Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,209 @@
+---
+base_model: gemma3-local
+library_name: peft
+tags:
+- base_model:adapter:gemma3-local
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.17.1

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForConditionalGeneration",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3"
+  },
+  "base_model_name_or_path": "gemma3-local",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbc4dae9f06be3d533fcf7efc5b734ccededd1a6ad9d4d11539b80d08997ca7
+size 137039712

added_tokens.json

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

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 -%}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb718a812552f849b8133d4f84a3093c54fb1d2311b06858d1d2e63c8c38a748
+size 67259621

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efcf0408e8792e24c3ea6ad5116ffa1e6b59c1ff3011ff32840a9f46b677d191
+size 1465

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
+  }
+}

tokenizer.json

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

tokenizer.model

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

trainer_state.json

@@ -0,0 +1,608 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 8175,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00012233164107896508,
+      "grad_norm": 65.99068450927734,
+      "learning_rate": 0.0,
+      "loss": 50.955,
+      "step": 1
+    },
+    {
+      "epoch": 0.012233164107896507,
+      "grad_norm": 17.452903747558594,
+      "learning_rate": 9.900000000000002e-06,
+      "loss": 42.946,
+      "step": 100
+    },
+    {
+      "epoch": 0.024466328215793014,
+      "grad_norm": 22.66090202331543,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 28.8711,
+      "step": 200
+    },
+    {
+      "epoch": 0.03669949232368952,
+      "grad_norm": 16.987436294555664,
+      "learning_rate": 2.9900000000000002e-05,
+      "loss": 26.5374,
+      "step": 300
+    },
+    {
+      "epoch": 0.04893265643158603,
+      "grad_norm": 25.907447814941406,
+      "learning_rate": 3.99e-05,
+      "loss": 25.783,
+      "step": 400
+    },
+    {
+      "epoch": 0.06116582053948254,
+      "grad_norm": 19.352567672729492,
+      "learning_rate": 4.99e-05,
+      "loss": 24.569,
+      "step": 500
+    },
+    {
+      "epoch": 0.07339898464737904,
+      "grad_norm": 14.426331520080566,
+      "learning_rate": 5.99e-05,
+      "loss": 24.9186,
+      "step": 600
+    },
+    {
+      "epoch": 0.08563214875527556,
+      "grad_norm": 11.17810344696045,
+      "learning_rate": 6.99e-05,
+      "loss": 24.3884,
+      "step": 700
+    },
+    {
+      "epoch": 0.09786531286317206,
+      "grad_norm": 12.638171195983887,
+      "learning_rate": 7.99e-05,
+      "loss": 24.0454,
+      "step": 800
+    },
+    {
+      "epoch": 0.11009847697106857,
+      "grad_norm": 13.978978157043457,
+      "learning_rate": 8.99e-05,
+      "loss": 23.3352,
+      "step": 900
+    },
+    {
+      "epoch": 0.12233164107896508,
+      "grad_norm": 14.576489448547363,
+      "learning_rate": 9.99e-05,
+      "loss": 23.6704,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1345648051868616,
+      "grad_norm": 12.676314353942871,
+      "learning_rate": 9.995303240438428e-05,
+      "loss": 23.5052,
+      "step": 1100
+    },
+    {
+      "epoch": 0.14679796929475808,
+      "grad_norm": 9.0546293258667,
+      "learning_rate": 9.981031747976037e-05,
+      "loss": 23.1583,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1590311334026546,
+      "grad_norm": 12.504559516906738,
+      "learning_rate": 9.957212399536335e-05,
+      "loss": 23.2603,
+      "step": 1300
+    },
+    {
+      "epoch": 0.1712642975105511,
+      "grad_norm": 17.034109115600586,
+      "learning_rate": 9.923890853071304e-05,
+      "loss": 23.6041,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1834974616184476,
+      "grad_norm": 10.441239356994629,
+      "learning_rate": 9.88113098075496e-05,
+      "loss": 23.3619,
+      "step": 1500
+    },
+    {
+      "epoch": 0.19573062572634412,
+      "grad_norm": 10.060807228088379,
+      "learning_rate": 9.829014746550421e-05,
+      "loss": 23.4193,
+      "step": 1600
+    },
+    {
+      "epoch": 0.20796378983424063,
+      "grad_norm": 8.788949012756348,
+      "learning_rate": 9.767642049097859e-05,
+      "loss": 22.9776,
+      "step": 1700
+    },
+    {
+      "epoch": 0.22019695394213715,
+      "grad_norm": 10.085823059082031,
+      "learning_rate": 9.697130530224482e-05,
+      "loss": 23.2445,
+      "step": 1800
+    },
+    {
+      "epoch": 0.23243011805003364,
+      "grad_norm": 11.247166633605957,
+      "learning_rate": 9.61761534944362e-05,
+      "loss": 23.2768,
+      "step": 1900
+    },
+    {
+      "epoch": 0.24466328215793015,
+      "grad_norm": 10.342413902282715,
+      "learning_rate": 9.529248924875159e-05,
+      "loss": 22.606,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25689644626582664,
+      "grad_norm": 12.145896911621094,
+      "learning_rate": 9.432200641083921e-05,
+      "loss": 22.4946,
+      "step": 2100
+    },
+    {
+      "epoch": 0.2691296103737232,
+      "grad_norm": 15.033831596374512,
+      "learning_rate": 9.326656524396051e-05,
+      "loss": 22.1312,
+      "step": 2200
+    },
+    {
+      "epoch": 0.28136277448161967,
+      "grad_norm": 10.084924697875977,
+      "learning_rate": 9.212818886315748e-05,
+      "loss": 23.0084,
+      "step": 2300
+    },
+    {
+      "epoch": 0.29359593858951616,
+      "grad_norm": 9.8973388671875,
+      "learning_rate": 9.090905935725866e-05,
+      "loss": 23.1228,
+      "step": 2400
+    },
+    {
+      "epoch": 0.3058291026974127,
+      "grad_norm": 9.82909870147705,
+      "learning_rate": 8.961151360615738e-05,
+      "loss": 22.5332,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3180622668053092,
+      "grad_norm": 10.787994384765625,
+      "learning_rate": 8.823803880137993e-05,
+      "loss": 22.6095,
+      "step": 2600
+    },
+    {
+      "epoch": 0.3302954309132057,
+      "grad_norm": 8.712728500366211,
+      "learning_rate": 8.679126767852963e-05,
+      "loss": 22.5694,
+      "step": 2700
+    },
+    {
+      "epoch": 0.3425285950211022,
+      "grad_norm": 9.088665008544922,
+      "learning_rate": 8.527397347074617e-05,
+      "loss": 22.462,
+      "step": 2800
+    },
+    {
+      "epoch": 0.3547617591289987,
+      "grad_norm": 13.562488555908203,
+      "learning_rate": 8.368906459285284e-05,
+      "loss": 22.355,
+      "step": 2900
+    },
+    {
+      "epoch": 0.3669949232368952,
+      "grad_norm": 10.234342575073242,
+      "learning_rate": 8.20395790663819e-05,
+      "loss": 22.7613,
+      "step": 3000
+    },
+    {
+      "epoch": 0.37922808734479174,
+      "grad_norm": 12.220288276672363,
+      "learning_rate": 8.032867869616422e-05,
+      "loss": 22.167,
+      "step": 3100
+    },
+    {
+      "epoch": 0.39146125145268823,
+      "grad_norm": 9.88776969909668,
+      "learning_rate": 7.855964300964568e-05,
+      "loss": 22.5988,
+      "step": 3200
+    },
+    {
+      "epoch": 0.4036944155605847,
+      "grad_norm": 9.015997886657715,
+      "learning_rate": 7.673586297054792e-05,
+      "loss": 22.6787,
+      "step": 3300
+    },
+    {
+      "epoch": 0.41592757966848126,
+      "grad_norm": 9.70136833190918,
+      "learning_rate": 7.48608344789231e-05,
+      "loss": 22.4641,
+      "step": 3400
+    },
+    {
+      "epoch": 0.42816074377637775,
+      "grad_norm": 10.355868339538574,
+      "learning_rate": 7.293815167006228e-05,
+      "loss": 22.1278,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4403939078842743,
+      "grad_norm": 12.009329795837402,
+      "learning_rate": 7.097150002510229e-05,
+      "loss": 22.7803,
+      "step": 3600
+    },
+    {
+      "epoch": 0.4526270719921708,
+      "grad_norm": 9.671050071716309,
+      "learning_rate": 6.896464930653688e-05,
+      "loss": 22.201,
+      "step": 3700
+    },
+    {
+      "epoch": 0.46486023610006727,
+      "grad_norm": 10.088167190551758,
+      "learning_rate": 6.692144633217373e-05,
+      "loss": 21.8431,
+      "step": 3800
+    },
+    {
+      "epoch": 0.4770934002079638,
+      "grad_norm": 10.55173397064209,
+      "learning_rate": 6.484580760138863e-05,
+      "loss": 22.5685,
+      "step": 3900
+    },
+    {
+      "epoch": 0.4893265643158603,
+      "grad_norm": 12.527661323547363,
+      "learning_rate": 6.274171178781088e-05,
+      "loss": 22.589,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5015597284237568,
+      "grad_norm": 10.967172622680664,
+      "learning_rate": 6.061319211283053e-05,
+      "loss": 22.0779,
+      "step": 4100
+    },
+    {
+      "epoch": 0.5137928925316533,
+      "grad_norm": 9.538653373718262,
+      "learning_rate": 5.846432861454612e-05,
+      "loss": 21.7708,
+      "step": 4200
+    },
+    {
+      "epoch": 0.5260260566395498,
+      "grad_norm": 10.186063766479492,
+      "learning_rate": 5.629924032697198e-05,
+      "loss": 22.8011,
+      "step": 4300
+    },
+    {
+      "epoch": 0.5382592207474464,
+      "grad_norm": 11.678515434265137,
+      "learning_rate": 5.412207738449671e-05,
+      "loss": 22.1819,
+      "step": 4400
+    },
+    {
+      "epoch": 0.5504923848553428,
+      "grad_norm": 11.063610076904297,
+      "learning_rate": 5.193701306672695e-05,
+      "loss": 22.7279,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5627255489632393,
+      "grad_norm": 8.978299140930176,
+      "learning_rate": 4.9748235798965476e-05,
+      "loss": 21.8511,
+      "step": 4600
+    },
+    {
+      "epoch": 0.5749587130711359,
+      "grad_norm": 10.103209495544434,
+      "learning_rate": 4.755994112365741e-05,
+      "loss": 22.1447,
+      "step": 4700
+    },
+    {
+      "epoch": 0.5871918771790323,
+      "grad_norm": 10.993765830993652,
+      "learning_rate": 4.537632365819387e-05,
+      "loss": 22.1694,
+      "step": 4800
+    },
+    {
+      "epoch": 0.5994250412869289,
+      "grad_norm": 9.201810836791992,
+      "learning_rate": 4.320156905448889e-05,
+      "loss": 22.0964,
+      "step": 4900
+    },
+    {
+      "epoch": 0.6116582053948254,
+      "grad_norm": 12.470918655395508,
+      "learning_rate": 4.103984597574172e-05,
+      "loss": 22.4633,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6238913695027218,
+      "grad_norm": 10.428497314453125,
+      "learning_rate": 3.889529810576387e-05,
+      "loss": 21.9301,
+      "step": 5100
+    },
+    {
+      "epoch": 0.6361245336106184,
+      "grad_norm": 9.10818099975586,
+      "learning_rate": 3.67720362061877e-05,
+      "loss": 22.5282,
+      "step": 5200
+    },
+    {
+      "epoch": 0.6483576977185149,
+      "grad_norm": 9.964956283569336,
+      "learning_rate": 3.467413023678156e-05,
+      "loss": 22.3872,
+      "step": 5300
+    },
+    {
+      "epoch": 0.6605908618264114,
+      "grad_norm": 13.921968460083008,
+      "learning_rate": 3.260560155397588e-05,
+      "loss": 21.8643,
+      "step": 5400
+    },
+    {
+      "epoch": 0.6728240259343079,
+      "grad_norm": 11.885836601257324,
+      "learning_rate": 3.057041520255407e-05,
+      "loss": 21.775,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6850571900422044,
+      "grad_norm": 11.764188766479492,
+      "learning_rate": 2.857247231528412e-05,
+      "loss": 21.8028,
+      "step": 5600
+    },
+    {
+      "epoch": 0.6972903541501009,
+      "grad_norm": 11.344134330749512,
+      "learning_rate": 2.66156026350594e-05,
+      "loss": 22.1666,
+      "step": 5700
+    },
+    {
+      "epoch": 0.7095235182579974,
+      "grad_norm": 10.856513023376465,
+      "learning_rate": 2.4703557173882753e-05,
+      "loss": 22.3851,
+      "step": 5800
+    },
+    {
+      "epoch": 0.721756682365894,
+      "grad_norm": 9.206277847290039,
+      "learning_rate": 2.284000102276528e-05,
+      "loss": 22.1939,
+      "step": 5900
+    },
+    {
+      "epoch": 0.7339898464737904,
+      "grad_norm": 11.804557800292969,
+      "learning_rate": 2.10285063263221e-05,
+      "loss": 22.0618,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7462230105816869,
+      "grad_norm": 8.50017261505127,
+      "learning_rate": 1.9272545435532014e-05,
+      "loss": 22.0315,
+      "step": 6100
+    },
+    {
+      "epoch": 0.7584561746895835,
+      "grad_norm": 9.053751945495605,
+      "learning_rate": 1.757548425178557e-05,
+      "loss": 22.0844,
+      "step": 6200
+    },
+    {
+      "epoch": 0.7706893387974799,
+      "grad_norm": 10.427083015441895,
+      "learning_rate": 1.5940575774980577e-05,
+      "loss": 22.5945,
+      "step": 6300
+    },
+    {
+      "epoch": 0.7829225029053765,
+      "grad_norm": 10.5215482711792,
+      "learning_rate": 1.43709538680319e-05,
+      "loss": 21.6508,
+      "step": 6400
+    },
+    {
+      "epoch": 0.795155667013273,
+      "grad_norm": 10.189133644104004,
+      "learning_rate": 1.2869627249748107e-05,
+      "loss": 21.913,
+      "step": 6500
+    },
+    {
+      "epoch": 0.8073888311211694,
+      "grad_norm": 9.796092987060547,
+      "learning_rate": 1.1439473727589922e-05,
+      "loss": 22.2168,
+      "step": 6600
+    },
+    {
+      "epoch": 0.819621995229066,
+      "grad_norm": 10.817292213439941,
+      "learning_rate": 1.0083234681364934e-05,
+      "loss": 22.0355,
+      "step": 6700
+    },
+    {
+      "epoch": 0.8318551593369625,
+      "grad_norm": 8.943832397460938,
+      "learning_rate": 8.80350980843293e-06,
+      "loss": 22.0202,
+      "step": 6800
+    },
+    {
+      "epoch": 0.8440883234448591,
+      "grad_norm": 9.288928985595703,
+      "learning_rate": 7.602752140494096e-06,
+      "loss": 21.9743,
+      "step": 6900
+    },
+    {
+      "epoch": 0.8563214875527555,
+      "grad_norm": 11.22246265411377,
+      "learning_rate": 6.483263341512264e-06,
+      "loss": 21.2844,
+      "step": 7000
+    },
+    {
+      "epoch": 0.868554651660652,
+      "grad_norm": 10.753755569458008,
+      "learning_rate": 5.44718929578647e-06,
+      "loss": 21.7079,
+      "step": 7100
+    },
+    {
+      "epoch": 0.8807878157685486,
+      "grad_norm": 11.079498291015625,
+      "learning_rate": 4.4965159946275145e-06,
+      "loss": 22.5284,
+      "step": 7200
+    },
+    {
+      "epoch": 0.893020979876445,
+      "grad_norm": 10.208023071289062,
+      "learning_rate": 3.633065729524454e-06,
+      "loss": 21.4437,
+      "step": 7300
+    },
+    {
+      "epoch": 0.9052541439843416,
+      "grad_norm": 8.745101928710938,
+      "learning_rate": 2.858493599097789e-06,
+      "loss": 21.905,
+      "step": 7400
+    },
+    {
+      "epoch": 0.9174873080922381,
+      "grad_norm": 10.450372695922852,
+      "learning_rate": 2.1742843365352427e-06,
+      "loss": 22.3337,
+      "step": 7500
+    },
+    {
+      "epoch": 0.9297204722001345,
+      "grad_norm": 13.562911987304688,
+      "learning_rate": 1.5817494635913143e-06,
+      "loss": 21.845,
+      "step": 7600
+    },
+    {
+      "epoch": 0.9419536363080311,
+      "grad_norm": 10.1763277053833,
+      "learning_rate": 1.0820247766059276e-06,
+      "loss": 22.2964,
+      "step": 7700
+    },
+    {
+      "epoch": 0.9541868004159276,
+      "grad_norm": 11.245414733886719,
+      "learning_rate": 6.760681693611437e-07,
+      "loss": 21.8236,
+      "step": 7800
+    },
+    {
+      "epoch": 0.9664199645238241,
+      "grad_norm": 10.980335235595703,
+      "learning_rate": 3.646577969491527e-07,
+      "loss": 22.217,
+      "step": 7900
+    },
+    {
+      "epoch": 0.9786531286317206,
+      "grad_norm": 11.447416305541992,
+      "learning_rate": 1.4839058417108752e-07,
+      "loss": 21.6952,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9908862927396171,
+      "grad_norm": 11.309075355529785,
+      "learning_rate": 2.768108132589764e-08,
+      "loss": 21.5793,
+      "step": 8100
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8175,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8195453395393823e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d20a52f4c4c357baf9bc775449f3b25462be6002354383584555e92e4675318
+size 6225