Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = 'You are Ministral-3-3B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYou power an AI assistant called Le Chat.\nYour knowledge base was last updated on 2023-10-01.\nThe current date is {today}.\n\nWhen you\'re not sure about some information or when the user\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\'t have the information and avoid making up anything.\nIf the user\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\nNext sections describe the capabilities that you have.\n\n# WEB BROWSING INSTRUCTIONS\n\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\n\n# MULTI-MODAL INSTRUCTIONS\n\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\nYou cannot read nor transcribe audio files or videos.\n\n# TOOL CALLING INSTRUCTIONS\n\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\n\n1. When the request requires up-to-date information.\n2. When the request requires specific data that you do not have in your knowledge base.\n3. When the request involves actions that you cannot perform without tools.\n\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.' %}
+
+{#- Begin of sequence token. #}
+{{- bos_token }}
+
+{#- Handle system prompt if it exists. #}
+{#- System prompt supports text content or text chunks. #}
+{%- if messages[0]['role'] == 'system' %}
+    {{- '[SYSTEM_PROMPT]' -}}
+    {%- if messages[0]['content'] is string %}
+        {{- messages[0]['content'] -}}
+    {%- else %}        
+        {%- for block in messages[0]['content'] %}
+            {%- if block['type'] == 'text' %}
+                {{- block['text'] }}
+            {%- else %}
+                {{- raise_exception('Only text chunks are supported in system message contents.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {{- '[/SYSTEM_PROMPT]' -}}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- if default_system_message != '' %}
+        {{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}
+    {%- endif %}
+{%- endif %}
+
+
+{#- Tools definition #}
+{%- set tools_definition = '' %}
+{%- set has_tools = false %}
+{%- if tools is defined and tools is not none and tools|length > 0 %}
+    {%- set has_tools = true %}
+    {%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}
+    {{- tools_definition }}
+{%- endif %}
+
+{#- Checks for alternating user/assistant messages. #}
+{%- set ns = namespace(index=0) %}
+{%- for message in loop_messages %}
+    {%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}
+        {%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}
+            {{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{#- Handle conversation messages. #}
+{%- for message in loop_messages %}
+
+    {#- User messages supports text content or text and image chunks. #}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- elif message['content'] | length > 0 %}
+            {{- '[INST]' }}
+            {%- if message['content'] | length == 2 %}
+                {%- set blocks = message['content'] | sort(attribute='type') %}
+            {%- else %}
+                {%- set blocks = message['content'] %}
+            {%- endif %}
+            {%- for block in blocks %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- else %}
+            {{- raise_exception('User message must have a string or a list of chunks in content') }}
+        {%- endif %}
+
+    {#- Assistant messages supports text content or text and image chunks. #}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}
+            {{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}
+        {%- endif %}
+
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- elif message['content'] | length > 0 %}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- else %}
+                    {{- raise_exception('Only text chunks are supported in assistant message contents.') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        
+        {%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
+            {%- for tool in message['tool_calls'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {%- if arguments is not string %}
+                    {%- set arguments = arguments|tojson|safe %}
+                {%- elif arguments == '' %}
+                    {%- set arguments = '{}' %}
+                {%- endif %}
+                {{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}
+            {%- endfor %}
+        {%- endif %}
+
+        {#- End of sequence token for each assistant messages. #}
+        {{- eos_token }}
+
+    {#- Tool messages only supports text content. #}
+    {%- elif message['role'] == 'tool' %}
+        {{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}
+
+    {#- Raise exception for unsupported roles. #}
+    {%- else %}
+        {{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role'] + '.') }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "pad_token_id": 11,
+  "projector_hidden_act": "gelu",
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "max_position_embeddings": 262144,
+    "model_type": "ministral3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 26,
+    "num_key_value_heads": 8,
+    "pad_token_id": 11,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "beta_fast": 32.0,
+      "beta_slow": 1.0,
+      "factor": 16.0,
+      "llama_4_scaling_beta": 0.1,
+      "mscale": 1.0,
+      "mscale_all_dim": 1.0,
+      "original_max_position_embeddings": 16384,
+      "rope_theta": 1000000.0,
+      "rope_type": "yarn",
+      "type": "yarn"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1540,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "vision_feature_layer": -1
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    2
+  ],
+  "max_length": 262144,
+  "pad_token_id": 11,
+  "transformers_version": "5.2.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d119866219aaa30ea5777b342fe074ab47d58b4957b895114bc85ecc758c00f
+size 13716235739

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac7071d3414eab95626689b78dadccc9975aa999c144a8b59cc987e20b17ee2
+size 7698394831

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94b1a91810562429d557b8e7351faf37318bcc85fdd6894e29a36576f9f1604
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197cfcfbf9a36f4f36efb39330b481554a65e22895ce4f427a55d7698d737749
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286acad9b0e27fce778ac429763536accf618ccb6ed72963b6f94685e531c5c7
+size 17077402

tokenizer_config.json

@@ -0,0 +1,1013 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "[AUDIO]",
+    "[BEGIN_AUDIO]",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "[ARGS]",
+    "[CALL_ID]",
+    "[THINK]",
+    "[/THINK]",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,1074 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.424242424242424,
+  "eval_steps": 100,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.9522146363556385,
+      "epoch": 0.16835016835016836,
+      "grad_norm": 0.376953125,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9937530517578125,
+      "mean_token_accuracy": 0.7483265110850335,
+      "num_tokens": 1591793.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.3762529502809048,
+      "epoch": 0.3367003367003367,
+      "grad_norm": 0.228515625,
+      "learning_rate": 1.6333333333333335e-05,
+      "loss": 0.3625458145141602,
+      "mean_token_accuracy": 0.8780256441235542,
+      "num_tokens": 3174240.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.3107199192792177,
+      "epoch": 0.5050505050505051,
+      "grad_norm": 0.154296875,
+      "learning_rate": 1.9997430173759876e-05,
+      "loss": 0.30434131622314453,
+      "mean_token_accuracy": 0.8953498190641404,
+      "num_tokens": 4755519.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.2847785219550133,
+      "epoch": 0.6734006734006734,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 1.9980063397715685e-05,
+      "loss": 0.28054773330688476,
+      "mean_token_accuracy": 0.9025071159005165,
+      "num_tokens": 6334024.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "eval_entropy": 0.2793949246406555,
+      "eval_loss": 0.2698107361793518,
+      "eval_mean_token_accuracy": 0.9054524502754211,
+      "eval_num_tokens": 6334024.0,
+      "eval_runtime": 14.0488,
+      "eval_samples_per_second": 17.795,
+      "eval_steps_per_second": 8.898,
+      "eval_token_accuracy": 0.9051616133787281,
+      "step": 100
+    },
+    {
+      "entropy": 0.26899013079702855,
+      "epoch": 0.8417508417508418,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 1.9946341631587086e-05,
+      "loss": 0.26340150833129883,
+      "mean_token_accuracy": 0.9085881695151329,
+      "num_tokens": 7921274.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.24236563958075583,
+      "epoch": 1.0067340067340067,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.9896320137462984e-05,
+      "loss": 0.23591676712036133,
+      "mean_token_accuracy": 0.9202974551186269,
+      "num_tokens": 9458752.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.19062039852142335,
+      "epoch": 1.1750841750841752,
+      "grad_norm": 0.1513671875,
+      "learning_rate": 1.983008088887478e-05,
+      "loss": 0.18400527954101562,
+      "mean_token_accuracy": 0.9372689473628998,
+      "num_tokens": 11049146.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.17757252234965562,
+      "epoch": 1.3434343434343434,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 1.9747732436460955e-05,
+      "loss": 0.17247369766235351,
+      "mean_token_accuracy": 0.9412289550900459,
+      "num_tokens": 12629069.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.3434343434343434,
+      "eval_entropy": 0.17348989713191987,
+      "eval_loss": 0.1803748607635498,
+      "eval_mean_token_accuracy": 0.9387603945732117,
+      "eval_num_tokens": 12629069.0,
+      "eval_runtime": 13.9222,
+      "eval_samples_per_second": 17.957,
+      "eval_steps_per_second": 8.978,
+      "eval_token_accuracy": 0.9386888733819055,
+      "step": 200
+    },
+    {
+      "entropy": 0.17212937109172344,
+      "epoch": 1.5117845117845117,
+      "grad_norm": 0.16015625,
+      "learning_rate": 1.9649409730077934e-05,
+      "loss": 0.1680605125427246,
+      "mean_token_accuracy": 0.9425190502405166,
+      "num_tokens": 14207351.0,
+      "step": 225
+    },
+    {
+      "entropy": 0.16998517245054245,
+      "epoch": 1.6801346801346801,
+      "grad_norm": 0.166015625,
+      "learning_rate": 1.9535273897648857e-05,
+      "loss": 0.1662980079650879,
+      "mean_token_accuracy": 0.943454926609993,
+      "num_tokens": 15787859.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.16503205563873052,
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.9405511981112553e-05,
+      "loss": 0.16160566329956055,
+      "mean_token_accuracy": 0.9454404374957085,
+      "num_tokens": 17374190.0,
+      "step": 275
+    },
+    {
+      "entropy": 0.1615225655615938,
+      "epoch": 2.0134680134680134,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.926033662990558e-05,
+      "loss": 0.15662331581115724,
+      "mean_token_accuracy": 0.9472035674416289,
+      "num_tokens": 18919416.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.0134680134680134,
+      "eval_entropy": 0.1541357452273369,
+      "eval_loss": 0.1643277257680893,
+      "eval_mean_token_accuracy": 0.9455152935981751,
+      "eval_num_tokens": 18919416.0,
+      "eval_runtime": 13.8817,
+      "eval_samples_per_second": 18.009,
+      "eval_steps_per_second": 9.005,
+      "eval_token_accuracy": 0.9454900486056786,
+      "step": 300
+    },
+    {
+      "entropy": 0.14235603258013727,
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 1.9099985752479505e-05,
+      "loss": 0.13640413284301758,
+      "mean_token_accuracy": 0.9537694716453552,
+      "num_tokens": 20493589.0,
+      "step": 325
+    },
+    {
+      "entropy": 0.1364088713005185,
+      "epoch": 2.3501683501683504,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 1.892472212642459e-05,
+      "loss": 0.13120804786682128,
+      "mean_token_accuracy": 0.9558958530426025,
+      "num_tokens": 22071046.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.1340012726187706,
+      "epoch": 2.5185185185185186,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 1.8734832967838775e-05,
+      "loss": 0.12886263847351073,
+      "mean_token_accuracy": 0.956660538315773,
+      "num_tokens": 23651892.0,
+      "step": 375
+    },
+    {
+      "entropy": 0.13179550088942052,
+      "epoch": 2.686868686868687,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 1.8530629460647658e-05,
+      "loss": 0.1262987232208252,
+      "mean_token_accuracy": 0.9577056321501732,
+      "num_tokens": 25237419.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.686868686868687,
+      "eval_entropy": 0.13389861524105073,
+      "eval_loss": 0.1478790044784546,
+      "eval_mean_token_accuracy": 0.9525656714439392,
+      "eval_num_tokens": 25237419.0,
+      "eval_runtime": 14.0025,
+      "eval_samples_per_second": 17.854,
+      "eval_steps_per_second": 8.927,
+      "eval_token_accuracy": 0.9525425978397923,
+      "step": 400
+    },
+    {
+      "entropy": 0.12678295791149138,
+      "epoch": 2.855218855218855,
+      "grad_norm": 0.1796875,
+      "learning_rate": 1.831244624664681e-05,
+      "loss": 0.12145834922790527,
+      "mean_token_accuracy": 0.9593311008810997,
+      "num_tokens": 26831783.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.12364728927460251,
+      "epoch": 3.0202020202020203,
+      "grad_norm": 0.1796875,
+      "learning_rate": 1.808064087710212e-05,
+      "loss": 0.11712233543395996,
+      "mean_token_accuracy": 0.9609322833771609,
+      "num_tokens": 28376572.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.09804413143545389,
+      "epoch": 3.1885521885521886,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.7835593226806902e-05,
+      "loss": 0.0911950397491455,
+      "mean_token_accuracy": 0.9690286010503769,
+      "num_tokens": 29961022.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.09506628409028053,
+      "epoch": 3.356902356902357,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 1.7577704871555924e-05,
+      "loss": 0.08855191230773926,
+      "mean_token_accuracy": 0.9698488730192184,
+      "num_tokens": 31553946.0,
+      "step": 500
+    },
+    {
+      "epoch": 3.356902356902357,
+      "eval_entropy": 0.10651444137096405,
+      "eval_loss": 0.1412735879421234,
+      "eval_mean_token_accuracy": 0.9571833200454712,
+      "eval_num_tokens": 31553946.0,
+      "eval_runtime": 13.9481,
+      "eval_samples_per_second": 17.924,
+      "eval_steps_per_second": 8.962,
+      "eval_token_accuracy": 0.9571799455825543,
+      "step": 500
+    },
+    {
+      "entropy": 0.09585228541865945,
+      "epoch": 3.525252525252525,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 1.7307398430056595e-05,
+      "loss": 0.08968615531921387,
+      "mean_token_accuracy": 0.9697143504023552,
+      "num_tokens": 33135630.0,
+      "step": 525
+    },
+    {
+      "entropy": 0.10036869466304779,
+      "epoch": 3.6936026936026938,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 1.7025116871355737e-05,
+      "loss": 0.09400833129882813,
+      "mean_token_accuracy": 0.9683772554993629,
+      "num_tokens": 34707432.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.0957243438065052,
+      "epoch": 3.861952861952862,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 1.6731322788916892e-05,
+      "loss": 0.08972453117370606,
+      "mean_token_accuracy": 0.9695299303531647,
+      "num_tokens": 36292817.0,
+      "step": 575
+    },
+    {
+      "entropy": 0.0924541620841744,
+      "epoch": 4.026936026936027,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.6426497642537826e-05,
+      "loss": 0.08610689163208007,
+      "mean_token_accuracy": 0.9709198608690378,
+      "num_tokens": 37832802.0,
+      "step": 600
+    },
+    {
+      "epoch": 4.026936026936027,
+      "eval_entropy": 0.08664591646194458,
+      "eval_loss": 0.14084948599338531,
+      "eval_mean_token_accuracy": 0.9594513201713561,
+      "eval_num_tokens": 37832802.0,
+      "eval_runtime": 14.1668,
+      "eval_samples_per_second": 17.647,
+      "eval_steps_per_second": 8.823,
+      "eval_token_accuracy": 0.9594704655647771,
+      "step": 600
+    },
+    {
+      "entropy": 0.07393988940864801,
+      "epoch": 4.1952861952861955,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 1.6111140969350504e-05,
+      "loss": 0.06671238899230957,
+      "mean_token_accuracy": 0.9773511955142021,
+      "num_tokens": 39420574.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.07375508725643158,
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 1.5785769565196543e-05,
+      "loss": 0.06662603855133056,
+      "mean_token_accuracy": 0.9770343449711799,
+      "num_tokens": 40995243.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.0700146171823144,
+      "epoch": 4.531986531986532,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.5450916637719683e-05,
+      "loss": 0.06388366222381592,
+      "mean_token_accuracy": 0.9781549483537674,
+      "num_tokens": 42585578.0,
+      "step": 675
+    },
+    {
+      "entropy": 0.07131696030497552,
+      "epoch": 4.700336700336701,
+      "grad_norm": 0.166015625,
+      "learning_rate": 1.5107130932563151e-05,
+      "loss": 0.0648357915878296,
+      "mean_token_accuracy": 0.9776528170704841,
+      "num_tokens": 44164669.0,
+      "step": 700
+    },
+    {
+      "epoch": 4.700336700336701,
+      "eval_entropy": 0.08206569665670395,
+      "eval_loss": 0.13808086514472961,
+      "eval_mean_token_accuracy": 0.9618017344474793,
+      "eval_num_tokens": 44164669.0,
+      "eval_runtime": 13.9704,
+      "eval_samples_per_second": 17.895,
+      "eval_steps_per_second": 8.947,
+      "eval_token_accuracy": 0.9618092493569853,
+      "step": 700
+    },
+    {
+      "entropy": 0.06924619141966104,
+      "epoch": 4.8686868686868685,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 1.4754975834103877e-05,
+      "loss": 0.06314377784729004,
+      "mean_token_accuracy": 0.9783227249979973,
+      "num_tokens": 45746386.0,
+      "step": 725
+    },
+    {
+      "entropy": 0.06477328384181066,
+      "epoch": 5.033670033670034,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.4395028442197231e-05,
+      "loss": 0.057736573219299314,
+      "mean_token_accuracy": 0.9802252127199756,
+      "num_tokens": 47291064.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.05126072809100151,
+      "epoch": 5.202020202020202,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 1.4027878626445339e-05,
+      "loss": 0.04461108207702637,
+      "mean_token_accuracy": 0.984737733900547,
+      "num_tokens": 48874157.0,
+      "step": 775
+    },
+    {
+      "entropy": 0.05017553111538291,
+      "epoch": 5.37037037037037,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 1.365412805953872e-05,
+      "loss": 0.043688578605651854,
+      "mean_token_accuracy": 0.9849283066391945,
+      "num_tokens": 50457004.0,
+      "step": 800
+    },
+    {
+      "epoch": 5.37037037037037,
+      "eval_entropy": 0.0671493958979845,
+      "eval_loss": 0.15137650072574615,
+      "eval_mean_token_accuracy": 0.9625004653930664,
+      "eval_num_tokens": 50457004.0,
+      "eval_runtime": 13.8354,
+      "eval_samples_per_second": 18.07,
+      "eval_steps_per_second": 9.035,
+      "eval_token_accuracy": 0.9625030416255251,
+      "step": 800
+    },
+    {
+      "entropy": 0.049754718681797386,
+      "epoch": 5.538720538720539,
+      "grad_norm": 0.138671875,
+      "learning_rate": 1.3274389231255466e-05,
+      "loss": 0.043588805198669436,
+      "mean_token_accuracy": 0.9849756741523743,
+      "num_tokens": 52047687.0,
+      "step": 825
+    },
+    {
+      "entropy": 0.048861624505370856,
+      "epoch": 5.707070707070707,
+      "grad_norm": 0.1484375,
+      "learning_rate": 1.2889284444733722e-05,
+      "loss": 0.04272536277770996,
+      "mean_token_accuracy": 0.9852952674031258,
+      "num_tokens": 53626751.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.049314973950386046,
+      "epoch": 5.875420875420875,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.2499444796662354e-05,
+      "loss": 0.04330784320831299,
+      "mean_token_accuracy": 0.9850323754549026,
+      "num_tokens": 55212090.0,
+      "step": 875
+    },
+    {
+      "entropy": 0.04571919083329184,
+      "epoch": 6.040404040404041,
+      "grad_norm": 0.140625,
+      "learning_rate": 1.2105509143061072e-05,
+      "loss": 0.03899869203567505,
+      "mean_token_accuracy": 0.9866329042278991,
+      "num_tokens": 56756053.0,
+      "step": 900
+    },
+    {
+      "epoch": 6.040404040404041,
+      "eval_entropy": 0.055020518347620964,
+      "eval_loss": 0.1728222817182541,
+      "eval_mean_token_accuracy": 0.9626847972869873,
+      "eval_num_tokens": 56756053.0,
+      "eval_runtime": 13.8671,
+      "eval_samples_per_second": 18.028,
+      "eval_steps_per_second": 9.014,
+      "eval_token_accuracy": 0.9626900638892185,
+      "step": 900
+    },
+    {
+      "entropy": 0.034643625281751154,
+      "epoch": 6.2087542087542085,
+      "grad_norm": 0.12109375,
+      "learning_rate": 1.1708123052344803e-05,
+      "loss": 0.028563168048858643,
+      "mean_token_accuracy": 0.9902752894163132,
+      "num_tokens": 58343293.0,
+      "step": 925
+    },
+    {
+      "entropy": 0.03522825219668448,
+      "epoch": 6.377104377104377,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 1.1307937747388034e-05,
+      "loss": 0.028969509601593016,
+      "mean_token_accuracy": 0.9901717621088028,
+      "num_tokens": 59924721.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.034883827781304715,
+      "epoch": 6.545454545454545,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 1.090560903832278e-05,
+      "loss": 0.028860065937042236,
+      "mean_token_accuracy": 0.9901738902926445,
+      "num_tokens": 61500807.0,
+      "step": 975
+    },
+    {
+      "entropy": 0.03482985371723771,
+      "epoch": 6.713804713804714,
+      "grad_norm": 0.166015625,
+      "learning_rate": 1.0501796247819176e-05,
+      "loss": 0.02919963836669922,
+      "mean_token_accuracy": 0.9900345727801323,
+      "num_tokens": 63084518.0,
+      "step": 1000
+    },
+    {
+      "epoch": 6.713804713804714,
+      "eval_entropy": 0.0541005334854126,
+      "eval_loss": 0.16875509917736053,
+      "eval_mean_token_accuracy": 0.9639611830711364,
+      "eval_num_tokens": 63084518.0,
+      "eval_runtime": 13.9974,
+      "eval_samples_per_second": 17.86,
+      "eval_steps_per_second": 8.93,
+      "eval_token_accuracy": 0.963954977909252,
+      "step": 1000
+    },
+    {
+      "entropy": 0.03346874587237835,
+      "epoch": 6.882154882154882,
+      "grad_norm": 0.1640625,
+      "learning_rate": 1.0097161130609774e-05,
+      "loss": 0.027893943786621092,
+      "mean_token_accuracy": 0.9905096918344498,
+      "num_tokens": 64660786.0,
+      "step": 1025
+    },
+    {
+      "entropy": 0.03328982365260623,
+      "epoch": 7.047138047138047,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 9.692366789028308e-06,
+      "loss": 0.026968984603881835,
+      "mean_token_accuracy": 0.990928383201969,
+      "num_tokens": 66215390.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.024703437695279717,
+      "epoch": 7.215488215488215,
+      "grad_norm": 0.140625,
+      "learning_rate": 9.288076586340005e-06,
+      "loss": 0.018726770877838136,
+      "mean_token_accuracy": 0.9938653546571732,
+      "num_tokens": 67789474.0,
+      "step": 1075
+    },
+    {
+      "entropy": 0.02491601270623505,
+      "epoch": 7.383838383838384,
+      "grad_norm": 0.1328125,
+      "learning_rate": 8.88495305964436e-06,
+      "loss": 0.019079389572143553,
+      "mean_token_accuracy": 0.9937083786725998,
+      "num_tokens": 69374157.0,
+      "step": 1100
+    },
+    {
+      "epoch": 7.383838383838384,
+      "eval_entropy": 0.04581953993439675,
+      "eval_loss": 0.19364017248153687,
+      "eval_mean_token_accuracy": 0.9638748369216918,
+      "eval_num_tokens": 69374157.0,
+      "eval_runtime": 13.8268,
+      "eval_samples_per_second": 18.081,
+      "eval_steps_per_second": 9.04,
+      "eval_token_accuracy": 0.9638604612813639,
+      "step": 1100
+    },
+    {
+      "entropy": 0.024102514907717705,
+      "epoch": 7.552188552188552,
+      "grad_norm": 0.140625,
+      "learning_rate": 8.48365683413172e-06,
+      "loss": 0.018542931079864503,
+      "mean_token_accuracy": 0.9938124868273736,
+      "num_tokens": 70951571.0,
+      "step": 1125
+    },
+    {
+      "entropy": 0.023655354911461472,
+      "epoch": 7.720538720538721,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 8.084845540473127e-06,
+      "loss": 0.0183677613735199,
+      "mean_token_accuracy": 0.9938945046067238,
+      "num_tokens": 72531150.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.02381689740344882,
+      "epoch": 7.888888888888889,
+      "grad_norm": 0.12109375,
+      "learning_rate": 7.689172737117389e-06,
+      "loss": 0.018559412956237795,
+      "mean_token_accuracy": 0.9938493025302887,
+      "num_tokens": 74120322.0,
+      "step": 1175
+    },
+    {
+      "entropy": 0.021846223494266064,
+      "epoch": 8.053872053872054,
+      "grad_norm": 0.09765625,
+      "learning_rate": 7.297286839261659e-06,
+      "loss": 0.016244869232177734,
+      "mean_token_accuracy": 0.9946904477416253,
+      "num_tokens": 75671469.0,
+      "step": 1200
+    },
+    {
+      "epoch": 8.053872053872054,
+      "eval_entropy": 0.04140873943269253,
+      "eval_loss": 0.21278557181358337,
+      "eval_mean_token_accuracy": 0.9638264698982238,
+      "eval_num_tokens": 75671469.0,
+      "eval_runtime": 13.8279,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 9.04,
+      "eval_token_accuracy": 0.9638101864792958,
+      "step": 1200
+    },
+    {
+      "entropy": 0.018266186909750105,
+      "epoch": 8.222222222222221,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.012853317260742188,
+      "mean_token_accuracy": 0.9959348595142364,
+      "num_tokens": 77255219.0,
+      "step": 1225
+    },
+    {
+      "entropy": 0.017858617678284644,
+      "epoch": 8.390572390572391,
+      "grad_norm": 0.107421875,
+      "learning_rate": 6.527437339145097e-06,
+      "loss": 0.012499079704284669,
+      "mean_token_accuracy": 0.9960082057118416,
+      "num_tokens": 78840351.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.018353314991109072,
+      "epoch": 8.558922558922559,
+      "grad_norm": 0.11376953125,
+      "learning_rate": 6.1507353401866896e-06,
+      "loss": 0.01300368070602417,
+      "mean_token_accuracy": 0.9958306196331977,
+      "num_tokens": 80420094.0,
+      "step": 1275
+    },
+    {
+      "entropy": 0.017453019949607552,
+      "epoch": 8.727272727272727,
+      "grad_norm": 0.103515625,
+      "learning_rate": 5.780341385860333e-06,
+      "loss": 0.012396881580352783,
+      "mean_token_accuracy": 0.9960150149464607,
+      "num_tokens": 82008321.0,
+      "step": 1300
+    },
+    {
+      "epoch": 8.727272727272727,
+      "eval_entropy": 0.03956229141354561,
+      "eval_loss": 0.22291041910648346,
+      "eval_mean_token_accuracy": 0.9638104586601257,
+      "eval_num_tokens": 82008321.0,
+      "eval_runtime": 13.8719,
+      "eval_samples_per_second": 18.022,
+      "eval_steps_per_second": 9.011,
+      "eval_token_accuracy": 0.9637880655663859,
+      "step": 1300
+    },
+    {
+      "entropy": 0.01774411663878709,
+      "epoch": 8.895622895622896,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 5.416862465241033e-06,
+      "loss": 0.012684780359268188,
+      "mean_token_accuracy": 0.9958784037828445,
+      "num_tokens": 83583971.0,
+      "step": 1325
+    },
+    {
+      "entropy": 0.01662842344435654,
+      "epoch": 9.06060606060606,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 5.060894235280637e-06,
+      "loss": 0.011442055702209472,
+      "mean_token_accuracy": 0.9964186977975222,
+      "num_tokens": 85130709.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.01486415593419224,
+      "epoch": 9.228956228956228,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 4.713020044665348e-06,
+      "loss": 0.009846681952476502,
+      "mean_token_accuracy": 0.9969244155287743,
+      "num_tokens": 86706204.0,
+      "step": 1375
+    },
+    {
+      "entropy": 0.015145676247775554,
+      "epoch": 9.397306397306398,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 4.373809977843676e-06,
+      "loss": 0.010009793043136596,
+      "mean_token_accuracy": 0.9968555930256844,
+      "num_tokens": 88290356.0,
+      "step": 1400
+    },
+    {
+      "epoch": 9.397306397306398,
+      "eval_entropy": 0.03756700618565083,
+      "eval_loss": 0.23951546847820282,
+      "eval_mean_token_accuracy": 0.9634870853424072,
+      "eval_num_tokens": 88290356.0,
+      "eval_runtime": 13.8742,
+      "eval_samples_per_second": 18.019,
+      "eval_steps_per_second": 9.009,
+      "eval_token_accuracy": 0.9634723398093982,
+      "step": 1400
+    },
+    {
+      "entropy": 0.014698740621097385,
+      "epoch": 9.565656565656566,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 4.043819920791322e-06,
+      "loss": 0.00973641276359558,
+      "mean_token_accuracy": 0.996994196176529,
+      "num_tokens": 89873272.0,
+      "step": 1425
+    },
+    {
+      "entropy": 0.014629123574122787,
+      "epoch": 9.734006734006734,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 3.7235906500440576e-06,
+      "loss": 0.00979375422000885,
+      "mean_token_accuracy": 0.9969650763273239,
+      "num_tokens": 91455959.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.014975303104147315,
+      "epoch": 9.902356902356903,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 3.413646946491458e-06,
+      "loss": 0.009887872934341431,
+      "mean_token_accuracy": 0.9969008722901345,
+      "num_tokens": 93038545.0,
+      "step": 1475
+    },
+    {
+      "entropy": 0.014437279744757985,
+      "epoch": 10.067340067340067,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 3.1144967353837196e-06,
+      "loss": 0.009359861612319947,
+      "mean_token_accuracy": 0.9971185049840382,
+      "num_tokens": 94591222.0,
+      "step": 1500
+    },
+    {
+      "epoch": 10.067340067340067,
+      "eval_entropy": 0.03697392378747463,
+      "eval_loss": 0.24305777251720428,
+      "eval_mean_token_accuracy": 0.9633980007171631,
+      "eval_num_tokens": 94591222.0,
+      "eval_runtime": 13.8912,
+      "eval_samples_per_second": 17.997,
+      "eval_steps_per_second": 8.999,
+      "eval_token_accuracy": 0.9633818451656756,
+      "step": 1500
+    },
+    {
+      "entropy": 0.013786709853447973,
+      "epoch": 10.235690235690235,
+      "grad_norm": 0.068359375,
+      "learning_rate": 2.8266302539609747e-06,
+      "loss": 0.008779547214508056,
+      "mean_token_accuracy": 0.9973234468698502,
+      "num_tokens": 96172254.0,
+      "step": 1525
+    },
+    {
+      "entropy": 0.013736034976318479,
+      "epoch": 10.404040404040405,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 2.5505192480690865e-06,
+      "loss": 0.008723703622817993,
+      "mean_token_accuracy": 0.9973191824555397,
+      "num_tokens": 97747622.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.01360086859203875,
+      "epoch": 10.572390572390573,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 2.2866161990785228e-06,
+      "loss": 0.008712610602378846,
+      "mean_token_accuracy": 0.997349898815155,
+      "num_tokens": 99335839.0,
+      "step": 1575
+    },
+    {
+      "entropy": 0.013570407247170806,
+      "epoch": 10.74074074074074,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 2.0353535823732053e-06,
+      "loss": 0.008633202314376831,
+      "mean_token_accuracy": 0.9973410308361054,
+      "num_tokens": 100917282.0,
+      "step": 1600
+    },
+    {
+      "epoch": 10.74074074074074,
+      "eval_entropy": 0.03649875710904598,
+      "eval_loss": 0.2482212781906128,
+      "eval_mean_token_accuracy": 0.9633483939170837,
+      "eval_num_tokens": 100917282.0,
+      "eval_runtime": 13.819,
+      "eval_samples_per_second": 18.091,
+      "eval_steps_per_second": 9.045,
+      "eval_token_accuracy": 0.9633335813556902,
+      "step": 1600
+    },
+    {
+      "entropy": 0.013947828765958547,
+      "epoch": 10.909090909090908,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 1.7971431586244814e-06,
+      "loss": 0.008911921381950379,
+      "mean_token_accuracy": 0.9972717782855034,
+      "num_tokens": 102499386.0,
+      "step": 1625
+    },
+    {
+      "entropy": 0.013590329364702409,
+      "epoch": 11.074074074074074,
+      "grad_norm": 0.0703125,
+      "learning_rate": 1.5723752990116948e-06,
+      "loss": 0.008526145815849304,
+      "mean_token_accuracy": 0.9974123969370005,
+      "num_tokens": 104048535.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.013840707880444825,
+      "epoch": 11.242424242424242,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 1.3614183454950824e-06,
+      "loss": 0.00863082766532898,
+      "mean_token_accuracy": 0.9974041077494621,
+      "num_tokens": 105626902.0,
+      "step": 1675
+    },
+    {
+      "entropy": 0.01306802561506629,
+      "epoch": 11.41077441077441,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 1.1646180071894608e-06,
+      "loss": 0.008170877695083617,
+      "mean_token_accuracy": 0.9975323963165283,
+      "num_tokens": 107208502.0,
+      "step": 1700
+    },
+    {
+      "epoch": 11.41077441077441,
+      "eval_entropy": 0.036279944390058515,
+      "eval_loss": 0.25036948919296265,
+      "eval_mean_token_accuracy": 0.9632471032142639,
+      "eval_num_tokens": 107208502.0,
+      "eval_runtime": 13.8985,
+      "eval_samples_per_second": 17.988,
+      "eval_steps_per_second": 8.994,
+      "eval_token_accuracy": 0.963233031751554,
+      "step": 1700
+    },
+    {
+      "entropy": 0.013187658675014972,
+      "epoch": 11.57912457912458,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 9.822967938278172e-07,
+      "loss": 0.008353355526924133,
+      "mean_token_accuracy": 0.9974633774161339,
+      "num_tokens": 108793895.0,
+      "step": 1725
+    },
+    {
+      "entropy": 0.013317351192235947,
+      "epoch": 11.747474747474747,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 8.147534872432761e-07,
+      "loss": 0.008341993093490601,
+      "mean_token_accuracy": 0.9975066068768501,
+      "num_tokens": 110382929.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.013570899264886976,
+      "epoch": 11.915824915824915,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 6.622626517355557e-07,
+      "loss": 0.008468236327171325,
+      "mean_token_accuracy": 0.9973884886503219,
+      "num_tokens": 111971394.0,
+      "step": 1775
+    },
+    {
+      "entropy": 0.013678188079359884,
+      "epoch": 12.080808080808081,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 5.250741841242735e-07,
+      "loss": 0.008458149433135987,
+      "mean_token_accuracy": 0.9974453488782961,
+      "num_tokens": 113511798.0,
+      "step": 1800
+    },
+    {
+      "epoch": 12.080808080808081,
+      "eval_entropy": 0.036235544994473456,
+      "eval_loss": 0.2506777346134186,
+      "eval_mean_token_accuracy": 0.9632981281280517,
+      "eval_num_tokens": 113511798.0,
+      "eval_runtime": 13.8333,
+      "eval_samples_per_second": 18.072,
+      "eval_steps_per_second": 9.036,
+      "eval_token_accuracy": 0.9632792845694567,
+      "step": 1800
+    },
+    {
+      "entropy": 0.013473317860625684,
+      "epoch": 12.24915824915825,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 4.034129042265067e-07,
+      "loss": 0.008400481343269348,
+      "mean_token_accuracy": 0.9974551931023597,
+      "num_tokens": 115097998.0,
+      "step": 1825
+    },
+    {
+      "entropy": 0.01321539796423167,
+      "epoch": 12.417508417508417,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 2.974781864296783e-07,
+      "loss": 0.008239768147468567,
+      "mean_token_accuracy": 0.9975069260597229,
+      "num_tokens": 116678393.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.013363241832703352,
+      "epoch": 12.585858585858587,
+      "grad_norm": 0.072265625,
+      "learning_rate": 2.0744363296356872e-07,
+      "loss": 0.008337837457656861,
+      "mean_token_accuracy": 0.9975020122528077,
+      "num_tokens": 118256344.0,
+      "step": 1875
+    },
+    {
+      "entropy": 0.013509186143055558,
+      "epoch": 12.754208754208754,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 1.3345678940684615e-07,
+      "loss": 0.008378518223762512,
+      "mean_token_accuracy": 0.9974912297725678,
+      "num_tokens": 119840932.0,
+      "step": 1900
+    },
+    {
+      "epoch": 12.754208754208754,
+      "eval_entropy": 0.036245557606220245,
+      "eval_loss": 0.2508084177970886,
+      "eval_mean_token_accuracy": 0.9633139533996582,
+      "eval_num_tokens": 119840932.0,
+      "eval_runtime": 13.8832,
+      "eval_samples_per_second": 18.007,
+      "eval_steps_per_second": 9.004,
+      "eval_token_accuracy": 0.9632933615140358,
+      "step": 1900
+    },
+    {
+      "entropy": 0.013419822426512837,
+      "epoch": 12.922558922558922,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 7.563890289437825e-08,
+      "loss": 0.008330971598625184,
+      "mean_token_accuracy": 0.9974869236350059,
+      "num_tokens": 121419896.0,
+      "step": 1925
+    },
+    {
+      "entropy": 0.013293538674978274,
+      "epoch": 13.087542087542088,
+      "grad_norm": 0.078125,
+      "learning_rate": 3.408472342152136e-08,
+      "loss": 0.008297484517097473,
+      "mean_token_accuracy": 0.9974846158708844,
+      "num_tokens": 122967645.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.013380372445099056,
+      "epoch": 13.255892255892256,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 8.862348571043733e-09,
+      "loss": 0.008304932117462159,
+      "mean_token_accuracy": 0.9974824267625809,
+      "num_tokens": 124542187.0,
+      "step": 1975
+    },
+    {
+      "entropy": 0.013427549134939909,
+      "epoch": 13.424242424242424,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 1.311191710651194e-11,
+      "loss": 0.008341950178146363,
+      "mean_token_accuracy": 0.9974777749180794,
+      "num_tokens": 126127250.0,
+      "step": 2000
+    },
+    {
+      "epoch": 13.424242424242424,
+      "eval_entropy": 0.036229205310344695,
+      "eval_loss": 0.2507854700088501,
+      "eval_mean_token_accuracy": 0.9632595100402832,
+      "eval_num_tokens": 126127250.0,
+      "eval_runtime": 13.8215,
+      "eval_samples_per_second": 18.088,
+      "eval_steps_per_second": 9.044,
+      "eval_token_accuracy": 0.9632390647278022,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 14,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.700374075876745e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}