stage2: epoch 2 (loss=2.0370)

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 stage1/latest/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+stage2/latest/tokenizer.json filter=lfs diff=lfs merge=lfs -text

stage2/latest/README.md

@@ -0,0 +1,207 @@
+---
+base_model: google/gemma-3-270m
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-270m
+- 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 0.18.1

stage2/latest/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-270m",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

stage2/latest/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ee785ca40224b5a7f353c56716356a8dfa79ddd84bdc39634d31d09c226a88
+size 4064208176

stage2/latest/added_tokens.json

@@ -0,0 +1,475 @@
+{
+  "<M0>": 262151,
+  "<M100>": 262152,
+  "<M101>": 262153,
+  "<M102>": 262154,
+  "<M103>": 262155,
+  "<M104>": 262156,
+  "<M105>": 262157,
+  "<M106>": 262158,
+  "<M107>": 262159,
+  "<M108>": 262160,
+  "<M109>": 262161,
+  "<M10>": 262162,
+  "<M110>": 262163,
+  "<M111>": 262164,
+  "<M112>": 262165,
+  "<M113>": 262166,
+  "<M114>": 262167,
+  "<M115>": 262168,
+  "<M116>": 262169,
+  "<M117>": 262170,
+  "<M118>": 262171,
+  "<M119>": 262172,
+  "<M11>": 262173,
+  "<M120>": 262174,
+  "<M121>": 262175,
+  "<M122>": 262176,
+  "<M123>": 262177,
+  "<M124>": 262178,
+  "<M125>": 262179,
+  "<M126>": 262180,
+  "<M127>": 262181,
+  "<M128>": 262182,
+  "<M129>": 262183,
+  "<M12>": 262184,
+  "<M130>": 262185,
+  "<M131>": 262186,
+  "<M132>": 262187,
+  "<M133>": 262188,
+  "<M134>": 262189,
+  "<M135>": 262190,
+  "<M136>": 262191,
+  "<M137>": 262192,
+  "<M138>": 262193,
+  "<M139>": 262194,
+  "<M13>": 262195,
+  "<M140>": 262196,
+  "<M141>": 262197,
+  "<M142>": 262198,
+  "<M143>": 262199,
+  "<M144>": 262200,
+  "<M145>": 262201,
+  "<M146>": 262202,
+  "<M147>": 262203,
+  "<M148>": 262204,
+  "<M149>": 262205,
+  "<M14>": 262206,
+  "<M150>": 262207,
+  "<M151>": 262208,
+  "<M152>": 262209,
+  "<M153>": 262210,
+  "<M154>": 262211,
+  "<M155>": 262212,
+  "<M156>": 262213,
+  "<M157>": 262214,
+  "<M158>": 262215,
+  "<M159>": 262216,
+  "<M15>": 262217,
+  "<M160>": 262218,
+  "<M161>": 262219,
+  "<M162>": 262220,
+  "<M163>": 262221,
+  "<M164>": 262222,
+  "<M165>": 262223,
+  "<M166>": 262224,
+  "<M167>": 262225,
+  "<M168>": 262226,
+  "<M169>": 262227,
+  "<M16>": 262228,
+  "<M170>": 262229,
+  "<M171>": 262230,
+  "<M172>": 262231,
+  "<M173>": 262232,
+  "<M174>": 262233,
+  "<M175>": 262234,
+  "<M176>": 262235,
+  "<M177>": 262236,
+  "<M178>": 262237,
+  "<M179>": 262238,
+  "<M17>": 262239,
+  "<M180>": 262240,
+  "<M181>": 262241,
+  "<M182>": 262242,
+  "<M183>": 262243,
+  "<M184>": 262244,
+  "<M185>": 262245,
+  "<M186>": 262246,
+  "<M187>": 262247,
+  "<M188>": 262248,
+  "<M18>": 262249,
+  "<M190>": 262250,
+  "<M191>": 262251,
+  "<M192>": 262252,
+  "<M194>": 262253,
+  "<M196>": 262254,
+  "<M197>": 262255,
+  "<M198>": 262256,
+  "<M199>": 262257,
+  "<M19>": 262258,
+  "<M1>": 262259,
+  "<M200>": 262260,
+  "<M205>": 262261,
+  "<M206>": 262262,
+  "<M207>": 262263,
+  "<M208>": 262264,
+  "<M209>": 262265,
+  "<M20>": 262266,
+  "<M210>": 262267,
+  "<M211>": 262268,
+  "<M212>": 262269,
+  "<M213>": 262270,
+  "<M214>": 262271,
+  "<M215>": 262272,
+  "<M216>": 262273,
+  "<M217>": 262274,
+  "<M218>": 262275,
+  "<M219>": 262276,
+  "<M21>": 262277,
+  "<M220>": 262278,
+  "<M221>": 262279,
+  "<M222>": 262280,
+  "<M223>": 262281,
+  "<M224>": 262282,
+  "<M225>": 262283,
+  "<M226>": 262284,
+  "<M227>": 262285,
+  "<M228>": 262286,
+  "<M229>": 262287,
+  "<M22>": 262288,
+  "<M230>": 262289,
+  "<M231>": 262290,
+  "<M232>": 262291,
+  "<M233>": 262292,
+  "<M234>": 262293,
+  "<M235>": 262294,
+  "<M236>": 262295,
+  "<M238>": 262296,
+  "<M239>": 262297,
+  "<M23>": 262298,
+  "<M240>": 262299,
+  "<M241>": 262300,
+  "<M242>": 262301,
+  "<M243>": 262302,
+  "<M244>": 262303,
+  "<M245>": 262304,
+  "<M246>": 262305,
+  "<M247>": 262306,
+  "<M248>": 262307,
+  "<M24>": 262308,
+  "<M250>": 262309,
+  "<M252>": 262310,
+  "<M254>": 262311,
+  "<M256>": 262312,
+  "<M257>": 262313,
+  "<M258>": 262314,
+  "<M259>": 262315,
+  "<M25>": 262316,
+  "<M260>": 262317,
+  "<M261>": 262318,
+  "<M262>": 262319,
+  "<M263>": 262320,
+  "<M264>": 262321,
+  "<M265>": 262322,
+  "<M266>": 262323,
+  "<M267>": 262324,
+  "<M268>": 262325,
+  "<M269>": 262326,
+  "<M26>": 262327,
+  "<M270>": 262328,
+  "<M271>": 262329,
+  "<M272>": 262330,
+  "<M273>": 262331,
+  "<M274>": 262332,
+  "<M275>": 262333,
+  "<M276>": 262334,
+  "<M277>": 262335,
+  "<M278>": 262336,
+  "<M27>": 262337,
+  "<M280>": 262338,
+  "<M282>": 262339,
+  "<M283>": 262340,
+  "<M284>": 262341,
+  "<M285>": 262342,
+  "<M286>": 262343,
+  "<M287>": 262344,
+  "<M289>": 262345,
+  "<M28>": 262346,
+  "<M290>": 262347,
+  "<M291>": 262348,
+  "<M292>": 262349,
+  "<M293>": 262350,
+  "<M295>": 262351,
+  "<M296>": 262352,
+  "<M297>": 262353,
+  "<M298>": 262354,
+  "<M29>": 262355,
+  "<M2>": 262356,
+  "<M300>": 262357,
+  "<M303>": 262358,
+  "<M304>": 262359,
+  "<M306>": 262360,
+  "<M307>": 262361,
+  "<M308>": 262362,
+  "<M309>": 262363,
+  "<M30>": 262364,
+  "<M310>": 262365,
+  "<M311>": 262366,
+  "<M312>": 262367,
+  "<M313>": 262368,
+  "<M315>": 262369,
+  "<M316>": 262370,
+  "<M317>": 262371,
+  "<M318>": 262372,
+  "<M319>": 262373,
+  "<M31>": 262374,
+  "<M320>": 262375,
+  "<M321>": 262376,
+  "<M322>": 262377,
+  "<M323>": 262378,
+  "<M324>": 262379,
+  "<M325>": 262380,
+  "<M326>": 262381,
+  "<M327>": 262382,
+  "<M328>": 262383,
+  "<M329>": 262384,
+  "<M32>": 262385,
+  "<M330>": 262386,
+  "<M332>": 262387,
+  "<M333>": 262388,
+  "<M334>": 262389,
+  "<M335>": 262390,
+  "<M336>": 262391,
+  "<M337>": 262392,
+  "<M338>": 262393,
+  "<M33>": 262394,
+  "<M342>": 262395,
+  "<M343>": 262396,
+  "<M345>": 262397,
+  "<M346>": 262398,
+  "<M347>": 262399,
+  "<M348>": 262400,
+  "<M349>": 262401,
+  "<M34>": 262402,
+  "<M350>": 262403,
+  "<M351>": 262404,
+  "<M352>": 262405,
+  "<M353>": 262406,
+  "<M354>": 262407,
+  "<M355>": 262408,
+  "<M356>": 262409,
+  "<M357>": 262410,
+  "<M359>": 262411,
+  "<M35>": 262412,
+  "<M360>": 262413,
+  "<M362>": 262414,
+  "<M363>": 262415,
+  "<M364>": 262416,
+  "<M365>": 262417,
+  "<M366>": 262418,
+  "<M367>": 262419,
+  "<M368>": 262420,
+  "<M369>": 262421,
+  "<M36>": 262422,
+  "<M370>": 262423,
+  "<M371>": 262424,
+  "<M372>": 262425,
+  "<M373>": 262426,
+  "<M374>": 262427,
+  "<M375>": 262428,
+  "<M376>": 262429,
+  "<M378>": 262430,
+  "<M379>": 262431,
+  "<M37>": 262432,
+  "<M380>": 262433,
+  "<M381>": 262434,
+  "<M382>": 262435,
+  "<M383>": 262436,
+  "<M384>": 262437,
+  "<M385>": 262438,
+  "<M386>": 262439,
+  "<M387>": 262440,
+  "<M388>": 262441,
+  "<M389>": 262442,
+  "<M38>": 262443,
+  "<M390>": 262444,
+  "<M391>": 262445,
+  "<M392>": 262446,
+  "<M393>": 262447,
+  "<M395>": 262448,
+  "<M396>": 262449,
+  "<M398>": 262450,
+  "<M39>": 262451,
+  "<M3>": 262452,
+  "<M402>": 262453,
+  "<M403>": 262454,
+  "<M404>": 262455,
+  "<M405>": 262456,
+  "<M406>": 262457,
+  "<M408>": 262458,
+  "<M409>": 262459,
+  "<M40>": 262460,
+  "<M410>": 262461,
+  "<M411>": 262462,
+  "<M412>": 262463,
+  "<M413>": 262464,
+  "<M414>": 262465,
+  "<M416>": 262466,
+  "<M418>": 262467,
+  "<M419>": 262468,
+  "<M41>": 262469,
+  "<M421>": 262470,
+  "<M422>": 262471,
+  "<M423>": 262472,
+  "<M424>": 262473,
+  "<M426>": 262474,
+  "<M427>": 262475,
+  "<M428>": 262476,
+  "<M429>": 262477,
+  "<M42>": 262478,
+  "<M430>": 262479,
+  "<M431>": 262480,
+  "<M432>": 262481,
+  "<M433>": 262482,
+  "<M434>": 262483,
+  "<M435>": 262484,
+  "<M436>": 262485,
+  "<M437>": 262486,
+  "<M438>": 262487,
+  "<M439>": 262488,
+  "<M43>": 262489,
+  "<M440>": 262490,
+  "<M441>": 262491,
+  "<M442>": 262492,
+  "<M443>": 262493,
+  "<M444>": 262494,
+  "<M445>": 262495,
+  "<M446>": 262496,
+  "<M447>": 262497,
+  "<M448>": 262498,
+  "<M449>": 262499,
+  "<M44>": 262500,
+  "<M450>": 262501,
+  "<M451>": 262502,
+  "<M452>": 262503,
+  "<M454>": 262504,
+  "<M455>": 262505,
+  "<M456>": 262506,
+  "<M457>": 262507,
+  "<M458>": 262508,
+  "<M459>": 262509,
+  "<M45>": 262510,
+  "<M460>": 262511,
+  "<M461>": 262512,
+  "<M462>": 262513,
+  "<M463>": 262514,
+  "<M464>": 262515,
+  "<M465>": 262516,
+  "<M466>": 262517,
+  "<M467>": 262518,
+  "<M468>": 262519,
+  "<M469>": 262520,
+  "<M46>": 262521,
+  "<M470>": 262522,
+  "<M471>": 262523,
+  "<M472>": 262524,
+  "<M473>": 262525,
+  "<M474>": 262526,
+  "<M475>": 262527,
+  "<M477>": 262528,
+  "<M479>": 262529,
+  "<M47>": 262530,
+  "<M481>": 262531,
+  "<M483>": 262532,
+  "<M484>": 262533,
+  "<M485>": 262534,
+  "<M487>": 262535,
+  "<M489>": 262536,
+  "<M48>": 262537,
+  "<M490>": 262538,
+  "<M491>": 262539,
+  "<M492>": 262540,
+  "<M493>": 262541,
+  "<M494>": 262542,
+  "<M495>": 262543,
+  "<M496>": 262544,
+  "<M497>": 262545,
+  "<M498>": 262546,
+  "<M499>": 262547,
+  "<M49>": 262548,
+  "<M4>": 262549,
+  "<M500>": 262550,
+  "<M501>": 262551,
+  "<M502>": 262552,
+  "<M503>": 262553,
+  "<M504>": 262554,
+  "<M505>": 262555,
+  "<M506>": 262556,
+  "<M507>": 262557,
+  "<M508>": 262558,
+  "<M509>": 262559,
+  "<M50>": 262560,
+  "<M510>": 262561,
+  "<M511>": 262562,
+  "<M51>": 262563,
+  "<M52>": 262564,
+  "<M53>": 262565,
+  "<M54>": 262566,
+  "<M55>": 262567,
+  "<M56>": 262568,
+  "<M57>": 262569,
+  "<M58>": 262570,
+  "<M59>": 262571,
+  "<M5>": 262572,
+  "<M60>": 262573,
+  "<M61>": 262574,
+  "<M62>": 262575,
+  "<M63>": 262576,
+  "<M64>": 262577,
+  "<M65>": 262578,
+  "<M66>": 262579,
+  "<M67>": 262580,
+  "<M68>": 262581,
+  "<M69>": 262582,
+  "<M6>": 262583,
+  "<M70>": 262584,
+  "<M71>": 262585,
+  "<M72>": 262586,
+  "<M73>": 262587,
+  "<M74>": 262588,
+  "<M75>": 262589,
+  "<M76>": 262590,
+  "<M77>": 262591,
+  "<M78>": 262592,
+  "<M79>": 262593,
+  "<M7>": 262594,
+  "<M80>": 262595,
+  "<M81>": 262596,
+  "<M82>": 262597,
+  "<M83>": 262598,
+  "<M84>": 262599,
+  "<M85>": 262600,
+  "<M86>": 262601,
+  "<M87>": 262602,
+  "<M88>": 262603,
+  "<M89>": 262604,
+  "<M8>": 262605,
+  "<M90>": 262606,
+  "<M91>": 262607,
+  "<M92>": 262608,
+  "<M93>": 262609,
+  "<M94>": 262610,
+  "<M95>": 262611,
+  "<M96>": 262612,
+  "<M97>": 262613,
+  "<M98>": 262614,
+  "<M99>": 262615,
+  "<M9>": 262616,
+  "<M_END>": 262147,
+  "<M_START>": 262146,
+  "<PAD>": 262145,
+  "<image_soft_token>": 262144,
+  "<|LEN_LONG|>": 262150,
+  "<|LEN_MEDIUM|>": 262149,
+  "<|LEN_SHORT|>": 262148
+}

stage2/latest/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c04f171d6ef0c3776cef4b38adc696581d6ce71dc755f4d652e72a30671c83
+size 2750164363

stage2/latest/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14b2e65070f75934c887817130bc50c3234b38f2e0b24c590a932a3f3836f32
+size 1593

stage2/latest/special_tokens_map.json

@@ -0,0 +1,70 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<M_START>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<M_END>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|LEN_SHORT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|LEN_MEDIUM|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|LEN_LONG|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

stage2/latest/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31abc1ffa28ad72cf54cf10c4225248b4e31d402da9f11b58e061a24d941f7da
+size 33470858

stage2/latest/tokenizer.model

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

stage2/latest/training_state.json

@@ -0,0 +1,10 @@
+{
+  "stage": "stage2",
+  "epoch_completed": 2,
+  "total_epochs": 30,
+  "avg_loss": 2.036984529169244,
+  "global_step": 1512,
+  "saved_at": "2026-02-10T23:12:59.105976Z",
+  "is_lora": true,
+  "base_model": "google/gemma-3-270m"
+}