Add files using upload-large-folder tool

.gitattributes

@@ -87,3 +87,14 @@ checkpoint-5050/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-5300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-6150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3850/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4050/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3150/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1900/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6f9e7fd634ca8eb2ce23b87dd5a633ef3856a5f9fff488f0703259d4d7eed8
+size 52231312

checkpoint-1900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3714f2e722cd2d96cffc829281a4b408638587be21211e3932d7f75e507ad3
+size 27860634

checkpoint-1900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+size 14244

checkpoint-1900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35624ee31f85b4a7572539bdf34ac172426fb9adc03c8acf79ddc01209916e91
+size 1064

checkpoint-1900/tokenizer.json

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

checkpoint-1900/tokenizer.model

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

checkpoint-1900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a005f970f4cec3bcd1f966ef18d4a684fb77d0ec7f69f10a53aafcf21569519
+size 5752

checkpoint-2050/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-2050/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2050/added_tokens.json

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

checkpoint-2050/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

checkpoint-2050/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2050/trainer_state.json

@@ -0,0 +1,361 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3217218918153497,
+  "eval_steps": 354,
+  "global_step": 2050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7603653073310852,
+      "learning_rate": 0.0001978110599078341,
+      "loss": 0.9425,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.6873273849487305,
+      "learning_rate": 0.00019205069124423964,
+      "loss": 0.6078,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6323167085647583,
+      "learning_rate": 0.00018629032258064517,
+      "loss": 0.6748,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 1.0095610618591309,
+      "learning_rate": 0.0001805299539170507,
+      "loss": 0.6594,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.5822212100028992,
+      "learning_rate": 0.00017476958525345623,
+      "loss": 0.6317,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.8490907549858093,
+      "learning_rate": 0.00016900921658986176,
+      "loss": 0.5742,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.6252707242965698,
+      "learning_rate": 0.0001632488479262673,
+      "loss": 0.5502,
+      "step": 350
+    },
+    {
+      "epoch": 0.4010195412064571,
+      "eval_loss": 0.6019027233123779,
+      "eval_runtime": 159.9351,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 2.457,
+      "step": 354
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.656812310218811,
+      "learning_rate": 0.00015748847926267282,
+      "loss": 0.5686,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.7391073703765869,
+      "learning_rate": 0.00015172811059907835,
+      "loss": 0.5701,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.9210707545280457,
+      "learning_rate": 0.00014596774193548388,
+      "loss": 0.6397,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8228403329849243,
+      "learning_rate": 0.00014020737327188939,
+      "loss": 0.5822,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.716748833656311,
+      "learning_rate": 0.00013444700460829494,
+      "loss": 0.5881,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.7144941091537476,
+      "learning_rate": 0.00012868663594470047,
+      "loss": 0.6032,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.016291618347168,
+      "learning_rate": 0.000122926267281106,
+      "loss": 0.6377,
+      "step": 700
+    },
+    {
+      "epoch": 0.8020390824129142,
+      "eval_loss": 0.5828524827957153,
+      "eval_runtime": 150.8754,
+      "eval_samples_per_second": 10.399,
+      "eval_steps_per_second": 2.605,
+      "step": 708
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.0243154764175415,
+      "learning_rate": 0.00011716589861751153,
+      "loss": 0.6005,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6541144251823425,
+      "learning_rate": 0.00011140552995391706,
+      "loss": 0.5723,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 1.0017038583755493,
+      "learning_rate": 0.00010564516129032258,
+      "loss": 0.5801,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.7527189254760742,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5511,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.7966899871826172,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.49,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7110822796821594,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4725,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.7837777733802795,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.527,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2027754177286887,
+      "eval_loss": 0.5833637714385986,
+      "eval_runtime": 150.6223,
+      "eval_samples_per_second": 10.417,
+      "eval_steps_per_second": 2.609,
+      "step": 1062
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 0.8119267821311951,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.4892,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 0.8631129860877991,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.5124,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 0.8685782551765442,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.4927,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 0.8397710919380188,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.5125,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 0.7606781721115112,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.4826,
+      "step": 1300
+    },
+    {
+      "epoch": 1.529028603794959,
+      "grad_norm": 1.1354798078536987,
+      "learning_rate": 4.8041474654377885e-05,
+      "loss": 0.5101,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "grad_norm": 1.28499174118042,
+      "learning_rate": 4.228110599078341e-05,
+      "loss": 0.4687,
+      "step": 1400
+    },
+    {
+      "epoch": 1.603794958935146,
+      "eval_loss": 0.5791710615158081,
+      "eval_runtime": 150.7437,
+      "eval_samples_per_second": 10.408,
+      "eval_steps_per_second": 2.607,
+      "step": 1416
+    },
+    {
+      "epoch": 1.6423109600679693,
+      "grad_norm": 0.7527874708175659,
+      "learning_rate": 3.6520737327188945e-05,
+      "loss": 0.4992,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6989521382044748,
+      "grad_norm": 0.9351261854171753,
+      "learning_rate": 3.076036866359447e-05,
+      "loss": 0.4873,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7555933163409798,
+      "grad_norm": 1.0196998119354248,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4946,
+      "step": 1550
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 0.9896508455276489,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.4895,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.150964617729187,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.5164,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 0.8384917378425598,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.4914,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 0.9231545329093933,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.4939,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0045312942509206,
+      "eval_loss": 0.5844214558601379,
+      "eval_runtime": 166.1298,
+      "eval_samples_per_second": 9.444,
+      "eval_steps_per_second": 2.366,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 0.9673134088516235,
+      "learning_rate": 0.00014248089741505446,
+      "loss": 0.4303,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.33237624168396,
+      "learning_rate": 0.00014085514550479596,
+      "loss": 0.4594,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.068943738937378,
+      "learning_rate": 0.0001392293935945375,
+      "loss": 0.4939,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.1625093221664429,
+      "learning_rate": 0.00013760364168427899,
+      "loss": 0.4757,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.080735683441162,
+      "learning_rate": 0.00013597788977402048,
+      "loss": 0.4724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 0.8823259472846985,
+      "learning_rate": 0.00013435213786376198,
+      "loss": 0.4821,
+      "step": 2050
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6181,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.92296336690537e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a820842b48f3b7f8c78f118e39b7eaa6ecb9d42a8b2594c306df211bb260a3
+size 52231312

checkpoint-2100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e8182d60aceed6c97a951bfe8fcd0a63f5da8c089add23013c5a8288736c0c
+size 27860634

checkpoint-2100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+size 14244

checkpoint-2100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb377410c6d098725a6e5e1c6950b3438960e7ebaa8cc1054e14b100f0c3f25
+size 1064

checkpoint-2100/tokenizer.json

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

checkpoint-2100/tokenizer.model

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

checkpoint-2100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a005f970f4cec3bcd1f966ef18d4a684fb77d0ec7f69f10a53aafcf21569519
+size 5752

checkpoint-2550/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ec0766d9e50dcd221780f432b17b2b29e25a322310e213597d0215f114de10
+size 52231312

checkpoint-2550/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab4cae5f209a63be348e99a5c336c9a613d03f1306bea998eccfa3ada5a8c98
+size 27860634

checkpoint-2550/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
+size 14244

checkpoint-2550/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3043add50df0d2aba563d94131b01ab82490cd24503ba71791143b45079fdf01
+size 1064

checkpoint-2550/tokenizer.json

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

checkpoint-2550/tokenizer.model

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

checkpoint-2550/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a005f970f4cec3bcd1f966ef18d4a684fb77d0ec7f69f10a53aafcf21569519
+size 5752

checkpoint-2600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a123f5a01649fa4c96058569993be446a2807c3ec9ed041af4e9215830f3a60
+size 52231312

checkpoint-2600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ae003f80dc450cb184a102bde16d84e6f23f1b5294e96af60921afc52837a6
+size 27860634

checkpoint-2600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
+size 14244

checkpoint-2600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4aab84eb929630322f3915b87f90f30fe29db908df50eacaabfcf4e5909026
+size 1064

checkpoint-2600/tokenizer.json

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

checkpoint-2600/tokenizer.model

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

checkpoint-2600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a005f970f4cec3bcd1f966ef18d4a684fb77d0ec7f69f10a53aafcf21569519
+size 5752

checkpoint-3150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf63b7baf65c145b82da91023f7f2c9e81399a5cff367cb7d917d8836b1a5e3
+size 27860634

checkpoint-3150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e5d946241df2516b06d7074d8779088eae7607173ad780df56583910a9589b
+size 14244

checkpoint-3150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addd861e9a63ab785a621558135586810bfb22e5e8069d6c4da214da1a23f76d
+size 1064

checkpoint-3150/tokenizer.json

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

checkpoint-3150/tokenizer.model

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

checkpoint-3150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a005f970f4cec3bcd1f966ef18d4a684fb77d0ec7f69f10a53aafcf21569519
+size 5752

checkpoint-3450/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3450/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

checkpoint-3450/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-3500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6d341b9146c14f8201cf294bf326d6f33d7b146b4126fde1fac9fcef0042ba
+size 52231312

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4457039c8545adc1dc19588862b3f68cab2ee2bbbf76f29fff37729f372dc8
+size 27860634

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7682299c566684ea51cf26f0c86b6ffaa3c0bc63cbdf84674b29a2c62ac72143
+size 14244

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbdf792e8fbc0681ae85ed476767ec9435e8cc7f6e0992b40acd89401f3a1f4
+size 1064

checkpoint-3500/tokenizer.json

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