Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,4 @@ checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2500/chat_template.jinja

@@ -0,0 +1,4 @@
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
+' + message['content'] | trim + '<end_of_turn>
+' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
+'}}{% endif %}

checkpoint-2500/config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 256000
+}

checkpoint-2500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    1
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.56.1"
+}

checkpoint-2500/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d4eb4fcbddfe01b0dc7a58386a3980826ededaf0ecd67d1ef38995b89615ba
+size 4903351912

checkpoint-2500/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712a589c333f49f7b6f3870838a9e0ab4b3c0260abd5130e8c54316e6c99640b
+size 4947570872

checkpoint-2500/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75bff1c6ab962a6d81cb81c7f3427386ed49e866c71e81e80ea55e0a8a83952a
+size 4962221464

checkpoint-2500/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6763008b4e6ba8fdc1b129ba710fc593f60b09eee5683e6bc0c2a7f2d5e47f0b
+size 3670322200

checkpoint-2500/model.safetensors.index.json

@@ -0,0 +1,472 @@
+{
+  "metadata": {
+    "total_parameters": 9241705984,
+    "total_size": 18483411968
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a166a7a6d7233a2d46b086ef1a778939c883dff73a93191a67c997fec535001
+size 1585596266

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7edf23f0cef681f30485dc71955f6a675cc4e0dbf22e0ed44c7452b774c627
+size 14645

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd200143f139327b4d41bcb99ffeaa13b2acc11ded5b3dbab181a6ff2ce855d7
+size 1465

checkpoint-2500/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

checkpoint-2500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-2500/trainer_state.json

@@ -0,0 +1,3084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.9888,
+  "eval_steps": 100,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.528095572441816,
+      "epoch": 0.032,
+      "grad_norm": 251.0,
+      "learning_rate": 1.8e-07,
+      "loss": 6.6082,
+      "mean_token_accuracy": 0.21971591785550118,
+      "num_tokens": 166758.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.540951229631901,
+      "epoch": 0.064,
+      "grad_norm": 255.0,
+      "learning_rate": 3.8e-07,
+      "loss": 6.521,
+      "mean_token_accuracy": 0.22138903560116888,
+      "num_tokens": 333231.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.5206488400697706,
+      "epoch": 0.096,
+      "grad_norm": 260.0,
+      "learning_rate": 5.800000000000001e-07,
+      "loss": 6.4223,
+      "mean_token_accuracy": 0.22258271211758257,
+      "num_tokens": 494697.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.5920443564653395,
+      "epoch": 0.128,
+      "grad_norm": 243.0,
+      "learning_rate": 7.8e-07,
+      "loss": 6.2586,
+      "mean_token_accuracy": 0.22078513531014324,
+      "num_tokens": 665636.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.7184064492583273,
+      "epoch": 0.16,
+      "grad_norm": 188.0,
+      "learning_rate": 9.800000000000001e-07,
+      "loss": 5.9925,
+      "mean_token_accuracy": 0.21972714476287364,
+      "num_tokens": 831010.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.7776166409254075,
+      "epoch": 0.192,
+      "grad_norm": 141.0,
+      "learning_rate": 1.1800000000000001e-06,
+      "loss": 5.3252,
+      "mean_token_accuracy": 0.23665523305535316,
+      "num_tokens": 997538.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.8701344512403013,
+      "epoch": 0.224,
+      "grad_norm": 80.5,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 4.6962,
+      "mean_token_accuracy": 0.26214539231732487,
+      "num_tokens": 1166249.0,
+      "step": 70
+    },
+    {
+      "entropy": 3.226949879527092,
+      "epoch": 0.256,
+      "grad_norm": 54.25,
+      "learning_rate": 1.5800000000000001e-06,
+      "loss": 4.2438,
+      "mean_token_accuracy": 0.2808788095600903,
+      "num_tokens": 1332878.0,
+      "step": 80
+    },
+    {
+      "entropy": 3.3381400883197783,
+      "epoch": 0.288,
+      "grad_norm": 35.75,
+      "learning_rate": 1.7800000000000001e-06,
+      "loss": 3.7944,
+      "mean_token_accuracy": 0.31892537530511617,
+      "num_tokens": 1499929.0,
+      "step": 90
+    },
+    {
+      "entropy": 3.3039391934871674,
+      "epoch": 0.32,
+      "grad_norm": 23.625,
+      "learning_rate": 1.98e-06,
+      "loss": 3.4785,
+      "mean_token_accuracy": 0.34879792630672457,
+      "num_tokens": 1660639.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "eval_coding_entropy": 1.9907222771644593,
+      "eval_coding_loss": 2.2322070598602295,
+      "eval_coding_mean_token_accuracy": 0.49504432117938996,
+      "eval_coding_num_tokens": 1660639.0,
+      "eval_coding_runtime": 80.8983,
+      "eval_coding_samples_per_second": 6.181,
+      "eval_coding_steps_per_second": 3.09,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "eval_physics_entropy": 3.267650173187256,
+      "eval_physics_loss": 3.3989615440368652,
+      "eval_physics_mean_token_accuracy": 0.35563090866804126,
+      "eval_physics_num_tokens": 1660639.0,
+      "eval_physics_runtime": 51.1457,
+      "eval_physics_samples_per_second": 9.776,
+      "eval_physics_steps_per_second": 4.888,
+      "step": 100
+    },
+    {
+      "entropy": 3.207504133880138,
+      "epoch": 0.352,
+      "grad_norm": 22.875,
+      "learning_rate": 2.1800000000000003e-06,
+      "loss": 3.2646,
+      "mean_token_accuracy": 0.36884861923754214,
+      "num_tokens": 1827104.0,
+      "step": 110
+    },
+    {
+      "entropy": 3.0256898537278176,
+      "epoch": 0.384,
+      "grad_norm": 17.625,
+      "learning_rate": 2.38e-06,
+      "loss": 3.0598,
+      "mean_token_accuracy": 0.393247177824378,
+      "num_tokens": 1991838.0,
+      "step": 120
+    },
+    {
+      "entropy": 2.9381186082959174,
+      "epoch": 0.416,
+      "grad_norm": 16.5,
+      "learning_rate": 2.5800000000000003e-06,
+      "loss": 2.9254,
+      "mean_token_accuracy": 0.41124203372746704,
+      "num_tokens": 2160667.0,
+      "step": 130
+    },
+    {
+      "entropy": 2.8182168558239935,
+      "epoch": 0.448,
+      "grad_norm": 15.625,
+      "learning_rate": 2.7800000000000005e-06,
+      "loss": 2.8359,
+      "mean_token_accuracy": 0.42758033741265533,
+      "num_tokens": 2318749.0,
+      "step": 140
+    },
+    {
+      "entropy": 2.7808817446231844,
+      "epoch": 0.48,
+      "grad_norm": 17.0,
+      "learning_rate": 2.9800000000000003e-06,
+      "loss": 2.7479,
+      "mean_token_accuracy": 0.43509358577430246,
+      "num_tokens": 2485149.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.71549072638154,
+      "epoch": 0.512,
+      "grad_norm": 14.0,
+      "learning_rate": 3.1800000000000005e-06,
+      "loss": 2.6955,
+      "mean_token_accuracy": 0.45029620360583067,
+      "num_tokens": 2649860.0,
+      "step": 160
+    },
+    {
+      "entropy": 2.6384543806314467,
+      "epoch": 0.544,
+      "grad_norm": 16.875,
+      "learning_rate": 3.3800000000000007e-06,
+      "loss": 2.6629,
+      "mean_token_accuracy": 0.4562853068113327,
+      "num_tokens": 2808370.0,
+      "step": 170
+    },
+    {
+      "entropy": 2.550112411379814,
+      "epoch": 0.576,
+      "grad_norm": 15.6875,
+      "learning_rate": 3.58e-06,
+      "loss": 2.522,
+      "mean_token_accuracy": 0.46982257775962355,
+      "num_tokens": 2983767.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.522789068520069,
+      "epoch": 0.608,
+      "grad_norm": 15.875,
+      "learning_rate": 3.7800000000000002e-06,
+      "loss": 2.5013,
+      "mean_token_accuracy": 0.47677798476070166,
+      "num_tokens": 3155652.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.527734723687172,
+      "epoch": 0.64,
+      "grad_norm": 14.1875,
+      "learning_rate": 3.980000000000001e-06,
+      "loss": 2.5057,
+      "mean_token_accuracy": 0.4807511504739523,
+      "num_tokens": 3318780.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.64,
+      "eval_coding_entropy": 1.9231958236694335,
+      "eval_coding_loss": 2.1203882694244385,
+      "eval_coding_mean_token_accuracy": 0.5172480183839798,
+      "eval_coding_num_tokens": 3318780.0,
+      "eval_coding_runtime": 80.4856,
+      "eval_coding_samples_per_second": 6.212,
+      "eval_coding_steps_per_second": 3.106,
+      "step": 200
+    },
+    {
+      "epoch": 0.64,
+      "eval_physics_entropy": 2.5159819135665895,
+      "eval_physics_loss": 2.5135059356689453,
+      "eval_physics_mean_token_accuracy": 0.4827461049556732,
+      "eval_physics_num_tokens": 3318780.0,
+      "eval_physics_runtime": 51.3771,
+      "eval_physics_samples_per_second": 9.732,
+      "eval_physics_steps_per_second": 4.866,
+      "step": 200
+    },
+    {
+      "entropy": 2.438960626721382,
+      "epoch": 0.672,
+      "grad_norm": 14.0,
+      "learning_rate": 4.18e-06,
+      "loss": 2.4172,
+      "mean_token_accuracy": 0.49055377542972567,
+      "num_tokens": 3487395.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.472309985756874,
+      "epoch": 0.704,
+      "grad_norm": 13.6875,
+      "learning_rate": 4.38e-06,
+      "loss": 2.4486,
+      "mean_token_accuracy": 0.49062253087759017,
+      "num_tokens": 3651864.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.414797979593277,
+      "epoch": 0.736,
+      "grad_norm": 14.6875,
+      "learning_rate": 4.58e-06,
+      "loss": 2.3461,
+      "mean_token_accuracy": 0.5045956864953041,
+      "num_tokens": 3818374.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.353023274987936,
+      "epoch": 0.768,
+      "grad_norm": 13.0,
+      "learning_rate": 4.78e-06,
+      "loss": 2.3681,
+      "mean_token_accuracy": 0.4942123286426067,
+      "num_tokens": 3988751.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.416274122148752,
+      "epoch": 0.8,
+      "grad_norm": 14.5625,
+      "learning_rate": 4.980000000000001e-06,
+      "loss": 2.3306,
+      "mean_token_accuracy": 0.5045285696163774,
+      "num_tokens": 4155352.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.281172037869692,
+      "epoch": 0.832,
+      "grad_norm": 15.5,
+      "learning_rate": 5.18e-06,
+      "loss": 2.2632,
+      "mean_token_accuracy": 0.5146352685987949,
+      "num_tokens": 4322729.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.2468128435313703,
+      "epoch": 0.864,
+      "grad_norm": 14.9375,
+      "learning_rate": 5.380000000000001e-06,
+      "loss": 2.2379,
+      "mean_token_accuracy": 0.5204494217410683,
+      "num_tokens": 4488640.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.2410816878080366,
+      "epoch": 0.896,
+      "grad_norm": 16.875,
+      "learning_rate": 5.580000000000001e-06,
+      "loss": 2.1895,
+      "mean_token_accuracy": 0.5250083984807133,
+      "num_tokens": 4652901.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.2374437876045703,
+      "epoch": 0.928,
+      "grad_norm": 14.0625,
+      "learning_rate": 5.78e-06,
+      "loss": 2.2064,
+      "mean_token_accuracy": 0.5245540315285325,
+      "num_tokens": 4816150.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.2606516920030115,
+      "epoch": 0.96,
+      "grad_norm": 19.125,
+      "learning_rate": 5.98e-06,
+      "loss": 2.2002,
+      "mean_token_accuracy": 0.5214386826381088,
+      "num_tokens": 4979460.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.96,
+      "eval_coding_entropy": 1.8473192281723023,
+      "eval_coding_loss": 2.0820884704589844,
+      "eval_coding_mean_token_accuracy": 0.524997807264328,
+      "eval_coding_num_tokens": 4979460.0,
+      "eval_coding_runtime": 80.4582,
+      "eval_coding_samples_per_second": 6.214,
+      "eval_coding_steps_per_second": 3.107,
+      "step": 300
+    },
+    {
+      "epoch": 0.96,
+      "eval_physics_entropy": 2.2321053309440613,
+      "eval_physics_loss": 2.229076623916626,
+      "eval_physics_mean_token_accuracy": 0.5284112887382507,
+      "eval_physics_num_tokens": 4979460.0,
+      "eval_physics_runtime": 51.2237,
+      "eval_physics_samples_per_second": 9.761,
+      "eval_physics_steps_per_second": 4.881,
+      "step": 300
+    },
+    {
+      "entropy": 2.2165822848677634,
+      "epoch": 0.992,
+      "grad_norm": 15.0625,
+      "learning_rate": 6.18e-06,
+      "loss": 2.1527,
+      "mean_token_accuracy": 0.5346193177625537,
+      "num_tokens": 5141579.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.1579121876704064,
+      "epoch": 1.0224,
+      "grad_norm": 14.9375,
+      "learning_rate": 6.380000000000001e-06,
+      "loss": 2.154,
+      "mean_token_accuracy": 0.5380644239485264,
+      "num_tokens": 5293853.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.174650950729847,
+      "epoch": 1.0544,
+      "grad_norm": 15.1875,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 2.0969,
+      "mean_token_accuracy": 0.5382843470200896,
+      "num_tokens": 5468879.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.1786041535437106,
+      "epoch": 1.0864,
+      "grad_norm": 16.375,
+      "learning_rate": 6.780000000000001e-06,
+      "loss": 2.134,
+      "mean_token_accuracy": 0.5381590958684683,
+      "num_tokens": 5631568.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.1562098674476147,
+      "epoch": 1.1184,
+      "grad_norm": 12.8125,
+      "learning_rate": 6.98e-06,
+      "loss": 2.1148,
+      "mean_token_accuracy": 0.5428470510989427,
+      "num_tokens": 5791547.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.059814189374447,
+      "epoch": 1.1504,
+      "grad_norm": 16.25,
+      "learning_rate": 7.180000000000001e-06,
+      "loss": 2.0175,
+      "mean_token_accuracy": 0.5590213229879737,
+      "num_tokens": 5956551.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.0704366780817507,
+      "epoch": 1.1824,
+      "grad_norm": 14.8125,
+      "learning_rate": 7.3800000000000005e-06,
+      "loss": 2.0403,
+      "mean_token_accuracy": 0.5531206054612994,
+      "num_tokens": 6115916.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.0873717822134497,
+      "epoch": 1.2144,
+      "grad_norm": 16.25,
+      "learning_rate": 7.58e-06,
+      "loss": 2.043,
+      "mean_token_accuracy": 0.5543898642063141,
+      "num_tokens": 6276148.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.04577656313777,
+      "epoch": 1.2464,
+      "grad_norm": 13.9375,
+      "learning_rate": 7.78e-06,
+      "loss": 1.993,
+      "mean_token_accuracy": 0.5662586340680719,
+      "num_tokens": 6439971.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.008312249928713,
+      "epoch": 1.2784,
+      "grad_norm": 16.625,
+      "learning_rate": 7.980000000000002e-06,
+      "loss": 1.9767,
+      "mean_token_accuracy": 0.5602528670802712,
+      "num_tokens": 6604463.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.2784,
+      "eval_coding_entropy": 1.8172951374053956,
+      "eval_coding_loss": 2.0788559913635254,
+      "eval_coding_mean_token_accuracy": 0.5274689586162568,
+      "eval_coding_num_tokens": 6604463.0,
+      "eval_coding_runtime": 80.4971,
+      "eval_coding_samples_per_second": 6.211,
+      "eval_coding_steps_per_second": 3.106,
+      "step": 400
+    },
+    {
+      "epoch": 1.2784,
+      "eval_physics_entropy": 2.0293436307907102,
+      "eval_physics_loss": 2.043572425842285,
+      "eval_physics_mean_token_accuracy": 0.559833680510521,
+      "eval_physics_num_tokens": 6604463.0,
+      "eval_physics_runtime": 51.3417,
+      "eval_physics_samples_per_second": 9.739,
+      "eval_physics_steps_per_second": 4.869,
+      "step": 400
+    },
+    {
+      "entropy": 2.016567553579807,
+      "epoch": 1.3104,
+      "grad_norm": 14.3125,
+      "learning_rate": 8.18e-06,
+      "loss": 1.9446,
+      "mean_token_accuracy": 0.5671767380088568,
+      "num_tokens": 6769215.0,
+      "step": 410
+    },
+    {
+      "entropy": 1.9617419019341469,
+      "epoch": 1.3424,
+      "grad_norm": 25.875,
+      "learning_rate": 8.380000000000001e-06,
+      "loss": 1.9262,
+      "mean_token_accuracy": 0.5718308322131633,
+      "num_tokens": 6937523.0,
+      "step": 420
+    },
+    {
+      "entropy": 1.9939539097249508,
+      "epoch": 1.3744,
+      "grad_norm": 17.625,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 1.9598,
+      "mean_token_accuracy": 0.5657142391428351,
+      "num_tokens": 7103833.0,
+      "step": 430
+    },
+    {
+      "entropy": 2.021407524496317,
+      "epoch": 1.4064,
+      "grad_norm": 18.125,
+      "learning_rate": 8.78e-06,
+      "loss": 1.9777,
+      "mean_token_accuracy": 0.5662051374092698,
+      "num_tokens": 7266794.0,
+      "step": 440
+    },
+    {
+      "entropy": 2.0202359184622765,
+      "epoch": 1.4384000000000001,
+      "grad_norm": 14.875,
+      "learning_rate": 8.98e-06,
+      "loss": 1.975,
+      "mean_token_accuracy": 0.5622007481753826,
+      "num_tokens": 7438987.0,
+      "step": 450
+    },
+    {
+      "entropy": 2.0199016578495503,
+      "epoch": 1.4704,
+      "grad_norm": 14.75,
+      "learning_rate": 9.180000000000002e-06,
+      "loss": 1.9361,
+      "mean_token_accuracy": 0.5685023127123714,
+      "num_tokens": 7604024.0,
+      "step": 460
+    },
+    {
+      "entropy": 1.8527320049703122,
+      "epoch": 1.5024,
+      "grad_norm": 14.25,
+      "learning_rate": 9.38e-06,
+      "loss": 1.8364,
+      "mean_token_accuracy": 0.5910809015855193,
+      "num_tokens": 7772263.0,
+      "step": 470
+    },
+    {
+      "entropy": 1.8955925963819027,
+      "epoch": 1.5344,
+      "grad_norm": 13.0625,
+      "learning_rate": 9.58e-06,
+      "loss": 1.8493,
+      "mean_token_accuracy": 0.5856360148638486,
+      "num_tokens": 7944833.0,
+      "step": 480
+    },
+    {
+      "entropy": 1.8996771439909934,
+      "epoch": 1.5664,
+      "grad_norm": 15.125,
+      "learning_rate": 9.780000000000001e-06,
+      "loss": 1.8505,
+      "mean_token_accuracy": 0.5866467090323567,
+      "num_tokens": 8107703.0,
+      "step": 490
+    },
+    {
+      "entropy": 1.8238245747983455,
+      "epoch": 1.5984,
+      "grad_norm": 17.75,
+      "learning_rate": 9.980000000000001e-06,
+      "loss": 1.801,
+      "mean_token_accuracy": 0.5916696371510625,
+      "num_tokens": 8272928.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.5984,
+      "eval_coding_entropy": 1.8537267336845398,
+      "eval_coding_loss": 2.075289011001587,
+      "eval_coding_mean_token_accuracy": 0.5279264715909958,
+      "eval_coding_num_tokens": 8272928.0,
+      "eval_coding_runtime": 80.953,
+      "eval_coding_samples_per_second": 6.176,
+      "eval_coding_steps_per_second": 3.088,
+      "step": 500
+    },
+    {
+      "epoch": 1.5984,
+      "eval_physics_entropy": 1.9223316903114318,
+      "eval_physics_loss": 1.9002431631088257,
+      "eval_physics_mean_token_accuracy": 0.5840845993757248,
+      "eval_physics_num_tokens": 8272928.0,
+      "eval_physics_runtime": 50.845,
+      "eval_physics_samples_per_second": 9.834,
+      "eval_physics_steps_per_second": 4.917,
+      "step": 500
+    },
+    {
+      "entropy": 1.8875005543231964,
+      "epoch": 1.6303999999999998,
+      "grad_norm": 13.5625,
+      "learning_rate": 1.018e-05,
+      "loss": 1.8381,
+      "mean_token_accuracy": 0.5840727794915438,
+      "num_tokens": 8436701.0,
+      "step": 510
+    },
+    {
+      "entropy": 1.9092106647789477,
+      "epoch": 1.6623999999999999,
+      "grad_norm": 16.75,
+      "learning_rate": 1.038e-05,
+      "loss": 1.8575,
+      "mean_token_accuracy": 0.5808946831151843,
+      "num_tokens": 8601859.0,
+      "step": 520
+    },
+    {
+      "entropy": 1.899788486212492,
+      "epoch": 1.6944,
+      "grad_norm": 14.5625,
+      "learning_rate": 1.0580000000000002e-05,
+      "loss": 1.8415,
+      "mean_token_accuracy": 0.5858881402760744,
+      "num_tokens": 8770215.0,
+      "step": 530
+    },
+    {
+      "entropy": 1.7706353828310966,
+      "epoch": 1.7264,
+      "grad_norm": 15.25,
+      "learning_rate": 1.0780000000000002e-05,
+      "loss": 1.7467,
+      "mean_token_accuracy": 0.6009473634883762,
+      "num_tokens": 8943490.0,
+      "step": 540
+    },
+    {
+      "entropy": 1.7995429947972297,
+      "epoch": 1.7584,
+      "grad_norm": 13.4375,
+      "learning_rate": 1.0980000000000002e-05,
+      "loss": 1.7282,
+      "mean_token_accuracy": 0.6000586733222008,
+      "num_tokens": 9105492.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.7555545069277287,
+      "epoch": 1.7904,
+      "grad_norm": 13.625,
+      "learning_rate": 1.1180000000000001e-05,
+      "loss": 1.7087,
+      "mean_token_accuracy": 0.6047776440158487,
+      "num_tokens": 9279120.0,
+      "step": 560
+    },
+    {
+      "entropy": 1.7950463570654391,
+      "epoch": 1.8224,
+      "grad_norm": 14.5625,
+      "learning_rate": 1.138e-05,
+      "loss": 1.7523,
+      "mean_token_accuracy": 0.5999677054584026,
+      "num_tokens": 9449267.0,
+      "step": 570
+    },
+    {
+      "entropy": 1.7747433319687844,
+      "epoch": 1.8544,
+      "grad_norm": 22.25,
+      "learning_rate": 1.1580000000000001e-05,
+      "loss": 1.7373,
+      "mean_token_accuracy": 0.6037633283063769,
+      "num_tokens": 9617568.0,
+      "step": 580
+    },
+    {
+      "entropy": 1.772039385139942,
+      "epoch": 1.8864,
+      "grad_norm": 15.3125,
+      "learning_rate": 1.178e-05,
+      "loss": 1.735,
+      "mean_token_accuracy": 0.606834676489234,
+      "num_tokens": 9784216.0,
+      "step": 590
+    },
+    {
+      "entropy": 1.7735156528651714,
+      "epoch": 1.9184,
+      "grad_norm": 12.75,
+      "learning_rate": 1.198e-05,
+      "loss": 1.7123,
+      "mean_token_accuracy": 0.6076807895675301,
+      "num_tokens": 9943304.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.9184,
+      "eval_coding_entropy": 1.7977273602485657,
+      "eval_coding_loss": 2.0856714248657227,
+      "eval_coding_mean_token_accuracy": 0.5285422785282134,
+      "eval_coding_num_tokens": 9943304.0,
+      "eval_coding_runtime": 79.9716,
+      "eval_coding_samples_per_second": 6.252,
+      "eval_coding_steps_per_second": 3.126,
+      "step": 600
+    },
+    {
+      "epoch": 1.9184,
+      "eval_physics_entropy": 1.749086142063141,
+      "eval_physics_loss": 1.7814992666244507,
+      "eval_physics_mean_token_accuracy": 0.6056386725902557,
+      "eval_physics_num_tokens": 9943304.0,
+      "eval_physics_runtime": 50.7965,
+      "eval_physics_samples_per_second": 9.843,
+      "eval_physics_steps_per_second": 4.922,
+      "step": 600
+    },
+    {
+      "entropy": 1.7359662670642138,
+      "epoch": 1.9504000000000001,
+      "grad_norm": 13.0625,
+      "learning_rate": 1.218e-05,
+      "loss": 1.7088,
+      "mean_token_accuracy": 0.6099759945645928,
+      "num_tokens": 10112076.0,
+      "step": 610
+    },
+    {
+      "entropy": 1.7528245896100998,
+      "epoch": 1.9824000000000002,
+      "grad_norm": 15.625,
+      "learning_rate": 1.2380000000000002e-05,
+      "loss": 1.7189,
+      "mean_token_accuracy": 0.6103452138602734,
+      "num_tokens": 10270035.0,
+      "step": 620
+    },
+    {
+      "entropy": 1.739827255669393,
+      "epoch": 2.0128,
+      "grad_norm": 13.9375,
+      "learning_rate": 1.2580000000000002e-05,
+      "loss": 1.6838,
+      "mean_token_accuracy": 0.6105770368717218,
+      "num_tokens": 10424317.0,
+      "step": 630
+    },
+    {
+      "entropy": 1.69152923040092,
+      "epoch": 2.0448,
+      "grad_norm": 13.125,
+      "learning_rate": 1.2780000000000001e-05,
+      "loss": 1.6453,
+      "mean_token_accuracy": 0.620452726073563,
+      "num_tokens": 10596317.0,
+      "step": 640
+    },
+    {
+      "entropy": 1.6712413053959607,
+      "epoch": 2.0768,
+      "grad_norm": 12.3125,
+      "learning_rate": 1.2980000000000001e-05,
+      "loss": 1.6189,
+      "mean_token_accuracy": 0.6253741530701518,
+      "num_tokens": 10761453.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.6307136636227368,
+      "epoch": 2.1088,
+      "grad_norm": 14.75,
+      "learning_rate": 1.3180000000000001e-05,
+      "loss": 1.5991,
+      "mean_token_accuracy": 0.6301249139010906,
+      "num_tokens": 10921701.0,
+      "step": 660
+    },
+    {
+      "entropy": 1.687684478983283,
+      "epoch": 2.1408,
+      "grad_norm": 14.9375,
+      "learning_rate": 1.3380000000000002e-05,
+      "loss": 1.6328,
+      "mean_token_accuracy": 0.6196143303066493,
+      "num_tokens": 11087232.0,
+      "step": 670
+    },
+    {
+      "entropy": 1.6771961346268653,
+      "epoch": 2.1728,
+      "grad_norm": 14.125,
+      "learning_rate": 1.3580000000000002e-05,
+      "loss": 1.6292,
+      "mean_token_accuracy": 0.6230741955339909,
+      "num_tokens": 11253164.0,
+      "step": 680
+    },
+    {
+      "entropy": 1.611368629708886,
+      "epoch": 2.2048,
+      "grad_norm": 14.0,
+      "learning_rate": 1.378e-05,
+      "loss": 1.5649,
+      "mean_token_accuracy": 0.6339864458888769,
+      "num_tokens": 11421725.0,
+      "step": 690
+    },
+    {
+      "entropy": 1.6195241075009108,
+      "epoch": 2.2368,
+      "grad_norm": 16.5,
+      "learning_rate": 1.398e-05,
+      "loss": 1.5982,
+      "mean_token_accuracy": 0.6278265208005905,
+      "num_tokens": 11585449.0,
+      "step": 700
+    },
+    {
+      "epoch": 2.2368,
+      "eval_coding_entropy": 1.7780175647735597,
+      "eval_coding_loss": 2.0996527671813965,
+      "eval_coding_mean_token_accuracy": 0.5274338216781617,
+      "eval_coding_num_tokens": 11585449.0,
+      "eval_coding_runtime": 80.0225,
+      "eval_coding_samples_per_second": 6.248,
+      "eval_coding_steps_per_second": 3.124,
+      "step": 700
+    },
+    {
+      "epoch": 2.2368,
+      "eval_physics_entropy": 1.6218082146644592,
+      "eval_physics_loss": 1.692482352256775,
+      "eval_physics_mean_token_accuracy": 0.620885151386261,
+      "eval_physics_num_tokens": 11585449.0,
+      "eval_physics_runtime": 50.8225,
+      "eval_physics_samples_per_second": 9.838,
+      "eval_physics_steps_per_second": 4.919,
+      "step": 700
+    },
+    {
+      "entropy": 1.6410126857459546,
+      "epoch": 2.2688,
+      "grad_norm": 12.4375,
+      "learning_rate": 1.418e-05,
+      "loss": 1.6146,
+      "mean_token_accuracy": 0.6292374039068818,
+      "num_tokens": 11754276.0,
+      "step": 710
+    },
+    {
+      "entropy": 1.6849966041743756,
+      "epoch": 2.3008,
+      "grad_norm": 19.125,
+      "learning_rate": 1.4380000000000001e-05,
+      "loss": 1.6219,
+      "mean_token_accuracy": 0.6232586612924933,
+      "num_tokens": 11914373.0,
+      "step": 720
+    },
+    {
+      "entropy": 1.6184583768248557,
+      "epoch": 2.3327999999999998,
+      "grad_norm": 15.1875,
+      "learning_rate": 1.4580000000000001e-05,
+      "loss": 1.5756,
+      "mean_token_accuracy": 0.6329402431845665,
+      "num_tokens": 12075851.0,
+      "step": 730
+    },
+    {
+      "entropy": 1.5511272184550762,
+      "epoch": 2.3648,
+      "grad_norm": 16.25,
+      "learning_rate": 1.478e-05,
+      "loss": 1.505,
+      "mean_token_accuracy": 0.6405650788918138,
+      "num_tokens": 12243196.0,
+      "step": 740
+    },
+    {
+      "entropy": 1.6357920836657285,
+      "epoch": 2.3968,
+      "grad_norm": 14.9375,
+      "learning_rate": 1.498e-05,
+      "loss": 1.5965,
+      "mean_token_accuracy": 0.6316607503220439,
+      "num_tokens": 12408334.0,
+      "step": 750
+    },
+    {
+      "entropy": 1.5845110703259706,
+      "epoch": 2.4288,
+      "grad_norm": 17.0,
+      "learning_rate": 1.5180000000000002e-05,
+      "loss": 1.5585,
+      "mean_token_accuracy": 0.6371361108496785,
+      "num_tokens": 12577925.0,
+      "step": 760
+    },
+    {
+      "entropy": 1.583767046034336,
+      "epoch": 2.4608,
+      "grad_norm": 11.5,
+      "learning_rate": 1.5380000000000002e-05,
+      "loss": 1.5441,
+      "mean_token_accuracy": 0.6363885937258601,
+      "num_tokens": 12747689.0,
+      "step": 770
+    },
+    {
+      "entropy": 1.6484511096030474,
+      "epoch": 2.4928,
+      "grad_norm": 13.25,
+      "learning_rate": 1.5580000000000003e-05,
+      "loss": 1.622,
+      "mean_token_accuracy": 0.627226597070694,
+      "num_tokens": 12911304.0,
+      "step": 780
+    },
+    {
+      "entropy": 1.573851015418768,
+      "epoch": 2.5248,
+      "grad_norm": 13.875,
+      "learning_rate": 1.578e-05,
+      "loss": 1.5318,
+      "mean_token_accuracy": 0.6389297921210527,
+      "num_tokens": 13077988.0,
+      "step": 790
+    },
+    {
+      "entropy": 1.5163878366351127,
+      "epoch": 2.5568,
+      "grad_norm": 16.0,
+      "learning_rate": 1.5980000000000003e-05,
+      "loss": 1.4691,
+      "mean_token_accuracy": 0.6486704317852855,
+      "num_tokens": 13251116.0,
+      "step": 800
+    },
+    {
+      "epoch": 2.5568,
+      "eval_coding_entropy": 1.8060252170562745,
+      "eval_coding_loss": 2.092843532562256,
+      "eval_coding_mean_token_accuracy": 0.5285344138145447,
+      "eval_coding_num_tokens": 13251116.0,
+      "eval_coding_runtime": 80.4848,
+      "eval_coding_samples_per_second": 6.212,
+      "eval_coding_steps_per_second": 3.106,
+      "step": 800
+    },
+    {
+      "epoch": 2.5568,
+      "eval_physics_entropy": 1.5968217768669128,
+      "eval_physics_loss": 1.6208738088607788,
+      "eval_physics_mean_token_accuracy": 0.6335020518302917,
+      "eval_physics_num_tokens": 13251116.0,
+      "eval_physics_runtime": 50.8683,
+      "eval_physics_samples_per_second": 9.829,
+      "eval_physics_steps_per_second": 4.915,
+      "step": 800
+    },
+    {
+      "entropy": 1.5594662837684155,
+      "epoch": 2.5888,
+      "grad_norm": 13.75,
+      "learning_rate": 1.618e-05,
+      "loss": 1.5023,
+      "mean_token_accuracy": 0.6443197656422853,
+      "num_tokens": 13415037.0,
+      "step": 810
+    },
+    {
+      "entropy": 1.5624911203980445,
+      "epoch": 2.6208,
+      "grad_norm": 15.1875,
+      "learning_rate": 1.638e-05,
+      "loss": 1.5367,
+      "mean_token_accuracy": 0.6421451514586807,
+      "num_tokens": 13579275.0,
+      "step": 820
+    },
+    {
+      "entropy": 1.5679792653769256,
+      "epoch": 2.6528,
+      "grad_norm": 15.125,
+      "learning_rate": 1.658e-05,
+      "loss": 1.5404,
+      "mean_token_accuracy": 0.6395369984209538,
+      "num_tokens": 13743818.0,
+      "step": 830
+    },
+    {
+      "entropy": 1.542407462745905,
+      "epoch": 2.6848,
+      "grad_norm": 13.1875,
+      "learning_rate": 1.6780000000000002e-05,
+      "loss": 1.4875,
+      "mean_token_accuracy": 0.6461015127599239,
+      "num_tokens": 13906946.0,
+      "step": 840
+    },
+    {
+      "entropy": 1.6198145560920238,
+      "epoch": 2.7168,
+      "grad_norm": 14.5,
+      "learning_rate": 1.698e-05,
+      "loss": 1.567,
+      "mean_token_accuracy": 0.6362641137093306,
+      "num_tokens": 14075222.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.554464604333043,
+      "epoch": 2.7488,
+      "grad_norm": 12.625,
+      "learning_rate": 1.718e-05,
+      "loss": 1.5116,
+      "mean_token_accuracy": 0.6433709865435958,
+      "num_tokens": 14239601.0,
+      "step": 860
+    },
+    {
+      "entropy": 1.5441818628460169,
+      "epoch": 2.7808,
+      "grad_norm": 12.5,
+      "learning_rate": 1.7380000000000003e-05,
+      "loss": 1.5182,
+      "mean_token_accuracy": 0.6423825263977051,
+      "num_tokens": 14408376.0,
+      "step": 870
+    },
+    {
+      "entropy": 1.5283652659505607,
+      "epoch": 2.8128,
+      "grad_norm": 13.5625,
+      "learning_rate": 1.758e-05,
+      "loss": 1.478,
+      "mean_token_accuracy": 0.6480804061517119,
+      "num_tokens": 14564818.0,
+      "step": 880
+    },
+    {
+      "entropy": 1.5146011773496866,
+      "epoch": 2.8448,
+      "grad_norm": 13.75,
+      "learning_rate": 1.7780000000000003e-05,
+      "loss": 1.4608,
+      "mean_token_accuracy": 0.6502496190369129,
+      "num_tokens": 14732642.0,
+      "step": 890
+    },
+    {
+      "entropy": 1.5364020358771087,
+      "epoch": 2.8768000000000002,
+      "grad_norm": 15.6875,
+      "learning_rate": 1.798e-05,
+      "loss": 1.509,
+      "mean_token_accuracy": 0.6441155642271041,
+      "num_tokens": 14906192.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.8768000000000002,
+      "eval_coding_entropy": 1.8139167137145995,
+      "eval_coding_loss": 2.1154234409332275,
+      "eval_coding_mean_token_accuracy": 0.524706524848938,
+      "eval_coding_num_tokens": 14906192.0,
+      "eval_coding_runtime": 80.7869,
+      "eval_coding_samples_per_second": 6.189,
+      "eval_coding_steps_per_second": 3.095,
+      "step": 900
+    },
+    {
+      "epoch": 2.8768000000000002,
+      "eval_physics_entropy": 1.5320607974529266,
+      "eval_physics_loss": 1.5520291328430176,
+      "eval_physics_mean_token_accuracy": 0.6448649351596832,
+      "eval_physics_num_tokens": 14906192.0,
+      "eval_physics_runtime": 51.5462,
+      "eval_physics_samples_per_second": 9.7,
+      "eval_physics_steps_per_second": 4.85,
+      "step": 900
+    },
+    {
+      "entropy": 1.5022410597652196,
+      "epoch": 2.9088000000000003,
+      "grad_norm": 14.4375,
+      "learning_rate": 1.8180000000000002e-05,
+      "loss": 1.4513,
+      "mean_token_accuracy": 0.6529894033446908,
+      "num_tokens": 15070320.0,
+      "step": 910
+    },
+    {
+      "entropy": 1.5046488154679536,
+      "epoch": 2.9408,
+      "grad_norm": 20.125,
+      "learning_rate": 1.8380000000000004e-05,
+      "loss": 1.4568,
+      "mean_token_accuracy": 0.6527702607214451,
+      "num_tokens": 15231317.0,
+      "step": 920
+    },
+    {
+      "entropy": 1.5122195985168219,
+      "epoch": 2.9728,
+      "grad_norm": 12.5,
+      "learning_rate": 1.858e-05,
+      "loss": 1.4689,
+      "mean_token_accuracy": 0.6519427731633186,
+      "num_tokens": 15396833.0,
+      "step": 930
+    },
+    {
+      "entropy": 1.50565195005191,
+      "epoch": 3.0032,
+      "grad_norm": 13.8125,
+      "learning_rate": 1.878e-05,
+      "loss": 1.4562,
+      "mean_token_accuracy": 0.6564571412378236,
+      "num_tokens": 15557192.0,
+      "step": 940
+    },
+    {
+      "entropy": 1.4080224443227052,
+      "epoch": 3.0352,
+      "grad_norm": 12.1875,
+      "learning_rate": 1.898e-05,
+      "loss": 1.3597,
+      "mean_token_accuracy": 0.6701016353443265,
+      "num_tokens": 15722813.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.4149111464619637,
+      "epoch": 3.0672,
+      "grad_norm": 13.375,
+      "learning_rate": 1.918e-05,
+      "loss": 1.365,
+      "mean_token_accuracy": 0.6669646181166172,
+      "num_tokens": 15886622.0,
+      "step": 960
+    },
+    {
+      "entropy": 1.4306254398077727,
+      "epoch": 3.0992,
+      "grad_norm": 11.125,
+      "learning_rate": 1.938e-05,
+      "loss": 1.3718,
+      "mean_token_accuracy": 0.6666815469041467,
+      "num_tokens": 16049773.0,
+      "step": 970
+    },
+    {
+      "entropy": 1.3589156921952963,
+      "epoch": 3.1312,
+      "grad_norm": 12.125,
+      "learning_rate": 1.9580000000000002e-05,
+      "loss": 1.3193,
+      "mean_token_accuracy": 0.6735636530444026,
+      "num_tokens": 16216938.0,
+      "step": 980
+    },
+    {
+      "entropy": 1.4204085629433394,
+      "epoch": 3.1632,
+      "grad_norm": 11.625,
+      "learning_rate": 1.978e-05,
+      "loss": 1.3887,
+      "mean_token_accuracy": 0.6646887071430683,
+      "num_tokens": 16384680.0,
+      "step": 990
+    },
+    {
+      "entropy": 1.4016960449516773,
+      "epoch": 3.1952,
+      "grad_norm": 11.8125,
+      "learning_rate": 1.9980000000000002e-05,
+      "loss": 1.355,
+      "mean_token_accuracy": 0.6743173876777291,
+      "num_tokens": 16560897.0,
+      "step": 1000
+    },
+    {
+      "epoch": 3.1952,
+      "eval_coding_entropy": 1.724121112346649,
+      "eval_coding_loss": 2.1316378116607666,
+      "eval_coding_mean_token_accuracy": 0.5262920687198639,
+      "eval_coding_num_tokens": 16560897.0,
+      "eval_coding_runtime": 81.4781,
+      "eval_coding_samples_per_second": 6.137,
+      "eval_coding_steps_per_second": 3.068,
+      "step": 1000
+    },
+    {
+      "epoch": 3.1952,
+      "eval_physics_entropy": 1.4079510734081269,
+      "eval_physics_loss": 1.4921677112579346,
+      "eval_physics_mean_token_accuracy": 0.6572906188964843,
+      "eval_physics_num_tokens": 16560897.0,
+      "eval_physics_runtime": 51.7808,
+      "eval_physics_samples_per_second": 9.656,
+      "eval_physics_steps_per_second": 4.828,
+      "step": 1000
+    },
+    {
+      "entropy": 1.3990164022892713,
+      "epoch": 3.2272,
+      "grad_norm": 11.9375,
+      "learning_rate": 1.9980000000000002e-05,
+      "loss": 1.3688,
+      "mean_token_accuracy": 0.6717343915253877,
+      "num_tokens": 16723316.0,
+      "step": 1010
+    },
+    {
+      "entropy": 1.4174137562513351,
+      "epoch": 3.2592,
+      "grad_norm": 12.8125,
+      "learning_rate": 1.995777777777778e-05,
+      "loss": 1.3817,
+      "mean_token_accuracy": 0.6680277943611145,
+      "num_tokens": 16889599.0,
+      "step": 1020
+    },
+    {
+      "entropy": 1.3461125120520592,
+      "epoch": 3.2912,
+      "grad_norm": 15.0625,
+      "learning_rate": 1.9935555555555557e-05,
+      "loss": 1.2978,
+      "mean_token_accuracy": 0.6807450173422694,
+      "num_tokens": 17062342.0,
+      "step": 1030
+    },
+    {
+      "entropy": 1.3572522435337304,
+      "epoch": 3.3232,
+      "grad_norm": 11.4375,
+      "learning_rate": 1.9913333333333335e-05,
+      "loss": 1.3296,
+      "mean_token_accuracy": 0.6781903292983771,
+      "num_tokens": 17230975.0,
+      "step": 1040
+    },
+    {
+      "entropy": 1.3926319386810064,
+      "epoch": 3.3552,
+      "grad_norm": 9.625,
+      "learning_rate": 1.9891111111111112e-05,
+      "loss": 1.3577,
+      "mean_token_accuracy": 0.6729108918458223,
+      "num_tokens": 17402449.0,
+      "step": 1050
+    },
+    {
+      "entropy": 1.3759503204375505,
+      "epoch": 3.3872,
+      "grad_norm": 11.75,
+      "learning_rate": 1.986888888888889e-05,
+      "loss": 1.3378,
+      "mean_token_accuracy": 0.6787287183105946,
+      "num_tokens": 17574961.0,
+      "step": 1060
+    },
+    {
+      "entropy": 1.3743376955389977,
+      "epoch": 3.4192,
+      "grad_norm": 11.8125,
+      "learning_rate": 1.9846666666666668e-05,
+      "loss": 1.3399,
+      "mean_token_accuracy": 0.6763688886538148,
+      "num_tokens": 17741134.0,
+      "step": 1070
+    },
+    {
+      "entropy": 1.370089204236865,
+      "epoch": 3.4512,
+      "grad_norm": 10.875,
+      "learning_rate": 1.9824444444444445e-05,
+      "loss": 1.3174,
+      "mean_token_accuracy": 0.6793139725923538,
+      "num_tokens": 17902781.0,
+      "step": 1080
+    },
+    {
+      "entropy": 1.3659917820245027,
+      "epoch": 3.4832,
+      "grad_norm": 14.125,
+      "learning_rate": 1.9802222222222226e-05,
+      "loss": 1.3486,
+      "mean_token_accuracy": 0.6747965268790722,
+      "num_tokens": 18067791.0,
+      "step": 1090
+    },
+    {
+      "entropy": 1.3515218559652566,
+      "epoch": 3.5152,
+      "grad_norm": 12.5,
+      "learning_rate": 1.978e-05,
+      "loss": 1.3149,
+      "mean_token_accuracy": 0.6794558309018612,
+      "num_tokens": 18235991.0,
+      "step": 1100
+    },
+    {
+      "epoch": 3.5152,
+      "eval_coding_entropy": 1.7129438319206238,
+      "eval_coding_loss": 2.139785051345825,
+      "eval_coding_mean_token_accuracy": 0.524884427189827,
+      "eval_coding_num_tokens": 18235991.0,
+      "eval_coding_runtime": 80.5175,
+      "eval_coding_samples_per_second": 6.21,
+      "eval_coding_steps_per_second": 3.105,
+      "step": 1100
+    },
+    {
+      "epoch": 3.5152,
+      "eval_physics_entropy": 1.3459106123447417,
+      "eval_physics_loss": 1.4353532791137695,
+      "eval_physics_mean_token_accuracy": 0.6661230815649033,
+      "eval_physics_num_tokens": 18235991.0,
+      "eval_physics_runtime": 51.4982,
+      "eval_physics_samples_per_second": 9.709,
+      "eval_physics_steps_per_second": 4.855,
+      "step": 1100
+    },
+    {
+      "entropy": 1.368555410206318,
+      "epoch": 3.5472,
+      "grad_norm": 12.6875,
+      "learning_rate": 1.975777777777778e-05,
+      "loss": 1.3236,
+      "mean_token_accuracy": 0.6762216202914715,
+      "num_tokens": 18401729.0,
+      "step": 1110
+    },
+    {
+      "entropy": 1.4057014767080545,
+      "epoch": 3.5792,
+      "grad_norm": 12.4375,
+      "learning_rate": 1.9735555555555556e-05,
+      "loss": 1.3441,
+      "mean_token_accuracy": 0.6745940167456865,
+      "num_tokens": 18561781.0,
+      "step": 1120
+    },
+    {
+      "entropy": 1.360729866847396,
+      "epoch": 3.6112,
+      "grad_norm": 10.5625,
+      "learning_rate": 1.9713333333333337e-05,
+      "loss": 1.3128,
+      "mean_token_accuracy": 0.6782749250531197,
+      "num_tokens": 18729784.0,
+      "step": 1130
+    },
+    {
+      "entropy": 1.3228930503129959,
+      "epoch": 3.6432,
+      "grad_norm": 11.0,
+      "learning_rate": 1.969111111111111e-05,
+      "loss": 1.2845,
+      "mean_token_accuracy": 0.6857476118952036,
+      "num_tokens": 18889241.0,
+      "step": 1140
+    },
+    {
+      "entropy": 1.3327897161245346,
+      "epoch": 3.6752000000000002,
+      "grad_norm": 10.1875,
+      "learning_rate": 1.9668888888888892e-05,
+      "loss": 1.2935,
+      "mean_token_accuracy": 0.6824455298483372,
+      "num_tokens": 19048271.0,
+      "step": 1150
+    },
+    {
+      "entropy": 1.333436906337738,
+      "epoch": 3.7072000000000003,
+      "grad_norm": 12.0625,
+      "learning_rate": 1.9646666666666666e-05,
+      "loss": 1.3031,
+      "mean_token_accuracy": 0.6833435738459229,
+      "num_tokens": 19217080.0,
+      "step": 1160
+    },
+    {
+      "entropy": 1.3309089098125697,
+      "epoch": 3.7392,
+      "grad_norm": 11.75,
+      "learning_rate": 1.9624444444444447e-05,
+      "loss": 1.2941,
+      "mean_token_accuracy": 0.684115232154727,
+      "num_tokens": 19374677.0,
+      "step": 1170
+    },
+    {
+      "entropy": 1.338182634487748,
+      "epoch": 3.7712,
+      "grad_norm": 10.8125,
+      "learning_rate": 1.9602222222222225e-05,
+      "loss": 1.3056,
+      "mean_token_accuracy": 0.6812731333076953,
+      "num_tokens": 19533723.0,
+      "step": 1180
+    },
+    {
+      "entropy": 1.296186040714383,
+      "epoch": 3.8032,
+      "grad_norm": 11.125,
+      "learning_rate": 1.9580000000000002e-05,
+      "loss": 1.2591,
+      "mean_token_accuracy": 0.6897632556036115,
+      "num_tokens": 19700672.0,
+      "step": 1190
+    },
+    {
+      "entropy": 1.3169755220413208,
+      "epoch": 3.8352,
+      "grad_norm": 12.125,
+      "learning_rate": 1.955777777777778e-05,
+      "loss": 1.2666,
+      "mean_token_accuracy": 0.6897730944678188,
+      "num_tokens": 19871261.0,
+      "step": 1200
+    },
+    {
+      "epoch": 3.8352,
+      "eval_coding_entropy": 1.744208794593811,
+      "eval_coding_loss": 2.159120559692383,
+      "eval_coding_mean_token_accuracy": 0.5213203144073486,
+      "eval_coding_num_tokens": 19871261.0,
+      "eval_coding_runtime": 80.7654,
+      "eval_coding_samples_per_second": 6.191,
+      "eval_coding_steps_per_second": 3.095,
+      "step": 1200
+    },
+    {
+      "epoch": 3.8352,
+      "eval_physics_entropy": 1.3578989911079407,
+      "eval_physics_loss": 1.3836426734924316,
+      "eval_physics_mean_token_accuracy": 0.6761476092338562,
+      "eval_physics_num_tokens": 19871261.0,
+      "eval_physics_runtime": 51.5431,
+      "eval_physics_samples_per_second": 9.701,
+      "eval_physics_steps_per_second": 4.85,
+      "step": 1200
+    },
+    {
+      "entropy": 1.2740023802965879,
+      "epoch": 3.8672,
+      "grad_norm": 9.4375,
+      "learning_rate": 1.9535555555555557e-05,
+      "loss": 1.2429,
+      "mean_token_accuracy": 0.6932176874950529,
+      "num_tokens": 20036482.0,
+      "step": 1210
+    },
+    {
+      "entropy": 1.3576739229261876,
+      "epoch": 3.8992,
+      "grad_norm": 10.125,
+      "learning_rate": 1.9513333333333335e-05,
+      "loss": 1.2989,
+      "mean_token_accuracy": 0.6787684431299568,
+      "num_tokens": 20200878.0,
+      "step": 1220
+    },
+    {
+      "entropy": 1.3019543394446373,
+      "epoch": 3.9312,
+      "grad_norm": 10.4375,
+      "learning_rate": 1.9491111111111113e-05,
+      "loss": 1.252,
+      "mean_token_accuracy": 0.6888652168214321,
+      "num_tokens": 20369285.0,
+      "step": 1230
+    },
+    {
+      "entropy": 1.2588012181222439,
+      "epoch": 3.9632,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.946888888888889e-05,
+      "loss": 1.2125,
+      "mean_token_accuracy": 0.6965269058942795,
+      "num_tokens": 20532097.0,
+      "step": 1240
+    },
+    {
+      "entropy": 1.3045038145035506,
+      "epoch": 3.9952,
+      "grad_norm": 10.625,
+      "learning_rate": 1.9446666666666668e-05,
+      "loss": 1.2601,
+      "mean_token_accuracy": 0.6899313658475876,
+      "num_tokens": 20698863.0,
+      "step": 1250
+    },
+    {
+      "entropy": 1.2075176940936792,
+      "epoch": 4.0256,
+      "grad_norm": 9.25,
+      "learning_rate": 1.9424444444444446e-05,
+      "loss": 1.1716,
+      "mean_token_accuracy": 0.7094790370840776,
+      "num_tokens": 20857766.0,
+      "step": 1260
+    },
+    {
+      "entropy": 1.1558428648859262,
+      "epoch": 4.0576,
+      "grad_norm": 9.625,
+      "learning_rate": 1.9402222222222223e-05,
+      "loss": 1.1242,
+      "mean_token_accuracy": 0.7157231424003839,
+      "num_tokens": 21026679.0,
+      "step": 1270
+    },
+    {
+      "entropy": 1.1972203195095061,
+      "epoch": 4.0896,
+      "grad_norm": 9.4375,
+      "learning_rate": 1.938e-05,
+      "loss": 1.1517,
+      "mean_token_accuracy": 0.7088419755920767,
+      "num_tokens": 21186241.0,
+      "step": 1280
+    },
+    {
+      "entropy": 1.1963561417534947,
+      "epoch": 4.1216,
+      "grad_norm": 8.9375,
+      "learning_rate": 1.935777777777778e-05,
+      "loss": 1.1457,
+      "mean_token_accuracy": 0.713546970486641,
+      "num_tokens": 21350399.0,
+      "step": 1290
+    },
+    {
+      "entropy": 1.1925376821309328,
+      "epoch": 4.1536,
+      "grad_norm": 10.1875,
+      "learning_rate": 1.9335555555555556e-05,
+      "loss": 1.1521,
+      "mean_token_accuracy": 0.7091899808496237,
+      "num_tokens": 21518243.0,
+      "step": 1300
+    },
+    {
+      "epoch": 4.1536,
+      "eval_coding_entropy": 1.5767053871154786,
+      "eval_coding_loss": 2.2092390060424805,
+      "eval_coding_mean_token_accuracy": 0.5204463745355606,
+      "eval_coding_num_tokens": 21518243.0,
+      "eval_coding_runtime": 80.6751,
+      "eval_coding_samples_per_second": 6.198,
+      "eval_coding_steps_per_second": 3.099,
+      "step": 1300
+    },
+    {
+      "epoch": 4.1536,
+      "eval_physics_entropy": 1.151607351064682,
+      "eval_physics_loss": 1.356305718421936,
+      "eval_physics_mean_token_accuracy": 0.6846682960987092,
+      "eval_physics_num_tokens": 21518243.0,
+      "eval_physics_runtime": 52.0383,
+      "eval_physics_samples_per_second": 9.608,
+      "eval_physics_steps_per_second": 4.804,
+      "step": 1300
+    },
+    {
+      "entropy": 1.1801189385354518,
+      "epoch": 4.1856,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.9313333333333334e-05,
+      "loss": 1.1425,
+      "mean_token_accuracy": 0.7108678799122572,
+      "num_tokens": 21677750.0,
+      "step": 1310
+    },
+    {
+      "entropy": 1.1682889927178621,
+      "epoch": 4.2176,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.9291111111111115e-05,
+      "loss": 1.1079,
+      "mean_token_accuracy": 0.7138631340116263,
+      "num_tokens": 21845173.0,
+      "step": 1320
+    },
+    {
+      "entropy": 1.157709751278162,
+      "epoch": 4.2496,
+      "grad_norm": 9.625,
+      "learning_rate": 1.926888888888889e-05,
+      "loss": 1.1024,
+      "mean_token_accuracy": 0.7179881976917386,
+      "num_tokens": 22009137.0,
+      "step": 1330
+    },
+    {
+      "entropy": 1.2081427805125713,
+      "epoch": 4.2816,
+      "grad_norm": 11.5,
+      "learning_rate": 1.924666666666667e-05,
+      "loss": 1.1743,
+      "mean_token_accuracy": 0.7052507167682052,
+      "num_tokens": 22175046.0,
+      "step": 1340
+    },
+    {
+      "entropy": 1.2216685824096203,
+      "epoch": 4.3136,
+      "grad_norm": 8.875,
+      "learning_rate": 1.9224444444444444e-05,
+      "loss": 1.1592,
+      "mean_token_accuracy": 0.7062308833003044,
+      "num_tokens": 22341391.0,
+      "step": 1350
+    },
+    {
+      "entropy": 1.1411818325519563,
+      "epoch": 4.3456,
+      "grad_norm": 9.4375,
+      "learning_rate": 1.9202222222222225e-05,
+      "loss": 1.0984,
+      "mean_token_accuracy": 0.7186709493398666,
+      "num_tokens": 22507465.0,
+      "step": 1360
+    },
+    {
+      "entropy": 1.1621076967567205,
+      "epoch": 4.3776,
+      "grad_norm": 8.9375,
+      "learning_rate": 1.918e-05,
+      "loss": 1.1423,
+      "mean_token_accuracy": 0.7130050586536527,
+      "num_tokens": 22672707.0,
+      "step": 1370
+    },
+    {
+      "entropy": 1.1641780041158198,
+      "epoch": 4.4096,
+      "grad_norm": 9.375,
+      "learning_rate": 1.915777777777778e-05,
+      "loss": 1.1355,
+      "mean_token_accuracy": 0.713141619041562,
+      "num_tokens": 22838278.0,
+      "step": 1380
+    },
+    {
+      "entropy": 1.1436150528490543,
+      "epoch": 4.4416,
+      "grad_norm": 8.6875,
+      "learning_rate": 1.9135555555555555e-05,
+      "loss": 1.1021,
+      "mean_token_accuracy": 0.7170177362859249,
+      "num_tokens": 23006714.0,
+      "step": 1390
+    },
+    {
+      "entropy": 1.131415880098939,
+      "epoch": 4.4736,
+      "grad_norm": 9.375,
+      "learning_rate": 1.9113333333333336e-05,
+      "loss": 1.0921,
+      "mean_token_accuracy": 0.7199389934539795,
+      "num_tokens": 23171616.0,
+      "step": 1400
+    },
+    {
+      "epoch": 4.4736,
+      "eval_coding_entropy": 1.6192174096107483,
+      "eval_coding_loss": 2.2012040615081787,
+      "eval_coding_mean_token_accuracy": 0.5209840197563171,
+      "eval_coding_num_tokens": 23171616.0,
+      "eval_coding_runtime": 81.8936,
+      "eval_coding_samples_per_second": 6.105,
+      "eval_coding_steps_per_second": 3.053,
+      "step": 1400
+    },
+    {
+      "epoch": 4.4736,
+      "eval_physics_entropy": 1.2294665141105652,
+      "eval_physics_loss": 1.3109028339385986,
+      "eval_physics_mean_token_accuracy": 0.6908313782215119,
+      "eval_physics_num_tokens": 23171616.0,
+      "eval_physics_runtime": 52.4694,
+      "eval_physics_samples_per_second": 9.529,
+      "eval_physics_steps_per_second": 4.765,
+      "step": 1400
+    },
+    {
+      "entropy": 1.1691782031208278,
+      "epoch": 4.5056,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.9091111111111113e-05,
+      "loss": 1.1276,
+      "mean_token_accuracy": 0.7141140529885888,
+      "num_tokens": 23339342.0,
+      "step": 1410
+    },
+    {
+      "entropy": 1.1408521559089422,
+      "epoch": 4.5376,
+      "grad_norm": 10.0,
+      "learning_rate": 1.906888888888889e-05,
+      "loss": 1.1334,
+      "mean_token_accuracy": 0.717669415473938,
+      "num_tokens": 23502858.0,
+      "step": 1420
+    },
+    {
+      "entropy": 1.1881117545068265,
+      "epoch": 4.5696,
+      "grad_norm": 10.3125,
+      "learning_rate": 1.904666666666667e-05,
+      "loss": 1.1501,
+      "mean_token_accuracy": 0.7118328493088484,
+      "num_tokens": 23671520.0,
+      "step": 1430
+    },
+    {
+      "entropy": 1.1651773374527692,
+      "epoch": 4.6016,
+      "grad_norm": 10.9375,
+      "learning_rate": 1.9024444444444446e-05,
+      "loss": 1.1427,
+      "mean_token_accuracy": 0.7142679516226054,
+      "num_tokens": 23832756.0,
+      "step": 1440
+    },
+    {
+      "entropy": 1.158542051911354,
+      "epoch": 4.6336,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.9002222222222224e-05,
+      "loss": 1.1028,
+      "mean_token_accuracy": 0.7187374413013459,
+      "num_tokens": 23994203.0,
+      "step": 1450
+    },
+    {
+      "entropy": 1.1147582449018956,
+      "epoch": 4.6655999999999995,
+      "grad_norm": 8.875,
+      "learning_rate": 1.898e-05,
+      "loss": 1.0791,
+      "mean_token_accuracy": 0.7234875354915857,
+      "num_tokens": 24170398.0,
+      "step": 1460
+    },
+    {
+      "entropy": 1.16308904774487,
+      "epoch": 4.6975999999999996,
+      "grad_norm": 10.125,
+      "learning_rate": 1.895777777777778e-05,
+      "loss": 1.1331,
+      "mean_token_accuracy": 0.7167198553681373,
+      "num_tokens": 24333281.0,
+      "step": 1470
+    },
+    {
+      "entropy": 1.1451086029410362,
+      "epoch": 4.7296,
+      "grad_norm": 8.8125,
+      "learning_rate": 1.8935555555555556e-05,
+      "loss": 1.1031,
+      "mean_token_accuracy": 0.7176411859691143,
+      "num_tokens": 24502037.0,
+      "step": 1480
+    },
+    {
+      "entropy": 1.2100287709385156,
+      "epoch": 4.7616,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.8913333333333334e-05,
+      "loss": 1.1568,
+      "mean_token_accuracy": 0.7084289535880088,
+      "num_tokens": 24667335.0,
+      "step": 1490
+    },
+    {
+      "entropy": 1.1385379381477834,
+      "epoch": 4.7936,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.8891111111111115e-05,
+      "loss": 1.1007,
+      "mean_token_accuracy": 0.7203466827049851,
+      "num_tokens": 24829965.0,
+      "step": 1500
+    },
+    {
+      "epoch": 4.7936,
+      "eval_coding_entropy": 1.6071018924713134,
+      "eval_coding_loss": 2.2054996490478516,
+      "eval_coding_mean_token_accuracy": 0.5207259600162506,
+      "eval_coding_num_tokens": 24829965.0,
+      "eval_coding_runtime": 82.6052,
+      "eval_coding_samples_per_second": 6.053,
+      "eval_coding_steps_per_second": 3.026,
+      "step": 1500
+    },
+    {
+      "epoch": 4.7936,
+      "eval_physics_entropy": 1.1821390426158904,
+      "eval_physics_loss": 1.2802668809890747,
+      "eval_physics_mean_token_accuracy": 0.6976329164505005,
+      "eval_physics_num_tokens": 24829965.0,
+      "eval_physics_runtime": 50.6887,
+      "eval_physics_samples_per_second": 9.864,
+      "eval_physics_steps_per_second": 4.932,
+      "step": 1500
+    },
+    {
+      "entropy": 1.1339262820780278,
+      "epoch": 4.8256,
+      "grad_norm": 8.4375,
+      "learning_rate": 1.886888888888889e-05,
+      "loss": 1.0898,
+      "mean_token_accuracy": 0.7229399343952536,
+      "num_tokens": 24993001.0,
+      "step": 1510
+    },
+    {
+      "entropy": 1.1489319629967212,
+      "epoch": 4.8576,
+      "grad_norm": 9.0,
+      "learning_rate": 1.884666666666667e-05,
+      "loss": 1.0956,
+      "mean_token_accuracy": 0.7196420207619667,
+      "num_tokens": 25161270.0,
+      "step": 1520
+    },
+    {
+      "entropy": 1.1502934597432612,
+      "epoch": 4.8896,
+      "grad_norm": 8.875,
+      "learning_rate": 1.8824444444444445e-05,
+      "loss": 1.1174,
+      "mean_token_accuracy": 0.7189344964921475,
+      "num_tokens": 25325907.0,
+      "step": 1530
+    },
+    {
+      "entropy": 1.092420133575797,
+      "epoch": 4.9216,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.8802222222222226e-05,
+      "loss": 1.0627,
+      "mean_token_accuracy": 0.7274942602962255,
+      "num_tokens": 25492085.0,
+      "step": 1540
+    },
+    {
+      "entropy": 1.196289550513029,
+      "epoch": 4.9536,
+      "grad_norm": 9.25,
+      "learning_rate": 1.878e-05,
+      "loss": 1.1418,
+      "mean_token_accuracy": 0.7106173977255821,
+      "num_tokens": 25653637.0,
+      "step": 1550
+    },
+    {
+      "entropy": 1.1429802037775516,
+      "epoch": 4.9856,
+      "grad_norm": 9.5,
+      "learning_rate": 1.875777777777778e-05,
+      "loss": 1.0915,
+      "mean_token_accuracy": 0.7196958020329476,
+      "num_tokens": 25825573.0,
+      "step": 1560
+    },
+    {
+      "entropy": 1.0252085781018985,
+      "epoch": 5.016,
+      "grad_norm": 9.125,
+      "learning_rate": 1.873555555555556e-05,
+      "loss": 0.9806,
+      "mean_token_accuracy": 0.7431941052016459,
+      "num_tokens": 25990067.0,
+      "step": 1570
+    },
+    {
+      "entropy": 0.9978800658136606,
+      "epoch": 5.048,
+      "grad_norm": 7.90625,
+      "learning_rate": 1.8713333333333336e-05,
+      "loss": 0.9496,
+      "mean_token_accuracy": 0.7502539362758398,
+      "num_tokens": 26157643.0,
+      "step": 1580
+    },
+    {
+      "entropy": 0.9946053113788367,
+      "epoch": 5.08,
+      "grad_norm": 7.3125,
+      "learning_rate": 1.8691111111111114e-05,
+      "loss": 0.9582,
+      "mean_token_accuracy": 0.7463313773274421,
+      "num_tokens": 26330383.0,
+      "step": 1590
+    },
+    {
+      "entropy": 1.0126261772587895,
+      "epoch": 5.112,
+      "grad_norm": 8.875,
+      "learning_rate": 1.866888888888889e-05,
+      "loss": 0.9684,
+      "mean_token_accuracy": 0.7450104162096978,
+      "num_tokens": 26496271.0,
+      "step": 1600
+    },
+    {
+      "epoch": 5.112,
+      "eval_coding_entropy": 1.4595765166282655,
+      "eval_coding_loss": 2.275820732116699,
+      "eval_coding_mean_token_accuracy": 0.5172890294790268,
+      "eval_coding_num_tokens": 26496271.0,
+      "eval_coding_runtime": 80.0195,
+      "eval_coding_samples_per_second": 6.248,
+      "eval_coding_steps_per_second": 3.124,
+      "step": 1600
+    },
+    {
+      "epoch": 5.112,
+      "eval_physics_entropy": 1.0461106979846955,
+      "eval_physics_loss": 1.2792062759399414,
+      "eval_physics_mean_token_accuracy": 0.7012547857761383,
+      "eval_physics_num_tokens": 26496271.0,
+      "eval_physics_runtime": 50.8139,
+      "eval_physics_samples_per_second": 9.84,
+      "eval_physics_steps_per_second": 4.92,
+      "step": 1600
+    },
+    {
+      "entropy": 1.0357391186058522,
+      "epoch": 5.144,
+      "grad_norm": 8.75,
+      "learning_rate": 1.864666666666667e-05,
+      "loss": 0.9946,
+      "mean_token_accuracy": 0.7396486084908247,
+      "num_tokens": 26657872.0,
+      "step": 1610
+    },
+    {
+      "entropy": 1.0501383509486915,
+      "epoch": 5.176,
+      "grad_norm": 8.5625,
+      "learning_rate": 1.8624444444444446e-05,
+      "loss": 1.0118,
+      "mean_token_accuracy": 0.7364444840699435,
+      "num_tokens": 26815558.0,
+      "step": 1620
+    },
+    {
+      "entropy": 0.9903883818536997,
+      "epoch": 5.208,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.8602222222222224e-05,
+      "loss": 0.9495,
+      "mean_token_accuracy": 0.7488659679889679,
+      "num_tokens": 26988857.0,
+      "step": 1630
+    },
+    {
+      "entropy": 1.0144404012709856,
+      "epoch": 5.24,
+      "grad_norm": 7.5,
+      "learning_rate": 1.858e-05,
+      "loss": 0.9706,
+      "mean_token_accuracy": 0.7453697588294744,
+      "num_tokens": 27149125.0,
+      "step": 1640
+    },
+    {
+      "entropy": 1.0191889710724353,
+      "epoch": 5.272,
+      "grad_norm": 8.3125,
+      "learning_rate": 1.855777777777778e-05,
+      "loss": 0.9819,
+      "mean_token_accuracy": 0.744130115583539,
+      "num_tokens": 27316852.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.9761725923046469,
+      "epoch": 5.304,
+      "grad_norm": 8.125,
+      "learning_rate": 1.8535555555555557e-05,
+      "loss": 0.9475,
+      "mean_token_accuracy": 0.7517474852502346,
+      "num_tokens": 27481303.0,
+      "step": 1660
+    },
+    {
+      "entropy": 1.0315170247107743,
+      "epoch": 5.336,
+      "grad_norm": 8.1875,
+      "learning_rate": 1.8513333333333335e-05,
+      "loss": 0.9947,
+      "mean_token_accuracy": 0.7406270373612642,
+      "num_tokens": 27658752.0,
+      "step": 1670
+    },
+    {
+      "entropy": 1.0055052107200027,
+      "epoch": 5.368,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.8491111111111112e-05,
+      "loss": 0.9678,
+      "mean_token_accuracy": 0.7463656073436141,
+      "num_tokens": 27825908.0,
+      "step": 1680
+    },
+    {
+      "entropy": 1.0419462624937297,
+      "epoch": 5.4,
+      "grad_norm": 8.25,
+      "learning_rate": 1.846888888888889e-05,
+      "loss": 0.9845,
+      "mean_token_accuracy": 0.7397806786000729,
+      "num_tokens": 27994598.0,
+      "step": 1690
+    },
+    {
+      "entropy": 1.042955220490694,
+      "epoch": 5.432,
+      "grad_norm": 8.5625,
+      "learning_rate": 1.8446666666666667e-05,
+      "loss": 0.9998,
+      "mean_token_accuracy": 0.7378627855330706,
+      "num_tokens": 28163244.0,
+      "step": 1700
+    },
+    {
+      "epoch": 5.432,
+      "eval_coding_entropy": 1.4777437753677367,
+      "eval_coding_loss": 2.277747631072998,
+      "eval_coding_mean_token_accuracy": 0.5185715831518173,
+      "eval_coding_num_tokens": 28163244.0,
+      "eval_coding_runtime": 80.042,
+      "eval_coding_samples_per_second": 6.247,
+      "eval_coding_steps_per_second": 3.123,
+      "step": 1700
+    },
+    {
+      "epoch": 5.432,
+      "eval_physics_entropy": 1.0643408155441285,
+      "eval_physics_loss": 1.2596138715744019,
+      "eval_physics_mean_token_accuracy": 0.7038933093547821,
+      "eval_physics_num_tokens": 28163244.0,
+      "eval_physics_runtime": 50.8348,
+      "eval_physics_samples_per_second": 9.836,
+      "eval_physics_steps_per_second": 4.918,
+      "step": 1700
+    },
+    {
+      "entropy": 0.9977170016616583,
+      "epoch": 5.464,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.842444444444445e-05,
+      "loss": 0.9714,
+      "mean_token_accuracy": 0.7471988730132579,
+      "num_tokens": 28327234.0,
+      "step": 1710
+    },
+    {
+      "entropy": 0.982015180028975,
+      "epoch": 5.496,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.8402222222222223e-05,
+      "loss": 0.9392,
+      "mean_token_accuracy": 0.7512154206633568,
+      "num_tokens": 28494226.0,
+      "step": 1720
+    },
+    {
+      "entropy": 1.012007206492126,
+      "epoch": 5.5280000000000005,
+      "grad_norm": 6.96875,
+      "learning_rate": 1.8380000000000004e-05,
+      "loss": 0.9818,
+      "mean_token_accuracy": 0.7440147709101439,
+      "num_tokens": 28662926.0,
+      "step": 1730
+    },
+    {
+      "entropy": 0.9774416748434305,
+      "epoch": 5.5600000000000005,
+      "grad_norm": 8.1875,
+      "learning_rate": 1.8357777777777778e-05,
+      "loss": 0.9452,
+      "mean_token_accuracy": 0.7503319170325995,
+      "num_tokens": 28827430.0,
+      "step": 1740
+    },
+    {
+      "entropy": 1.020398671925068,
+      "epoch": 5.592,
+      "grad_norm": 7.75,
+      "learning_rate": 1.833555555555556e-05,
+      "loss": 0.9773,
+      "mean_token_accuracy": 0.7404747471213341,
+      "num_tokens": 28993938.0,
+      "step": 1750
+    },
+    {
+      "entropy": 1.0490892603993416,
+      "epoch": 5.624,
+      "grad_norm": 8.6875,
+      "learning_rate": 1.8313333333333333e-05,
+      "loss": 1.016,
+      "mean_token_accuracy": 0.7372140675783158,
+      "num_tokens": 29159365.0,
+      "step": 1760
+    },
+    {
+      "entropy": 1.026135996170342,
+      "epoch": 5.656,
+      "grad_norm": 8.375,
+      "learning_rate": 1.8291111111111114e-05,
+      "loss": 1.0025,
+      "mean_token_accuracy": 0.7405038315802812,
+      "num_tokens": 29320125.0,
+      "step": 1770
+    },
+    {
+      "entropy": 1.047302521020174,
+      "epoch": 5.688,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.8268888888888888e-05,
+      "loss": 0.9859,
+      "mean_token_accuracy": 0.7409991217777133,
+      "num_tokens": 29481876.0,
+      "step": 1780
+    },
+    {
+      "entropy": 1.0233549170196057,
+      "epoch": 5.72,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.824666666666667e-05,
+      "loss": 0.987,
+      "mean_token_accuracy": 0.7419757056981325,
+      "num_tokens": 29641581.0,
+      "step": 1790
+    },
+    {
+      "entropy": 1.0335674609988927,
+      "epoch": 5.752,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.8224444444444447e-05,
+      "loss": 0.9857,
+      "mean_token_accuracy": 0.7423797022551298,
+      "num_tokens": 29804639.0,
+      "step": 1800
+    },
+    {
+      "epoch": 5.752,
+      "eval_coding_entropy": 1.4844380550384522,
+      "eval_coding_loss": 2.3004150390625,
+      "eval_coding_mean_token_accuracy": 0.5159263869524002,
+      "eval_coding_num_tokens": 29804639.0,
+      "eval_coding_runtime": 80.5137,
+      "eval_coding_samples_per_second": 6.21,
+      "eval_coding_steps_per_second": 3.105,
+      "step": 1800
+    },
+    {
+      "epoch": 5.752,
+      "eval_physics_entropy": 1.067388994693756,
+      "eval_physics_loss": 1.2464126348495483,
+      "eval_physics_mean_token_accuracy": 0.7066913852691651,
+      "eval_physics_num_tokens": 29804639.0,
+      "eval_physics_runtime": 51.0316,
+      "eval_physics_samples_per_second": 9.798,
+      "eval_physics_steps_per_second": 4.899,
+      "step": 1800
+    },
+    {
+      "entropy": 1.0015105351805687,
+      "epoch": 5.784,
+      "grad_norm": 7.34375,
+      "learning_rate": 1.8202222222222225e-05,
+      "loss": 0.972,
+      "mean_token_accuracy": 0.7444529678672552,
+      "num_tokens": 29978576.0,
+      "step": 1810
+    },
+    {
+      "entropy": 1.0132002836093306,
+      "epoch": 5.816,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.8180000000000002e-05,
+      "loss": 0.9771,
+      "mean_token_accuracy": 0.7456060782074928,
+      "num_tokens": 30141916.0,
+      "step": 1820
+    },
+    {
+      "entropy": 0.9955538790673018,
+      "epoch": 5.848,
+      "grad_norm": 7.375,
+      "learning_rate": 1.815777777777778e-05,
+      "loss": 0.9692,
+      "mean_token_accuracy": 0.7480616871267557,
+      "num_tokens": 30307900.0,
+      "step": 1830
+    },
+    {
+      "entropy": 1.0551919762045145,
+      "epoch": 5.88,
+      "grad_norm": 7.75,
+      "learning_rate": 1.8135555555555557e-05,
+      "loss": 0.9944,
+      "mean_token_accuracy": 0.7364229299128056,
+      "num_tokens": 30470302.0,
+      "step": 1840
+    },
+    {
+      "entropy": 1.0333939548581839,
+      "epoch": 5.912,
+      "grad_norm": 8.625,
+      "learning_rate": 1.8113333333333335e-05,
+      "loss": 0.9958,
+      "mean_token_accuracy": 0.7395027175545692,
+      "num_tokens": 30636029.0,
+      "step": 1850
+    },
+    {
+      "entropy": 1.0492048785090446,
+      "epoch": 5.944,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.8091111111111113e-05,
+      "loss": 1.0063,
+      "mean_token_accuracy": 0.7376182321459055,
+      "num_tokens": 30799363.0,
+      "step": 1860
+    },
+    {
+      "entropy": 1.0491292778402568,
+      "epoch": 5.976,
+      "grad_norm": 8.6875,
+      "learning_rate": 1.806888888888889e-05,
+      "loss": 1.007,
+      "mean_token_accuracy": 0.7397043209522962,
+      "num_tokens": 30960267.0,
+      "step": 1870
+    },
+    {
+      "entropy": 1.0033901220089512,
+      "epoch": 6.0064,
+      "grad_norm": 7.21875,
+      "learning_rate": 1.8046666666666668e-05,
+      "loss": 0.9577,
+      "mean_token_accuracy": 0.7508013134724215,
+      "num_tokens": 31115221.0,
+      "step": 1880
+    },
+    {
+      "entropy": 0.8799053080379963,
+      "epoch": 6.0384,
+      "grad_norm": 8.5,
+      "learning_rate": 1.8024444444444445e-05,
+      "loss": 0.8421,
+      "mean_token_accuracy": 0.7726955726742745,
+      "num_tokens": 31282640.0,
+      "step": 1890
+    },
+    {
+      "entropy": 0.8743755616247654,
+      "epoch": 6.0704,
+      "grad_norm": 7.59375,
+      "learning_rate": 1.8002222222222223e-05,
+      "loss": 0.8413,
+      "mean_token_accuracy": 0.7713052142411471,
+      "num_tokens": 31452030.0,
+      "step": 1900
+    },
+    {
+      "epoch": 6.0704,
+      "eval_coding_entropy": 1.4276922750473022,
+      "eval_coding_loss": 2.3653318881988525,
+      "eval_coding_mean_token_accuracy": 0.5115255815982819,
+      "eval_coding_num_tokens": 31452030.0,
+      "eval_coding_runtime": 80.5075,
+      "eval_coding_samples_per_second": 6.211,
+      "eval_coding_steps_per_second": 3.105,
+      "step": 1900
+    },
+    {
+      "epoch": 6.0704,
+      "eval_physics_entropy": 0.9663202397823334,
+      "eval_physics_loss": 1.2572896480560303,
+      "eval_physics_mean_token_accuracy": 0.7080614182949067,
+      "eval_physics_num_tokens": 31452030.0,
+      "eval_physics_runtime": 51.1398,
+      "eval_physics_samples_per_second": 9.777,
+      "eval_physics_steps_per_second": 4.889,
+      "step": 1900
+    },
+    {
+      "entropy": 0.8911404553800821,
+      "epoch": 6.1024,
+      "grad_norm": 8.5,
+      "learning_rate": 1.798e-05,
+      "loss": 0.8417,
+      "mean_token_accuracy": 0.7735247768461704,
+      "num_tokens": 31617821.0,
+      "step": 1910
+    },
+    {
+      "entropy": 0.8949294181540608,
+      "epoch": 6.1344,
+      "grad_norm": 7.875,
+      "learning_rate": 1.7957777777777778e-05,
+      "loss": 0.856,
+      "mean_token_accuracy": 0.7668255034834146,
+      "num_tokens": 31783257.0,
+      "step": 1920
+    },
+    {
+      "entropy": 0.904043540544808,
+      "epoch": 6.1664,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.7935555555555556e-05,
+      "loss": 0.8687,
+      "mean_token_accuracy": 0.766658914834261,
+      "num_tokens": 31945987.0,
+      "step": 1930
+    },
+    {
+      "entropy": 0.892748880572617,
+      "epoch": 6.1984,
+      "grad_norm": 8.1875,
+      "learning_rate": 1.7913333333333337e-05,
+      "loss": 0.8445,
+      "mean_token_accuracy": 0.7715954016894102,
+      "num_tokens": 32108923.0,
+      "step": 1940
+    },
+    {
+      "entropy": 0.8627868793904782,
+      "epoch": 6.2304,
+      "grad_norm": 7.34375,
+      "learning_rate": 1.789111111111111e-05,
+      "loss": 0.8205,
+      "mean_token_accuracy": 0.774358106404543,
+      "num_tokens": 32280527.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.935067780688405,
+      "epoch": 6.2624,
+      "grad_norm": 8.1875,
+      "learning_rate": 1.7868888888888892e-05,
+      "loss": 0.8771,
+      "mean_token_accuracy": 0.7616540655493736,
+      "num_tokens": 32448689.0,
+      "step": 1960
+    },
+    {
+      "entropy": 0.8619815381243825,
+      "epoch": 6.2943999999999996,
+      "grad_norm": 6.75,
+      "learning_rate": 1.7846666666666666e-05,
+      "loss": 0.8203,
+      "mean_token_accuracy": 0.7761578068137169,
+      "num_tokens": 32623655.0,
+      "step": 1970
+    },
+    {
+      "entropy": 0.9105080384761095,
+      "epoch": 6.3264,
+      "grad_norm": 8.75,
+      "learning_rate": 1.7824444444444447e-05,
+      "loss": 0.8749,
+      "mean_token_accuracy": 0.7641179401427507,
+      "num_tokens": 32788431.0,
+      "step": 1980
+    },
+    {
+      "entropy": 0.9150203362107276,
+      "epoch": 6.3584,
+      "grad_norm": 7.15625,
+      "learning_rate": 1.780222222222222e-05,
+      "loss": 0.8895,
+      "mean_token_accuracy": 0.7654095780104399,
+      "num_tokens": 32953331.0,
+      "step": 1990
+    },
+    {
+      "entropy": 0.9151443220674992,
+      "epoch": 6.3904,
+      "grad_norm": 6.96875,
+      "learning_rate": 1.7780000000000003e-05,
+      "loss": 0.8604,
+      "mean_token_accuracy": 0.7665283579379321,
+      "num_tokens": 33123102.0,
+      "step": 2000
+    },
+    {
+      "epoch": 6.3904,
+      "eval_coding_entropy": 1.3934270286560058,
+      "eval_coding_loss": 2.4072625637054443,
+      "eval_coding_mean_token_accuracy": 0.5086399167776108,
+      "eval_coding_num_tokens": 33123102.0,
+      "eval_coding_runtime": 80.4742,
+      "eval_coding_samples_per_second": 6.213,
+      "eval_coding_steps_per_second": 3.107,
+      "step": 2000
+    },
+    {
+      "epoch": 6.3904,
+      "eval_physics_entropy": 0.9661147429943084,
+      "eval_physics_loss": 1.2546967267990112,
+      "eval_physics_mean_token_accuracy": 0.7096827251911163,
+      "eval_physics_num_tokens": 33123102.0,
+      "eval_physics_runtime": 50.4983,
+      "eval_physics_samples_per_second": 9.901,
+      "eval_physics_steps_per_second": 4.951,
+      "step": 2000
+    },
+    {
+      "entropy": 0.9143168790265918,
+      "epoch": 6.4224,
+      "grad_norm": 9.25,
+      "learning_rate": 1.7757777777777777e-05,
+      "loss": 0.8664,
+      "mean_token_accuracy": 0.7659744843840599,
+      "num_tokens": 33286459.0,
+      "step": 2010
+    },
+    {
+      "entropy": 0.9008195903152227,
+      "epoch": 6.4544,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.7735555555555558e-05,
+      "loss": 0.8609,
+      "mean_token_accuracy": 0.7678866066038609,
+      "num_tokens": 33452198.0,
+      "step": 2020
+    },
+    {
+      "entropy": 0.9174474649131298,
+      "epoch": 6.4864,
+      "grad_norm": 6.96875,
+      "learning_rate": 1.7713333333333335e-05,
+      "loss": 0.8828,
+      "mean_token_accuracy": 0.7651618968695402,
+      "num_tokens": 33617056.0,
+      "step": 2030
+    },
+    {
+      "entropy": 0.9258514747023583,
+      "epoch": 6.5184,
+      "grad_norm": 9.0,
+      "learning_rate": 1.7691111111111113e-05,
+      "loss": 0.8849,
+      "mean_token_accuracy": 0.7615245707333088,
+      "num_tokens": 33778782.0,
+      "step": 2040
+    },
+    {
+      "entropy": 0.8773188255727291,
+      "epoch": 6.5504,
+      "grad_norm": 7.34375,
+      "learning_rate": 1.766888888888889e-05,
+      "loss": 0.8513,
+      "mean_token_accuracy": 0.7721717149019242,
+      "num_tokens": 33946435.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.8679801823571325,
+      "epoch": 6.5824,
+      "grad_norm": 7.1875,
+      "learning_rate": 1.7646666666666668e-05,
+      "loss": 0.8448,
+      "mean_token_accuracy": 0.7743362218141556,
+      "num_tokens": 34110878.0,
+      "step": 2060
+    },
+    {
+      "entropy": 0.9021867254748941,
+      "epoch": 6.6144,
+      "grad_norm": 7.71875,
+      "learning_rate": 1.7624444444444446e-05,
+      "loss": 0.8595,
+      "mean_token_accuracy": 0.7639507986605167,
+      "num_tokens": 34276122.0,
+      "step": 2070
+    },
+    {
+      "entropy": 0.9054385522380471,
+      "epoch": 6.6464,
+      "grad_norm": 7.28125,
+      "learning_rate": 1.7602222222222223e-05,
+      "loss": 0.8509,
+      "mean_token_accuracy": 0.7672549616545439,
+      "num_tokens": 34445468.0,
+      "step": 2080
+    },
+    {
+      "entropy": 0.9238305319100618,
+      "epoch": 6.6784,
+      "grad_norm": 7.875,
+      "learning_rate": 1.758e-05,
+      "loss": 0.8878,
+      "mean_token_accuracy": 0.7622724357992411,
+      "num_tokens": 34607967.0,
+      "step": 2090
+    },
+    {
+      "entropy": 0.9155510788783431,
+      "epoch": 6.7104,
+      "grad_norm": 7.78125,
+      "learning_rate": 1.755777777777778e-05,
+      "loss": 0.8703,
+      "mean_token_accuracy": 0.7665455520153046,
+      "num_tokens": 34767297.0,
+      "step": 2100
+    },
+    {
+      "epoch": 6.7104,
+      "eval_coding_entropy": 1.3831247334480286,
+      "eval_coding_loss": 2.4127957820892334,
+      "eval_coding_mean_token_accuracy": 0.5079380587339402,
+      "eval_coding_num_tokens": 34767297.0,
+      "eval_coding_runtime": 80.0354,
+      "eval_coding_samples_per_second": 6.247,
+      "eval_coding_steps_per_second": 3.124,
+      "step": 2100
+    },
+    {
+      "epoch": 6.7104,
+      "eval_physics_entropy": 0.948450217962265,
+      "eval_physics_loss": 1.2423639297485352,
+      "eval_physics_mean_token_accuracy": 0.712554681301117,
+      "eval_physics_num_tokens": 34767297.0,
+      "eval_physics_runtime": 51.0873,
+      "eval_physics_samples_per_second": 9.787,
+      "eval_physics_steps_per_second": 4.894,
+      "step": 2100
+    },
+    {
+      "entropy": 0.9181889228522777,
+      "epoch": 6.7424,
+      "grad_norm": 7.90625,
+      "learning_rate": 1.7535555555555556e-05,
+      "loss": 0.8632,
+      "mean_token_accuracy": 0.7635320980101824,
+      "num_tokens": 34934673.0,
+      "step": 2110
+    },
+    {
+      "entropy": 0.9264846274629235,
+      "epoch": 6.7744,
+      "grad_norm": 7.21875,
+      "learning_rate": 1.7513333333333334e-05,
+      "loss": 0.8849,
+      "mean_token_accuracy": 0.7640311282128096,
+      "num_tokens": 35095715.0,
+      "step": 2120
+    },
+    {
+      "entropy": 0.9454937249422073,
+      "epoch": 6.8064,
+      "grad_norm": 8.625,
+      "learning_rate": 1.749111111111111e-05,
+      "loss": 0.886,
+      "mean_token_accuracy": 0.76067238971591,
+      "num_tokens": 35252925.0,
+      "step": 2130
+    },
+    {
+      "entropy": 0.8765326388180256,
+      "epoch": 6.8384,
+      "grad_norm": 7.34375,
+      "learning_rate": 1.746888888888889e-05,
+      "loss": 0.8529,
+      "mean_token_accuracy": 0.771139046177268,
+      "num_tokens": 35421004.0,
+      "step": 2140
+    },
+    {
+      "entropy": 0.9181803734973073,
+      "epoch": 6.8704,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.7446666666666667e-05,
+      "loss": 0.8818,
+      "mean_token_accuracy": 0.7621538914740086,
+      "num_tokens": 35588850.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.9150473818182945,
+      "epoch": 6.9024,
+      "grad_norm": 7.1875,
+      "learning_rate": 1.7424444444444444e-05,
+      "loss": 0.8757,
+      "mean_token_accuracy": 0.7644228901714086,
+      "num_tokens": 35756753.0,
+      "step": 2160
+    },
+    {
+      "entropy": 0.9008896285668015,
+      "epoch": 6.9344,
+      "grad_norm": 7.34375,
+      "learning_rate": 1.7402222222222222e-05,
+      "loss": 0.8555,
+      "mean_token_accuracy": 0.7681890320032835,
+      "num_tokens": 35927158.0,
+      "step": 2170
+    },
+    {
+      "entropy": 0.9253141183406115,
+      "epoch": 6.9664,
+      "grad_norm": 9.125,
+      "learning_rate": 1.7380000000000003e-05,
+      "loss": 0.8772,
+      "mean_token_accuracy": 0.7653466906398535,
+      "num_tokens": 36090024.0,
+      "step": 2180
+    },
+    {
+      "entropy": 0.8797704441472888,
+      "epoch": 6.9984,
+      "grad_norm": 8.25,
+      "learning_rate": 1.735777777777778e-05,
+      "loss": 0.8474,
+      "mean_token_accuracy": 0.7717636529356241,
+      "num_tokens": 36258284.0,
+      "step": 2190
+    },
+    {
+      "entropy": 0.8152320165383188,
+      "epoch": 7.0288,
+      "grad_norm": 7.75,
+      "learning_rate": 1.7335555555555558e-05,
+      "loss": 0.7805,
+      "mean_token_accuracy": 0.7884461746404046,
+      "num_tokens": 36413412.0,
+      "step": 2200
+    },
+    {
+      "epoch": 7.0288,
+      "eval_coding_entropy": 1.3640027561187744,
+      "eval_coding_loss": 2.441347122192383,
+      "eval_coding_mean_token_accuracy": 0.5073574657440185,
+      "eval_coding_num_tokens": 36413412.0,
+      "eval_coding_runtime": 80.1284,
+      "eval_coding_samples_per_second": 6.24,
+      "eval_coding_steps_per_second": 3.12,
+      "step": 2200
+    },
+    {
+      "epoch": 7.0288,
+      "eval_physics_entropy": 0.9083407464027404,
+      "eval_physics_loss": 1.255447268486023,
+      "eval_physics_mean_token_accuracy": 0.7122914800643921,
+      "eval_physics_num_tokens": 36413412.0,
+      "eval_physics_runtime": 50.8376,
+      "eval_physics_samples_per_second": 9.835,
+      "eval_physics_steps_per_second": 4.918,
+      "step": 2200
+    },
+    {
+      "entropy": 0.8199690246954561,
+      "epoch": 7.0608,
+      "grad_norm": 6.71875,
+      "learning_rate": 1.7313333333333336e-05,
+      "loss": 0.7725,
+      "mean_token_accuracy": 0.7883035071194172,
+      "num_tokens": 36577814.0,
+      "step": 2210
+    },
+    {
+      "entropy": 0.8005543855950237,
+      "epoch": 7.0928,
+      "grad_norm": 6.34375,
+      "learning_rate": 1.7291111111111113e-05,
+      "loss": 0.7537,
+      "mean_token_accuracy": 0.792709443345666,
+      "num_tokens": 36743769.0,
+      "step": 2220
+    },
+    {
+      "entropy": 0.7737716905772686,
+      "epoch": 7.1248,
+      "grad_norm": 7.28125,
+      "learning_rate": 1.726888888888889e-05,
+      "loss": 0.7337,
+      "mean_token_accuracy": 0.7980268448591232,
+      "num_tokens": 36905500.0,
+      "step": 2230
+    },
+    {
+      "entropy": 0.7658384937793017,
+      "epoch": 7.1568,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.724666666666667e-05,
+      "loss": 0.722,
+      "mean_token_accuracy": 0.7982677388936281,
+      "num_tokens": 37072276.0,
+      "step": 2240
+    },
+    {
+      "entropy": 0.7949446378275752,
+      "epoch": 7.1888,
+      "grad_norm": 7.0625,
+      "learning_rate": 1.7224444444444446e-05,
+      "loss": 0.7447,
+      "mean_token_accuracy": 0.7916857376694679,
+      "num_tokens": 37243206.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.7903180595487356,
+      "epoch": 7.2208,
+      "grad_norm": 7.65625,
+      "learning_rate": 1.7202222222222224e-05,
+      "loss": 0.7493,
+      "mean_token_accuracy": 0.7914611048996448,
+      "num_tokens": 37403782.0,
+      "step": 2260
+    },
+    {
+      "entropy": 0.8121693830937147,
+      "epoch": 7.2528,
+      "grad_norm": 8.5,
+      "learning_rate": 1.718e-05,
+      "loss": 0.7584,
+      "mean_token_accuracy": 0.7896586664021015,
+      "num_tokens": 37579757.0,
+      "step": 2270
+    },
+    {
+      "entropy": 0.8230916598811746,
+      "epoch": 7.2848,
+      "grad_norm": 8.5,
+      "learning_rate": 1.715777777777778e-05,
+      "loss": 0.7654,
+      "mean_token_accuracy": 0.7857871890068054,
+      "num_tokens": 37748293.0,
+      "step": 2280
+    },
+    {
+      "entropy": 0.7982223512604832,
+      "epoch": 7.3168,
+      "grad_norm": 7.5,
+      "learning_rate": 1.7135555555555557e-05,
+      "loss": 0.7683,
+      "mean_token_accuracy": 0.7907465297728777,
+      "num_tokens": 37911700.0,
+      "step": 2290
+    },
+    {
+      "entropy": 0.7962693426758051,
+      "epoch": 7.3488,
+      "grad_norm": 7.0,
+      "learning_rate": 1.7113333333333334e-05,
+      "loss": 0.7486,
+      "mean_token_accuracy": 0.792203564196825,
+      "num_tokens": 38075680.0,
+      "step": 2300
+    },
+    {
+      "epoch": 7.3488,
+      "eval_coding_entropy": 1.287874354839325,
+      "eval_coding_loss": 2.5074503421783447,
+      "eval_coding_mean_token_accuracy": 0.5053789194822311,
+      "eval_coding_num_tokens": 38075680.0,
+      "eval_coding_runtime": 80.6264,
+      "eval_coding_samples_per_second": 6.201,
+      "eval_coding_steps_per_second": 3.101,
+      "step": 2300
+    },
+    {
+      "epoch": 7.3488,
+      "eval_physics_entropy": 0.8666039036512375,
+      "eval_physics_loss": 1.271466851234436,
+      "eval_physics_mean_token_accuracy": 0.7124857680797577,
+      "eval_physics_num_tokens": 38075680.0,
+      "eval_physics_runtime": 51.1957,
+      "eval_physics_samples_per_second": 9.766,
+      "eval_physics_steps_per_second": 4.883,
+      "step": 2300
+    },
+    {
+      "entropy": 0.7924799317494035,
+      "epoch": 7.3808,
+      "grad_norm": 6.9375,
+      "learning_rate": 1.7091111111111112e-05,
+      "loss": 0.7463,
+      "mean_token_accuracy": 0.7927690587937832,
+      "num_tokens": 38244451.0,
+      "step": 2310
+    },
+    {
+      "entropy": 0.8048048110678792,
+      "epoch": 7.4128,
+      "grad_norm": 8.5625,
+      "learning_rate": 1.706888888888889e-05,
+      "loss": 0.7566,
+      "mean_token_accuracy": 0.7889414615929127,
+      "num_tokens": 38412760.0,
+      "step": 2320
+    },
+    {
+      "entropy": 0.7931113267317415,
+      "epoch": 7.4448,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.704666666666667e-05,
+      "loss": 0.7602,
+      "mean_token_accuracy": 0.79053318426013,
+      "num_tokens": 38573566.0,
+      "step": 2330
+    },
+    {
+      "entropy": 0.8242617558687926,
+      "epoch": 7.4768,
+      "grad_norm": 7.1875,
+      "learning_rate": 1.7024444444444445e-05,
+      "loss": 0.7762,
+      "mean_token_accuracy": 0.7849719982594252,
+      "num_tokens": 38740056.0,
+      "step": 2340
+    },
+    {
+      "entropy": 0.8317271640524269,
+      "epoch": 7.5088,
+      "grad_norm": 7.75,
+      "learning_rate": 1.7002222222222226e-05,
+      "loss": 0.7815,
+      "mean_token_accuracy": 0.7838639069348574,
+      "num_tokens": 38905300.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.8092041697353125,
+      "epoch": 7.5408,
+      "grad_norm": 6.84375,
+      "learning_rate": 1.698e-05,
+      "loss": 0.7511,
+      "mean_token_accuracy": 0.7874078020453453,
+      "num_tokens": 39071340.0,
+      "step": 2360
+    },
+    {
+      "entropy": 0.7718355517834425,
+      "epoch": 7.5728,
+      "grad_norm": 7.59375,
+      "learning_rate": 1.695777777777778e-05,
+      "loss": 0.7366,
+      "mean_token_accuracy": 0.7969939954578876,
+      "num_tokens": 39241074.0,
+      "step": 2370
+    },
+    {
+      "entropy": 0.8089465990662574,
+      "epoch": 7.6048,
+      "grad_norm": 8.625,
+      "learning_rate": 1.6935555555555555e-05,
+      "loss": 0.769,
+      "mean_token_accuracy": 0.7888308063149452,
+      "num_tokens": 39406361.0,
+      "step": 2380
+    },
+    {
+      "entropy": 0.8250319881364703,
+      "epoch": 7.6368,
+      "grad_norm": 8.5625,
+      "learning_rate": 1.6913333333333336e-05,
+      "loss": 0.7913,
+      "mean_token_accuracy": 0.7831788897514343,
+      "num_tokens": 39565971.0,
+      "step": 2390
+    },
+    {
+      "entropy": 0.8007921712473035,
+      "epoch": 7.6688,
+      "grad_norm": 6.71875,
+      "learning_rate": 1.689111111111111e-05,
+      "loss": 0.7537,
+      "mean_token_accuracy": 0.7911801379173994,
+      "num_tokens": 39732063.0,
+      "step": 2400
+    },
+    {
+      "epoch": 7.6688,
+      "eval_coding_entropy": 1.2879135403633117,
+      "eval_coding_loss": 2.5043892860412598,
+      "eval_coding_mean_token_accuracy": 0.5054650387763977,
+      "eval_coding_num_tokens": 39732063.0,
+      "eval_coding_runtime": 80.6584,
+      "eval_coding_samples_per_second": 6.199,
+      "eval_coding_steps_per_second": 3.099,
+      "step": 2400
+    },
+    {
+      "epoch": 7.6688,
+      "eval_physics_entropy": 0.8899753086566925,
+      "eval_physics_loss": 1.2538994550704956,
+      "eval_physics_mean_token_accuracy": 0.7139942421913147,
+      "eval_physics_num_tokens": 39732063.0,
+      "eval_physics_runtime": 51.2089,
+      "eval_physics_samples_per_second": 9.764,
+      "eval_physics_steps_per_second": 4.882,
+      "step": 2400
+    },
+    {
+      "entropy": 0.8204136060550808,
+      "epoch": 7.7008,
+      "grad_norm": 8.3125,
+      "learning_rate": 1.686888888888889e-05,
+      "loss": 0.7736,
+      "mean_token_accuracy": 0.7871936142444611,
+      "num_tokens": 39893958.0,
+      "step": 2410
+    },
+    {
+      "entropy": 0.8038571827113629,
+      "epoch": 7.7328,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.684666666666667e-05,
+      "loss": 0.7666,
+      "mean_token_accuracy": 0.7876993417739868,
+      "num_tokens": 40056286.0,
+      "step": 2420
+    },
+    {
+      "entropy": 0.7649493917822838,
+      "epoch": 7.7648,
+      "grad_norm": 7.28125,
+      "learning_rate": 1.6824444444444447e-05,
+      "loss": 0.7237,
+      "mean_token_accuracy": 0.7977251056581736,
+      "num_tokens": 40224885.0,
+      "step": 2430
+    },
+    {
+      "entropy": 0.8389663999900222,
+      "epoch": 7.7968,
+      "grad_norm": 7.9375,
+      "learning_rate": 1.6802222222222224e-05,
+      "loss": 0.7836,
+      "mean_token_accuracy": 0.7819656167179346,
+      "num_tokens": 40386001.0,
+      "step": 2440
+    },
+    {
+      "entropy": 0.8192150767892599,
+      "epoch": 7.8288,
+      "grad_norm": 7.3125,
+      "learning_rate": 1.6780000000000002e-05,
+      "loss": 0.7741,
+      "mean_token_accuracy": 0.7869136918336153,
+      "num_tokens": 40550394.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.8238677924498916,
+      "epoch": 7.8608,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.675777777777778e-05,
+      "loss": 0.7798,
+      "mean_token_accuracy": 0.786088028550148,
+      "num_tokens": 40714123.0,
+      "step": 2460
+    },
+    {
+      "entropy": 0.822707281820476,
+      "epoch": 7.8928,
+      "grad_norm": 7.75,
+      "learning_rate": 1.6735555555555557e-05,
+      "loss": 0.7852,
+      "mean_token_accuracy": 0.7847356092184782,
+      "num_tokens": 40878910.0,
+      "step": 2470
+    },
+    {
+      "entropy": 0.7849974310025573,
+      "epoch": 7.9248,
+      "grad_norm": 7.09375,
+      "learning_rate": 1.6713333333333335e-05,
+      "loss": 0.7509,
+      "mean_token_accuracy": 0.7924100607633591,
+      "num_tokens": 41048568.0,
+      "step": 2480
+    },
+    {
+      "entropy": 0.8023886883631348,
+      "epoch": 7.9568,
+      "grad_norm": 7.28125,
+      "learning_rate": 1.6691111111111112e-05,
+      "loss": 0.7632,
+      "mean_token_accuracy": 0.7890365641564131,
+      "num_tokens": 41215871.0,
+      "step": 2490
+    },
+    {
+      "entropy": 0.8149305360391736,
+      "epoch": 7.9888,
+      "grad_norm": 6.875,
+      "learning_rate": 1.666888888888889e-05,
+      "loss": 0.7698,
+      "mean_token_accuracy": 0.7843944601714611,
+      "num_tokens": 41389758.0,
+      "step": 2500
+    },
+    {
+      "epoch": 7.9888,
+      "eval_coding_entropy": 1.306984958410263,
+      "eval_coding_loss": 2.501882791519165,
+      "eval_coding_mean_token_accuracy": 0.5061199169158935,
+      "eval_coding_num_tokens": 41389758.0,
+      "eval_coding_runtime": 80.3039,
+      "eval_coding_samples_per_second": 6.226,
+      "eval_coding_steps_per_second": 3.113,
+      "step": 2500
+    },
+    {
+      "epoch": 7.9888,
+      "eval_physics_entropy": 0.8865963050127029,
+      "eval_physics_loss": 1.246237874031067,
+      "eval_physics_mean_token_accuracy": 0.7165059688091278,
+      "eval_physics_num_tokens": 41389758.0,
+      "eval_physics_runtime": 50.4383,
+      "eval_physics_samples_per_second": 9.913,
+      "eval_physics_steps_per_second": 4.957,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 32,
+  "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": 2.599915186815615e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83c1fc92689b78591cfacf5d391db2a2b258cc12a1565bf88bbb8100f92f13d
+size 6353