Add Devstral-14B CPT training run

.gitattributes

@@ -43,3 +43,8 @@ cpt_qwen_14B/checkpoints/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge
 cpt_qwen_14B/checkpoints/checkpoint-656/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 cpt_qwen_14B/wandb/offline-run-20251223_125436-g6vlcw0j/run-g6vlcw0j.wandb filter=lfs diff=lfs merge=lfs -text
 sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/run-ldjr67u6.wandb filter=lfs diff=lfs merge=lfs -text
+cpt_devstral_24B/best_adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+cpt_devstral_24B/checkpoints/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+cpt_devstral_24B/checkpoints/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+cpt_devstral_24B/checkpoints/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+cpt_devstral_24B/checkpoints/checkpoint-686/tokenizer.json filter=lfs diff=lfs merge=lfs -text

cpt_devstral_24B/best_adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/Models/Devstral-Small-2-24B-Instruct-2512
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/Models/Devstral-Small-2-24B-Instruct-2512
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

cpt_devstral_24B/best_adapter/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/Models/Devstral-Small-2-24B-Instruct-2512",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

cpt_devstral_24B/best_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6528dd74de4fce9bff6c944acd9bc01868d155b1ea5403fe93fb8c5ced4d4ec
+size 364983848

cpt_devstral_24B/best_adapter/chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = '' %}
+
+{#- 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 %}

cpt_devstral_24B/best_adapter/tokenizer.json

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

cpt_devstral_24B/best_adapter/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": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

cpt_devstral_24B/best_adapter/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62526ec2433add7ac031c48b1f6ff360f1ade77275765112cbf7cf361d64ca5
+size 5201

cpt_devstral_24B/checkpoints/checkpoint-400/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/Models/Devstral-Small-2-24B-Instruct-2512
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/Models/Devstral-Small-2-24B-Instruct-2512
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

cpt_devstral_24B/checkpoints/checkpoint-400/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/Models/Devstral-Small-2-24B-Instruct-2512",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

cpt_devstral_24B/checkpoints/checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb99e750772d0be3eae91b1278f180702595f9e801cdcfe108166e6afe96e5ca
+size 364983848

cpt_devstral_24B/checkpoints/checkpoint-400/chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = '' %}
+
+{#- 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 %}

cpt_devstral_24B/checkpoints/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5539bb24f0e90b59b5feaa90ce48faf2a89fef6e84d938cfdb015b096793c9e
+size 160131559

cpt_devstral_24B/checkpoints/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c636bd3acde73735b158db1a7551369c5642650cac64756dc42008fea4a8a41c
+size 14645

cpt_devstral_24B/checkpoints/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63227fb4710085463616ae42dc93bbd119bc402348d37ec9f6ab60b0d130235e
+size 1465

cpt_devstral_24B/checkpoints/checkpoint-400/tokenizer.json

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

cpt_devstral_24B/checkpoints/checkpoint-400/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": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

cpt_devstral_24B/checkpoints/checkpoint-400/trainer_state.json

@@ -0,0 +1,2898 @@
+{
+  "best_global_step": 400,
+  "best_metric": 0.4318464398384094,
+  "best_model_checkpoint": "runs/cpt_run_v1/checkpoints/checkpoint-400",
+  "epoch": 1.1662716499544212,
+  "eval_steps": 50,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029170464904284413,
+      "grad_norm": 1.1577509641647339,
+      "learning_rate": 0.0,
+      "loss": 0.9893555045127869,
+      "step": 1
+    },
+    {
+      "epoch": 0.005834092980856883,
+      "grad_norm": 0.9491796493530273,
+      "learning_rate": 2.8985507246376816e-07,
+      "loss": 0.8791205883026123,
+      "step": 2
+    },
+    {
+      "epoch": 0.008751139471285323,
+      "grad_norm": 1.1600768566131592,
+      "learning_rate": 5.797101449275363e-07,
+      "loss": 0.9858248233795166,
+      "step": 3
+    },
+    {
+      "epoch": 0.011668185961713765,
+      "grad_norm": 1.2298306226730347,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.0516364574432373,
+      "step": 4
+    },
+    {
+      "epoch": 0.014585232452142206,
+      "grad_norm": 0.9520533680915833,
+      "learning_rate": 1.1594202898550726e-06,
+      "loss": 0.8392249345779419,
+      "step": 5
+    },
+    {
+      "epoch": 0.017502278942570646,
+      "grad_norm": 1.2451188564300537,
+      "learning_rate": 1.4492753623188408e-06,
+      "loss": 1.0955077409744263,
+      "step": 6
+    },
+    {
+      "epoch": 0.02041932543299909,
+      "grad_norm": 1.1123991012573242,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.9201866388320923,
+      "step": 7
+    },
+    {
+      "epoch": 0.02333637192342753,
+      "grad_norm": 0.9283139705657959,
+      "learning_rate": 2.028985507246377e-06,
+      "loss": 0.9770950078964233,
+      "step": 8
+    },
+    {
+      "epoch": 0.02625341841385597,
+      "grad_norm": 0.9589216113090515,
+      "learning_rate": 2.3188405797101453e-06,
+      "loss": 0.9442565441131592,
+      "step": 9
+    },
+    {
+      "epoch": 0.02917046490428441,
+      "grad_norm": 0.8866703510284424,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.9354464411735535,
+      "step": 10
+    },
+    {
+      "epoch": 0.03208751139471285,
+      "grad_norm": 0.7191241383552551,
+      "learning_rate": 2.8985507246376816e-06,
+      "loss": 0.7659736275672913,
+      "step": 11
+    },
+    {
+      "epoch": 0.03500455788514129,
+      "grad_norm": 0.9110142588615417,
+      "learning_rate": 3.188405797101449e-06,
+      "loss": 0.9319326877593994,
+      "step": 12
+    },
+    {
+      "epoch": 0.03792160437556973,
+      "grad_norm": 0.8754057288169861,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.9819356203079224,
+      "step": 13
+    },
+    {
+      "epoch": 0.04083865086599818,
+      "grad_norm": 0.896181046962738,
+      "learning_rate": 3.768115942028986e-06,
+      "loss": 1.026316523551941,
+      "step": 14
+    },
+    {
+      "epoch": 0.04375569735642662,
+      "grad_norm": 0.6104832887649536,
+      "learning_rate": 4.057971014492754e-06,
+      "loss": 0.8427562713623047,
+      "step": 15
+    },
+    {
+      "epoch": 0.04667274384685506,
+      "grad_norm": 0.6529208421707153,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.8496565222740173,
+      "step": 16
+    },
+    {
+      "epoch": 0.0495897903372835,
+      "grad_norm": 0.6319335699081421,
+      "learning_rate": 4.637681159420291e-06,
+      "loss": 0.9139047861099243,
+      "step": 17
+    },
+    {
+      "epoch": 0.05250683682771194,
+      "grad_norm": 0.7458649277687073,
+      "learning_rate": 4.927536231884059e-06,
+      "loss": 0.8867442011833191,
+      "step": 18
+    },
+    {
+      "epoch": 0.05542388331814038,
+      "grad_norm": 0.6179773211479187,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.9579408168792725,
+      "step": 19
+    },
+    {
+      "epoch": 0.05834092980856882,
+      "grad_norm": 0.794481635093689,
+      "learning_rate": 5.507246376811595e-06,
+      "loss": 0.8736554980278015,
+      "step": 20
+    },
+    {
+      "epoch": 0.06125797629899726,
+      "grad_norm": 0.8356145620346069,
+      "learning_rate": 5.797101449275363e-06,
+      "loss": 0.9358762502670288,
+      "step": 21
+    },
+    {
+      "epoch": 0.0641750227894257,
+      "grad_norm": 0.5891932845115662,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.8972038626670837,
+      "step": 22
+    },
+    {
+      "epoch": 0.06709206927985414,
+      "grad_norm": 0.6931268572807312,
+      "learning_rate": 6.376811594202898e-06,
+      "loss": 0.9583507776260376,
+      "step": 23
+    },
+    {
+      "epoch": 0.07000911577028258,
+      "grad_norm": 0.7298229336738586,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8119489550590515,
+      "step": 24
+    },
+    {
+      "epoch": 0.07292616226071102,
+      "grad_norm": 0.6419956684112549,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.9386100769042969,
+      "step": 25
+    },
+    {
+      "epoch": 0.07584320875113947,
+      "grad_norm": 0.7508338689804077,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 0.9272583723068237,
+      "step": 26
+    },
+    {
+      "epoch": 0.0787602552415679,
+      "grad_norm": 0.5848079919815063,
+      "learning_rate": 7.536231884057972e-06,
+      "loss": 0.8967856168746948,
+      "step": 27
+    },
+    {
+      "epoch": 0.08167730173199636,
+      "grad_norm": 0.7384837865829468,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.8696568012237549,
+      "step": 28
+    },
+    {
+      "epoch": 0.0845943482224248,
+      "grad_norm": 0.5069604516029358,
+      "learning_rate": 8.115942028985508e-06,
+      "loss": 0.9121193885803223,
+      "step": 29
+    },
+    {
+      "epoch": 0.08751139471285324,
+      "grad_norm": 0.833165168762207,
+      "learning_rate": 8.405797101449275e-06,
+      "loss": 0.8180589079856873,
+      "step": 30
+    },
+    {
+      "epoch": 0.09042844120328168,
+      "grad_norm": 0.6355920433998108,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.8640957474708557,
+      "step": 31
+    },
+    {
+      "epoch": 0.09334548769371012,
+      "grad_norm": 1.0429315567016602,
+      "learning_rate": 8.985507246376812e-06,
+      "loss": 0.9517915844917297,
+      "step": 32
+    },
+    {
+      "epoch": 0.09626253418413856,
+      "grad_norm": 0.5875154733657837,
+      "learning_rate": 9.275362318840581e-06,
+      "loss": 0.9443603754043579,
+      "step": 33
+    },
+    {
+      "epoch": 0.099179580674567,
+      "grad_norm": 1.9913769960403442,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.9510866403579712,
+      "step": 34
+    },
+    {
+      "epoch": 0.10209662716499544,
+      "grad_norm": 0.5310097932815552,
+      "learning_rate": 9.855072463768118e-06,
+      "loss": 0.8653419613838196,
+      "step": 35
+    },
+    {
+      "epoch": 0.10501367365542388,
+      "grad_norm": 0.624421238899231,
+      "learning_rate": 1.0144927536231885e-05,
+      "loss": 0.7941208481788635,
+      "step": 36
+    },
+    {
+      "epoch": 0.10793072014585232,
+      "grad_norm": 0.6314200758934021,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.8931174278259277,
+      "step": 37
+    },
+    {
+      "epoch": 0.11084776663628076,
+      "grad_norm": 0.6272342205047607,
+      "learning_rate": 1.0724637681159422e-05,
+      "loss": 0.8978185057640076,
+      "step": 38
+    },
+    {
+      "epoch": 0.1137648131267092,
+      "grad_norm": 0.5711184740066528,
+      "learning_rate": 1.101449275362319e-05,
+      "loss": 0.808263897895813,
+      "step": 39
+    },
+    {
+      "epoch": 0.11668185961713765,
+      "grad_norm": 0.7581208944320679,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.7456756830215454,
+      "step": 40
+    },
+    {
+      "epoch": 0.11959890610756609,
+      "grad_norm": 0.4989977180957794,
+      "learning_rate": 1.1594202898550726e-05,
+      "loss": 0.8273333311080933,
+      "step": 41
+    },
+    {
+      "epoch": 0.12251595259799453,
+      "grad_norm": 0.8602972626686096,
+      "learning_rate": 1.1884057971014494e-05,
+      "loss": 0.8514784574508667,
+      "step": 42
+    },
+    {
+      "epoch": 0.12543299908842298,
+      "grad_norm": 0.6918581128120422,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.8182265162467957,
+      "step": 43
+    },
+    {
+      "epoch": 0.1283500455788514,
+      "grad_norm": 0.653099536895752,
+      "learning_rate": 1.2463768115942029e-05,
+      "loss": 0.8242791891098022,
+      "step": 44
+    },
+    {
+      "epoch": 0.13126709206927986,
+      "grad_norm": 0.7485584616661072,
+      "learning_rate": 1.2753623188405797e-05,
+      "loss": 0.8229591250419617,
+      "step": 45
+    },
+    {
+      "epoch": 0.1341841385597083,
+      "grad_norm": 0.6724833250045776,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.8146833181381226,
+      "step": 46
+    },
+    {
+      "epoch": 0.13710118505013674,
+      "grad_norm": 0.857208251953125,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8154427409172058,
+      "step": 47
+    },
+    {
+      "epoch": 0.14001823154056517,
+      "grad_norm": 0.5559669137001038,
+      "learning_rate": 1.3623188405797103e-05,
+      "loss": 0.879005491733551,
+      "step": 48
+    },
+    {
+      "epoch": 0.14293527803099362,
+      "grad_norm": 0.5910897850990295,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.8148283362388611,
+      "step": 49
+    },
+    {
+      "epoch": 0.14585232452142205,
+      "grad_norm": 0.6478891372680664,
+      "learning_rate": 1.420289855072464e-05,
+      "loss": 0.8293006420135498,
+      "step": 50
+    },
+    {
+      "epoch": 0.14585232452142205,
+      "eval_loss": 0.7892261147499084,
+      "eval_runtime": 973.2157,
+      "eval_samples_per_second": 0.649,
+      "eval_steps_per_second": 0.649,
+      "step": 50
+    },
+    {
+      "epoch": 0.1487693710118505,
+      "grad_norm": 0.757882833480835,
+      "learning_rate": 1.4492753623188407e-05,
+      "loss": 0.8114852905273438,
+      "step": 51
+    },
+    {
+      "epoch": 0.15168641750227893,
+      "grad_norm": 0.8496116995811462,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.7886185050010681,
+      "step": 52
+    },
+    {
+      "epoch": 0.15460346399270739,
+      "grad_norm": 0.6078857183456421,
+      "learning_rate": 1.5072463768115944e-05,
+      "loss": 0.7298170924186707,
+      "step": 53
+    },
+    {
+      "epoch": 0.1575205104831358,
+      "grad_norm": 0.5856835246086121,
+      "learning_rate": 1.536231884057971e-05,
+      "loss": 0.7407160997390747,
+      "step": 54
+    },
+    {
+      "epoch": 0.16043755697356427,
+      "grad_norm": 1.0533701181411743,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.7057831287384033,
+      "step": 55
+    },
+    {
+      "epoch": 0.16335460346399272,
+      "grad_norm": 0.8087610006332397,
+      "learning_rate": 1.5942028985507246e-05,
+      "loss": 0.7409019470214844,
+      "step": 56
+    },
+    {
+      "epoch": 0.16627164995442115,
+      "grad_norm": 0.629945695400238,
+      "learning_rate": 1.6231884057971015e-05,
+      "loss": 0.7768293023109436,
+      "step": 57
+    },
+    {
+      "epoch": 0.1691886964448496,
+      "grad_norm": 0.5187911987304688,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.825718104839325,
+      "step": 58
+    },
+    {
+      "epoch": 0.17210574293527803,
+      "grad_norm": 0.5866358280181885,
+      "learning_rate": 1.681159420289855e-05,
+      "loss": 0.8575979471206665,
+      "step": 59
+    },
+    {
+      "epoch": 0.17502278942570648,
+      "grad_norm": 1.5098934173583984,
+      "learning_rate": 1.710144927536232e-05,
+      "loss": 0.8058848977088928,
+      "step": 60
+    },
+    {
+      "epoch": 0.1779398359161349,
+      "grad_norm": 0.6981958150863647,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.7640778422355652,
+      "step": 61
+    },
+    {
+      "epoch": 0.18085688240656336,
+      "grad_norm": 0.631349503993988,
+      "learning_rate": 1.7681159420289858e-05,
+      "loss": 0.7896331548690796,
+      "step": 62
+    },
+    {
+      "epoch": 0.1837739288969918,
+      "grad_norm": 0.6930747032165527,
+      "learning_rate": 1.7971014492753624e-05,
+      "loss": 0.6762524247169495,
+      "step": 63
+    },
+    {
+      "epoch": 0.18669097538742024,
+      "grad_norm": 0.599399209022522,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.7285035848617554,
+      "step": 64
+    },
+    {
+      "epoch": 0.18960802187784867,
+      "grad_norm": 0.6194344758987427,
+      "learning_rate": 1.8550724637681162e-05,
+      "loss": 0.7682523131370544,
+      "step": 65
+    },
+    {
+      "epoch": 0.19252506836827712,
+      "grad_norm": 0.5691342949867249,
+      "learning_rate": 1.8840579710144928e-05,
+      "loss": 0.6791993379592896,
+      "step": 66
+    },
+    {
+      "epoch": 0.19544211485870555,
+      "grad_norm": 0.6257390379905701,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.6744828224182129,
+      "step": 67
+    },
+    {
+      "epoch": 0.198359161349134,
+      "grad_norm": 0.5871018767356873,
+      "learning_rate": 1.9420289855072467e-05,
+      "loss": 0.7317330837249756,
+      "step": 68
+    },
+    {
+      "epoch": 0.20127620783956243,
+      "grad_norm": 1.0744612216949463,
+      "learning_rate": 1.9710144927536236e-05,
+      "loss": 0.6617178916931152,
+      "step": 69
+    },
+    {
+      "epoch": 0.2041932543299909,
+      "grad_norm": 0.675946831703186,
+      "learning_rate": 2e-05,
+      "loss": 0.7615712881088257,
+      "step": 70
+    },
+    {
+      "epoch": 0.2071103008204193,
+      "grad_norm": 0.7663411498069763,
+      "learning_rate": 1.9999870372100614e-05,
+      "loss": 0.7131291627883911,
+      "step": 71
+    },
+    {
+      "epoch": 0.21002734731084777,
+      "grad_norm": 0.6725395321846008,
+      "learning_rate": 1.9999481491763123e-05,
+      "loss": 0.7452989816665649,
+      "step": 72
+    },
+    {
+      "epoch": 0.21294439380127622,
+      "grad_norm": 0.6505664587020874,
+      "learning_rate": 1.9998833369069483e-05,
+      "loss": 0.7477136850357056,
+      "step": 73
+    },
+    {
+      "epoch": 0.21586144029170465,
+      "grad_norm": 0.7032860517501831,
+      "learning_rate": 1.9997926020822643e-05,
+      "loss": 0.6854275465011597,
+      "step": 74
+    },
+    {
+      "epoch": 0.2187784867821331,
+      "grad_norm": 0.645345151424408,
+      "learning_rate": 1.999675947054614e-05,
+      "loss": 0.7552425265312195,
+      "step": 75
+    },
+    {
+      "epoch": 0.22169553327256153,
+      "grad_norm": 0.6620492935180664,
+      "learning_rate": 1.9995333748483464e-05,
+      "loss": 0.7262853384017944,
+      "step": 76
+    },
+    {
+      "epoch": 0.22461257976298998,
+      "grad_norm": 0.6511455774307251,
+      "learning_rate": 1.9993648891597284e-05,
+      "loss": 0.7591732144355774,
+      "step": 77
+    },
+    {
+      "epoch": 0.2275296262534184,
+      "grad_norm": 0.6775254011154175,
+      "learning_rate": 1.9991704943568497e-05,
+      "loss": 0.7498704195022583,
+      "step": 78
+    },
+    {
+      "epoch": 0.23044667274384686,
+      "grad_norm": 0.8199896216392517,
+      "learning_rate": 1.9989501954795076e-05,
+      "loss": 0.7238684296607971,
+      "step": 79
+    },
+    {
+      "epoch": 0.2333637192342753,
+      "grad_norm": 0.8197569847106934,
+      "learning_rate": 1.998703998239079e-05,
+      "loss": 0.7028778195381165,
+      "step": 80
+    },
+    {
+      "epoch": 0.23628076572470375,
+      "grad_norm": 0.6602625250816345,
+      "learning_rate": 1.9984319090183692e-05,
+      "loss": 0.8842703104019165,
+      "step": 81
+    },
+    {
+      "epoch": 0.23919781221513217,
+      "grad_norm": 0.9587129354476929,
+      "learning_rate": 1.99813393487145e-05,
+      "loss": 0.732614278793335,
+      "step": 82
+    },
+    {
+      "epoch": 0.24211485870556063,
+      "grad_norm": 0.6822189092636108,
+      "learning_rate": 1.997810083523473e-05,
+      "loss": 0.7544928193092346,
+      "step": 83
+    },
+    {
+      "epoch": 0.24503190519598905,
+      "grad_norm": 0.8980082869529724,
+      "learning_rate": 1.9974603633704726e-05,
+      "loss": 0.6704054474830627,
+      "step": 84
+    },
+    {
+      "epoch": 0.2479489516864175,
+      "grad_norm": 0.7413425445556641,
+      "learning_rate": 1.9970847834791472e-05,
+      "loss": 0.693661093711853,
+      "step": 85
+    },
+    {
+      "epoch": 0.25086599817684596,
+      "grad_norm": 0.8314999341964722,
+      "learning_rate": 1.9966833535866223e-05,
+      "loss": 0.667654275894165,
+      "step": 86
+    },
+    {
+      "epoch": 0.25378304466727436,
+      "grad_norm": 0.7972444891929626,
+      "learning_rate": 1.9962560841002013e-05,
+      "loss": 0.8403134942054749,
+      "step": 87
+    },
+    {
+      "epoch": 0.2567000911577028,
+      "grad_norm": 0.8519951701164246,
+      "learning_rate": 1.995802986097093e-05,
+      "loss": 0.6897370219230652,
+      "step": 88
+    },
+    {
+      "epoch": 0.25961713764813127,
+      "grad_norm": 0.8268933892250061,
+      "learning_rate": 1.995324071324126e-05,
+      "loss": 0.6690632700920105,
+      "step": 89
+    },
+    {
+      "epoch": 0.2625341841385597,
+      "grad_norm": 0.7133983969688416,
+      "learning_rate": 1.9948193521974436e-05,
+      "loss": 0.6314147114753723,
+      "step": 90
+    },
+    {
+      "epoch": 0.2654512306289881,
+      "grad_norm": 0.889302134513855,
+      "learning_rate": 1.9942888418021814e-05,
+      "loss": 0.7389825582504272,
+      "step": 91
+    },
+    {
+      "epoch": 0.2683682771194166,
+      "grad_norm": 0.7022432088851929,
+      "learning_rate": 1.99373255389213e-05,
+      "loss": 0.6916261911392212,
+      "step": 92
+    },
+    {
+      "epoch": 0.27128532360984503,
+      "grad_norm": 0.696432888507843,
+      "learning_rate": 1.9931505028893748e-05,
+      "loss": 0.6908476948738098,
+      "step": 93
+    },
+    {
+      "epoch": 0.2742023701002735,
+      "grad_norm": 0.7667419910430908,
+      "learning_rate": 1.9925427038839267e-05,
+      "loss": 0.6500837206840515,
+      "step": 94
+    },
+    {
+      "epoch": 0.27711941659070194,
+      "grad_norm": 0.6974894404411316,
+      "learning_rate": 1.9919091726333265e-05,
+      "loss": 0.7059191465377808,
+      "step": 95
+    },
+    {
+      "epoch": 0.28003646308113034,
+      "grad_norm": 0.7047077417373657,
+      "learning_rate": 1.9912499255622397e-05,
+      "loss": 0.6287837624549866,
+      "step": 96
+    },
+    {
+      "epoch": 0.2829535095715588,
+      "grad_norm": 0.7729557156562805,
+      "learning_rate": 1.990564979762029e-05,
+      "loss": 0.6738612055778503,
+      "step": 97
+    },
+    {
+      "epoch": 0.28587055606198725,
+      "grad_norm": 0.7020529508590698,
+      "learning_rate": 1.989854352990311e-05,
+      "loss": 0.662042498588562,
+      "step": 98
+    },
+    {
+      "epoch": 0.2887876025524157,
+      "grad_norm": 0.7369800209999084,
+      "learning_rate": 1.9891180636704975e-05,
+      "loss": 0.6246830821037292,
+      "step": 99
+    },
+    {
+      "epoch": 0.2917046490428441,
+      "grad_norm": 0.7412623167037964,
+      "learning_rate": 1.9883561308913154e-05,
+      "loss": 0.6623879075050354,
+      "step": 100
+    },
+    {
+      "epoch": 0.2917046490428441,
+      "eval_loss": 0.6552971005439758,
+      "eval_runtime": 966.7072,
+      "eval_samples_per_second": 0.654,
+      "eval_steps_per_second": 0.654,
+      "step": 100
+    },
+    {
+      "epoch": 0.29462169553327255,
+      "grad_norm": 0.8428792953491211,
+      "learning_rate": 1.987568574406314e-05,
+      "loss": 0.6312171816825867,
+      "step": 101
+    },
+    {
+      "epoch": 0.297538742023701,
+      "grad_norm": 0.6948133707046509,
+      "learning_rate": 1.9867554146333517e-05,
+      "loss": 0.6266146898269653,
+      "step": 102
+    },
+    {
+      "epoch": 0.30045578851412946,
+      "grad_norm": 1.3897597789764404,
+      "learning_rate": 1.985916672654068e-05,
+      "loss": 0.6669265031814575,
+      "step": 103
+    },
+    {
+      "epoch": 0.30337283500455786,
+      "grad_norm": 0.8838400840759277,
+      "learning_rate": 1.985052370213334e-05,
+      "loss": 0.6601086854934692,
+      "step": 104
+    },
+    {
+      "epoch": 0.3062898814949863,
+      "grad_norm": 0.8471395373344421,
+      "learning_rate": 1.9841625297186925e-05,
+      "loss": 0.5984431505203247,
+      "step": 105
+    },
+    {
+      "epoch": 0.30920692798541477,
+      "grad_norm": 0.8940042853355408,
+      "learning_rate": 1.983247174239774e-05,
+      "loss": 0.7223822474479675,
+      "step": 106
+    },
+    {
+      "epoch": 0.3121239744758432,
+      "grad_norm": 0.7833696603775024,
+      "learning_rate": 1.9823063275076998e-05,
+      "loss": 0.6868705749511719,
+      "step": 107
+    },
+    {
+      "epoch": 0.3150410209662716,
+      "grad_norm": 0.8794649243354797,
+      "learning_rate": 1.9813400139144673e-05,
+      "loss": 0.6246675848960876,
+      "step": 108
+    },
+    {
+      "epoch": 0.3179580674567001,
+      "grad_norm": 0.8126057982444763,
+      "learning_rate": 1.9803482585123165e-05,
+      "loss": 0.5908697247505188,
+      "step": 109
+    },
+    {
+      "epoch": 0.32087511394712853,
+      "grad_norm": 0.7947676777839661,
+      "learning_rate": 1.979331087013082e-05,
+      "loss": 0.5751246809959412,
+      "step": 110
+    },
+    {
+      "epoch": 0.323792160437557,
+      "grad_norm": 0.713545560836792,
+      "learning_rate": 1.978288525787524e-05,
+      "loss": 0.6081106066703796,
+      "step": 111
+    },
+    {
+      "epoch": 0.32670920692798544,
+      "grad_norm": 1.011828064918518,
+      "learning_rate": 1.977220601864647e-05,
+      "loss": 0.7039169669151306,
+      "step": 112
+    },
+    {
+      "epoch": 0.32962625341841384,
+      "grad_norm": 0.730570912361145,
+      "learning_rate": 1.9761273429309982e-05,
+      "loss": 0.6140255928039551,
+      "step": 113
+    },
+    {
+      "epoch": 0.3325432999088423,
+      "grad_norm": 1.059688687324524,
+      "learning_rate": 1.9750087773299492e-05,
+      "loss": 0.648114025592804,
+      "step": 114
+    },
+    {
+      "epoch": 0.33546034639927075,
+      "grad_norm": 0.9336895942687988,
+      "learning_rate": 1.973864934060962e-05,
+      "loss": 0.622555673122406,
+      "step": 115
+    },
+    {
+      "epoch": 0.3383773928896992,
+      "grad_norm": 0.7195945978164673,
+      "learning_rate": 1.9726958427788367e-05,
+      "loss": 0.70485520362854,
+      "step": 116
+    },
+    {
+      "epoch": 0.3412944393801276,
+      "grad_norm": 0.8101872801780701,
+      "learning_rate": 1.971501533792942e-05,
+      "loss": 0.6958848834037781,
+      "step": 117
+    },
+    {
+      "epoch": 0.34421148587055606,
+      "grad_norm": 1.6075212955474854,
+      "learning_rate": 1.970282038066432e-05,
+      "loss": 0.6021550893783569,
+      "step": 118
+    },
+    {
+      "epoch": 0.3471285323609845,
+      "grad_norm": 0.7881433963775635,
+      "learning_rate": 1.9690373872154396e-05,
+      "loss": 0.6449777483940125,
+      "step": 119
+    },
+    {
+      "epoch": 0.35004557885141296,
+      "grad_norm": 1.014639973640442,
+      "learning_rate": 1.9677676135082606e-05,
+      "loss": 0.5939379930496216,
+      "step": 120
+    },
+    {
+      "epoch": 0.35296262534184136,
+      "grad_norm": 0.8198449611663818,
+      "learning_rate": 1.9664727498645144e-05,
+      "loss": 0.6210286617279053,
+      "step": 121
+    },
+    {
+      "epoch": 0.3558796718322698,
+      "grad_norm": 1.0194576978683472,
+      "learning_rate": 1.9651528298542918e-05,
+      "loss": 0.624247670173645,
+      "step": 122
+    },
+    {
+      "epoch": 0.35879671832269827,
+      "grad_norm": 0.7963470220565796,
+      "learning_rate": 1.9638078876972842e-05,
+      "loss": 0.6479315757751465,
+      "step": 123
+    },
+    {
+      "epoch": 0.3617137648131267,
+      "grad_norm": 0.9007541537284851,
+      "learning_rate": 1.9624379582618976e-05,
+      "loss": 0.6131505370140076,
+      "step": 124
+    },
+    {
+      "epoch": 0.3646308113035551,
+      "grad_norm": 0.8712120056152344,
+      "learning_rate": 1.9610430770643464e-05,
+      "loss": 0.6249448657035828,
+      "step": 125
+    },
+    {
+      "epoch": 0.3675478577939836,
+      "grad_norm": 1.1482540369033813,
+      "learning_rate": 1.9596232802677347e-05,
+      "loss": 0.5844688415527344,
+      "step": 126
+    },
+    {
+      "epoch": 0.37046490428441203,
+      "grad_norm": 0.8662379384040833,
+      "learning_rate": 1.9581786046811175e-05,
+      "loss": 0.6573485732078552,
+      "step": 127
+    },
+    {
+      "epoch": 0.3733819507748405,
+      "grad_norm": 0.8191388845443726,
+      "learning_rate": 1.9567090877585477e-05,
+      "loss": 0.5896862745285034,
+      "step": 128
+    },
+    {
+      "epoch": 0.37629899726526894,
+      "grad_norm": 1.0187078714370728,
+      "learning_rate": 1.955214767598103e-05,
+      "loss": 0.613490879535675,
+      "step": 129
+    },
+    {
+      "epoch": 0.37921604375569734,
+      "grad_norm": 0.8444119691848755,
+      "learning_rate": 1.953695682940901e-05,
+      "loss": 0.727687656879425,
+      "step": 130
+    },
+    {
+      "epoch": 0.3821330902461258,
+      "grad_norm": 0.74753737449646,
+      "learning_rate": 1.9521518731700913e-05,
+      "loss": 0.6102436780929565,
+      "step": 131
+    },
+    {
+      "epoch": 0.38505013673655425,
+      "grad_norm": 1.0166202783584595,
+      "learning_rate": 1.9505833783098378e-05,
+      "loss": 0.6244844198226929,
+      "step": 132
+    },
+    {
+      "epoch": 0.3879671832269827,
+      "grad_norm": 0.8175772428512573,
+      "learning_rate": 1.9489902390242793e-05,
+      "loss": 0.5939282178878784,
+      "step": 133
+    },
+    {
+      "epoch": 0.3908842297174111,
+      "grad_norm": 1.0177713632583618,
+      "learning_rate": 1.947372496616476e-05,
+      "loss": 0.6418229937553406,
+      "step": 134
+    },
+    {
+      "epoch": 0.39380127620783956,
+      "grad_norm": 0.8652453422546387,
+      "learning_rate": 1.9457301930273376e-05,
+      "loss": 0.5870395302772522,
+      "step": 135
+    },
+    {
+      "epoch": 0.396718322698268,
+      "grad_norm": 0.8378894925117493,
+      "learning_rate": 1.9440633708345365e-05,
+      "loss": 0.6480278372764587,
+      "step": 136
+    },
+    {
+      "epoch": 0.39963536918869647,
+      "grad_norm": 0.8303541541099548,
+      "learning_rate": 1.9423720732514052e-05,
+      "loss": 0.6191359758377075,
+      "step": 137
+    },
+    {
+      "epoch": 0.40255241567912486,
+      "grad_norm": 0.8576734662055969,
+      "learning_rate": 1.9406563441258145e-05,
+      "loss": 0.5696198344230652,
+      "step": 138
+    },
+    {
+      "epoch": 0.4054694621695533,
+      "grad_norm": 0.9558727145195007,
+      "learning_rate": 1.9389162279390362e-05,
+      "loss": 0.6177623271942139,
+      "step": 139
+    },
+    {
+      "epoch": 0.4083865086599818,
+      "grad_norm": 0.7046042084693909,
+      "learning_rate": 1.9371517698045922e-05,
+      "loss": 0.5836521983146667,
+      "step": 140
+    },
+    {
+      "epoch": 0.4113035551504102,
+      "grad_norm": 1.0522717237472534,
+      "learning_rate": 1.935363015467082e-05,
+      "loss": 0.5728275775909424,
+      "step": 141
+    },
+    {
+      "epoch": 0.4142206016408386,
+      "grad_norm": 0.9554787874221802,
+      "learning_rate": 1.933550011301e-05,
+      "loss": 0.632586658000946,
+      "step": 142
+    },
+    {
+      "epoch": 0.4171376481312671,
+      "grad_norm": 0.8874214291572571,
+      "learning_rate": 1.9317128043095293e-05,
+      "loss": 0.5850118398666382,
+      "step": 143
+    },
+    {
+      "epoch": 0.42005469462169553,
+      "grad_norm": 1.0708963871002197,
+      "learning_rate": 1.9298514421233276e-05,
+      "loss": 0.6260685324668884,
+      "step": 144
+    },
+    {
+      "epoch": 0.422971741112124,
+      "grad_norm": 0.8135736584663391,
+      "learning_rate": 1.9279659729992888e-05,
+      "loss": 0.6031094193458557,
+      "step": 145
+    },
+    {
+      "epoch": 0.42588878760255244,
+      "grad_norm": 0.7971774339675903,
+      "learning_rate": 1.9260564458192926e-05,
+      "loss": 0.6101322770118713,
+      "step": 146
+    },
+    {
+      "epoch": 0.42880583409298084,
+      "grad_norm": 0.9374974966049194,
+      "learning_rate": 1.9241229100889397e-05,
+      "loss": 0.5836313366889954,
+      "step": 147
+    },
+    {
+      "epoch": 0.4317228805834093,
+      "grad_norm": 0.8043425679206848,
+      "learning_rate": 1.9221654159362636e-05,
+      "loss": 0.6181215047836304,
+      "step": 148
+    },
+    {
+      "epoch": 0.43463992707383775,
+      "grad_norm": 0.8923380374908447,
+      "learning_rate": 1.920184014110436e-05,
+      "loss": 0.6149677634239197,
+      "step": 149
+    },
+    {
+      "epoch": 0.4375569735642662,
+      "grad_norm": 0.8908132314682007,
+      "learning_rate": 1.918178755980449e-05,
+      "loss": 0.5899742841720581,
+      "step": 150
+    },
+    {
+      "epoch": 0.4375569735642662,
+      "eval_loss": 0.5903874635696411,
+      "eval_runtime": 1186.9542,
+      "eval_samples_per_second": 0.532,
+      "eval_steps_per_second": 0.532,
+      "step": 150
+    },
+    {
+      "epoch": 0.4404740200546946,
+      "grad_norm": 1.060531497001648,
+      "learning_rate": 1.9161496935337808e-05,
+      "loss": 0.5852696895599365,
+      "step": 151
+    },
+    {
+      "epoch": 0.44339106654512306,
+      "grad_norm": 0.9723032712936401,
+      "learning_rate": 1.914096879375053e-05,
+      "loss": 0.5822056531906128,
+      "step": 152
+    },
+    {
+      "epoch": 0.4463081130355515,
+      "grad_norm": 0.9519931674003601,
+      "learning_rate": 1.912020366724663e-05,
+      "loss": 0.6183493137359619,
+      "step": 153
+    },
+    {
+      "epoch": 0.44922515952597997,
+      "grad_norm": 0.8282918334007263,
+      "learning_rate": 1.9099202094174055e-05,
+      "loss": 0.6229860782623291,
+      "step": 154
+    },
+    {
+      "epoch": 0.45214220601640837,
+      "grad_norm": 0.9251292943954468,
+      "learning_rate": 1.907796461901076e-05,
+      "loss": 0.6552959680557251,
+      "step": 155
+    },
+    {
+      "epoch": 0.4550592525068368,
+      "grad_norm": 1.0349540710449219,
+      "learning_rate": 1.9056491792350606e-05,
+      "loss": 0.6170098781585693,
+      "step": 156
+    },
+    {
+      "epoch": 0.4579762989972653,
+      "grad_norm": 0.8720711469650269,
+      "learning_rate": 1.9034784170889076e-05,
+      "loss": 0.5870137810707092,
+      "step": 157
+    },
+    {
+      "epoch": 0.46089334548769373,
+      "grad_norm": 1.0785977840423584,
+      "learning_rate": 1.9012842317408843e-05,
+      "loss": 0.5515124201774597,
+      "step": 158
+    },
+    {
+      "epoch": 0.4638103919781221,
+      "grad_norm": 1.0634154081344604,
+      "learning_rate": 1.8990666800765187e-05,
+      "loss": 0.6073828339576721,
+      "step": 159
+    },
+    {
+      "epoch": 0.4667274384685506,
+      "grad_norm": 0.8770879507064819,
+      "learning_rate": 1.896825819587123e-05,
+      "loss": 0.5960907936096191,
+      "step": 160
+    },
+    {
+      "epoch": 0.46964448495897904,
+      "grad_norm": 1.1225898265838623,
+      "learning_rate": 1.894561708368305e-05,
+      "loss": 0.545990526676178,
+      "step": 161
+    },
+    {
+      "epoch": 0.4725615314494075,
+      "grad_norm": 0.9373893141746521,
+      "learning_rate": 1.8922744051184613e-05,
+      "loss": 0.5566108822822571,
+      "step": 162
+    },
+    {
+      "epoch": 0.4754785779398359,
+      "grad_norm": 1.5016087293624878,
+      "learning_rate": 1.8899639691372545e-05,
+      "loss": 0.558845043182373,
+      "step": 163
+    },
+    {
+      "epoch": 0.47839562443026434,
+      "grad_norm": 0.903020977973938,
+      "learning_rate": 1.8876304603240773e-05,
+      "loss": 0.6824233531951904,
+      "step": 164
+    },
+    {
+      "epoch": 0.4813126709206928,
+      "grad_norm": 0.8239623308181763,
+      "learning_rate": 1.8852739391764993e-05,
+      "loss": 0.5630610585212708,
+      "step": 165
+    },
+    {
+      "epoch": 0.48422971741112125,
+      "grad_norm": 0.926069438457489,
+      "learning_rate": 1.882894466788697e-05,
+      "loss": 0.6211802363395691,
+      "step": 166
+    },
+    {
+      "epoch": 0.4871467639015497,
+      "grad_norm": 1.0098828077316284,
+      "learning_rate": 1.8804921048498722e-05,
+      "loss": 0.5513257384300232,
+      "step": 167
+    },
+    {
+      "epoch": 0.4900638103919781,
+      "grad_norm": 0.9228141903877258,
+      "learning_rate": 1.8780669156426517e-05,
+      "loss": 0.6197121739387512,
+      "step": 168
+    },
+    {
+      "epoch": 0.49298085688240656,
+      "grad_norm": 1.0551754236221313,
+      "learning_rate": 1.8756189620414712e-05,
+      "loss": 0.5221806764602661,
+      "step": 169
+    },
+    {
+      "epoch": 0.495897903372835,
+      "grad_norm": 0.9017496109008789,
+      "learning_rate": 1.873148307510948e-05,
+      "loss": 0.5766995549201965,
+      "step": 170
+    },
+    {
+      "epoch": 0.49881494986326347,
+      "grad_norm": 0.9704970717430115,
+      "learning_rate": 1.870655016104233e-05,
+      "loss": 0.6514763832092285,
+      "step": 171
+    },
+    {
+      "epoch": 0.5017319963536919,
+      "grad_norm": 0.9972712397575378,
+      "learning_rate": 1.8681391524613518e-05,
+      "loss": 0.5273895263671875,
+      "step": 172
+    },
+    {
+      "epoch": 0.5046490428441204,
+      "grad_norm": 0.9473339319229126,
+      "learning_rate": 1.8656007818075288e-05,
+      "loss": 0.5548599362373352,
+      "step": 173
+    },
+    {
+      "epoch": 0.5075660893345487,
+      "grad_norm": 1.2493574619293213,
+      "learning_rate": 1.8630399699514944e-05,
+      "loss": 0.5593586564064026,
+      "step": 174
+    },
+    {
+      "epoch": 0.5104831358249772,
+      "grad_norm": 1.2766696214675903,
+      "learning_rate": 1.860456783283781e-05,
+      "loss": 0.6054630279541016,
+      "step": 175
+    },
+    {
+      "epoch": 0.5134001823154056,
+      "grad_norm": 0.9555240869522095,
+      "learning_rate": 1.857851288775002e-05,
+      "loss": 0.508592963218689,
+      "step": 176
+    },
+    {
+      "epoch": 0.5163172288058341,
+      "grad_norm": 1.260219931602478,
+      "learning_rate": 1.8552235539741118e-05,
+      "loss": 0.5532065629959106,
+      "step": 177
+    },
+    {
+      "epoch": 0.5192342752962625,
+      "grad_norm": 1.1859954595565796,
+      "learning_rate": 1.8525736470066595e-05,
+      "loss": 0.5683344006538391,
+      "step": 178
+    },
+    {
+      "epoch": 0.522151321786691,
+      "grad_norm": 1.3044344186782837,
+      "learning_rate": 1.8499016365730203e-05,
+      "loss": 0.5281959772109985,
+      "step": 179
+    },
+    {
+      "epoch": 0.5250683682771194,
+      "grad_norm": 1.3049921989440918,
+      "learning_rate": 1.8472075919466137e-05,
+      "loss": 0.49621230363845825,
+      "step": 180
+    },
+    {
+      "epoch": 0.5279854147675479,
+      "grad_norm": 1.0488537549972534,
+      "learning_rate": 1.844491582972109e-05,
+      "loss": 0.6194032430648804,
+      "step": 181
+    },
+    {
+      "epoch": 0.5309024612579762,
+      "grad_norm": 1.5553455352783203,
+      "learning_rate": 1.8417536800636138e-05,
+      "loss": 0.5645846724510193,
+      "step": 182
+    },
+    {
+      "epoch": 0.5338195077484047,
+      "grad_norm": 1.2673912048339844,
+      "learning_rate": 1.8389939542028484e-05,
+      "loss": 0.6267315745353699,
+      "step": 183
+    },
+    {
+      "epoch": 0.5367365542388332,
+      "grad_norm": 1.0273847579956055,
+      "learning_rate": 1.8362124769373064e-05,
+      "loss": 0.5256403684616089,
+      "step": 184
+    },
+    {
+      "epoch": 0.5396536007292616,
+      "grad_norm": 1.006093978881836,
+      "learning_rate": 1.8334093203783986e-05,
+      "loss": 0.5916382074356079,
+      "step": 185
+    },
+    {
+      "epoch": 0.5425706472196901,
+      "grad_norm": 1.2740857601165771,
+      "learning_rate": 1.8305845571995843e-05,
+      "loss": 0.581648588180542,
+      "step": 186
+    },
+    {
+      "epoch": 0.5454876937101185,
+      "grad_norm": 1.494248390197754,
+      "learning_rate": 1.8277382606344872e-05,
+      "loss": 0.4824523627758026,
+      "step": 187
+    },
+    {
+      "epoch": 0.548404740200547,
+      "grad_norm": 1.1862496137619019,
+      "learning_rate": 1.824870504474996e-05,
+      "loss": 0.5531858205795288,
+      "step": 188
+    },
+    {
+      "epoch": 0.5513217866909754,
+      "grad_norm": 3.503049373626709,
+      "learning_rate": 1.8219813630693523e-05,
+      "loss": 0.6308296918869019,
+      "step": 189
+    },
+    {
+      "epoch": 0.5542388331814039,
+      "grad_norm": 1.7544710636138916,
+      "learning_rate": 1.819070911320222e-05,
+      "loss": 0.6146273016929626,
+      "step": 190
+    },
+    {
+      "epoch": 0.5571558796718322,
+      "grad_norm": 1.3367774486541748,
+      "learning_rate": 1.8161392246827546e-05,
+      "loss": 0.5848966240882874,
+      "step": 191
+    },
+    {
+      "epoch": 0.5600729261622607,
+      "grad_norm": 1.696418046951294,
+      "learning_rate": 1.8131863791626263e-05,
+      "loss": 0.6621730327606201,
+      "step": 192
+    },
+    {
+      "epoch": 0.5629899726526891,
+      "grad_norm": 1.360052227973938,
+      "learning_rate": 1.8102124513140694e-05,
+      "loss": 0.5972204208374023,
+      "step": 193
+    },
+    {
+      "epoch": 0.5659070191431176,
+      "grad_norm": 1.5376263856887817,
+      "learning_rate": 1.807217518237888e-05,
+      "loss": 0.4938785433769226,
+      "step": 194
+    },
+    {
+      "epoch": 0.568824065633546,
+      "grad_norm": 1.2249681949615479,
+      "learning_rate": 1.8042016575794585e-05,
+      "loss": 0.5366095304489136,
+      "step": 195
+    },
+    {
+      "epoch": 0.5717411121239745,
+      "grad_norm": 1.7868080139160156,
+      "learning_rate": 1.8011649475267178e-05,
+      "loss": 0.5116773843765259,
+      "step": 196
+    },
+    {
+      "epoch": 0.574658158614403,
+      "grad_norm": 2.369993209838867,
+      "learning_rate": 1.7981074668081345e-05,
+      "loss": 0.49072742462158203,
+      "step": 197
+    },
+    {
+      "epoch": 0.5775752051048314,
+      "grad_norm": 1.0168434381484985,
+      "learning_rate": 1.7950292946906695e-05,
+      "loss": 0.5691611170768738,
+      "step": 198
+    },
+    {
+      "epoch": 0.5804922515952597,
+      "grad_norm": 1.2990851402282715,
+      "learning_rate": 1.7919305109777195e-05,
+      "loss": 0.5515039563179016,
+      "step": 199
+    },
+    {
+      "epoch": 0.5834092980856882,
+      "grad_norm": 1.4859853982925415,
+      "learning_rate": 1.7888111960070493e-05,
+      "loss": 0.5017011165618896,
+      "step": 200
+    },
+    {
+      "epoch": 0.5834092980856882,
+      "eval_loss": 0.5414339303970337,
+      "eval_runtime": 1180.7894,
+      "eval_samples_per_second": 0.535,
+      "eval_steps_per_second": 0.535,
+      "step": 200
+    },
+    {
+      "epoch": 0.5863263445761167,
+      "grad_norm": 1.0065829753875732,
+      "learning_rate": 1.7856714306487088e-05,
+      "loss": 0.5677731037139893,
+      "step": 201
+    },
+    {
+      "epoch": 0.5892433910665451,
+      "grad_norm": 1.1727538108825684,
+      "learning_rate": 1.7825112963029352e-05,
+      "loss": 0.4525509476661682,
+      "step": 202
+    },
+    {
+      "epoch": 0.5921604375569736,
+      "grad_norm": 1.3376752138137817,
+      "learning_rate": 1.7793308748980437e-05,
+      "loss": 0.5208959579467773,
+      "step": 203
+    },
+    {
+      "epoch": 0.595077484047402,
+      "grad_norm": 0.9196159839630127,
+      "learning_rate": 1.776130248888304e-05,
+      "loss": 0.6033903360366821,
+      "step": 204
+    },
+    {
+      "epoch": 0.5979945305378305,
+      "grad_norm": 1.0750919580459595,
+      "learning_rate": 1.772909501251801e-05,
+      "loss": 0.5449609160423279,
+      "step": 205
+    },
+    {
+      "epoch": 0.6009115770282589,
+      "grad_norm": 1.2459467649459839,
+      "learning_rate": 1.769668715488285e-05,
+      "loss": 0.5685338377952576,
+      "step": 206
+    },
+    {
+      "epoch": 0.6038286235186874,
+      "grad_norm": 1.1690552234649658,
+      "learning_rate": 1.766407975617006e-05,
+      "loss": 0.5240382552146912,
+      "step": 207
+    },
+    {
+      "epoch": 0.6067456700091157,
+      "grad_norm": 1.0816599130630493,
+      "learning_rate": 1.7631273661745362e-05,
+      "loss": 0.6802893877029419,
+      "step": 208
+    },
+    {
+      "epoch": 0.6096627164995442,
+      "grad_norm": 1.3662947416305542,
+      "learning_rate": 1.7598269722125775e-05,
+      "loss": 0.48193931579589844,
+      "step": 209
+    },
+    {
+      "epoch": 0.6125797629899726,
+      "grad_norm": 0.9364766478538513,
+      "learning_rate": 1.7565068792957576e-05,
+      "loss": 0.5675849914550781,
+      "step": 210
+    },
+    {
+      "epoch": 0.6154968094804011,
+      "grad_norm": 1.123828411102295,
+      "learning_rate": 1.75316717349941e-05,
+      "loss": 0.5474762916564941,
+      "step": 211
+    },
+    {
+      "epoch": 0.6184138559708295,
+      "grad_norm": 1.1924363374710083,
+      "learning_rate": 1.749807941407345e-05,
+      "loss": 0.4918654263019562,
+      "step": 212
+    },
+    {
+      "epoch": 0.621330902461258,
+      "grad_norm": 1.101293921470642,
+      "learning_rate": 1.7464292701096014e-05,
+      "loss": 0.5742691159248352,
+      "step": 213
+    },
+    {
+      "epoch": 0.6242479489516864,
+      "grad_norm": 1.7374963760375977,
+      "learning_rate": 1.7430312472001928e-05,
+      "loss": 0.5828965902328491,
+      "step": 214
+    },
+    {
+      "epoch": 0.6271649954421149,
+      "grad_norm": 1.3195666074752808,
+      "learning_rate": 1.739613960774833e-05,
+      "loss": 0.5265159010887146,
+      "step": 215
+    },
+    {
+      "epoch": 0.6300820419325432,
+      "grad_norm": 1.254686713218689,
+      "learning_rate": 1.7361774994286545e-05,
+      "loss": 0.4929371476173401,
+      "step": 216
+    },
+    {
+      "epoch": 0.6329990884229717,
+      "grad_norm": 1.1476380825042725,
+      "learning_rate": 1.7327219522539102e-05,
+      "loss": 0.5060417652130127,
+      "step": 217
+    },
+    {
+      "epoch": 0.6359161349134002,
+      "grad_norm": 1.0914150476455688,
+      "learning_rate": 1.7292474088376643e-05,
+      "loss": 0.504043698310852,
+      "step": 218
+    },
+    {
+      "epoch": 0.6388331814038286,
+      "grad_norm": 1.1339508295059204,
+      "learning_rate": 1.7257539592594698e-05,
+      "loss": 0.4797310531139374,
+      "step": 219
+    },
+    {
+      "epoch": 0.6417502278942571,
+      "grad_norm": 1.0805399417877197,
+      "learning_rate": 1.722241694089033e-05,
+      "loss": 0.5878555178642273,
+      "step": 220
+    },
+    {
+      "epoch": 0.6446672743846855,
+      "grad_norm": 1.8615056276321411,
+      "learning_rate": 1.718710704383865e-05,
+      "loss": 0.5005823969841003,
+      "step": 221
+    },
+    {
+      "epoch": 0.647584320875114,
+      "grad_norm": 1.1445401906967163,
+      "learning_rate": 1.7151610816869214e-05,
+      "loss": 0.4949319064617157,
+      "step": 222
+    },
+    {
+      "epoch": 0.6505013673655424,
+      "grad_norm": 0.9726515412330627,
+      "learning_rate": 1.711592918024229e-05,
+      "loss": 0.5073204040527344,
+      "step": 223
+    },
+    {
+      "epoch": 0.6534184138559709,
+      "grad_norm": 1.4491140842437744,
+      "learning_rate": 1.7080063059024998e-05,
+      "loss": 0.47885262966156006,
+      "step": 224
+    },
+    {
+      "epoch": 0.6563354603463992,
+      "grad_norm": 1.0070592164993286,
+      "learning_rate": 1.7044013383067327e-05,
+      "loss": 0.5775837898254395,
+      "step": 225
+    },
+    {
+      "epoch": 0.6592525068368277,
+      "grad_norm": 0.966221272945404,
+      "learning_rate": 1.7007781086978037e-05,
+      "loss": 0.5050399899482727,
+      "step": 226
+    },
+    {
+      "epoch": 0.6621695533272561,
+      "grad_norm": 0.9808815121650696,
+      "learning_rate": 1.6971367110100407e-05,
+      "loss": 0.5737045407295227,
+      "step": 227
+    },
+    {
+      "epoch": 0.6650865998176846,
+      "grad_norm": 1.0158127546310425,
+      "learning_rate": 1.6934772396487906e-05,
+      "loss": 0.48077821731567383,
+      "step": 228
+    },
+    {
+      "epoch": 0.668003646308113,
+      "grad_norm": 1.32015860080719,
+      "learning_rate": 1.6897997894879706e-05,
+      "loss": 0.5614925026893616,
+      "step": 229
+    },
+    {
+      "epoch": 0.6709206927985415,
+      "grad_norm": 1.1055903434753418,
+      "learning_rate": 1.686104455867608e-05,
+      "loss": 0.4970760643482208,
+      "step": 230
+    },
+    {
+      "epoch": 0.67383773928897,
+      "grad_norm": 1.0804500579833984,
+      "learning_rate": 1.682391334591371e-05,
+      "loss": 0.5540452003479004,
+      "step": 231
+    },
+    {
+      "epoch": 0.6767547857793984,
+      "grad_norm": 1.1906245946884155,
+      "learning_rate": 1.6786605219240807e-05,
+      "loss": 0.5778501033782959,
+      "step": 232
+    },
+    {
+      "epoch": 0.6796718322698267,
+      "grad_norm": 0.9758645296096802,
+      "learning_rate": 1.6749121145892192e-05,
+      "loss": 0.49073565006256104,
+      "step": 233
+    },
+    {
+      "epoch": 0.6825888787602552,
+      "grad_norm": 1.1678364276885986,
+      "learning_rate": 1.6711462097664207e-05,
+      "loss": 0.4828741252422333,
+      "step": 234
+    },
+    {
+      "epoch": 0.6855059252506837,
+      "grad_norm": 1.148301362991333,
+      "learning_rate": 1.6673629050889507e-05,
+      "loss": 0.5143818855285645,
+      "step": 235
+    },
+    {
+      "epoch": 0.6884229717411121,
+      "grad_norm": 1.005898356437683,
+      "learning_rate": 1.6635622986411776e-05,
+      "loss": 0.5301160216331482,
+      "step": 236
+    },
+    {
+      "epoch": 0.6913400182315406,
+      "grad_norm": 1.2227320671081543,
+      "learning_rate": 1.659744488956027e-05,
+      "loss": 0.4800386130809784,
+      "step": 237
+    },
+    {
+      "epoch": 0.694257064721969,
+      "grad_norm": 0.986456573009491,
+      "learning_rate": 1.6559095750124296e-05,
+      "loss": 0.5098081827163696,
+      "step": 238
+    },
+    {
+      "epoch": 0.6971741112123975,
+      "grad_norm": 1.1474376916885376,
+      "learning_rate": 1.6520576562327518e-05,
+      "loss": 0.5147273540496826,
+      "step": 239
+    },
+    {
+      "epoch": 0.7000911577028259,
+      "grad_norm": 1.10917067527771,
+      "learning_rate": 1.6481888324802223e-05,
+      "loss": 0.5023190379142761,
+      "step": 240
+    },
+    {
+      "epoch": 0.7030082041932544,
+      "grad_norm": 1.2339262962341309,
+      "learning_rate": 1.644303204056341e-05,
+      "loss": 0.5282092690467834,
+      "step": 241
+    },
+    {
+      "epoch": 0.7059252506836827,
+      "grad_norm": 0.997941255569458,
+      "learning_rate": 1.640400871698277e-05,
+      "loss": 0.5635963082313538,
+      "step": 242
+    },
+    {
+      "epoch": 0.7088422971741112,
+      "grad_norm": 1.0345823764801025,
+      "learning_rate": 1.63648193657626e-05,
+      "loss": 0.5577977895736694,
+      "step": 243
+    },
+    {
+      "epoch": 0.7117593436645396,
+      "grad_norm": 1.3468303680419922,
+      "learning_rate": 1.6325465002909554e-05,
+      "loss": 0.4365362524986267,
+      "step": 244
+    },
+    {
+      "epoch": 0.7146763901549681,
+      "grad_norm": 1.2817128896713257,
+      "learning_rate": 1.628594664870831e-05,
+      "loss": 0.46069926023483276,
+      "step": 245
+    },
+    {
+      "epoch": 0.7175934366453965,
+      "grad_norm": 1.043311357498169,
+      "learning_rate": 1.6246265327695117e-05,
+      "loss": 0.5476971864700317,
+      "step": 246
+    },
+    {
+      "epoch": 0.720510483135825,
+      "grad_norm": 1.0297389030456543,
+      "learning_rate": 1.620642206863124e-05,
+      "loss": 0.48051249980926514,
+      "step": 247
+    },
+    {
+      "epoch": 0.7234275296262535,
+      "grad_norm": 1.4869836568832397,
+      "learning_rate": 1.6166417904476257e-05,
+      "loss": 0.5683314800262451,
+      "step": 248
+    },
+    {
+      "epoch": 0.7263445761166819,
+      "grad_norm": 1.0628005266189575,
+      "learning_rate": 1.6126253872361336e-05,
+      "loss": 0.5277887582778931,
+      "step": 249
+    },
+    {
+      "epoch": 0.7292616226071102,
+      "grad_norm": 1.2682170867919922,
+      "learning_rate": 1.608593101356229e-05,
+      "loss": 0.5048879384994507,
+      "step": 250
+    },
+    {
+      "epoch": 0.7292616226071102,
+      "eval_loss": 0.5038471221923828,
+      "eval_runtime": 1175.0375,
+      "eval_samples_per_second": 0.538,
+      "eval_steps_per_second": 0.538,
+      "step": 250
+    },
+    {
+      "epoch": 0.7321786690975387,
+      "grad_norm": 1.7376199960708618,
+      "learning_rate": 1.6045450373472626e-05,
+      "loss": 0.5093721151351929,
+      "step": 251
+    },
+    {
+      "epoch": 0.7350957155879672,
+      "grad_norm": 1.6047718524932861,
+      "learning_rate": 1.6004813001576405e-05,
+      "loss": 0.4796055555343628,
+      "step": 252
+    },
+    {
+      "epoch": 0.7380127620783956,
+      "grad_norm": 1.3582886457443237,
+      "learning_rate": 1.5964019951421058e-05,
+      "loss": 0.4733014702796936,
+      "step": 253
+    },
+    {
+      "epoch": 0.7409298085688241,
+      "grad_norm": 0.9468897581100464,
+      "learning_rate": 1.5923072280590072e-05,
+      "loss": 0.5312032103538513,
+      "step": 254
+    },
+    {
+      "epoch": 0.7438468550592525,
+      "grad_norm": 1.3890198469161987,
+      "learning_rate": 1.5881971050675547e-05,
+      "loss": 0.47576645016670227,
+      "step": 255
+    },
+    {
+      "epoch": 0.746763901549681,
+      "grad_norm": 1.782992959022522,
+      "learning_rate": 1.584071732725071e-05,
+      "loss": 0.5555092096328735,
+      "step": 256
+    },
+    {
+      "epoch": 0.7496809480401094,
+      "grad_norm": 1.1790621280670166,
+      "learning_rate": 1.5799312179842265e-05,
+      "loss": 0.5148727893829346,
+      "step": 257
+    },
+    {
+      "epoch": 0.7525979945305379,
+      "grad_norm": 1.446694254875183,
+      "learning_rate": 1.5757756681902664e-05,
+      "loss": 0.49939870834350586,
+      "step": 258
+    },
+    {
+      "epoch": 0.7555150410209662,
+      "grad_norm": 1.1786166429519653,
+      "learning_rate": 1.571605191078229e-05,
+      "loss": 0.562156081199646,
+      "step": 259
+    },
+    {
+      "epoch": 0.7584320875113947,
+      "grad_norm": 1.16925847530365,
+      "learning_rate": 1.567419894770151e-05,
+      "loss": 0.49580734968185425,
+      "step": 260
+    },
+    {
+      "epoch": 0.7613491340018231,
+      "grad_norm": 1.60944664478302,
+      "learning_rate": 1.5632198877722676e-05,
+      "loss": 0.4821680784225464,
+      "step": 261
+    },
+    {
+      "epoch": 0.7642661804922516,
+      "grad_norm": 1.3957884311676025,
+      "learning_rate": 1.5590052789721946e-05,
+      "loss": 0.4392276406288147,
+      "step": 262
+    },
+    {
+      "epoch": 0.76718322698268,
+      "grad_norm": 1.636195421218872,
+      "learning_rate": 1.5547761776361096e-05,
+      "loss": 0.39603114128112793,
+      "step": 263
+    },
+    {
+      "epoch": 0.7701002734731085,
+      "grad_norm": 1.496766448020935,
+      "learning_rate": 1.550532693405917e-05,
+      "loss": 0.4833749234676361,
+      "step": 264
+    },
+    {
+      "epoch": 0.773017319963537,
+      "grad_norm": 1.3587844371795654,
+      "learning_rate": 1.5462749362964058e-05,
+      "loss": 0.43738317489624023,
+      "step": 265
+    },
+    {
+      "epoch": 0.7759343664539654,
+      "grad_norm": 1.670704960823059,
+      "learning_rate": 1.5420030166923983e-05,
+      "loss": 0.4476737380027771,
+      "step": 266
+    },
+    {
+      "epoch": 0.7788514129443938,
+      "grad_norm": 1.2674932479858398,
+      "learning_rate": 1.537717045345888e-05,
+      "loss": 0.42266708612442017,
+      "step": 267
+    },
+    {
+      "epoch": 0.7817684594348222,
+      "grad_norm": 2.0639536380767822,
+      "learning_rate": 1.5334171333731666e-05,
+      "loss": 0.5245381593704224,
+      "step": 268
+    },
+    {
+      "epoch": 0.7846855059252507,
+      "grad_norm": 1.2091766595840454,
+      "learning_rate": 1.529103392251946e-05,
+      "loss": 0.5166443586349487,
+      "step": 269
+    },
+    {
+      "epoch": 0.7876025524156791,
+      "grad_norm": 1.1021631956100464,
+      "learning_rate": 1.5247759338184653e-05,
+      "loss": 0.5674265027046204,
+      "step": 270
+    },
+    {
+      "epoch": 0.7905195989061076,
+      "grad_norm": 1.3143829107284546,
+      "learning_rate": 1.520434870264595e-05,
+      "loss": 0.40855613350868225,
+      "step": 271
+    },
+    {
+      "epoch": 0.793436645396536,
+      "grad_norm": 1.1784812211990356,
+      "learning_rate": 1.5160803141349244e-05,
+      "loss": 0.4308925271034241,
+      "step": 272
+    },
+    {
+      "epoch": 0.7963536918869645,
+      "grad_norm": 2.1635706424713135,
+      "learning_rate": 1.5117123783238458e-05,
+      "loss": 0.45035502314567566,
+      "step": 273
+    },
+    {
+      "epoch": 0.7992707383773929,
+      "grad_norm": 1.569203495979309,
+      "learning_rate": 1.5073311760726287e-05,
+      "loss": 0.5095728635787964,
+      "step": 274
+    },
+    {
+      "epoch": 0.8021877848678214,
+      "grad_norm": 2.532621383666992,
+      "learning_rate": 1.5029368209664822e-05,
+      "loss": 0.496748685836792,
+      "step": 275
+    },
+    {
+      "epoch": 0.8051048313582497,
+      "grad_norm": 1.6312552690505981,
+      "learning_rate": 1.4985294269316098e-05,
+      "loss": 0.4972914159297943,
+      "step": 276
+    },
+    {
+      "epoch": 0.8080218778486782,
+      "grad_norm": 1.3996756076812744,
+      "learning_rate": 1.4941091082322579e-05,
+      "loss": 0.5589750409126282,
+      "step": 277
+    },
+    {
+      "epoch": 0.8109389243391066,
+      "grad_norm": 1.1288363933563232,
+      "learning_rate": 1.4896759794677526e-05,
+      "loss": 0.5349453687667847,
+      "step": 278
+    },
+    {
+      "epoch": 0.8138559708295351,
+      "grad_norm": 1.6913920640945435,
+      "learning_rate": 1.4852301555695268e-05,
+      "loss": 0.46511000394821167,
+      "step": 279
+    },
+    {
+      "epoch": 0.8167730173199635,
+      "grad_norm": 1.1913212537765503,
+      "learning_rate": 1.4807717517981439e-05,
+      "loss": 0.4715422987937927,
+      "step": 280
+    },
+    {
+      "epoch": 0.819690063810392,
+      "grad_norm": 1.1179691553115845,
+      "learning_rate": 1.476300883740307e-05,
+      "loss": 0.53330397605896,
+      "step": 281
+    },
+    {
+      "epoch": 0.8226071103008205,
+      "grad_norm": 1.7473797798156738,
+      "learning_rate": 1.4718176673058624e-05,
+      "loss": 0.47564437985420227,
+      "step": 282
+    },
+    {
+      "epoch": 0.8255241567912489,
+      "grad_norm": 1.2653177976608276,
+      "learning_rate": 1.4673222187247963e-05,
+      "loss": 0.46364277601242065,
+      "step": 283
+    },
+    {
+      "epoch": 0.8284412032816773,
+      "grad_norm": 1.2567330598831177,
+      "learning_rate": 1.4628146545442202e-05,
+      "loss": 0.4778091013431549,
+      "step": 284
+    },
+    {
+      "epoch": 0.8313582497721057,
+      "grad_norm": 1.5848406553268433,
+      "learning_rate": 1.4582950916253488e-05,
+      "loss": 0.4480203688144684,
+      "step": 285
+    },
+    {
+      "epoch": 0.8342752962625342,
+      "grad_norm": 1.3278183937072754,
+      "learning_rate": 1.453763647140472e-05,
+      "loss": 0.37945032119750977,
+      "step": 286
+    },
+    {
+      "epoch": 0.8371923427529626,
+      "grad_norm": 1.0961651802062988,
+      "learning_rate": 1.4492204385699155e-05,
+      "loss": 0.5306747555732727,
+      "step": 287
+    },
+    {
+      "epoch": 0.8401093892433911,
+      "grad_norm": 1.176276683807373,
+      "learning_rate": 1.4446655836989961e-05,
+      "loss": 0.49950045347213745,
+      "step": 288
+    },
+    {
+      "epoch": 0.8430264357338195,
+      "grad_norm": 1.2228269577026367,
+      "learning_rate": 1.4400992006149674e-05,
+      "loss": 0.494475394487381,
+      "step": 289
+    },
+    {
+      "epoch": 0.845943482224248,
+      "grad_norm": 1.1584209203720093,
+      "learning_rate": 1.4355214077039592e-05,
+      "loss": 0.44170859456062317,
+      "step": 290
+    },
+    {
+      "epoch": 0.8488605287146764,
+      "grad_norm": 1.2041938304901123,
+      "learning_rate": 1.4309323236479071e-05,
+      "loss": 0.4359871745109558,
+      "step": 291
+    },
+    {
+      "epoch": 0.8517775752051049,
+      "grad_norm": 1.279645562171936,
+      "learning_rate": 1.4263320674214762e-05,
+      "loss": 0.45031386613845825,
+      "step": 292
+    },
+    {
+      "epoch": 0.8546946216955332,
+      "grad_norm": 1.3958357572555542,
+      "learning_rate": 1.4217207582889769e-05,
+      "loss": 0.4832204580307007,
+      "step": 293
+    },
+    {
+      "epoch": 0.8576116681859617,
+      "grad_norm": 1.2788586616516113,
+      "learning_rate": 1.4170985158012725e-05,
+      "loss": 0.5154346227645874,
+      "step": 294
+    },
+    {
+      "epoch": 0.8605287146763901,
+      "grad_norm": 1.3634892702102661,
+      "learning_rate": 1.4124654597926795e-05,
+      "loss": 0.46777206659317017,
+      "step": 295
+    },
+    {
+      "epoch": 0.8634457611668186,
+      "grad_norm": 1.2719579935073853,
+      "learning_rate": 1.4078217103778619e-05,
+      "loss": 0.4247053265571594,
+      "step": 296
+    },
+    {
+      "epoch": 0.866362807657247,
+      "grad_norm": 2.890467643737793,
+      "learning_rate": 1.4031673879487161e-05,
+      "loss": 0.38349640369415283,
+      "step": 297
+    },
+    {
+      "epoch": 0.8692798541476755,
+      "grad_norm": 2.4354801177978516,
+      "learning_rate": 1.3985026131712499e-05,
+      "loss": 0.4134889543056488,
+      "step": 298
+    },
+    {
+      "epoch": 0.872196900638104,
+      "grad_norm": 1.0138323307037354,
+      "learning_rate": 1.3938275069824541e-05,
+      "loss": 0.5176680684089661,
+      "step": 299
+    },
+    {
+      "epoch": 0.8751139471285324,
+      "grad_norm": 1.2316186428070068,
+      "learning_rate": 1.389142190587168e-05,
+      "loss": 0.4818477928638458,
+      "step": 300
+    },
+    {
+      "epoch": 0.8751139471285324,
+      "eval_loss": 0.4752846360206604,
+      "eval_runtime": 1189.1666,
+      "eval_samples_per_second": 0.531,
+      "eval_steps_per_second": 0.531,
+      "step": 300
+    },
+    {
+      "epoch": 0.8780309936189608,
+      "grad_norm": 1.515487551689148,
+      "learning_rate": 1.384446785454936e-05,
+      "loss": 0.47766175866127014,
+      "step": 301
+    },
+    {
+      "epoch": 0.8809480401093892,
+      "grad_norm": 1.4357497692108154,
+      "learning_rate": 1.3797414133168591e-05,
+      "loss": 0.49297061562538147,
+      "step": 302
+    },
+    {
+      "epoch": 0.8838650865998177,
+      "grad_norm": 1.2523037195205688,
+      "learning_rate": 1.3750261961624383e-05,
+      "loss": 0.4629015326499939,
+      "step": 303
+    },
+    {
+      "epoch": 0.8867821330902461,
+      "grad_norm": 3.5790023803710938,
+      "learning_rate": 1.3703012562364124e-05,
+      "loss": 0.3773120045661926,
+      "step": 304
+    },
+    {
+      "epoch": 0.8896991795806746,
+      "grad_norm": 1.9305704832077026,
+      "learning_rate": 1.3655667160355892e-05,
+      "loss": 0.496719628572464,
+      "step": 305
+    },
+    {
+      "epoch": 0.892616226071103,
+      "grad_norm": 1.1506154537200928,
+      "learning_rate": 1.3608226983056687e-05,
+      "loss": 0.49487072229385376,
+      "step": 306
+    },
+    {
+      "epoch": 0.8955332725615315,
+      "grad_norm": 1.8046090602874756,
+      "learning_rate": 1.3560693260380614e-05,
+      "loss": 0.4910697937011719,
+      "step": 307
+    },
+    {
+      "epoch": 0.8984503190519599,
+      "grad_norm": 2.0088653564453125,
+      "learning_rate": 1.3513067224667e-05,
+      "loss": 0.508246660232544,
+      "step": 308
+    },
+    {
+      "epoch": 0.9013673655423883,
+      "grad_norm": 1.2966033220291138,
+      "learning_rate": 1.3465350110648437e-05,
+      "loss": 0.5125166177749634,
+      "step": 309
+    },
+    {
+      "epoch": 0.9042844120328167,
+      "grad_norm": 1.9976309537887573,
+      "learning_rate": 1.3417543155418775e-05,
+      "loss": 0.43942537903785706,
+      "step": 310
+    },
+    {
+      "epoch": 0.9072014585232452,
+      "grad_norm": 1.2663682699203491,
+      "learning_rate": 1.336964759840105e-05,
+      "loss": 0.4839101731777191,
+      "step": 311
+    },
+    {
+      "epoch": 0.9101185050136736,
+      "grad_norm": 1.1223328113555908,
+      "learning_rate": 1.3321664681315354e-05,
+      "loss": 0.48008066415786743,
+      "step": 312
+    },
+    {
+      "epoch": 0.9130355515041021,
+      "grad_norm": 1.5786972045898438,
+      "learning_rate": 1.3273595648146634e-05,
+      "loss": 0.47250309586524963,
+      "step": 313
+    },
+    {
+      "epoch": 0.9159525979945305,
+      "grad_norm": 1.2150241136550903,
+      "learning_rate": 1.322544174511245e-05,
+      "loss": 0.5149738788604736,
+      "step": 314
+    },
+    {
+      "epoch": 0.918869644484959,
+      "grad_norm": 1.3676542043685913,
+      "learning_rate": 1.3177204220630662e-05,
+      "loss": 0.4430195093154907,
+      "step": 315
+    },
+    {
+      "epoch": 0.9217866909753875,
+      "grad_norm": 1.0703285932540894,
+      "learning_rate": 1.3128884325287064e-05,
+      "loss": 0.4798983037471771,
+      "step": 316
+    },
+    {
+      "epoch": 0.9247037374658159,
+      "grad_norm": 1.3131535053253174,
+      "learning_rate": 1.308048331180296e-05,
+      "loss": 0.4241073727607727,
+      "step": 317
+    },
+    {
+      "epoch": 0.9276207839562443,
+      "grad_norm": 1.4485348463058472,
+      "learning_rate": 1.3032002435002698e-05,
+      "loss": 0.527199923992157,
+      "step": 318
+    },
+    {
+      "epoch": 0.9305378304466727,
+      "grad_norm": 1.370936393737793,
+      "learning_rate": 1.2983442951781114e-05,
+      "loss": 0.47125962376594543,
+      "step": 319
+    },
+    {
+      "epoch": 0.9334548769371012,
+      "grad_norm": 1.2369643449783325,
+      "learning_rate": 1.2934806121070973e-05,
+      "loss": 0.4814244210720062,
+      "step": 320
+    },
+    {
+      "epoch": 0.9363719234275296,
+      "grad_norm": 1.2632933855056763,
+      "learning_rate": 1.2886093203810314e-05,
+      "loss": 0.4915548264980316,
+      "step": 321
+    },
+    {
+      "epoch": 0.9392889699179581,
+      "grad_norm": 1.054569959640503,
+      "learning_rate": 1.2837305462909764e-05,
+      "loss": 0.5325602293014526,
+      "step": 322
+    },
+    {
+      "epoch": 0.9422060164083865,
+      "grad_norm": 1.15959632396698,
+      "learning_rate": 1.27884441632198e-05,
+      "loss": 0.43607404828071594,
+      "step": 323
+    },
+    {
+      "epoch": 0.945123062898815,
+      "grad_norm": 1.1667979955673218,
+      "learning_rate": 1.2739510571497945e-05,
+      "loss": 0.4631507992744446,
+      "step": 324
+    },
+    {
+      "epoch": 0.9480401093892434,
+      "grad_norm": 1.6009081602096558,
+      "learning_rate": 1.2690505956375944e-05,
+      "loss": 0.4935731887817383,
+      "step": 325
+    },
+    {
+      "epoch": 0.9509571558796718,
+      "grad_norm": 1.1193996667861938,
+      "learning_rate": 1.2641431588326858e-05,
+      "loss": 0.45883435010910034,
+      "step": 326
+    },
+    {
+      "epoch": 0.9538742023701002,
+      "grad_norm": 1.5365067720413208,
+      "learning_rate": 1.2592288739632138e-05,
+      "loss": 0.5206276178359985,
+      "step": 327
+    },
+    {
+      "epoch": 0.9567912488605287,
+      "grad_norm": 1.0714622735977173,
+      "learning_rate": 1.2543078684348632e-05,
+      "loss": 0.5242853760719299,
+      "step": 328
+    },
+    {
+      "epoch": 0.9597082953509571,
+      "grad_norm": 1.3009248971939087,
+      "learning_rate": 1.2493802698275557e-05,
+      "loss": 0.4794357717037201,
+      "step": 329
+    },
+    {
+      "epoch": 0.9626253418413856,
+      "grad_norm": 1.495771050453186,
+      "learning_rate": 1.244446205892143e-05,
+      "loss": 0.5849282145500183,
+      "step": 330
+    },
+    {
+      "epoch": 0.965542388331814,
+      "grad_norm": 1.2046003341674805,
+      "learning_rate": 1.2395058045470935e-05,
+      "loss": 0.47758305072784424,
+      "step": 331
+    },
+    {
+      "epoch": 0.9684594348222425,
+      "grad_norm": 1.1362569332122803,
+      "learning_rate": 1.2345591938751772e-05,
+      "loss": 0.4490663409233093,
+      "step": 332
+    },
+    {
+      "epoch": 0.971376481312671,
+      "grad_norm": 1.2658129930496216,
+      "learning_rate": 1.2296065021201438e-05,
+      "loss": 0.4035309851169586,
+      "step": 333
+    },
+    {
+      "epoch": 0.9742935278030994,
+      "grad_norm": 4.370306015014648,
+      "learning_rate": 1.2246478576833993e-05,
+      "loss": 0.495273619890213,
+      "step": 334
+    },
+    {
+      "epoch": 0.9772105742935278,
+      "grad_norm": 1.3863654136657715,
+      "learning_rate": 1.219683389120676e-05,
+      "loss": 0.46410733461380005,
+      "step": 335
+    },
+    {
+      "epoch": 0.9801276207839562,
+      "grad_norm": 1.4544321298599243,
+      "learning_rate": 1.2147132251387004e-05,
+      "loss": 0.4301709830760956,
+      "step": 336
+    },
+    {
+      "epoch": 0.9830446672743847,
+      "grad_norm": 1.0852457284927368,
+      "learning_rate": 1.2097374945918554e-05,
+      "loss": 0.48892468214035034,
+      "step": 337
+    },
+    {
+      "epoch": 0.9859617137648131,
+      "grad_norm": 1.5062257051467896,
+      "learning_rate": 1.2047563264788412e-05,
+      "loss": 0.4667983055114746,
+      "step": 338
+    },
+    {
+      "epoch": 0.9888787602552416,
+      "grad_norm": 1.2472951412200928,
+      "learning_rate": 1.199769849939329e-05,
+      "loss": 0.4827345013618469,
+      "step": 339
+    },
+    {
+      "epoch": 0.99179580674567,
+      "grad_norm": 1.2589871883392334,
+      "learning_rate": 1.1947781942506151e-05,
+      "loss": 0.405245304107666,
+      "step": 340
+    },
+    {
+      "epoch": 0.9947128532360985,
+      "grad_norm": 1.25636625289917,
+      "learning_rate": 1.1897814888242679e-05,
+      "loss": 0.37956133484840393,
+      "step": 341
+    },
+    {
+      "epoch": 0.9976298997265269,
+      "grad_norm": 2.7064895629882812,
+      "learning_rate": 1.1847798632027726e-05,
+      "loss": 0.489456444978714,
+      "step": 342
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6156240701675415,
+      "learning_rate": 1.1797734470561744e-05,
+      "loss": 0.46473199129104614,
+      "step": 343
+    },
+    {
+      "epoch": 1.0029170464904285,
+      "grad_norm": 1.3046343326568604,
+      "learning_rate": 1.1747623701787143e-05,
+      "loss": 0.3504878282546997,
+      "step": 344
+    },
+    {
+      "epoch": 1.005834092980857,
+      "grad_norm": 1.414828896522522,
+      "learning_rate": 1.1697467624854666e-05,
+      "loss": 0.4719260334968567,
+      "step": 345
+    },
+    {
+      "epoch": 1.0087511394712854,
+      "grad_norm": 1.1873356103897095,
+      "learning_rate": 1.164726754008969e-05,
+      "loss": 0.45313555002212524,
+      "step": 346
+    },
+    {
+      "epoch": 1.0116681859617138,
+      "grad_norm": 1.1382380723953247,
+      "learning_rate": 1.1597024748958526e-05,
+      "loss": 0.4365478456020355,
+      "step": 347
+    },
+    {
+      "epoch": 1.0145852324521423,
+      "grad_norm": 1.8141961097717285,
+      "learning_rate": 1.1546740554034661e-05,
+      "loss": 0.3694503605365753,
+      "step": 348
+    },
+    {
+      "epoch": 1.0175022789425707,
+      "grad_norm": 1.333388328552246,
+      "learning_rate": 1.1496416258965015e-05,
+      "loss": 0.4755721688270569,
+      "step": 349
+    },
+    {
+      "epoch": 1.0204193254329992,
+      "grad_norm": 1.3464443683624268,
+      "learning_rate": 1.1446053168436117e-05,
+      "loss": 0.4227846562862396,
+      "step": 350
+    },
+    {
+      "epoch": 1.0204193254329992,
+      "eval_loss": 0.44924086332321167,
+      "eval_runtime": 1214.6648,
+      "eval_samples_per_second": 0.52,
+      "eval_steps_per_second": 0.52,
+      "step": 350
+    },
+    {
+      "epoch": 1.0233363719234276,
+      "grad_norm": 1.2682689428329468,
+      "learning_rate": 1.1395652588140292e-05,
+      "loss": 0.44300130009651184,
+      "step": 351
+    },
+    {
+      "epoch": 1.0262534184138559,
+      "grad_norm": 1.7737696170806885,
+      "learning_rate": 1.1345215824741814e-05,
+      "loss": 0.5106258988380432,
+      "step": 352
+    },
+    {
+      "epoch": 1.0291704649042843,
+      "grad_norm": 1.2601238489151,
+      "learning_rate": 1.1294744185843014e-05,
+      "loss": 0.45930635929107666,
+      "step": 353
+    },
+    {
+      "epoch": 1.0320875113947128,
+      "grad_norm": 1.2162678241729736,
+      "learning_rate": 1.1244238979950406e-05,
+      "loss": 0.44163084030151367,
+      "step": 354
+    },
+    {
+      "epoch": 1.0350045578851412,
+      "grad_norm": 1.0905817747116089,
+      "learning_rate": 1.1193701516440733e-05,
+      "loss": 0.510662317276001,
+      "step": 355
+    },
+    {
+      "epoch": 1.0379216043755697,
+      "grad_norm": 0.9624952673912048,
+      "learning_rate": 1.1143133105527048e-05,
+      "loss": 0.5297917127609253,
+      "step": 356
+    },
+    {
+      "epoch": 1.0408386508659981,
+      "grad_norm": 1.2757681608200073,
+      "learning_rate": 1.1092535058224725e-05,
+      "loss": 0.4332093596458435,
+      "step": 357
+    },
+    {
+      "epoch": 1.0437556973564266,
+      "grad_norm": 1.6885719299316406,
+      "learning_rate": 1.104190868631748e-05,
+      "loss": 0.4337635040283203,
+      "step": 358
+    },
+    {
+      "epoch": 1.046672743846855,
+      "grad_norm": 1.175484538078308,
+      "learning_rate": 1.099125530232336e-05,
+      "loss": 0.45411020517349243,
+      "step": 359
+    },
+    {
+      "epoch": 1.0495897903372835,
+      "grad_norm": 1.0964939594268799,
+      "learning_rate": 1.0940576219460723e-05,
+      "loss": 0.5333439707756042,
+      "step": 360
+    },
+    {
+      "epoch": 1.052506836827712,
+      "grad_norm": 1.5493136644363403,
+      "learning_rate": 1.0889872751614176e-05,
+      "loss": 0.4400906264781952,
+      "step": 361
+    },
+    {
+      "epoch": 1.0554238833181404,
+      "grad_norm": 1.2491416931152344,
+      "learning_rate": 1.0839146213300526e-05,
+      "loss": 0.31049978733062744,
+      "step": 362
+    },
+    {
+      "epoch": 1.0583409298085689,
+      "grad_norm": 1.7213693857192993,
+      "learning_rate": 1.0788397919634694e-05,
+      "loss": 0.389009028673172,
+      "step": 363
+    },
+    {
+      "epoch": 1.0612579762989973,
+      "grad_norm": 1.5405336618423462,
+      "learning_rate": 1.0737629186295621e-05,
+      "loss": 0.4068562984466553,
+      "step": 364
+    },
+    {
+      "epoch": 1.0641750227894258,
+      "grad_norm": 1.225455641746521,
+      "learning_rate": 1.0686841329492159e-05,
+      "loss": 0.47358617186546326,
+      "step": 365
+    },
+    {
+      "epoch": 1.0670920692798542,
+      "grad_norm": 1.3436250686645508,
+      "learning_rate": 1.0636035665928945e-05,
+      "loss": 0.47050854563713074,
+      "step": 366
+    },
+    {
+      "epoch": 1.0700091157702827,
+      "grad_norm": 1.4952112436294556,
+      "learning_rate": 1.058521351277227e-05,
+      "loss": 0.43496906757354736,
+      "step": 367
+    },
+    {
+      "epoch": 1.072926162260711,
+      "grad_norm": 1.549112319946289,
+      "learning_rate": 1.0534376187615924e-05,
+      "loss": 0.45711052417755127,
+      "step": 368
+    },
+    {
+      "epoch": 1.0758432087511394,
+      "grad_norm": 1.3851526975631714,
+      "learning_rate": 1.048352500844704e-05,
+      "loss": 0.45045915246009827,
+      "step": 369
+    },
+    {
+      "epoch": 1.0787602552415678,
+      "grad_norm": 1.6302049160003662,
+      "learning_rate": 1.0432661293611927e-05,
+      "loss": 0.3736046254634857,
+      "step": 370
+    },
+    {
+      "epoch": 1.0816773017319963,
+      "grad_norm": 1.3365869522094727,
+      "learning_rate": 1.0381786361781885e-05,
+      "loss": 0.42242100834846497,
+      "step": 371
+    },
+    {
+      "epoch": 1.0845943482224247,
+      "grad_norm": 1.4369138479232788,
+      "learning_rate": 1.0330901531919026e-05,
+      "loss": 0.44570961594581604,
+      "step": 372
+    },
+    {
+      "epoch": 1.0875113947128532,
+      "grad_norm": 1.3528283834457397,
+      "learning_rate": 1.0280008123242069e-05,
+      "loss": 0.43440738320350647,
+      "step": 373
+    },
+    {
+      "epoch": 1.0904284412032816,
+      "grad_norm": 1.469660997390747,
+      "learning_rate": 1.0229107455192147e-05,
+      "loss": 0.3960394263267517,
+      "step": 374
+    },
+    {
+      "epoch": 1.09334548769371,
+      "grad_norm": 1.4542185068130493,
+      "learning_rate": 1.0178200847398595e-05,
+      "loss": 0.47834208607673645,
+      "step": 375
+    },
+    {
+      "epoch": 1.0962625341841385,
+      "grad_norm": 1.6470292806625366,
+      "learning_rate": 1.0127289619644737e-05,
+      "loss": 0.42791086435317993,
+      "step": 376
+    },
+    {
+      "epoch": 1.099179580674567,
+      "grad_norm": 1.1934021711349487,
+      "learning_rate": 1.0076375091833681e-05,
+      "loss": 0.4401305019855499,
+      "step": 377
+    },
+    {
+      "epoch": 1.1020966271649955,
+      "grad_norm": 0.9786668419837952,
+      "learning_rate": 1.0025458583954078e-05,
+      "loss": 0.4816555678844452,
+      "step": 378
+    },
+    {
+      "epoch": 1.105013673655424,
+      "grad_norm": 1.1348779201507568,
+      "learning_rate": 9.974541416045924e-06,
+      "loss": 0.41516968607902527,
+      "step": 379
+    },
+    {
+      "epoch": 1.1079307201458524,
+      "grad_norm": 1.0188615322113037,
+      "learning_rate": 9.923624908166322e-06,
+      "loss": 0.48087278008461,
+      "step": 380
+    },
+    {
+      "epoch": 1.1108477666362808,
+      "grad_norm": 1.0821740627288818,
+      "learning_rate": 9.872710380355263e-06,
+      "loss": 0.41974008083343506,
+      "step": 381
+    },
+    {
+      "epoch": 1.1137648131267093,
+      "grad_norm": 1.250951886177063,
+      "learning_rate": 9.82179915260141e-06,
+      "loss": 0.42703643441200256,
+      "step": 382
+    },
+    {
+      "epoch": 1.1166818596171377,
+      "grad_norm": 1.4528254270553589,
+      "learning_rate": 9.770892544807856e-06,
+      "loss": 0.43801453709602356,
+      "step": 383
+    },
+    {
+      "epoch": 1.1195989061075662,
+      "grad_norm": 1.813859462738037,
+      "learning_rate": 9.719991876757934e-06,
+      "loss": 0.4344240725040436,
+      "step": 384
+    },
+    {
+      "epoch": 1.1225159525979946,
+      "grad_norm": 1.6681253910064697,
+      "learning_rate": 9.669098468080976e-06,
+      "loss": 0.4356998801231384,
+      "step": 385
+    },
+    {
+      "epoch": 1.125432999088423,
+      "grad_norm": 1.3447953462600708,
+      "learning_rate": 9.618213638218117e-06,
+      "loss": 0.43189188838005066,
+      "step": 386
+    },
+    {
+      "epoch": 1.1283500455788513,
+      "grad_norm": 1.9577926397323608,
+      "learning_rate": 9.567338706388074e-06,
+      "loss": 0.34984707832336426,
+      "step": 387
+    },
+    {
+      "epoch": 1.1312670920692798,
+      "grad_norm": 1.5225576162338257,
+      "learning_rate": 9.516474991552965e-06,
+      "loss": 0.4243963062763214,
+      "step": 388
+    },
+    {
+      "epoch": 1.1341841385597082,
+      "grad_norm": 1.7416809797286987,
+      "learning_rate": 9.46562381238408e-06,
+      "loss": 0.3414606750011444,
+      "step": 389
+    },
+    {
+      "epoch": 1.1371011850501367,
+      "grad_norm": 1.8358951807022095,
+      "learning_rate": 9.414786487227732e-06,
+      "loss": 0.387447327375412,
+      "step": 390
+    },
+    {
+      "epoch": 1.1400182315405651,
+      "grad_norm": 1.9706153869628906,
+      "learning_rate": 9.363964334071057e-06,
+      "loss": 0.4599088728427887,
+      "step": 391
+    },
+    {
+      "epoch": 1.1429352780309936,
+      "grad_norm": 1.0604286193847656,
+      "learning_rate": 9.313158670507843e-06,
+      "loss": 0.4633581042289734,
+      "step": 392
+    },
+    {
+      "epoch": 1.145852324521422,
+      "grad_norm": 1.4851202964782715,
+      "learning_rate": 9.262370813704379e-06,
+      "loss": 0.3872259557247162,
+      "step": 393
+    },
+    {
+      "epoch": 1.1487693710118505,
+      "grad_norm": 1.7839159965515137,
+      "learning_rate": 9.21160208036531e-06,
+      "loss": 0.5215944647789001,
+      "step": 394
+    },
+    {
+      "epoch": 1.151686417502279,
+      "grad_norm": 1.3054656982421875,
+      "learning_rate": 9.160853786699475e-06,
+      "loss": 0.4030425548553467,
+      "step": 395
+    },
+    {
+      "epoch": 1.1546034639927074,
+      "grad_norm": 3.8467981815338135,
+      "learning_rate": 9.110127248385827e-06,
+      "loss": 0.4032524824142456,
+      "step": 396
+    },
+    {
+      "epoch": 1.1575205104831359,
+      "grad_norm": 1.8513801097869873,
+      "learning_rate": 9.05942378053928e-06,
+      "loss": 0.46577155590057373,
+      "step": 397
+    },
+    {
+      "epoch": 1.1604375569735643,
+      "grad_norm": 1.312689185142517,
+      "learning_rate": 9.008744697676642e-06,
+      "loss": 0.39114487171173096,
+      "step": 398
+    },
+    {
+      "epoch": 1.1633546034639928,
+      "grad_norm": 1.1996328830718994,
+      "learning_rate": 8.958091313682521e-06,
+      "loss": 0.481199711561203,
+      "step": 399
+    },
+    {
+      "epoch": 1.1662716499544212,
+      "grad_norm": 5.172409534454346,
+      "learning_rate": 8.90746494177528e-06,
+      "loss": 0.3803558945655823,
+      "step": 400
+    },
+    {
+      "epoch": 1.1662716499544212,
+      "eval_loss": 0.4318464398384094,
+      "eval_runtime": 1206.0306,
+      "eval_samples_per_second": 0.524,
+      "eval_steps_per_second": 0.524,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 686,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.6837285277665853e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

cpt_devstral_24B/checkpoints/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62526ec2433add7ac031c48b1f6ff360f1ade77275765112cbf7cf361d64ca5
+size 5201

cpt_devstral_24B/checkpoints/checkpoint-500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/Models/Devstral-Small-2-24B-Instruct-2512
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/Models/Devstral-Small-2-24B-Instruct-2512
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

cpt_devstral_24B/checkpoints/checkpoint-500/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/Models/Devstral-Small-2-24B-Instruct-2512",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

cpt_devstral_24B/checkpoints/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d8d694c7fc76d670a2720c03cab875ad7ac3e20bfdbf2d2360ed074f2d69a8
+size 364983848

cpt_devstral_24B/checkpoints/checkpoint-500/chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = '' %}
+
+{#- 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 %}

cpt_devstral_24B/checkpoints/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335aa629db8c0490b49c6dbd8a2212e0cb7b06d115ab83a96e1f18d23652855c
+size 160131559

cpt_devstral_24B/checkpoints/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08185a483370e678d79b51807a988cfe41d318265f91634025d2a0d25c5a3615
+size 14645

cpt_devstral_24B/checkpoints/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee4726958e54cc743c86acde73ad8c729bc35b56d33cb9894bdb5eba634ffd9
+size 1465

cpt_devstral_24B/checkpoints/checkpoint-500/tokenizer.json

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

cpt_devstral_24B/checkpoints/checkpoint-500/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": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

cpt_devstral_24B/checkpoints/checkpoint-500/trainer_state.json

@@ -0,0 +1,3614 @@
+{
+  "best_global_step": 500,
+  "best_metric": 0.40706494450569153,
+  "best_model_checkpoint": "runs/cpt_run_v1/checkpoints/checkpoint-500",
+  "epoch": 1.4579762989972653,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029170464904284413,
+      "grad_norm": 1.1577509641647339,
+      "learning_rate": 0.0,
+      "loss": 0.9893555045127869,
+      "step": 1
+    },
+    {
+      "epoch": 0.005834092980856883,
+      "grad_norm": 0.9491796493530273,
+      "learning_rate": 2.8985507246376816e-07,
+      "loss": 0.8791205883026123,
+      "step": 2
+    },
+    {
+      "epoch": 0.008751139471285323,
+      "grad_norm": 1.1600768566131592,
+      "learning_rate": 5.797101449275363e-07,
+      "loss": 0.9858248233795166,
+      "step": 3
+    },
+    {
+      "epoch": 0.011668185961713765,
+      "grad_norm": 1.2298306226730347,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.0516364574432373,
+      "step": 4
+    },
+    {
+      "epoch": 0.014585232452142206,
+      "grad_norm": 0.9520533680915833,
+      "learning_rate": 1.1594202898550726e-06,
+      "loss": 0.8392249345779419,
+      "step": 5
+    },
+    {
+      "epoch": 0.017502278942570646,
+      "grad_norm": 1.2451188564300537,
+      "learning_rate": 1.4492753623188408e-06,
+      "loss": 1.0955077409744263,
+      "step": 6
+    },
+    {
+      "epoch": 0.02041932543299909,
+      "grad_norm": 1.1123991012573242,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.9201866388320923,
+      "step": 7
+    },
+    {
+      "epoch": 0.02333637192342753,
+      "grad_norm": 0.9283139705657959,
+      "learning_rate": 2.028985507246377e-06,
+      "loss": 0.9770950078964233,
+      "step": 8
+    },
+    {
+      "epoch": 0.02625341841385597,
+      "grad_norm": 0.9589216113090515,
+      "learning_rate": 2.3188405797101453e-06,
+      "loss": 0.9442565441131592,
+      "step": 9
+    },
+    {
+      "epoch": 0.02917046490428441,
+      "grad_norm": 0.8866703510284424,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.9354464411735535,
+      "step": 10
+    },
+    {
+      "epoch": 0.03208751139471285,
+      "grad_norm": 0.7191241383552551,
+      "learning_rate": 2.8985507246376816e-06,
+      "loss": 0.7659736275672913,
+      "step": 11
+    },
+    {
+      "epoch": 0.03500455788514129,
+      "grad_norm": 0.9110142588615417,
+      "learning_rate": 3.188405797101449e-06,
+      "loss": 0.9319326877593994,
+      "step": 12
+    },
+    {
+      "epoch": 0.03792160437556973,
+      "grad_norm": 0.8754057288169861,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.9819356203079224,
+      "step": 13
+    },
+    {
+      "epoch": 0.04083865086599818,
+      "grad_norm": 0.896181046962738,
+      "learning_rate": 3.768115942028986e-06,
+      "loss": 1.026316523551941,
+      "step": 14
+    },
+    {
+      "epoch": 0.04375569735642662,
+      "grad_norm": 0.6104832887649536,
+      "learning_rate": 4.057971014492754e-06,
+      "loss": 0.8427562713623047,
+      "step": 15
+    },
+    {
+      "epoch": 0.04667274384685506,
+      "grad_norm": 0.6529208421707153,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.8496565222740173,
+      "step": 16
+    },
+    {
+      "epoch": 0.0495897903372835,
+      "grad_norm": 0.6319335699081421,
+      "learning_rate": 4.637681159420291e-06,
+      "loss": 0.9139047861099243,
+      "step": 17
+    },
+    {
+      "epoch": 0.05250683682771194,
+      "grad_norm": 0.7458649277687073,
+      "learning_rate": 4.927536231884059e-06,
+      "loss": 0.8867442011833191,
+      "step": 18
+    },
+    {
+      "epoch": 0.05542388331814038,
+      "grad_norm": 0.6179773211479187,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.9579408168792725,
+      "step": 19
+    },
+    {
+      "epoch": 0.05834092980856882,
+      "grad_norm": 0.794481635093689,
+      "learning_rate": 5.507246376811595e-06,
+      "loss": 0.8736554980278015,
+      "step": 20
+    },
+    {
+      "epoch": 0.06125797629899726,
+      "grad_norm": 0.8356145620346069,
+      "learning_rate": 5.797101449275363e-06,
+      "loss": 0.9358762502670288,
+      "step": 21
+    },
+    {
+      "epoch": 0.0641750227894257,
+      "grad_norm": 0.5891932845115662,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.8972038626670837,
+      "step": 22
+    },
+    {
+      "epoch": 0.06709206927985414,
+      "grad_norm": 0.6931268572807312,
+      "learning_rate": 6.376811594202898e-06,
+      "loss": 0.9583507776260376,
+      "step": 23
+    },
+    {
+      "epoch": 0.07000911577028258,
+      "grad_norm": 0.7298229336738586,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8119489550590515,
+      "step": 24
+    },
+    {
+      "epoch": 0.07292616226071102,
+      "grad_norm": 0.6419956684112549,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.9386100769042969,
+      "step": 25
+    },
+    {
+      "epoch": 0.07584320875113947,
+      "grad_norm": 0.7508338689804077,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 0.9272583723068237,
+      "step": 26
+    },
+    {
+      "epoch": 0.0787602552415679,
+      "grad_norm": 0.5848079919815063,
+      "learning_rate": 7.536231884057972e-06,
+      "loss": 0.8967856168746948,
+      "step": 27
+    },
+    {
+      "epoch": 0.08167730173199636,
+      "grad_norm": 0.7384837865829468,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.8696568012237549,
+      "step": 28
+    },
+    {
+      "epoch": 0.0845943482224248,
+      "grad_norm": 0.5069604516029358,
+      "learning_rate": 8.115942028985508e-06,
+      "loss": 0.9121193885803223,
+      "step": 29
+    },
+    {
+      "epoch": 0.08751139471285324,
+      "grad_norm": 0.833165168762207,
+      "learning_rate": 8.405797101449275e-06,
+      "loss": 0.8180589079856873,
+      "step": 30
+    },
+    {
+      "epoch": 0.09042844120328168,
+      "grad_norm": 0.6355920433998108,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.8640957474708557,
+      "step": 31
+    },
+    {
+      "epoch": 0.09334548769371012,
+      "grad_norm": 1.0429315567016602,
+      "learning_rate": 8.985507246376812e-06,
+      "loss": 0.9517915844917297,
+      "step": 32
+    },
+    {
+      "epoch": 0.09626253418413856,
+      "grad_norm": 0.5875154733657837,
+      "learning_rate": 9.275362318840581e-06,
+      "loss": 0.9443603754043579,
+      "step": 33
+    },
+    {
+      "epoch": 0.099179580674567,
+      "grad_norm": 1.9913769960403442,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.9510866403579712,
+      "step": 34
+    },
+    {
+      "epoch": 0.10209662716499544,
+      "grad_norm": 0.5310097932815552,
+      "learning_rate": 9.855072463768118e-06,
+      "loss": 0.8653419613838196,
+      "step": 35
+    },
+    {
+      "epoch": 0.10501367365542388,
+      "grad_norm": 0.624421238899231,
+      "learning_rate": 1.0144927536231885e-05,
+      "loss": 0.7941208481788635,
+      "step": 36
+    },
+    {
+      "epoch": 0.10793072014585232,
+      "grad_norm": 0.6314200758934021,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.8931174278259277,
+      "step": 37
+    },
+    {
+      "epoch": 0.11084776663628076,
+      "grad_norm": 0.6272342205047607,
+      "learning_rate": 1.0724637681159422e-05,
+      "loss": 0.8978185057640076,
+      "step": 38
+    },
+    {
+      "epoch": 0.1137648131267092,
+      "grad_norm": 0.5711184740066528,
+      "learning_rate": 1.101449275362319e-05,
+      "loss": 0.808263897895813,
+      "step": 39
+    },
+    {
+      "epoch": 0.11668185961713765,
+      "grad_norm": 0.7581208944320679,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.7456756830215454,
+      "step": 40
+    },
+    {
+      "epoch": 0.11959890610756609,
+      "grad_norm": 0.4989977180957794,
+      "learning_rate": 1.1594202898550726e-05,
+      "loss": 0.8273333311080933,
+      "step": 41
+    },
+    {
+      "epoch": 0.12251595259799453,
+      "grad_norm": 0.8602972626686096,
+      "learning_rate": 1.1884057971014494e-05,
+      "loss": 0.8514784574508667,
+      "step": 42
+    },
+    {
+      "epoch": 0.12543299908842298,
+      "grad_norm": 0.6918581128120422,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.8182265162467957,
+      "step": 43
+    },
+    {
+      "epoch": 0.1283500455788514,
+      "grad_norm": 0.653099536895752,
+      "learning_rate": 1.2463768115942029e-05,
+      "loss": 0.8242791891098022,
+      "step": 44
+    },
+    {
+      "epoch": 0.13126709206927986,
+      "grad_norm": 0.7485584616661072,
+      "learning_rate": 1.2753623188405797e-05,
+      "loss": 0.8229591250419617,
+      "step": 45
+    },
+    {
+      "epoch": 0.1341841385597083,
+      "grad_norm": 0.6724833250045776,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.8146833181381226,
+      "step": 46
+    },
+    {
+      "epoch": 0.13710118505013674,
+      "grad_norm": 0.857208251953125,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8154427409172058,
+      "step": 47
+    },
+    {
+      "epoch": 0.14001823154056517,
+      "grad_norm": 0.5559669137001038,
+      "learning_rate": 1.3623188405797103e-05,
+      "loss": 0.879005491733551,
+      "step": 48
+    },
+    {
+      "epoch": 0.14293527803099362,
+      "grad_norm": 0.5910897850990295,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.8148283362388611,
+      "step": 49
+    },
+    {
+      "epoch": 0.14585232452142205,
+      "grad_norm": 0.6478891372680664,
+      "learning_rate": 1.420289855072464e-05,
+      "loss": 0.8293006420135498,
+      "step": 50
+    },
+    {
+      "epoch": 0.14585232452142205,
+      "eval_loss": 0.7892261147499084,
+      "eval_runtime": 973.2157,
+      "eval_samples_per_second": 0.649,
+      "eval_steps_per_second": 0.649,
+      "step": 50
+    },
+    {
+      "epoch": 0.1487693710118505,
+      "grad_norm": 0.757882833480835,
+      "learning_rate": 1.4492753623188407e-05,
+      "loss": 0.8114852905273438,
+      "step": 51
+    },
+    {
+      "epoch": 0.15168641750227893,
+      "grad_norm": 0.8496116995811462,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.7886185050010681,
+      "step": 52
+    },
+    {
+      "epoch": 0.15460346399270739,
+      "grad_norm": 0.6078857183456421,
+      "learning_rate": 1.5072463768115944e-05,
+      "loss": 0.7298170924186707,
+      "step": 53
+    },
+    {
+      "epoch": 0.1575205104831358,
+      "grad_norm": 0.5856835246086121,
+      "learning_rate": 1.536231884057971e-05,
+      "loss": 0.7407160997390747,
+      "step": 54
+    },
+    {
+      "epoch": 0.16043755697356427,
+      "grad_norm": 1.0533701181411743,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.7057831287384033,
+      "step": 55
+    },
+    {
+      "epoch": 0.16335460346399272,
+      "grad_norm": 0.8087610006332397,
+      "learning_rate": 1.5942028985507246e-05,
+      "loss": 0.7409019470214844,
+      "step": 56
+    },
+    {
+      "epoch": 0.16627164995442115,
+      "grad_norm": 0.629945695400238,
+      "learning_rate": 1.6231884057971015e-05,
+      "loss": 0.7768293023109436,
+      "step": 57
+    },
+    {
+      "epoch": 0.1691886964448496,
+      "grad_norm": 0.5187911987304688,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.825718104839325,
+      "step": 58
+    },
+    {
+      "epoch": 0.17210574293527803,
+      "grad_norm": 0.5866358280181885,
+      "learning_rate": 1.681159420289855e-05,
+      "loss": 0.8575979471206665,
+      "step": 59
+    },
+    {
+      "epoch": 0.17502278942570648,
+      "grad_norm": 1.5098934173583984,
+      "learning_rate": 1.710144927536232e-05,
+      "loss": 0.8058848977088928,
+      "step": 60
+    },
+    {
+      "epoch": 0.1779398359161349,
+      "grad_norm": 0.6981958150863647,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.7640778422355652,
+      "step": 61
+    },
+    {
+      "epoch": 0.18085688240656336,
+      "grad_norm": 0.631349503993988,
+      "learning_rate": 1.7681159420289858e-05,
+      "loss": 0.7896331548690796,
+      "step": 62
+    },
+    {
+      "epoch": 0.1837739288969918,
+      "grad_norm": 0.6930747032165527,
+      "learning_rate": 1.7971014492753624e-05,
+      "loss": 0.6762524247169495,
+      "step": 63
+    },
+    {
+      "epoch": 0.18669097538742024,
+      "grad_norm": 0.599399209022522,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.7285035848617554,
+      "step": 64
+    },
+    {
+      "epoch": 0.18960802187784867,
+      "grad_norm": 0.6194344758987427,
+      "learning_rate": 1.8550724637681162e-05,
+      "loss": 0.7682523131370544,
+      "step": 65
+    },
+    {
+      "epoch": 0.19252506836827712,
+      "grad_norm": 0.5691342949867249,
+      "learning_rate": 1.8840579710144928e-05,
+      "loss": 0.6791993379592896,
+      "step": 66
+    },
+    {
+      "epoch": 0.19544211485870555,
+      "grad_norm": 0.6257390379905701,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.6744828224182129,
+      "step": 67
+    },
+    {
+      "epoch": 0.198359161349134,
+      "grad_norm": 0.5871018767356873,
+      "learning_rate": 1.9420289855072467e-05,
+      "loss": 0.7317330837249756,
+      "step": 68
+    },
+    {
+      "epoch": 0.20127620783956243,
+      "grad_norm": 1.0744612216949463,
+      "learning_rate": 1.9710144927536236e-05,
+      "loss": 0.6617178916931152,
+      "step": 69
+    },
+    {
+      "epoch": 0.2041932543299909,
+      "grad_norm": 0.675946831703186,
+      "learning_rate": 2e-05,
+      "loss": 0.7615712881088257,
+      "step": 70
+    },
+    {
+      "epoch": 0.2071103008204193,
+      "grad_norm": 0.7663411498069763,
+      "learning_rate": 1.9999870372100614e-05,
+      "loss": 0.7131291627883911,
+      "step": 71
+    },
+    {
+      "epoch": 0.21002734731084777,
+      "grad_norm": 0.6725395321846008,
+      "learning_rate": 1.9999481491763123e-05,
+      "loss": 0.7452989816665649,
+      "step": 72
+    },
+    {
+      "epoch": 0.21294439380127622,
+      "grad_norm": 0.6505664587020874,
+      "learning_rate": 1.9998833369069483e-05,
+      "loss": 0.7477136850357056,
+      "step": 73
+    },
+    {
+      "epoch": 0.21586144029170465,
+      "grad_norm": 0.7032860517501831,
+      "learning_rate": 1.9997926020822643e-05,
+      "loss": 0.6854275465011597,
+      "step": 74
+    },
+    {
+      "epoch": 0.2187784867821331,
+      "grad_norm": 0.645345151424408,
+      "learning_rate": 1.999675947054614e-05,
+      "loss": 0.7552425265312195,
+      "step": 75
+    },
+    {
+      "epoch": 0.22169553327256153,
+      "grad_norm": 0.6620492935180664,
+      "learning_rate": 1.9995333748483464e-05,
+      "loss": 0.7262853384017944,
+      "step": 76
+    },
+    {
+      "epoch": 0.22461257976298998,
+      "grad_norm": 0.6511455774307251,
+      "learning_rate": 1.9993648891597284e-05,
+      "loss": 0.7591732144355774,
+      "step": 77
+    },
+    {
+      "epoch": 0.2275296262534184,
+      "grad_norm": 0.6775254011154175,
+      "learning_rate": 1.9991704943568497e-05,
+      "loss": 0.7498704195022583,
+      "step": 78
+    },
+    {
+      "epoch": 0.23044667274384686,
+      "grad_norm": 0.8199896216392517,
+      "learning_rate": 1.9989501954795076e-05,
+      "loss": 0.7238684296607971,
+      "step": 79
+    },
+    {
+      "epoch": 0.2333637192342753,
+      "grad_norm": 0.8197569847106934,
+      "learning_rate": 1.998703998239079e-05,
+      "loss": 0.7028778195381165,
+      "step": 80
+    },
+    {
+      "epoch": 0.23628076572470375,
+      "grad_norm": 0.6602625250816345,
+      "learning_rate": 1.9984319090183692e-05,
+      "loss": 0.8842703104019165,
+      "step": 81
+    },
+    {
+      "epoch": 0.23919781221513217,
+      "grad_norm": 0.9587129354476929,
+      "learning_rate": 1.99813393487145e-05,
+      "loss": 0.732614278793335,
+      "step": 82
+    },
+    {
+      "epoch": 0.24211485870556063,
+      "grad_norm": 0.6822189092636108,
+      "learning_rate": 1.997810083523473e-05,
+      "loss": 0.7544928193092346,
+      "step": 83
+    },
+    {
+      "epoch": 0.24503190519598905,
+      "grad_norm": 0.8980082869529724,
+      "learning_rate": 1.9974603633704726e-05,
+      "loss": 0.6704054474830627,
+      "step": 84
+    },
+    {
+      "epoch": 0.2479489516864175,
+      "grad_norm": 0.7413425445556641,
+      "learning_rate": 1.9970847834791472e-05,
+      "loss": 0.693661093711853,
+      "step": 85
+    },
+    {
+      "epoch": 0.25086599817684596,
+      "grad_norm": 0.8314999341964722,
+      "learning_rate": 1.9966833535866223e-05,
+      "loss": 0.667654275894165,
+      "step": 86
+    },
+    {
+      "epoch": 0.25378304466727436,
+      "grad_norm": 0.7972444891929626,
+      "learning_rate": 1.9962560841002013e-05,
+      "loss": 0.8403134942054749,
+      "step": 87
+    },
+    {
+      "epoch": 0.2567000911577028,
+      "grad_norm": 0.8519951701164246,
+      "learning_rate": 1.995802986097093e-05,
+      "loss": 0.6897370219230652,
+      "step": 88
+    },
+    {
+      "epoch": 0.25961713764813127,
+      "grad_norm": 0.8268933892250061,
+      "learning_rate": 1.995324071324126e-05,
+      "loss": 0.6690632700920105,
+      "step": 89
+    },
+    {
+      "epoch": 0.2625341841385597,
+      "grad_norm": 0.7133983969688416,
+      "learning_rate": 1.9948193521974436e-05,
+      "loss": 0.6314147114753723,
+      "step": 90
+    },
+    {
+      "epoch": 0.2654512306289881,
+      "grad_norm": 0.889302134513855,
+      "learning_rate": 1.9942888418021814e-05,
+      "loss": 0.7389825582504272,
+      "step": 91
+    },
+    {
+      "epoch": 0.2683682771194166,
+      "grad_norm": 0.7022432088851929,
+      "learning_rate": 1.99373255389213e-05,
+      "loss": 0.6916261911392212,
+      "step": 92
+    },
+    {
+      "epoch": 0.27128532360984503,
+      "grad_norm": 0.696432888507843,
+      "learning_rate": 1.9931505028893748e-05,
+      "loss": 0.6908476948738098,
+      "step": 93
+    },
+    {
+      "epoch": 0.2742023701002735,
+      "grad_norm": 0.7667419910430908,
+      "learning_rate": 1.9925427038839267e-05,
+      "loss": 0.6500837206840515,
+      "step": 94
+    },
+    {
+      "epoch": 0.27711941659070194,
+      "grad_norm": 0.6974894404411316,
+      "learning_rate": 1.9919091726333265e-05,
+      "loss": 0.7059191465377808,
+      "step": 95
+    },
+    {
+      "epoch": 0.28003646308113034,
+      "grad_norm": 0.7047077417373657,
+      "learning_rate": 1.9912499255622397e-05,
+      "loss": 0.6287837624549866,
+      "step": 96
+    },
+    {
+      "epoch": 0.2829535095715588,
+      "grad_norm": 0.7729557156562805,
+      "learning_rate": 1.990564979762029e-05,
+      "loss": 0.6738612055778503,
+      "step": 97
+    },
+    {
+      "epoch": 0.28587055606198725,
+      "grad_norm": 0.7020529508590698,
+      "learning_rate": 1.989854352990311e-05,
+      "loss": 0.662042498588562,
+      "step": 98
+    },
+    {
+      "epoch": 0.2887876025524157,
+      "grad_norm": 0.7369800209999084,
+      "learning_rate": 1.9891180636704975e-05,
+      "loss": 0.6246830821037292,
+      "step": 99
+    },
+    {
+      "epoch": 0.2917046490428441,
+      "grad_norm": 0.7412623167037964,
+      "learning_rate": 1.9883561308913154e-05,
+      "loss": 0.6623879075050354,
+      "step": 100
+    },
+    {
+      "epoch": 0.2917046490428441,
+      "eval_loss": 0.6552971005439758,
+      "eval_runtime": 966.7072,
+      "eval_samples_per_second": 0.654,
+      "eval_steps_per_second": 0.654,
+      "step": 100
+    },
+    {
+      "epoch": 0.29462169553327255,
+      "grad_norm": 0.8428792953491211,
+      "learning_rate": 1.987568574406314e-05,
+      "loss": 0.6312171816825867,
+      "step": 101
+    },
+    {
+      "epoch": 0.297538742023701,
+      "grad_norm": 0.6948133707046509,
+      "learning_rate": 1.9867554146333517e-05,
+      "loss": 0.6266146898269653,
+      "step": 102
+    },
+    {
+      "epoch": 0.30045578851412946,
+      "grad_norm": 1.3897597789764404,
+      "learning_rate": 1.985916672654068e-05,
+      "loss": 0.6669265031814575,
+      "step": 103
+    },
+    {
+      "epoch": 0.30337283500455786,
+      "grad_norm": 0.8838400840759277,
+      "learning_rate": 1.985052370213334e-05,
+      "loss": 0.6601086854934692,
+      "step": 104
+    },
+    {
+      "epoch": 0.3062898814949863,
+      "grad_norm": 0.8471395373344421,
+      "learning_rate": 1.9841625297186925e-05,
+      "loss": 0.5984431505203247,
+      "step": 105
+    },
+    {
+      "epoch": 0.30920692798541477,
+      "grad_norm": 0.8940042853355408,
+      "learning_rate": 1.983247174239774e-05,
+      "loss": 0.7223822474479675,
+      "step": 106
+    },
+    {
+      "epoch": 0.3121239744758432,
+      "grad_norm": 0.7833696603775024,
+      "learning_rate": 1.9823063275076998e-05,
+      "loss": 0.6868705749511719,
+      "step": 107
+    },
+    {
+      "epoch": 0.3150410209662716,
+      "grad_norm": 0.8794649243354797,
+      "learning_rate": 1.9813400139144673e-05,
+      "loss": 0.6246675848960876,
+      "step": 108
+    },
+    {
+      "epoch": 0.3179580674567001,
+      "grad_norm": 0.8126057982444763,
+      "learning_rate": 1.9803482585123165e-05,
+      "loss": 0.5908697247505188,
+      "step": 109
+    },
+    {
+      "epoch": 0.32087511394712853,
+      "grad_norm": 0.7947676777839661,
+      "learning_rate": 1.979331087013082e-05,
+      "loss": 0.5751246809959412,
+      "step": 110
+    },
+    {
+      "epoch": 0.323792160437557,
+      "grad_norm": 0.713545560836792,
+      "learning_rate": 1.978288525787524e-05,
+      "loss": 0.6081106066703796,
+      "step": 111
+    },
+    {
+      "epoch": 0.32670920692798544,
+      "grad_norm": 1.011828064918518,
+      "learning_rate": 1.977220601864647e-05,
+      "loss": 0.7039169669151306,
+      "step": 112
+    },
+    {
+      "epoch": 0.32962625341841384,
+      "grad_norm": 0.730570912361145,
+      "learning_rate": 1.9761273429309982e-05,
+      "loss": 0.6140255928039551,
+      "step": 113
+    },
+    {
+      "epoch": 0.3325432999088423,
+      "grad_norm": 1.059688687324524,
+      "learning_rate": 1.9750087773299492e-05,
+      "loss": 0.648114025592804,
+      "step": 114
+    },
+    {
+      "epoch": 0.33546034639927075,
+      "grad_norm": 0.9336895942687988,
+      "learning_rate": 1.973864934060962e-05,
+      "loss": 0.622555673122406,
+      "step": 115
+    },
+    {
+      "epoch": 0.3383773928896992,
+      "grad_norm": 0.7195945978164673,
+      "learning_rate": 1.9726958427788367e-05,
+      "loss": 0.70485520362854,
+      "step": 116
+    },
+    {
+      "epoch": 0.3412944393801276,
+      "grad_norm": 0.8101872801780701,
+      "learning_rate": 1.971501533792942e-05,
+      "loss": 0.6958848834037781,
+      "step": 117
+    },
+    {
+      "epoch": 0.34421148587055606,
+      "grad_norm": 1.6075212955474854,
+      "learning_rate": 1.970282038066432e-05,
+      "loss": 0.6021550893783569,
+      "step": 118
+    },
+    {
+      "epoch": 0.3471285323609845,
+      "grad_norm": 0.7881433963775635,
+      "learning_rate": 1.9690373872154396e-05,
+      "loss": 0.6449777483940125,
+      "step": 119
+    },
+    {
+      "epoch": 0.35004557885141296,
+      "grad_norm": 1.014639973640442,
+      "learning_rate": 1.9677676135082606e-05,
+      "loss": 0.5939379930496216,
+      "step": 120
+    },
+    {
+      "epoch": 0.35296262534184136,
+      "grad_norm": 0.8198449611663818,
+      "learning_rate": 1.9664727498645144e-05,
+      "loss": 0.6210286617279053,
+      "step": 121
+    },
+    {
+      "epoch": 0.3558796718322698,
+      "grad_norm": 1.0194576978683472,
+      "learning_rate": 1.9651528298542918e-05,
+      "loss": 0.624247670173645,
+      "step": 122
+    },
+    {
+      "epoch": 0.35879671832269827,
+      "grad_norm": 0.7963470220565796,
+      "learning_rate": 1.9638078876972842e-05,
+      "loss": 0.6479315757751465,
+      "step": 123
+    },
+    {
+      "epoch": 0.3617137648131267,
+      "grad_norm": 0.9007541537284851,
+      "learning_rate": 1.9624379582618976e-05,
+      "loss": 0.6131505370140076,
+      "step": 124
+    },
+    {
+      "epoch": 0.3646308113035551,
+      "grad_norm": 0.8712120056152344,
+      "learning_rate": 1.9610430770643464e-05,
+      "loss": 0.6249448657035828,
+      "step": 125
+    },
+    {
+      "epoch": 0.3675478577939836,
+      "grad_norm": 1.1482540369033813,
+      "learning_rate": 1.9596232802677347e-05,
+      "loss": 0.5844688415527344,
+      "step": 126
+    },
+    {
+      "epoch": 0.37046490428441203,
+      "grad_norm": 0.8662379384040833,
+      "learning_rate": 1.9581786046811175e-05,
+      "loss": 0.6573485732078552,
+      "step": 127
+    },
+    {
+      "epoch": 0.3733819507748405,
+      "grad_norm": 0.8191388845443726,
+      "learning_rate": 1.9567090877585477e-05,
+      "loss": 0.5896862745285034,
+      "step": 128
+    },
+    {
+      "epoch": 0.37629899726526894,
+      "grad_norm": 1.0187078714370728,
+      "learning_rate": 1.955214767598103e-05,
+      "loss": 0.613490879535675,
+      "step": 129
+    },
+    {
+      "epoch": 0.37921604375569734,
+      "grad_norm": 0.8444119691848755,
+      "learning_rate": 1.953695682940901e-05,
+      "loss": 0.727687656879425,
+      "step": 130
+    },
+    {
+      "epoch": 0.3821330902461258,
+      "grad_norm": 0.74753737449646,
+      "learning_rate": 1.9521518731700913e-05,
+      "loss": 0.6102436780929565,
+      "step": 131
+    },
+    {
+      "epoch": 0.38505013673655425,
+      "grad_norm": 1.0166202783584595,
+      "learning_rate": 1.9505833783098378e-05,
+      "loss": 0.6244844198226929,
+      "step": 132
+    },
+    {
+      "epoch": 0.3879671832269827,
+      "grad_norm": 0.8175772428512573,
+      "learning_rate": 1.9489902390242793e-05,
+      "loss": 0.5939282178878784,
+      "step": 133
+    },
+    {
+      "epoch": 0.3908842297174111,
+      "grad_norm": 1.0177713632583618,
+      "learning_rate": 1.947372496616476e-05,
+      "loss": 0.6418229937553406,
+      "step": 134
+    },
+    {
+      "epoch": 0.39380127620783956,
+      "grad_norm": 0.8652453422546387,
+      "learning_rate": 1.9457301930273376e-05,
+      "loss": 0.5870395302772522,
+      "step": 135
+    },
+    {
+      "epoch": 0.396718322698268,
+      "grad_norm": 0.8378894925117493,
+      "learning_rate": 1.9440633708345365e-05,
+      "loss": 0.6480278372764587,
+      "step": 136
+    },
+    {
+      "epoch": 0.39963536918869647,
+      "grad_norm": 0.8303541541099548,
+      "learning_rate": 1.9423720732514052e-05,
+      "loss": 0.6191359758377075,
+      "step": 137
+    },
+    {
+      "epoch": 0.40255241567912486,
+      "grad_norm": 0.8576734662055969,
+      "learning_rate": 1.9406563441258145e-05,
+      "loss": 0.5696198344230652,
+      "step": 138
+    },
+    {
+      "epoch": 0.4054694621695533,
+      "grad_norm": 0.9558727145195007,
+      "learning_rate": 1.9389162279390362e-05,
+      "loss": 0.6177623271942139,
+      "step": 139
+    },
+    {
+      "epoch": 0.4083865086599818,
+      "grad_norm": 0.7046042084693909,
+      "learning_rate": 1.9371517698045922e-05,
+      "loss": 0.5836521983146667,
+      "step": 140
+    },
+    {
+      "epoch": 0.4113035551504102,
+      "grad_norm": 1.0522717237472534,
+      "learning_rate": 1.935363015467082e-05,
+      "loss": 0.5728275775909424,
+      "step": 141
+    },
+    {
+      "epoch": 0.4142206016408386,
+      "grad_norm": 0.9554787874221802,
+      "learning_rate": 1.933550011301e-05,
+      "loss": 0.632586658000946,
+      "step": 142
+    },
+    {
+      "epoch": 0.4171376481312671,
+      "grad_norm": 0.8874214291572571,
+      "learning_rate": 1.9317128043095293e-05,
+      "loss": 0.5850118398666382,
+      "step": 143
+    },
+    {
+      "epoch": 0.42005469462169553,
+      "grad_norm": 1.0708963871002197,
+      "learning_rate": 1.9298514421233276e-05,
+      "loss": 0.6260685324668884,
+      "step": 144
+    },
+    {
+      "epoch": 0.422971741112124,
+      "grad_norm": 0.8135736584663391,
+      "learning_rate": 1.9279659729992888e-05,
+      "loss": 0.6031094193458557,
+      "step": 145
+    },
+    {
+      "epoch": 0.42588878760255244,
+      "grad_norm": 0.7971774339675903,
+      "learning_rate": 1.9260564458192926e-05,
+      "loss": 0.6101322770118713,
+      "step": 146
+    },
+    {
+      "epoch": 0.42880583409298084,
+      "grad_norm": 0.9374974966049194,
+      "learning_rate": 1.9241229100889397e-05,
+      "loss": 0.5836313366889954,
+      "step": 147
+    },
+    {
+      "epoch": 0.4317228805834093,
+      "grad_norm": 0.8043425679206848,
+      "learning_rate": 1.9221654159362636e-05,
+      "loss": 0.6181215047836304,
+      "step": 148
+    },
+    {
+      "epoch": 0.43463992707383775,
+      "grad_norm": 0.8923380374908447,
+      "learning_rate": 1.920184014110436e-05,
+      "loss": 0.6149677634239197,
+      "step": 149
+    },
+    {
+      "epoch": 0.4375569735642662,
+      "grad_norm": 0.8908132314682007,
+      "learning_rate": 1.918178755980449e-05,
+      "loss": 0.5899742841720581,
+      "step": 150
+    },
+    {
+      "epoch": 0.4375569735642662,
+      "eval_loss": 0.5903874635696411,
+      "eval_runtime": 1186.9542,
+      "eval_samples_per_second": 0.532,
+      "eval_steps_per_second": 0.532,
+      "step": 150
+    },
+    {
+      "epoch": 0.4404740200546946,
+      "grad_norm": 1.060531497001648,
+      "learning_rate": 1.9161496935337808e-05,
+      "loss": 0.5852696895599365,
+      "step": 151
+    },
+    {
+      "epoch": 0.44339106654512306,
+      "grad_norm": 0.9723032712936401,
+      "learning_rate": 1.914096879375053e-05,
+      "loss": 0.5822056531906128,
+      "step": 152
+    },
+    {
+      "epoch": 0.4463081130355515,
+      "grad_norm": 0.9519931674003601,
+      "learning_rate": 1.912020366724663e-05,
+      "loss": 0.6183493137359619,
+      "step": 153
+    },
+    {
+      "epoch": 0.44922515952597997,
+      "grad_norm": 0.8282918334007263,
+      "learning_rate": 1.9099202094174055e-05,
+      "loss": 0.6229860782623291,
+      "step": 154
+    },
+    {
+      "epoch": 0.45214220601640837,
+      "grad_norm": 0.9251292943954468,
+      "learning_rate": 1.907796461901076e-05,
+      "loss": 0.6552959680557251,
+      "step": 155
+    },
+    {
+      "epoch": 0.4550592525068368,
+      "grad_norm": 1.0349540710449219,
+      "learning_rate": 1.9056491792350606e-05,
+      "loss": 0.6170098781585693,
+      "step": 156
+    },
+    {
+      "epoch": 0.4579762989972653,
+      "grad_norm": 0.8720711469650269,
+      "learning_rate": 1.9034784170889076e-05,
+      "loss": 0.5870137810707092,
+      "step": 157
+    },
+    {
+      "epoch": 0.46089334548769373,
+      "grad_norm": 1.0785977840423584,
+      "learning_rate": 1.9012842317408843e-05,
+      "loss": 0.5515124201774597,
+      "step": 158
+    },
+    {
+      "epoch": 0.4638103919781221,
+      "grad_norm": 1.0634154081344604,
+      "learning_rate": 1.8990666800765187e-05,
+      "loss": 0.6073828339576721,
+      "step": 159
+    },
+    {
+      "epoch": 0.4667274384685506,
+      "grad_norm": 0.8770879507064819,
+      "learning_rate": 1.896825819587123e-05,
+      "loss": 0.5960907936096191,
+      "step": 160
+    },
+    {
+      "epoch": 0.46964448495897904,
+      "grad_norm": 1.1225898265838623,
+      "learning_rate": 1.894561708368305e-05,
+      "loss": 0.545990526676178,
+      "step": 161
+    },
+    {
+      "epoch": 0.4725615314494075,
+      "grad_norm": 0.9373893141746521,
+      "learning_rate": 1.8922744051184613e-05,
+      "loss": 0.5566108822822571,
+      "step": 162
+    },
+    {
+      "epoch": 0.4754785779398359,
+      "grad_norm": 1.5016087293624878,
+      "learning_rate": 1.8899639691372545e-05,
+      "loss": 0.558845043182373,
+      "step": 163
+    },
+    {
+      "epoch": 0.47839562443026434,
+      "grad_norm": 0.903020977973938,
+      "learning_rate": 1.8876304603240773e-05,
+      "loss": 0.6824233531951904,
+      "step": 164
+    },
+    {
+      "epoch": 0.4813126709206928,
+      "grad_norm": 0.8239623308181763,
+      "learning_rate": 1.8852739391764993e-05,
+      "loss": 0.5630610585212708,
+      "step": 165
+    },
+    {
+      "epoch": 0.48422971741112125,
+      "grad_norm": 0.926069438457489,
+      "learning_rate": 1.882894466788697e-05,
+      "loss": 0.6211802363395691,
+      "step": 166
+    },
+    {
+      "epoch": 0.4871467639015497,
+      "grad_norm": 1.0098828077316284,
+      "learning_rate": 1.8804921048498722e-05,
+      "loss": 0.5513257384300232,
+      "step": 167
+    },
+    {
+      "epoch": 0.4900638103919781,
+      "grad_norm": 0.9228141903877258,
+      "learning_rate": 1.8780669156426517e-05,
+      "loss": 0.6197121739387512,
+      "step": 168
+    },
+    {
+      "epoch": 0.49298085688240656,
+      "grad_norm": 1.0551754236221313,
+      "learning_rate": 1.8756189620414712e-05,
+      "loss": 0.5221806764602661,
+      "step": 169
+    },
+    {
+      "epoch": 0.495897903372835,
+      "grad_norm": 0.9017496109008789,
+      "learning_rate": 1.873148307510948e-05,
+      "loss": 0.5766995549201965,
+      "step": 170
+    },
+    {
+      "epoch": 0.49881494986326347,
+      "grad_norm": 0.9704970717430115,
+      "learning_rate": 1.870655016104233e-05,
+      "loss": 0.6514763832092285,
+      "step": 171
+    },
+    {
+      "epoch": 0.5017319963536919,
+      "grad_norm": 0.9972712397575378,
+      "learning_rate": 1.8681391524613518e-05,
+      "loss": 0.5273895263671875,
+      "step": 172
+    },
+    {
+      "epoch": 0.5046490428441204,
+      "grad_norm": 0.9473339319229126,
+      "learning_rate": 1.8656007818075288e-05,
+      "loss": 0.5548599362373352,
+      "step": 173
+    },
+    {
+      "epoch": 0.5075660893345487,
+      "grad_norm": 1.2493574619293213,
+      "learning_rate": 1.8630399699514944e-05,
+      "loss": 0.5593586564064026,
+      "step": 174
+    },
+    {
+      "epoch": 0.5104831358249772,
+      "grad_norm": 1.2766696214675903,
+      "learning_rate": 1.860456783283781e-05,
+      "loss": 0.6054630279541016,
+      "step": 175
+    },
+    {
+      "epoch": 0.5134001823154056,
+      "grad_norm": 0.9555240869522095,
+      "learning_rate": 1.857851288775002e-05,
+      "loss": 0.508592963218689,
+      "step": 176
+    },
+    {
+      "epoch": 0.5163172288058341,
+      "grad_norm": 1.260219931602478,
+      "learning_rate": 1.8552235539741118e-05,
+      "loss": 0.5532065629959106,
+      "step": 177
+    },
+    {
+      "epoch": 0.5192342752962625,
+      "grad_norm": 1.1859954595565796,
+      "learning_rate": 1.8525736470066595e-05,
+      "loss": 0.5683344006538391,
+      "step": 178
+    },
+    {
+      "epoch": 0.522151321786691,
+      "grad_norm": 1.3044344186782837,
+      "learning_rate": 1.8499016365730203e-05,
+      "loss": 0.5281959772109985,
+      "step": 179
+    },
+    {
+      "epoch": 0.5250683682771194,
+      "grad_norm": 1.3049921989440918,
+      "learning_rate": 1.8472075919466137e-05,
+      "loss": 0.49621230363845825,
+      "step": 180
+    },
+    {
+      "epoch": 0.5279854147675479,
+      "grad_norm": 1.0488537549972534,
+      "learning_rate": 1.844491582972109e-05,
+      "loss": 0.6194032430648804,
+      "step": 181
+    },
+    {
+      "epoch": 0.5309024612579762,
+      "grad_norm": 1.5553455352783203,
+      "learning_rate": 1.8417536800636138e-05,
+      "loss": 0.5645846724510193,
+      "step": 182
+    },
+    {
+      "epoch": 0.5338195077484047,
+      "grad_norm": 1.2673912048339844,
+      "learning_rate": 1.8389939542028484e-05,
+      "loss": 0.6267315745353699,
+      "step": 183
+    },
+    {
+      "epoch": 0.5367365542388332,
+      "grad_norm": 1.0273847579956055,
+      "learning_rate": 1.8362124769373064e-05,
+      "loss": 0.5256403684616089,
+      "step": 184
+    },
+    {
+      "epoch": 0.5396536007292616,
+      "grad_norm": 1.006093978881836,
+      "learning_rate": 1.8334093203783986e-05,
+      "loss": 0.5916382074356079,
+      "step": 185
+    },
+    {
+      "epoch": 0.5425706472196901,
+      "grad_norm": 1.2740857601165771,
+      "learning_rate": 1.8305845571995843e-05,
+      "loss": 0.581648588180542,
+      "step": 186
+    },
+    {
+      "epoch": 0.5454876937101185,
+      "grad_norm": 1.494248390197754,
+      "learning_rate": 1.8277382606344872e-05,
+      "loss": 0.4824523627758026,
+      "step": 187
+    },
+    {
+      "epoch": 0.548404740200547,
+      "grad_norm": 1.1862496137619019,
+      "learning_rate": 1.824870504474996e-05,
+      "loss": 0.5531858205795288,
+      "step": 188
+    },
+    {
+      "epoch": 0.5513217866909754,
+      "grad_norm": 3.503049373626709,
+      "learning_rate": 1.8219813630693523e-05,
+      "loss": 0.6308296918869019,
+      "step": 189
+    },
+    {
+      "epoch": 0.5542388331814039,
+      "grad_norm": 1.7544710636138916,
+      "learning_rate": 1.819070911320222e-05,
+      "loss": 0.6146273016929626,
+      "step": 190
+    },
+    {
+      "epoch": 0.5571558796718322,
+      "grad_norm": 1.3367774486541748,
+      "learning_rate": 1.8161392246827546e-05,
+      "loss": 0.5848966240882874,
+      "step": 191
+    },
+    {
+      "epoch": 0.5600729261622607,
+      "grad_norm": 1.696418046951294,
+      "learning_rate": 1.8131863791626263e-05,
+      "loss": 0.6621730327606201,
+      "step": 192
+    },
+    {
+      "epoch": 0.5629899726526891,
+      "grad_norm": 1.360052227973938,
+      "learning_rate": 1.8102124513140694e-05,
+      "loss": 0.5972204208374023,
+      "step": 193
+    },
+    {
+      "epoch": 0.5659070191431176,
+      "grad_norm": 1.5376263856887817,
+      "learning_rate": 1.807217518237888e-05,
+      "loss": 0.4938785433769226,
+      "step": 194
+    },
+    {
+      "epoch": 0.568824065633546,
+      "grad_norm": 1.2249681949615479,
+      "learning_rate": 1.8042016575794585e-05,
+      "loss": 0.5366095304489136,
+      "step": 195
+    },
+    {
+      "epoch": 0.5717411121239745,
+      "grad_norm": 1.7868080139160156,
+      "learning_rate": 1.8011649475267178e-05,
+      "loss": 0.5116773843765259,
+      "step": 196
+    },
+    {
+      "epoch": 0.574658158614403,
+      "grad_norm": 2.369993209838867,
+      "learning_rate": 1.7981074668081345e-05,
+      "loss": 0.49072742462158203,
+      "step": 197
+    },
+    {
+      "epoch": 0.5775752051048314,
+      "grad_norm": 1.0168434381484985,
+      "learning_rate": 1.7950292946906695e-05,
+      "loss": 0.5691611170768738,
+      "step": 198
+    },
+    {
+      "epoch": 0.5804922515952597,
+      "grad_norm": 1.2990851402282715,
+      "learning_rate": 1.7919305109777195e-05,
+      "loss": 0.5515039563179016,
+      "step": 199
+    },
+    {
+      "epoch": 0.5834092980856882,
+      "grad_norm": 1.4859853982925415,
+      "learning_rate": 1.7888111960070493e-05,
+      "loss": 0.5017011165618896,
+      "step": 200
+    },
+    {
+      "epoch": 0.5834092980856882,
+      "eval_loss": 0.5414339303970337,
+      "eval_runtime": 1180.7894,
+      "eval_samples_per_second": 0.535,
+      "eval_steps_per_second": 0.535,
+      "step": 200
+    },
+    {
+      "epoch": 0.5863263445761167,
+      "grad_norm": 1.0065829753875732,
+      "learning_rate": 1.7856714306487088e-05,
+      "loss": 0.5677731037139893,
+      "step": 201
+    },
+    {
+      "epoch": 0.5892433910665451,
+      "grad_norm": 1.1727538108825684,
+      "learning_rate": 1.7825112963029352e-05,
+      "loss": 0.4525509476661682,
+      "step": 202
+    },
+    {
+      "epoch": 0.5921604375569736,
+      "grad_norm": 1.3376752138137817,
+      "learning_rate": 1.7793308748980437e-05,
+      "loss": 0.5208959579467773,
+      "step": 203
+    },
+    {
+      "epoch": 0.595077484047402,
+      "grad_norm": 0.9196159839630127,
+      "learning_rate": 1.776130248888304e-05,
+      "loss": 0.6033903360366821,
+      "step": 204
+    },
+    {
+      "epoch": 0.5979945305378305,
+      "grad_norm": 1.0750919580459595,
+      "learning_rate": 1.772909501251801e-05,
+      "loss": 0.5449609160423279,
+      "step": 205
+    },
+    {
+      "epoch": 0.6009115770282589,
+      "grad_norm": 1.2459467649459839,
+      "learning_rate": 1.769668715488285e-05,
+      "loss": 0.5685338377952576,
+      "step": 206
+    },
+    {
+      "epoch": 0.6038286235186874,
+      "grad_norm": 1.1690552234649658,
+      "learning_rate": 1.766407975617006e-05,
+      "loss": 0.5240382552146912,
+      "step": 207
+    },
+    {
+      "epoch": 0.6067456700091157,
+      "grad_norm": 1.0816599130630493,
+      "learning_rate": 1.7631273661745362e-05,
+      "loss": 0.6802893877029419,
+      "step": 208
+    },
+    {
+      "epoch": 0.6096627164995442,
+      "grad_norm": 1.3662947416305542,
+      "learning_rate": 1.7598269722125775e-05,
+      "loss": 0.48193931579589844,
+      "step": 209
+    },
+    {
+      "epoch": 0.6125797629899726,
+      "grad_norm": 0.9364766478538513,
+      "learning_rate": 1.7565068792957576e-05,
+      "loss": 0.5675849914550781,
+      "step": 210
+    },
+    {
+      "epoch": 0.6154968094804011,
+      "grad_norm": 1.123828411102295,
+      "learning_rate": 1.75316717349941e-05,
+      "loss": 0.5474762916564941,
+      "step": 211
+    },
+    {
+      "epoch": 0.6184138559708295,
+      "grad_norm": 1.1924363374710083,
+      "learning_rate": 1.749807941407345e-05,
+      "loss": 0.4918654263019562,
+      "step": 212
+    },
+    {
+      "epoch": 0.621330902461258,
+      "grad_norm": 1.101293921470642,
+      "learning_rate": 1.7464292701096014e-05,
+      "loss": 0.5742691159248352,
+      "step": 213
+    },
+    {
+      "epoch": 0.6242479489516864,
+      "grad_norm": 1.7374963760375977,
+      "learning_rate": 1.7430312472001928e-05,
+      "loss": 0.5828965902328491,
+      "step": 214
+    },
+    {
+      "epoch": 0.6271649954421149,
+      "grad_norm": 1.3195666074752808,
+      "learning_rate": 1.739613960774833e-05,
+      "loss": 0.5265159010887146,
+      "step": 215
+    },
+    {
+      "epoch": 0.6300820419325432,
+      "grad_norm": 1.254686713218689,
+      "learning_rate": 1.7361774994286545e-05,
+      "loss": 0.4929371476173401,
+      "step": 216
+    },
+    {
+      "epoch": 0.6329990884229717,
+      "grad_norm": 1.1476380825042725,
+      "learning_rate": 1.7327219522539102e-05,
+      "loss": 0.5060417652130127,
+      "step": 217
+    },
+    {
+      "epoch": 0.6359161349134002,
+      "grad_norm": 1.0914150476455688,
+      "learning_rate": 1.7292474088376643e-05,
+      "loss": 0.504043698310852,
+      "step": 218
+    },
+    {
+      "epoch": 0.6388331814038286,
+      "grad_norm": 1.1339508295059204,
+      "learning_rate": 1.7257539592594698e-05,
+      "loss": 0.4797310531139374,
+      "step": 219
+    },
+    {
+      "epoch": 0.6417502278942571,
+      "grad_norm": 1.0805399417877197,
+      "learning_rate": 1.722241694089033e-05,
+      "loss": 0.5878555178642273,
+      "step": 220
+    },
+    {
+      "epoch": 0.6446672743846855,
+      "grad_norm": 1.8615056276321411,
+      "learning_rate": 1.718710704383865e-05,
+      "loss": 0.5005823969841003,
+      "step": 221
+    },
+    {
+      "epoch": 0.647584320875114,
+      "grad_norm": 1.1445401906967163,
+      "learning_rate": 1.7151610816869214e-05,
+      "loss": 0.4949319064617157,
+      "step": 222
+    },
+    {
+      "epoch": 0.6505013673655424,
+      "grad_norm": 0.9726515412330627,
+      "learning_rate": 1.711592918024229e-05,
+      "loss": 0.5073204040527344,
+      "step": 223
+    },
+    {
+      "epoch": 0.6534184138559709,
+      "grad_norm": 1.4491140842437744,
+      "learning_rate": 1.7080063059024998e-05,
+      "loss": 0.47885262966156006,
+      "step": 224
+    },
+    {
+      "epoch": 0.6563354603463992,
+      "grad_norm": 1.0070592164993286,
+      "learning_rate": 1.7044013383067327e-05,
+      "loss": 0.5775837898254395,
+      "step": 225
+    },
+    {
+      "epoch": 0.6592525068368277,
+      "grad_norm": 0.966221272945404,
+      "learning_rate": 1.7007781086978037e-05,
+      "loss": 0.5050399899482727,
+      "step": 226
+    },
+    {
+      "epoch": 0.6621695533272561,
+      "grad_norm": 0.9808815121650696,
+      "learning_rate": 1.6971367110100407e-05,
+      "loss": 0.5737045407295227,
+      "step": 227
+    },
+    {
+      "epoch": 0.6650865998176846,
+      "grad_norm": 1.0158127546310425,
+      "learning_rate": 1.6934772396487906e-05,
+      "loss": 0.48077821731567383,
+      "step": 228
+    },
+    {
+      "epoch": 0.668003646308113,
+      "grad_norm": 1.32015860080719,
+      "learning_rate": 1.6897997894879706e-05,
+      "loss": 0.5614925026893616,
+      "step": 229
+    },
+    {
+      "epoch": 0.6709206927985415,
+      "grad_norm": 1.1055903434753418,
+      "learning_rate": 1.686104455867608e-05,
+      "loss": 0.4970760643482208,
+      "step": 230
+    },
+    {
+      "epoch": 0.67383773928897,
+      "grad_norm": 1.0804500579833984,
+      "learning_rate": 1.682391334591371e-05,
+      "loss": 0.5540452003479004,
+      "step": 231
+    },
+    {
+      "epoch": 0.6767547857793984,
+      "grad_norm": 1.1906245946884155,
+      "learning_rate": 1.6786605219240807e-05,
+      "loss": 0.5778501033782959,
+      "step": 232
+    },
+    {
+      "epoch": 0.6796718322698267,
+      "grad_norm": 0.9758645296096802,
+      "learning_rate": 1.6749121145892192e-05,
+      "loss": 0.49073565006256104,
+      "step": 233
+    },
+    {
+      "epoch": 0.6825888787602552,
+      "grad_norm": 1.1678364276885986,
+      "learning_rate": 1.6711462097664207e-05,
+      "loss": 0.4828741252422333,
+      "step": 234
+    },
+    {
+      "epoch": 0.6855059252506837,
+      "grad_norm": 1.148301362991333,
+      "learning_rate": 1.6673629050889507e-05,
+      "loss": 0.5143818855285645,
+      "step": 235
+    },
+    {
+      "epoch": 0.6884229717411121,
+      "grad_norm": 1.005898356437683,
+      "learning_rate": 1.6635622986411776e-05,
+      "loss": 0.5301160216331482,
+      "step": 236
+    },
+    {
+      "epoch": 0.6913400182315406,
+      "grad_norm": 1.2227320671081543,
+      "learning_rate": 1.659744488956027e-05,
+      "loss": 0.4800386130809784,
+      "step": 237
+    },
+    {
+      "epoch": 0.694257064721969,
+      "grad_norm": 0.986456573009491,
+      "learning_rate": 1.6559095750124296e-05,
+      "loss": 0.5098081827163696,
+      "step": 238
+    },
+    {
+      "epoch": 0.6971741112123975,
+      "grad_norm": 1.1474376916885376,
+      "learning_rate": 1.6520576562327518e-05,
+      "loss": 0.5147273540496826,
+      "step": 239
+    },
+    {
+      "epoch": 0.7000911577028259,
+      "grad_norm": 1.10917067527771,
+      "learning_rate": 1.6481888324802223e-05,
+      "loss": 0.5023190379142761,
+      "step": 240
+    },
+    {
+      "epoch": 0.7030082041932544,
+      "grad_norm": 1.2339262962341309,
+      "learning_rate": 1.644303204056341e-05,
+      "loss": 0.5282092690467834,
+      "step": 241
+    },
+    {
+      "epoch": 0.7059252506836827,
+      "grad_norm": 0.997941255569458,
+      "learning_rate": 1.640400871698277e-05,
+      "loss": 0.5635963082313538,
+      "step": 242
+    },
+    {
+      "epoch": 0.7088422971741112,
+      "grad_norm": 1.0345823764801025,
+      "learning_rate": 1.63648193657626e-05,
+      "loss": 0.5577977895736694,
+      "step": 243
+    },
+    {
+      "epoch": 0.7117593436645396,
+      "grad_norm": 1.3468303680419922,
+      "learning_rate": 1.6325465002909554e-05,
+      "loss": 0.4365362524986267,
+      "step": 244
+    },
+    {
+      "epoch": 0.7146763901549681,
+      "grad_norm": 1.2817128896713257,
+      "learning_rate": 1.628594664870831e-05,
+      "loss": 0.46069926023483276,
+      "step": 245
+    },
+    {
+      "epoch": 0.7175934366453965,
+      "grad_norm": 1.043311357498169,
+      "learning_rate": 1.6246265327695117e-05,
+      "loss": 0.5476971864700317,
+      "step": 246
+    },
+    {
+      "epoch": 0.720510483135825,
+      "grad_norm": 1.0297389030456543,
+      "learning_rate": 1.620642206863124e-05,
+      "loss": 0.48051249980926514,
+      "step": 247
+    },
+    {
+      "epoch": 0.7234275296262535,
+      "grad_norm": 1.4869836568832397,
+      "learning_rate": 1.6166417904476257e-05,
+      "loss": 0.5683314800262451,
+      "step": 248
+    },
+    {
+      "epoch": 0.7263445761166819,
+      "grad_norm": 1.0628005266189575,
+      "learning_rate": 1.6126253872361336e-05,
+      "loss": 0.5277887582778931,
+      "step": 249
+    },
+    {
+      "epoch": 0.7292616226071102,
+      "grad_norm": 1.2682170867919922,
+      "learning_rate": 1.608593101356229e-05,
+      "loss": 0.5048879384994507,
+      "step": 250
+    },
+    {
+      "epoch": 0.7292616226071102,
+      "eval_loss": 0.5038471221923828,
+      "eval_runtime": 1175.0375,
+      "eval_samples_per_second": 0.538,
+      "eval_steps_per_second": 0.538,
+      "step": 250
+    },
+    {
+      "epoch": 0.7321786690975387,
+      "grad_norm": 1.7376199960708618,
+      "learning_rate": 1.6045450373472626e-05,
+      "loss": 0.5093721151351929,
+      "step": 251
+    },
+    {
+      "epoch": 0.7350957155879672,
+      "grad_norm": 1.6047718524932861,
+      "learning_rate": 1.6004813001576405e-05,
+      "loss": 0.4796055555343628,
+      "step": 252
+    },
+    {
+      "epoch": 0.7380127620783956,
+      "grad_norm": 1.3582886457443237,
+      "learning_rate": 1.5964019951421058e-05,
+      "loss": 0.4733014702796936,
+      "step": 253
+    },
+    {
+      "epoch": 0.7409298085688241,
+      "grad_norm": 0.9468897581100464,
+      "learning_rate": 1.5923072280590072e-05,
+      "loss": 0.5312032103538513,
+      "step": 254
+    },
+    {
+      "epoch": 0.7438468550592525,
+      "grad_norm": 1.3890198469161987,
+      "learning_rate": 1.5881971050675547e-05,
+      "loss": 0.47576645016670227,
+      "step": 255
+    },
+    {
+      "epoch": 0.746763901549681,
+      "grad_norm": 1.782992959022522,
+      "learning_rate": 1.584071732725071e-05,
+      "loss": 0.5555092096328735,
+      "step": 256
+    },
+    {
+      "epoch": 0.7496809480401094,
+      "grad_norm": 1.1790621280670166,
+      "learning_rate": 1.5799312179842265e-05,
+      "loss": 0.5148727893829346,
+      "step": 257
+    },
+    {
+      "epoch": 0.7525979945305379,
+      "grad_norm": 1.446694254875183,
+      "learning_rate": 1.5757756681902664e-05,
+      "loss": 0.49939870834350586,
+      "step": 258
+    },
+    {
+      "epoch": 0.7555150410209662,
+      "grad_norm": 1.1786166429519653,
+      "learning_rate": 1.571605191078229e-05,
+      "loss": 0.562156081199646,
+      "step": 259
+    },
+    {
+      "epoch": 0.7584320875113947,
+      "grad_norm": 1.16925847530365,
+      "learning_rate": 1.567419894770151e-05,
+      "loss": 0.49580734968185425,
+      "step": 260
+    },
+    {
+      "epoch": 0.7613491340018231,
+      "grad_norm": 1.60944664478302,
+      "learning_rate": 1.5632198877722676e-05,
+      "loss": 0.4821680784225464,
+      "step": 261
+    },
+    {
+      "epoch": 0.7642661804922516,
+      "grad_norm": 1.3957884311676025,
+      "learning_rate": 1.5590052789721946e-05,
+      "loss": 0.4392276406288147,
+      "step": 262
+    },
+    {
+      "epoch": 0.76718322698268,
+      "grad_norm": 1.636195421218872,
+      "learning_rate": 1.5547761776361096e-05,
+      "loss": 0.39603114128112793,
+      "step": 263
+    },
+    {
+      "epoch": 0.7701002734731085,
+      "grad_norm": 1.496766448020935,
+      "learning_rate": 1.550532693405917e-05,
+      "loss": 0.4833749234676361,
+      "step": 264
+    },
+    {
+      "epoch": 0.773017319963537,
+      "grad_norm": 1.3587844371795654,
+      "learning_rate": 1.5462749362964058e-05,
+      "loss": 0.43738317489624023,
+      "step": 265
+    },
+    {
+      "epoch": 0.7759343664539654,
+      "grad_norm": 1.670704960823059,
+      "learning_rate": 1.5420030166923983e-05,
+      "loss": 0.4476737380027771,
+      "step": 266
+    },
+    {
+      "epoch": 0.7788514129443938,
+      "grad_norm": 1.2674932479858398,
+      "learning_rate": 1.537717045345888e-05,
+      "loss": 0.42266708612442017,
+      "step": 267
+    },
+    {
+      "epoch": 0.7817684594348222,
+      "grad_norm": 2.0639536380767822,
+      "learning_rate": 1.5334171333731666e-05,
+      "loss": 0.5245381593704224,
+      "step": 268
+    },
+    {
+      "epoch": 0.7846855059252507,
+      "grad_norm": 1.2091766595840454,
+      "learning_rate": 1.529103392251946e-05,
+      "loss": 0.5166443586349487,
+      "step": 269
+    },
+    {
+      "epoch": 0.7876025524156791,
+      "grad_norm": 1.1021631956100464,
+      "learning_rate": 1.5247759338184653e-05,
+      "loss": 0.5674265027046204,
+      "step": 270
+    },
+    {
+      "epoch": 0.7905195989061076,
+      "grad_norm": 1.3143829107284546,
+      "learning_rate": 1.520434870264595e-05,
+      "loss": 0.40855613350868225,
+      "step": 271
+    },
+    {
+      "epoch": 0.793436645396536,
+      "grad_norm": 1.1784812211990356,
+      "learning_rate": 1.5160803141349244e-05,
+      "loss": 0.4308925271034241,
+      "step": 272
+    },
+    {
+      "epoch": 0.7963536918869645,
+      "grad_norm": 2.1635706424713135,
+      "learning_rate": 1.5117123783238458e-05,
+      "loss": 0.45035502314567566,
+      "step": 273
+    },
+    {
+      "epoch": 0.7992707383773929,
+      "grad_norm": 1.569203495979309,
+      "learning_rate": 1.5073311760726287e-05,
+      "loss": 0.5095728635787964,
+      "step": 274
+    },
+    {
+      "epoch": 0.8021877848678214,
+      "grad_norm": 2.532621383666992,
+      "learning_rate": 1.5029368209664822e-05,
+      "loss": 0.496748685836792,
+      "step": 275
+    },
+    {
+      "epoch": 0.8051048313582497,
+      "grad_norm": 1.6312552690505981,
+      "learning_rate": 1.4985294269316098e-05,
+      "loss": 0.4972914159297943,
+      "step": 276
+    },
+    {
+      "epoch": 0.8080218778486782,
+      "grad_norm": 1.3996756076812744,
+      "learning_rate": 1.4941091082322579e-05,
+      "loss": 0.5589750409126282,
+      "step": 277
+    },
+    {
+      "epoch": 0.8109389243391066,
+      "grad_norm": 1.1288363933563232,
+      "learning_rate": 1.4896759794677526e-05,
+      "loss": 0.5349453687667847,
+      "step": 278
+    },
+    {
+      "epoch": 0.8138559708295351,
+      "grad_norm": 1.6913920640945435,
+      "learning_rate": 1.4852301555695268e-05,
+      "loss": 0.46511000394821167,
+      "step": 279
+    },
+    {
+      "epoch": 0.8167730173199635,
+      "grad_norm": 1.1913212537765503,
+      "learning_rate": 1.4807717517981439e-05,
+      "loss": 0.4715422987937927,
+      "step": 280
+    },
+    {
+      "epoch": 0.819690063810392,
+      "grad_norm": 1.1179691553115845,
+      "learning_rate": 1.476300883740307e-05,
+      "loss": 0.53330397605896,
+      "step": 281
+    },
+    {
+      "epoch": 0.8226071103008205,
+      "grad_norm": 1.7473797798156738,
+      "learning_rate": 1.4718176673058624e-05,
+      "loss": 0.47564437985420227,
+      "step": 282
+    },
+    {
+      "epoch": 0.8255241567912489,
+      "grad_norm": 1.2653177976608276,
+      "learning_rate": 1.4673222187247963e-05,
+      "loss": 0.46364277601242065,
+      "step": 283
+    },
+    {
+      "epoch": 0.8284412032816773,
+      "grad_norm": 1.2567330598831177,
+      "learning_rate": 1.4628146545442202e-05,
+      "loss": 0.4778091013431549,
+      "step": 284
+    },
+    {
+      "epoch": 0.8313582497721057,
+      "grad_norm": 1.5848406553268433,
+      "learning_rate": 1.4582950916253488e-05,
+      "loss": 0.4480203688144684,
+      "step": 285
+    },
+    {
+      "epoch": 0.8342752962625342,
+      "grad_norm": 1.3278183937072754,
+      "learning_rate": 1.453763647140472e-05,
+      "loss": 0.37945032119750977,
+      "step": 286
+    },
+    {
+      "epoch": 0.8371923427529626,
+      "grad_norm": 1.0961651802062988,
+      "learning_rate": 1.4492204385699155e-05,
+      "loss": 0.5306747555732727,
+      "step": 287
+    },
+    {
+      "epoch": 0.8401093892433911,
+      "grad_norm": 1.176276683807373,
+      "learning_rate": 1.4446655836989961e-05,
+      "loss": 0.49950045347213745,
+      "step": 288
+    },
+    {
+      "epoch": 0.8430264357338195,
+      "grad_norm": 1.2228269577026367,
+      "learning_rate": 1.4400992006149674e-05,
+      "loss": 0.494475394487381,
+      "step": 289
+    },
+    {
+      "epoch": 0.845943482224248,
+      "grad_norm": 1.1584209203720093,
+      "learning_rate": 1.4355214077039592e-05,
+      "loss": 0.44170859456062317,
+      "step": 290
+    },
+    {
+      "epoch": 0.8488605287146764,
+      "grad_norm": 1.2041938304901123,
+      "learning_rate": 1.4309323236479071e-05,
+      "loss": 0.4359871745109558,
+      "step": 291
+    },
+    {
+      "epoch": 0.8517775752051049,
+      "grad_norm": 1.279645562171936,
+      "learning_rate": 1.4263320674214762e-05,
+      "loss": 0.45031386613845825,
+      "step": 292
+    },
+    {
+      "epoch": 0.8546946216955332,
+      "grad_norm": 1.3958357572555542,
+      "learning_rate": 1.4217207582889769e-05,
+      "loss": 0.4832204580307007,
+      "step": 293
+    },
+    {
+      "epoch": 0.8576116681859617,
+      "grad_norm": 1.2788586616516113,
+      "learning_rate": 1.4170985158012725e-05,
+      "loss": 0.5154346227645874,
+      "step": 294
+    },
+    {
+      "epoch": 0.8605287146763901,
+      "grad_norm": 1.3634892702102661,
+      "learning_rate": 1.4124654597926795e-05,
+      "loss": 0.46777206659317017,
+      "step": 295
+    },
+    {
+      "epoch": 0.8634457611668186,
+      "grad_norm": 1.2719579935073853,
+      "learning_rate": 1.4078217103778619e-05,
+      "loss": 0.4247053265571594,
+      "step": 296
+    },
+    {
+      "epoch": 0.866362807657247,
+      "grad_norm": 2.890467643737793,
+      "learning_rate": 1.4031673879487161e-05,
+      "loss": 0.38349640369415283,
+      "step": 297
+    },
+    {
+      "epoch": 0.8692798541476755,
+      "grad_norm": 2.4354801177978516,
+      "learning_rate": 1.3985026131712499e-05,
+      "loss": 0.4134889543056488,
+      "step": 298
+    },
+    {
+      "epoch": 0.872196900638104,
+      "grad_norm": 1.0138323307037354,
+      "learning_rate": 1.3938275069824541e-05,
+      "loss": 0.5176680684089661,
+      "step": 299
+    },
+    {
+      "epoch": 0.8751139471285324,
+      "grad_norm": 1.2316186428070068,
+      "learning_rate": 1.389142190587168e-05,
+      "loss": 0.4818477928638458,
+      "step": 300
+    },
+    {
+      "epoch": 0.8751139471285324,
+      "eval_loss": 0.4752846360206604,
+      "eval_runtime": 1189.1666,
+      "eval_samples_per_second": 0.531,
+      "eval_steps_per_second": 0.531,
+      "step": 300
+    },
+    {
+      "epoch": 0.8780309936189608,
+      "grad_norm": 1.515487551689148,
+      "learning_rate": 1.384446785454936e-05,
+      "loss": 0.47766175866127014,
+      "step": 301
+    },
+    {
+      "epoch": 0.8809480401093892,
+      "grad_norm": 1.4357497692108154,
+      "learning_rate": 1.3797414133168591e-05,
+      "loss": 0.49297061562538147,
+      "step": 302
+    },
+    {
+      "epoch": 0.8838650865998177,
+      "grad_norm": 1.2523037195205688,
+      "learning_rate": 1.3750261961624383e-05,
+      "loss": 0.4629015326499939,
+      "step": 303
+    },
+    {
+      "epoch": 0.8867821330902461,
+      "grad_norm": 3.5790023803710938,
+      "learning_rate": 1.3703012562364124e-05,
+      "loss": 0.3773120045661926,
+      "step": 304
+    },
+    {
+      "epoch": 0.8896991795806746,
+      "grad_norm": 1.9305704832077026,
+      "learning_rate": 1.3655667160355892e-05,
+      "loss": 0.496719628572464,
+      "step": 305
+    },
+    {
+      "epoch": 0.892616226071103,
+      "grad_norm": 1.1506154537200928,
+      "learning_rate": 1.3608226983056687e-05,
+      "loss": 0.49487072229385376,
+      "step": 306
+    },
+    {
+      "epoch": 0.8955332725615315,
+      "grad_norm": 1.8046090602874756,
+      "learning_rate": 1.3560693260380614e-05,
+      "loss": 0.4910697937011719,
+      "step": 307
+    },
+    {
+      "epoch": 0.8984503190519599,
+      "grad_norm": 2.0088653564453125,
+      "learning_rate": 1.3513067224667e-05,
+      "loss": 0.508246660232544,
+      "step": 308
+    },
+    {
+      "epoch": 0.9013673655423883,
+      "grad_norm": 1.2966033220291138,
+      "learning_rate": 1.3465350110648437e-05,
+      "loss": 0.5125166177749634,
+      "step": 309
+    },
+    {
+      "epoch": 0.9042844120328167,
+      "grad_norm": 1.9976309537887573,
+      "learning_rate": 1.3417543155418775e-05,
+      "loss": 0.43942537903785706,
+      "step": 310
+    },
+    {
+      "epoch": 0.9072014585232452,
+      "grad_norm": 1.2663682699203491,
+      "learning_rate": 1.336964759840105e-05,
+      "loss": 0.4839101731777191,
+      "step": 311
+    },
+    {
+      "epoch": 0.9101185050136736,
+      "grad_norm": 1.1223328113555908,
+      "learning_rate": 1.3321664681315354e-05,
+      "loss": 0.48008066415786743,
+      "step": 312
+    },
+    {
+      "epoch": 0.9130355515041021,
+      "grad_norm": 1.5786972045898438,
+      "learning_rate": 1.3273595648146634e-05,
+      "loss": 0.47250309586524963,
+      "step": 313
+    },
+    {
+      "epoch": 0.9159525979945305,
+      "grad_norm": 1.2150241136550903,
+      "learning_rate": 1.322544174511245e-05,
+      "loss": 0.5149738788604736,
+      "step": 314
+    },
+    {
+      "epoch": 0.918869644484959,
+      "grad_norm": 1.3676542043685913,
+      "learning_rate": 1.3177204220630662e-05,
+      "loss": 0.4430195093154907,
+      "step": 315
+    },
+    {
+      "epoch": 0.9217866909753875,
+      "grad_norm": 1.0703285932540894,
+      "learning_rate": 1.3128884325287064e-05,
+      "loss": 0.4798983037471771,
+      "step": 316
+    },
+    {
+      "epoch": 0.9247037374658159,
+      "grad_norm": 1.3131535053253174,
+      "learning_rate": 1.308048331180296e-05,
+      "loss": 0.4241073727607727,
+      "step": 317
+    },
+    {
+      "epoch": 0.9276207839562443,
+      "grad_norm": 1.4485348463058472,
+      "learning_rate": 1.3032002435002698e-05,
+      "loss": 0.527199923992157,
+      "step": 318
+    },
+    {
+      "epoch": 0.9305378304466727,
+      "grad_norm": 1.370936393737793,
+      "learning_rate": 1.2983442951781114e-05,
+      "loss": 0.47125962376594543,
+      "step": 319
+    },
+    {
+      "epoch": 0.9334548769371012,
+      "grad_norm": 1.2369643449783325,
+      "learning_rate": 1.2934806121070973e-05,
+      "loss": 0.4814244210720062,
+      "step": 320
+    },
+    {
+      "epoch": 0.9363719234275296,
+      "grad_norm": 1.2632933855056763,
+      "learning_rate": 1.2886093203810314e-05,
+      "loss": 0.4915548264980316,
+      "step": 321
+    },
+    {
+      "epoch": 0.9392889699179581,
+      "grad_norm": 1.054569959640503,
+      "learning_rate": 1.2837305462909764e-05,
+      "loss": 0.5325602293014526,
+      "step": 322
+    },
+    {
+      "epoch": 0.9422060164083865,
+      "grad_norm": 1.15959632396698,
+      "learning_rate": 1.27884441632198e-05,
+      "loss": 0.43607404828071594,
+      "step": 323
+    },
+    {
+      "epoch": 0.945123062898815,
+      "grad_norm": 1.1667979955673218,
+      "learning_rate": 1.2739510571497945e-05,
+      "loss": 0.4631507992744446,
+      "step": 324
+    },
+    {
+      "epoch": 0.9480401093892434,
+      "grad_norm": 1.6009081602096558,
+      "learning_rate": 1.2690505956375944e-05,
+      "loss": 0.4935731887817383,
+      "step": 325
+    },
+    {
+      "epoch": 0.9509571558796718,
+      "grad_norm": 1.1193996667861938,
+      "learning_rate": 1.2641431588326858e-05,
+      "loss": 0.45883435010910034,
+      "step": 326
+    },
+    {
+      "epoch": 0.9538742023701002,
+      "grad_norm": 1.5365067720413208,
+      "learning_rate": 1.2592288739632138e-05,
+      "loss": 0.5206276178359985,
+      "step": 327
+    },
+    {
+      "epoch": 0.9567912488605287,
+      "grad_norm": 1.0714622735977173,
+      "learning_rate": 1.2543078684348632e-05,
+      "loss": 0.5242853760719299,
+      "step": 328
+    },
+    {
+      "epoch": 0.9597082953509571,
+      "grad_norm": 1.3009248971939087,
+      "learning_rate": 1.2493802698275557e-05,
+      "loss": 0.4794357717037201,
+      "step": 329
+    },
+    {
+      "epoch": 0.9626253418413856,
+      "grad_norm": 1.495771050453186,
+      "learning_rate": 1.244446205892143e-05,
+      "loss": 0.5849282145500183,
+      "step": 330
+    },
+    {
+      "epoch": 0.965542388331814,
+      "grad_norm": 1.2046003341674805,
+      "learning_rate": 1.2395058045470935e-05,
+      "loss": 0.47758305072784424,
+      "step": 331
+    },
+    {
+      "epoch": 0.9684594348222425,
+      "grad_norm": 1.1362569332122803,
+      "learning_rate": 1.2345591938751772e-05,
+      "loss": 0.4490663409233093,
+      "step": 332
+    },
+    {
+      "epoch": 0.971376481312671,
+      "grad_norm": 1.2658129930496216,
+      "learning_rate": 1.2296065021201438e-05,
+      "loss": 0.4035309851169586,
+      "step": 333
+    },
+    {
+      "epoch": 0.9742935278030994,
+      "grad_norm": 4.370306015014648,
+      "learning_rate": 1.2246478576833993e-05,
+      "loss": 0.495273619890213,
+      "step": 334
+    },
+    {
+      "epoch": 0.9772105742935278,
+      "grad_norm": 1.3863654136657715,
+      "learning_rate": 1.219683389120676e-05,
+      "loss": 0.46410733461380005,
+      "step": 335
+    },
+    {
+      "epoch": 0.9801276207839562,
+      "grad_norm": 1.4544321298599243,
+      "learning_rate": 1.2147132251387004e-05,
+      "loss": 0.4301709830760956,
+      "step": 336
+    },
+    {
+      "epoch": 0.9830446672743847,
+      "grad_norm": 1.0852457284927368,
+      "learning_rate": 1.2097374945918554e-05,
+      "loss": 0.48892468214035034,
+      "step": 337
+    },
+    {
+      "epoch": 0.9859617137648131,
+      "grad_norm": 1.5062257051467896,
+      "learning_rate": 1.2047563264788412e-05,
+      "loss": 0.4667983055114746,
+      "step": 338
+    },
+    {
+      "epoch": 0.9888787602552416,
+      "grad_norm": 1.2472951412200928,
+      "learning_rate": 1.199769849939329e-05,
+      "loss": 0.4827345013618469,
+      "step": 339
+    },
+    {
+      "epoch": 0.99179580674567,
+      "grad_norm": 1.2589871883392334,
+      "learning_rate": 1.1947781942506151e-05,
+      "loss": 0.405245304107666,
+      "step": 340
+    },
+    {
+      "epoch": 0.9947128532360985,
+      "grad_norm": 1.25636625289917,
+      "learning_rate": 1.1897814888242679e-05,
+      "loss": 0.37956133484840393,
+      "step": 341
+    },
+    {
+      "epoch": 0.9976298997265269,
+      "grad_norm": 2.7064895629882812,
+      "learning_rate": 1.1847798632027726e-05,
+      "loss": 0.489456444978714,
+      "step": 342
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6156240701675415,
+      "learning_rate": 1.1797734470561744e-05,
+      "loss": 0.46473199129104614,
+      "step": 343
+    },
+    {
+      "epoch": 1.0029170464904285,
+      "grad_norm": 1.3046343326568604,
+      "learning_rate": 1.1747623701787143e-05,
+      "loss": 0.3504878282546997,
+      "step": 344
+    },
+    {
+      "epoch": 1.005834092980857,
+      "grad_norm": 1.414828896522522,
+      "learning_rate": 1.1697467624854666e-05,
+      "loss": 0.4719260334968567,
+      "step": 345
+    },
+    {
+      "epoch": 1.0087511394712854,
+      "grad_norm": 1.1873356103897095,
+      "learning_rate": 1.164726754008969e-05,
+      "loss": 0.45313555002212524,
+      "step": 346
+    },
+    {
+      "epoch": 1.0116681859617138,
+      "grad_norm": 1.1382380723953247,
+      "learning_rate": 1.1597024748958526e-05,
+      "loss": 0.4365478456020355,
+      "step": 347
+    },
+    {
+      "epoch": 1.0145852324521423,
+      "grad_norm": 1.8141961097717285,
+      "learning_rate": 1.1546740554034661e-05,
+      "loss": 0.3694503605365753,
+      "step": 348
+    },
+    {
+      "epoch": 1.0175022789425707,
+      "grad_norm": 1.333388328552246,
+      "learning_rate": 1.1496416258965015e-05,
+      "loss": 0.4755721688270569,
+      "step": 349
+    },
+    {
+      "epoch": 1.0204193254329992,
+      "grad_norm": 1.3464443683624268,
+      "learning_rate": 1.1446053168436117e-05,
+      "loss": 0.4227846562862396,
+      "step": 350
+    },
+    {
+      "epoch": 1.0204193254329992,
+      "eval_loss": 0.44924086332321167,
+      "eval_runtime": 1214.6648,
+      "eval_samples_per_second": 0.52,
+      "eval_steps_per_second": 0.52,
+      "step": 350
+    },
+    {
+      "epoch": 1.0233363719234276,
+      "grad_norm": 1.2682689428329468,
+      "learning_rate": 1.1395652588140292e-05,
+      "loss": 0.44300130009651184,
+      "step": 351
+    },
+    {
+      "epoch": 1.0262534184138559,
+      "grad_norm": 1.7737696170806885,
+      "learning_rate": 1.1345215824741814e-05,
+      "loss": 0.5106258988380432,
+      "step": 352
+    },
+    {
+      "epoch": 1.0291704649042843,
+      "grad_norm": 1.2601238489151,
+      "learning_rate": 1.1294744185843014e-05,
+      "loss": 0.45930635929107666,
+      "step": 353
+    },
+    {
+      "epoch": 1.0320875113947128,
+      "grad_norm": 1.2162678241729736,
+      "learning_rate": 1.1244238979950406e-05,
+      "loss": 0.44163084030151367,
+      "step": 354
+    },
+    {
+      "epoch": 1.0350045578851412,
+      "grad_norm": 1.0905817747116089,
+      "learning_rate": 1.1193701516440733e-05,
+      "loss": 0.510662317276001,
+      "step": 355
+    },
+    {
+      "epoch": 1.0379216043755697,
+      "grad_norm": 0.9624952673912048,
+      "learning_rate": 1.1143133105527048e-05,
+      "loss": 0.5297917127609253,
+      "step": 356
+    },
+    {
+      "epoch": 1.0408386508659981,
+      "grad_norm": 1.2757681608200073,
+      "learning_rate": 1.1092535058224725e-05,
+      "loss": 0.4332093596458435,
+      "step": 357
+    },
+    {
+      "epoch": 1.0437556973564266,
+      "grad_norm": 1.6885719299316406,
+      "learning_rate": 1.104190868631748e-05,
+      "loss": 0.4337635040283203,
+      "step": 358
+    },
+    {
+      "epoch": 1.046672743846855,
+      "grad_norm": 1.175484538078308,
+      "learning_rate": 1.099125530232336e-05,
+      "loss": 0.45411020517349243,
+      "step": 359
+    },
+    {
+      "epoch": 1.0495897903372835,
+      "grad_norm": 1.0964939594268799,
+      "learning_rate": 1.0940576219460723e-05,
+      "loss": 0.5333439707756042,
+      "step": 360
+    },
+    {
+      "epoch": 1.052506836827712,
+      "grad_norm": 1.5493136644363403,
+      "learning_rate": 1.0889872751614176e-05,
+      "loss": 0.4400906264781952,
+      "step": 361
+    },
+    {
+      "epoch": 1.0554238833181404,
+      "grad_norm": 1.2491416931152344,
+      "learning_rate": 1.0839146213300526e-05,
+      "loss": 0.31049978733062744,
+      "step": 362
+    },
+    {
+      "epoch": 1.0583409298085689,
+      "grad_norm": 1.7213693857192993,
+      "learning_rate": 1.0788397919634694e-05,
+      "loss": 0.389009028673172,
+      "step": 363
+    },
+    {
+      "epoch": 1.0612579762989973,
+      "grad_norm": 1.5405336618423462,
+      "learning_rate": 1.0737629186295621e-05,
+      "loss": 0.4068562984466553,
+      "step": 364
+    },
+    {
+      "epoch": 1.0641750227894258,
+      "grad_norm": 1.225455641746521,
+      "learning_rate": 1.0686841329492159e-05,
+      "loss": 0.47358617186546326,
+      "step": 365
+    },
+    {
+      "epoch": 1.0670920692798542,
+      "grad_norm": 1.3436250686645508,
+      "learning_rate": 1.0636035665928945e-05,
+      "loss": 0.47050854563713074,
+      "step": 366
+    },
+    {
+      "epoch": 1.0700091157702827,
+      "grad_norm": 1.4952112436294556,
+      "learning_rate": 1.058521351277227e-05,
+      "loss": 0.43496906757354736,
+      "step": 367
+    },
+    {
+      "epoch": 1.072926162260711,
+      "grad_norm": 1.549112319946289,
+      "learning_rate": 1.0534376187615924e-05,
+      "loss": 0.45711052417755127,
+      "step": 368
+    },
+    {
+      "epoch": 1.0758432087511394,
+      "grad_norm": 1.3851526975631714,
+      "learning_rate": 1.048352500844704e-05,
+      "loss": 0.45045915246009827,
+      "step": 369
+    },
+    {
+      "epoch": 1.0787602552415678,
+      "grad_norm": 1.6302049160003662,
+      "learning_rate": 1.0432661293611927e-05,
+      "loss": 0.3736046254634857,
+      "step": 370
+    },
+    {
+      "epoch": 1.0816773017319963,
+      "grad_norm": 1.3365869522094727,
+      "learning_rate": 1.0381786361781885e-05,
+      "loss": 0.42242100834846497,
+      "step": 371
+    },
+    {
+      "epoch": 1.0845943482224247,
+      "grad_norm": 1.4369138479232788,
+      "learning_rate": 1.0330901531919026e-05,
+      "loss": 0.44570961594581604,
+      "step": 372
+    },
+    {
+      "epoch": 1.0875113947128532,
+      "grad_norm": 1.3528283834457397,
+      "learning_rate": 1.0280008123242069e-05,
+      "loss": 0.43440738320350647,
+      "step": 373
+    },
+    {
+      "epoch": 1.0904284412032816,
+      "grad_norm": 1.469660997390747,
+      "learning_rate": 1.0229107455192147e-05,
+      "loss": 0.3960394263267517,
+      "step": 374
+    },
+    {
+      "epoch": 1.09334548769371,
+      "grad_norm": 1.4542185068130493,
+      "learning_rate": 1.0178200847398595e-05,
+      "loss": 0.47834208607673645,
+      "step": 375
+    },
+    {
+      "epoch": 1.0962625341841385,
+      "grad_norm": 1.6470292806625366,
+      "learning_rate": 1.0127289619644737e-05,
+      "loss": 0.42791086435317993,
+      "step": 376
+    },
+    {
+      "epoch": 1.099179580674567,
+      "grad_norm": 1.1934021711349487,
+      "learning_rate": 1.0076375091833681e-05,
+      "loss": 0.4401305019855499,
+      "step": 377
+    },
+    {
+      "epoch": 1.1020966271649955,
+      "grad_norm": 0.9786668419837952,
+      "learning_rate": 1.0025458583954078e-05,
+      "loss": 0.4816555678844452,
+      "step": 378
+    },
+    {
+      "epoch": 1.105013673655424,
+      "grad_norm": 1.1348779201507568,
+      "learning_rate": 9.974541416045924e-06,
+      "loss": 0.41516968607902527,
+      "step": 379
+    },
+    {
+      "epoch": 1.1079307201458524,
+      "grad_norm": 1.0188615322113037,
+      "learning_rate": 9.923624908166322e-06,
+      "loss": 0.48087278008461,
+      "step": 380
+    },
+    {
+      "epoch": 1.1108477666362808,
+      "grad_norm": 1.0821740627288818,
+      "learning_rate": 9.872710380355263e-06,
+      "loss": 0.41974008083343506,
+      "step": 381
+    },
+    {
+      "epoch": 1.1137648131267093,
+      "grad_norm": 1.250951886177063,
+      "learning_rate": 9.82179915260141e-06,
+      "loss": 0.42703643441200256,
+      "step": 382
+    },
+    {
+      "epoch": 1.1166818596171377,
+      "grad_norm": 1.4528254270553589,
+      "learning_rate": 9.770892544807856e-06,
+      "loss": 0.43801453709602356,
+      "step": 383
+    },
+    {
+      "epoch": 1.1195989061075662,
+      "grad_norm": 1.813859462738037,
+      "learning_rate": 9.719991876757934e-06,
+      "loss": 0.4344240725040436,
+      "step": 384
+    },
+    {
+      "epoch": 1.1225159525979946,
+      "grad_norm": 1.6681253910064697,
+      "learning_rate": 9.669098468080976e-06,
+      "loss": 0.4356998801231384,
+      "step": 385
+    },
+    {
+      "epoch": 1.125432999088423,
+      "grad_norm": 1.3447953462600708,
+      "learning_rate": 9.618213638218117e-06,
+      "loss": 0.43189188838005066,
+      "step": 386
+    },
+    {
+      "epoch": 1.1283500455788513,
+      "grad_norm": 1.9577926397323608,
+      "learning_rate": 9.567338706388074e-06,
+      "loss": 0.34984707832336426,
+      "step": 387
+    },
+    {
+      "epoch": 1.1312670920692798,
+      "grad_norm": 1.5225576162338257,
+      "learning_rate": 9.516474991552965e-06,
+      "loss": 0.4243963062763214,
+      "step": 388
+    },
+    {
+      "epoch": 1.1341841385597082,
+      "grad_norm": 1.7416809797286987,
+      "learning_rate": 9.46562381238408e-06,
+      "loss": 0.3414606750011444,
+      "step": 389
+    },
+    {
+      "epoch": 1.1371011850501367,
+      "grad_norm": 1.8358951807022095,
+      "learning_rate": 9.414786487227732e-06,
+      "loss": 0.387447327375412,
+      "step": 390
+    },
+    {
+      "epoch": 1.1400182315405651,
+      "grad_norm": 1.9706153869628906,
+      "learning_rate": 9.363964334071057e-06,
+      "loss": 0.4599088728427887,
+      "step": 391
+    },
+    {
+      "epoch": 1.1429352780309936,
+      "grad_norm": 1.0604286193847656,
+      "learning_rate": 9.313158670507843e-06,
+      "loss": 0.4633581042289734,
+      "step": 392
+    },
+    {
+      "epoch": 1.145852324521422,
+      "grad_norm": 1.4851202964782715,
+      "learning_rate": 9.262370813704379e-06,
+      "loss": 0.3872259557247162,
+      "step": 393
+    },
+    {
+      "epoch": 1.1487693710118505,
+      "grad_norm": 1.7839159965515137,
+      "learning_rate": 9.21160208036531e-06,
+      "loss": 0.5215944647789001,
+      "step": 394
+    },
+    {
+      "epoch": 1.151686417502279,
+      "grad_norm": 1.3054656982421875,
+      "learning_rate": 9.160853786699475e-06,
+      "loss": 0.4030425548553467,
+      "step": 395
+    },
+    {
+      "epoch": 1.1546034639927074,
+      "grad_norm": 3.8467981815338135,
+      "learning_rate": 9.110127248385827e-06,
+      "loss": 0.4032524824142456,
+      "step": 396
+    },
+    {
+      "epoch": 1.1575205104831359,
+      "grad_norm": 1.8513801097869873,
+      "learning_rate": 9.05942378053928e-06,
+      "loss": 0.46577155590057373,
+      "step": 397
+    },
+    {
+      "epoch": 1.1604375569735643,
+      "grad_norm": 1.312689185142517,
+      "learning_rate": 9.008744697676642e-06,
+      "loss": 0.39114487171173096,
+      "step": 398
+    },
+    {
+      "epoch": 1.1633546034639928,
+      "grad_norm": 1.1996328830718994,
+      "learning_rate": 8.958091313682521e-06,
+      "loss": 0.481199711561203,
+      "step": 399
+    },
+    {
+      "epoch": 1.1662716499544212,
+      "grad_norm": 5.172409534454346,
+      "learning_rate": 8.90746494177528e-06,
+      "loss": 0.3803558945655823,
+      "step": 400
+    },
+    {
+      "epoch": 1.1662716499544212,
+      "eval_loss": 0.4318464398384094,
+      "eval_runtime": 1206.0306,
+      "eval_samples_per_second": 0.524,
+      "eval_steps_per_second": 0.524,
+      "step": 400
+    },
+    {
+      "epoch": 1.1691886964448497,
+      "grad_norm": 1.0115015506744385,
+      "learning_rate": 8.856866894472954e-06,
+      "loss": 0.39636704325675964,
+      "step": 401
+    },
+    {
+      "epoch": 1.172105742935278,
+      "grad_norm": 1.1557435989379883,
+      "learning_rate": 8.806298483559268e-06,
+      "loss": 0.4076298475265503,
+      "step": 402
+    },
+    {
+      "epoch": 1.1750227894257064,
+      "grad_norm": 1.2802515029907227,
+      "learning_rate": 8.755761020049597e-06,
+      "loss": 0.44352248311042786,
+      "step": 403
+    },
+    {
+      "epoch": 1.1779398359161348,
+      "grad_norm": 1.2755069732666016,
+      "learning_rate": 8.705255814156988e-06,
+      "loss": 0.390497624874115,
+      "step": 404
+    },
+    {
+      "epoch": 1.1808568824065633,
+      "grad_norm": 1.2799782752990723,
+      "learning_rate": 8.654784175258188e-06,
+      "loss": 0.35810694098472595,
+      "step": 405
+    },
+    {
+      "epoch": 1.1837739288969917,
+      "grad_norm": 1.0968674421310425,
+      "learning_rate": 8.604347411859713e-06,
+      "loss": 0.3890265226364136,
+      "step": 406
+    },
+    {
+      "epoch": 1.1866909753874202,
+      "grad_norm": 1.3334455490112305,
+      "learning_rate": 8.553946831563886e-06,
+      "loss": 0.3916901648044586,
+      "step": 407
+    },
+    {
+      "epoch": 1.1896080218778486,
+      "grad_norm": 1.1888184547424316,
+      "learning_rate": 8.503583741034988e-06,
+      "loss": 0.5231326222419739,
+      "step": 408
+    },
+    {
+      "epoch": 1.192525068368277,
+      "grad_norm": 1.1163763999938965,
+      "learning_rate": 8.45325944596534e-06,
+      "loss": 0.4249858558177948,
+      "step": 409
+    },
+    {
+      "epoch": 1.1954421148587056,
+      "grad_norm": 1.3470333814620972,
+      "learning_rate": 8.40297525104148e-06,
+      "loss": 0.5201632380485535,
+      "step": 410
+    },
+    {
+      "epoch": 1.198359161349134,
+      "grad_norm": 1.5412285327911377,
+      "learning_rate": 8.35273245991031e-06,
+      "loss": 0.39376699924468994,
+      "step": 411
+    },
+    {
+      "epoch": 1.2012762078395625,
+      "grad_norm": 1.3408735990524292,
+      "learning_rate": 8.302532375145339e-06,
+      "loss": 0.39554283022880554,
+      "step": 412
+    },
+    {
+      "epoch": 1.204193254329991,
+      "grad_norm": 1.990668773651123,
+      "learning_rate": 8.25237629821286e-06,
+      "loss": 0.42424261569976807,
+      "step": 413
+    },
+    {
+      "epoch": 1.2071103008204194,
+      "grad_norm": 1.6471989154815674,
+      "learning_rate": 8.202265529438259e-06,
+      "loss": 0.3234582543373108,
+      "step": 414
+    },
+    {
+      "epoch": 1.2100273473108478,
+      "grad_norm": 1.1483631134033203,
+      "learning_rate": 8.152201367972275e-06,
+      "loss": 0.39163246750831604,
+      "step": 415
+    },
+    {
+      "epoch": 1.2129443938012763,
+      "grad_norm": 1.800149917602539,
+      "learning_rate": 8.102185111757323e-06,
+      "loss": 0.5055042505264282,
+      "step": 416
+    },
+    {
+      "epoch": 1.2158614402917047,
+      "grad_norm": 1.4394795894622803,
+      "learning_rate": 8.052218057493849e-06,
+      "loss": 0.4761751592159271,
+      "step": 417
+    },
+    {
+      "epoch": 1.2187784867821332,
+      "grad_norm": 1.622689962387085,
+      "learning_rate": 8.002301500606715e-06,
+      "loss": 0.4490141272544861,
+      "step": 418
+    },
+    {
+      "epoch": 1.2216955332725616,
+      "grad_norm": 1.2564961910247803,
+      "learning_rate": 7.952436735211593e-06,
+      "loss": 0.3964035212993622,
+      "step": 419
+    },
+    {
+      "epoch": 1.22461257976299,
+      "grad_norm": 1.3248411417007446,
+      "learning_rate": 7.902625054081449e-06,
+      "loss": 0.46039122343063354,
+      "step": 420
+    },
+    {
+      "epoch": 1.2275296262534183,
+      "grad_norm": 1.568983793258667,
+      "learning_rate": 7.852867748613e-06,
+      "loss": 0.49916595220565796,
+      "step": 421
+    },
+    {
+      "epoch": 1.2304466727438468,
+      "grad_norm": 1.4784491062164307,
+      "learning_rate": 7.803166108793243e-06,
+      "loss": 0.4035068154335022,
+      "step": 422
+    },
+    {
+      "epoch": 1.2333637192342752,
+      "grad_norm": 1.2940057516098022,
+      "learning_rate": 7.753521423166007e-06,
+      "loss": 0.4154140055179596,
+      "step": 423
+    },
+    {
+      "epoch": 1.2362807657247037,
+      "grad_norm": 1.167786717414856,
+      "learning_rate": 7.703934978798565e-06,
+      "loss": 0.39541637897491455,
+      "step": 424
+    },
+    {
+      "epoch": 1.2391978122151321,
+      "grad_norm": 1.5126771926879883,
+      "learning_rate": 7.65440806124823e-06,
+      "loss": 0.37744253873825073,
+      "step": 425
+    },
+    {
+      "epoch": 1.2421148587055606,
+      "grad_norm": 1.2595263719558716,
+      "learning_rate": 7.604941954529067e-06,
+      "loss": 0.46380615234375,
+      "step": 426
+    },
+    {
+      "epoch": 1.245031905195989,
+      "grad_norm": 1.4258298873901367,
+      "learning_rate": 7.555537941078573e-06,
+      "loss": 0.3391319513320923,
+      "step": 427
+    },
+    {
+      "epoch": 1.2479489516864175,
+      "grad_norm": 1.5371774435043335,
+      "learning_rate": 7.506197301724446e-06,
+      "loss": 0.39805102348327637,
+      "step": 428
+    },
+    {
+      "epoch": 1.250865998176846,
+      "grad_norm": 1.3789173364639282,
+      "learning_rate": 7.456921315651371e-06,
+      "loss": 0.37969034910202026,
+      "step": 429
+    },
+    {
+      "epoch": 1.2537830446672744,
+      "grad_norm": 1.32931649684906,
+      "learning_rate": 7.407711260367867e-06,
+      "loss": 0.3841526508331299,
+      "step": 430
+    },
+    {
+      "epoch": 1.2567000911577029,
+      "grad_norm": 1.2836817502975464,
+      "learning_rate": 7.358568411673145e-06,
+      "loss": 0.340289443731308,
+      "step": 431
+    },
+    {
+      "epoch": 1.2596171376481313,
+      "grad_norm": 1.0418318510055542,
+      "learning_rate": 7.309494043624059e-06,
+      "loss": 0.44747158885002136,
+      "step": 432
+    },
+    {
+      "epoch": 1.2625341841385598,
+      "grad_norm": 1.1769362688064575,
+      "learning_rate": 7.260489428502058e-06,
+      "loss": 0.45737382769584656,
+      "step": 433
+    },
+    {
+      "epoch": 1.265451230628988,
+      "grad_norm": 2.2730748653411865,
+      "learning_rate": 7.211555836780203e-06,
+      "loss": 0.3827931582927704,
+      "step": 434
+    },
+    {
+      "epoch": 1.2683682771194165,
+      "grad_norm": 1.263096809387207,
+      "learning_rate": 7.162694537090235e-06,
+      "loss": 0.3589435815811157,
+      "step": 435
+    },
+    {
+      "epoch": 1.271285323609845,
+      "grad_norm": 1.4073514938354492,
+      "learning_rate": 7.113906796189692e-06,
+      "loss": 0.45206642150878906,
+      "step": 436
+    },
+    {
+      "epoch": 1.2742023701002734,
+      "grad_norm": 1.064585566520691,
+      "learning_rate": 7.0651938789290306e-06,
+      "loss": 0.5409261584281921,
+      "step": 437
+    },
+    {
+      "epoch": 1.2771194165907018,
+      "grad_norm": 1.2346999645233154,
+      "learning_rate": 7.016557048218889e-06,
+      "loss": 0.40680158138275146,
+      "step": 438
+    },
+    {
+      "epoch": 1.2800364630811303,
+      "grad_norm": 1.5816547870635986,
+      "learning_rate": 6.967997564997306e-06,
+      "loss": 0.38718655705451965,
+      "step": 439
+    },
+    {
+      "epoch": 1.2829535095715587,
+      "grad_norm": 1.085268259048462,
+      "learning_rate": 6.919516688197041e-06,
+      "loss": 0.4863276779651642,
+      "step": 440
+    },
+    {
+      "epoch": 1.2858705560619872,
+      "grad_norm": 1.0984629392623901,
+      "learning_rate": 6.871115674712937e-06,
+      "loss": 0.39562875032424927,
+      "step": 441
+    },
+    {
+      "epoch": 1.2887876025524156,
+      "grad_norm": 1.3004229068756104,
+      "learning_rate": 6.822795779369339e-06,
+      "loss": 0.44437694549560547,
+      "step": 442
+    },
+    {
+      "epoch": 1.291704649042844,
+      "grad_norm": 1.3541183471679688,
+      "learning_rate": 6.774558254887553e-06,
+      "loss": 0.4728967249393463,
+      "step": 443
+    },
+    {
+      "epoch": 1.2946216955332726,
+      "grad_norm": 1.2485377788543701,
+      "learning_rate": 6.7264043518533695e-06,
+      "loss": 0.4052809476852417,
+      "step": 444
+    },
+    {
+      "epoch": 1.297538742023701,
+      "grad_norm": 1.412827730178833,
+      "learning_rate": 6.67833531868465e-06,
+      "loss": 0.40149861574172974,
+      "step": 445
+    },
+    {
+      "epoch": 1.3004557885141295,
+      "grad_norm": 1.5576224327087402,
+      "learning_rate": 6.630352401598953e-06,
+      "loss": 0.44107240438461304,
+      "step": 446
+    },
+    {
+      "epoch": 1.303372835004558,
+      "grad_norm": 1.1551047563552856,
+      "learning_rate": 6.582456844581226e-06,
+      "loss": 0.4898405969142914,
+      "step": 447
+    },
+    {
+      "epoch": 1.3062898814949864,
+      "grad_norm": 1.9939689636230469,
+      "learning_rate": 6.5346498893515645e-06,
+      "loss": 0.4791329801082611,
+      "step": 448
+    },
+    {
+      "epoch": 1.3092069279854148,
+      "grad_norm": 1.4782553911209106,
+      "learning_rate": 6.486932775333002e-06,
+      "loss": 0.472908616065979,
+      "step": 449
+    },
+    {
+      "epoch": 1.3121239744758433,
+      "grad_norm": 1.2496148347854614,
+      "learning_rate": 6.439306739619387e-06,
+      "loss": 0.514995276927948,
+      "step": 450
+    },
+    {
+      "epoch": 1.3121239744758433,
+      "eval_loss": 0.4178673028945923,
+      "eval_runtime": 1197.5534,
+      "eval_samples_per_second": 0.528,
+      "eval_steps_per_second": 0.528,
+      "step": 450
+    },
+    {
+      "epoch": 1.3150410209662717,
+      "grad_norm": 1.3996772766113281,
+      "learning_rate": 6.391773016943316e-06,
+      "loss": 0.4087896943092346,
+      "step": 451
+    },
+    {
+      "epoch": 1.3179580674567002,
+      "grad_norm": 1.20390784740448,
+      "learning_rate": 6.344332839644111e-06,
+      "loss": 0.43224579095840454,
+      "step": 452
+    },
+    {
+      "epoch": 1.3208751139471286,
+      "grad_norm": 1.2709496021270752,
+      "learning_rate": 6.296987437635876e-06,
+      "loss": 0.44104093313217163,
+      "step": 453
+    },
+    {
+      "epoch": 1.323792160437557,
+      "grad_norm": 1.0112334489822388,
+      "learning_rate": 6.249738038375618e-06,
+      "loss": 0.47084498405456543,
+      "step": 454
+    },
+    {
+      "epoch": 1.3267092069279856,
+      "grad_norm": 1.0771515369415283,
+      "learning_rate": 6.202585866831411e-06,
+      "loss": 0.4700928032398224,
+      "step": 455
+    },
+    {
+      "epoch": 1.3296262534184138,
+      "grad_norm": 1.4937143325805664,
+      "learning_rate": 6.15553214545064e-06,
+      "loss": 0.345747709274292,
+      "step": 456
+    },
+    {
+      "epoch": 1.3325432999088422,
+      "grad_norm": 1.1348456144332886,
+      "learning_rate": 6.108578094128321e-06,
+      "loss": 0.33824583888053894,
+      "step": 457
+    },
+    {
+      "epoch": 1.3354603463992707,
+      "grad_norm": 1.2502707242965698,
+      "learning_rate": 6.061724930175461e-06,
+      "loss": 0.3528832197189331,
+      "step": 458
+    },
+    {
+      "epoch": 1.3383773928896991,
+      "grad_norm": 1.5359619855880737,
+      "learning_rate": 6.014973868287504e-06,
+      "loss": 0.4413869082927704,
+      "step": 459
+    },
+    {
+      "epoch": 1.3412944393801276,
+      "grad_norm": 0.9747081398963928,
+      "learning_rate": 5.9683261205128395e-06,
+      "loss": 0.6849499940872192,
+      "step": 460
+    },
+    {
+      "epoch": 1.344211485870556,
+      "grad_norm": 1.3150533437728882,
+      "learning_rate": 5.921782896221383e-06,
+      "loss": 0.3901931047439575,
+      "step": 461
+    },
+    {
+      "epoch": 1.3471285323609845,
+      "grad_norm": 1.137770652770996,
+      "learning_rate": 5.875345402073207e-06,
+      "loss": 0.37498384714126587,
+      "step": 462
+    },
+    {
+      "epoch": 1.350045578851413,
+      "grad_norm": 1.2216367721557617,
+      "learning_rate": 5.829014841987277e-06,
+      "loss": 0.3874579966068268,
+      "step": 463
+    },
+    {
+      "epoch": 1.3529626253418414,
+      "grad_norm": 1.135439157485962,
+      "learning_rate": 5.782792417110233e-06,
+      "loss": 0.384797066450119,
+      "step": 464
+    },
+    {
+      "epoch": 1.3558796718322699,
+      "grad_norm": 1.2400696277618408,
+      "learning_rate": 5.736679325785239e-06,
+      "loss": 0.46303266286849976,
+      "step": 465
+    },
+    {
+      "epoch": 1.3587967183226983,
+      "grad_norm": 1.8848882913589478,
+      "learning_rate": 5.6906767635209304e-06,
+      "loss": 0.5068309903144836,
+      "step": 466
+    },
+    {
+      "epoch": 1.3617137648131268,
+      "grad_norm": 1.4707008600234985,
+      "learning_rate": 5.644785922960412e-06,
+      "loss": 0.364332914352417,
+      "step": 467
+    },
+    {
+      "epoch": 1.364630811303555,
+      "grad_norm": 2.4436841011047363,
+      "learning_rate": 5.599007993850329e-06,
+      "loss": 0.485107421875,
+      "step": 468
+    },
+    {
+      "epoch": 1.3675478577939835,
+      "grad_norm": 1.1924740076065063,
+      "learning_rate": 5.553344163010039e-06,
+      "loss": 0.34547489881515503,
+      "step": 469
+    },
+    {
+      "epoch": 1.370464904284412,
+      "grad_norm": 1.1255877017974854,
+      "learning_rate": 5.507795614300846e-06,
+      "loss": 0.39645254611968994,
+      "step": 470
+    },
+    {
+      "epoch": 1.3733819507748404,
+      "grad_norm": 1.0937018394470215,
+      "learning_rate": 5.4623635285952815e-06,
+      "loss": 0.4267856478691101,
+      "step": 471
+    },
+    {
+      "epoch": 1.3762989972652688,
+      "grad_norm": 1.3355520963668823,
+      "learning_rate": 5.417049083746513e-06,
+      "loss": 0.3669992983341217,
+      "step": 472
+    },
+    {
+      "epoch": 1.3792160437556973,
+      "grad_norm": 1.7302504777908325,
+      "learning_rate": 5.3718534545578035e-06,
+      "loss": 0.3873697519302368,
+      "step": 473
+    },
+    {
+      "epoch": 1.3821330902461257,
+      "grad_norm": 1.17263662815094,
+      "learning_rate": 5.326777812752041e-06,
+      "loss": 0.4581540524959564,
+      "step": 474
+    },
+    {
+      "epoch": 1.3850501367365542,
+      "grad_norm": 1.0998128652572632,
+      "learning_rate": 5.281823326941377e-06,
+      "loss": 0.43062761425971985,
+      "step": 475
+    },
+    {
+      "epoch": 1.3879671832269826,
+      "grad_norm": 1.1194556951522827,
+      "learning_rate": 5.236991162596932e-06,
+      "loss": 0.381741464138031,
+      "step": 476
+    },
+    {
+      "epoch": 1.390884229717411,
+      "grad_norm": 1.2759051322937012,
+      "learning_rate": 5.19228248201856e-06,
+      "loss": 0.49175748229026794,
+      "step": 477
+    },
+    {
+      "epoch": 1.3938012762078396,
+      "grad_norm": 1.2134747505187988,
+      "learning_rate": 5.147698444304732e-06,
+      "loss": 0.4997562766075134,
+      "step": 478
+    },
+    {
+      "epoch": 1.396718322698268,
+      "grad_norm": 1.0833078622817993,
+      "learning_rate": 5.1032402053224804e-06,
+      "loss": 0.42580488324165344,
+      "step": 479
+    },
+    {
+      "epoch": 1.3996353691886965,
+      "grad_norm": 1.4838510751724243,
+      "learning_rate": 5.058908917677426e-06,
+      "loss": 0.5015593767166138,
+      "step": 480
+    },
+    {
+      "epoch": 1.402552415679125,
+      "grad_norm": 1.218610167503357,
+      "learning_rate": 5.014705730683904e-06,
+      "loss": 0.34739193320274353,
+      "step": 481
+    },
+    {
+      "epoch": 1.4054694621695534,
+      "grad_norm": 1.1883307695388794,
+      "learning_rate": 4.970631790335181e-06,
+      "loss": 0.41708022356033325,
+      "step": 482
+    },
+    {
+      "epoch": 1.4083865086599818,
+      "grad_norm": 1.209291696548462,
+      "learning_rate": 4.926688239273713e-06,
+      "loss": 0.43546172976493835,
+      "step": 483
+    },
+    {
+      "epoch": 1.4113035551504103,
+      "grad_norm": 1.0801606178283691,
+      "learning_rate": 4.882876216761543e-06,
+      "loss": 0.44491735100746155,
+      "step": 484
+    },
+    {
+      "epoch": 1.4142206016408387,
+      "grad_norm": 1.2746628522872925,
+      "learning_rate": 4.839196858650763e-06,
+      "loss": 0.436122864484787,
+      "step": 485
+    },
+    {
+      "epoch": 1.4171376481312672,
+      "grad_norm": 1.4465962648391724,
+      "learning_rate": 4.795651297354056e-06,
+      "loss": 0.3750447630882263,
+      "step": 486
+    },
+    {
+      "epoch": 1.4200546946216956,
+      "grad_norm": 1.6736211776733398,
+      "learning_rate": 4.752240661815346e-06,
+      "loss": 0.38286519050598145,
+      "step": 487
+    },
+    {
+      "epoch": 1.422971741112124,
+      "grad_norm": 1.1946996450424194,
+      "learning_rate": 4.708966077480544e-06,
+      "loss": 0.4488063156604767,
+      "step": 488
+    },
+    {
+      "epoch": 1.4258887876025526,
+      "grad_norm": 1.42599356174469,
+      "learning_rate": 4.665828666268335e-06,
+      "loss": 0.44088613986968994,
+      "step": 489
+    },
+    {
+      "epoch": 1.4288058340929808,
+      "grad_norm": 1.2281016111373901,
+      "learning_rate": 4.622829546541121e-06,
+      "loss": 0.4030645489692688,
+      "step": 490
+    },
+    {
+      "epoch": 1.4317228805834092,
+      "grad_norm": 1.2875670194625854,
+      "learning_rate": 4.57996983307602e-06,
+      "loss": 0.44702020287513733,
+      "step": 491
+    },
+    {
+      "epoch": 1.4346399270738377,
+      "grad_norm": 1.2456860542297363,
+      "learning_rate": 4.537250637035947e-06,
+      "loss": 0.4067370593547821,
+      "step": 492
+    },
+    {
+      "epoch": 1.4375569735642661,
+      "grad_norm": 1.2822725772857666,
+      "learning_rate": 4.494673065940833e-06,
+      "loss": 0.4237740635871887,
+      "step": 493
+    },
+    {
+      "epoch": 1.4404740200546946,
+      "grad_norm": 1.5517818927764893,
+      "learning_rate": 4.452238223638906e-06,
+      "loss": 0.40579724311828613,
+      "step": 494
+    },
+    {
+      "epoch": 1.443391066545123,
+      "grad_norm": 1.275344967842102,
+      "learning_rate": 4.409947210278056e-06,
+      "loss": 0.38880717754364014,
+      "step": 495
+    },
+    {
+      "epoch": 1.4463081130355515,
+      "grad_norm": 1.22952139377594,
+      "learning_rate": 4.367801122277327e-06,
+      "loss": 0.4042310416698456,
+      "step": 496
+    },
+    {
+      "epoch": 1.44922515952598,
+      "grad_norm": 1.122261643409729,
+      "learning_rate": 4.325801052298493e-06,
+      "loss": 0.5408368110656738,
+      "step": 497
+    },
+    {
+      "epoch": 1.4521422060164084,
+      "grad_norm": 1.5885361433029175,
+      "learning_rate": 4.283948089217715e-06,
+      "loss": 0.37697717547416687,
+      "step": 498
+    },
+    {
+      "epoch": 1.4550592525068369,
+      "grad_norm": 2.3565149307250977,
+      "learning_rate": 4.242243318097338e-06,
+      "loss": 0.3811529576778412,
+      "step": 499
+    },
+    {
+      "epoch": 1.4579762989972653,
+      "grad_norm": 1.1944137811660767,
+      "learning_rate": 4.200687820157735e-06,
+      "loss": 0.414781391620636,
+      "step": 500
+    },
+    {
+      "epoch": 1.4579762989972653,
+      "eval_loss": 0.40706494450569153,
+      "eval_runtime": 1189.1593,
+      "eval_samples_per_second": 0.531,
+      "eval_steps_per_second": 0.531,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 686,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.6050925490932285e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

cpt_devstral_24B/checkpoints/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62526ec2433add7ac031c48b1f6ff360f1ade77275765112cbf7cf361d64ca5
+size 5201

cpt_devstral_24B/checkpoints/checkpoint-600/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/Models/Devstral-Small-2-24B-Instruct-2512
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/Models/Devstral-Small-2-24B-Instruct-2512
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

cpt_devstral_24B/checkpoints/checkpoint-600/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/Models/Devstral-Small-2-24B-Instruct-2512",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

cpt_devstral_24B/checkpoints/checkpoint-600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6528dd74de4fce9bff6c944acd9bc01868d155b1ea5403fe93fb8c5ced4d4ec
+size 364983848

cpt_devstral_24B/checkpoints/checkpoint-600/chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = '' %}
+
+{#- 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 %}

cpt_devstral_24B/checkpoints/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9b2e44d0ab7459e766b2b426fe5e300025849ada2eb46e1e2d89ca430a99f5
+size 160131559

cpt_devstral_24B/checkpoints/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225b67663a6b759f77f860fb03e0bd5eaf5759053344c810157aab3c54e1e986
+size 14645

cpt_devstral_24B/checkpoints/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3d2efb23ab02a563acff2988a53e730d4e5d08f3c1c39f1bd998cc5047ea45
+size 1465

cpt_devstral_24B/checkpoints/checkpoint-600/tokenizer.json

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

cpt_devstral_24B/checkpoints/checkpoint-600/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": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

cpt_devstral_24B/checkpoints/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62526ec2433add7ac031c48b1f6ff360f1ade77275765112cbf7cf361d64ca5
+size 5201

cpt_devstral_24B/checkpoints/checkpoint-686/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/Models/Devstral-Small-2-24B-Instruct-2512
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/Models/Devstral-Small-2-24B-Instruct-2512
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

cpt_devstral_24B/checkpoints/checkpoint-686/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/Models/Devstral-Small-2-24B-Instruct-2512",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

cpt_devstral_24B/checkpoints/checkpoint-686/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03251a15616d79fc9469a2a39740e675ba2e6c64b84f82511ff46a4917a1a103
+size 364983848

cpt_devstral_24B/checkpoints/checkpoint-686/chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = '' %}
+
+{#- 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 %}

cpt_devstral_24B/checkpoints/checkpoint-686/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f935371d01b010e5f58a9120e2561936056ae567db9fe04fb52a1b63061363
+size 160131559

cpt_devstral_24B/checkpoints/checkpoint-686/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e706874d7a72e865503ef7a4aaf06a0ded1324badabfab0b0223627edcf671a8
+size 14645

cpt_devstral_24B/checkpoints/checkpoint-686/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac75df5c8a3fb8b97098c85f14d52dc911b665df45efe2b05fbc8192aba4e49f
+size 1465

cpt_devstral_24B/checkpoints/checkpoint-686/tokenizer.json

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

cpt_devstral_24B/checkpoints/checkpoint-686/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": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}