Upload folder using huggingface_hub

checkpoint-500/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-500/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-500/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-500/model-00001-of-00003.safetensors

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

checkpoint-500/model-00002-of-00003.safetensors

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

checkpoint-500/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2294f1e00f49d02b95a07172c2e0810801dc984f0e4f95d99d1e6d402c0c0e6
+size 4645523448

checkpoint-500/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-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342d409984b77f9a3c8d058030dc2c2076f46f2c9f89ae192a139db39e2008ae
+size 3263319914

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd74ad34e3c5060506b53a8a3fafbfb35d44065ee496b2abf3a0b9a3b93ba09
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc00081d4f892d131a0d2b4d4827a214275362bfa62dfb8413f489c1bfad457
+size 1465

checkpoint-500/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-500/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-500/trainer_state.json

@@ -0,0 +1,754 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4451121126133645,
+  "eval_steps": 100,
+  "global_step": 500,
+  "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
+    }
+  ],
+  "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": 3.508671492730061e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

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