Upload 11 files

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML",
+  "activation": "silu",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11520,
+  "max_position_embeddings": 8192,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766373d6bbb28856e9584fab43ea667380df7e7af960e8ad13a6e162f7ece8f4
+size 4922190736

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d75b7fb53687c54c7013395faff583fbc3cbca948796c5fa169d5b7430049ed
+size 4993562512

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9801bab99c848e1cb8ac7db1bb56a8123d0bee64381131752f0fffcc83367b2
+size 4915951392

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3c4ae429b3566d27a318555e73c964bf8c563995aefa6a03825fc56f369a17
+size 1996548832

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 16828211200
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1749 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9878691983122363,
+  "eval_steps": 30,
+  "global_step": 236,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008447729672650475,
+      "grad_norm": 12.0625,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 1.4041,
+      "step": 1
+    },
+    {
+      "epoch": 0.008447729672650475,
+      "eval_loss": 1.5854278802871704,
+      "eval_runtime": 142.1442,
+      "eval_samples_per_second": 8.273,
+      "eval_steps_per_second": 4.137,
+      "step": 1
+    },
+    {
+      "epoch": 0.01689545934530095,
+      "grad_norm": 11.875,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.4201,
+      "step": 2
+    },
+    {
+      "epoch": 0.025343189017951427,
+      "grad_norm": 11.8125,
+      "learning_rate": 1.3043478260869566e-06,
+      "loss": 1.3999,
+      "step": 3
+    },
+    {
+      "epoch": 0.0337909186906019,
+      "grad_norm": 11.375,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 1.3856,
+      "step": 4
+    },
+    {
+      "epoch": 0.042238648363252376,
+      "grad_norm": 11.0,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 1.3965,
+      "step": 5
+    },
+    {
+      "epoch": 0.050686378035902854,
+      "grad_norm": 11.5,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 1.4083,
+      "step": 6
+    },
+    {
+      "epoch": 0.059134107708553325,
+      "grad_norm": 10.75,
+      "learning_rate": 3.043478260869566e-06,
+      "loss": 1.3994,
+      "step": 7
+    },
+    {
+      "epoch": 0.0675818373812038,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 1.3706,
+      "step": 8
+    },
+    {
+      "epoch": 0.07602956705385427,
+      "grad_norm": 8.5625,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 1.341,
+      "step": 9
+    },
+    {
+      "epoch": 0.08447729672650475,
+      "grad_norm": 7.625,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 1.3271,
+      "step": 10
+    },
+    {
+      "epoch": 0.09292502639915523,
+      "grad_norm": 6.03125,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 1.2922,
+      "step": 11
+    },
+    {
+      "epoch": 0.10137275607180571,
+      "grad_norm": 5.3125,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 1.2625,
+      "step": 12
+    },
+    {
+      "epoch": 0.10982048574445617,
+      "grad_norm": 4.625,
+      "learning_rate": 5.652173913043479e-06,
+      "loss": 1.215,
+      "step": 13
+    },
+    {
+      "epoch": 0.11826821541710665,
+      "grad_norm": 4.1875,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 1.1877,
+      "step": 14
+    },
+    {
+      "epoch": 0.12671594508975711,
+      "grad_norm": 4.21875,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 1.2066,
+      "step": 15
+    },
+    {
+      "epoch": 0.1351636747624076,
+      "grad_norm": 3.984375,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 1.1631,
+      "step": 16
+    },
+    {
+      "epoch": 0.14361140443505807,
+      "grad_norm": 3.796875,
+      "learning_rate": 7.391304347826087e-06,
+      "loss": 1.1573,
+      "step": 17
+    },
+    {
+      "epoch": 0.15205913410770855,
+      "grad_norm": 3.96875,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 1.1425,
+      "step": 18
+    },
+    {
+      "epoch": 0.16050686378035903,
+      "grad_norm": 3.390625,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 1.118,
+      "step": 19
+    },
+    {
+      "epoch": 0.1689545934530095,
+      "grad_norm": 5.0625,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 1.1083,
+      "step": 20
+    },
+    {
+      "epoch": 0.17740232312565998,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 1.1026,
+      "step": 21
+    },
+    {
+      "epoch": 0.18585005279831046,
+      "grad_norm": 4.28125,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 1.106,
+      "step": 22
+    },
+    {
+      "epoch": 0.19429778247096094,
+      "grad_norm": 2.71875,
+      "learning_rate": 1e-05,
+      "loss": 1.0824,
+      "step": 23
+    },
+    {
+      "epoch": 0.20274551214361142,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.999456158087994e-06,
+      "loss": 1.0823,
+      "step": 24
+    },
+    {
+      "epoch": 0.21119324181626187,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.997824750657586e-06,
+      "loss": 1.0782,
+      "step": 25
+    },
+    {
+      "epoch": 0.21964097148891235,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.995106132599869e-06,
+      "loss": 1.0511,
+      "step": 26
+    },
+    {
+      "epoch": 0.22808870116156282,
+      "grad_norm": 2.03125,
+      "learning_rate": 9.99130089531422e-06,
+      "loss": 1.0665,
+      "step": 27
+    },
+    {
+      "epoch": 0.2365364308342133,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.98640986657965e-06,
+      "loss": 1.0453,
+      "step": 28
+    },
+    {
+      "epoch": 0.24498416050686378,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.980434110374725e-06,
+      "loss": 1.0415,
+      "step": 29
+    },
+    {
+      "epoch": 0.25343189017951423,
+      "grad_norm": 2.265625,
+      "learning_rate": 9.973374926646117e-06,
+      "loss": 1.0445,
+      "step": 30
+    },
+    {
+      "epoch": 0.25343189017951423,
+      "eval_loss": 1.1312532424926758,
+      "eval_runtime": 142.3016,
+      "eval_samples_per_second": 8.264,
+      "eval_steps_per_second": 4.132,
+      "step": 30
+    },
+    {
+      "epoch": 0.26187961985216474,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.965233851025816e-06,
+      "loss": 1.0201,
+      "step": 31
+    },
+    {
+      "epoch": 0.2703273495248152,
+      "grad_norm": 0.94140625,
+      "learning_rate": 9.956012654497073e-06,
+      "loss": 1.0249,
+      "step": 32
+    },
+    {
+      "epoch": 0.2787750791974657,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.945713343009154e-06,
+      "loss": 1.0274,
+      "step": 33
+    },
+    {
+      "epoch": 0.28722280887011614,
+      "grad_norm": 0.984375,
+      "learning_rate": 9.934338157040953e-06,
+      "loss": 1.0145,
+      "step": 34
+    },
+    {
+      "epoch": 0.29567053854276665,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.921889571113629e-06,
+      "loss": 0.9935,
+      "step": 35
+    },
+    {
+      "epoch": 0.3041182682154171,
+      "grad_norm": 1.171875,
+      "learning_rate": 9.90837029325229e-06,
+      "loss": 0.982,
+      "step": 36
+    },
+    {
+      "epoch": 0.3125659978880676,
+      "grad_norm": 3.328125,
+      "learning_rate": 9.893783264396903e-06,
+      "loss": 1.0048,
+      "step": 37
+    },
+    {
+      "epoch": 0.32101372756071805,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.878131657762535e-06,
+      "loss": 1.0004,
+      "step": 38
+    },
+    {
+      "epoch": 0.32946145723336856,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.861418878149056e-06,
+      "loss": 1.0112,
+      "step": 39
+    },
+    {
+      "epoch": 0.337909186906019,
+      "grad_norm": 1.25,
+      "learning_rate": 9.843648561200476e-06,
+      "loss": 1.0133,
+      "step": 40
+    },
+    {
+      "epoch": 0.34635691657866946,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.82482457261405e-06,
+      "loss": 0.9826,
+      "step": 41
+    },
+    {
+      "epoch": 0.35480464625131997,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.80495100729936e-06,
+      "loss": 0.9907,
+      "step": 42
+    },
+    {
+      "epoch": 0.3632523759239704,
+      "grad_norm": 0.9140625,
+      "learning_rate": 9.784032188487507e-06,
+      "loss": 0.9871,
+      "step": 43
+    },
+    {
+      "epoch": 0.3717001055966209,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.762072666790658e-06,
+      "loss": 0.9809,
+      "step": 44
+    },
+    {
+      "epoch": 0.3801478352692714,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.73907721921212e-06,
+      "loss": 0.9862,
+      "step": 45
+    },
+    {
+      "epoch": 0.3885955649419219,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.715050848107167e-06,
+      "loss": 0.9739,
+      "step": 46
+    },
+    {
+      "epoch": 0.39704329461457233,
+      "grad_norm": 0.8828125,
+      "learning_rate": 9.689998780094839e-06,
+      "loss": 0.9704,
+      "step": 47
+    },
+    {
+      "epoch": 0.40549102428722283,
+      "grad_norm": 0.859375,
+      "learning_rate": 9.663926464920959e-06,
+      "loss": 0.9508,
+      "step": 48
+    },
+    {
+      "epoch": 0.4139387539598733,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.636839574272623e-06,
+      "loss": 0.9603,
+      "step": 49
+    },
+    {
+      "epoch": 0.42238648363252373,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.608744000544392e-06,
+      "loss": 0.9525,
+      "step": 50
+    },
+    {
+      "epoch": 0.43083421330517424,
+      "grad_norm": 1.25,
+      "learning_rate": 9.579645855556481e-06,
+      "loss": 0.984,
+      "step": 51
+    },
+    {
+      "epoch": 0.4392819429778247,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.54955146922521e-06,
+      "loss": 0.9727,
+      "step": 52
+    },
+    {
+      "epoch": 0.4477296726504752,
+      "grad_norm": 1.125,
+      "learning_rate": 9.51846738818602e-06,
+      "loss": 0.9785,
+      "step": 53
+    },
+    {
+      "epoch": 0.45617740232312565,
+      "grad_norm": 0.98828125,
+      "learning_rate": 9.48640037436934e-06,
+      "loss": 0.9683,
+      "step": 54
+    },
+    {
+      "epoch": 0.46462513199577615,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.453357403529609e-06,
+      "loss": 0.9551,
+      "step": 55
+    },
+    {
+      "epoch": 0.4730728616684266,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.419345663727805e-06,
+      "loss": 0.9722,
+      "step": 56
+    },
+    {
+      "epoch": 0.4815205913410771,
+      "grad_norm": 1.3359375,
+      "learning_rate": 9.38437255376777e-06,
+      "loss": 0.9641,
+      "step": 57
+    },
+    {
+      "epoch": 0.48996832101372756,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.348445681586703e-06,
+      "loss": 0.9395,
+      "step": 58
+    },
+    {
+      "epoch": 0.498416050686378,
+      "grad_norm": 0.84765625,
+      "learning_rate": 9.31157286260014e-06,
+      "loss": 0.953,
+      "step": 59
+    },
+    {
+      "epoch": 0.5068637803590285,
+      "grad_norm": 2.84375,
+      "learning_rate": 9.273762118001837e-06,
+      "loss": 0.9479,
+      "step": 60
+    },
+    {
+      "epoch": 0.5068637803590285,
+      "eval_loss": 1.0488032102584839,
+      "eval_runtime": 142.7281,
+      "eval_samples_per_second": 8.239,
+      "eval_steps_per_second": 4.12,
+      "step": 60
+    },
+    {
+      "epoch": 0.515311510031679,
+      "grad_norm": 0.87890625,
+      "learning_rate": 9.235021673018849e-06,
+      "loss": 0.9366,
+      "step": 61
+    },
+    {
+      "epoch": 0.5237592397043295,
+      "grad_norm": 0.84375,
+      "learning_rate": 9.195359955122244e-06,
+      "loss": 0.9726,
+      "step": 62
+    },
+    {
+      "epoch": 0.53220696937698,
+      "grad_norm": 0.8984375,
+      "learning_rate": 9.15478559219382e-06,
+      "loss": 0.9478,
+      "step": 63
+    },
+    {
+      "epoch": 0.5406546990496304,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.113307410649222e-06,
+      "loss": 0.9812,
+      "step": 64
+    },
+    {
+      "epoch": 0.5491024287222809,
+      "grad_norm": 1.8671875,
+      "learning_rate": 9.070934433517872e-06,
+      "loss": 0.9506,
+      "step": 65
+    },
+    {
+      "epoch": 0.5575501583949314,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.027675878480131e-06,
+      "loss": 0.9582,
+      "step": 66
+    },
+    {
+      "epoch": 0.5659978880675819,
+      "grad_norm": 0.8203125,
+      "learning_rate": 8.983541155862114e-06,
+      "loss": 0.9444,
+      "step": 67
+    },
+    {
+      "epoch": 0.5744456177402323,
+      "grad_norm": 0.90234375,
+      "learning_rate": 8.938539866588593e-06,
+      "loss": 0.9455,
+      "step": 68
+    },
+    {
+      "epoch": 0.5828933474128828,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.892681800094447e-06,
+      "loss": 0.9613,
+      "step": 69
+    },
+    {
+      "epoch": 0.5913410770855333,
+      "grad_norm": 0.796875,
+      "learning_rate": 8.845976932195104e-06,
+      "loss": 0.9584,
+      "step": 70
+    },
+    {
+      "epoch": 0.5997888067581837,
+      "grad_norm": 1.0859375,
+      "learning_rate": 8.798435422916425e-06,
+      "loss": 0.9418,
+      "step": 71
+    },
+    {
+      "epoch": 0.6082365364308342,
+      "grad_norm": 1.328125,
+      "learning_rate": 8.750067614284534e-06,
+      "loss": 0.9655,
+      "step": 72
+    },
+    {
+      "epoch": 0.6166842661034847,
+      "grad_norm": 1.7109375,
+      "learning_rate": 8.700884028076042e-06,
+      "loss": 0.9684,
+      "step": 73
+    },
+    {
+      "epoch": 0.6251319957761352,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.650895363529172e-06,
+      "loss": 0.9617,
+      "step": 74
+    },
+    {
+      "epoch": 0.6335797254487856,
+      "grad_norm": 1.7578125,
+      "learning_rate": 8.600112495016289e-06,
+      "loss": 0.9341,
+      "step": 75
+    },
+    {
+      "epoch": 0.6420274551214361,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.548546469678311e-06,
+      "loss": 0.9542,
+      "step": 76
+    },
+    {
+      "epoch": 0.6504751847940866,
+      "grad_norm": 4.28125,
+      "learning_rate": 8.496208505021572e-06,
+      "loss": 0.982,
+      "step": 77
+    },
+    {
+      "epoch": 0.6589229144667371,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.443109986477574e-06,
+      "loss": 0.9432,
+      "step": 78
+    },
+    {
+      "epoch": 0.6673706441393875,
+      "grad_norm": 1.265625,
+      "learning_rate": 8.389262464926256e-06,
+      "loss": 0.9329,
+      "step": 79
+    },
+    {
+      "epoch": 0.675818373812038,
+      "grad_norm": 2.5,
+      "learning_rate": 8.334677654183254e-06,
+      "loss": 0.9208,
+      "step": 80
+    },
+    {
+      "epoch": 0.6842661034846885,
+      "grad_norm": 1.1484375,
+      "learning_rate": 8.279367428451703e-06,
+      "loss": 0.9526,
+      "step": 81
+    },
+    {
+      "epoch": 0.6927138331573389,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.223343819739164e-06,
+      "loss": 0.9455,
+      "step": 82
+    },
+    {
+      "epoch": 0.7011615628299894,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.166619015240236e-06,
+      "loss": 0.9448,
+      "step": 83
+    },
+    {
+      "epoch": 0.7096092925026399,
+      "grad_norm": 1.8046875,
+      "learning_rate": 8.109205354685367e-06,
+      "loss": 0.9445,
+      "step": 84
+    },
+    {
+      "epoch": 0.7180570221752904,
+      "grad_norm": 1.8125,
+      "learning_rate": 8.051115327656538e-06,
+      "loss": 0.9399,
+      "step": 85
+    },
+    {
+      "epoch": 0.7265047518479408,
+      "grad_norm": 1.640625,
+      "learning_rate": 7.992361570870289e-06,
+      "loss": 0.9302,
+      "step": 86
+    },
+    {
+      "epoch": 0.7349524815205913,
+      "grad_norm": 0.83203125,
+      "learning_rate": 7.932956865428792e-06,
+      "loss": 0.9388,
+      "step": 87
+    },
+    {
+      "epoch": 0.7434002111932418,
+      "grad_norm": 3.375,
+      "learning_rate": 7.872914134039485e-06,
+      "loss": 0.9298,
+      "step": 88
+    },
+    {
+      "epoch": 0.7518479408658922,
+      "grad_norm": 2.703125,
+      "learning_rate": 7.812246438203905e-06,
+      "loss": 0.9471,
+      "step": 89
+    },
+    {
+      "epoch": 0.7602956705385427,
+      "grad_norm": 3.0,
+      "learning_rate": 7.750966975376328e-06,
+      "loss": 0.9697,
+      "step": 90
+    },
+    {
+      "epoch": 0.7602956705385427,
+      "eval_loss": 1.028804063796997,
+      "eval_runtime": 142.7249,
+      "eval_samples_per_second": 8.24,
+      "eval_steps_per_second": 4.12,
+      "step": 90
+    },
+    {
+      "epoch": 0.7687434002111933,
+      "grad_norm": 1.546875,
+      "learning_rate": 7.689089076092851e-06,
+      "loss": 0.9306,
+      "step": 91
+    },
+    {
+      "epoch": 0.7771911298838438,
+      "grad_norm": 1.09375,
+      "learning_rate": 7.626626201071494e-06,
+      "loss": 0.9473,
+      "step": 92
+    },
+    {
+      "epoch": 0.7856388595564942,
+      "grad_norm": 1.5,
+      "learning_rate": 7.563591938284012e-06,
+      "loss": 0.9601,
+      "step": 93
+    },
+    {
+      "epoch": 0.7940865892291447,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.9532,
+      "step": 94
+    },
+    {
+      "epoch": 0.8025343189017952,
+      "grad_norm": 1.1484375,
+      "learning_rate": 7.4358642198039835e-06,
+      "loss": 0.9402,
+      "step": 95
+    },
+    {
+      "epoch": 0.8109820485744457,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.371198549586091e-06,
+      "loss": 0.9503,
+      "step": 96
+    },
+    {
+      "epoch": 0.8194297782470961,
+      "grad_norm": 1.5625,
+      "learning_rate": 7.306017056507018e-06,
+      "loss": 0.9521,
+      "step": 97
+    },
+    {
+      "epoch": 0.8278775079197466,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.240333919937893e-06,
+      "loss": 0.9512,
+      "step": 98
+    },
+    {
+      "epoch": 0.8363252375923971,
+      "grad_norm": 1.421875,
+      "learning_rate": 7.174163428375748e-06,
+      "loss": 0.9363,
+      "step": 99
+    },
+    {
+      "epoch": 0.8447729672650475,
+      "grad_norm": 2.453125,
+      "learning_rate": 7.107519976335241e-06,
+      "loss": 0.9602,
+      "step": 100
+    },
+    {
+      "epoch": 0.853220696937698,
+      "grad_norm": 1.3125,
+      "learning_rate": 7.040418061217325e-06,
+      "loss": 0.9253,
+      "step": 101
+    },
+    {
+      "epoch": 0.8616684266103485,
+      "grad_norm": 1.984375,
+      "learning_rate": 6.972872280155528e-06,
+      "loss": 0.9227,
+      "step": 102
+    },
+    {
+      "epoch": 0.870116156282999,
+      "grad_norm": 1.9765625,
+      "learning_rate": 6.9048973268405375e-06,
+      "loss": 0.935,
+      "step": 103
+    },
+    {
+      "epoch": 0.8785638859556494,
+      "grad_norm": 1.2578125,
+      "learning_rate": 6.836507988323785e-06,
+      "loss": 0.9207,
+      "step": 104
+    },
+    {
+      "epoch": 0.8870116156282999,
+      "grad_norm": 3.5,
+      "learning_rate": 6.767719141800718e-06,
+      "loss": 0.9622,
+      "step": 105
+    },
+    {
+      "epoch": 0.8954593453009504,
+      "grad_norm": 0.9609375,
+      "learning_rate": 6.698545751374465e-06,
+      "loss": 0.9386,
+      "step": 106
+    },
+    {
+      "epoch": 0.9039070749736009,
+      "grad_norm": 0.875,
+      "learning_rate": 6.629002864800589e-06,
+      "loss": 0.9356,
+      "step": 107
+    },
+    {
+      "epoch": 0.9123548046462513,
+      "grad_norm": 0.9921875,
+      "learning_rate": 6.55910561021365e-06,
+      "loss": 0.9412,
+      "step": 108
+    },
+    {
+      "epoch": 0.9208025343189018,
+      "grad_norm": 1.171875,
+      "learning_rate": 6.488869192836279e-06,
+      "loss": 0.9422,
+      "step": 109
+    },
+    {
+      "epoch": 0.9292502639915523,
+      "grad_norm": 1.2265625,
+      "learning_rate": 6.418308891671484e-06,
+      "loss": 0.9244,
+      "step": 110
+    },
+    {
+      "epoch": 0.9376979936642027,
+      "grad_norm": 1.375,
+      "learning_rate": 6.347440056178904e-06,
+      "loss": 0.9541,
+      "step": 111
+    },
+    {
+      "epoch": 0.9461457233368532,
+      "grad_norm": 0.83203125,
+      "learning_rate": 6.27627810293574e-06,
+      "loss": 0.9455,
+      "step": 112
+    },
+    {
+      "epoch": 0.9545934530095037,
+      "grad_norm": 1.5546875,
+      "learning_rate": 6.204838512283073e-06,
+      "loss": 0.9408,
+      "step": 113
+    },
+    {
+      "epoch": 0.9630411826821542,
+      "grad_norm": 0.875,
+      "learning_rate": 6.133136824958334e-06,
+      "loss": 0.9358,
+      "step": 114
+    },
+    {
+      "epoch": 0.9714889123548046,
+      "grad_norm": 1.2109375,
+      "learning_rate": 6.061188638714616e-06,
+      "loss": 0.9362,
+      "step": 115
+    },
+    {
+      "epoch": 0.9799366420274551,
+      "grad_norm": 1.9453125,
+      "learning_rate": 5.989009604927587e-06,
+      "loss": 0.9186,
+      "step": 116
+    },
+    {
+      "epoch": 0.9883843717001056,
+      "grad_norm": 2.03125,
+      "learning_rate": 5.916615425190744e-06,
+      "loss": 0.9247,
+      "step": 117
+    },
+    {
+      "epoch": 0.996832101372756,
+      "grad_norm": 1.6640625,
+      "learning_rate": 5.844021847899735e-06,
+      "loss": 0.9272,
+      "step": 118
+    },
+    {
+      "epoch": 1.0005274261603376,
+      "grad_norm": 1.25,
+      "learning_rate": 5.771244664826512e-06,
+      "loss": 0.9336,
+      "step": 119
+    },
+    {
+      "epoch": 1.0089662447257384,
+      "grad_norm": 1.140625,
+      "learning_rate": 5.698299707684031e-06,
+      "loss": 0.9126,
+      "step": 120
+    },
+    {
+      "epoch": 1.0089662447257384,
+      "eval_loss": 1.01927649974823,
+      "eval_runtime": 142.6079,
+      "eval_samples_per_second": 8.246,
+      "eval_steps_per_second": 4.123,
+      "step": 120
+    },
+    {
+      "epoch": 1.0174050632911393,
+      "grad_norm": 1.0546875,
+      "learning_rate": 5.6252028446822805e-06,
+      "loss": 0.9456,
+      "step": 121
+    },
+    {
+      "epoch": 1.02584388185654,
+      "grad_norm": 1.3984375,
+      "learning_rate": 5.55196997707635e-06,
+      "loss": 0.8995,
+      "step": 122
+    },
+    {
+      "epoch": 1.034282700421941,
+      "grad_norm": 1.7578125,
+      "learning_rate": 5.478617035707337e-06,
+      "loss": 0.9174,
+      "step": 123
+    },
+    {
+      "epoch": 1.0427215189873418,
+      "grad_norm": 3.015625,
+      "learning_rate": 5.4051599775368e-06,
+      "loss": 0.9243,
+      "step": 124
+    },
+    {
+      "epoch": 1.0511603375527425,
+      "grad_norm": 5.0,
+      "learning_rate": 5.33161478217552e-06,
+      "loss": 0.9076,
+      "step": 125
+    },
+    {
+      "epoch": 1.0595991561181435,
+      "grad_norm": 1.375,
+      "learning_rate": 5.257997448407366e-06,
+      "loss": 0.9037,
+      "step": 126
+    },
+    {
+      "epoch": 1.0680379746835442,
+      "grad_norm": 1.1015625,
+      "learning_rate": 5.184323990708959e-06,
+      "loss": 0.9205,
+      "step": 127
+    },
+    {
+      "epoch": 1.0764767932489452,
+      "grad_norm": 0.796875,
+      "learning_rate": 5.110610435765935e-06,
+      "loss": 0.9253,
+      "step": 128
+    },
+    {
+      "epoch": 1.084915611814346,
+      "grad_norm": 0.8828125,
+      "learning_rate": 5.0368728189865624e-06,
+      "loss": 0.8919,
+      "step": 129
+    },
+    {
+      "epoch": 1.0933544303797469,
+      "grad_norm": 1.0,
+      "learning_rate": 4.9631271810134375e-06,
+      "loss": 0.9086,
+      "step": 130
+    },
+    {
+      "epoch": 1.1017932489451476,
+      "grad_norm": 0.91015625,
+      "learning_rate": 4.8893895642340665e-06,
+      "loss": 0.919,
+      "step": 131
+    },
+    {
+      "epoch": 1.1102320675105486,
+      "grad_norm": 1.296875,
+      "learning_rate": 4.815676009291044e-06,
+      "loss": 0.8987,
+      "step": 132
+    },
+    {
+      "epoch": 1.1186708860759493,
+      "grad_norm": 1.5234375,
+      "learning_rate": 4.742002551592635e-06,
+      "loss": 0.8944,
+      "step": 133
+    },
+    {
+      "epoch": 1.1271097046413503,
+      "grad_norm": 1.15625,
+      "learning_rate": 4.668385217824482e-06,
+      "loss": 0.8949,
+      "step": 134
+    },
+    {
+      "epoch": 1.135548523206751,
+      "grad_norm": 1.125,
+      "learning_rate": 4.594840022463201e-06,
+      "loss": 0.9191,
+      "step": 135
+    },
+    {
+      "epoch": 1.143987341772152,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.5213829642926635e-06,
+      "loss": 0.9198,
+      "step": 136
+    },
+    {
+      "epoch": 1.1524261603375527,
+      "grad_norm": 1.71875,
+      "learning_rate": 4.4480300229236525e-06,
+      "loss": 0.913,
+      "step": 137
+    },
+    {
+      "epoch": 1.1608649789029535,
+      "grad_norm": 0.83984375,
+      "learning_rate": 4.374797155317721e-06,
+      "loss": 0.901,
+      "step": 138
+    },
+    {
+      "epoch": 1.1693037974683544,
+      "grad_norm": 1.1328125,
+      "learning_rate": 4.30170029231597e-06,
+      "loss": 0.9069,
+      "step": 139
+    },
+    {
+      "epoch": 1.1777426160337552,
+      "grad_norm": 3.28125,
+      "learning_rate": 4.228755335173488e-06,
+      "loss": 0.9043,
+      "step": 140
+    },
+    {
+      "epoch": 1.1861814345991561,
+      "grad_norm": 1.8671875,
+      "learning_rate": 4.155978152100266e-06,
+      "loss": 0.9341,
+      "step": 141
+    },
+    {
+      "epoch": 1.1946202531645569,
+      "grad_norm": 1.890625,
+      "learning_rate": 4.0833845748092586e-06,
+      "loss": 0.9226,
+      "step": 142
+    },
+    {
+      "epoch": 1.2030590717299579,
+      "grad_norm": 2.28125,
+      "learning_rate": 4.010990395072414e-06,
+      "loss": 0.8963,
+      "step": 143
+    },
+    {
+      "epoch": 1.2114978902953586,
+      "grad_norm": 0.79296875,
+      "learning_rate": 3.938811361285386e-06,
+      "loss": 0.9268,
+      "step": 144
+    },
+    {
+      "epoch": 1.2199367088607596,
+      "grad_norm": 1.1328125,
+      "learning_rate": 3.866863175041666e-06,
+      "loss": 0.9315,
+      "step": 145
+    },
+    {
+      "epoch": 1.2283755274261603,
+      "grad_norm": 1.4453125,
+      "learning_rate": 3.7951614877169285e-06,
+      "loss": 0.9213,
+      "step": 146
+    },
+    {
+      "epoch": 1.2368143459915613,
+      "grad_norm": 1.5859375,
+      "learning_rate": 3.7237218970642624e-06,
+      "loss": 0.9374,
+      "step": 147
+    },
+    {
+      "epoch": 1.245253164556962,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.6525599438210956e-06,
+      "loss": 0.9161,
+      "step": 148
+    },
+    {
+      "epoch": 1.253691983122363,
+      "grad_norm": 1.3203125,
+      "learning_rate": 3.5816911083285165e-06,
+      "loss": 0.9227,
+      "step": 149
+    },
+    {
+      "epoch": 1.2621308016877637,
+      "grad_norm": 0.83984375,
+      "learning_rate": 3.511130807163724e-06,
+      "loss": 0.9006,
+      "step": 150
+    },
+    {
+      "epoch": 1.2621308016877637,
+      "eval_loss": 1.0156337022781372,
+      "eval_runtime": 142.5229,
+      "eval_samples_per_second": 8.251,
+      "eval_steps_per_second": 4.126,
+      "step": 150
+    },
+    {
+      "epoch": 1.2705696202531644,
+      "grad_norm": 1.859375,
+      "learning_rate": 3.440894389786352e-06,
+      "loss": 0.9186,
+      "step": 151
+    },
+    {
+      "epoch": 1.2790084388185654,
+      "grad_norm": 0.80078125,
+      "learning_rate": 3.370997135199413e-06,
+      "loss": 0.9189,
+      "step": 152
+    },
+    {
+      "epoch": 1.2874472573839664,
+      "grad_norm": 0.828125,
+      "learning_rate": 3.3014542486255365e-06,
+      "loss": 0.9234,
+      "step": 153
+    },
+    {
+      "epoch": 1.2958860759493671,
+      "grad_norm": 1.0546875,
+      "learning_rate": 3.2322808581992825e-06,
+      "loss": 0.9301,
+      "step": 154
+    },
+    {
+      "epoch": 1.3043248945147679,
+      "grad_norm": 1.265625,
+      "learning_rate": 3.1634920116762175e-06,
+      "loss": 0.8999,
+      "step": 155
+    },
+    {
+      "epoch": 1.3127637130801688,
+      "grad_norm": 1.1796875,
+      "learning_rate": 3.0951026731594634e-06,
+      "loss": 0.9196,
+      "step": 156
+    },
+    {
+      "epoch": 1.3212025316455696,
+      "grad_norm": 1.3046875,
+      "learning_rate": 3.0271277198444737e-06,
+      "loss": 0.9,
+      "step": 157
+    },
+    {
+      "epoch": 1.3296413502109705,
+      "grad_norm": 2.703125,
+      "learning_rate": 2.9595819387826753e-06,
+      "loss": 0.9072,
+      "step": 158
+    },
+    {
+      "epoch": 1.3380801687763713,
+      "grad_norm": 1.6015625,
+      "learning_rate": 2.89248002366476e-06,
+      "loss": 0.9319,
+      "step": 159
+    },
+    {
+      "epoch": 1.3465189873417722,
+      "grad_norm": 0.94140625,
+      "learning_rate": 2.8258365716242543e-06,
+      "loss": 0.9182,
+      "step": 160
+    },
+    {
+      "epoch": 1.354957805907173,
+      "grad_norm": 12.0625,
+      "learning_rate": 2.7596660800621076e-06,
+      "loss": 0.926,
+      "step": 161
+    },
+    {
+      "epoch": 1.363396624472574,
+      "grad_norm": 2.078125,
+      "learning_rate": 2.6939829434929834e-06,
+      "loss": 0.907,
+      "step": 162
+    },
+    {
+      "epoch": 1.3718354430379747,
+      "grad_norm": 1.109375,
+      "learning_rate": 2.6288014504139104e-06,
+      "loss": 0.9023,
+      "step": 163
+    },
+    {
+      "epoch": 1.3802742616033754,
+      "grad_norm": 1.78125,
+      "learning_rate": 2.5641357801960186e-06,
+      "loss": 0.9076,
+      "step": 164
+    },
+    {
+      "epoch": 1.3887130801687764,
+      "grad_norm": 1.296875,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.9169,
+      "step": 165
+    },
+    {
+      "epoch": 1.3971518987341773,
+      "grad_norm": 1.0703125,
+      "learning_rate": 2.4364080617159885e-06,
+      "loss": 0.909,
+      "step": 166
+    },
+    {
+      "epoch": 1.405590717299578,
+      "grad_norm": 1.015625,
+      "learning_rate": 2.373373798928507e-06,
+      "loss": 0.8992,
+      "step": 167
+    },
+    {
+      "epoch": 1.4140295358649788,
+      "grad_norm": 0.73828125,
+      "learning_rate": 2.310910923907149e-06,
+      "loss": 0.8999,
+      "step": 168
+    },
+    {
+      "epoch": 1.4224683544303798,
+      "grad_norm": 1.2578125,
+      "learning_rate": 2.249033024623672e-06,
+      "loss": 0.9233,
+      "step": 169
+    },
+    {
+      "epoch": 1.4309071729957805,
+      "grad_norm": 1.2578125,
+      "learning_rate": 2.187753561796097e-06,
+      "loss": 0.9251,
+      "step": 170
+    },
+    {
+      "epoch": 1.4393459915611815,
+      "grad_norm": 0.80859375,
+      "learning_rate": 2.127085865960516e-06,
+      "loss": 0.9033,
+      "step": 171
+    },
+    {
+      "epoch": 1.4477848101265822,
+      "grad_norm": 0.81640625,
+      "learning_rate": 2.0670431345712092e-06,
+      "loss": 0.9113,
+      "step": 172
+    },
+    {
+      "epoch": 1.4562236286919832,
+      "grad_norm": 0.93359375,
+      "learning_rate": 2.0076384291297134e-06,
+      "loss": 0.9255,
+      "step": 173
+    },
+    {
+      "epoch": 1.464662447257384,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.9488846723434646e-06,
+      "loss": 0.8948,
+      "step": 174
+    },
+    {
+      "epoch": 1.4731012658227849,
+      "grad_norm": 0.7734375,
+      "learning_rate": 1.890794645314633e-06,
+      "loss": 0.9286,
+      "step": 175
+    },
+    {
+      "epoch": 1.4815400843881856,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.8333809847597644e-06,
+      "loss": 0.9314,
+      "step": 176
+    },
+    {
+      "epoch": 1.4899789029535864,
+      "grad_norm": 1.0546875,
+      "learning_rate": 1.7766561802608374e-06,
+      "loss": 0.9154,
+      "step": 177
+    },
+    {
+      "epoch": 1.4984177215189873,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.7206325715483003e-06,
+      "loss": 0.9293,
+      "step": 178
+    },
+    {
+      "epoch": 1.5068565400843883,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.665322345816746e-06,
+      "loss": 0.9358,
+      "step": 179
+    },
+    {
+      "epoch": 1.515295358649789,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.6107375350737437e-06,
+      "loss": 0.9038,
+      "step": 180
+    },
+    {
+      "epoch": 1.515295358649789,
+      "eval_loss": 1.0140331983566284,
+      "eval_runtime": 142.6045,
+      "eval_samples_per_second": 8.247,
+      "eval_steps_per_second": 4.123,
+      "step": 180
+    },
+    {
+      "epoch": 1.5237341772151898,
+      "grad_norm": 0.796875,
+      "learning_rate": 1.556890013522428e-06,
+      "loss": 0.9108,
+      "step": 181
+    },
+    {
+      "epoch": 1.5321729957805907,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.50379149497843e-06,
+      "loss": 0.9137,
+      "step": 182
+    },
+    {
+      "epoch": 1.5406118143459917,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.4514535303216893e-06,
+      "loss": 0.9258,
+      "step": 183
+    },
+    {
+      "epoch": 1.5490506329113924,
+      "grad_norm": 0.7890625,
+      "learning_rate": 1.3998875049837141e-06,
+      "loss": 0.8968,
+      "step": 184
+    },
+    {
+      "epoch": 1.5574894514767932,
+      "grad_norm": 1.1953125,
+      "learning_rate": 1.3491046364708294e-06,
+      "loss": 0.8999,
+      "step": 185
+    },
+    {
+      "epoch": 1.5659282700421941,
+      "grad_norm": 1.1640625,
+      "learning_rate": 1.2991159719239581e-06,
+      "loss": 0.9049,
+      "step": 186
+    },
+    {
+      "epoch": 1.5743670886075949,
+      "grad_norm": 1.1328125,
+      "learning_rate": 1.249932385715467e-06,
+      "loss": 0.9268,
+      "step": 187
+    },
+    {
+      "epoch": 1.5828059071729959,
+      "grad_norm": 1.25,
+      "learning_rate": 1.2015645770835765e-06,
+      "loss": 0.9136,
+      "step": 188
+    },
+    {
+      "epoch": 1.5912447257383966,
+      "grad_norm": 0.9609375,
+      "learning_rate": 1.1540230678048969e-06,
+      "loss": 0.8777,
+      "step": 189
+    },
+    {
+      "epoch": 1.5996835443037973,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.1073181999055538e-06,
+      "loss": 0.8875,
+      "step": 190
+    },
+    {
+      "epoch": 1.6081223628691983,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.0614601334114099e-06,
+      "loss": 0.9136,
+      "step": 191
+    },
+    {
+      "epoch": 1.6165611814345993,
+      "grad_norm": 1.015625,
+      "learning_rate": 1.016458844137887e-06,
+      "loss": 0.9114,
+      "step": 192
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.83984375,
+      "learning_rate": 9.723241215198692e-07,
+      "loss": 0.9235,
+      "step": 193
+    },
+    {
+      "epoch": 1.6334388185654007,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.290655664821296e-07,
+      "loss": 0.9176,
+      "step": 194
+    },
+    {
+      "epoch": 1.6418776371308017,
+      "grad_norm": 1.765625,
+      "learning_rate": 8.866925893507805e-07,
+      "loss": 0.8998,
+      "step": 195
+    },
+    {
+      "epoch": 1.6503164556962027,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.45214407806182e-07,
+      "loss": 0.9041,
+      "step": 196
+    },
+    {
+      "epoch": 1.6587552742616034,
+      "grad_norm": 1.6796875,
+      "learning_rate": 8.046400448777575e-07,
+      "loss": 0.9111,
+      "step": 197
+    },
+    {
+      "epoch": 1.6671940928270041,
+      "grad_norm": 1.1328125,
+      "learning_rate": 7.649783269811523e-07,
+      "loss": 0.9159,
+      "step": 198
+    },
+    {
+      "epoch": 1.6756329113924051,
+      "grad_norm": 1.84375,
+      "learning_rate": 7.26237881998163e-07,
+      "loss": 0.8953,
+      "step": 199
+    },
+    {
+      "epoch": 1.6840717299578059,
+      "grad_norm": 0.98828125,
+      "learning_rate": 6.884271373998608e-07,
+      "loss": 0.9039,
+      "step": 200
+    },
+    {
+      "epoch": 1.6925105485232068,
+      "grad_norm": 1.828125,
+      "learning_rate": 6.515543184133e-07,
+      "loss": 0.9155,
+      "step": 201
+    },
+    {
+      "epoch": 1.7009493670886076,
+      "grad_norm": 0.79296875,
+      "learning_rate": 6.156274462322292e-07,
+      "loss": 0.8962,
+      "step": 202
+    },
+    {
+      "epoch": 1.7093881856540083,
+      "grad_norm": 3.140625,
+      "learning_rate": 5.806543362721945e-07,
+      "loss": 0.9149,
+      "step": 203
+    },
+    {
+      "epoch": 1.7178270042194093,
+      "grad_norm": 0.75390625,
+      "learning_rate": 5.466425964703914e-07,
+      "loss": 0.9013,
+      "step": 204
+    },
+    {
+      "epoch": 1.7262658227848102,
+      "grad_norm": 2.28125,
+      "learning_rate": 5.135996256306619e-07,
+      "loss": 0.9258,
+      "step": 205
+    },
+    {
+      "epoch": 1.734704641350211,
+      "grad_norm": 0.80078125,
+      "learning_rate": 4.815326118139813e-07,
+      "loss": 0.9308,
+      "step": 206
+    },
+    {
+      "epoch": 1.7431434599156117,
+      "grad_norm": 0.7265625,
+      "learning_rate": 4.5044853077479134e-07,
+      "loss": 0.9125,
+      "step": 207
+    },
+    {
+      "epoch": 1.7515822784810127,
+      "grad_norm": 0.8828125,
+      "learning_rate": 4.203541444435211e-07,
+      "loss": 0.8996,
+      "step": 208
+    },
+    {
+      "epoch": 1.7600210970464136,
+      "grad_norm": 0.92578125,
+      "learning_rate": 3.9125599945560866e-07,
+      "loss": 0.9171,
+      "step": 209
+    },
+    {
+      "epoch": 1.7684599156118144,
+      "grad_norm": 1.25,
+      "learning_rate": 3.631604257273774e-07,
+      "loss": 0.9095,
+      "step": 210
+    },
+    {
+      "epoch": 1.7684599156118144,
+      "eval_loss": 1.0137686729431152,
+      "eval_runtime": 142.61,
+      "eval_samples_per_second": 8.246,
+      "eval_steps_per_second": 4.123,
+      "step": 210
+    },
+    {
+      "epoch": 1.7768987341772151,
+      "grad_norm": 0.87890625,
+      "learning_rate": 3.360735350790428e-07,
+      "loss": 0.886,
+      "step": 211
+    },
+    {
+      "epoch": 1.785337552742616,
+      "grad_norm": 0.8046875,
+      "learning_rate": 3.100012199051627e-07,
+      "loss": 0.8977,
+      "step": 212
+    },
+    {
+      "epoch": 1.793776371308017,
+      "grad_norm": 0.89453125,
+      "learning_rate": 2.8494915189283325e-07,
+      "loss": 0.9127,
+      "step": 213
+    },
+    {
+      "epoch": 1.8022151898734178,
+      "grad_norm": 0.81640625,
+      "learning_rate": 2.6092278078788004e-07,
+      "loss": 0.9386,
+      "step": 214
+    },
+    {
+      "epoch": 1.8106540084388185,
+      "grad_norm": 0.8125,
+      "learning_rate": 2.3792733320934348e-07,
+      "loss": 0.8919,
+      "step": 215
+    },
+    {
+      "epoch": 1.8190928270042193,
+      "grad_norm": 0.84375,
+      "learning_rate": 2.1596781151249524e-07,
+      "loss": 0.9077,
+      "step": 216
+    },
+    {
+      "epoch": 1.8275316455696202,
+      "grad_norm": 0.97265625,
+      "learning_rate": 1.9504899270064105e-07,
+      "loss": 0.8998,
+      "step": 217
+    },
+    {
+      "epoch": 1.8359704641350212,
+      "grad_norm": 1.28125,
+      "learning_rate": 1.7517542738595071e-07,
+      "loss": 0.8967,
+      "step": 218
+    },
+    {
+      "epoch": 1.844409282700422,
+      "grad_norm": 1.1875,
+      "learning_rate": 1.5635143879952575e-07,
+      "loss": 0.8876,
+      "step": 219
+    },
+    {
+      "epoch": 1.8528481012658227,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.3858112185094418e-07,
+      "loss": 0.9276,
+      "step": 220
+    },
+    {
+      "epoch": 1.8612869198312236,
+      "grad_norm": 1.015625,
+      "learning_rate": 1.2186834223746612e-07,
+      "loss": 0.8981,
+      "step": 221
+    },
+    {
+      "epoch": 1.8697257383966246,
+      "grad_norm": 0.9921875,
+      "learning_rate": 1.0621673560309798e-07,
+      "loss": 0.9253,
+      "step": 222
+    },
+    {
+      "epoch": 1.8781645569620253,
+      "grad_norm": 0.8828125,
+      "learning_rate": 9.162970674771177e-08,
+      "loss": 0.9087,
+      "step": 223
+    },
+    {
+      "epoch": 1.886603375527426,
+      "grad_norm": 0.984375,
+      "learning_rate": 7.81104288863721e-08,
+      "loss": 0.8867,
+      "step": 224
+    },
+    {
+      "epoch": 1.895042194092827,
+      "grad_norm": 1.1015625,
+      "learning_rate": 6.566184295904777e-08,
+      "loss": 0.9037,
+      "step": 225
+    },
+    {
+      "epoch": 1.903481012658228,
+      "grad_norm": 0.80078125,
+      "learning_rate": 5.4286656990847897e-08,
+      "loss": 0.9141,
+      "step": 226
+    },
+    {
+      "epoch": 1.9119198312236287,
+      "grad_norm": 1.734375,
+      "learning_rate": 4.398734550292716e-08,
+      "loss": 0.9037,
+      "step": 227
+    },
+    {
+      "epoch": 1.9203586497890295,
+      "grad_norm": 1.3359375,
+      "learning_rate": 3.476614897418573e-08,
+      "loss": 0.8929,
+      "step": 228
+    },
+    {
+      "epoch": 1.9287974683544302,
+      "grad_norm": 0.88671875,
+      "learning_rate": 2.6625073353884756e-08,
+      "loss": 0.8782,
+      "step": 229
+    },
+    {
+      "epoch": 1.9372362869198312,
+      "grad_norm": 0.71484375,
+      "learning_rate": 1.9565889625275945e-08,
+      "loss": 0.8863,
+      "step": 230
+    },
+    {
+      "epoch": 1.9456751054852321,
+      "grad_norm": 0.7265625,
+      "learning_rate": 1.3590133420350315e-08,
+      "loss": 0.9191,
+      "step": 231
+    },
+    {
+      "epoch": 1.9541139240506329,
+      "grad_norm": 0.76953125,
+      "learning_rate": 8.699104685779835e-09,
+      "loss": 0.914,
+      "step": 232
+    },
+    {
+      "epoch": 1.9625527426160336,
+      "grad_norm": 0.74609375,
+      "learning_rate": 4.89386740013198e-09,
+      "loss": 0.9168,
+      "step": 233
+    },
+    {
+      "epoch": 1.9709915611814346,
+      "grad_norm": 2.171875,
+      "learning_rate": 2.1752493424148647e-09,
+      "loss": 0.9424,
+      "step": 234
+    },
+    {
+      "epoch": 1.9794303797468356,
+      "grad_norm": 0.99609375,
+      "learning_rate": 5.438419120062933e-10,
+      "loss": 0.9252,
+      "step": 235
+    },
+    {
+      "epoch": 1.9878691983122363,
+      "grad_norm": 0.859375,
+      "learning_rate": 0.0,
+      "loss": 0.9248,
+      "step": 236
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 236,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 59,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.847994502064636e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}