Upload folder using huggingface_hub

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,9 @@
+{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>
+' + message['content'] + '
+' }}{% elif message['role'] == 'user' %}{{ '<|user|>
+' + message['content'] + '
+' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>
+'  + message['content'] + eos_token + '
+' }}{% else %}{{ '<|assistant|>
+'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>
+' }}{% endif %}{% endfor %}

checkpoint-2000/config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Olmo2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "dtype": "bfloat16",
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": false,
+  "vocab_size": 100352
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": [
+    100257
+  ],
+  "pad_token_id": 100277,
+  "transformers_version": "4.56.1"
+}

checkpoint-2000/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ae91e1171f1f1753b23df3a5a6740d89da377932b33a1661bb7485d6ec530e
+size 4970591184

checkpoint-2000/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d41b81fe0d7e4c1d673a77beded5ee77080e39d6a6940b523e82f61eaa1dcbd
+size 4981161496

checkpoint-2000/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd5726d1c66491ae9cb225292cb2937722a7fa79c13f2d8956cad96db0c1eea
+size 4645523448

checkpoint-2000/model.safetensors.index.json

@@ -0,0 +1,363 @@
+{
+  "metadata": {
+    "total_parameters": 7298617344,
+    "total_size": 14597234688
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68fe85b6befce9645f338c4470726079a4fac5173ba343a5abcf58523543952d
+size 3263319914

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b9960af9f375d6610afc4ea390ff365f3d73ca111acb951466c1057ba5ff02
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c56cc7d2ab3dfe9edf7a28cb038a85004572c59f841d9bdfd8a137d5d874b19
+size 1465

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,2914 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7798364212986146,
+  "eval_steps": 100,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.0013165885582567,
+      "epoch": 0.00890224225226729,
+      "grad_norm": 4.25,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.1036,
+      "mean_token_accuracy": 0.5934873595833778,
+      "num_tokens": 128102.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.0327254055067896,
+      "epoch": 0.01780448450453458,
+      "grad_norm": 3.75,
+      "learning_rate": 1.2666666666666669e-06,
+      "loss": 2.1318,
+      "mean_token_accuracy": 0.5815463203936815,
+      "num_tokens": 255758.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.0127216134220363,
+      "epoch": 0.026706726756801868,
+      "grad_norm": 3.4375,
+      "learning_rate": 1.9333333333333336e-06,
+      "loss": 2.0994,
+      "mean_token_accuracy": 0.5902250200510025,
+      "num_tokens": 392254.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.9930799461901187,
+      "epoch": 0.03560896900906916,
+      "grad_norm": 3.4375,
+      "learning_rate": 2.6e-06,
+      "loss": 2.0443,
+      "mean_token_accuracy": 0.5956933092325926,
+      "num_tokens": 525545.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.011460742354393,
+      "epoch": 0.04451121126133645,
+      "grad_norm": 3.59375,
+      "learning_rate": 3.266666666666667e-06,
+      "loss": 2.0996,
+      "mean_token_accuracy": 0.5882656103000045,
+      "num_tokens": 659462.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.030308809503913,
+      "epoch": 0.053413453513603736,
+      "grad_norm": 3.5,
+      "learning_rate": 3.9333333333333335e-06,
+      "loss": 2.0506,
+      "mean_token_accuracy": 0.5891991708427667,
+      "num_tokens": 797469.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.0320250753313303,
+      "epoch": 0.06231569576587103,
+      "grad_norm": 3.484375,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 2.018,
+      "mean_token_accuracy": 0.5905353711917997,
+      "num_tokens": 926574.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.0368458257988096,
+      "epoch": 0.07121793801813832,
+      "grad_norm": 3.0,
+      "learning_rate": 5.2666666666666665e-06,
+      "loss": 1.9841,
+      "mean_token_accuracy": 0.5963305428624153,
+      "num_tokens": 1056145.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.9638574384152889,
+      "epoch": 0.08012018027040561,
+      "grad_norm": 2.75,
+      "learning_rate": 5.933333333333335e-06,
+      "loss": 1.8996,
+      "mean_token_accuracy": 0.6114491229876876,
+      "num_tokens": 1195941.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.98968401607126,
+      "epoch": 0.0890224225226729,
+      "grad_norm": 2.609375,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 1.855,
+      "mean_token_accuracy": 0.6124794160947203,
+      "num_tokens": 1322822.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.0890224225226729,
+      "eval_biology_entropy": 1.7304411175251007,
+      "eval_biology_loss": 3.744920492172241,
+      "eval_biology_mean_token_accuracy": 0.3840184355974197,
+      "eval_biology_num_tokens": 1322822.0,
+      "eval_biology_runtime": 19.0021,
+      "eval_biology_samples_per_second": 26.313,
+      "eval_biology_steps_per_second": 13.156,
+      "step": 100
+    },
+    {
+      "epoch": 0.0890224225226729,
+      "eval_chemistry_entropy": 0.9838921461105347,
+      "eval_chemistry_loss": 1.8955185413360596,
+      "eval_chemistry_mean_token_accuracy": 0.6147462700605393,
+      "eval_chemistry_num_tokens": 1322822.0,
+      "eval_chemistry_runtime": 24.0155,
+      "eval_chemistry_samples_per_second": 20.82,
+      "eval_chemistry_steps_per_second": 10.41,
+      "step": 100
+    },
+    {
+      "epoch": 0.0890224225226729,
+      "eval_math_entropy": 0.754765457034111,
+      "eval_math_loss": 2.326155424118042,
+      "eval_math_mean_token_accuracy": 0.591344870209694,
+      "eval_math_num_tokens": 1322822.0,
+      "eval_math_runtime": 24.4976,
+      "eval_math_samples_per_second": 20.41,
+      "eval_math_steps_per_second": 10.205,
+      "step": 100
+    },
+    {
+      "epoch": 0.0890224225226729,
+      "eval_physics_entropy": 0.9091537948846817,
+      "eval_physics_loss": 1.9409757852554321,
+      "eval_physics_mean_token_accuracy": 0.6192746138572693,
+      "eval_physics_num_tokens": 1322822.0,
+      "eval_physics_runtime": 29.069,
+      "eval_physics_samples_per_second": 17.2,
+      "eval_physics_steps_per_second": 8.6,
+      "step": 100
+    },
+    {
+      "entropy": 1.0018818765878676,
+      "epoch": 0.09792466477494019,
+      "grad_norm": 2.359375,
+      "learning_rate": 7.266666666666668e-06,
+      "loss": 1.8412,
+      "mean_token_accuracy": 0.6112866658717394,
+      "num_tokens": 1455622.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.013153598085046,
+      "epoch": 0.10682690702720747,
+      "grad_norm": 2.078125,
+      "learning_rate": 7.933333333333334e-06,
+      "loss": 1.7484,
+      "mean_token_accuracy": 0.6222657721489668,
+      "num_tokens": 1592594.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.0879363805055617,
+      "epoch": 0.11572914927947477,
+      "grad_norm": 2.0,
+      "learning_rate": 8.6e-06,
+      "loss": 1.7365,
+      "mean_token_accuracy": 0.6194966306909919,
+      "num_tokens": 1723223.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.090317297540605,
+      "epoch": 0.12463139153174206,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.266666666666667e-06,
+      "loss": 1.5882,
+      "mean_token_accuracy": 0.6410850418731571,
+      "num_tokens": 1854187.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.1811468597501515,
+      "epoch": 0.13353363378400934,
+      "grad_norm": 1.7421875,
+      "learning_rate": 9.933333333333334e-06,
+      "loss": 1.5436,
+      "mean_token_accuracy": 0.6420513158664107,
+      "num_tokens": 1980984.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.2093722522258759,
+      "epoch": 0.14243587603627664,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.0600000000000002e-05,
+      "loss": 1.4029,
+      "mean_token_accuracy": 0.6615621751174331,
+      "num_tokens": 2114069.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.2789871104061603,
+      "epoch": 0.15133811828854393,
+      "grad_norm": 1.171875,
+      "learning_rate": 1.1266666666666668e-05,
+      "loss": 1.3526,
+      "mean_token_accuracy": 0.673838303796947,
+      "num_tokens": 2248456.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.3190820906311274,
+      "epoch": 0.16024036054081123,
+      "grad_norm": 1.1328125,
+      "learning_rate": 1.1933333333333335e-05,
+      "loss": 1.3278,
+      "mean_token_accuracy": 0.6813167624175549,
+      "num_tokens": 2384381.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.3156713977456094,
+      "epoch": 0.1691426027930785,
+      "grad_norm": 0.984375,
+      "learning_rate": 1.2600000000000001e-05,
+      "loss": 1.273,
+      "mean_token_accuracy": 0.6898887110874057,
+      "num_tokens": 2510885.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.3284545745700598,
+      "epoch": 0.1780448450453458,
+      "grad_norm": 0.9375,
+      "learning_rate": 1.3266666666666668e-05,
+      "loss": 1.2541,
+      "mean_token_accuracy": 0.6897036660462618,
+      "num_tokens": 2640613.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.1780448450453458,
+      "eval_biology_entropy": 2.3898276572227477,
+      "eval_biology_loss": 2.6390066146850586,
+      "eval_biology_mean_token_accuracy": 0.4844123523235321,
+      "eval_biology_num_tokens": 2640613.0,
+      "eval_biology_runtime": 18.9294,
+      "eval_biology_samples_per_second": 26.414,
+      "eval_biology_steps_per_second": 13.207,
+      "step": 200
+    },
+    {
+      "epoch": 0.1780448450453458,
+      "eval_chemistry_entropy": 1.2916195030212403,
+      "eval_chemistry_loss": 1.269665241241455,
+      "eval_chemistry_mean_token_accuracy": 0.6933187863826752,
+      "eval_chemistry_num_tokens": 2640613.0,
+      "eval_chemistry_runtime": 23.9969,
+      "eval_chemistry_samples_per_second": 20.836,
+      "eval_chemistry_steps_per_second": 10.418,
+      "step": 200
+    },
+    {
+      "epoch": 0.1780448450453458,
+      "eval_math_entropy": 1.0382833310365678,
+      "eval_math_loss": 1.4177786111831665,
+      "eval_math_mean_token_accuracy": 0.6727467269897461,
+      "eval_math_num_tokens": 2640613.0,
+      "eval_math_runtime": 24.4826,
+      "eval_math_samples_per_second": 20.423,
+      "eval_math_steps_per_second": 10.211,
+      "step": 200
+    },
+    {
+      "epoch": 0.1780448450453458,
+      "eval_physics_entropy": 1.2059782876968383,
+      "eval_physics_loss": 1.2801809310913086,
+      "eval_physics_mean_token_accuracy": 0.6974429616928101,
+      "eval_physics_num_tokens": 2640613.0,
+      "eval_physics_runtime": 28.6856,
+      "eval_physics_samples_per_second": 17.43,
+      "eval_physics_steps_per_second": 8.715,
+      "step": 200
+    },
+    {
+      "entropy": 1.235218785330653,
+      "epoch": 0.18694708729761308,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.3933333333333334e-05,
+      "loss": 1.1936,
+      "mean_token_accuracy": 0.7037674445658922,
+      "num_tokens": 2779589.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.2612369772046805,
+      "epoch": 0.19584932954988038,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.46e-05,
+      "loss": 1.1973,
+      "mean_token_accuracy": 0.6993423495441675,
+      "num_tokens": 2909779.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.224467835202813,
+      "epoch": 0.20475157180214767,
+      "grad_norm": 0.9609375,
+      "learning_rate": 1.5266666666666667e-05,
+      "loss": 1.1453,
+      "mean_token_accuracy": 0.710259860381484,
+      "num_tokens": 3045030.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.2651627618819474,
+      "epoch": 0.21365381405441494,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.5933333333333336e-05,
+      "loss": 1.1668,
+      "mean_token_accuracy": 0.7021638717502355,
+      "num_tokens": 3180769.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.2010735258460046,
+      "epoch": 0.22255605630668224,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.66e-05,
+      "loss": 1.1257,
+      "mean_token_accuracy": 0.7146535400301218,
+      "num_tokens": 3317450.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.2229063987731934,
+      "epoch": 0.23145829855894953,
+      "grad_norm": 0.984375,
+      "learning_rate": 1.726666666666667e-05,
+      "loss": 1.161,
+      "mean_token_accuracy": 0.7094106379896402,
+      "num_tokens": 3448841.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.1914008114486934,
+      "epoch": 0.24036054081121683,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.7933333333333333e-05,
+      "loss": 1.091,
+      "mean_token_accuracy": 0.7163884485140443,
+      "num_tokens": 3582810.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.2218066401779653,
+      "epoch": 0.24926278306348412,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.86e-05,
+      "loss": 1.1147,
+      "mean_token_accuracy": 0.7146718475967646,
+      "num_tokens": 3713242.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.2504509769380092,
+      "epoch": 0.2581650253157514,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.926666666666667e-05,
+      "loss": 1.1535,
+      "mean_token_accuracy": 0.7055120941251516,
+      "num_tokens": 3846944.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.1762213349342345,
+      "epoch": 0.2670672675680187,
+      "grad_norm": 0.9296875,
+      "learning_rate": 1.9933333333333334e-05,
+      "loss": 1.0892,
+      "mean_token_accuracy": 0.7208757739514112,
+      "num_tokens": 3984712.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.2670672675680187,
+      "eval_biology_entropy": 2.2724351935386657,
+      "eval_biology_loss": 2.3849706649780273,
+      "eval_biology_mean_token_accuracy": 0.5212258485555649,
+      "eval_biology_num_tokens": 3984712.0,
+      "eval_biology_runtime": 18.9323,
+      "eval_biology_samples_per_second": 26.41,
+      "eval_biology_steps_per_second": 13.205,
+      "step": 300
+    },
+    {
+      "epoch": 0.2670672675680187,
+      "eval_chemistry_entropy": 1.172815949201584,
+      "eval_chemistry_loss": 1.1251518726348877,
+      "eval_chemistry_mean_token_accuracy": 0.7213010289669037,
+      "eval_chemistry_num_tokens": 3984712.0,
+      "eval_chemistry_runtime": 24.0284,
+      "eval_chemistry_samples_per_second": 20.809,
+      "eval_chemistry_steps_per_second": 10.404,
+      "step": 300
+    },
+    {
+      "epoch": 0.2670672675680187,
+      "eval_math_entropy": 1.013439424276352,
+      "eval_math_loss": 1.2600808143615723,
+      "eval_math_mean_token_accuracy": 0.7004911189079285,
+      "eval_math_num_tokens": 3984712.0,
+      "eval_math_runtime": 24.488,
+      "eval_math_samples_per_second": 20.418,
+      "eval_math_steps_per_second": 10.209,
+      "step": 300
+    },
+    {
+      "epoch": 0.2670672675680187,
+      "eval_physics_entropy": 1.146550934791565,
+      "eval_physics_loss": 1.1405712366104126,
+      "eval_physics_mean_token_accuracy": 0.7223960258960724,
+      "eval_physics_num_tokens": 3984712.0,
+      "eval_physics_runtime": 28.6721,
+      "eval_physics_samples_per_second": 17.439,
+      "eval_physics_steps_per_second": 8.719,
+      "step": 300
+    },
+    {
+      "entropy": 1.1852697040885687,
+      "epoch": 0.275969509820286,
+      "grad_norm": 0.875,
+      "learning_rate": 1.9933333333333334e-05,
+      "loss": 1.0941,
+      "mean_token_accuracy": 0.7201298415660858,
+      "num_tokens": 4126779.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.1581873616203666,
+      "epoch": 0.2848717520725533,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.985925925925926e-05,
+      "loss": 1.0739,
+      "mean_token_accuracy": 0.7240971345454454,
+      "num_tokens": 4259617.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.1453685130923987,
+      "epoch": 0.29377399432482054,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.9785185185185187e-05,
+      "loss": 1.0543,
+      "mean_token_accuracy": 0.7301174711436034,
+      "num_tokens": 4391745.0,
+      "step": 330
+    },
+    {
+      "entropy": 1.1414084695279598,
+      "epoch": 0.30267623657708786,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.971111111111111e-05,
+      "loss": 1.0486,
+      "mean_token_accuracy": 0.7298893980681896,
+      "num_tokens": 4525776.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.096273798495531,
+      "epoch": 0.31157847882935513,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.963703703703704e-05,
+      "loss": 1.0093,
+      "mean_token_accuracy": 0.7381538521498442,
+      "num_tokens": 4653203.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.194446151703596,
+      "epoch": 0.32048072108162245,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.9562962962962964e-05,
+      "loss": 1.0889,
+      "mean_token_accuracy": 0.7179776296019554,
+      "num_tokens": 4786866.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.1112803112715484,
+      "epoch": 0.3293829633338897,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.948888888888889e-05,
+      "loss": 1.019,
+      "mean_token_accuracy": 0.7352581065148115,
+      "num_tokens": 4921793.0,
+      "step": 370
+    },
+    {
+      "entropy": 1.145531201735139,
+      "epoch": 0.338285205586157,
+      "grad_norm": 0.71484375,
+      "learning_rate": 1.9414814814814817e-05,
+      "loss": 1.0382,
+      "mean_token_accuracy": 0.7289914164692164,
+      "num_tokens": 5055990.0,
+      "step": 380
+    },
+    {
+      "entropy": 1.1610372081398963,
+      "epoch": 0.3471874478384243,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.9340740740740743e-05,
+      "loss": 1.0628,
+      "mean_token_accuracy": 0.7227894127368927,
+      "num_tokens": 5182611.0,
+      "step": 390
+    },
+    {
+      "entropy": 1.1239100523293017,
+      "epoch": 0.3560896900906916,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.926666666666667e-05,
+      "loss": 1.0403,
+      "mean_token_accuracy": 0.729755662754178,
+      "num_tokens": 5313795.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.3560896900906916,
+      "eval_biology_entropy": 2.1833299980163576,
+      "eval_biology_loss": 2.2870590686798096,
+      "eval_biology_mean_token_accuracy": 0.5356344033479691,
+      "eval_biology_num_tokens": 5313795.0,
+      "eval_biology_runtime": 18.975,
+      "eval_biology_samples_per_second": 26.35,
+      "eval_biology_steps_per_second": 13.175,
+      "step": 400
+    },
+    {
+      "epoch": 0.3560896900906916,
+      "eval_chemistry_entropy": 1.1136225144863128,
+      "eval_chemistry_loss": 1.0691337585449219,
+      "eval_chemistry_mean_token_accuracy": 0.7317903306484222,
+      "eval_chemistry_num_tokens": 5313795.0,
+      "eval_chemistry_runtime": 24.7923,
+      "eval_chemistry_samples_per_second": 20.168,
+      "eval_chemistry_steps_per_second": 10.084,
+      "step": 400
+    },
+    {
+      "epoch": 0.3560896900906916,
+      "eval_math_entropy": 0.9845062309503555,
+      "eval_math_loss": 1.2056244611740112,
+      "eval_math_mean_token_accuracy": 0.711446602344513,
+      "eval_math_num_tokens": 5313795.0,
+      "eval_math_runtime": 24.5234,
+      "eval_math_samples_per_second": 20.389,
+      "eval_math_steps_per_second": 10.194,
+      "step": 400
+    },
+    {
+      "epoch": 0.3560896900906916,
+      "eval_physics_entropy": 1.108200379371643,
+      "eval_physics_loss": 1.0871150493621826,
+      "eval_physics_mean_token_accuracy": 0.7332238068580628,
+      "eval_physics_num_tokens": 5313795.0,
+      "eval_physics_runtime": 28.6972,
+      "eval_physics_samples_per_second": 17.423,
+      "eval_physics_steps_per_second": 8.712,
+      "step": 400
+    },
+    {
+      "entropy": 1.0743986388668418,
+      "epoch": 0.3649919323429589,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.9192592592592593e-05,
+      "loss": 0.9898,
+      "mean_token_accuracy": 0.7425458256155253,
+      "num_tokens": 5447087.0,
+      "step": 410
+    },
+    {
+      "entropy": 1.1058754766359926,
+      "epoch": 0.37389417459522617,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.911851851851852e-05,
+      "loss": 1.0094,
+      "mean_token_accuracy": 0.7370415050536394,
+      "num_tokens": 5573445.0,
+      "step": 420
+    },
+    {
+      "entropy": 1.0946383344009518,
+      "epoch": 0.38279641684749344,
+      "grad_norm": 0.85546875,
+      "learning_rate": 1.9044444444444446e-05,
+      "loss": 1.0192,
+      "mean_token_accuracy": 0.7376058127731084,
+      "num_tokens": 5703640.0,
+      "step": 430
+    },
+    {
+      "entropy": 1.1165539000183344,
+      "epoch": 0.39169865909976076,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.8970370370370372e-05,
+      "loss": 1.0148,
+      "mean_token_accuracy": 0.7342595763504505,
+      "num_tokens": 5836274.0,
+      "step": 440
+    },
+    {
+      "entropy": 1.1028259133920073,
+      "epoch": 0.400600901352028,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.8896296296296295e-05,
+      "loss": 1.009,
+      "mean_token_accuracy": 0.7364393822848797,
+      "num_tokens": 5967215.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.0587953502312302,
+      "epoch": 0.40950314360429535,
+      "grad_norm": 0.734375,
+      "learning_rate": 1.8822222222222225e-05,
+      "loss": 0.9688,
+      "mean_token_accuracy": 0.746485960483551,
+      "num_tokens": 6101944.0,
+      "step": 460
+    },
+    {
+      "entropy": 1.1212815966457128,
+      "epoch": 0.4184053858565626,
+      "grad_norm": 0.85546875,
+      "learning_rate": 1.874814814814815e-05,
+      "loss": 1.0258,
+      "mean_token_accuracy": 0.733516975864768,
+      "num_tokens": 6231388.0,
+      "step": 470
+    },
+    {
+      "entropy": 1.0713276099413633,
+      "epoch": 0.4273076281088299,
+      "grad_norm": 0.73828125,
+      "learning_rate": 1.8674074074074075e-05,
+      "loss": 0.9709,
+      "mean_token_accuracy": 0.7428883332759142,
+      "num_tokens": 6363951.0,
+      "step": 480
+    },
+    {
+      "entropy": 1.09543631747365,
+      "epoch": 0.4362098703610972,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.86e-05,
+      "loss": 1.01,
+      "mean_token_accuracy": 0.735943990573287,
+      "num_tokens": 6495585.0,
+      "step": 490
+    },
+    {
+      "entropy": 1.0952462505549192,
+      "epoch": 0.4451121126133645,
+      "grad_norm": 0.76171875,
+      "learning_rate": 1.8525925925925928e-05,
+      "loss": 1.0042,
+      "mean_token_accuracy": 0.7367089048027993,
+      "num_tokens": 6622502.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.4451121126133645,
+      "eval_biology_entropy": 2.1483897223472597,
+      "eval_biology_loss": 2.2432360649108887,
+      "eval_biology_mean_token_accuracy": 0.5430341627597809,
+      "eval_biology_num_tokens": 6622502.0,
+      "eval_biology_runtime": 19.1686,
+      "eval_biology_samples_per_second": 26.084,
+      "eval_biology_steps_per_second": 13.042,
+      "step": 500
+    },
+    {
+      "epoch": 0.4451121126133645,
+      "eval_chemistry_entropy": 1.091737098813057,
+      "eval_chemistry_loss": 1.040204644203186,
+      "eval_chemistry_mean_token_accuracy": 0.7374620385169983,
+      "eval_chemistry_num_tokens": 6622502.0,
+      "eval_chemistry_runtime": 23.9529,
+      "eval_chemistry_samples_per_second": 20.874,
+      "eval_chemistry_steps_per_second": 10.437,
+      "step": 500
+    },
+    {
+      "epoch": 0.4451121126133645,
+      "eval_math_entropy": 0.9775256743431091,
+      "eval_math_loss": 1.186624526977539,
+      "eval_math_mean_token_accuracy": 0.7151267173290252,
+      "eval_math_num_tokens": 6622502.0,
+      "eval_math_runtime": 24.4031,
+      "eval_math_samples_per_second": 20.489,
+      "eval_math_steps_per_second": 10.245,
+      "step": 500
+    },
+    {
+      "epoch": 0.4451121126133645,
+      "eval_physics_entropy": 1.0940199873447418,
+      "eval_physics_loss": 1.0634400844573975,
+      "eval_physics_mean_token_accuracy": 0.737773185968399,
+      "eval_physics_num_tokens": 6622502.0,
+      "eval_physics_runtime": 28.632,
+      "eval_physics_samples_per_second": 17.463,
+      "eval_physics_steps_per_second": 8.731,
+      "step": 500
+    },
+    {
+      "entropy": 1.0699838446453214,
+      "epoch": 0.4540143548656318,
+      "grad_norm": 0.75,
+      "learning_rate": 1.8451851851851855e-05,
+      "loss": 0.9686,
+      "mean_token_accuracy": 0.7425621785223484,
+      "num_tokens": 6751161.0,
+      "step": 510
+    },
+    {
+      "entropy": 1.086439424008131,
+      "epoch": 0.46291659711789906,
+      "grad_norm": 0.7265625,
+      "learning_rate": 1.8377777777777778e-05,
+      "loss": 0.9859,
+      "mean_token_accuracy": 0.7420764189213515,
+      "num_tokens": 6881616.0,
+      "step": 520
+    },
+    {
+      "entropy": 1.067279956676066,
+      "epoch": 0.4718188393701664,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.8303703703703704e-05,
+      "loss": 0.9765,
+      "mean_token_accuracy": 0.7449497696012258,
+      "num_tokens": 7017868.0,
+      "step": 530
+    },
+    {
+      "entropy": 1.091121963970363,
+      "epoch": 0.48072108162243365,
+      "grad_norm": 0.7578125,
+      "learning_rate": 1.822962962962963e-05,
+      "loss": 1.0114,
+      "mean_token_accuracy": 0.7365596149116754,
+      "num_tokens": 7151294.0,
+      "step": 540
+    },
+    {
+      "entropy": 1.0589939182624222,
+      "epoch": 0.4896233238747009,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.8155555555555557e-05,
+      "loss": 0.9649,
+      "mean_token_accuracy": 0.7470602467656136,
+      "num_tokens": 7295452.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.0378610417246819,
+      "epoch": 0.49852556612696824,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.8081481481481484e-05,
+      "loss": 0.9457,
+      "mean_token_accuracy": 0.7502593748271466,
+      "num_tokens": 7427354.0,
+      "step": 560
+    },
+    {
+      "entropy": 1.0780232414603232,
+      "epoch": 0.5074278083792355,
+      "grad_norm": 0.69921875,
+      "learning_rate": 1.800740740740741e-05,
+      "loss": 0.9837,
+      "mean_token_accuracy": 0.7401763413101434,
+      "num_tokens": 7558252.0,
+      "step": 570
+    },
+    {
+      "entropy": 1.0984149038791657,
+      "epoch": 0.5163300506315028,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.7933333333333333e-05,
+      "loss": 0.9951,
+      "mean_token_accuracy": 0.737068784981966,
+      "num_tokens": 7688220.0,
+      "step": 580
+    },
+    {
+      "entropy": 1.0815258041024207,
+      "epoch": 0.52523229288377,
+      "grad_norm": 0.80859375,
+      "learning_rate": 1.785925925925926e-05,
+      "loss": 0.9935,
+      "mean_token_accuracy": 0.7424198940396309,
+      "num_tokens": 7819813.0,
+      "step": 590
+    },
+    {
+      "entropy": 1.0907988570630551,
+      "epoch": 0.5341345351360374,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.7785185185185186e-05,
+      "loss": 0.9922,
+      "mean_token_accuracy": 0.739279318973422,
+      "num_tokens": 7951372.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.5341345351360374,
+      "eval_biology_entropy": 2.1178611373901366,
+      "eval_biology_loss": 2.214088201522827,
+      "eval_biology_mean_token_accuracy": 0.5480384603738785,
+      "eval_biology_num_tokens": 7951372.0,
+      "eval_biology_runtime": 18.9891,
+      "eval_biology_samples_per_second": 26.331,
+      "eval_biology_steps_per_second": 13.165,
+      "step": 600
+    },
+    {
+      "epoch": 0.5341345351360374,
+      "eval_chemistry_entropy": 1.0694828644990921,
+      "eval_chemistry_loss": 1.0220880508422852,
+      "eval_chemistry_mean_token_accuracy": 0.7412470579147339,
+      "eval_chemistry_num_tokens": 7951372.0,
+      "eval_chemistry_runtime": 24.074,
+      "eval_chemistry_samples_per_second": 20.769,
+      "eval_chemistry_steps_per_second": 10.385,
+      "step": 600
+    },
+    {
+      "epoch": 0.5341345351360374,
+      "eval_math_entropy": 0.9660351483821868,
+      "eval_math_loss": 1.1651713848114014,
+      "eval_math_mean_token_accuracy": 0.7203534297943115,
+      "eval_math_num_tokens": 7951372.0,
+      "eval_math_runtime": 24.6005,
+      "eval_math_samples_per_second": 20.325,
+      "eval_math_steps_per_second": 10.162,
+      "step": 600
+    },
+    {
+      "epoch": 0.5341345351360374,
+      "eval_physics_entropy": 1.0763019816875459,
+      "eval_physics_loss": 1.047385573387146,
+      "eval_physics_mean_token_accuracy": 0.741036681652069,
+      "eval_physics_num_tokens": 7951372.0,
+      "eval_physics_runtime": 28.7125,
+      "eval_physics_samples_per_second": 17.414,
+      "eval_physics_steps_per_second": 8.707,
+      "step": 600
+    },
+    {
+      "entropy": 1.0812974084168672,
+      "epoch": 0.5430367773883047,
+      "grad_norm": 0.79296875,
+      "learning_rate": 1.7711111111111113e-05,
+      "loss": 0.9848,
+      "mean_token_accuracy": 0.7414944332093001,
+      "num_tokens": 8086060.0,
+      "step": 610
+    },
+    {
+      "entropy": 1.0596148006618022,
+      "epoch": 0.551939019640572,
+      "grad_norm": 0.7265625,
+      "learning_rate": 1.763703703703704e-05,
+      "loss": 0.981,
+      "mean_token_accuracy": 0.7439363609999419,
+      "num_tokens": 8224064.0,
+      "step": 620
+    },
+    {
+      "entropy": 1.0637529838830233,
+      "epoch": 0.5608412618928392,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.7562962962962962e-05,
+      "loss": 0.9797,
+      "mean_token_accuracy": 0.743705640360713,
+      "num_tokens": 8347686.0,
+      "step": 630
+    },
+    {
+      "entropy": 1.04844657368958,
+      "epoch": 0.5697435041451065,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.7488888888888892e-05,
+      "loss": 0.9901,
+      "mean_token_accuracy": 0.7446227420121432,
+      "num_tokens": 8479025.0,
+      "step": 640
+    },
+    {
+      "entropy": 1.0554169865325094,
+      "epoch": 0.5786457463973739,
+      "grad_norm": 0.9453125,
+      "learning_rate": 1.7414814814814815e-05,
+      "loss": 0.963,
+      "mean_token_accuracy": 0.7450377620756626,
+      "num_tokens": 8604855.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.0970475694164634,
+      "epoch": 0.5875479886496411,
+      "grad_norm": 0.921875,
+      "learning_rate": 1.7340740740740742e-05,
+      "loss": 0.9982,
+      "mean_token_accuracy": 0.7373595230281353,
+      "num_tokens": 8739828.0,
+      "step": 660
+    },
+    {
+      "entropy": 1.0422217467799784,
+      "epoch": 0.5964502309019084,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.726666666666667e-05,
+      "loss": 0.96,
+      "mean_token_accuracy": 0.7486237779259681,
+      "num_tokens": 8868152.0,
+      "step": 670
+    },
+    {
+      "entropy": 1.0182484578341247,
+      "epoch": 0.6053524731541757,
+      "grad_norm": 0.71484375,
+      "learning_rate": 1.7192592592592595e-05,
+      "loss": 0.9422,
+      "mean_token_accuracy": 0.749386464804411,
+      "num_tokens": 9006122.0,
+      "step": 680
+    },
+    {
+      "entropy": 1.0727280082181097,
+      "epoch": 0.614254715406443,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.711851851851852e-05,
+      "loss": 0.9849,
+      "mean_token_accuracy": 0.7426282811909914,
+      "num_tokens": 9135332.0,
+      "step": 690
+    },
+    {
+      "entropy": 1.0424362102523446,
+      "epoch": 0.6231569576587103,
+      "grad_norm": 0.82421875,
+      "learning_rate": 1.7044444444444445e-05,
+      "loss": 0.9488,
+      "mean_token_accuracy": 0.7479008056223393,
+      "num_tokens": 9273088.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.6231569576587103,
+      "eval_biology_entropy": 2.1061350786685944,
+      "eval_biology_loss": 2.1926093101501465,
+      "eval_biology_mean_token_accuracy": 0.550960058927536,
+      "eval_biology_num_tokens": 9273088.0,
+      "eval_biology_runtime": 19.0758,
+      "eval_biology_samples_per_second": 26.211,
+      "eval_biology_steps_per_second": 13.106,
+      "step": 700
+    },
+    {
+      "epoch": 0.6231569576587103,
+      "eval_chemistry_entropy": 1.0614726347923278,
+      "eval_chemistry_loss": 1.0082380771636963,
+      "eval_chemistry_mean_token_accuracy": 0.7441184866428375,
+      "eval_chemistry_num_tokens": 9273088.0,
+      "eval_chemistry_runtime": 24.1338,
+      "eval_chemistry_samples_per_second": 20.718,
+      "eval_chemistry_steps_per_second": 10.359,
+      "step": 700
+    },
+    {
+      "epoch": 0.6231569576587103,
+      "eval_math_entropy": 0.9611164342164993,
+      "eval_math_loss": 1.1547077894210815,
+      "eval_math_mean_token_accuracy": 0.7228360230922699,
+      "eval_math_num_tokens": 9273088.0,
+      "eval_math_runtime": 24.528,
+      "eval_math_samples_per_second": 20.385,
+      "eval_math_steps_per_second": 10.192,
+      "step": 700
+    },
+    {
+      "epoch": 0.6231569576587103,
+      "eval_physics_entropy": 1.0682205600738526,
+      "eval_physics_loss": 1.0357767343521118,
+      "eval_physics_mean_token_accuracy": 0.743281735420227,
+      "eval_physics_num_tokens": 9273088.0,
+      "eval_physics_runtime": 28.7501,
+      "eval_physics_samples_per_second": 17.391,
+      "eval_physics_steps_per_second": 8.696,
+      "step": 700
+    },
+    {
+      "entropy": 1.0483794966712594,
+      "epoch": 0.6320591999109776,
+      "grad_norm": 0.8203125,
+      "learning_rate": 1.697037037037037e-05,
+      "loss": 0.9756,
+      "mean_token_accuracy": 0.7465494040399789,
+      "num_tokens": 9405858.0,
+      "step": 710
+    },
+    {
+      "entropy": 1.0315969336777926,
+      "epoch": 0.6409614421632449,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.6896296296296298e-05,
+      "loss": 0.9318,
+      "mean_token_accuracy": 0.7522267319262028,
+      "num_tokens": 9540719.0,
+      "step": 720
+    },
+    {
+      "entropy": 1.0228697720915079,
+      "epoch": 0.6498636844155121,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.6822222222222224e-05,
+      "loss": 0.9206,
+      "mean_token_accuracy": 0.754125602915883,
+      "num_tokens": 9674589.0,
+      "step": 730
+    },
+    {
+      "entropy": 1.0417734686285258,
+      "epoch": 0.6587659266677794,
+      "grad_norm": 0.734375,
+      "learning_rate": 1.6748148148148147e-05,
+      "loss": 0.963,
+      "mean_token_accuracy": 0.7486015625298024,
+      "num_tokens": 9805714.0,
+      "step": 740
+    },
+    {
+      "entropy": 1.0292632792145013,
+      "epoch": 0.6676681689200468,
+      "grad_norm": 0.78125,
+      "learning_rate": 1.6674074074074077e-05,
+      "loss": 0.9268,
+      "mean_token_accuracy": 0.7511202458292245,
+      "num_tokens": 9933853.0,
+      "step": 750
+    },
+    {
+      "entropy": 1.0266933845356108,
+      "epoch": 0.676570411172314,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.66e-05,
+      "loss": 0.948,
+      "mean_token_accuracy": 0.7509643025696278,
+      "num_tokens": 10073440.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.9969334525987505,
+      "epoch": 0.6854726534245813,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.6525925925925927e-05,
+      "loss": 0.9175,
+      "mean_token_accuracy": 0.7583379317075014,
+      "num_tokens": 10211274.0,
+      "step": 770
+    },
+    {
+      "entropy": 1.0174086516723038,
+      "epoch": 0.6943748956768486,
+      "grad_norm": 0.75390625,
+      "learning_rate": 1.6451851851851853e-05,
+      "loss": 0.9262,
+      "mean_token_accuracy": 0.75306093133986,
+      "num_tokens": 10342522.0,
+      "step": 780
+    },
+    {
+      "entropy": 1.0142306819558145,
+      "epoch": 0.703277137929116,
+      "grad_norm": 0.79296875,
+      "learning_rate": 1.637777777777778e-05,
+      "loss": 0.9373,
+      "mean_token_accuracy": 0.7523925706744194,
+      "num_tokens": 10478874.0,
+      "step": 790
+    },
+    {
+      "entropy": 1.0250910749658941,
+      "epoch": 0.7121793801813832,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.6303703703703706e-05,
+      "loss": 0.9313,
+      "mean_token_accuracy": 0.7509257387369871,
+      "num_tokens": 10611038.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.7121793801813832,
+      "eval_biology_entropy": 2.069473657131195,
+      "eval_biology_loss": 2.180377960205078,
+      "eval_biology_mean_token_accuracy": 0.5537625602483749,
+      "eval_biology_num_tokens": 10611038.0,
+      "eval_biology_runtime": 18.989,
+      "eval_biology_samples_per_second": 26.331,
+      "eval_biology_steps_per_second": 13.166,
+      "step": 800
+    },
+    {
+      "epoch": 0.7121793801813832,
+      "eval_chemistry_entropy": 1.0416202774047851,
+      "eval_chemistry_loss": 0.9986625909805298,
+      "eval_chemistry_mean_token_accuracy": 0.7456459767818451,
+      "eval_chemistry_num_tokens": 10611038.0,
+      "eval_chemistry_runtime": 24.1612,
+      "eval_chemistry_samples_per_second": 20.694,
+      "eval_chemistry_steps_per_second": 10.347,
+      "step": 800
+    },
+    {
+      "epoch": 0.7121793801813832,
+      "eval_math_entropy": 0.9473755178451538,
+      "eval_math_loss": 1.1492873430252075,
+      "eval_math_mean_token_accuracy": 0.7247429151535034,
+      "eval_math_num_tokens": 10611038.0,
+      "eval_math_runtime": 24.5113,
+      "eval_math_samples_per_second": 20.399,
+      "eval_math_steps_per_second": 10.199,
+      "step": 800
+    },
+    {
+      "epoch": 0.7121793801813832,
+      "eval_physics_entropy": 1.0511555817127227,
+      "eval_physics_loss": 1.0280060768127441,
+      "eval_physics_mean_token_accuracy": 0.7451158492565155,
+      "eval_physics_num_tokens": 10611038.0,
+      "eval_physics_runtime": 28.6841,
+      "eval_physics_samples_per_second": 17.431,
+      "eval_physics_steps_per_second": 8.716,
+      "step": 800
+    },
+    {
+      "entropy": 0.9938568271696567,
+      "epoch": 0.7210816224336505,
+      "grad_norm": 0.75390625,
+      "learning_rate": 1.622962962962963e-05,
+      "loss": 0.9057,
+      "mean_token_accuracy": 0.7613154832273722,
+      "num_tokens": 10741681.0,
+      "step": 810
+    },
+    {
+      "entropy": 1.0242274224758148,
+      "epoch": 0.7299838646859178,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.6155555555555556e-05,
+      "loss": 0.9589,
+      "mean_token_accuracy": 0.7503436904400587,
+      "num_tokens": 10874184.0,
+      "step": 820
+    },
+    {
+      "entropy": 1.0636370442807674,
+      "epoch": 0.738886106938185,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.6081481481481482e-05,
+      "loss": 0.965,
+      "mean_token_accuracy": 0.7441002728417516,
+      "num_tokens": 11006058.0,
+      "step": 830
+    },
+    {
+      "entropy": 1.006078546307981,
+      "epoch": 0.7477883491904523,
+      "grad_norm": 0.73828125,
+      "learning_rate": 1.600740740740741e-05,
+      "loss": 0.9198,
+      "mean_token_accuracy": 0.7565505605190992,
+      "num_tokens": 11140344.0,
+      "step": 840
+    },
+    {
+      "entropy": 1.041573415696621,
+      "epoch": 0.7566905914427197,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.5933333333333336e-05,
+      "loss": 0.9585,
+      "mean_token_accuracy": 0.746536037698388,
+      "num_tokens": 11273755.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.0404196836054325,
+      "epoch": 0.7655928336949869,
+      "grad_norm": 0.75390625,
+      "learning_rate": 1.5859259259259262e-05,
+      "loss": 0.9599,
+      "mean_token_accuracy": 0.7491594787687064,
+      "num_tokens": 11411558.0,
+      "step": 860
+    },
+    {
+      "entropy": 1.0480362083762884,
+      "epoch": 0.7744950759472542,
+      "grad_norm": 0.71484375,
+      "learning_rate": 1.5785185185185185e-05,
+      "loss": 0.9531,
+      "mean_token_accuracy": 0.7495062164962292,
+      "num_tokens": 11542129.0,
+      "step": 870
+    },
+    {
+      "entropy": 1.0487740390002727,
+      "epoch": 0.7833973181995215,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.571111111111111e-05,
+      "loss": 0.9719,
+      "mean_token_accuracy": 0.7440535627305508,
+      "num_tokens": 11676795.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.9984678329899908,
+      "epoch": 0.7922995604517888,
+      "grad_norm": 0.82421875,
+      "learning_rate": 1.5637037037037038e-05,
+      "loss": 0.9075,
+      "mean_token_accuracy": 0.7598592435941101,
+      "num_tokens": 11813290.0,
+      "step": 890
+    },
+    {
+      "entropy": 1.067121583223343,
+      "epoch": 0.801201802704056,
+      "grad_norm": 0.7890625,
+      "learning_rate": 1.5562962962962965e-05,
+      "loss": 0.9839,
+      "mean_token_accuracy": 0.7415191430598498,
+      "num_tokens": 11939057.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.801201802704056,
+      "eval_biology_entropy": 2.0663459722995756,
+      "eval_biology_loss": 2.1661489009857178,
+      "eval_biology_mean_token_accuracy": 0.5559320805072785,
+      "eval_biology_num_tokens": 11939057.0,
+      "eval_biology_runtime": 18.9535,
+      "eval_biology_samples_per_second": 26.38,
+      "eval_biology_steps_per_second": 13.19,
+      "step": 900
+    },
+    {
+      "epoch": 0.801201802704056,
+      "eval_chemistry_entropy": 1.037217586994171,
+      "eval_chemistry_loss": 0.9907548427581787,
+      "eval_chemistry_mean_token_accuracy": 0.7475485587120057,
+      "eval_chemistry_num_tokens": 11939057.0,
+      "eval_chemistry_runtime": 24.0512,
+      "eval_chemistry_samples_per_second": 20.789,
+      "eval_chemistry_steps_per_second": 10.394,
+      "step": 900
+    },
+    {
+      "epoch": 0.801201802704056,
+      "eval_math_entropy": 0.945040546298027,
+      "eval_math_loss": 1.1432464122772217,
+      "eval_math_mean_token_accuracy": 0.7263167641162872,
+      "eval_math_num_tokens": 11939057.0,
+      "eval_math_runtime": 24.5059,
+      "eval_math_samples_per_second": 20.403,
+      "eval_math_steps_per_second": 10.202,
+      "step": 900
+    },
+    {
+      "epoch": 0.801201802704056,
+      "eval_physics_entropy": 1.0482188910245895,
+      "eval_physics_loss": 1.0214959383010864,
+      "eval_physics_mean_token_accuracy": 0.7463257222175598,
+      "eval_physics_num_tokens": 11939057.0,
+      "eval_physics_runtime": 28.687,
+      "eval_physics_samples_per_second": 17.43,
+      "eval_physics_steps_per_second": 8.715,
+      "step": 900
+    },
+    {
+      "entropy": 1.022822911851108,
+      "epoch": 0.8101040449563234,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.548888888888889e-05,
+      "loss": 0.9437,
+      "mean_token_accuracy": 0.7512454934418201,
+      "num_tokens": 12071285.0,
+      "step": 910
+    },
+    {
+      "entropy": 1.0286116361618043,
+      "epoch": 0.8190062872085907,
+      "grad_norm": 0.75,
+      "learning_rate": 1.5414814814814814e-05,
+      "loss": 0.9501,
+      "mean_token_accuracy": 0.7485235787928104,
+      "num_tokens": 12197416.0,
+      "step": 920
+    },
+    {
+      "entropy": 1.008828422985971,
+      "epoch": 0.8279085294608579,
+      "grad_norm": 0.734375,
+      "learning_rate": 1.5340740740740744e-05,
+      "loss": 0.9133,
+      "mean_token_accuracy": 0.7554512336850167,
+      "num_tokens": 12338376.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.9990727547556162,
+      "epoch": 0.8368107717131252,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.5266666666666667e-05,
+      "loss": 0.9257,
+      "mean_token_accuracy": 0.7566340938210487,
+      "num_tokens": 12481276.0,
+      "step": 940
+    },
+    {
+      "entropy": 1.023878287896514,
+      "epoch": 0.8457130139653926,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.5192592592592594e-05,
+      "loss": 0.9283,
+      "mean_token_accuracy": 0.7518570881336928,
+      "num_tokens": 12614378.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.019566267542541,
+      "epoch": 0.8546152562176598,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.5118518518518519e-05,
+      "loss": 0.9469,
+      "mean_token_accuracy": 0.753068869188428,
+      "num_tokens": 12749299.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.9727985240519047,
+      "epoch": 0.8635174984699271,
+      "grad_norm": 0.69921875,
+      "learning_rate": 1.5044444444444445e-05,
+      "loss": 0.8757,
+      "mean_token_accuracy": 0.7642812915146351,
+      "num_tokens": 12880725.0,
+      "step": 970
+    },
+    {
+      "entropy": 1.023832948692143,
+      "epoch": 0.8724197407221944,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.497037037037037e-05,
+      "loss": 0.9526,
+      "mean_token_accuracy": 0.7505445629358292,
+      "num_tokens": 13016669.0,
+      "step": 980
+    },
+    {
+      "entropy": 1.063824800774455,
+      "epoch": 0.8813219829744617,
+      "grad_norm": 0.80859375,
+      "learning_rate": 1.4896296296296298e-05,
+      "loss": 0.9742,
+      "mean_token_accuracy": 0.7439213328063488,
+      "num_tokens": 13137848.0,
+      "step": 990
+    },
+    {
+      "entropy": 1.0260636931285263,
+      "epoch": 0.890224225226729,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.4822222222222225e-05,
+      "loss": 0.9381,
+      "mean_token_accuracy": 0.7512999761849641,
+      "num_tokens": 13270597.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.890224225226729,
+      "eval_biology_entropy": 2.052604050397873,
+      "eval_biology_loss": 2.1542117595672607,
+      "eval_biology_mean_token_accuracy": 0.557542849779129,
+      "eval_biology_num_tokens": 13270597.0,
+      "eval_biology_runtime": 18.9941,
+      "eval_biology_samples_per_second": 26.324,
+      "eval_biology_steps_per_second": 13.162,
+      "step": 1000
+    },
+    {
+      "epoch": 0.890224225226729,
+      "eval_chemistry_entropy": 1.0286521710157395,
+      "eval_chemistry_loss": 0.9842055439949036,
+      "eval_chemistry_mean_token_accuracy": 0.7491220705509186,
+      "eval_chemistry_num_tokens": 13270597.0,
+      "eval_chemistry_runtime": 23.8824,
+      "eval_chemistry_samples_per_second": 20.936,
+      "eval_chemistry_steps_per_second": 10.468,
+      "step": 1000
+    },
+    {
+      "epoch": 0.890224225226729,
+      "eval_math_entropy": 0.9400006744861603,
+      "eval_math_loss": 1.138838768005371,
+      "eval_math_mean_token_accuracy": 0.7270237381458282,
+      "eval_math_num_tokens": 13270597.0,
+      "eval_math_runtime": 24.4346,
+      "eval_math_samples_per_second": 20.463,
+      "eval_math_steps_per_second": 10.231,
+      "step": 1000
+    },
+    {
+      "epoch": 0.890224225226729,
+      "eval_physics_entropy": 1.0414861241579056,
+      "eval_physics_loss": 1.016461968421936,
+      "eval_physics_mean_token_accuracy": 0.7471425406932831,
+      "eval_physics_num_tokens": 13270597.0,
+      "eval_physics_runtime": 28.7138,
+      "eval_physics_samples_per_second": 17.413,
+      "eval_physics_steps_per_second": 8.707,
+      "step": 1000
+    },
+    {
+      "entropy": 1.0016938548535108,
+      "epoch": 0.8991264674789963,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.474814814814815e-05,
+      "loss": 0.9333,
+      "mean_token_accuracy": 0.7536258392035962,
+      "num_tokens": 13403656.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.9872909057885408,
+      "epoch": 0.9080287097312636,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.4674074074074076e-05,
+      "loss": 0.8839,
+      "mean_token_accuracy": 0.7587992373853922,
+      "num_tokens": 13539164.0,
+      "step": 1020
+    },
+    {
+      "entropy": 0.9914543008431792,
+      "epoch": 0.9169309519835308,
+      "grad_norm": 0.7734375,
+      "learning_rate": 1.46e-05,
+      "loss": 0.9019,
+      "mean_token_accuracy": 0.7592810332775116,
+      "num_tokens": 13674316.0,
+      "step": 1030
+    },
+    {
+      "entropy": 1.065089125558734,
+      "epoch": 0.9258331942357981,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.4525925925925927e-05,
+      "loss": 0.9692,
+      "mean_token_accuracy": 0.745220497623086,
+      "num_tokens": 13801522.0,
+      "step": 1040
+    },
+    {
+      "entropy": 1.0313379902392625,
+      "epoch": 0.9347354364880655,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.4451851851851852e-05,
+      "loss": 0.9497,
+      "mean_token_accuracy": 0.7498588923364877,
+      "num_tokens": 13921010.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.9975925302132964,
+      "epoch": 0.9436376787403328,
+      "grad_norm": 0.7578125,
+      "learning_rate": 1.4377777777777779e-05,
+      "loss": 0.9028,
+      "mean_token_accuracy": 0.7564504377543926,
+      "num_tokens": 14060350.0,
+      "step": 1060
+    },
+    {
+      "entropy": 1.0274140175431967,
+      "epoch": 0.9525399209926,
+      "grad_norm": 0.7890625,
+      "learning_rate": 1.4303703703703703e-05,
+      "loss": 0.9394,
+      "mean_token_accuracy": 0.751261069253087,
+      "num_tokens": 14188718.0,
+      "step": 1070
+    },
+    {
+      "entropy": 1.033200218901038,
+      "epoch": 0.9614421632448673,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.4229629629629632e-05,
+      "loss": 0.9626,
+      "mean_token_accuracy": 0.7483007371425628,
+      "num_tokens": 14320755.0,
+      "step": 1080
+    },
+    {
+      "entropy": 1.0117560898885132,
+      "epoch": 0.9703444054971346,
+      "grad_norm": 0.75390625,
+      "learning_rate": 1.4155555555555556e-05,
+      "loss": 0.9183,
+      "mean_token_accuracy": 0.7542101304978133,
+      "num_tokens": 14458656.0,
+      "step": 1090
+    },
+    {
+      "entropy": 1.0004739014431834,
+      "epoch": 0.9792466477494018,
+      "grad_norm": 0.7578125,
+      "learning_rate": 1.4081481481481483e-05,
+      "loss": 0.9176,
+      "mean_token_accuracy": 0.7560600288212299,
+      "num_tokens": 14585803.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9792466477494018,
+      "eval_biology_entropy": 2.0482051389217375,
+      "eval_biology_loss": 2.1475307941436768,
+      "eval_biology_mean_token_accuracy": 0.5585559306144714,
+      "eval_biology_num_tokens": 14585803.0,
+      "eval_biology_runtime": 19.0106,
+      "eval_biology_samples_per_second": 26.301,
+      "eval_biology_steps_per_second": 13.151,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9792466477494018,
+      "eval_chemistry_entropy": 1.0246449884176254,
+      "eval_chemistry_loss": 0.9792535305023193,
+      "eval_chemistry_mean_token_accuracy": 0.7504522104263306,
+      "eval_chemistry_num_tokens": 14585803.0,
+      "eval_chemistry_runtime": 24.1164,
+      "eval_chemistry_samples_per_second": 20.733,
+      "eval_chemistry_steps_per_second": 10.366,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9792466477494018,
+      "eval_math_entropy": 0.9384239608049393,
+      "eval_math_loss": 1.1329792737960815,
+      "eval_math_mean_token_accuracy": 0.7282352995872498,
+      "eval_math_num_tokens": 14585803.0,
+      "eval_math_runtime": 24.4727,
+      "eval_math_samples_per_second": 20.431,
+      "eval_math_steps_per_second": 10.215,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9792466477494018,
+      "eval_physics_entropy": 1.0389812450408935,
+      "eval_physics_loss": 1.0122268199920654,
+      "eval_physics_mean_token_accuracy": 0.7480283100605011,
+      "eval_physics_num_tokens": 14585803.0,
+      "eval_physics_runtime": 28.673,
+      "eval_physics_samples_per_second": 17.438,
+      "eval_physics_steps_per_second": 8.719,
+      "step": 1100
+    },
+    {
+      "entropy": 0.994432588852942,
+      "epoch": 0.9881488900016692,
+      "grad_norm": 0.734375,
+      "learning_rate": 1.400740740740741e-05,
+      "loss": 0.9239,
+      "mean_token_accuracy": 0.7581027742475271,
+      "num_tokens": 14725715.0,
+      "step": 1110
+    },
+    {
+      "entropy": 1.041189231723547,
+      "epoch": 0.9970511322539365,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.3933333333333334e-05,
+      "loss": 0.9847,
+      "mean_token_accuracy": 0.7463182125240564,
+      "num_tokens": 14852093.0,
+      "step": 1120
+    },
+    {
+      "entropy": 1.0045464154857917,
+      "epoch": 1.0053413453513604,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.385925925925926e-05,
+      "loss": 0.8942,
+      "mean_token_accuracy": 0.7575381806232785,
+      "num_tokens": 14975166.0,
+      "step": 1130
+    },
+    {
+      "entropy": 0.9730835447087884,
+      "epoch": 1.0142435876036278,
+      "grad_norm": 0.66015625,
+      "learning_rate": 1.3785185185185186e-05,
+      "loss": 0.8765,
+      "mean_token_accuracy": 0.7642713971436024,
+      "num_tokens": 15110185.0,
+      "step": 1140
+    },
+    {
+      "entropy": 1.034207416512072,
+      "epoch": 1.0231458298558949,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.3711111111111112e-05,
+      "loss": 0.9334,
+      "mean_token_accuracy": 0.75177633613348,
+      "num_tokens": 15238440.0,
+      "step": 1150
+    },
+    {
+      "entropy": 1.0306764474138617,
+      "epoch": 1.0320480721081622,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.3637037037037037e-05,
+      "loss": 0.926,
+      "mean_token_accuracy": 0.7505626730620861,
+      "num_tokens": 15368850.0,
+      "step": 1160
+    },
+    {
+      "entropy": 0.9705905102193355,
+      "epoch": 1.0409503143604295,
+      "grad_norm": 0.703125,
+      "learning_rate": 1.3562962962962965e-05,
+      "loss": 0.8801,
+      "mean_token_accuracy": 0.7647023960947991,
+      "num_tokens": 15513660.0,
+      "step": 1170
+    },
+    {
+      "entropy": 1.0006306374445557,
+      "epoch": 1.0498525566126968,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.3488888888888888e-05,
+      "loss": 0.9337,
+      "mean_token_accuracy": 0.7582154147326946,
+      "num_tokens": 15644089.0,
+      "step": 1180
+    },
+    {
+      "entropy": 1.0167981253936886,
+      "epoch": 1.0587547988649642,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.3414814814814817e-05,
+      "loss": 0.9245,
+      "mean_token_accuracy": 0.7520396485924721,
+      "num_tokens": 15778331.0,
+      "step": 1190
+    },
+    {
+      "entropy": 1.0086401265114546,
+      "epoch": 1.0676570411172315,
+      "grad_norm": 0.6796875,
+      "learning_rate": 1.3340740740740741e-05,
+      "loss": 0.9222,
+      "mean_token_accuracy": 0.7566419139504432,
+      "num_tokens": 15910655.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0676570411172315,
+      "eval_biology_entropy": 2.048806533575058,
+      "eval_biology_loss": 2.1414027214050293,
+      "eval_biology_mean_token_accuracy": 0.5591386820077896,
+      "eval_biology_num_tokens": 15910655.0,
+      "eval_biology_runtime": 19.0305,
+      "eval_biology_samples_per_second": 26.274,
+      "eval_biology_steps_per_second": 13.137,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0676570411172315,
+      "eval_chemistry_entropy": 1.0218273503780364,
+      "eval_chemistry_loss": 0.9755556583404541,
+      "eval_chemistry_mean_token_accuracy": 0.7509123682975769,
+      "eval_chemistry_num_tokens": 15910655.0,
+      "eval_chemistry_runtime": 24.3424,
+      "eval_chemistry_samples_per_second": 20.54,
+      "eval_chemistry_steps_per_second": 10.27,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0676570411172315,
+      "eval_math_entropy": 0.937392254948616,
+      "eval_math_loss": 1.1316936016082764,
+      "eval_math_mean_token_accuracy": 0.7284993779659271,
+      "eval_math_num_tokens": 15910655.0,
+      "eval_math_runtime": 24.7952,
+      "eval_math_samples_per_second": 20.165,
+      "eval_math_steps_per_second": 10.083,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0676570411172315,
+      "eval_physics_entropy": 1.0369812508821488,
+      "eval_physics_loss": 1.0092358589172363,
+      "eval_physics_mean_token_accuracy": 0.7487501664161682,
+      "eval_physics_num_tokens": 15910655.0,
+      "eval_physics_runtime": 28.896,
+      "eval_physics_samples_per_second": 17.303,
+      "eval_physics_steps_per_second": 8.652,
+      "step": 1200
+    },
+    {
+      "entropy": 0.9577315801754593,
+      "epoch": 1.0765592833694986,
+      "grad_norm": 0.66015625,
+      "learning_rate": 1.3266666666666668e-05,
+      "loss": 0.876,
+      "mean_token_accuracy": 0.7670470379292965,
+      "num_tokens": 16049696.0,
+      "step": 1210
+    },
+    {
+      "entropy": 1.0141907054930925,
+      "epoch": 1.085461525621766,
+      "grad_norm": 0.76953125,
+      "learning_rate": 1.3192592592592594e-05,
+      "loss": 0.9279,
+      "mean_token_accuracy": 0.755303044244647,
+      "num_tokens": 16182504.0,
+      "step": 1220
+    },
+    {
+      "entropy": 1.0404379174113274,
+      "epoch": 1.0943637678740332,
+      "grad_norm": 0.75390625,
+      "learning_rate": 1.311851851851852e-05,
+      "loss": 0.938,
+      "mean_token_accuracy": 0.7506488140672445,
+      "num_tokens": 16313808.0,
+      "step": 1230
+    },
+    {
+      "entropy": 1.0109531041234732,
+      "epoch": 1.1032660101263005,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.3044444444444446e-05,
+      "loss": 0.9226,
+      "mean_token_accuracy": 0.757753336057067,
+      "num_tokens": 16448180.0,
+      "step": 1240
+    },
+    {
+      "entropy": 1.0011115856468678,
+      "epoch": 1.1121682523785679,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.297037037037037e-05,
+      "loss": 0.8975,
+      "mean_token_accuracy": 0.7575169585645198,
+      "num_tokens": 16578096.0,
+      "step": 1250
+    },
+    {
+      "entropy": 1.0072824424132705,
+      "epoch": 1.1210704946308352,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.2896296296296299e-05,
+      "loss": 0.904,
+      "mean_token_accuracy": 0.7560192253440619,
+      "num_tokens": 16716301.0,
+      "step": 1260
+    },
+    {
+      "entropy": 1.0174341920763255,
+      "epoch": 1.1299727368831025,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.2822222222222222e-05,
+      "loss": 0.9377,
+      "mean_token_accuracy": 0.7541048441082239,
+      "num_tokens": 16848963.0,
+      "step": 1270
+    },
+    {
+      "entropy": 0.9653377663344145,
+      "epoch": 1.1388749791353696,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.274814814814815e-05,
+      "loss": 0.8864,
+      "mean_token_accuracy": 0.7635095983743667,
+      "num_tokens": 16982075.0,
+      "step": 1280
+    },
+    {
+      "entropy": 0.9920188255608082,
+      "epoch": 1.147777221387637,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.2674074074074075e-05,
+      "loss": 0.9015,
+      "mean_token_accuracy": 0.7589824173599482,
+      "num_tokens": 17114157.0,
+      "step": 1290
+    },
+    {
+      "entropy": 1.028341007232666,
+      "epoch": 1.1566794636399043,
+      "grad_norm": 0.76953125,
+      "learning_rate": 1.2600000000000001e-05,
+      "loss": 0.9336,
+      "mean_token_accuracy": 0.7501583714038134,
+      "num_tokens": 17245025.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1566794636399043,
+      "eval_biology_entropy": 2.040317675590515,
+      "eval_biology_loss": 2.1370644569396973,
+      "eval_biology_mean_token_accuracy": 0.5601756105422974,
+      "eval_biology_num_tokens": 17245025.0,
+      "eval_biology_runtime": 19.1089,
+      "eval_biology_samples_per_second": 26.166,
+      "eval_biology_steps_per_second": 13.083,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1566794636399043,
+      "eval_chemistry_entropy": 1.0197941246032716,
+      "eval_chemistry_loss": 0.97270667552948,
+      "eval_chemistry_mean_token_accuracy": 0.7514277906417847,
+      "eval_chemistry_num_tokens": 17245025.0,
+      "eval_chemistry_runtime": 24.2386,
+      "eval_chemistry_samples_per_second": 20.628,
+      "eval_chemistry_steps_per_second": 10.314,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1566794636399043,
+      "eval_math_entropy": 0.9364101912975311,
+      "eval_math_loss": 1.1282024383544922,
+      "eval_math_mean_token_accuracy": 0.7295171325206756,
+      "eval_math_num_tokens": 17245025.0,
+      "eval_math_runtime": 24.6414,
+      "eval_math_samples_per_second": 20.291,
+      "eval_math_steps_per_second": 10.146,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1566794636399043,
+      "eval_physics_entropy": 1.0356826380491257,
+      "eval_physics_loss": 1.0066264867782593,
+      "eval_physics_mean_token_accuracy": 0.7495199704170227,
+      "eval_physics_num_tokens": 17245025.0,
+      "eval_physics_runtime": 28.9223,
+      "eval_physics_samples_per_second": 17.288,
+      "eval_physics_steps_per_second": 8.644,
+      "step": 1300
+    },
+    {
+      "entropy": 1.0108375845476985,
+      "epoch": 1.1655817058921716,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.2525925925925928e-05,
+      "loss": 0.9358,
+      "mean_token_accuracy": 0.7542513150721788,
+      "num_tokens": 17377169.0,
+      "step": 1310
+    },
+    {
+      "entropy": 1.0600576546043157,
+      "epoch": 1.174483948144439,
+      "grad_norm": 0.80859375,
+      "learning_rate": 1.2451851851851853e-05,
+      "loss": 0.9436,
+      "mean_token_accuracy": 0.7435958338901401,
+      "num_tokens": 17510694.0,
+      "step": 1320
+    },
+    {
+      "entropy": 1.0078904403373599,
+      "epoch": 1.1833861903967062,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.237777777777778e-05,
+      "loss": 0.9095,
+      "mean_token_accuracy": 0.754418694600463,
+      "num_tokens": 17644368.0,
+      "step": 1330
+    },
+    {
+      "entropy": 1.0075497096404433,
+      "epoch": 1.1922884326489736,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.2303703703703704e-05,
+      "loss": 0.9086,
+      "mean_token_accuracy": 0.7555957213044167,
+      "num_tokens": 17779858.0,
+      "step": 1340
+    },
+    {
+      "entropy": 0.9998210400342942,
+      "epoch": 1.2011906749012407,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.222962962962963e-05,
+      "loss": 0.905,
+      "mean_token_accuracy": 0.757889486476779,
+      "num_tokens": 17908860.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.9919102193787694,
+      "epoch": 1.210092917153508,
+      "grad_norm": 0.75390625,
+      "learning_rate": 1.2155555555555555e-05,
+      "loss": 0.9157,
+      "mean_token_accuracy": 0.7589156001806259,
+      "num_tokens": 18045704.0,
+      "step": 1360
+    },
+    {
+      "entropy": 1.0109667349606752,
+      "epoch": 1.2189951594057753,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.2081481481481484e-05,
+      "loss": 0.9092,
+      "mean_token_accuracy": 0.7577930960804224,
+      "num_tokens": 18186305.0,
+      "step": 1370
+    },
+    {
+      "entropy": 1.0232981404289603,
+      "epoch": 1.2278974016580426,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.2007407407407408e-05,
+      "loss": 0.9374,
+      "mean_token_accuracy": 0.753229970112443,
+      "num_tokens": 18312712.0,
+      "step": 1380
+    },
+    {
+      "entropy": 1.0313591081649065,
+      "epoch": 1.23679964391031,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.1933333333333335e-05,
+      "loss": 0.9323,
+      "mean_token_accuracy": 0.7518048360943794,
+      "num_tokens": 18446897.0,
+      "step": 1390
+    },
+    {
+      "entropy": 0.9975250829011202,
+      "epoch": 1.2457018861625773,
+      "grad_norm": 0.75390625,
+      "learning_rate": 1.185925925925926e-05,
+      "loss": 0.9025,
+      "mean_token_accuracy": 0.7583462674170732,
+      "num_tokens": 18582685.0,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2457018861625773,
+      "eval_biology_entropy": 2.0289463448524474,
+      "eval_biology_loss": 2.1329195499420166,
+      "eval_biology_mean_token_accuracy": 0.5607757045030594,
+      "eval_biology_num_tokens": 18582685.0,
+      "eval_biology_runtime": 18.8941,
+      "eval_biology_samples_per_second": 26.463,
+      "eval_biology_steps_per_second": 13.232,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2457018861625773,
+      "eval_chemistry_entropy": 1.0126679302453996,
+      "eval_chemistry_loss": 0.970359742641449,
+      "eval_chemistry_mean_token_accuracy": 0.7518892657756805,
+      "eval_chemistry_num_tokens": 18582685.0,
+      "eval_chemistry_runtime": 23.9747,
+      "eval_chemistry_samples_per_second": 20.855,
+      "eval_chemistry_steps_per_second": 10.428,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2457018861625773,
+      "eval_math_entropy": 0.9310557426214218,
+      "eval_math_loss": 1.1270216703414917,
+      "eval_math_mean_token_accuracy": 0.72994606757164,
+      "eval_math_num_tokens": 18582685.0,
+      "eval_math_runtime": 24.4129,
+      "eval_math_samples_per_second": 20.481,
+      "eval_math_steps_per_second": 10.24,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2457018861625773,
+      "eval_physics_entropy": 1.0292026166915893,
+      "eval_physics_loss": 1.0049251317977905,
+      "eval_physics_mean_token_accuracy": 0.7496011610031128,
+      "eval_physics_num_tokens": 18582685.0,
+      "eval_physics_runtime": 28.618,
+      "eval_physics_samples_per_second": 17.472,
+      "eval_physics_steps_per_second": 8.736,
+      "step": 1400
+    },
+    {
+      "entropy": 0.9999802680686116,
+      "epoch": 1.2546041284148446,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.1785185185185186e-05,
+      "loss": 0.9154,
+      "mean_token_accuracy": 0.756169842928648,
+      "num_tokens": 18724203.0,
+      "step": 1410
+    },
+    {
+      "entropy": 0.9876425944268703,
+      "epoch": 1.2635063706671117,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.1711111111111113e-05,
+      "loss": 0.8931,
+      "mean_token_accuracy": 0.7611255884170532,
+      "num_tokens": 18855233.0,
+      "step": 1420
+    },
+    {
+      "entropy": 1.023998738825321,
+      "epoch": 1.272408612919379,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.1637037037037037e-05,
+      "loss": 0.9296,
+      "mean_token_accuracy": 0.7521598249673843,
+      "num_tokens": 18994709.0,
+      "step": 1430
+    },
+    {
+      "entropy": 1.019489830173552,
+      "epoch": 1.2813108551716463,
+      "grad_norm": 0.703125,
+      "learning_rate": 1.1562962962962964e-05,
+      "loss": 0.9347,
+      "mean_token_accuracy": 0.7539405088871718,
+      "num_tokens": 19128237.0,
+      "step": 1440
+    },
+    {
+      "entropy": 0.9920928861945868,
+      "epoch": 1.2902130974239137,
+      "grad_norm": 0.734375,
+      "learning_rate": 1.1488888888888889e-05,
+      "loss": 0.9134,
+      "mean_token_accuracy": 0.7595972217619419,
+      "num_tokens": 19270694.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.9608436211943626,
+      "epoch": 1.299115339676181,
+      "grad_norm": 0.66015625,
+      "learning_rate": 1.1414814814814817e-05,
+      "loss": 0.8802,
+      "mean_token_accuracy": 0.7658909805119037,
+      "num_tokens": 19405981.0,
+      "step": 1460
+    },
+    {
+      "entropy": 0.983773030154407,
+      "epoch": 1.3080175819284483,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.1340740740740742e-05,
+      "loss": 0.8906,
+      "mean_token_accuracy": 0.7623354118317366,
+      "num_tokens": 19540569.0,
+      "step": 1470
+    },
+    {
+      "entropy": 0.9917311523109674,
+      "epoch": 1.3169198241807156,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.1266666666666668e-05,
+      "loss": 0.9105,
+      "mean_token_accuracy": 0.7595894075930119,
+      "num_tokens": 19670336.0,
+      "step": 1480
+    },
+    {
+      "entropy": 1.0092295063659549,
+      "epoch": 1.3258220664329827,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.1192592592592593e-05,
+      "loss": 0.8987,
+      "mean_token_accuracy": 0.7556359302252531,
+      "num_tokens": 19801983.0,
+      "step": 1490
+    },
+    {
+      "entropy": 0.9918091669678688,
+      "epoch": 1.33472430868525,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.111851851851852e-05,
+      "loss": 0.8973,
+      "mean_token_accuracy": 0.7591681893914938,
+      "num_tokens": 19931729.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.33472430868525,
+      "eval_biology_entropy": 2.0258102512359617,
+      "eval_biology_loss": 2.131002187728882,
+      "eval_biology_mean_token_accuracy": 0.5611058915853501,
+      "eval_biology_num_tokens": 19931729.0,
+      "eval_biology_runtime": 18.8477,
+      "eval_biology_samples_per_second": 26.528,
+      "eval_biology_steps_per_second": 13.264,
+      "step": 1500
+    },
+    {
+      "epoch": 1.33472430868525,
+      "eval_chemistry_entropy": 1.0114747372865678,
+      "eval_chemistry_loss": 0.9682854413986206,
+      "eval_chemistry_mean_token_accuracy": 0.7523500380516053,
+      "eval_chemistry_num_tokens": 19931729.0,
+      "eval_chemistry_runtime": 23.8184,
+      "eval_chemistry_samples_per_second": 20.992,
+      "eval_chemistry_steps_per_second": 10.496,
+      "step": 1500
+    },
+    {
+      "epoch": 1.33472430868525,
+      "eval_math_entropy": 0.9300646790266037,
+      "eval_math_loss": 1.1255069971084595,
+      "eval_math_mean_token_accuracy": 0.7304130113124847,
+      "eval_math_num_tokens": 19931729.0,
+      "eval_math_runtime": 24.2831,
+      "eval_math_samples_per_second": 20.59,
+      "eval_math_steps_per_second": 10.295,
+      "step": 1500
+    },
+    {
+      "epoch": 1.33472430868525,
+      "eval_physics_entropy": 1.0275612835884094,
+      "eval_physics_loss": 1.0034619569778442,
+      "eval_physics_mean_token_accuracy": 0.7499863088130951,
+      "eval_physics_num_tokens": 19931729.0,
+      "eval_physics_runtime": 28.889,
+      "eval_physics_samples_per_second": 17.308,
+      "eval_physics_steps_per_second": 8.654,
+      "step": 1500
+    },
+    {
+      "entropy": 1.0401024248450994,
+      "epoch": 1.3436265509375174,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.1044444444444444e-05,
+      "loss": 0.9414,
+      "mean_token_accuracy": 0.7487192116677761,
+      "num_tokens": 20062157.0,
+      "step": 1510
+    },
+    {
+      "entropy": 0.9860046286135912,
+      "epoch": 1.3525287931897847,
+      "grad_norm": 0.734375,
+      "learning_rate": 1.0970370370370371e-05,
+      "loss": 0.8975,
+      "mean_token_accuracy": 0.7605720847845078,
+      "num_tokens": 20192459.0,
+      "step": 1520
+    },
+    {
+      "entropy": 1.0068744245916605,
+      "epoch": 1.361431035442052,
+      "grad_norm": 0.7578125,
+      "learning_rate": 1.0896296296296298e-05,
+      "loss": 0.9141,
+      "mean_token_accuracy": 0.7565324511379004,
+      "num_tokens": 20322306.0,
+      "step": 1530
+    },
+    {
+      "entropy": 0.9997985826805234,
+      "epoch": 1.3703332776943191,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.0822222222222222e-05,
+      "loss": 0.9094,
+      "mean_token_accuracy": 0.7578164864331484,
+      "num_tokens": 20457368.0,
+      "step": 1540
+    },
+    {
+      "entropy": 1.042620269395411,
+      "epoch": 1.3792355199465867,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.074814814814815e-05,
+      "loss": 0.9649,
+      "mean_token_accuracy": 0.7502748232334853,
+      "num_tokens": 20582646.0,
+      "step": 1550
+    },
+    {
+      "entropy": 1.0267199439927936,
+      "epoch": 1.3881377621988538,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.0674074074074074e-05,
+      "loss": 0.9329,
+      "mean_token_accuracy": 0.7522567234933376,
+      "num_tokens": 20711114.0,
+      "step": 1560
+    },
+    {
+      "entropy": 1.0233941435813905,
+      "epoch": 1.397040004451121,
+      "grad_norm": 0.76171875,
+      "learning_rate": 1.0600000000000002e-05,
+      "loss": 0.9285,
+      "mean_token_accuracy": 0.7541898198425769,
+      "num_tokens": 20842639.0,
+      "step": 1570
+    },
+    {
+      "entropy": 1.0475757207721472,
+      "epoch": 1.4059422467033884,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.0525925925925927e-05,
+      "loss": 0.9631,
+      "mean_token_accuracy": 0.7465129170566798,
+      "num_tokens": 20974218.0,
+      "step": 1580
+    },
+    {
+      "entropy": 1.0215191347524524,
+      "epoch": 1.4148444889556557,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.0451851851851853e-05,
+      "loss": 0.924,
+      "mean_token_accuracy": 0.7544053990393877,
+      "num_tokens": 21106470.0,
+      "step": 1590
+    },
+    {
+      "entropy": 1.002201915718615,
+      "epoch": 1.423746731207923,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.0377777777777778e-05,
+      "loss": 0.9119,
+      "mean_token_accuracy": 0.7578132838010788,
+      "num_tokens": 21241744.0,
+      "step": 1600
+    },
+    {
+      "epoch": 1.423746731207923,
+      "eval_biology_entropy": 2.025591229200363,
+      "eval_biology_loss": 2.1277236938476562,
+      "eval_biology_mean_token_accuracy": 0.5615192129611969,
+      "eval_biology_num_tokens": 21241744.0,
+      "eval_biology_runtime": 18.902,
+      "eval_biology_samples_per_second": 26.452,
+      "eval_biology_steps_per_second": 13.226,
+      "step": 1600
+    },
+    {
+      "epoch": 1.423746731207923,
+      "eval_chemistry_entropy": 1.0093150942325593,
+      "eval_chemistry_loss": 0.966478168964386,
+      "eval_chemistry_mean_token_accuracy": 0.752682238817215,
+      "eval_chemistry_num_tokens": 21241744.0,
+      "eval_chemistry_runtime": 24.0359,
+      "eval_chemistry_samples_per_second": 20.802,
+      "eval_chemistry_steps_per_second": 10.401,
+      "step": 1600
+    },
+    {
+      "epoch": 1.423746731207923,
+      "eval_math_entropy": 0.9292137649059296,
+      "eval_math_loss": 1.1244679689407349,
+      "eval_math_mean_token_accuracy": 0.7306574966907501,
+      "eval_math_num_tokens": 21241744.0,
+      "eval_math_runtime": 24.4447,
+      "eval_math_samples_per_second": 20.454,
+      "eval_math_steps_per_second": 10.227,
+      "step": 1600
+    },
+    {
+      "epoch": 1.423746731207923,
+      "eval_physics_entropy": 1.026391778230667,
+      "eval_physics_loss": 1.0021922588348389,
+      "eval_physics_mean_token_accuracy": 0.750161004781723,
+      "eval_physics_num_tokens": 21241744.0,
+      "eval_physics_runtime": 28.6013,
+      "eval_physics_samples_per_second": 17.482,
+      "eval_physics_steps_per_second": 8.741,
+      "step": 1600
+    },
+    {
+      "entropy": 1.03016886562109,
+      "epoch": 1.4326489734601902,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.0303703703703705e-05,
+      "loss": 0.9359,
+      "mean_token_accuracy": 0.7508798144757748,
+      "num_tokens": 21376863.0,
+      "step": 1610
+    },
+    {
+      "entropy": 0.9919080374762416,
+      "epoch": 1.4415512157124577,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.0229629629629631e-05,
+      "loss": 0.9179,
+      "mean_token_accuracy": 0.7578859634697437,
+      "num_tokens": 21513583.0,
+      "step": 1620
+    },
+    {
+      "entropy": 1.022333799675107,
+      "epoch": 1.4504534579647248,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.0155555555555556e-05,
+      "loss": 0.9256,
+      "mean_token_accuracy": 0.7530937936156988,
+      "num_tokens": 21638317.0,
+      "step": 1630
+    },
+    {
+      "entropy": 0.9792770128697157,
+      "epoch": 1.4593557002169921,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.0081481481481484e-05,
+      "loss": 0.8994,
+      "mean_token_accuracy": 0.7637054190039635,
+      "num_tokens": 21767025.0,
+      "step": 1640
+    },
+    {
+      "entropy": 1.0167023092508316,
+      "epoch": 1.4682579424692594,
+      "grad_norm": 0.796875,
+      "learning_rate": 1.0007407407407407e-05,
+      "loss": 0.9227,
+      "mean_token_accuracy": 0.7549007095396518,
+      "num_tokens": 21897527.0,
+      "step": 1650
+    },
+    {
+      "entropy": 1.0218092637136578,
+      "epoch": 1.4771601847215268,
+      "grad_norm": 0.703125,
+      "learning_rate": 9.933333333333334e-06,
+      "loss": 0.9285,
+      "mean_token_accuracy": 0.7508806932717562,
+      "num_tokens": 22033346.0,
+      "step": 1660
+    },
+    {
+      "entropy": 1.031794124469161,
+      "epoch": 1.486062426973794,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.85925925925926e-06,
+      "loss": 0.9464,
+      "mean_token_accuracy": 0.7501063853502273,
+      "num_tokens": 22167509.0,
+      "step": 1670
+    },
+    {
+      "entropy": 1.0033700566738843,
+      "epoch": 1.4949646692260612,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.785185185185187e-06,
+      "loss": 0.9006,
+      "mean_token_accuracy": 0.7571231830865145,
+      "num_tokens": 22300536.0,
+      "step": 1680
+    },
+    {
+      "entropy": 1.008541435562074,
+      "epoch": 1.5038669114783287,
+      "grad_norm": 0.671875,
+      "learning_rate": 9.711111111111111e-06,
+      "loss": 0.9365,
+      "mean_token_accuracy": 0.7536230113357305,
+      "num_tokens": 22435726.0,
+      "step": 1690
+    },
+    {
+      "entropy": 0.992847067117691,
+      "epoch": 1.5127691537305958,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.637037037037038e-06,
+      "loss": 0.8937,
+      "mean_token_accuracy": 0.7610627774149179,
+      "num_tokens": 22565589.0,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5127691537305958,
+      "eval_biology_entropy": 2.0122655897140502,
+      "eval_biology_loss": 2.1256110668182373,
+      "eval_biology_mean_token_accuracy": 0.5618942753076553,
+      "eval_biology_num_tokens": 22565589.0,
+      "eval_biology_runtime": 18.9124,
+      "eval_biology_samples_per_second": 26.438,
+      "eval_biology_steps_per_second": 13.219,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5127691537305958,
+      "eval_chemistry_entropy": 1.0036332979202272,
+      "eval_chemistry_loss": 0.9652226567268372,
+      "eval_chemistry_mean_token_accuracy": 0.7529698076248169,
+      "eval_chemistry_num_tokens": 22565589.0,
+      "eval_chemistry_runtime": 24.0396,
+      "eval_chemistry_samples_per_second": 20.799,
+      "eval_chemistry_steps_per_second": 10.4,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5127691537305958,
+      "eval_math_entropy": 0.9236747875213623,
+      "eval_math_loss": 1.1252063512802124,
+      "eval_math_mean_token_accuracy": 0.7303525774478913,
+      "eval_math_num_tokens": 22565589.0,
+      "eval_math_runtime": 24.5159,
+      "eval_math_samples_per_second": 20.395,
+      "eval_math_steps_per_second": 10.197,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5127691537305958,
+      "eval_physics_entropy": 1.0204626792669296,
+      "eval_physics_loss": 1.0009655952453613,
+      "eval_physics_mean_token_accuracy": 0.7503002121448517,
+      "eval_physics_num_tokens": 22565589.0,
+      "eval_physics_runtime": 28.693,
+      "eval_physics_samples_per_second": 17.426,
+      "eval_physics_steps_per_second": 8.713,
+      "step": 1700
+    },
+    {
+      "entropy": 0.9994206981733441,
+      "epoch": 1.5216713959828632,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.562962962962965e-06,
+      "loss": 0.9023,
+      "mean_token_accuracy": 0.7591567263007164,
+      "num_tokens": 22698686.0,
+      "step": 1710
+    },
+    {
+      "entropy": 0.9683190802112221,
+      "epoch": 1.5305736382351305,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.48888888888889e-06,
+      "loss": 0.882,
+      "mean_token_accuracy": 0.7618000447750092,
+      "num_tokens": 22834474.0,
+      "step": 1720
+    },
+    {
+      "entropy": 1.0202100694179534,
+      "epoch": 1.5394758804873978,
+      "grad_norm": 0.8203125,
+      "learning_rate": 9.414814814814816e-06,
+      "loss": 0.9256,
+      "mean_token_accuracy": 0.7522198557853699,
+      "num_tokens": 22961658.0,
+      "step": 1730
+    },
+    {
+      "entropy": 0.9988253280520439,
+      "epoch": 1.5483781227396651,
+      "grad_norm": 0.76953125,
+      "learning_rate": 9.34074074074074e-06,
+      "loss": 0.9089,
+      "mean_token_accuracy": 0.7570457577705383,
+      "num_tokens": 23088024.0,
+      "step": 1740
+    },
+    {
+      "entropy": 0.9920793252065778,
+      "epoch": 1.5572803649919322,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.266666666666667e-06,
+      "loss": 0.8947,
+      "mean_token_accuracy": 0.7595769252628088,
+      "num_tokens": 23216202.0,
+      "step": 1750
+    },
+    {
+      "entropy": 1.0168918997049332,
+      "epoch": 1.5661826072441998,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.192592592592594e-06,
+      "loss": 0.9303,
+      "mean_token_accuracy": 0.7543978549540042,
+      "num_tokens": 23352254.0,
+      "step": 1760
+    },
+    {
+      "entropy": 1.0322391271591187,
+      "epoch": 1.5750848494964669,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.118518518518518e-06,
+      "loss": 0.9284,
+      "mean_token_accuracy": 0.7508225381374359,
+      "num_tokens": 23482862.0,
+      "step": 1770
+    },
+    {
+      "entropy": 1.005371204018593,
+      "epoch": 1.5839870917487342,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.044444444444445e-06,
+      "loss": 0.8995,
+      "mean_token_accuracy": 0.7587582629173995,
+      "num_tokens": 23618698.0,
+      "step": 1780
+    },
+    {
+      "entropy": 1.0004733871668576,
+      "epoch": 1.5928893340010015,
+      "grad_norm": 0.69140625,
+      "learning_rate": 8.970370370370372e-06,
+      "loss": 0.9164,
+      "mean_token_accuracy": 0.7546517603099346,
+      "num_tokens": 23752957.0,
+      "step": 1790
+    },
+    {
+      "entropy": 0.9979297908022999,
+      "epoch": 1.6017915762532688,
+      "grad_norm": 0.8984375,
+      "learning_rate": 8.896296296296298e-06,
+      "loss": 0.9195,
+      "mean_token_accuracy": 0.7555133253335953,
+      "num_tokens": 23880415.0,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6017915762532688,
+      "eval_biology_entropy": 2.0173105149269106,
+      "eval_biology_loss": 2.1241087913513184,
+      "eval_biology_mean_token_accuracy": 0.562729345202446,
+      "eval_biology_num_tokens": 23880415.0,
+      "eval_biology_runtime": 18.9444,
+      "eval_biology_samples_per_second": 26.393,
+      "eval_biology_steps_per_second": 13.197,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6017915762532688,
+      "eval_chemistry_entropy": 1.0052111333608627,
+      "eval_chemistry_loss": 0.9641526937484741,
+      "eval_chemistry_mean_token_accuracy": 0.7533584263324737,
+      "eval_chemistry_num_tokens": 23880415.0,
+      "eval_chemistry_runtime": 24.0831,
+      "eval_chemistry_samples_per_second": 20.761,
+      "eval_chemistry_steps_per_second": 10.381,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6017915762532688,
+      "eval_math_entropy": 0.9254970207214356,
+      "eval_math_loss": 1.1230454444885254,
+      "eval_math_mean_token_accuracy": 0.7310211069583893,
+      "eval_math_num_tokens": 23880415.0,
+      "eval_math_runtime": 25.0685,
+      "eval_math_samples_per_second": 19.945,
+      "eval_math_steps_per_second": 9.973,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6017915762532688,
+      "eval_physics_entropy": 1.0226905109882354,
+      "eval_physics_loss": 1.0000629425048828,
+      "eval_physics_mean_token_accuracy": 0.7504880855083466,
+      "eval_physics_num_tokens": 23880415.0,
+      "eval_physics_runtime": 28.6499,
+      "eval_physics_samples_per_second": 17.452,
+      "eval_physics_steps_per_second": 8.726,
+      "step": 1800
+    },
+    {
+      "entropy": 0.9905398432165384,
+      "epoch": 1.6106938185055362,
+      "grad_norm": 0.609375,
+      "learning_rate": 8.822222222222223e-06,
+      "loss": 0.9055,
+      "mean_token_accuracy": 0.7605366300791502,
+      "num_tokens": 24017017.0,
+      "step": 1810
+    },
+    {
+      "entropy": 0.9657800393179059,
+      "epoch": 1.6195960607578033,
+      "grad_norm": 0.77734375,
+      "learning_rate": 8.74814814814815e-06,
+      "loss": 0.8826,
+      "mean_token_accuracy": 0.7643621765077114,
+      "num_tokens": 24157031.0,
+      "step": 1820
+    },
+    {
+      "entropy": 1.0321623418480157,
+      "epoch": 1.6284983030100708,
+      "grad_norm": 0.85546875,
+      "learning_rate": 8.674074074074074e-06,
+      "loss": 0.9368,
+      "mean_token_accuracy": 0.7502922285348177,
+      "num_tokens": 24283018.0,
+      "step": 1830
+    },
+    {
+      "entropy": 0.9933631762862205,
+      "epoch": 1.637400545262338,
+      "grad_norm": 0.75,
+      "learning_rate": 8.6e-06,
+      "loss": 0.8993,
+      "mean_token_accuracy": 0.7593170210719109,
+      "num_tokens": 24409888.0,
+      "step": 1840
+    },
+    {
+      "entropy": 0.9827067364007235,
+      "epoch": 1.6463027875146052,
+      "grad_norm": 0.75390625,
+      "learning_rate": 8.525925925925927e-06,
+      "loss": 0.8786,
+      "mean_token_accuracy": 0.762890399619937,
+      "num_tokens": 24543826.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.950797894410789,
+      "epoch": 1.6552050297668726,
+      "grad_norm": 0.71484375,
+      "learning_rate": 8.451851851851852e-06,
+      "loss": 0.8684,
+      "mean_token_accuracy": 0.7690653670579195,
+      "num_tokens": 24678800.0,
+      "step": 1860
+    },
+    {
+      "entropy": 0.995796344988048,
+      "epoch": 1.6641072720191397,
+      "grad_norm": 0.68359375,
+      "learning_rate": 8.377777777777779e-06,
+      "loss": 0.8925,
+      "mean_token_accuracy": 0.7603240333497524,
+      "num_tokens": 24815214.0,
+      "step": 1870
+    },
+    {
+      "entropy": 1.0053923385217787,
+      "epoch": 1.6730095142714072,
+      "grad_norm": 0.73046875,
+      "learning_rate": 8.303703703703705e-06,
+      "loss": 0.9142,
+      "mean_token_accuracy": 0.7559387862682343,
+      "num_tokens": 24946978.0,
+      "step": 1880
+    },
+    {
+      "entropy": 1.0206347620114684,
+      "epoch": 1.6819117565236743,
+      "grad_norm": 0.8125,
+      "learning_rate": 8.229629629629632e-06,
+      "loss": 0.9438,
+      "mean_token_accuracy": 0.7511203195899725,
+      "num_tokens": 25077886.0,
+      "step": 1890
+    },
+    {
+      "entropy": 0.9430066786706448,
+      "epoch": 1.6908139987759419,
+      "grad_norm": 0.75,
+      "learning_rate": 8.155555555555556e-06,
+      "loss": 0.8636,
+      "mean_token_accuracy": 0.7684857059270144,
+      "num_tokens": 25212156.0,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6908139987759419,
+      "eval_biology_entropy": 2.0157932362556457,
+      "eval_biology_loss": 2.122405529022217,
+      "eval_biology_mean_token_accuracy": 0.5626547236442566,
+      "eval_biology_num_tokens": 25212156.0,
+      "eval_biology_runtime": 18.9641,
+      "eval_biology_samples_per_second": 26.366,
+      "eval_biology_steps_per_second": 13.183,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6908139987759419,
+      "eval_chemistry_entropy": 1.0041394897699356,
+      "eval_chemistry_loss": 0.9633175134658813,
+      "eval_chemistry_mean_token_accuracy": 0.7533679773807526,
+      "eval_chemistry_num_tokens": 25212156.0,
+      "eval_chemistry_runtime": 24.0415,
+      "eval_chemistry_samples_per_second": 20.797,
+      "eval_chemistry_steps_per_second": 10.399,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6908139987759419,
+      "eval_math_entropy": 0.9244353786706925,
+      "eval_math_loss": 1.1229627132415771,
+      "eval_math_mean_token_accuracy": 0.731002632856369,
+      "eval_math_num_tokens": 25212156.0,
+      "eval_math_runtime": 24.5063,
+      "eval_math_samples_per_second": 20.403,
+      "eval_math_steps_per_second": 10.201,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6908139987759419,
+      "eval_physics_entropy": 1.0216196060180665,
+      "eval_physics_loss": 0.9995249509811401,
+      "eval_physics_mean_token_accuracy": 0.750792946100235,
+      "eval_physics_num_tokens": 25212156.0,
+      "eval_physics_runtime": 28.7095,
+      "eval_physics_samples_per_second": 17.416,
+      "eval_physics_steps_per_second": 8.708,
+      "step": 1900
+    },
+    {
+      "entropy": 0.9993637457489968,
+      "epoch": 1.699716241028209,
+      "grad_norm": 0.69921875,
+      "learning_rate": 8.081481481481483e-06,
+      "loss": 0.8938,
+      "mean_token_accuracy": 0.759690074622631,
+      "num_tokens": 25345426.0,
+      "step": 1910
+    },
+    {
+      "entropy": 1.0246091675013305,
+      "epoch": 1.7086184832804763,
+      "grad_norm": 0.80078125,
+      "learning_rate": 8.007407407407408e-06,
+      "loss": 0.9378,
+      "mean_token_accuracy": 0.7524834290146828,
+      "num_tokens": 25469260.0,
+      "step": 1920
+    },
+    {
+      "entropy": 1.0245067680254578,
+      "epoch": 1.7175207255327436,
+      "grad_norm": 0.6640625,
+      "learning_rate": 7.933333333333334e-06,
+      "loss": 0.9315,
+      "mean_token_accuracy": 0.7509147390723229,
+      "num_tokens": 25601251.0,
+      "step": 1930
+    },
+    {
+      "entropy": 1.0039795268326999,
+      "epoch": 1.7264229677850107,
+      "grad_norm": 0.72265625,
+      "learning_rate": 7.859259259259259e-06,
+      "loss": 0.9036,
+      "mean_token_accuracy": 0.7555113852024078,
+      "num_tokens": 25730811.0,
+      "step": 1940
+    },
+    {
+      "entropy": 0.9806737070903182,
+      "epoch": 1.7353252100372782,
+      "grad_norm": 0.68359375,
+      "learning_rate": 7.785185185185185e-06,
+      "loss": 0.9032,
+      "mean_token_accuracy": 0.7609169717878104,
+      "num_tokens": 25867878.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.9942740418016911,
+      "epoch": 1.7442274522895453,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.711111111111112e-06,
+      "loss": 0.9016,
+      "mean_token_accuracy": 0.7598113764077425,
+      "num_tokens": 25998521.0,
+      "step": 1960
+    },
+    {
+      "entropy": 0.9879547640681267,
+      "epoch": 1.7531296945418127,
+      "grad_norm": 0.7734375,
+      "learning_rate": 7.637037037037037e-06,
+      "loss": 0.8935,
+      "mean_token_accuracy": 0.761596117913723,
+      "num_tokens": 26135246.0,
+      "step": 1970
+    },
+    {
+      "entropy": 0.9436089185997844,
+      "epoch": 1.76203193679408,
+      "grad_norm": 0.73828125,
+      "learning_rate": 7.562962962962963e-06,
+      "loss": 0.8681,
+      "mean_token_accuracy": 0.7667636949568987,
+      "num_tokens": 26266131.0,
+      "step": 1980
+    },
+    {
+      "entropy": 0.9930436752736569,
+      "epoch": 1.7709341790463473,
+      "grad_norm": 0.625,
+      "learning_rate": 7.48888888888889e-06,
+      "loss": 0.9035,
+      "mean_token_accuracy": 0.7570448875427246,
+      "num_tokens": 26401317.0,
+      "step": 1990
+    },
+    {
+      "entropy": 0.9844840195029974,
+      "epoch": 1.7798364212986146,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.4148148148148155e-06,
+      "loss": 0.8806,
+      "mean_token_accuracy": 0.7603437446057797,
+      "num_tokens": 26530594.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7798364212986146,
+      "eval_biology_entropy": 2.0130158250331878,
+      "eval_biology_loss": 2.1220955848693848,
+      "eval_biology_mean_token_accuracy": 0.5627384769916535,
+      "eval_biology_num_tokens": 26530594.0,
+      "eval_biology_runtime": 19.0207,
+      "eval_biology_samples_per_second": 26.287,
+      "eval_biology_steps_per_second": 13.144,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7798364212986146,
+      "eval_chemistry_entropy": 1.0035682756900788,
+      "eval_chemistry_loss": 0.9626900553703308,
+      "eval_chemistry_mean_token_accuracy": 0.7535324826240539,
+      "eval_chemistry_num_tokens": 26530594.0,
+      "eval_chemistry_runtime": 23.9451,
+      "eval_chemistry_samples_per_second": 20.881,
+      "eval_chemistry_steps_per_second": 10.441,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7798364212986146,
+      "eval_math_entropy": 0.9233778233528137,
+      "eval_math_loss": 1.1230123043060303,
+      "eval_math_mean_token_accuracy": 0.7310037231445312,
+      "eval_math_num_tokens": 26530594.0,
+      "eval_math_runtime": 24.4147,
+      "eval_math_samples_per_second": 20.48,
+      "eval_math_steps_per_second": 10.24,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7798364212986146,
+      "eval_physics_entropy": 1.020226985692978,
+      "eval_physics_loss": 0.9989672303199768,
+      "eval_physics_mean_token_accuracy": 0.7507679476737976,
+      "eval_physics_num_tokens": 26530594.0,
+      "eval_physics_runtime": 28.6625,
+      "eval_physics_samples_per_second": 17.444,
+      "eval_physics_steps_per_second": 8.722,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3000,
+  "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": 1.4034704980628767e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb9a34e89b7d8c95a81493eb6544aba0518c88426dff960a23b34fb84d634b2
+size 6481