+      "epoch": 0.7114624505928854,
+      "grad_norm": 0.7014210224151611,
+      "learning_rate": 9.075619547999328e-06,
+      "loss": 0.5665,
+      "step": 390
+    },
+    {
+      "epoch": 0.7151109759805412,
+      "grad_norm": 0.7121542096138,
+      "learning_rate": 9.063928122955673e-06,
+      "loss": 0.5788,
+      "step": 392
+    },
+    {
+      "epoch": 0.718759501368197,
+      "grad_norm": 0.6985682249069214,
+      "learning_rate": 9.052170856465688e-06,
+      "loss": 0.5724,
+      "step": 394
+    },
+    {
+      "epoch": 0.7224080267558528,
+      "grad_norm": 0.6903934478759766,
+      "learning_rate": 9.0403479390139e-06,
+      "loss": 0.5311,
+      "step": 396
+    },
+    {
+      "epoch": 0.7260565521435086,
+      "grad_norm": 0.6758017539978027,
+      "learning_rate": 9.028459562148479e-06,
+      "loss": 0.5406,
+      "step": 398
+    },
+    {
+      "epoch": 0.7297050775311645,
+      "grad_norm": 0.6947284936904907,
+      "learning_rate": 9.016505918478126e-06,
+      "loss": 0.6009,
+      "step": 400
+    },
+    {
+      "epoch": 0.7333536029188203,
+      "grad_norm": 0.7199047803878784,
+      "learning_rate": 9.004487201668962e-06,
+      "loss": 0.5693,
+      "step": 402
+    },
+    {
+      "epoch": 0.7370021283064762,
+      "grad_norm": 0.7680858969688416,
+      "learning_rate": 8.992403606441386e-06,
+      "loss": 0.5848,
+      "step": 404
+    },
+    {
+      "epoch": 0.740650653694132,
+      "grad_norm": 0.727476954460144,
+      "learning_rate": 8.980255328566914e-06,
+      "loss": 0.5926,
+      "step": 406
+    },
+    {
+      "epoch": 0.7442991790817878,
+      "grad_norm": 0.7595219016075134,
+      "learning_rate": 8.968042564865018e-06,
+      "loss": 0.5917,
+      "step": 408
+    },
+    {
+      "epoch": 0.7479477044694436,
+      "grad_norm": 2.183056354522705,
+      "learning_rate": 8.955765513199935e-06,
+      "loss": 0.5854,
+      "step": 410
+    },
+    {
+      "epoch": 0.7515962298570994,
+      "grad_norm": 0.767233669757843,
+      "learning_rate": 8.943424372477455e-06,
+      "loss": 0.5806,
+      "step": 412
+    },
+    {
+      "epoch": 0.7552447552447552,
+      "grad_norm": 0.7878931164741516,
+      "learning_rate": 8.931019342641702e-06,
+      "loss": 0.5893,
+      "step": 414
+    },
+    {
+      "epoch": 0.758893280632411,
+      "grad_norm": 0.7827096581459045,
+      "learning_rate": 8.918550624671899e-06,
+      "loss": 0.5871,
+      "step": 416
+    },
+    {
+      "epoch": 0.7625418060200669,
+      "grad_norm": 0.6943903565406799,
+      "learning_rate": 8.906018420579102e-06,
+      "loss": 0.5587,
+      "step": 418
+    },
+    {
+      "epoch": 0.7661903314077227,
+      "grad_norm": 0.7684059143066406,
+      "learning_rate": 8.893422933402939e-06,
+      "loss": 0.5728,
+      "step": 420
+    },
+    {
+      "epoch": 0.7698388567953786,
+      "grad_norm": 0.747462809085846,
+      "learning_rate": 8.880764367208311e-06,
+      "loss": 0.5733,
+      "step": 422
+    },
+    {
+      "epoch": 0.7734873821830344,
+      "grad_norm": 0.7486701011657715,
+      "learning_rate": 8.86804292708209e-06,
+      "loss": 0.5708,
+      "step": 424
+    },
+    {
+      "epoch": 0.7771359075706902,
+      "grad_norm": 0.6867607831954956,
+      "learning_rate": 8.855258819129796e-06,
+      "loss": 0.5606,
+      "step": 426
+    },
+    {
+      "epoch": 0.780784432958346,
+      "grad_norm": 0.6859204769134521,
+      "learning_rate": 8.842412250472257e-06,
+      "loss": 0.5518,
+      "step": 428
+    },
+    {
+      "epoch": 0.7844329583460018,
+      "grad_norm": 0.7135295867919922,
+      "learning_rate": 8.82950342924225e-06,
+      "loss": 0.5606,
+      "step": 430
+    },
+    {
+      "epoch": 0.7880814837336576,
+      "grad_norm": 0.7061953544616699,
+      "learning_rate": 8.816532564581141e-06,
+      "loss": 0.5435,
+      "step": 432
+    },
+    {
+      "epoch": 0.7917300091213134,
+      "grad_norm": 0.7126162648200989,
+      "learning_rate": 8.803499866635484e-06,
+      "loss": 0.5659,
+      "step": 434
+    },
+    {
+      "epoch": 0.7953785345089693,
+      "grad_norm": 0.6607726812362671,
+      "learning_rate": 8.790405546553615e-06,
+      "loss": 0.5624,
+      "step": 436
+    },
+    {
+      "epoch": 0.7990270598966251,
+      "grad_norm": 0.8032154440879822,
+      "learning_rate": 8.777249816482248e-06,
+      "loss": 0.5847,
+      "step": 438
+    },
+    {
+      "epoch": 0.802675585284281,
+      "grad_norm": 0.7459051012992859,
+      "learning_rate": 8.764032889563017e-06,
+      "loss": 0.5369,
+      "step": 440
+    },
+    {
+      "epoch": 0.8063241106719368,
+      "grad_norm": 0.7046535015106201,
+      "learning_rate": 8.750754979929039e-06,
+      "loss": 0.5954,
+      "step": 442
+    },
+    {
+      "epoch": 0.8099726360595926,
+      "grad_norm": 0.7219237089157104,
+      "learning_rate": 8.737416302701431e-06,
+      "loss": 0.5786,
+      "step": 444
+    },
+    {
+      "epoch": 0.8136211614472484,
+      "grad_norm": 0.7423882484436035,
+      "learning_rate": 8.724017073985839e-06,
+      "loss": 0.5965,
+      "step": 446
+    },
+    {
+      "epoch": 0.8172696868349042,
+      "grad_norm": 0.6467640995979309,
+      "learning_rate": 8.710557510868927e-06,
+      "loss": 0.5411,
+      "step": 448
+    },
+    {
+      "epoch": 0.82091821222256,
+      "grad_norm": 0.6709014177322388,
+      "learning_rate": 8.697037831414864e-06,
+      "loss": 0.5536,
+      "step": 450
+    },
+    {
+      "epoch": 0.8245667376102158,
+      "grad_norm": 0.7297953367233276,
+      "learning_rate": 8.683458254661781e-06,
+      "loss": 0.603,
+      "step": 452
+    },
+    {
+      "epoch": 0.8282152629978717,
+      "grad_norm": 0.7067564129829407,
+      "learning_rate": 8.669819000618248e-06,
+      "loss": 0.5763,
+      "step": 454
+    },
+    {
+      "epoch": 0.8318637883855275,
+      "grad_norm": 0.7232553958892822,
+      "learning_rate": 8.656120290259673e-06,
+      "loss": 0.5614,
+      "step": 456
+    },
+    {
+      "epoch": 0.8355123137731834,
+      "grad_norm": 0.6735249161720276,
+      "learning_rate": 8.642362345524758e-06,
+      "loss": 0.5691,
+      "step": 458
+    },
+    {
+      "epoch": 0.8391608391608392,
+      "grad_norm": 0.6731123924255371,
+      "learning_rate": 8.628545389311872e-06,
+      "loss": 0.5838,
+      "step": 460
+    },
+    {
+      "epoch": 0.842809364548495,
+      "grad_norm": 0.8049919605255127,
+      "learning_rate": 8.614669645475472e-06,
+      "loss": 0.571,
+      "step": 462
+    },
+    {
+      "epoch": 0.8464578899361508,
+      "grad_norm": 0.6665669083595276,
+      "learning_rate": 8.600735338822437e-06,
+      "loss": 0.5752,
+      "step": 464
+    },
+    {
+      "epoch": 0.8501064153238066,
+      "grad_norm": 0.7003177404403687,
+      "learning_rate": 8.586742695108466e-06,
+      "loss": 0.5614,
+      "step": 466
+    },
+    {
+      "epoch": 0.8537549407114624,
+      "grad_norm": 0.6717367768287659,
+      "learning_rate": 8.57269194103439e-06,
+      "loss": 0.5567,
+      "step": 468
+    },
+    {
+      "epoch": 0.8574034660991183,
+      "grad_norm": 0.6508170366287231,
+      "learning_rate": 8.558583304242517e-06,
+      "loss": 0.5593,
+      "step": 470
+    },
+    {
+      "epoch": 0.8610519914867741,
+      "grad_norm": 0.7082860469818115,
+      "learning_rate": 8.544417013312936e-06,
+      "loss": 0.5785,
+      "step": 472
+    },
+    {
+      "epoch": 0.86470051687443,
+      "grad_norm": 0.7284791469573975,
+      "learning_rate": 8.530193297759815e-06,
+      "loss": 0.5782,
+      "step": 474
+    },
+    {
+      "epoch": 0.8683490422620858,
+      "grad_norm": 0.6406228542327881,
+      "learning_rate": 8.515912388027686e-06,
+      "loss": 0.548,
+      "step": 476
+    },
+    {
+      "epoch": 0.8719975676497416,
+      "grad_norm": 0.6882789731025696,
+      "learning_rate": 8.501574515487703e-06,
+      "loss": 0.5652,
+      "step": 478
+    },
+    {
+      "epoch": 0.8756460930373974,
+      "grad_norm": 0.7030681371688843,
+      "learning_rate": 8.487179912433901e-06,
+      "loss": 0.5627,
+      "step": 480
+    },
+    {
+      "epoch": 0.8792946184250532,
+      "grad_norm": 0.6933782696723938,
+      "learning_rate": 8.472728812079436e-06,
+      "loss": 0.5419,
+      "step": 482
+    },
+    {
+      "epoch": 0.882943143812709,
+      "grad_norm": 0.6431456208229065,
+      "learning_rate": 8.458221448552793e-06,
+      "loss": 0.5627,
+      "step": 484
+    },
+    {
+      "epoch": 0.8865916692003648,
+      "grad_norm": 0.6375321745872498,
+      "learning_rate": 8.443658056894002e-06,
+      "loss": 0.5301,
+      "step": 486
+    },
+    {
+      "epoch": 0.8902401945880207,
+      "grad_norm": 0.7267205715179443,
+      "learning_rate": 8.429038873050837e-06,
+      "loss": 0.5773,
+      "step": 488
+    },
+    {
+      "epoch": 0.8938887199756765,
+      "grad_norm": 0.7091553211212158,
+      "learning_rate": 8.414364133874975e-06,
+      "loss": 0.6014,
+      "step": 490
+    },
+    {
+      "epoch": 0.8975372453633323,
+      "grad_norm": 0.719589114189148,
+      "learning_rate": 8.399634077118174e-06,
+      "loss": 0.569,
+      "step": 492
+    },
+    {
+      "epoch": 0.9011857707509882,
+      "grad_norm": 0.69126296043396,
+      "learning_rate": 8.384848941428416e-06,
+      "loss": 0.5909,
+      "step": 494
+    },
+    {
+      "epoch": 0.904834296138644,
+      "grad_norm": 0.6553617715835571,
+      "learning_rate": 8.370008966346037e-06,
+      "loss": 0.5883,
+      "step": 496
+    },
+    {
+      "epoch": 0.9084828215262998,
+      "grad_norm": 0.6911901831626892,
+      "learning_rate": 8.355114392299854e-06,
+      "loss": 0.5858,
+      "step": 498
+    },
+    {
+      "epoch": 0.9121313469139556,
+      "grad_norm": 0.7813802361488342,
+      "learning_rate": 8.340165460603265e-06,
+      "loss": 0.5711,
+      "step": 500
+    },
+    {
+      "epoch": 0.9157798723016114,
+      "grad_norm": 0.7495428323745728,
+      "learning_rate": 8.325162413450335e-06,
+      "loss": 0.5834,
+      "step": 502
+    },
+    {
+      "epoch": 0.9194283976892672,
+      "grad_norm": 0.684932291507721,
+      "learning_rate": 8.31010549391188e-06,
+      "loss": 0.5607,
+      "step": 504
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.6697359085083008,
+      "learning_rate": 8.294994945931524e-06,
+      "loss": 0.5677,
+      "step": 506
+    },
+    {
+      "epoch": 0.9267254484645789,
+      "grad_norm": 0.7115737199783325,
+      "learning_rate": 8.279831014321755e-06,
+      "loss": 0.571,
+      "step": 508
+    },
+    {
+      "epoch": 0.9303739738522347,
+      "grad_norm": 0.6556895971298218,
+      "learning_rate": 8.264613944759942e-06,
+      "loss": 0.5709,
+      "step": 510
+    },
+    {
+      "epoch": 0.9340224992398906,
+      "grad_norm": 0.694290816783905,
+      "learning_rate": 8.249343983784374e-06,
+      "loss": 0.5358,
+      "step": 512
+    },
+    {
+      "epoch": 0.9376710246275464,
+      "grad_norm": 0.5983056426048279,
+      "learning_rate": 8.23402137879025e-06,
+      "loss": 0.5439,
+      "step": 514
+    },
+    {
+      "epoch": 0.9413195500152022,
+      "grad_norm": 0.6577212810516357,
+      "learning_rate": 8.218646378025677e-06,
+      "loss": 0.5554,
+      "step": 516
+    },
+    {
+      "epoch": 0.944968075402858,
+      "grad_norm": 0.6748146414756775,
+      "learning_rate": 8.203219230587654e-06,
+      "loss": 0.5435,
+      "step": 518
+    },
+    {
+      "epoch": 0.9486166007905138,
+      "grad_norm": 0.6512753367424011,
+      "learning_rate": 8.187740186418027e-06,
+      "loss": 0.5404,
+      "step": 520
+    },
+    {
+      "epoch": 0.9522651261781696,
+      "grad_norm": 0.6830946803092957,
+      "learning_rate": 8.172209496299446e-06,
+      "loss": 0.5555,
+      "step": 522
+    },
+    {
+      "epoch": 0.9559136515658255,
+      "grad_norm": 0.6637577414512634,
+      "learning_rate": 8.156627411851295e-06,
+      "loss": 0.5902,
+      "step": 524
+    },
+    {
+      "epoch": 0.9595621769534813,
+      "grad_norm": 0.7317308187484741,
+      "learning_rate": 8.140994185525622e-06,
+      "loss": 0.5737,
+      "step": 526
+    },
+    {
+      "epoch": 0.9632107023411371,
+      "grad_norm": 0.6722338199615479,
+      "learning_rate": 8.125310070603048e-06,
+      "loss": 0.5649,
+      "step": 528
+    },
+    {
+      "epoch": 0.966859227728793,
+      "grad_norm": 0.6682706475257874,
+      "learning_rate": 8.109575321188657e-06,
+      "loss": 0.5534,
+      "step": 530
+    },
+    {
+      "epoch": 0.9705077531164488,
+      "grad_norm": 0.6923969984054565,
+      "learning_rate": 8.093790192207893e-06,
+      "loss": 0.5639,
+      "step": 532
+    },
+    {
+      "epoch": 0.9741562785041046,
+      "grad_norm": 0.707283079624176,
+      "learning_rate": 8.07795493940241e-06,
+      "loss": 0.5886,
+      "step": 534
+    },
+    {
+      "epoch": 0.9778048038917604,
+      "grad_norm": 0.6633589863777161,
+      "learning_rate": 8.062069819325948e-06,
+      "loss": 0.5547,
+      "step": 536
+    },
+    {
+      "epoch": 0.9814533292794162,
+      "grad_norm": 0.575999915599823,
+      "learning_rate": 8.046135089340165e-06,
+      "loss": 0.5494,
+      "step": 538
+    },
+    {
+      "epoch": 0.985101854667072,
+      "grad_norm": 0.6812056303024292,
+      "learning_rate": 8.03015100761047e-06,
+      "loss": 0.569,
+      "step": 540
+    },
+    {
+      "epoch": 0.9887503800547279,
+      "grad_norm": 0.663683295249939,
+      "learning_rate": 8.014117833101844e-06,
+      "loss": 0.5863,
+      "step": 542
+    },
+    {
+      "epoch": 0.9923989054423837,
+      "grad_norm": 0.6432536840438843,
+      "learning_rate": 7.998035825574634e-06,
+      "loss": 0.5641,
+      "step": 544
+    },
+    {
+      "epoch": 0.9960474308300395,
+      "grad_norm": 0.6330881714820862,
+      "learning_rate": 7.981905245580363e-06,
+      "loss": 0.569,
+      "step": 546
+    },
+    {
+      "epoch": 0.9996959562176954,
+      "grad_norm": 0.6574995517730713,
+      "learning_rate": 7.965726354457486e-06,
+      "loss": 0.5461,
+      "step": 548
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1644,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.853012348182462e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0afac4cbcc66936217fc932e152fccbb59574ebce2450d3f3bb42a245f3c82
+size 7992

irish_deepseek_llama31_8b_translated_bespoke_stratos_17k_with_cot/checkpoint-548/zero_to_fp32.py

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