Rename folder

.gitattributes

@@ -67,3 +67,4 @@ checkpoint-3100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-3254/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+old-cp-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text

old-cp-1300/README.md

@@ -0,0 +1,209 @@
+---
+base_model: google/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-1b-it
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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

old-cp-1300/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-3-1b-it",
+  "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": 48,
+  "lora_bias": false,
+  "lora_dropout": 0.02,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 24,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

old-cp-1300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee57f11a5766541c71baaddf74a1a8b91c5d59d9aa94fe9b2818c5f1edea067
+size 2494243760

old-cp-1300/added_tokens.json

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

old-cp-1300/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 -%}

old-cp-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfc85fbc48ef0890653fc8af89805c5131f8f7721174742af63315fe046ef4c
+size 4988685133

old-cp-1300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee9612c1c3082569f57a7924bf66f479b863fb65d599991901e8f0be0662d82
+size 14455

old-cp-1300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46806977068e5794521bf16c63b92eae867bfa32a464e1f31f137f5d33dc6907
+size 1465

old-cp-1300/special_tokens_map.json

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

old-cp-1300/tokenizer.json

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

old-cp-1300/tokenizer.model

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

old-cp-1300/trainer_state.json

@@ -0,0 +1,307 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7990165949600492,
+  "eval_steps": 100,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.3584375,
+      "epoch": 0.06146281499692686,
+      "grad_norm": 1.859375,
+      "learning_rate": 0.0002,
+      "loss": 1.41,
+      "mean_token_accuracy": 0.58572265625,
+      "num_tokens": 98685.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.06146281499692686,
+      "eval_entropy": 1.2765668162983426,
+      "eval_loss": 1.2490719556808472,
+      "eval_mean_token_accuracy": 0.6143387430939227,
+      "eval_num_tokens": 98685.0,
+      "eval_runtime": 206.8785,
+      "eval_samples_per_second": 1.75,
+      "eval_steps_per_second": 0.875,
+      "step": 100
+    },
+    {
+      "entropy": 1.20640625,
+      "epoch": 0.12292562999385372,
+      "grad_norm": 1.6953125,
+      "learning_rate": 0.0002,
+      "loss": 1.215,
+      "mean_token_accuracy": 0.61802734375,
+      "num_tokens": 197523.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.12292562999385372,
+      "eval_entropy": 1.153444406077348,
+      "eval_loss": 1.188773274421692,
+      "eval_mean_token_accuracy": 0.6300608598066298,
+      "eval_num_tokens": 197523.0,
+      "eval_runtime": 32.2999,
+      "eval_samples_per_second": 11.207,
+      "eval_steps_per_second": 5.604,
+      "step": 200
+    },
+    {
+      "entropy": 1.110703125,
+      "epoch": 0.18438844499078058,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.0002,
+      "loss": 1.115,
+      "mean_token_accuracy": 0.6464453125,
+      "num_tokens": 97970.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.18438844499078058,
+      "eval_entropy": 1.0573204419889504,
+      "eval_loss": 1.1379704475402832,
+      "eval_mean_token_accuracy": 0.6407760704419889,
+      "eval_num_tokens": 97970.0,
+      "eval_runtime": 210.3028,
+      "eval_samples_per_second": 1.721,
+      "eval_steps_per_second": 0.861,
+      "step": 300
+    },
+    {
+      "entropy": 1.1028515625,
+      "epoch": 0.24585125998770743,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.0002,
+      "loss": 1.11,
+      "mean_token_accuracy": 0.64390625,
+      "num_tokens": 197424.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.24585125998770743,
+      "eval_entropy": 1.0773049033149171,
+      "eval_loss": 1.1074110269546509,
+      "eval_mean_token_accuracy": 0.647369216160221,
+      "eval_num_tokens": 197424.0,
+      "eval_runtime": 31.6351,
+      "eval_samples_per_second": 11.443,
+      "eval_steps_per_second": 5.721,
+      "step": 400
+    },
+    {
+      "entropy": 1.0771484375,
+      "epoch": 0.3073140749846343,
+      "grad_norm": 1.5625,
+      "learning_rate": 0.0002,
+      "loss": 1.08,
+      "mean_token_accuracy": 0.65841796875,
+      "num_tokens": 296229.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.3073140749846343,
+      "eval_entropy": 1.0846641919889504,
+      "eval_loss": 1.0807902812957764,
+      "eval_mean_token_accuracy": 0.6544695269337016,
+      "eval_num_tokens": 296229.0,
+      "eval_runtime": 32.3955,
+      "eval_samples_per_second": 11.174,
+      "eval_steps_per_second": 5.587,
+      "step": 500
+    },
+    {
+      "entropy": 1.035234375,
+      "epoch": 0.36877688998156116,
+      "grad_norm": 1.3671875,
+      "learning_rate": 0.0002,
+      "loss": 1.04,
+      "mean_token_accuracy": 0.667421875,
+      "num_tokens": 395552.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.36877688998156116,
+      "eval_entropy": 1.031185255524862,
+      "eval_loss": 1.0730425119400024,
+      "eval_mean_token_accuracy": 0.6574801450276243,
+      "eval_num_tokens": 395552.0,
+      "eval_runtime": 32.4043,
+      "eval_samples_per_second": 11.171,
+      "eval_steps_per_second": 5.586,
+      "step": 600
+    },
+    {
+      "entropy": 1.032109375,
+      "epoch": 0.430239704978488,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.0002,
+      "loss": 1.045,
+      "mean_token_accuracy": 0.675859375,
+      "num_tokens": 495199.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.430239704978488,
+      "eval_entropy": 0.9912594958563536,
+      "eval_loss": 1.055194616317749,
+      "eval_mean_token_accuracy": 0.662292817679558,
+      "eval_num_tokens": 495199.0,
+      "eval_runtime": 32.5634,
+      "eval_samples_per_second": 11.117,
+      "eval_steps_per_second": 5.558,
+      "step": 700
+    },
+    {
+      "entropy": 0.9919140625,
+      "epoch": 0.49170251997541486,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.0002,
+      "loss": 0.985,
+      "mean_token_accuracy": 0.6714453125,
+      "num_tokens": 595086.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.49170251997541486,
+      "eval_entropy": 1.007046357044199,
+      "eval_loss": 1.0382640361785889,
+      "eval_mean_token_accuracy": 0.665648739640884,
+      "eval_num_tokens": 595086.0,
+      "eval_runtime": 32.802,
+      "eval_samples_per_second": 11.036,
+      "eval_steps_per_second": 5.518,
+      "step": 800
+    },
+    {
+      "entropy": 1.02255859375,
+      "epoch": 0.5531653349723418,
+      "grad_norm": 1.609375,
+      "learning_rate": 0.0002,
+      "loss": 1.02,
+      "mean_token_accuracy": 0.6636328125,
+      "num_tokens": 695825.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.5531653349723418,
+      "eval_entropy": 1.064420752762431,
+      "eval_loss": 1.0350699424743652,
+      "eval_mean_token_accuracy": 0.6666306975138122,
+      "eval_num_tokens": 695825.0,
+      "eval_runtime": 32.8674,
+      "eval_samples_per_second": 11.014,
+      "eval_steps_per_second": 5.507,
+      "step": 900
+    },
+    {
+      "entropy": 0.98873046875,
+      "epoch": 0.6146281499692686,
+      "grad_norm": 1.5703125,
+      "learning_rate": 0.0002,
+      "loss": 0.99,
+      "mean_token_accuracy": 0.6741796875,
+      "num_tokens": 794476.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6146281499692686,
+      "eval_entropy": 1.048763380524862,
+      "eval_loss": 1.0293077230453491,
+      "eval_mean_token_accuracy": 0.6697060600828729,
+      "eval_num_tokens": 794476.0,
+      "eval_runtime": 32.3093,
+      "eval_samples_per_second": 11.204,
+      "eval_steps_per_second": 5.602,
+      "step": 1000
+    },
+    {
+      "entropy": 0.981328125,
+      "epoch": 0.6760909649661955,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.0002,
+      "loss": 0.97,
+      "mean_token_accuracy": 0.6811328125,
+      "num_tokens": 893802.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6760909649661955,
+      "eval_entropy": 1.0053306284530388,
+      "eval_loss": 1.0188190937042236,
+      "eval_mean_token_accuracy": 0.6710764848066298,
+      "eval_num_tokens": 893802.0,
+      "eval_runtime": 32.0567,
+      "eval_samples_per_second": 11.292,
+      "eval_steps_per_second": 5.646,
+      "step": 1100
+    },
+    {
+      "entropy": 0.9630078125,
+      "epoch": 0.7375537799631223,
+      "grad_norm": 1.5546875,
+      "learning_rate": 0.0002,
+      "loss": 0.955,
+      "mean_token_accuracy": 0.68578125,
+      "num_tokens": 994015.0,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7375537799631223,
+      "eval_entropy": 0.994442765883978,
+      "eval_loss": 1.0154739618301392,
+      "eval_mean_token_accuracy": 0.6716807665745856,
+      "eval_num_tokens": 994015.0,
+      "eval_runtime": 32.0089,
+      "eval_samples_per_second": 11.309,
+      "eval_steps_per_second": 5.655,
+      "step": 1200
+    },
+    {
+      "entropy": 0.9655078125,
+      "epoch": 0.7990165949600492,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002,
+      "loss": 0.985,
+      "mean_token_accuracy": 0.6850390625,
+      "num_tokens": 99555.0,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7990165949600492,
+      "eval_entropy": 1.013186291436464,
+      "eval_loss": 1.0059565305709839,
+      "eval_mean_token_accuracy": 0.6738820787292817,
+      "eval_num_tokens": 99555.0,
+      "eval_runtime": 206.7503,
+      "eval_samples_per_second": 1.751,
+      "eval_steps_per_second": 0.875,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3254,
+  "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": 1.053726171285504e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

old-cp-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a9789126f3f6758727b589f2bdfc70add5dc118951ff54104a1d1ece7fe1da5
+size 6289