Upload folder using huggingface_hub

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 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-2000/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_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 + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-2000/config.json

@@ -0,0 +1,86 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3840,
+  "initializer_range": 0.02,
+  "intermediate_size": 15360,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": {
+    "factor": 8.0,
+    "rope_type": "linear"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 1024,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 262208
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.56.1"
+}

checkpoint-2000/model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4c14f38ffc9e23d873fa999eea1fc965dcedcec267e7a99f07c6fdbe8760d8
+size 4915892992

checkpoint-2000/model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0335ce336b31e38c581326acb77ff28330c2073764b1924ad7108d788b56ba68
+size 4931294472

checkpoint-2000/model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d6a60cf6a1708be0613ab7c4d10457ad99b98c02e40ebd5f320fe02aa0d50c
+size 4931294528

checkpoint-2000/model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd9340bc368427bcc805e329f32ec7f6a73ab12274d00a8b9c03d49fe0853d0
+size 4931294528

checkpoint-2000/model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d80ec30fa09df9cb78149b3af4da5e7f22bbe89087198871d4f36c70903e30a6
+size 3822364808

checkpoint-2000/model.safetensors.index.json

@@ -0,0 +1,634 @@
+{
+  "metadata": {
+    "total_parameters": 11766034176,
+    "total_size": 23532068352
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086069abddf33788aa14f88cc69494ac6ca08415d49ad9112f04cb8aef5f9af1
+size 18355

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7993dc63b304673dcc82de3f9b7ca8dddf6548aee44d77968103b480a102016
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95ad2f3950cee1b83b106cf88750c8604566acab211d78973b3b5c4917b1a30
+size 1465

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "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-2000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-2000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-2000/trainer_state.json

@@ -0,0 +1,2474 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 100,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.085290367901325,
+      "epoch": 0.008,
+      "grad_norm": 0.0146484375,
+      "learning_rate": 1.8e-07,
+      "loss": 2.8737,
+      "mean_token_accuracy": 0.48555898685008286,
+      "num_tokens": 173886.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.082674165070057,
+      "epoch": 0.016,
+      "grad_norm": 0.00750732421875,
+      "learning_rate": 3.8e-07,
+      "loss": 2.8766,
+      "mean_token_accuracy": 0.48314503096044065,
+      "num_tokens": 338352.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.083346585184336,
+      "epoch": 0.024,
+      "grad_norm": 0.01116943359375,
+      "learning_rate": 5.800000000000001e-07,
+      "loss": 2.8206,
+      "mean_token_accuracy": 0.4898203007876873,
+      "num_tokens": 505613.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.084573998302221,
+      "epoch": 0.032,
+      "grad_norm": 0.01361083984375,
+      "learning_rate": 7.8e-07,
+      "loss": 2.846,
+      "mean_token_accuracy": 0.4879810094833374,
+      "num_tokens": 671193.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.112175610661507,
+      "epoch": 0.04,
+      "grad_norm": 0.0184326171875,
+      "learning_rate": 9.800000000000001e-07,
+      "loss": 2.8945,
+      "mean_token_accuracy": 0.48235367350280284,
+      "num_tokens": 835868.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.004745631664991,
+      "epoch": 0.048,
+      "grad_norm": 0.01055908203125,
+      "learning_rate": 1.1800000000000001e-06,
+      "loss": 2.7943,
+      "mean_token_accuracy": 0.4953182445839047,
+      "num_tokens": 1001008.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.0760968685150147,
+      "epoch": 0.056,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 2.8689,
+      "mean_token_accuracy": 0.48274643896147607,
+      "num_tokens": 1166615.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.1421599693596365,
+      "epoch": 0.064,
+      "grad_norm": 0.01226806640625,
+      "learning_rate": 1.5800000000000001e-06,
+      "loss": 2.927,
+      "mean_token_accuracy": 0.47564963400363924,
+      "num_tokens": 1331208.0,
+      "step": 80
+    },
+    {
+      "entropy": 2.0629068821668626,
+      "epoch": 0.072,
+      "grad_norm": 0.00994873046875,
+      "learning_rate": 1.7800000000000001e-06,
+      "loss": 2.8669,
+      "mean_token_accuracy": 0.48655857108533385,
+      "num_tokens": 1499449.0,
+      "step": 90
+    },
+    {
+      "entropy": 2.1223726868629456,
+      "epoch": 0.08,
+      "grad_norm": 0.0184326171875,
+      "learning_rate": 1.98e-06,
+      "loss": 2.8834,
+      "mean_token_accuracy": 0.48028963077813386,
+      "num_tokens": 1667532.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 1667532.0,
+      "eval_coding_runtime": 96.0471,
+      "eval_coding_samples_per_second": 5.206,
+      "eval_coding_steps_per_second": 2.603,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 1667532.0,
+      "eval_physics_runtime": 63.6847,
+      "eval_physics_samples_per_second": 7.851,
+      "eval_physics_steps_per_second": 3.926,
+      "step": 100
+    },
+    {
+      "entropy": 2.028460328280926,
+      "epoch": 0.088,
+      "grad_norm": 0.00732421875,
+      "learning_rate": 2.1800000000000003e-06,
+      "loss": 2.7998,
+      "mean_token_accuracy": 0.4919602179899812,
+      "num_tokens": 1835489.0,
+      "step": 110
+    },
+    {
+      "entropy": 2.0500536493957044,
+      "epoch": 0.096,
+      "grad_norm": 0.0166015625,
+      "learning_rate": 2.38e-06,
+      "loss": 2.843,
+      "mean_token_accuracy": 0.486666096188128,
+      "num_tokens": 2007176.0,
+      "step": 120
+    },
+    {
+      "entropy": 2.133950074762106,
+      "epoch": 0.104,
+      "grad_norm": 0.00897216796875,
+      "learning_rate": 2.5800000000000003e-06,
+      "loss": 2.908,
+      "mean_token_accuracy": 0.47787463404238223,
+      "num_tokens": 2171335.0,
+      "step": 130
+    },
+    {
+      "entropy": 2.0415130145847797,
+      "epoch": 0.112,
+      "grad_norm": 0.0125732421875,
+      "learning_rate": 2.7800000000000005e-06,
+      "loss": 2.8213,
+      "mean_token_accuracy": 0.48844432439655067,
+      "num_tokens": 2342259.0,
+      "step": 140
+    },
+    {
+      "entropy": 2.19760585129261,
+      "epoch": 0.12,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 2.9800000000000003e-06,
+      "loss": 2.9587,
+      "mean_token_accuracy": 0.4719714432954788,
+      "num_tokens": 2504279.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.133862767368555,
+      "epoch": 0.128,
+      "grad_norm": 0.0101318359375,
+      "learning_rate": 3.1800000000000005e-06,
+      "loss": 2.895,
+      "mean_token_accuracy": 0.48206167966127395,
+      "num_tokens": 2663987.0,
+      "step": 160
+    },
+    {
+      "entropy": 2.1023842833936213,
+      "epoch": 0.136,
+      "grad_norm": 0.00836181640625,
+      "learning_rate": 3.3800000000000007e-06,
+      "loss": 2.8679,
+      "mean_token_accuracy": 0.48314376436173917,
+      "num_tokens": 2829720.0,
+      "step": 170
+    },
+    {
+      "entropy": 2.096611645817757,
+      "epoch": 0.144,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 3.58e-06,
+      "loss": 2.882,
+      "mean_token_accuracy": 0.4854999572038651,
+      "num_tokens": 2997824.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.104377479106188,
+      "epoch": 0.152,
+      "grad_norm": 0.00860595703125,
+      "learning_rate": 3.7800000000000002e-06,
+      "loss": 2.8908,
+      "mean_token_accuracy": 0.48179021421819923,
+      "num_tokens": 3159946.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.091322401165962,
+      "epoch": 0.16,
+      "grad_norm": 0.00927734375,
+      "learning_rate": 3.980000000000001e-06,
+      "loss": 2.8428,
+      "mean_token_accuracy": 0.4882024429738522,
+      "num_tokens": 3330597.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 3330597.0,
+      "eval_coding_runtime": 95.6196,
+      "eval_coding_samples_per_second": 5.229,
+      "eval_coding_steps_per_second": 2.615,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 3330597.0,
+      "eval_physics_runtime": 63.6492,
+      "eval_physics_samples_per_second": 7.856,
+      "eval_physics_steps_per_second": 3.928,
+      "step": 200
+    },
+    {
+      "entropy": 2.142216607928276,
+      "epoch": 0.168,
+      "grad_norm": 0.00701904296875,
+      "learning_rate": 4.18e-06,
+      "loss": 2.9186,
+      "mean_token_accuracy": 0.4779110599309206,
+      "num_tokens": 3496104.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.1577497258782388,
+      "epoch": 0.176,
+      "grad_norm": 0.010498046875,
+      "learning_rate": 4.38e-06,
+      "loss": 2.9356,
+      "mean_token_accuracy": 0.4760912239551544,
+      "num_tokens": 3658264.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.1311790965497495,
+      "epoch": 0.184,
+      "grad_norm": 0.006317138671875,
+      "learning_rate": 4.58e-06,
+      "loss": 2.8804,
+      "mean_token_accuracy": 0.48113634046167136,
+      "num_tokens": 3821352.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.110344947129488,
+      "epoch": 0.192,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 4.78e-06,
+      "loss": 2.8458,
+      "mean_token_accuracy": 0.4866057766601443,
+      "num_tokens": 3995568.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.1274008348584177,
+      "epoch": 0.2,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 4.980000000000001e-06,
+      "loss": 2.9325,
+      "mean_token_accuracy": 0.47856651023030283,
+      "num_tokens": 4160918.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.0445496000349523,
+      "epoch": 0.208,
+      "grad_norm": 0.0072021484375,
+      "learning_rate": 5.18e-06,
+      "loss": 2.7895,
+      "mean_token_accuracy": 0.49246302992105484,
+      "num_tokens": 4321436.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.118650445342064,
+      "epoch": 0.216,
+      "grad_norm": 0.0118408203125,
+      "learning_rate": 5.380000000000001e-06,
+      "loss": 2.831,
+      "mean_token_accuracy": 0.48565028738230465,
+      "num_tokens": 4482225.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.0710766136646273,
+      "epoch": 0.224,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 5.580000000000001e-06,
+      "loss": 2.8524,
+      "mean_token_accuracy": 0.4889204766601324,
+      "num_tokens": 4648491.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.0747790560126305,
+      "epoch": 0.232,
+      "grad_norm": 0.009033203125,
+      "learning_rate": 5.78e-06,
+      "loss": 2.8736,
+      "mean_token_accuracy": 0.4836031161248684,
+      "num_tokens": 4813449.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.1116694904863835,
+      "epoch": 0.24,
+      "grad_norm": 0.01141357421875,
+      "learning_rate": 5.98e-06,
+      "loss": 2.8974,
+      "mean_token_accuracy": 0.47815693244338037,
+      "num_tokens": 4986175.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.24,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 4986175.0,
+      "eval_coding_runtime": 95.7299,
+      "eval_coding_samples_per_second": 5.223,
+      "eval_coding_steps_per_second": 2.612,
+      "step": 300
+    },
+    {
+      "epoch": 0.24,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 4986175.0,
+      "eval_physics_runtime": 63.6784,
+      "eval_physics_samples_per_second": 7.852,
+      "eval_physics_steps_per_second": 3.926,
+      "step": 300
+    },
+    {
+      "entropy": 2.085676248371601,
+      "epoch": 0.248,
+      "grad_norm": 0.01513671875,
+      "learning_rate": 6.18e-06,
+      "loss": 2.8547,
+      "mean_token_accuracy": 0.4871716873720288,
+      "num_tokens": 5164741.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.111249604821205,
+      "epoch": 0.256,
+      "grad_norm": 0.01324462890625,
+      "learning_rate": 6.380000000000001e-06,
+      "loss": 2.869,
+      "mean_token_accuracy": 0.482149850204587,
+      "num_tokens": 5329320.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.0735500395298003,
+      "epoch": 0.264,
+      "grad_norm": 0.01300048828125,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 2.815,
+      "mean_token_accuracy": 0.4895795300602913,
+      "num_tokens": 5497259.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.1957527093589304,
+      "epoch": 0.272,
+      "grad_norm": 0.0155029296875,
+      "learning_rate": 6.780000000000001e-06,
+      "loss": 2.9296,
+      "mean_token_accuracy": 0.4737250735983253,
+      "num_tokens": 5658796.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.0978702254593373,
+      "epoch": 0.28,
+      "grad_norm": 0.012939453125,
+      "learning_rate": 6.98e-06,
+      "loss": 2.9223,
+      "mean_token_accuracy": 0.47742239478975534,
+      "num_tokens": 5819027.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.126638425886631,
+      "epoch": 0.288,
+      "grad_norm": 0.01104736328125,
+      "learning_rate": 7.180000000000001e-06,
+      "loss": 2.8822,
+      "mean_token_accuracy": 0.48392471522092817,
+      "num_tokens": 5980201.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.1021372735500337,
+      "epoch": 0.296,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 7.3800000000000005e-06,
+      "loss": 2.8638,
+      "mean_token_accuracy": 0.4845348121598363,
+      "num_tokens": 6139830.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.1106897443532944,
+      "epoch": 0.304,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 7.58e-06,
+      "loss": 2.8357,
+      "mean_token_accuracy": 0.4834788400679827,
+      "num_tokens": 6298858.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.143523923307657,
+      "epoch": 0.312,
+      "grad_norm": 0.00958251953125,
+      "learning_rate": 7.78e-06,
+      "loss": 2.9236,
+      "mean_token_accuracy": 0.47671638112515213,
+      "num_tokens": 6456502.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.1132052429020405,
+      "epoch": 0.32,
+      "grad_norm": 0.01336669921875,
+      "learning_rate": 7.980000000000002e-06,
+      "loss": 2.8795,
+      "mean_token_accuracy": 0.48184755612164737,
+      "num_tokens": 6622798.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 6622798.0,
+      "eval_coding_runtime": 95.588,
+      "eval_coding_samples_per_second": 5.231,
+      "eval_coding_steps_per_second": 2.615,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 6622798.0,
+      "eval_physics_runtime": 63.5621,
+      "eval_physics_samples_per_second": 7.866,
+      "eval_physics_steps_per_second": 3.933,
+      "step": 400
+    },
+    {
+      "entropy": 2.1359100699424745,
+      "epoch": 0.328,
+      "grad_norm": 0.01220703125,
+      "learning_rate": 8.18e-06,
+      "loss": 2.892,
+      "mean_token_accuracy": 0.4762568075209856,
+      "num_tokens": 6782985.0,
+      "step": 410
+    },
+    {
+      "entropy": 2.080799935385585,
+      "epoch": 0.336,
+      "grad_norm": 0.021484375,
+      "learning_rate": 8.380000000000001e-06,
+      "loss": 2.8705,
+      "mean_token_accuracy": 0.4826640056446195,
+      "num_tokens": 6953611.0,
+      "step": 420
+    },
+    {
+      "entropy": 2.0621030911803246,
+      "epoch": 0.344,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 2.777,
+      "mean_token_accuracy": 0.48948597013950346,
+      "num_tokens": 7121949.0,
+      "step": 430
+    },
+    {
+      "entropy": 2.0954283088445664,
+      "epoch": 0.352,
+      "grad_norm": 0.01080322265625,
+      "learning_rate": 8.78e-06,
+      "loss": 2.8529,
+      "mean_token_accuracy": 0.48598715253174307,
+      "num_tokens": 7290378.0,
+      "step": 440
+    },
+    {
+      "entropy": 2.1145325861871243,
+      "epoch": 0.36,
+      "grad_norm": 0.01611328125,
+      "learning_rate": 8.98e-06,
+      "loss": 2.864,
+      "mean_token_accuracy": 0.48475142791867254,
+      "num_tokens": 7452920.0,
+      "step": 450
+    },
+    {
+      "entropy": 2.0749227844178675,
+      "epoch": 0.368,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 9.180000000000002e-06,
+      "loss": 2.842,
+      "mean_token_accuracy": 0.4888931142166257,
+      "num_tokens": 7621082.0,
+      "step": 460
+    },
+    {
+      "entropy": 2.158674482256174,
+      "epoch": 0.376,
+      "grad_norm": 0.0189208984375,
+      "learning_rate": 9.38e-06,
+      "loss": 2.8965,
+      "mean_token_accuracy": 0.47893171701580284,
+      "num_tokens": 7787036.0,
+      "step": 470
+    },
+    {
+      "entropy": 2.172913119196892,
+      "epoch": 0.384,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 9.58e-06,
+      "loss": 2.9484,
+      "mean_token_accuracy": 0.47502864580601456,
+      "num_tokens": 7955570.0,
+      "step": 480
+    },
+    {
+      "entropy": 2.133708968013525,
+      "epoch": 0.392,
+      "grad_norm": 0.0089111328125,
+      "learning_rate": 9.780000000000001e-06,
+      "loss": 2.9115,
+      "mean_token_accuracy": 0.481097811833024,
+      "num_tokens": 8123527.0,
+      "step": 490
+    },
+    {
+      "entropy": 2.075808613747358,
+      "epoch": 0.4,
+      "grad_norm": 0.01458740234375,
+      "learning_rate": 9.980000000000001e-06,
+      "loss": 2.8509,
+      "mean_token_accuracy": 0.4880217058584094,
+      "num_tokens": 8291049.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 8291049.0,
+      "eval_coding_runtime": 95.8745,
+      "eval_coding_samples_per_second": 5.215,
+      "eval_coding_steps_per_second": 2.608,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 8291049.0,
+      "eval_physics_runtime": 63.2475,
+      "eval_physics_samples_per_second": 7.905,
+      "eval_physics_steps_per_second": 3.953,
+      "step": 500
+    },
+    {
+      "entropy": 2.0808891989290714,
+      "epoch": 0.408,
+      "grad_norm": 0.00933837890625,
+      "learning_rate": 1.018e-05,
+      "loss": 2.8602,
+      "mean_token_accuracy": 0.48418706730008126,
+      "num_tokens": 8459795.0,
+      "step": 510
+    },
+    {
+      "entropy": 2.108520568162203,
+      "epoch": 0.416,
+      "grad_norm": 0.01300048828125,
+      "learning_rate": 1.038e-05,
+      "loss": 2.8709,
+      "mean_token_accuracy": 0.4807485779747367,
+      "num_tokens": 8627310.0,
+      "step": 520
+    },
+    {
+      "entropy": 2.095228637009859,
+      "epoch": 0.424,
+      "grad_norm": 0.0186767578125,
+      "learning_rate": 1.0580000000000002e-05,
+      "loss": 2.8575,
+      "mean_token_accuracy": 0.4873119568452239,
+      "num_tokens": 8792574.0,
+      "step": 530
+    },
+    {
+      "entropy": 2.0733875431120397,
+      "epoch": 0.432,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 1.0780000000000002e-05,
+      "loss": 2.8746,
+      "mean_token_accuracy": 0.48152947407215835,
+      "num_tokens": 8958371.0,
+      "step": 540
+    },
+    {
+      "entropy": 2.0743850864470006,
+      "epoch": 0.44,
+      "grad_norm": 0.0142822265625,
+      "learning_rate": 1.0980000000000002e-05,
+      "loss": 2.8417,
+      "mean_token_accuracy": 0.48614103216677906,
+      "num_tokens": 9125564.0,
+      "step": 550
+    },
+    {
+      "entropy": 2.0296142108738424,
+      "epoch": 0.448,
+      "grad_norm": 0.00909423828125,
+      "learning_rate": 1.1180000000000001e-05,
+      "loss": 2.8092,
+      "mean_token_accuracy": 0.49211322125047446,
+      "num_tokens": 9294388.0,
+      "step": 560
+    },
+    {
+      "entropy": 2.042448101937771,
+      "epoch": 0.456,
+      "grad_norm": 0.00897216796875,
+      "learning_rate": 1.138e-05,
+      "loss": 2.8196,
+      "mean_token_accuracy": 0.4887328814715147,
+      "num_tokens": 9455428.0,
+      "step": 570
+    },
+    {
+      "entropy": 2.124661027640104,
+      "epoch": 0.464,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 1.1580000000000001e-05,
+      "loss": 2.8825,
+      "mean_token_accuracy": 0.4844032688066363,
+      "num_tokens": 9620366.0,
+      "step": 580
+    },
+    {
+      "entropy": 2.0920108027756212,
+      "epoch": 0.472,
+      "grad_norm": 0.01458740234375,
+      "learning_rate": 1.178e-05,
+      "loss": 2.8011,
+      "mean_token_accuracy": 0.49246231019496917,
+      "num_tokens": 9788925.0,
+      "step": 590
+    },
+    {
+      "entropy": 2.0895667865872385,
+      "epoch": 0.48,
+      "grad_norm": 0.007568359375,
+      "learning_rate": 1.198e-05,
+      "loss": 2.8784,
+      "mean_token_accuracy": 0.4846471020951867,
+      "num_tokens": 9955431.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.48,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 9955431.0,
+      "eval_coding_runtime": 95.6269,
+      "eval_coding_samples_per_second": 5.229,
+      "eval_coding_steps_per_second": 2.614,
+      "step": 600
+    },
+    {
+      "epoch": 0.48,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 9955431.0,
+      "eval_physics_runtime": 63.6584,
+      "eval_physics_samples_per_second": 7.854,
+      "eval_physics_steps_per_second": 3.927,
+      "step": 600
+    },
+    {
+      "entropy": 2.1037806943058968,
+      "epoch": 0.488,
+      "grad_norm": 0.01434326171875,
+      "learning_rate": 1.218e-05,
+      "loss": 2.8897,
+      "mean_token_accuracy": 0.48129043709486724,
+      "num_tokens": 10119599.0,
+      "step": 610
+    },
+    {
+      "entropy": 2.1045577257871626,
+      "epoch": 0.496,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 1.2380000000000002e-05,
+      "loss": 2.8986,
+      "mean_token_accuracy": 0.4801080621778965,
+      "num_tokens": 10289883.0,
+      "step": 620
+    },
+    {
+      "entropy": 2.1075518101453783,
+      "epoch": 0.504,
+      "grad_norm": 0.007354736328125,
+      "learning_rate": 1.2580000000000002e-05,
+      "loss": 2.8519,
+      "mean_token_accuracy": 0.4833444032818079,
+      "num_tokens": 10454683.0,
+      "step": 630
+    },
+    {
+      "entropy": 2.106730377674103,
+      "epoch": 0.512,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 1.2780000000000001e-05,
+      "loss": 2.9125,
+      "mean_token_accuracy": 0.4791097413748503,
+      "num_tokens": 10619468.0,
+      "step": 640
+    },
+    {
+      "entropy": 2.149070845544338,
+      "epoch": 0.52,
+      "grad_norm": 0.017822265625,
+      "learning_rate": 1.2980000000000001e-05,
+      "loss": 2.9383,
+      "mean_token_accuracy": 0.4766066731885076,
+      "num_tokens": 10781285.0,
+      "step": 650
+    },
+    {
+      "entropy": 2.109221810847521,
+      "epoch": 0.528,
+      "grad_norm": 0.01123046875,
+      "learning_rate": 1.3180000000000001e-05,
+      "loss": 2.8512,
+      "mean_token_accuracy": 0.48691278155893086,
+      "num_tokens": 10944904.0,
+      "step": 660
+    },
+    {
+      "entropy": 2.10501976236701,
+      "epoch": 0.536,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 1.3380000000000002e-05,
+      "loss": 2.8583,
+      "mean_token_accuracy": 0.48396560084074736,
+      "num_tokens": 11106538.0,
+      "step": 670
+    },
+    {
+      "entropy": 2.1422630779445173,
+      "epoch": 0.544,
+      "grad_norm": 0.013916015625,
+      "learning_rate": 1.3580000000000002e-05,
+      "loss": 2.9198,
+      "mean_token_accuracy": 0.4756466532126069,
+      "num_tokens": 11266409.0,
+      "step": 680
+    },
+    {
+      "entropy": 2.066490865498781,
+      "epoch": 0.552,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 1.378e-05,
+      "loss": 2.8749,
+      "mean_token_accuracy": 0.48253467567265035,
+      "num_tokens": 11438391.0,
+      "step": 690
+    },
+    {
+      "entropy": 2.1218110136687756,
+      "epoch": 0.56,
+      "grad_norm": 0.00811767578125,
+      "learning_rate": 1.398e-05,
+      "loss": 2.8685,
+      "mean_token_accuracy": 0.4830782825127244,
+      "num_tokens": 11605544.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.56,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 11605544.0,
+      "eval_coding_runtime": 95.6063,
+      "eval_coding_samples_per_second": 5.23,
+      "eval_coding_steps_per_second": 2.615,
+      "step": 700
+    },
+    {
+      "epoch": 0.56,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 11605544.0,
+      "eval_physics_runtime": 63.652,
+      "eval_physics_samples_per_second": 7.855,
+      "eval_physics_steps_per_second": 3.928,
+      "step": 700
+    },
+    {
+      "entropy": 2.0374118871986866,
+      "epoch": 0.568,
+      "grad_norm": 0.0164794921875,
+      "learning_rate": 1.418e-05,
+      "loss": 2.8443,
+      "mean_token_accuracy": 0.48784226551651955,
+      "num_tokens": 11765430.0,
+      "step": 710
+    },
+    {
+      "entropy": 2.079664882272482,
+      "epoch": 0.576,
+      "grad_norm": 0.01336669921875,
+      "learning_rate": 1.4380000000000001e-05,
+      "loss": 2.8436,
+      "mean_token_accuracy": 0.4859828842803836,
+      "num_tokens": 11931715.0,
+      "step": 720
+    },
+    {
+      "entropy": 2.091735219210386,
+      "epoch": 0.584,
+      "grad_norm": 0.00836181640625,
+      "learning_rate": 1.4580000000000001e-05,
+      "loss": 2.891,
+      "mean_token_accuracy": 0.4845219163224101,
+      "num_tokens": 12093686.0,
+      "step": 730
+    },
+    {
+      "entropy": 2.092084125429392,
+      "epoch": 0.592,
+      "grad_norm": 0.01153564453125,
+      "learning_rate": 1.478e-05,
+      "loss": 2.8884,
+      "mean_token_accuracy": 0.4797184634953737,
+      "num_tokens": 12257243.0,
+      "step": 740
+    },
+    {
+      "entropy": 2.138279449939728,
+      "epoch": 0.6,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 1.498e-05,
+      "loss": 2.8937,
+      "mean_token_accuracy": 0.4808414502069354,
+      "num_tokens": 12422008.0,
+      "step": 750
+    },
+    {
+      "entropy": 2.025119251012802,
+      "epoch": 0.608,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 1.5180000000000002e-05,
+      "loss": 2.801,
+      "mean_token_accuracy": 0.4929833130910993,
+      "num_tokens": 12583154.0,
+      "step": 760
+    },
+    {
+      "entropy": 2.068293011188507,
+      "epoch": 0.616,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 1.5380000000000002e-05,
+      "loss": 2.8332,
+      "mean_token_accuracy": 0.4890221064910293,
+      "num_tokens": 12746458.0,
+      "step": 770
+    },
+    {
+      "entropy": 2.1028603583574297,
+      "epoch": 0.624,
+      "grad_norm": 0.009033203125,
+      "learning_rate": 1.5580000000000003e-05,
+      "loss": 2.9238,
+      "mean_token_accuracy": 0.4755176778882742,
+      "num_tokens": 12905392.0,
+      "step": 780
+    },
+    {
+      "entropy": 2.103465436398983,
+      "epoch": 0.632,
+      "grad_norm": 0.012939453125,
+      "learning_rate": 1.578e-05,
+      "loss": 2.8914,
+      "mean_token_accuracy": 0.48264262825250626,
+      "num_tokens": 13071058.0,
+      "step": 790
+    },
+    {
+      "entropy": 2.107102530449629,
+      "epoch": 0.64,
+      "grad_norm": 0.01373291015625,
+      "learning_rate": 1.5980000000000003e-05,
+      "loss": 2.8937,
+      "mean_token_accuracy": 0.4812551226466894,
+      "num_tokens": 13232198.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.64,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 13232198.0,
+      "eval_coding_runtime": 95.5879,
+      "eval_coding_samples_per_second": 5.231,
+      "eval_coding_steps_per_second": 2.615,
+      "step": 800
+    },
+    {
+      "epoch": 0.64,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 13232198.0,
+      "eval_physics_runtime": 63.5241,
+      "eval_physics_samples_per_second": 7.871,
+      "eval_physics_steps_per_second": 3.936,
+      "step": 800
+    },
+    {
+      "entropy": 2.1226571217179298,
+      "epoch": 0.648,
+      "grad_norm": 0.010009765625,
+      "learning_rate": 1.618e-05,
+      "loss": 2.8715,
+      "mean_token_accuracy": 0.48374479077756405,
+      "num_tokens": 13401064.0,
+      "step": 810
+    },
+    {
+      "entropy": 2.071519161760807,
+      "epoch": 0.656,
+      "grad_norm": 0.007476806640625,
+      "learning_rate": 1.638e-05,
+      "loss": 2.8209,
+      "mean_token_accuracy": 0.48990428987890483,
+      "num_tokens": 13575902.0,
+      "step": 820
+    },
+    {
+      "entropy": 2.1139444075524807,
+      "epoch": 0.664,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 1.658e-05,
+      "loss": 2.9185,
+      "mean_token_accuracy": 0.48024304024875164,
+      "num_tokens": 13733192.0,
+      "step": 830
+    },
+    {
+      "entropy": 2.1097038336098195,
+      "epoch": 0.672,
+      "grad_norm": 0.0201416015625,
+      "learning_rate": 1.6780000000000002e-05,
+      "loss": 2.856,
+      "mean_token_accuracy": 0.48414181135594847,
+      "num_tokens": 13895997.0,
+      "step": 840
+    },
+    {
+      "entropy": 2.0350618422031403,
+      "epoch": 0.68,
+      "grad_norm": 0.007354736328125,
+      "learning_rate": 1.698e-05,
+      "loss": 2.8006,
+      "mean_token_accuracy": 0.49249137472361326,
+      "num_tokens": 14074579.0,
+      "step": 850
+    },
+    {
+      "entropy": 2.1360582523047924,
+      "epoch": 0.688,
+      "grad_norm": 0.012939453125,
+      "learning_rate": 1.718e-05,
+      "loss": 2.9135,
+      "mean_token_accuracy": 0.48240375574678185,
+      "num_tokens": 14234888.0,
+      "step": 860
+    },
+    {
+      "entropy": 2.0854096628725527,
+      "epoch": 0.696,
+      "grad_norm": 0.0159912109375,
+      "learning_rate": 1.7380000000000003e-05,
+      "loss": 2.8889,
+      "mean_token_accuracy": 0.48132998365908863,
+      "num_tokens": 14411150.0,
+      "step": 870
+    },
+    {
+      "entropy": 2.1598948813974856,
+      "epoch": 0.704,
+      "grad_norm": 0.0067138671875,
+      "learning_rate": 1.758e-05,
+      "loss": 2.941,
+      "mean_token_accuracy": 0.47370197977870704,
+      "num_tokens": 14567908.0,
+      "step": 880
+    },
+    {
+      "entropy": 2.1014511175453663,
+      "epoch": 0.712,
+      "grad_norm": 0.01458740234375,
+      "learning_rate": 1.7780000000000003e-05,
+      "loss": 2.8989,
+      "mean_token_accuracy": 0.4840679431334138,
+      "num_tokens": 14728975.0,
+      "step": 890
+    },
+    {
+      "entropy": 2.128746274113655,
+      "epoch": 0.72,
+      "grad_norm": 0.01361083984375,
+      "learning_rate": 1.798e-05,
+      "loss": 2.8664,
+      "mean_token_accuracy": 0.4867586812004447,
+      "num_tokens": 14882927.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.72,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 14882927.0,
+      "eval_coding_runtime": 95.8303,
+      "eval_coding_samples_per_second": 5.218,
+      "eval_coding_steps_per_second": 2.609,
+      "step": 900
+    },
+    {
+      "epoch": 0.72,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 14882927.0,
+      "eval_physics_runtime": 63.6666,
+      "eval_physics_samples_per_second": 7.853,
+      "eval_physics_steps_per_second": 3.927,
+      "step": 900
+    },
+    {
+      "entropy": 2.0901576526463033,
+      "epoch": 0.728,
+      "grad_norm": 0.0067138671875,
+      "learning_rate": 1.8180000000000002e-05,
+      "loss": 2.8708,
+      "mean_token_accuracy": 0.48403808698058126,
+      "num_tokens": 15052770.0,
+      "step": 910
+    },
+    {
+      "entropy": 2.122075318545103,
+      "epoch": 0.736,
+      "grad_norm": 0.01129150390625,
+      "learning_rate": 1.8380000000000004e-05,
+      "loss": 2.8633,
+      "mean_token_accuracy": 0.4852804895490408,
+      "num_tokens": 15217342.0,
+      "step": 920
+    },
+    {
+      "entropy": 2.093779005110264,
+      "epoch": 0.744,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 1.858e-05,
+      "loss": 2.8451,
+      "mean_token_accuracy": 0.48721388857811687,
+      "num_tokens": 15385161.0,
+      "step": 930
+    },
+    {
+      "entropy": 2.131568420678377,
+      "epoch": 0.752,
+      "grad_norm": 0.0096435546875,
+      "learning_rate": 1.878e-05,
+      "loss": 2.9118,
+      "mean_token_accuracy": 0.479784238897264,
+      "num_tokens": 15547710.0,
+      "step": 940
+    },
+    {
+      "entropy": 2.18331568017602,
+      "epoch": 0.76,
+      "grad_norm": 0.007171630859375,
+      "learning_rate": 1.898e-05,
+      "loss": 2.9565,
+      "mean_token_accuracy": 0.4732973873615265,
+      "num_tokens": 15704494.0,
+      "step": 950
+    },
+    {
+      "entropy": 2.1320055924355983,
+      "epoch": 0.768,
+      "grad_norm": 0.01177978515625,
+      "learning_rate": 1.918e-05,
+      "loss": 2.8867,
+      "mean_token_accuracy": 0.4821720516309142,
+      "num_tokens": 15877177.0,
+      "step": 960
+    },
+    {
+      "entropy": 2.035961114615202,
+      "epoch": 0.776,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 1.938e-05,
+      "loss": 2.8155,
+      "mean_token_accuracy": 0.4874297235161066,
+      "num_tokens": 16050530.0,
+      "step": 970
+    },
+    {
+      "entropy": 2.0721310496330263,
+      "epoch": 0.784,
+      "grad_norm": 0.01214599609375,
+      "learning_rate": 1.9580000000000002e-05,
+      "loss": 2.8311,
+      "mean_token_accuracy": 0.4866502169519663,
+      "num_tokens": 16219640.0,
+      "step": 980
+    },
+    {
+      "entropy": 2.1055771827697756,
+      "epoch": 0.792,
+      "grad_norm": 0.00927734375,
+      "learning_rate": 1.978e-05,
+      "loss": 2.8748,
+      "mean_token_accuracy": 0.4852980706840754,
+      "num_tokens": 16378820.0,
+      "step": 990
+    },
+    {
+      "entropy": 2.0726777322590353,
+      "epoch": 0.8,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 1.9980000000000002e-05,
+      "loss": 2.8588,
+      "mean_token_accuracy": 0.4857082888484001,
+      "num_tokens": 16548261.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 16548261.0,
+      "eval_coding_runtime": 95.9331,
+      "eval_coding_samples_per_second": 5.212,
+      "eval_coding_steps_per_second": 2.606,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 16548261.0,
+      "eval_physics_runtime": 63.1527,
+      "eval_physics_samples_per_second": 7.917,
+      "eval_physics_steps_per_second": 3.959,
+      "step": 1000
+    },
+    {
+      "entropy": 2.1674983091652393,
+      "epoch": 0.808,
+      "grad_norm": 0.0155029296875,
+      "learning_rate": 1.9980000000000002e-05,
+      "loss": 2.9179,
+      "mean_token_accuracy": 0.4778887365013361,
+      "num_tokens": 16711667.0,
+      "step": 1010
+    },
+    {
+      "entropy": 2.082773020863533,
+      "epoch": 0.816,
+      "grad_norm": 0.00738525390625,
+      "learning_rate": 1.995777777777778e-05,
+      "loss": 2.8647,
+      "mean_token_accuracy": 0.48503445759415625,
+      "num_tokens": 16870533.0,
+      "step": 1020
+    },
+    {
+      "entropy": 2.1195092521607877,
+      "epoch": 0.824,
+      "grad_norm": 0.0084228515625,
+      "learning_rate": 1.9935555555555557e-05,
+      "loss": 2.8734,
+      "mean_token_accuracy": 0.4803088143467903,
+      "num_tokens": 17035600.0,
+      "step": 1030
+    },
+    {
+      "entropy": 2.1006917230784894,
+      "epoch": 0.832,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 1.9913333333333335e-05,
+      "loss": 2.8807,
+      "mean_token_accuracy": 0.48227673936635257,
+      "num_tokens": 17196371.0,
+      "step": 1040
+    },
+    {
+      "entropy": 2.1442659996449946,
+      "epoch": 0.84,
+      "grad_norm": 0.01171875,
+      "learning_rate": 1.9891111111111112e-05,
+      "loss": 2.891,
+      "mean_token_accuracy": 0.48074845802038907,
+      "num_tokens": 17356919.0,
+      "step": 1050
+    },
+    {
+      "entropy": 2.0704655081033705,
+      "epoch": 0.848,
+      "grad_norm": 0.0177001953125,
+      "learning_rate": 1.986888888888889e-05,
+      "loss": 2.8486,
+      "mean_token_accuracy": 0.4880160320550203,
+      "num_tokens": 17527066.0,
+      "step": 1060
+    },
+    {
+      "entropy": 2.125109201669693,
+      "epoch": 0.856,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 1.9846666666666668e-05,
+      "loss": 2.8795,
+      "mean_token_accuracy": 0.4847541594877839,
+      "num_tokens": 17689902.0,
+      "step": 1070
+    },
+    {
+      "entropy": 2.1320445723831654,
+      "epoch": 0.864,
+      "grad_norm": 0.0140380859375,
+      "learning_rate": 1.9824444444444445e-05,
+      "loss": 2.8809,
+      "mean_token_accuracy": 0.480629575625062,
+      "num_tokens": 17859605.0,
+      "step": 1080
+    },
+    {
+      "entropy": 2.1207774586975576,
+      "epoch": 0.872,
+      "grad_norm": 0.0140380859375,
+      "learning_rate": 1.9802222222222226e-05,
+      "loss": 2.8729,
+      "mean_token_accuracy": 0.4811369523406029,
+      "num_tokens": 18019924.0,
+      "step": 1090
+    },
+    {
+      "entropy": 2.1364660277962684,
+      "epoch": 0.88,
+      "grad_norm": 0.01361083984375,
+      "learning_rate": 1.978e-05,
+      "loss": 2.8681,
+      "mean_token_accuracy": 0.4821885580196977,
+      "num_tokens": 18187315.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.88,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 18187315.0,
+      "eval_coding_runtime": 95.6457,
+      "eval_coding_samples_per_second": 5.228,
+      "eval_coding_steps_per_second": 2.614,
+      "step": 1100
+    },
+    {
+      "epoch": 0.88,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 18187315.0,
+      "eval_physics_runtime": 63.6627,
+      "eval_physics_samples_per_second": 7.854,
+      "eval_physics_steps_per_second": 3.927,
+      "step": 1100
+    },
+    {
+      "entropy": 1.9653398767113686,
+      "epoch": 0.888,
+      "grad_norm": 0.009033203125,
+      "learning_rate": 1.975777777777778e-05,
+      "loss": 2.7728,
+      "mean_token_accuracy": 0.4965917535126209,
+      "num_tokens": 18366329.0,
+      "step": 1110
+    },
+    {
+      "entropy": 2.0933822274208067,
+      "epoch": 0.896,
+      "grad_norm": 0.0191650390625,
+      "learning_rate": 1.9735555555555556e-05,
+      "loss": 2.8728,
+      "mean_token_accuracy": 0.4872217344120145,
+      "num_tokens": 18536790.0,
+      "step": 1120
+    },
+    {
+      "entropy": 2.1074513986706735,
+      "epoch": 0.904,
+      "grad_norm": 0.007049560546875,
+      "learning_rate": 1.9713333333333337e-05,
+      "loss": 2.9176,
+      "mean_token_accuracy": 0.48107887227088214,
+      "num_tokens": 18701809.0,
+      "step": 1130
+    },
+    {
+      "entropy": 2.160377311706543,
+      "epoch": 0.912,
+      "grad_norm": 0.006683349609375,
+      "learning_rate": 1.969111111111111e-05,
+      "loss": 2.9384,
+      "mean_token_accuracy": 0.4739804005250335,
+      "num_tokens": 18869344.0,
+      "step": 1140
+    },
+    {
+      "entropy": 2.0753089264035225,
+      "epoch": 0.92,
+      "grad_norm": 0.01416015625,
+      "learning_rate": 1.9668888888888892e-05,
+      "loss": 2.882,
+      "mean_token_accuracy": 0.48446453278884294,
+      "num_tokens": 19033910.0,
+      "step": 1150
+    },
+    {
+      "entropy": 2.1365489259362223,
+      "epoch": 0.928,
+      "grad_norm": 0.006988525390625,
+      "learning_rate": 1.9646666666666666e-05,
+      "loss": 2.8854,
+      "mean_token_accuracy": 0.4823284359648824,
+      "num_tokens": 19199834.0,
+      "step": 1160
+    },
+    {
+      "entropy": 2.0710911326110364,
+      "epoch": 0.936,
+      "grad_norm": 0.007080078125,
+      "learning_rate": 1.9624444444444447e-05,
+      "loss": 2.8127,
+      "mean_token_accuracy": 0.48797463029623034,
+      "num_tokens": 19361703.0,
+      "step": 1170
+    },
+    {
+      "entropy": 2.116609390079975,
+      "epoch": 0.944,
+      "grad_norm": 0.007110595703125,
+      "learning_rate": 1.9602222222222225e-05,
+      "loss": 2.8751,
+      "mean_token_accuracy": 0.48552187960594895,
+      "num_tokens": 19525385.0,
+      "step": 1180
+    },
+    {
+      "entropy": 2.0949166089296343,
+      "epoch": 0.952,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 1.9580000000000002e-05,
+      "loss": 2.8499,
+      "mean_token_accuracy": 0.48639670219272374,
+      "num_tokens": 19690715.0,
+      "step": 1190
+    },
+    {
+      "entropy": 2.1095651358366014,
+      "epoch": 0.96,
+      "grad_norm": 0.015380859375,
+      "learning_rate": 1.955777777777778e-05,
+      "loss": 2.8706,
+      "mean_token_accuracy": 0.48429451026022435,
+      "num_tokens": 19856973.0,
+      "step": 1200
+    },
+    {
+      "epoch": 0.96,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 19856973.0,
+      "eval_coding_runtime": 95.6684,
+      "eval_coding_samples_per_second": 5.226,
+      "eval_coding_steps_per_second": 2.613,
+      "step": 1200
+    },
+    {
+      "epoch": 0.96,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 19856973.0,
+      "eval_physics_runtime": 63.6635,
+      "eval_physics_samples_per_second": 7.854,
+      "eval_physics_steps_per_second": 3.927,
+      "step": 1200
+    },
+    {
+      "entropy": 2.0797565251588823,
+      "epoch": 0.968,
+      "grad_norm": 0.0091552734375,
+      "learning_rate": 1.9535555555555557e-05,
+      "loss": 2.8871,
+      "mean_token_accuracy": 0.487212173268199,
+      "num_tokens": 20021093.0,
+      "step": 1210
+    },
+    {
+      "entropy": 2.0395397424697874,
+      "epoch": 0.976,
+      "grad_norm": 0.01397705078125,
+      "learning_rate": 1.9513333333333335e-05,
+      "loss": 2.8149,
+      "mean_token_accuracy": 0.4898043507710099,
+      "num_tokens": 20190600.0,
+      "step": 1220
+    },
+    {
+      "entropy": 2.170710327476263,
+      "epoch": 0.984,
+      "grad_norm": 0.0123291015625,
+      "learning_rate": 1.9491111111111113e-05,
+      "loss": 2.9186,
+      "mean_token_accuracy": 0.4756599869579077,
+      "num_tokens": 20352255.0,
+      "step": 1230
+    },
+    {
+      "entropy": 2.074953277409077,
+      "epoch": 0.992,
+      "grad_norm": 0.01092529296875,
+      "learning_rate": 1.946888888888889e-05,
+      "loss": 2.8591,
+      "mean_token_accuracy": 0.48683627638965843,
+      "num_tokens": 20518014.0,
+      "step": 1240
+    },
+    {
+      "entropy": 2.1222646929323674,
+      "epoch": 1.0,
+      "grad_norm": 0.00909423828125,
+      "learning_rate": 1.9446666666666668e-05,
+      "loss": 2.8802,
+      "mean_token_accuracy": 0.4825377007946372,
+      "num_tokens": 20686804.0,
+      "step": 1250
+    },
+    {
+      "entropy": 2.071950024366379,
+      "epoch": 1.008,
+      "grad_norm": 0.01141357421875,
+      "learning_rate": 1.9424444444444446e-05,
+      "loss": 2.8335,
+      "mean_token_accuracy": 0.4894521238282323,
+      "num_tokens": 20859215.0,
+      "step": 1260
+    },
+    {
+      "entropy": 2.178350891917944,
+      "epoch": 1.016,
+      "grad_norm": 0.0086669921875,
+      "learning_rate": 1.9402222222222223e-05,
+      "loss": 2.9515,
+      "mean_token_accuracy": 0.475351152010262,
+      "num_tokens": 21019542.0,
+      "step": 1270
+    },
+    {
+      "entropy": 2.0342648893594744,
+      "epoch": 1.024,
+      "grad_norm": 0.01483154296875,
+      "learning_rate": 1.938e-05,
+      "loss": 2.8036,
+      "mean_token_accuracy": 0.4928664604201913,
+      "num_tokens": 21186658.0,
+      "step": 1280
+    },
+    {
+      "entropy": 2.0908240154385567,
+      "epoch": 1.032,
+      "grad_norm": 0.00897216796875,
+      "learning_rate": 1.935777777777778e-05,
+      "loss": 2.8868,
+      "mean_token_accuracy": 0.483198188431561,
+      "num_tokens": 21351715.0,
+      "step": 1290
+    },
+    {
+      "entropy": 2.1210865639150143,
+      "epoch": 1.04,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 1.9335555555555556e-05,
+      "loss": 2.9071,
+      "mean_token_accuracy": 0.47981371227651837,
+      "num_tokens": 21517237.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.04,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 21517237.0,
+      "eval_coding_runtime": 96.1911,
+      "eval_coding_samples_per_second": 5.198,
+      "eval_coding_steps_per_second": 2.599,
+      "step": 1300
+    },
+    {
+      "epoch": 1.04,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 21517237.0,
+      "eval_physics_runtime": 63.9611,
+      "eval_physics_samples_per_second": 7.817,
+      "eval_physics_steps_per_second": 3.909,
+      "step": 1300
+    },
+    {
+      "entropy": 2.102020622044802,
+      "epoch": 1.048,
+      "grad_norm": 0.007415771484375,
+      "learning_rate": 1.9313333333333334e-05,
+      "loss": 2.8719,
+      "mean_token_accuracy": 0.4847179941833019,
+      "num_tokens": 21682780.0,
+      "step": 1310
+    },
+    {
+      "entropy": 2.045586694777012,
+      "epoch": 1.056,
+      "grad_norm": 0.0086669921875,
+      "learning_rate": 1.9291111111111115e-05,
+      "loss": 2.8189,
+      "mean_token_accuracy": 0.48618846032768487,
+      "num_tokens": 21852528.0,
+      "step": 1320
+    },
+    {
+      "entropy": 2.0868709199130535,
+      "epoch": 1.064,
+      "grad_norm": 0.01226806640625,
+      "learning_rate": 1.926888888888889e-05,
+      "loss": 2.8313,
+      "mean_token_accuracy": 0.4878941228613257,
+      "num_tokens": 22021514.0,
+      "step": 1330
+    },
+    {
+      "entropy": 2.111675312370062,
+      "epoch": 1.072,
+      "grad_norm": 0.00909423828125,
+      "learning_rate": 1.924666666666667e-05,
+      "loss": 2.889,
+      "mean_token_accuracy": 0.4821753781288862,
+      "num_tokens": 22192380.0,
+      "step": 1340
+    },
+    {
+      "entropy": 2.080042862892151,
+      "epoch": 1.08,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 1.9224444444444444e-05,
+      "loss": 2.8401,
+      "mean_token_accuracy": 0.4857699448242784,
+      "num_tokens": 22356835.0,
+      "step": 1350
+    },
+    {
+      "entropy": 2.138657582551241,
+      "epoch": 1.088,
+      "grad_norm": 0.006927490234375,
+      "learning_rate": 1.9202222222222225e-05,
+      "loss": 2.9223,
+      "mean_token_accuracy": 0.4771748060360551,
+      "num_tokens": 22517971.0,
+      "step": 1360
+    },
+    {
+      "entropy": 2.1065418414771555,
+      "epoch": 1.096,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 1.918e-05,
+      "loss": 2.8768,
+      "mean_token_accuracy": 0.4816119741648436,
+      "num_tokens": 22681680.0,
+      "step": 1370
+    },
+    {
+      "entropy": 2.087523814290762,
+      "epoch": 1.104,
+      "grad_norm": 0.020751953125,
+      "learning_rate": 1.915777777777778e-05,
+      "loss": 2.8938,
+      "mean_token_accuracy": 0.4846269652247429,
+      "num_tokens": 22848694.0,
+      "step": 1380
+    },
+    {
+      "entropy": 2.1188573092222214,
+      "epoch": 1.112,
+      "grad_norm": 0.0087890625,
+      "learning_rate": 1.9135555555555555e-05,
+      "loss": 2.8744,
+      "mean_token_accuracy": 0.48116844836622474,
+      "num_tokens": 23016014.0,
+      "step": 1390
+    },
+    {
+      "entropy": 2.071516238898039,
+      "epoch": 1.12,
+      "grad_norm": 0.01544189453125,
+      "learning_rate": 1.9113333333333336e-05,
+      "loss": 2.8453,
+      "mean_token_accuracy": 0.48592273648828266,
+      "num_tokens": 23183889.0,
+      "step": 1400
+    },
+    {
+      "epoch": 1.12,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 23183889.0,
+      "eval_coding_runtime": 96.0999,
+      "eval_coding_samples_per_second": 5.203,
+      "eval_coding_steps_per_second": 2.601,
+      "step": 1400
+    },
+    {
+      "epoch": 1.12,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 23183889.0,
+      "eval_physics_runtime": 64.1646,
+      "eval_physics_samples_per_second": 7.792,
+      "eval_physics_steps_per_second": 3.896,
+      "step": 1400
+    },
+    {
+      "entropy": 2.0450177520513533,
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 1.9091111111111113e-05,
+      "loss": 2.8314,
+      "mean_token_accuracy": 0.4920926999300718,
+      "num_tokens": 23354096.0,
+      "step": 1410
+    },
+    {
+      "entropy": 2.0993775948882103,
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.0146484375,
+      "learning_rate": 1.906888888888889e-05,
+      "loss": 2.8513,
+      "mean_token_accuracy": 0.4838741825893521,
+      "num_tokens": 23523903.0,
+      "step": 1420
+    },
+    {
+      "entropy": 2.0676057398319245,
+      "epoch": 1.144,
+      "grad_norm": 0.0135498046875,
+      "learning_rate": 1.904666666666667e-05,
+      "loss": 2.8661,
+      "mean_token_accuracy": 0.4864560257643461,
+      "num_tokens": 23684571.0,
+      "step": 1430
+    },
+    {
+      "entropy": 2.0999209016561506,
+      "epoch": 1.152,
+      "grad_norm": 0.00982666015625,
+      "learning_rate": 1.9024444444444446e-05,
+      "loss": 2.8681,
+      "mean_token_accuracy": 0.4822270443663001,
+      "num_tokens": 23848848.0,
+      "step": 1440
+    },
+    {
+      "entropy": 2.110722591727972,
+      "epoch": 1.16,
+      "grad_norm": 0.0086669921875,
+      "learning_rate": 1.9002222222222224e-05,
+      "loss": 2.871,
+      "mean_token_accuracy": 0.48459589947015047,
+      "num_tokens": 24011654.0,
+      "step": 1450
+    },
+    {
+      "entropy": 2.181078152358532,
+      "epoch": 1.168,
+      "grad_norm": 0.0098876953125,
+      "learning_rate": 1.898e-05,
+      "loss": 2.943,
+      "mean_token_accuracy": 0.47790372706949713,
+      "num_tokens": 24174589.0,
+      "step": 1460
+    },
+    {
+      "entropy": 2.134608647972345,
+      "epoch": 1.176,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 1.895777777777778e-05,
+      "loss": 2.8963,
+      "mean_token_accuracy": 0.4795195382088423,
+      "num_tokens": 24336249.0,
+      "step": 1470
+    },
+    {
+      "entropy": 2.0590513460338116,
+      "epoch": 1.184,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 1.8935555555555556e-05,
+      "loss": 2.8476,
+      "mean_token_accuracy": 0.4868919890373945,
+      "num_tokens": 24495981.0,
+      "step": 1480
+    },
+    {
+      "entropy": 2.094113527983427,
+      "epoch": 1.192,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 1.8913333333333334e-05,
+      "loss": 2.8476,
+      "mean_token_accuracy": 0.488334871083498,
+      "num_tokens": 24658862.0,
+      "step": 1490
+    },
+    {
+      "entropy": 2.066910207271576,
+      "epoch": 1.2,
+      "grad_norm": 0.01214599609375,
+      "learning_rate": 1.8891111111111115e-05,
+      "loss": 2.8177,
+      "mean_token_accuracy": 0.4844546576961875,
+      "num_tokens": 24826245.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 24826245.0,
+      "eval_coding_runtime": 95.975,
+      "eval_coding_samples_per_second": 5.21,
+      "eval_coding_steps_per_second": 2.605,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 24826245.0,
+      "eval_physics_runtime": 63.6317,
+      "eval_physics_samples_per_second": 7.858,
+      "eval_physics_steps_per_second": 3.929,
+      "step": 1500
+    },
+    {
+      "entropy": 2.1044005908071997,
+      "epoch": 1.208,
+      "grad_norm": 0.01177978515625,
+      "learning_rate": 1.886888888888889e-05,
+      "loss": 2.8829,
+      "mean_token_accuracy": 0.48166574332863094,
+      "num_tokens": 24988821.0,
+      "step": 1510
+    },
+    {
+      "entropy": 2.1516220718622208,
+      "epoch": 1.216,
+      "grad_norm": 0.012451171875,
+      "learning_rate": 1.884666666666667e-05,
+      "loss": 2.9433,
+      "mean_token_accuracy": 0.47657596562057736,
+      "num_tokens": 25147775.0,
+      "step": 1520
+    },
+    {
+      "entropy": 2.1071897082030775,
+      "epoch": 1.224,
+      "grad_norm": 0.00860595703125,
+      "learning_rate": 1.8824444444444445e-05,
+      "loss": 2.8592,
+      "mean_token_accuracy": 0.479968504793942,
+      "num_tokens": 25312652.0,
+      "step": 1530
+    },
+    {
+      "entropy": 2.031100772321224,
+      "epoch": 1.232,
+      "grad_norm": 0.006103515625,
+      "learning_rate": 1.8802222222222226e-05,
+      "loss": 2.8016,
+      "mean_token_accuracy": 0.4919817751273513,
+      "num_tokens": 25480033.0,
+      "step": 1540
+    },
+    {
+      "entropy": 2.0882932603359223,
+      "epoch": 1.24,
+      "grad_norm": 0.017822265625,
+      "learning_rate": 1.878e-05,
+      "loss": 2.87,
+      "mean_token_accuracy": 0.4867149593308568,
+      "num_tokens": 25643821.0,
+      "step": 1550
+    },
+    {
+      "entropy": 2.1069738253951074,
+      "epoch": 1.248,
+      "grad_norm": 0.01275634765625,
+      "learning_rate": 1.875777777777778e-05,
+      "loss": 2.9072,
+      "mean_token_accuracy": 0.48037715051323177,
+      "num_tokens": 25811978.0,
+      "step": 1560
+    },
+    {
+      "entropy": 2.1235784739255905,
+      "epoch": 1.256,
+      "grad_norm": 0.0098876953125,
+      "learning_rate": 1.873555555555556e-05,
+      "loss": 2.8361,
+      "mean_token_accuracy": 0.4876450767740607,
+      "num_tokens": 25980217.0,
+      "step": 1570
+    },
+    {
+      "entropy": 2.07255465015769,
+      "epoch": 1.264,
+      "grad_norm": 0.0205078125,
+      "learning_rate": 1.8713333333333336e-05,
+      "loss": 2.8226,
+      "mean_token_accuracy": 0.48956795781850815,
+      "num_tokens": 26146299.0,
+      "step": 1580
+    },
+    {
+      "entropy": 2.083909762650728,
+      "epoch": 1.272,
+      "grad_norm": 0.006805419921875,
+      "learning_rate": 1.8691111111111114e-05,
+      "loss": 2.8296,
+      "mean_token_accuracy": 0.48632726091891526,
+      "num_tokens": 26315594.0,
+      "step": 1590
+    },
+    {
+      "entropy": 2.1811861269176007,
+      "epoch": 1.28,
+      "grad_norm": 0.017333984375,
+      "learning_rate": 1.866888888888889e-05,
+      "loss": 2.9711,
+      "mean_token_accuracy": 0.47178333820775153,
+      "num_tokens": 26478207.0,
+      "step": 1600
+    },
+    {
+      "epoch": 1.28,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 26478207.0,
+      "eval_coding_runtime": 95.7162,
+      "eval_coding_samples_per_second": 5.224,
+      "eval_coding_steps_per_second": 2.612,
+      "step": 1600
+    },
+    {
+      "epoch": 1.28,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 26478207.0,
+      "eval_physics_runtime": 63.6631,
+      "eval_physics_samples_per_second": 7.854,
+      "eval_physics_steps_per_second": 3.927,
+      "step": 1600
+    },
+    {
+      "entropy": 2.018047058582306,
+      "epoch": 1.288,
+      "grad_norm": 0.015869140625,
+      "learning_rate": 1.864666666666667e-05,
+      "loss": 2.7963,
+      "mean_token_accuracy": 0.49348701871931555,
+      "num_tokens": 26647567.0,
+      "step": 1610
+    },
+    {
+      "entropy": 2.1041888780891895,
+      "epoch": 1.296,
+      "grad_norm": 0.0081787109375,
+      "learning_rate": 1.8624444444444446e-05,
+      "loss": 2.8794,
+      "mean_token_accuracy": 0.4833239272236824,
+      "num_tokens": 26806477.0,
+      "step": 1620
+    },
+    {
+      "entropy": 2.0873175472021104,
+      "epoch": 1.304,
+      "grad_norm": 0.0169677734375,
+      "learning_rate": 1.8602222222222224e-05,
+      "loss": 2.8534,
+      "mean_token_accuracy": 0.4844379436224699,
+      "num_tokens": 26973124.0,
+      "step": 1630
+    },
+    {
+      "entropy": 2.184805364906788,
+      "epoch": 1.312,
+      "grad_norm": 0.0081787109375,
+      "learning_rate": 1.858e-05,
+      "loss": 2.9204,
+      "mean_token_accuracy": 0.4806702647358179,
+      "num_tokens": 27137528.0,
+      "step": 1640
+    },
+    {
+      "entropy": 2.1004837110638617,
+      "epoch": 1.32,
+      "grad_norm": 0.0189208984375,
+      "learning_rate": 1.855777777777778e-05,
+      "loss": 2.839,
+      "mean_token_accuracy": 0.4855312593281269,
+      "num_tokens": 27300986.0,
+      "step": 1650
+    },
+    {
+      "entropy": 2.1488297916948795,
+      "epoch": 1.328,
+      "grad_norm": 0.00677490234375,
+      "learning_rate": 1.8535555555555557e-05,
+      "loss": 2.876,
+      "mean_token_accuracy": 0.48554224893450737,
+      "num_tokens": 27465859.0,
+      "step": 1660
+    },
+    {
+      "entropy": 2.11965301707387,
+      "epoch": 1.336,
+      "grad_norm": 0.0089111328125,
+      "learning_rate": 1.8513333333333335e-05,
+      "loss": 2.909,
+      "mean_token_accuracy": 0.4828299328684807,
+      "num_tokens": 27627148.0,
+      "step": 1670
+    },
+    {
+      "entropy": 2.139040616154671,
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.01214599609375,
+      "learning_rate": 1.8491111111111112e-05,
+      "loss": 2.9133,
+      "mean_token_accuracy": 0.4807636830955744,
+      "num_tokens": 27795568.0,
+      "step": 1680
+    },
+    {
+      "entropy": 2.1508292332291603,
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.00848388671875,
+      "learning_rate": 1.846888888888889e-05,
+      "loss": 2.9009,
+      "mean_token_accuracy": 0.48149400427937505,
+      "num_tokens": 27958162.0,
+      "step": 1690
+    },
+    {
+      "entropy": 2.0931077137589456,
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.0201416015625,
+      "learning_rate": 1.8446666666666667e-05,
+      "loss": 2.8726,
+      "mean_token_accuracy": 0.4807087674736977,
+      "num_tokens": 28129988.0,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 28129988.0,
+      "eval_coding_runtime": 96.0975,
+      "eval_coding_samples_per_second": 5.203,
+      "eval_coding_steps_per_second": 2.602,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 28129988.0,
+      "eval_physics_runtime": 63.7443,
+      "eval_physics_samples_per_second": 7.844,
+      "eval_physics_steps_per_second": 3.922,
+      "step": 1700
+    },
+    {
+      "entropy": 2.0795333731919525,
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.0096435546875,
+      "learning_rate": 1.842444444444445e-05,
+      "loss": 2.8522,
+      "mean_token_accuracy": 0.4887755334377289,
+      "num_tokens": 28299534.0,
+      "step": 1710
+    },
+    {
+      "entropy": 2.141296311467886,
+      "epoch": 1.376,
+      "grad_norm": 0.0157470703125,
+      "learning_rate": 1.8402222222222223e-05,
+      "loss": 2.9271,
+      "mean_token_accuracy": 0.4771733907982707,
+      "num_tokens": 28465903.0,
+      "step": 1720
+    },
+    {
+      "entropy": 2.0781943283975126,
+      "epoch": 1.384,
+      "grad_norm": 0.01055908203125,
+      "learning_rate": 1.8380000000000004e-05,
+      "loss": 2.8574,
+      "mean_token_accuracy": 0.4866001008078456,
+      "num_tokens": 28639289.0,
+      "step": 1730
+    },
+    {
+      "entropy": 2.0997987784445287,
+      "epoch": 1.392,
+      "grad_norm": 0.02099609375,
+      "learning_rate": 1.8357777777777778e-05,
+      "loss": 2.8585,
+      "mean_token_accuracy": 0.48320644851773975,
+      "num_tokens": 28801554.0,
+      "step": 1740
+    },
+    {
+      "entropy": 2.150196324288845,
+      "epoch": 1.4,
+      "grad_norm": 0.007354736328125,
+      "learning_rate": 1.833555555555556e-05,
+      "loss": 2.9002,
+      "mean_token_accuracy": 0.48246240708976984,
+      "num_tokens": 28963885.0,
+      "step": 1750
+    },
+    {
+      "entropy": 2.084288237988949,
+      "epoch": 1.408,
+      "grad_norm": 0.01806640625,
+      "learning_rate": 1.8313333333333333e-05,
+      "loss": 2.8911,
+      "mean_token_accuracy": 0.4849772537127137,
+      "num_tokens": 29125114.0,
+      "step": 1760
+    },
+    {
+      "entropy": 2.1347289800643923,
+      "epoch": 1.416,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 1.8291111111111114e-05,
+      "loss": 2.9129,
+      "mean_token_accuracy": 0.477182531170547,
+      "num_tokens": 29285272.0,
+      "step": 1770
+    },
+    {
+      "entropy": 2.1285498954355715,
+      "epoch": 1.424,
+      "grad_norm": 0.018310546875,
+      "learning_rate": 1.8268888888888888e-05,
+      "loss": 2.9215,
+      "mean_token_accuracy": 0.4772155126556754,
+      "num_tokens": 29454334.0,
+      "step": 1780
+    },
+    {
+      "entropy": 2.0727533496916295,
+      "epoch": 1.432,
+      "grad_norm": 0.01336669921875,
+      "learning_rate": 1.824666666666667e-05,
+      "loss": 2.8803,
+      "mean_token_accuracy": 0.4822785761207342,
+      "num_tokens": 29616865.0,
+      "step": 1790
+    },
+    {
+      "entropy": 2.0606922268867494,
+      "epoch": 1.44,
+      "grad_norm": 0.00860595703125,
+      "learning_rate": 1.8224444444444447e-05,
+      "loss": 2.8232,
+      "mean_token_accuracy": 0.48800144270062445,
+      "num_tokens": 29789253.0,
+      "step": 1800
+    },
+    {
+      "epoch": 1.44,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 29789253.0,
+      "eval_coding_runtime": 96.3208,
+      "eval_coding_samples_per_second": 5.191,
+      "eval_coding_steps_per_second": 2.595,
+      "step": 1800
+    },
+    {
+      "epoch": 1.44,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 29789253.0,
+      "eval_physics_runtime": 63.9922,
+      "eval_physics_samples_per_second": 7.813,
+      "eval_physics_steps_per_second": 3.907,
+      "step": 1800
+    },
+    {
+      "entropy": 2.0618888407945635,
+      "epoch": 1.448,
+      "grad_norm": 0.007171630859375,
+      "learning_rate": 1.8202222222222225e-05,
+      "loss": 2.8573,
+      "mean_token_accuracy": 0.4843838458880782,
+      "num_tokens": 29953006.0,
+      "step": 1810
+    },
+    {
+      "entropy": 2.022880507260561,
+      "epoch": 1.456,
+      "grad_norm": 0.0194091796875,
+      "learning_rate": 1.8180000000000002e-05,
+      "loss": 2.8031,
+      "mean_token_accuracy": 0.49401772283017636,
+      "num_tokens": 30128576.0,
+      "step": 1820
+    },
+    {
+      "entropy": 2.0860828548669814,
+      "epoch": 1.464,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 1.815777777777778e-05,
+      "loss": 2.8756,
+      "mean_token_accuracy": 0.4849246619269252,
+      "num_tokens": 30288894.0,
+      "step": 1830
+    },
+    {
+      "entropy": 2.188418509066105,
+      "epoch": 1.472,
+      "grad_norm": 0.015869140625,
+      "learning_rate": 1.8135555555555557e-05,
+      "loss": 2.9527,
+      "mean_token_accuracy": 0.4721253639087081,
+      "num_tokens": 30452719.0,
+      "step": 1840
+    },
+    {
+      "entropy": 2.085013201087713,
+      "epoch": 1.48,
+      "grad_norm": 0.00946044921875,
+      "learning_rate": 1.8113333333333335e-05,
+      "loss": 2.8646,
+      "mean_token_accuracy": 0.486043793335557,
+      "num_tokens": 30620659.0,
+      "step": 1850
+    },
+    {
+      "entropy": 2.143638453632593,
+      "epoch": 1.488,
+      "grad_norm": 0.0108642578125,
+      "learning_rate": 1.8091111111111113e-05,
+      "loss": 2.9264,
+      "mean_token_accuracy": 0.47975865937769413,
+      "num_tokens": 30782343.0,
+      "step": 1860
+    },
+    {
+      "entropy": 2.110791251808405,
+      "epoch": 1.496,
+      "grad_norm": 0.00689697265625,
+      "learning_rate": 1.806888888888889e-05,
+      "loss": 2.8831,
+      "mean_token_accuracy": 0.4842625314369798,
+      "num_tokens": 30947703.0,
+      "step": 1870
+    },
+    {
+      "entropy": 2.1235111109912395,
+      "epoch": 1.504,
+      "grad_norm": 0.0181884765625,
+      "learning_rate": 1.8046666666666668e-05,
+      "loss": 2.8413,
+      "mean_token_accuracy": 0.4860221529379487,
+      "num_tokens": 31113238.0,
+      "step": 1880
+    },
+    {
+      "entropy": 2.0822810381650925,
+      "epoch": 1.512,
+      "grad_norm": 0.0125732421875,
+      "learning_rate": 1.8024444444444445e-05,
+      "loss": 2.864,
+      "mean_token_accuracy": 0.48232704903930423,
+      "num_tokens": 31283883.0,
+      "step": 1890
+    },
+    {
+      "entropy": 2.1699491038918497,
+      "epoch": 1.52,
+      "grad_norm": 0.0101318359375,
+      "learning_rate": 1.8002222222222223e-05,
+      "loss": 2.9505,
+      "mean_token_accuracy": 0.4706884307786822,
+      "num_tokens": 31444589.0,
+      "step": 1900
+    },
+    {
+      "epoch": 1.52,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 31444589.0,
+      "eval_coding_runtime": 95.9376,
+      "eval_coding_samples_per_second": 5.212,
+      "eval_coding_steps_per_second": 2.606,
+      "step": 1900
+    },
+    {
+      "epoch": 1.52,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 31444589.0,
+      "eval_physics_runtime": 63.8135,
+      "eval_physics_samples_per_second": 7.835,
+      "eval_physics_steps_per_second": 3.918,
+      "step": 1900
+    },
+    {
+      "entropy": 2.1199583016335963,
+      "epoch": 1.528,
+      "grad_norm": 0.007598876953125,
+      "learning_rate": 1.798e-05,
+      "loss": 2.8928,
+      "mean_token_accuracy": 0.4802051903679967,
+      "num_tokens": 31608952.0,
+      "step": 1910
+    },
+    {
+      "entropy": 2.175958313792944,
+      "epoch": 1.536,
+      "grad_norm": 0.0089111328125,
+      "learning_rate": 1.7957777777777778e-05,
+      "loss": 2.9365,
+      "mean_token_accuracy": 0.4747030269354582,
+      "num_tokens": 31774137.0,
+      "step": 1920
+    },
+    {
+      "entropy": 2.086700049042702,
+      "epoch": 1.544,
+      "grad_norm": 0.0113525390625,
+      "learning_rate": 1.7935555555555556e-05,
+      "loss": 2.8777,
+      "mean_token_accuracy": 0.4859625767916441,
+      "num_tokens": 31937927.0,
+      "step": 1930
+    },
+    {
+      "entropy": 2.1010241121053697,
+      "epoch": 1.552,
+      "grad_norm": 0.0068359375,
+      "learning_rate": 1.7913333333333337e-05,
+      "loss": 2.8916,
+      "mean_token_accuracy": 0.4840227223932743,
+      "num_tokens": 32101776.0,
+      "step": 1940
+    },
+    {
+      "entropy": 2.1249936796724795,
+      "epoch": 1.56,
+      "grad_norm": 0.01446533203125,
+      "learning_rate": 1.789111111111111e-05,
+      "loss": 2.8819,
+      "mean_token_accuracy": 0.48242205642163755,
+      "num_tokens": 32271213.0,
+      "step": 1950
+    },
+    {
+      "entropy": 2.040369462966919,
+      "epoch": 1.568,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 1.7868888888888892e-05,
+      "loss": 2.8209,
+      "mean_token_accuracy": 0.48918427657335994,
+      "num_tokens": 32428021.0,
+      "step": 1960
+    },
+    {
+      "entropy": 2.2181196875870226,
+      "epoch": 1.576,
+      "grad_norm": 0.0108642578125,
+      "learning_rate": 1.7846666666666666e-05,
+      "loss": 2.9794,
+      "mean_token_accuracy": 0.4697700636461377,
+      "num_tokens": 32585407.0,
+      "step": 1970
+    },
+    {
+      "entropy": 2.096325629204512,
+      "epoch": 1.584,
+      "grad_norm": 0.0196533203125,
+      "learning_rate": 1.7824444444444447e-05,
+      "loss": 2.8507,
+      "mean_token_accuracy": 0.4877478454262018,
+      "num_tokens": 32752735.0,
+      "step": 1980
+    },
+    {
+      "entropy": 2.1082000881433487,
+      "epoch": 1.592,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 1.780222222222222e-05,
+      "loss": 2.8789,
+      "mean_token_accuracy": 0.482938090339303,
+      "num_tokens": 32912519.0,
+      "step": 1990
+    },
+    {
+      "entropy": 2.139867788553238,
+      "epoch": 1.6,
+      "grad_norm": 0.01007080078125,
+      "learning_rate": 1.7780000000000003e-05,
+      "loss": 2.9136,
+      "mean_token_accuracy": 0.4764457972720265,
+      "num_tokens": 33075822.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 33075822.0,
+      "eval_coding_runtime": 96.1948,
+      "eval_coding_samples_per_second": 5.198,
+      "eval_coding_steps_per_second": 2.599,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 33075822.0,
+      "eval_physics_runtime": 63.6877,
+      "eval_physics_samples_per_second": 7.851,
+      "eval_physics_steps_per_second": 3.925,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 2.6802547029475983e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594a67699005466f1daf68590dd4f89845497a197a7fed03f0c80b5f94e6119e
+size 6417