Delete gemma4_lora

gemma4_lora/README.md

@@ -1,207 +0,0 @@
----
-base_model: coder3101/gemma-4-E2B-it-heretic
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:coder3101/gemma-4-E2B-it-heretic
-- 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 0.21.2

gemma4_lora/adapter_config.json

@@ -1,258 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "coder3101/gemma-4-E2B-it-heretic",
-  "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,
-  "kasa_config": null,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "monteclora_config": null,
-  "peft_type": "LORA",
-  "peft_version": "0.21.2",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "linear",
-    "language_model.layers.3.self_attn.k_proj",
-    "26.mlp.down_proj",
-    "language_model.layers.15.self_attn.q_proj",
-    "18.mlp.down_proj",
-    "18.mlp.up_proj",
-    "language_model.layers.7.self_attn.o_proj",
-    "language_model.layers.0.mlp.up_proj",
-    "language_model.layers.15.mlp.up_proj",
-    "language_model.layers.7.self_attn.q_proj",
-    "language_model.layers.1.mlp.gate_proj",
-    "language_model.layers.9.mlp.gate_proj",
-    "language_model.layers.8.mlp.down_proj",
-    "29.self_attn.q_proj",
-    "language_model.layers.5.self_attn.o_proj",
-    "language_model.layers.3.self_attn.q_proj",
-    "language_model.layers.5.mlp.gate_proj",
-    "25.self_attn.o_proj",
-    "output_proj",
-    "26.self_attn.q_proj",
-    "16.self_attn.q_proj",
-    "language_model.layers.6.self_attn.k_proj",
-    "33.mlp.down_proj",
-    "language_model.layers.5.mlp.down_proj",
-    "language_model.layers.0.self_attn.o_proj",
-    "language_model.layers.14.self_attn.o_proj",
-    "language_model.layers.1.self_attn.o_proj",
-    "30.mlp.up_proj",
-    "21.mlp.up_proj",
-    "25.mlp.gate_proj",
-    "34.mlp.down_proj",
-    "31.mlp.down_proj",
-    "language_model.layers.8.mlp.up_proj",
-    "21.self_attn.o_proj",
-    "32.mlp.up_proj",
-    "language_model.layers.4.self_attn.q_proj",
-    "language_model.layers.13.mlp.gate_proj",
-    "32.mlp.gate_proj",
-    "18.self_attn.q_proj",
-    "language_model.layers.7.self_attn.v_proj",
-    "language_model.layers.0.self_attn.q_proj",
-    "23.mlp.gate_proj",
-    "language_model.layers.10.self_attn.q_proj",
-    "language_model.layers.6.mlp.gate_proj",
-    "language_model.layers.10.self_attn.v_proj",
-    "per_layer_projection",
-    "language_model.layers.0.mlp.down_proj",
-    "19.mlp.down_proj",
-    "language_model.layers.6.mlp.down_proj",
-    "20.mlp.gate_proj",
-    "language_model.layers.12.self_attn.q_proj",
-    "22.mlp.up_proj",
-    "16.self_attn.o_proj",
-    "24.self_attn.o_proj",
-    "language_model.layers.13.mlp.down_proj",
-    "language_model.layers.12.mlp.gate_proj",
-    "28.self_attn.o_proj",
-    "language_model.layers.0.self_attn.k_proj",
-    "language_model.layers.4.self_attn.o_proj",
-    "27.mlp.up_proj",
-    "32.self_attn.o_proj",
-    "20.self_attn.q_proj",
-    "language_model.layers.11.mlp.up_proj",
-    "language_model.layers.11.self_attn.v_proj",
-    "23.mlp.up_proj",
-    "language_model.layers.9.self_attn.v_proj",
-    "input_proj",
-    "19.self_attn.o_proj",
-    "language_model.layers.13.self_attn.q_proj",
-    "19.mlp.up_proj",
-    "language_model.layers.6.self_attn.q_proj",
-    "language_model.layers.8.mlp.gate_proj",
-    "33.self_attn.o_proj",
-    "27.mlp.down_proj",
-    "language_model.layers.11.self_attn.k_proj",
-    "language_model.layers.10.self_attn.k_proj",
-    "language_model.layers.9.self_attn.q_proj",
-    "language_model.layers.1.self_attn.k_proj",
-    "21.mlp.gate_proj",
-    "language_model.layers.11.self_attn.o_proj",
-    "language_model.layers.12.self_attn.v_proj",
-    "20.self_attn.o_proj",
-    "language_model.layers.8.self_attn.q_proj",
-    "language_model.layers.6.self_attn.o_proj",
-    "language_model.layers.5.self_attn.v_proj",
-    "30.self_attn.q_proj",
-    "language_model.layers.13.self_attn.k_proj",
-    "31.self_attn.o_proj",
-    "input_proj_linear",
-    "language_model.layers.9.self_attn.o_proj",
-    "language_model.layers.13.self_attn.o_proj",
-    "26.mlp.up_proj",
-    "22.mlp.down_proj",
-    "language_model.layers.2.mlp.gate_proj",
-    "language_model.layers.15.self_attn.o_proj",
-    "language_model.layers.10.mlp.gate_proj",
-    "language_model.layers.2.self_attn.k_proj",
-    "16.mlp.down_proj",
-    "30.mlp.gate_proj",
-    "language_model.layers.12.mlp.up_proj",
-    "relative_k_proj",
-    "34.self_attn.q_proj",
-    "21.mlp.down_proj",
-    "language_model.layers.4.mlp.up_proj",
-    "language_model.layers.12.self_attn.o_proj",
-    "29.mlp.down_proj",
-    "29.mlp.up_proj",
-    "29.self_attn.o_proj",
-    "language_model.layers.7.self_attn.k_proj",
-    "language_model.layers.2.self_attn.o_proj",
-    "language_model.layers.1.mlp.up_proj",
-    "language_model.layers.9.mlp.down_proj",
-    "26.mlp.gate_proj",
-    "per_layer_model_projection",
-    "language_model.layers.2.self_attn.v_proj",
-    "language_model.layers.12.self_attn.k_proj",
-    "language_model.layers.5.mlp.up_proj",
-    "language_model.layers.11.self_attn.q_proj",
-    "language_model.layers.1.self_attn.v_proj",
-    "language_model.layers.11.mlp.gate_proj",
-    "language_model.layers.5.self_attn.q_proj",
-    "16.mlp.up_proj",
-    "language_model.layers.14.mlp.up_proj",
-    "language_model.layers.4.mlp.gate_proj",
-    "language_model.layers.11.mlp.down_proj",
-    "language_model.layers.4.self_attn.v_proj",
-    "24.mlp.down_proj",
-    "language_model.layers.15.mlp.gate_proj",
-    "33.mlp.up_proj",
-    "27.self_attn.q_proj",
-    "language_model.layers.10.mlp.up_proj",
-    "19.mlp.gate_proj",
-    "language_model.layers.14.self_attn.q_proj",
-    "language_model.layers.15.mlp.down_proj",
-    "language_model.layers.7.mlp.down_proj",
-    "18.mlp.gate_proj",
-    "25.mlp.down_proj",
-    "31.mlp.gate_proj",
-    "language_model.layers.7.mlp.gate_proj",
-    "language_model.layers.2.mlp.up_proj",
-    "34.self_attn.o_proj",
-    "language_model.layers.3.mlp.up_proj",
-    "language_model.layers.3.mlp.down_proj",
-    "language_model.layers.10.mlp.down_proj",
-    "33.self_attn.q_proj",
-    "language_model.layers.7.mlp.up_proj",
-    "23.mlp.down_proj",
-    "language_model.layers.9.self_attn.k_proj",
-    "language_model.layers.12.mlp.down_proj",
-    "22.self_attn.q_proj",
-    "28.mlp.gate_proj",
-    "30.mlp.down_proj",
-    "language_model.layers.14.self_attn.v_proj",
-    "23.self_attn.q_proj",
-    "language_model.layers.2.self_attn.q_proj",
-    "language_model.layers.14.mlp.down_proj",
-    "language_model.layers.13.mlp.up_proj",
-    "24.mlp.up_proj",
-    "language_model.layers.14.self_attn.k_proj",
-    "31.mlp.up_proj",
-    "17.mlp.up_proj",
-    "27.mlp.gate_proj",
-    "language_model.layers.5.self_attn.k_proj",
-    "28.mlp.down_proj",
-    "18.self_attn.o_proj",
-    "22.self_attn.o_proj",
-    "34.mlp.gate_proj",
-    "32.mlp.down_proj",
-    "language_model.layers.1.mlp.down_proj",
-    "language_model.layers.1.self_attn.q_proj",
-    "25.self_attn.q_proj",
-    "language_model.layers.3.self_attn.o_proj",
-    "22.mlp.gate_proj",
-    "29.mlp.gate_proj",
-    "28.mlp.up_proj",
-    "23.self_attn.o_proj",
-    "language_model.layers.6.self_attn.v_proj",
-    "language_model.layers.3.self_attn.v_proj",
-    "language_model.layers.4.mlp.down_proj",
-    "language_model.layers.8.self_attn.o_proj",
-    "language_model.layers.0.self_attn.v_proj",
-    "19.self_attn.q_proj",
-    "24.mlp.gate_proj",
-    "31.self_attn.q_proj",
-    "20.mlp.down_proj",
-    "language_model.layers.13.self_attn.v_proj",
-    "32.self_attn.q_proj",
-    "20.mlp.up_proj",
-    "17.self_attn.q_proj",
-    "34.mlp.up_proj",
-    "language_model.layers.14.mlp.gate_proj",
-    "28.self_attn.q_proj",
-    "17.mlp.gate_proj",
-    "26.self_attn.o_proj",
-    "27.self_attn.o_proj",
-    "16.mlp.gate_proj",
-    "17.self_attn.o_proj",
-    "language_model.layers.9.mlp.up_proj",
-    "24.self_attn.q_proj",
-    "language_model.layers.4.self_attn.k_proj",
-    "embedding_projection",
-    "language_model.layers.10.self_attn.o_proj",
-    "per_layer_input_gate",
-    "33.mlp.gate_proj",
-    "language_model.layers.6.mlp.up_proj",
-    "language_model.layers.2.mlp.down_proj",
-    "language_model.layers.8.self_attn.v_proj",
-    "17.mlp.down_proj",
-    "30.self_attn.o_proj",
-    "language_model.layers.0.mlp.gate_proj",
-    "language_model.layers.8.self_attn.k_proj",
-    "25.mlp.up_proj",
-    "language_model.layers.3.mlp.gate_proj",
-    "21.self_attn.q_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
-}

gemma4_lora/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7346110d4763bdd4a12cd709a24bf8399f93fa577d87638e00f6f0f8635dd718
-size 151844848

gemma4_lora/gradient_health_audit.json

@@ -1,143 +0,0 @@
-{
-    "audit_version": 1,
-    "audit_timestamp_unix": 1793918763.25352,
-    "base_model": "coder3101/gemma-4-E2B-it-heretic",
-    "adapter_directory": "/kaggle/working/gemma4_lora/adapter",
-    "gradient_health_passed": true,
-    "numerical_recovery_passed": true,
-    "adapter_weights_finite": true,
-    "adapter_export_eligible": true,
-    "gradient_checks": 120,
-    "skipped_optimizer_steps": 0,
-    "skipped_step_indices": [],
-    "nonfinite_gradient_steps": [],
-    "nonfinite_gradient_tensors": 0,
-    "gradient_norm_statistics": {
-        "count": 120,
-        "minimum": 0.01549019716854724,
-        "median": 0.2999997905589369,
-        "maximum": 0.2999999967057757,
-        "mean": 0.23312759692201965
-    },
-    "grad_scaler_initial": 2048.0,
-    "grad_scaler_final": 2048.0,
-    "grad_scaler_minimum": 512.0,
-    "loss_history_entries": 121,
-    "adapter_tensor_count": 1050,
-    "adapter_parameter_count": 37920768,
-    "nonfinite_adapter_tensors": [],
-    "passed_checks": 22,
-    "failed_checks": 0,
-    "checks": [
-        {
-            "name": "Gradient monitoring executed",
-            "passed": true,
-            "detail": "120 optimizer attempts were monitored."
-        },
-        {
-            "name": "Gradient norm history length",
-            "passed": true,
-            "detail": "120 norms for 120 checks."
-        },
-        {
-            "name": "Gradient tensor-count history length",
-            "passed": true,
-            "detail": "120 entries for 120 checks."
-        },
-        {
-            "name": "GradScaler history length",
-            "passed": true,
-            "detail": "120 entries for 120 checks."
-        },
-        {
-            "name": "Skipped optimizer update limit",
-            "passed": true,
-            "detail": "0 skipped; maximum allowed is 2."
-        },
-        {
-            "name": "Skipped update indices are unique",
-            "passed": true,
-            "detail": "Indices: []"
-        },
-        {
-            "name": "Skipped update indices are in range",
-            "passed": true,
-            "detail": "Valid range: 0 to 119."
-        },
-        {
-            "name": "Non-finite gradient indices are unique",
-            "passed": true,
-            "detail": "Indices: []"
-        },
-        {
-            "name": "Non-finite gradient indices are in range",
-            "passed": true,
-            "detail": "Valid range: 0 to 119."
-        },
-        {
-            "name": "Overflow attempts match skipped optimizer attempts",
-            "passed": true,
-            "detail": "Skipped=[]; non-finite=[]."
-        },
-        {
-            "name": "Non-finite tensor count is consistent",
-            "passed": true,
-            "detail": "0 non-finite gradient tensors."
-        },
-        {
-            "name": "No optimizer attempt lacked all gradients",
-            "passed": true,
-            "detail": "No-gradient attempts: []."
-        },
-        {
-            "name": "No consecutive overflow attempts",
-            "passed": true,
-            "detail": "Overflow indices: []."
-        },
-        {
-            "name": "Final overflow has recovery window",
-            "passed": true,
-            "detail": "No overflow in the final two attempts."
-        },
-        {
-            "name": "Missing gradient norms match overflow attempts",
-            "passed": true,
-            "detail": "Missing norms=[]; overflow attempts=[]."
-        },
-        {
-            "name": "All recorded finite gradient norms are valid",
-            "passed": true,
-            "detail": "120 finite norms; invalid indices=[]."
-        },
-        {
-            "name": "GradScaler history is finite and positive",
-            "passed": true,
-            "detail": "120 recorded values."
-        },
-        {
-            "name": "Initial GradScaler value is valid",
-            "passed": true,
-            "detail": "Initial scale: 2048.0."
-        },
-        {
-            "name": "Final GradScaler value is valid",
-            "passed": true,
-            "detail": "Final scale: 2048.0."
-        },
-        {
-            "name": "Final GradScaler meets minimum",
-            "passed": true,
-            "detail": "Final=2048.0; minimum=512.0."
-        },
-        {
-            "name": "Recorded loss history contains valid values",
-            "passed": true,
-            "detail": "120 finite loss values; invalid entries=[]."
-        },
-        {
-            "name": "Adapter weights contain only finite values",
-            "passed": true,
-            "detail": "1050 tensors; 37,920,768 parameters; 0 non-finite tensors."
-        }
-    ]
-}

gemma4_lora/gradient_health_report.json

@@ -1,1223 +0,0 @@
-{
-    "gradient_checks": 120,
-    "skipped_optimizer_steps": 0,
-    "skipped_step_indices": [],
-    "nonfinite_gradient_steps": [],
-    "nonfinite_gradient_tensors": 0,
-    "no_gradient_steps": [],
-    "gradient_norms": [
-        0.2999999967057757,
-        0.29999993283753906,
-        0.2999999882627466,
-        0.29999995549701025,
-        0.2999999056871044,
-        0.29999997674311024,
-        0.29999996019639635,
-        0.2999999331868226,
-        0.2999999190714327,
-        0.29999994453961754,
-        0.29999992767652045,
-        0.2999999171052898,
-        0.299999891168433,
-        0.2999999387562522,
-        0.2999998559474201,
-        0.2999998651608199,
-        0.29999989888361955,
-        0.299999860837114,
-        0.2999998637005364,
-        0.2999999487365302,
-        0.29999991210927746,
-        0.29999983302762295,
-        0.29999986467178447,
-        0.2999999246373012,
-        0.2999998710247092,
-        0.29999993885001613,
-        0.2999998562013249,
-        0.2999997898603423,
-        0.2999998988001732,
-        0.2999997968720858,
-        0.29999981960907923,
-        0.29999979953123646,
-        0.29999993062910396,
-        0.2999998143369396,
-        0.29999988013220563,
-        0.29999991627050243,
-        0.2999998549485208,
-        0.29999983698781824,
-        0.29999988739171235,
-        0.29999984926746825,
-        0.29999978238735703,
-        0.29999989584211356,
-        0.29999983784788814,
-        0.2999997514863681,
-        0.2999997904095978,
-        0.29999987607479484,
-        0.29999983808389075,
-        0.29999982376193984,
-        0.299999843238001,
-        0.2999997380879359,
-        0.29999984200200724,
-        0.2999998571695013,
-        0.29999993043955364,
-        0.2999998548770266,
-        0.29999998275241463,
-        0.2999998385367787,
-        0.29999985670904267,
-        0.2999998650251881,
-        0.29999990770273105,
-        0.2999997907082759,
-        0.29999975991044014,
-        0.2999998386237497,
-        0.29999976701075326,
-        0.2999996384655255,
-        0.2999998653212779,
-        0.29999942298684046,
-        0.29999983928156604,
-        0.2999998335974349,
-        0.2999997630936651,
-        0.29999957808098776,
-        0.2999993324745417,
-        0.29999964148031316,
-        0.2999993150217098,
-        0.2999994021040341,
-        0.29999970079639704,
-        0.2999996212821266,
-        0.29999923384458965,
-        0.2400580492521267,
-        0.2999991859568465,
-        0.29999952391317286,
-        0.29999943933173767,
-        0.23904489591558,
-        0.22082136702898114,
-        0.2999996496006251,
-        0.29999960097840744,
-        0.06084565240294252,
-        0.29999985714989785,
-        0.27001140019986175,
-        0.24196433419393892,
-        0.05825369805852839,
-        0.2999991469929516,
-        0.15705863171793738,
-        0.03828652322329344,
-        0.023200811595227796,
-        0.04129434956180859,
-        0.049138123368485935,
-        0.04487694375693962,
-        0.224603229033112,
-        0.03229273522786361,
-        0.032599237798871604,
-        0.022936590735817202,
-        0.02703242390409454,
-        0.04120622897715978,
-        0.08993883373234765,
-        0.017092950887663435,
-        0.0368967124461106,
-        0.032362015474763244,
-        0.020569942602627754,
-        0.033200306693477066,
-        0.030664452587451013,
-        0.01549019716854724,
-        0.06880451374310592,
-        0.1791207763483352,
-        0.035754383235644914,
-        0.0195178739292786,
-        0.021198802830342003,
-        0.0159683130342503,
-        0.03289778612980872,
-        0.03374332580161473,
-        0.026582601743105054
-    ],
-    "gradient_tensor_counts": [
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780,
-        780
-    ],
-    "grad_scaler_values": [
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0,
-        2048.0
-    ],
-    "loss_history": [
-        {
-            "global_step": 1,
-            "epoch": 0.25,
-            "loss": 3.0028076171875,
-            "learning_rate": 0.0,
-            "grad_norm": 5.735446453094482
-        },
-        {
-            "global_step": 2,
-            "epoch": 0.5,
-            "loss": 2.5738320350646973,
-            "learning_rate": 3.3333333333333335e-05,
-            "grad_norm": 4.246273517608643
-        },
-        {
-            "global_step": 3,
-            "epoch": 0.75,
-            "loss": 3.9848618507385254,
-            "learning_rate": 6.666666666666667e-05,
-            "grad_norm": 7.595849990844727
-        },
-        {
-            "global_step": 4,
-            "epoch": 1.0,
-            "loss": 2.5158143043518066,
-            "learning_rate": 0.0001,
-            "grad_norm": 4.926611423492432
-        },
-        {
-            "global_step": 5,
-            "epoch": 1.25,
-            "loss": 2.6317954063415527,
-            "learning_rate": 9.998197638354428e-05,
-            "grad_norm": 3.7285847663879395
-        },
-        {
-            "global_step": 6,
-            "epoch": 1.5,
-            "loss": 3.391207218170166,
-            "learning_rate": 9.992791852820709e-05,
-            "grad_norm": 6.960104465484619
-        },
-        {
-            "global_step": 7,
-            "epoch": 1.75,
-            "loss": 1.7886579036712646,
-            "learning_rate": 9.983786540671051e-05,
-            "grad_norm": 3.496877431869507
-        },
-        {
-            "global_step": 8,
-            "epoch": 2.0,
-            "loss": 1.9815987348556519,
-            "learning_rate": 9.97118819423714e-05,
-            "grad_norm": 2.860832691192627
-        },
-        {
-            "global_step": 9,
-            "epoch": 2.25,
-            "loss": 1.775098443031311,
-            "learning_rate": 9.955005896229543e-05,
-            "grad_norm": 3.4511520862579346
-        },
-        {
-            "global_step": 10,
-            "epoch": 2.5,
-            "loss": 1.6050281524658203,
-            "learning_rate": 9.935251313189564e-05,
-            "grad_norm": 3.639047384262085
-        },
-        {
-            "global_step": 11,
-            "epoch": 2.75,
-            "loss": 2.5201776027679443,
-            "learning_rate": 9.911938687078324e-05,
-            "grad_norm": 3.662109613418579
-        },
-        {
-            "global_step": 12,
-            "epoch": 3.0,
-            "loss": 1.7487728595733643,
-            "learning_rate": 9.885084825009086e-05,
-            "grad_norm": 2.736379384994507
-        },
-        {
-            "global_step": 13,
-            "epoch": 3.25,
-            "loss": 1.685441255569458,
-            "learning_rate": 9.85470908713026e-05,
-            "grad_norm": 2.4754011631011963
-        },
-        {
-            "global_step": 14,
-            "epoch": 3.5,
-            "loss": 2.0612027645111084,
-            "learning_rate": 9.820833372667812e-05,
-            "grad_norm": 2.888793468475342
-        },
-        {
-            "global_step": 15,
-            "epoch": 3.75,
-            "loss": 1.2462215423583984,
-            "learning_rate": 9.783482104137127e-05,
-            "grad_norm": 2.124307632446289
-        },
-        {
-            "global_step": 16,
-            "epoch": 4.0,
-            "loss": 1.5945758819580078,
-            "learning_rate": 9.742682209735727e-05,
-            "grad_norm": 2.0276503562927246
-        },
-        {
-            "global_step": 17,
-            "epoch": 4.25,
-            "loss": 1.8966870307922363,
-            "learning_rate": 9.698463103929542e-05,
-            "grad_norm": 2.2649166584014893
-        },
-        {
-            "global_step": 18,
-            "epoch": 4.5,
-            "loss": 1.220649242401123,
-            "learning_rate": 9.650856666246693e-05,
-            "grad_norm": 1.7242375612258911
-        },
-        {
-            "global_step": 19,
-            "epoch": 4.75,
-            "loss": 1.4429657459259033,
-            "learning_rate": 9.599897218294122e-05,
-            "grad_norm": 1.889949083328247
-        },
-        {
-            "global_step": 20,
-            "epoch": 5.0,
-            "loss": 1.791039228439331,
-            "learning_rate": 9.54562149901362e-05,
-            "grad_norm": 3.159863233566284
-        },
-        {
-            "global_step": 21,
-            "epoch": 5.25,
-            "loss": 1.2491681575775146,
-            "learning_rate": 9.48806863819507e-05,
-            "grad_norm": 2.510749340057373
-        },
-        {
-            "global_step": 22,
-            "epoch": 5.5,
-            "loss": 0.9549908638000488,
-            "learning_rate": 9.42728012826605e-05,
-            "grad_norm": 1.8189880847930908
-        },
-        {
-            "global_step": 23,
-            "epoch": 5.75,
-            "loss": 1.671364188194275,
-            "learning_rate": 9.363299794378073e-05,
-            "grad_norm": 1.8584535121917725
-        },
-        {
-            "global_step": 24,
-            "epoch": 6.0,
-            "loss": 1.1979198455810547,
-            "learning_rate": 9.296173762811085e-05,
-            "grad_norm": 2.8647730350494385
-        },
-        {
-            "global_step": 25,
-            "epoch": 6.25,
-            "loss": 1.0778791904449463,
-            "learning_rate": 9.225950427718975e-05,
-            "grad_norm": 2.2521347999572754
-        },
-        {
-            "global_step": 26,
-            "epoch": 6.5,
-            "loss": 0.9626718759536743,
-            "learning_rate": 9.152680416240059e-05,
-            "grad_norm": 2.9740376472473145
-        },
-        {
-            "global_step": 27,
-            "epoch": 6.75,
-            "loss": 1.4524807929992676,
-            "learning_rate": 9.076416551997721e-05,
-            "grad_norm": 1.8301929235458374
-        },
-        {
-            "global_step": 28,
-            "epoch": 7.0,
-            "loss": 0.9822371006011963,
-            "learning_rate": 8.997213817017507e-05,
-            "grad_norm": 1.515589952468872
-        },
-        {
-            "global_step": 29,
-            "epoch": 7.25,
-            "loss": 1.3678052425384521,
-            "learning_rate": 8.915129312088112e-05,
-            "grad_norm": 2.429225444793701
-        },
-        {
-            "global_step": 30,
-            "epoch": 7.5,
-            "loss": 0.7263110876083374,
-            "learning_rate": 8.83022221559489e-05,
-            "grad_norm": 1.299315333366394
-        },
-        {
-            "global_step": 31,
-            "epoch": 7.75,
-            "loss": 0.8736010789871216,
-            "learning_rate": 8.742553740855506e-05,
-            "grad_norm": 1.5025458335876465
-        },
-        {
-            "global_step": 32,
-            "epoch": 8.0,
-            "loss": 0.9786587357521057,
-            "learning_rate": 8.652187091988517e-05,
-            "grad_norm": 1.3604384660720825
-        },
-        {
-            "global_step": 33,
-            "epoch": 8.25,
-            "loss": 0.5913520455360413,
-            "learning_rate": 8.559187418346703e-05,
-            "grad_norm": 3.1408023834228516
-        },
-        {
-            "global_step": 34,
-            "epoch": 8.5,
-            "loss": 0.8007135391235352,
-            "learning_rate": 8.463621767547998e-05,
-            "grad_norm": 1.5192880630493164
-        },
-        {
-            "global_step": 35,
-            "epoch": 8.75,
-            "loss": 0.8744857311248779,
-            "learning_rate": 8.365559037137852e-05,
-            "grad_norm": 2.1710562705993652
-        },
-        {
-            "global_step": 36,
-            "epoch": 9.0,
-            "loss": 0.8190163373947144,
-            "learning_rate": 8.265069924917925e-05,
-            "grad_norm": 3.7557790279388428
-        },
-        {
-            "global_step": 37,
-            "epoch": 9.25,
-            "loss": 0.7986066341400146,
-            "learning_rate": 8.162226877976887e-05,
-            "grad_norm": 1.8751171827316284
-        },
-        {
-            "global_step": 38,
-            "epoch": 9.5,
-            "loss": 0.5472699403762817,
-            "learning_rate": 8.057104040460062e-05,
-            "grad_norm": 1.435860514640808
-        },
-        {
-            "global_step": 39,
-            "epoch": 9.75,
-            "loss": 0.728087306022644,
-            "learning_rate": 7.949777200115616e-05,
-            "grad_norm": 2.4945225715637207
-        },
-        {
-            "global_step": 40,
-            "epoch": 10.0,
-            "loss": 0.7109437584877014,
-            "learning_rate": 7.840323733655778e-05,
-            "grad_norm": 1.7653728723526
-        },
-        {
-            "global_step": 41,
-            "epoch": 10.25,
-            "loss": 0.4470646381378174,
-            "learning_rate": 7.728822550972523e-05,
-            "grad_norm": 1.2734816074371338
-        },
-        {
-            "global_step": 42,
-            "epoch": 10.5,
-            "loss": 0.7584569454193115,
-            "learning_rate": 7.615354038247888e-05,
-            "grad_norm": 2.3084428310394287
-        },
-        {
-            "global_step": 43,
-            "epoch": 10.75,
-            "loss": 0.46312659978866577,
-            "learning_rate": 7.500000000000001e-05,
-            "grad_norm": 1.7591501474380493
-        },
-        {
-            "global_step": 44,
-            "epoch": 11.0,
-            "loss": 0.45575660467147827,
-            "learning_rate": 7.38284360010654e-05,
-            "grad_norm": 1.154929518699646
-        },
-        {
-            "global_step": 45,
-            "epoch": 11.25,
-            "loss": 0.4252345860004425,
-            "learning_rate": 7.263969301848188e-05,
-            "grad_norm": 1.0464447736740112
-        },
-        {
-            "global_step": 46,
-            "epoch": 11.5,
-            "loss": 0.5287308692932129,
-            "learning_rate": 7.143462807015271e-05,
-            "grad_norm": 2.1150853633880615
-        },
-        {
-            "global_step": 47,
-            "epoch": 11.75,
-            "loss": 0.4766055643558502,
-            "learning_rate": 7.021410994121525e-05,
-            "grad_norm": 2.03830885887146
-        },
-        {
-            "global_step": 48,
-            "epoch": 12.0,
-            "loss": 0.23271411657333374,
-            "learning_rate": 6.897901855769483e-05,
-            "grad_norm": 1.4084392786026
-        },
-        {
-            "global_step": 49,
-            "epoch": 12.25,
-            "loss": 0.35807982087135315,
-            "learning_rate": 6.773024435212678e-05,
-            "grad_norm": 1.8897265195846558
-        },
-        {
-            "global_step": 50,
-            "epoch": 12.5,
-            "loss": 0.18392693996429443,
-            "learning_rate": 6.646868762160399e-05,
-            "grad_norm": 1.135053038597107
-        },
-        {
-            "global_step": 51,
-            "epoch": 12.75,
-            "loss": 0.4107872247695923,
-            "learning_rate": 6.519525787871235e-05,
-            "grad_norm": 1.7325575351715088
-        },
-        {
-            "global_step": 52,
-            "epoch": 13.0,
-            "loss": 0.295409232378006,
-            "learning_rate": 6.391087319582264e-05,
-            "grad_norm": 1.7553775310516357
-        },
-        {
-            "global_step": 53,
-            "epoch": 13.25,
-            "loss": 0.24841588735580444,
-            "learning_rate": 6.261645954321109e-05,
-            "grad_norm": 2.4505655765533447
-        },
-        {
-            "global_step": 54,
-            "epoch": 13.5,
-            "loss": 0.28180259466171265,
-            "learning_rate": 6.131295012148612e-05,
-            "grad_norm": 1.7769156694412231
-        },
-        {
-            "global_step": 55,
-            "epoch": 13.75,
-            "loss": 0.21721918880939484,
-            "learning_rate": 6.0001284688802226e-05,
-            "grad_norm": 8.174845695495605
-        },
-        {
-            "global_step": 56,
-            "epoch": 14.0,
-            "loss": 0.18195383250713348,
-            "learning_rate": 5.868240888334653e-05,
-            "grad_norm": 1.8216534852981567
-        },
-        {
-            "global_step": 57,
-            "epoch": 14.25,
-            "loss": 0.15293434262275696,
-            "learning_rate": 5.735727354158581e-05,
-            "grad_norm": 1.528199315071106
-        },
-        {
-            "global_step": 58,
-            "epoch": 14.5,
-            "loss": 0.18003931641578674,
-            "learning_rate": 5.602683401276615e-05,
-            "grad_norm": 1.7730704545974731
-        },
-        {
-            "global_step": 59,
-            "epoch": 14.75,
-            "loss": 0.16167467832565308,
-            "learning_rate": 5.469204947015897e-05,
-            "grad_norm": 2.5438311100006104
-        },
-        {
-            "global_step": 60,
-            "epoch": 15.0,
-            "loss": 0.06871137768030167,
-            "learning_rate": 5.335388221955012e-05,
-            "grad_norm": 1.244670033454895
-        },
-        {
-            "global_step": 61,
-            "epoch": 15.25,
-            "loss": 0.08273965865373611,
-            "learning_rate": 5.201329700547076e-05,
-            "grad_norm": 1.158942699432373
-        },
-        {
-            "global_step": 62,
-            "epoch": 15.5,
-            "loss": 0.1550861895084381,
-            "learning_rate": 5.0671260315669875e-05,
-            "grad_norm": 1.5921404361724854
-        },
-        {
-            "global_step": 63,
-            "epoch": 15.75,
-            "loss": 0.07742718607187271,
-            "learning_rate": 4.9328739684330137e-05,
-            "grad_norm": 1.2498779296875
-        },
-        {
-            "global_step": 64,
-            "epoch": 16.0,
-            "loss": 0.060180872678756714,
-            "learning_rate": 4.798670299452926e-05,
-            "grad_norm": 0.8160451650619507
-        },
-        {
-            "global_step": 65,
-            "epoch": 16.25,
-            "loss": 0.11217842251062393,
-            "learning_rate": 4.6646117780449876e-05,
-            "grad_norm": 2.351928472518921
-        },
-        {
-            "global_step": 66,
-            "epoch": 16.5,
-            "loss": 0.029149621725082397,
-            "learning_rate": 4.530795052984104e-05,
-            "grad_norm": 0.5133053064346313
-        },
-        {
-            "global_step": 67,
-            "epoch": 16.75,
-            "loss": 0.057295918464660645,
-            "learning_rate": 4.397316598723385e-05,
-            "grad_norm": 1.4209790229797363
-        },
-        {
-            "global_step": 68,
-            "epoch": 17.0,
-            "loss": 0.05391449108719826,
-            "learning_rate": 4.264272645841419e-05,
-            "grad_norm": 1.5596890449523926
-        },
-        {
-            "global_step": 69,
-            "epoch": 17.25,
-            "loss": 0.07454235851764679,
-            "learning_rate": 4.131759111665349e-05,
-            "grad_norm": 1.2337915897369385
-        },
-        {
-            "global_step": 70,
-            "epoch": 17.5,
-            "loss": 0.03401903435587883,
-            "learning_rate": 3.9998715311197785e-05,
-            "grad_norm": 0.718992292881012
-        },
-        {
-            "global_step": 71,
-            "epoch": 17.75,
-            "loss": 0.016408829018473625,
-            "learning_rate": 3.86870498785139e-05,
-            "grad_norm": 0.44305819272994995
-        },
-        {
-            "global_step": 72,
-            "epoch": 18.0,
-            "loss": 0.03439335897564888,
-            "learning_rate": 3.738354045678891e-05,
-            "grad_norm": 0.8151929974555969
-        },
-        {
-            "global_step": 73,
-            "epoch": 18.25,
-            "loss": 0.01341971568763256,
-            "learning_rate": 3.608912680417737e-05,
-            "grad_norm": 0.44037967920303345
-        },
-        {
-            "global_step": 74,
-            "epoch": 18.5,
-            "loss": 0.015053657814860344,
-            "learning_rate": 3.480474212128766e-05,
-            "grad_norm": 0.505387008190155
-        },
-        {
-            "global_step": 75,
-            "epoch": 18.75,
-            "loss": 0.020888736471533775,
-            "learning_rate": 3.3531312378396026e-05,
-            "grad_norm": 0.9699237942695618
-        },
-        {
-            "global_step": 76,
-            "epoch": 19.0,
-            "loss": 0.015053548850119114,
-            "learning_rate": 3.226975564787322e-05,
-            "grad_norm": 0.7767230868339539
-        },
-        {
-            "global_step": 77,
-            "epoch": 19.25,
-            "loss": 0.005396610591560602,
-            "learning_rate": 3.1020981442305184e-05,
-            "grad_norm": 0.40644827485084534
-        },
-        {
-            "global_step": 78,
-            "epoch": 19.5,
-            "loss": 0.004981599748134613,
-            "learning_rate": 2.978589005878476e-05,
-            "grad_norm": 0.2400580644607544
-        },
-        {
-            "global_step": 79,
-            "epoch": 19.75,
-            "loss": 0.004586038179695606,
-            "learning_rate": 2.8565371929847284e-05,
-            "grad_norm": 0.35911986231803894
-        },
-        {
-            "global_step": 80,
-            "epoch": 20.0,
-            "loss": 0.013846193440258503,
-            "learning_rate": 2.7360306981518146e-05,
-            "grad_norm": 0.644167959690094
-        },
-        {
-            "global_step": 81,
-            "epoch": 20.25,
-            "loss": 0.009072684682905674,
-            "learning_rate": 2.6171563998934605e-05,
-            "grad_norm": 0.559910237789154
-        },
-        {
-            "global_step": 82,
-            "epoch": 20.5,
-            "loss": 0.0030265708919614553,
-            "learning_rate": 2.500000000000001e-05,
-            "grad_norm": 0.2390448898077011
-        },
-        {
-            "global_step": 83,
-            "epoch": 20.75,
-            "loss": 0.0019349269568920135,
-            "learning_rate": 2.3846459617521128e-05,
-            "grad_norm": 0.220821350812912
-        },
-        {
-            "global_step": 84,
-            "epoch": 21.0,
-            "loss": 0.008226916193962097,
-            "learning_rate": 2.2711774490274766e-05,
-            "grad_norm": 0.8569097518920898
-        },
-        {
-            "global_step": 85,
-            "epoch": 21.25,
-            "loss": 0.007080879062414169,
-            "learning_rate": 2.1596762663442218e-05,
-            "grad_norm": 0.7534610629081726
-        },
-        {
-            "global_step": 86,
-            "epoch": 21.5,
-            "loss": 0.0010789937805384398,
-            "learning_rate": 2.050222799884387e-05,
-            "grad_norm": 0.06084565073251724
-        },
-        {
-            "global_step": 87,
-            "epoch": 21.75,
-            "loss": 0.0016643002163618803,
-            "learning_rate": 1.942895959539939e-05,
-            "grad_norm": 1.5307955741882324
-        },
-        {
-            "global_step": 88,
-            "epoch": 22.0,
-            "loss": 0.002636656863614917,
-            "learning_rate": 1.837773122023114e-05,
-            "grad_norm": 0.27001139521598816
-        },
-        {
-            "global_step": 89,
-            "epoch": 22.25,
-            "loss": 0.0008208074723370373,
-            "learning_rate": 1.734930075082076e-05,
-            "grad_norm": 0.24196434020996094
-        },
-        {
-            "global_step": 90,
-            "epoch": 22.5,
-            "loss": 0.001030398067086935,
-            "learning_rate": 1.6344409628621484e-05,
-            "grad_norm": 0.0582536980509758
-        },
-        {
-            "global_step": 91,
-            "epoch": 22.75,
-            "loss": 0.001805206760764122,
-            "learning_rate": 1.536378232452003e-05,
-            "grad_norm": 0.3588670790195465
-        },
-        {
-            "global_step": 92,
-            "epoch": 23.0,
-            "loss": 0.0013909051194787025,
-            "learning_rate": 1.440812581653298e-05,
-            "grad_norm": 0.15705862641334534
-        },
-        {
-            "global_step": 93,
-            "epoch": 23.25,
-            "loss": 0.0007190693868324161,
-            "learning_rate": 1.3478129080114848e-05,
-            "grad_norm": 0.03828652575612068
-        },
-        {
-            "global_step": 94,
-            "epoch": 23.5,
-            "loss": 0.00025069594266824424,
-            "learning_rate": 1.257446259144494e-05,
-            "grad_norm": 0.023200809955596924
-        },
-        {
-            "global_step": 95,
-            "epoch": 23.75,
-            "loss": 0.0011277927551418543,
-            "learning_rate": 1.1697777844051105e-05,
-            "grad_norm": 0.04129434749484062
-        },
-        {
-            "global_step": 96,
-            "epoch": 24.0,
-            "loss": 0.0009472159435972571,
-            "learning_rate": 1.0848706879118892e-05,
-            "grad_norm": 0.04913812503218651
-        },
-        {
-            "global_step": 97,
-            "epoch": 24.25,
-            "loss": 0.0007696544635109603,
-            "learning_rate": 1.0027861829824952e-05,
-            "grad_norm": 0.04487694054841995
-        },
-        {
-            "global_step": 98,
-            "epoch": 24.5,
-            "loss": 0.0009453248931095004,
-            "learning_rate": 9.235834480022787e-06,
-            "grad_norm": 0.22460322082042694
-        },
-        {
-            "global_step": 99,
-            "epoch": 24.75,
-            "loss": 0.000631998700555414,
-            "learning_rate": 8.473195837599418e-06,
-            "grad_norm": 0.03229273483157158
-        },
-        {
-            "global_step": 100,
-            "epoch": 25.0,
-            "loss": 0.0006901748711243272,
-            "learning_rate": 7.740495722810271e-06,
-            "grad_norm": 0.03259923681616783
-        },
-        {
-            "global_step": 101,
-            "epoch": 25.25,
-            "loss": 0.0003148592368233949,
-            "learning_rate": 7.038262371889159e-06,
-            "grad_norm": 0.022936590015888214
-        },
-        {
-            "global_step": 102,
-            "epoch": 25.5,
-            "loss": 0.0004651989438571036,
-            "learning_rate": 6.367002056219284e-06,
-            "grad_norm": 0.02703242376446724
-        },
-        {
-            "global_step": 103,
-            "epoch": 25.75,
-            "loss": 0.0010305196046829224,
-            "learning_rate": 5.727198717339511e-06,
-            "grad_norm": 0.041206229478120804
-        },
-        {
-            "global_step": 104,
-            "epoch": 26.0,
-            "loss": 0.000634815136436373,
-            "learning_rate": 5.1193136180493095e-06,
-            "grad_norm": 0.08993884176015854
-        },
-        {
-            "global_step": 105,
-            "epoch": 26.25,
-            "loss": 0.00019032439740840346,
-            "learning_rate": 4.54378500986381e-06,
-            "grad_norm": 0.017092950642108917
-        },
-        {
-            "global_step": 106,
-            "epoch": 26.5,
-            "loss": 0.0008260362083092332,
-            "learning_rate": 4.001027817058789e-06,
-            "grad_norm": 0.036896709352731705
-        },
-        {
-            "global_step": 107,
-            "epoch": 26.75,
-            "loss": 0.0005347628612071276,
-            "learning_rate": 3.4914333375330898e-06,
-            "grad_norm": 0.032362014055252075
-        },
-        {
-            "global_step": 108,
-            "epoch": 27.0,
-            "loss": 0.0005628281505778432,
-            "learning_rate": 3.0153689607045845e-06,
-            "grad_norm": 0.020569942891597748
-        },
-        {
-            "global_step": 109,
-            "epoch": 27.25,
-            "loss": 0.0006590321427211165,
-            "learning_rate": 2.573177902642726e-06,
-            "grad_norm": 0.033200304955244064
-        },
-        {
-            "global_step": 110,
-            "epoch": 27.5,
-            "loss": 0.0005788324633613229,
-            "learning_rate": 2.1651789586287442e-06,
-            "grad_norm": 0.03066444955766201
-        },
-        {
-            "global_step": 111,
-            "epoch": 27.75,
-            "loss": 0.0002574412210378796,
-            "learning_rate": 1.7916662733218847e-06,
-            "grad_norm": 0.015490197576582432
-        },
-        {
-            "global_step": 112,
-            "epoch": 28.0,
-            "loss": 0.0007605571881867945,
-            "learning_rate": 1.4529091286973995e-06,
-            "grad_norm": 0.06880451738834381
-        },
-        {
-            "global_step": 113,
-            "epoch": 28.25,
-            "loss": 0.0004236309032421559,
-            "learning_rate": 1.1491517499091498e-06,
-            "grad_norm": 0.17912079393863678
-        },
-        {
-            "global_step": 114,
-            "epoch": 28.5,
-            "loss": 0.0008066121954470873,
-            "learning_rate": 8.806131292167618e-07,
-            "grad_norm": 0.035754382610321045
-        },
-        {
-            "global_step": 115,
-            "epoch": 28.75,
-            "loss": 0.000279993808362633,
-            "learning_rate": 6.474868681043578e-07,
-            "grad_norm": 0.019517874345183372
-        },
-        {
-            "global_step": 116,
-            "epoch": 29.0,
-            "loss": 0.0005598465213552117,
-            "learning_rate": 4.4994103770457653e-07,
-            "grad_norm": 0.021198801696300507
-        },
-        {
-            "global_step": 117,
-            "epoch": 29.25,
-            "loss": 0.000262636283878237,
-            "learning_rate": 2.8811805762860576e-07,
-            "grad_norm": 0.015968313440680504
-        },
-        {
-            "global_step": 118,
-            "epoch": 29.5,
-            "loss": 0.000800407025963068,
-            "learning_rate": 1.6213459328950352e-07,
-            "grad_norm": 0.03289778530597687
-        },
-        {
-            "global_step": 119,
-            "epoch": 29.75,
-            "loss": 0.0005571640795096755,
-            "learning_rate": 7.208147179291192e-08,
-            "grad_norm": 0.033743325620889664
-        },
-        {
-            "global_step": 120,
-            "epoch": 30.0,
-            "loss": 0.00039453001227229834,
-            "learning_rate": 1.802361645573125e-08,
-            "grad_norm": 0.02658260241150856
-        },
-        {
-            "global_step": 120,
-            "epoch": 30.0,
-            "loss": null,
-            "learning_rate": null,
-            "grad_norm": null
-        }
-    ]
-}

gemma4_lora/processor/chat_template.jinja

@@ -1,330 +0,0 @@
-{%- macro format_parameters(properties, required) -%}
-    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
-    {%- set ns = namespace(found_first=false) -%}
-    {%- for key, value in properties | dictsort -%}
-        {%- set add_comma = false -%}
-        {%- if key not in standard_keys -%}
-            {%- if ns.found_first %},{% endif -%}
-            {%- set ns.found_first = true -%}
-            {{ key }}:{
-            {%- if value['description'] -%}
-                description:<|"|>{{ value['description'] }}<|"|>
-                {%- set add_comma = true -%}
-            {%- endif -%}
-            {%- if value['type'] | upper == 'STRING' -%}
-                {%- if value['enum'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    enum:{{ format_argument(value['enum']) }}
-                {%- endif -%}
-            {%- elif value['type'] | upper == 'ARRAY' -%}
-                {%- if value['items'] is mapping and value['items'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    items:{
-                    {%- set ns_items = namespace(found_first=false) -%}
-                    {%- for item_key, item_value in value['items'] | dictsort -%}
-                        {%- if item_value is not none -%}
-                            {%- if ns_items.found_first %},{% endif -%}
-                            {%- set ns_items.found_first = true -%}
-                            {%- if item_key == 'properties' -%}
-                                properties:{
-                                {%- if item_value is mapping -%}
-                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
-                                {%- endif -%}
-                                }
-                            {%- elif item_key == 'required' -%}
-                                required:[
-                                {%- for req_item in item_value -%}
-                                    <|"|>{{- req_item -}}<|"|>
-                                    {%- if not loop.last %},{% endif -%}
-                                {%- endfor -%}
-                                ]
-                            {%- elif item_key == 'type' -%}
-                                {%- if item_value is string -%}
-                                    type:{{ format_argument(item_value | upper) }}
-                                {%- else -%}
-                                    type:{{ format_argument(item_value | map('upper') | list) }}
-                                {%- endif -%}
-                            {%- else -%}
-                                {{ item_key }}:{{ format_argument(item_value) }}
-                            {%- endif -%}
-                        {%- endif -%}
-                    {%- endfor -%}
-                    }
-                {%- endif -%}
-            {%- endif -%}
-            {%- if value['nullable'] %}
-                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                nullable:true
-            {%- endif -%}
-            {%- if value['type'] | upper == 'OBJECT' -%}
-                {%- if value['properties'] is defined and value['properties'] is mapping -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    properties:{
-                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
-                    }
-                {%- elif value is mapping -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    properties:{
-                    {{- format_parameters(value, value['required'] | default([])) -}}
-                    }
-                {%- endif -%}
-                {%- if value['required'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    required:[
-                    {%- for item in value['required'] | default([]) -%}
-                        <|"|>{{- item -}}<|"|>
-                        {%- if not loop.last %},{% endif -%}
-                    {%- endfor -%}
-                    ]
-                {%- endif -%}
-            {%- endif -%}
-            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-            type:<|"|>{{ value['type'] | upper }}<|"|>}
-        {%- endif -%}
-    {%- endfor -%}
-{%- endmacro -%}
-{%- macro format_function_declaration(tool_data) -%}
-    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
-    {%- set params = tool_data['function']['parameters'] -%}
-    {%- if params -%}
-        ,parameters:{
-        {%- if params['properties'] -%}
-            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
-        {%- endif -%}
-        {%- if params['required'] -%}
-            required:[
-            {%- for item in params['required'] -%}
-                <|"|>{{- item -}}<|"|>
-                {{- ',' if not loop.last -}}
-            {%- endfor -%}
-            ],
-        {%- endif -%}
-        {%- if params['type'] -%}
-            type:<|"|>{{- params['type'] | upper -}}<|"|>}
-        {%- endif -%}
-    {%- endif -%}
-    {%- if 'response' in tool_data['function'] -%}
-        {%- set response_declaration = tool_data['function']['response'] -%}
-        ,response:{
-        {%- if response_declaration['description'] -%}
-            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
-        {%- endif -%}
-        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
-            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
-        {%- endif -%}
-    {%- endif -%}
-    }
-{%- endmacro -%}
-{%- macro format_argument(argument, escape_keys=True) -%}
-    {%- if argument is string -%}
-        {{- '<|"|>' + argument + '<|"|>' -}}
-    {%- elif argument is boolean -%}
-        {{- 'true' if argument else 'false' -}}
-    {%- elif argument is mapping -%}
-        {{- '{' -}}
-        {%- set ns = namespace(found_first=false) -%}
-        {%- for key, value in argument | dictsort -%}
-            {%- if ns.found_first %},{% endif -%}
-            {%- set ns.found_first = true -%}
-            {%- if escape_keys -%}
-                {{- '<|"|>' + key + '<|"|>' -}}
-            {%- else -%}
-                {{- key -}}
-            {%- endif -%}
-            :{{- format_argument(value, escape_keys=escape_keys) -}}
-        {%- endfor -%}
-        {{- '}' -}}
-    {%- elif argument is sequence -%}
-        {{- '[' -}}
-        {%- for item in argument -%}
-            {{- format_argument(item, escape_keys=escape_keys) -}}
-            {%- if not loop.last %},{% endif -%}
-        {%- endfor -%}
-        {{- ']' -}}
-    {%- else -%}
-        {{- argument -}}
-    {%- endif -%}
-{%- endmacro -%}
-{%- macro strip_thinking(text) -%}
-    {%- set ns = namespace(result='') -%}
-    {%- for part in text.split('<channel|>') -%}
-        {%- if '<|channel>' in part -%}
-            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
-        {%- else -%}
-            {%- set ns.result = ns.result + part -%}
-        {%- endif -%}
-    {%- endfor -%}
-    {{- ns.result | trim -}}
-{%- endmacro -%}
-{%- macro format_tool_response_block(tool_name, response) -%}
-    {{- '<|tool_response>' -}}
-    {%- if response is mapping -%}
-        {{- 'response:' + tool_name + '{' -}}
-        {%- for key, value in response | dictsort -%}
-            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
-            {%- if not loop.last %},{% endif -%}
-        {%- endfor -%}
-        {{- '}' -}}
-    {%- else -%}
-        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
-    {%- endif -%}
-    {{- '<tool_response|>' -}}
-{%- endmacro -%}
-{%- set ns = namespace(prev_message_type=None) -%}
-{%- set loop_messages = messages -%}
-{{- bos_token -}}
-{#- Handle System/Tool Definitions Block -#}
-{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
-    {{- '<|turn>system\n' -}}
-    {#- Inject Thinking token at the very top of the FIRST system turn -#}
-    {%- if enable_thinking is defined and enable_thinking -%}
-        {{- '<|think|>\n' -}}
-        {%- set ns.prev_message_type = 'think' -%}
-    {%- endif -%}
-    {%- if messages[0]['role'] in ['system', 'developer'] -%}
-        {{- messages[0]['content'] | trim -}}
-        {%- set loop_messages = messages[1:] -%}
-    {%- endif -%}
-    {%- if tools -%}
-        {%- for tool in tools %}
-            {{- '<|tool>' -}}
-            {{- format_function_declaration(tool) | trim -}}
-            {{- '<tool|>' -}}
-        {%- endfor %}
-        {%- set ns.prev_message_type = 'tool' -%}
-    {%- endif -%}
-    {{- '<turn|>\n' -}}
-{%- endif %}
-{#- Pre-scan: find last user message index for reasoning guard -#}
-{%- set ns_turn = namespace(last_user_idx=-1) -%}
-{%- for i in range(loop_messages | length) -%}
-    {%- if loop_messages[i]['role'] == 'user' -%}
-        {%- set ns_turn.last_user_idx = i -%}
-    {%- endif -%}
-{%- endfor -%}
-{#- Loop through messages -#}
-{%- for message in loop_messages -%}
-    {%- if message['role'] != 'tool' -%}
-    {%- set ns.prev_message_type = None -%}
-    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
-    {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
-    {%- set prev_nt = namespace(role=None, found=false) -%}
-    {%- if loop.index0 > 0 -%}
-        {%- for j in range(loop.index0 - 1, -1, -1) -%}
-            {%- if not prev_nt.found -%}
-                {%- if loop_messages[j]['role'] != 'tool' -%}
-                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
-                    {%- set prev_nt.found = true -%}
-                {%- endif -%}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- endif -%}
-    {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
-    {%- if not continue_same_model_turn -%}
-        {{- '<|turn>' + role + '\n' }}
-    {%- endif -%}
-    {#- Render reasoning/reasoning_content as thinking channel -#}
-    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
-    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
-        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
-    {%- endif -%}
-            {%- if message['tool_calls'] -%}
-                {%- for tool_call in message['tool_calls'] -%}
-                    {%- set function = tool_call['function'] -%}
-                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
-                    {%- if function['arguments'] is mapping -%}
-                        {%- set ns_args = namespace(found_first=false) -%}
-                        {%- for key, value in function['arguments'] | dictsort -%}
-                            {%- if ns_args.found_first %},{% endif -%}
-                            {%- set ns_args.found_first = true -%}
-                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
-                        {%- endfor -%}
-                    {%- elif function['arguments'] is string -%}
-                        {{- function['arguments'] -}}
-                    {%- endif -%}
-                    {{- '}<tool_call|>' -}}
-                {%- endfor -%}
-                {%- set ns.prev_message_type = 'tool_call' -%}
-            {%- endif -%}
-            {%- set ns_tr_out = namespace(flag=false) -%}
-            {%- if message.get('tool_responses') -%}
-                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
-                {%- for tool_response in message['tool_responses'] -%}
-                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
-                    {%- set ns_tr_out.flag = true -%}
-                    {%- set ns.prev_message_type = 'tool_response' -%}
-                {%- endfor -%}
-            {%- elif message.get('tool_calls') -%}
-                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
-                {%- set ns_tool_scan = namespace(stopped=false) -%}
-                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
-                    {%- if ns_tool_scan.stopped -%}
-                    {%- elif loop_messages[k]['role'] != 'tool' -%}
-                        {%- set ns_tool_scan.stopped = true -%}
-                    {%- else -%}
-                        {%- set follow = loop_messages[k] -%}
-                        {#- Resolve tool_call_id to function name -#}
-                        {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
-                        {%- for tc in message['tool_calls'] -%}
-                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
-                                {%- set ns_tname.name = tc['function']['name'] -%}
-                            {%- endif -%}
-                        {%- endfor -%}
-                        {#- Handle content as string or content-parts array -#}
-                        {%- set tool_body = follow.get('content') -%}
-                        {%- if tool_body is string -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- elif tool_body is sequence and tool_body is not string -%}
-                            {%- set ns_txt = namespace(s='') -%}
-                            {%- for part in tool_body -%}
-                                {%- if part.get('type') == 'text' -%}
-                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
-                                {%- endif -%}
-                            {%- endfor -%}
-                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
-                        {%- else -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- endif -%}
-                        {%- set ns_tr_out.flag = true -%}
-                        {%- set ns.prev_message_type = 'tool_response' -%}
-                    {%- endif -%}
-                {%- endfor -%}
-            {%- endif -%}
-            {%- if message['content'] is string -%}
-                {%- if role == 'model' -%}
-                    {{- strip_thinking(message['content']) -}}
-                {%- else -%}
-                    {{- message['content'] | trim -}}
-                {%- endif -%}
-            {%- elif message['content'] is sequence -%}
-                {%- for item in message['content'] -%}
-                    {%- if item['type'] == 'text' -%}
-                        {%- if role == 'model' -%}
-                            {{- strip_thinking(item['text']) -}}
-                        {%- else -%}
-                            {{- item['text'] | trim -}}
-                        {%- endif -%}
-                    {%- elif item['type'] == 'image' -%}
-                        {{- '<|image|>' -}}
-                        {%- set ns.prev_message_type = 'image' -%}
-                    {%- elif item['type'] == 'audio' -%}
-                        {{- '<|audio|>' -}}
-                        {%- set ns.prev_message_type = 'audio' -%}
-                    {%- elif item['type'] == 'video' -%}
-                        {{- '<|video|>' -}}
-                        {%- set ns.prev_message_type = 'video' -%}
-                    {%- endif -%}
-                {%- endfor -%}
-            {%- endif -%}
-        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
-            {{- '<|tool_response>' -}}
-        {%- elif not (ns_tr_out.flag and not message.get('content')) -%}
-            {{- '<turn|>\n' -}}
-        {%- endif -%}
-    {%- endif -%}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
-        {{- '<|turn>model\n' -}}
-    {%- endif -%}
-{%- endif -%}

gemma4_lora/processor/processor_config.json

@@ -1,290 +0,0 @@
-{
-  "audio_ms_per_token": 40,
-  "audio_seq_length": 750,
-  "feature_extractor": {
-    "audio_ms_per_token": 40,
-    "audio_seq_length": 750,
-    "dither": 0.0,
-    "feature_extractor": {
-      "dither": 0.0,
-      "feature_extractor_type": "Gemma4AudioFeatureExtractor",
-      "feature_size": 128,
-      "fft_length": 512,
-      "fft_overdrive": false,
-      "frame_length": 320,
-      "hop_length": 160,
-      "input_scale_factor": 1.0,
-      "max_frequency": 8000.0,
-      "mel_floor": 0.001,
-      "min_frequency": 0.0,
-      "padding_side": "right",
-      "padding_value": 0.0,
-      "per_bin_mean": null,
-      "per_bin_stddev": null,
-      "preemphasis": 0.0,
-      "preemphasis_htk_flavor": true,
-      "return_attention_mask": true,
-      "sampling_rate": 16000
-    },
-    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
-    "feature_size": 128,
-    "fft_length": 512,
-    "fft_overdrive": false,
-    "frame_length": 320,
-    "hop_length": 160,
-    "image_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": false,
-      "do_rescale": true,
-      "do_resize": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_processor_type": "Gemma4ImageProcessor",
-      "image_seq_length": 280,
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 280,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098
-    },
-    "image_seq_length": 280,
-    "input_scale_factor": 1.0,
-    "max_frequency": 8000.0,
-    "mel_floor": 0.001,
-    "min_frequency": 0.0,
-    "padding_side": "right",
-    "padding_value": 0.0,
-    "per_bin_mean": null,
-    "per_bin_stddev": null,
-    "preemphasis": 0.0,
-    "preemphasis_htk_flavor": true,
-    "return_attention_mask": true,
-    "sampling_rate": 16000,
-    "video_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": true,
-      "do_rescale": true,
-      "do_resize": true,
-      "do_sample_frames": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 70,
-      "num_frames": 32,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098,
-      "return_metadata": false,
-      "video_processor_type": "Gemma4VideoProcessor"
-    }
-  },
-  "image_processor": {
-    "audio_ms_per_token": 40,
-    "audio_seq_length": 750,
-    "do_convert_rgb": true,
-    "do_normalize": false,
-    "do_rescale": true,
-    "do_resize": true,
-    "feature_extractor": {
-      "dither": 0.0,
-      "feature_extractor_type": "Gemma4AudioFeatureExtractor",
-      "feature_size": 128,
-      "fft_length": 512,
-      "fft_overdrive": false,
-      "frame_length": 320,
-      "hop_length": 160,
-      "input_scale_factor": 1.0,
-      "max_frequency": 8000.0,
-      "mel_floor": 0.001,
-      "min_frequency": 0.0,
-      "padding_side": "right",
-      "padding_value": 0.0,
-      "per_bin_mean": null,
-      "per_bin_stddev": null,
-      "preemphasis": 0.0,
-      "preemphasis_htk_flavor": true,
-      "return_attention_mask": true,
-      "sampling_rate": 16000
-    },
-    "image_mean": [
-      0.0,
-      0.0,
-      0.0
-    ],
-    "image_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": false,
-      "do_rescale": true,
-      "do_resize": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_processor_type": "Gemma4ImageProcessor",
-      "image_seq_length": 280,
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 280,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098
-    },
-    "image_processor_type": "Gemma4ImageProcessor",
-    "image_seq_length": 280,
-    "image_std": [
-      1.0,
-      1.0,
-      1.0
-    ],
-    "max_soft_tokens": 280,
-    "patch_size": 16,
-    "pooling_kernel_size": 3,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "video_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": true,
-      "do_rescale": true,
-      "do_resize": true,
-      "do_sample_frames": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 70,
-      "num_frames": 32,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098,
-      "return_metadata": false,
-      "video_processor_type": "Gemma4VideoProcessor"
-    }
-  },
-  "image_seq_length": 280,
-  "processor_class": "Gemma4Processor",
-  "video_processor": {
-    "audio_ms_per_token": 40,
-    "audio_seq_length": 750,
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "do_sample_frames": true,
-    "feature_extractor": {
-      "dither": 0.0,
-      "feature_extractor_type": "Gemma4AudioFeatureExtractor",
-      "feature_size": 128,
-      "fft_length": 512,
-      "fft_overdrive": false,
-      "frame_length": 320,
-      "hop_length": 160,
-      "input_scale_factor": 1.0,
-      "max_frequency": 8000.0,
-      "mel_floor": 0.001,
-      "min_frequency": 0.0,
-      "padding_side": "right",
-      "padding_value": 0.0,
-      "per_bin_mean": null,
-      "per_bin_stddev": null,
-      "preemphasis": 0.0,
-      "preemphasis_htk_flavor": true,
-      "return_attention_mask": true,
-      "sampling_rate": 16000
-    },
-    "image_mean": [
-      0.0,
-      0.0,
-      0.0
-    ],
-    "image_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": false,
-      "do_rescale": true,
-      "do_resize": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_processor_type": "Gemma4ImageProcessor",
-      "image_seq_length": 280,
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 280,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098
-    },
-    "image_seq_length": 280,
-    "image_std": [
-      1.0,
-      1.0,
-      1.0
-    ],
-    "max_soft_tokens": 70,
-    "num_frames": 32,
-    "patch_size": 16,
-    "pooling_kernel_size": 3,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "return_metadata": false,
-    "video_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": true,
-      "do_rescale": true,
-      "do_resize": true,
-      "do_sample_frames": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 70,
-      "num_frames": 32,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098,
-      "return_metadata": false,
-      "video_processor_type": "Gemma4VideoProcessor"
-    },
-    "video_processor_type": "Gemma4VideoProcessor"
-  }
-}

gemma4_lora/processor/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
-size 32169626

gemma4_lora/processor/tokenizer_config.json

@@ -1,96 +0,0 @@
-{
-  "audio_token": "<|audio|>",
-  "backend": "tokenizers",
-  "boa_token": "<|audio>",
-  "boi_token": "<|image>",
-  "bos_token": "<bos>",
-  "eoa_token": "<audio|>",
-  "eoc_token": "<channel|>",
-  "eoi_token": "<image|>",
-  "eos_token": "<eos>",
-  "eot_token": "<turn|>",
-  "escape_token": "<|\"|>",
-  "etc_token": "<tool_call|>",
-  "etd_token": "<tool|>",
-  "etr_token": "<tool_response|>",
-  "extra_special_tokens": [
-    "<|video|>"
-  ],
-  "image_token": "<|image|>",
-  "is_local": false,
-  "local_files_only": false,
-  "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
-  "model_specific_special_tokens": {
-    "audio_token": "<|audio|>",
-    "boa_token": "<|audio>",
-    "boi_token": "<|image>",
-    "eoa_token": "<audio|>",
-    "eoc_token": "<channel|>",
-    "eoi_token": "<image|>",
-    "eot_token": "<turn|>",
-    "escape_token": "<|\"|>",
-    "etc_token": "<tool_call|>",
-    "etd_token": "<tool|>",
-    "etr_token": "<tool_response|>",
-    "image_token": "<|image|>",
-    "soc_token": "<|channel>",
-    "sot_token": "<|turn>",
-    "stc_token": "<|tool_call>",
-    "std_token": "<|tool>",
-    "str_token": "<|tool_response>",
-    "think_token": "<|think|>"
-  },
-  "pad_token": "<pad>",
-  "padding_side": "right",
-  "processor_class": "Gemma4Processor",
-  "response_schema": {
-    "properties": {
-      "content": {
-        "type": "string"
-      },
-      "role": {
-        "const": "assistant"
-      },
-      "thinking": {
-        "type": "string"
-      },
-      "tool_calls": {
-        "items": {
-          "properties": {
-            "function": {
-              "properties": {
-                "arguments": {
-                  "additionalProperties": {},
-                  "type": "object",
-                  "x-parser": "gemma4-tool-call"
-                },
-                "name": {
-                  "type": "string"
-                }
-              },
-              "type": "object",
-              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
-            },
-            "type": {
-              "const": "function"
-            }
-          },
-          "type": "object"
-        },
-        "type": "array",
-        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
-      }
-    },
-    "type": "object",
-    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
-  },
-  "soc_token": "<|channel>",
-  "sot_token": "<|turn>",
-  "stc_token": "<|tool_call>",
-  "std_token": "<|tool>",
-  "str_token": "<|tool_response>",
-  "think_token": "<|think|>",
-  "tokenizer_class": "GemmaTokenizer",
-  "unk_token": "<unk>"
-}

gemma4_lora/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:83fff43465ff39aa286290f3bdba0ee1b978483b463631d8eb11dee70e2790e7
-size 5265

gemma4_lora/training_metadata.json

@@ -1,1433 +0,0 @@
-{
-    "base_model": "coder3101/gemma-4-E2B-it-heretic",
-    "training_method": "QLoRA",
-    "quantization": "NF4 4-bit",
-    "compute_dtype": "float16",
-    "lora_dtype": "float32",
-    "lora_rank": 16,
-    "lora_alpha": 16,
-    "lora_dropout": 0.05,
-    "target_modules": "all-linear",
-    "optimizer": "paged_adamw_8bit",
-    "world_size": 2,
-    "distributed_method": "DDP",
-    "ddp_find_unused_parameters": true,
-    "per_device_batch_size": 1,
-    "gradient_accumulation": 1,
-    "epochs": 30,
-    "estimated_optimizer_updates": 120,
-    "observed_gradient_checks": 120,
-    "trainer_global_step": 120,
-    "learning_rate": 0.0001,
-    "lr_scheduler_type": "cosine",
-    "weight_decay": 0.01,
-    "warmup_ratio": 0.03,
-    "warmup_steps": 3,
-    "max_grad_norm": 0.3,
-    "gradient_checkpointing": true,
-    "fp16_initial_scale": 2048.0,
-    "fp16_final_scale": 2048.0,
-    "fp16_min_final_scale": 512.0,
-    "max_skipped_optimizer_steps": 2,
-    "training_examples": 7,
-    "validation_examples": 0,
-    "dataset_repository": "codeShare/gemma4-precomputed-dataset",
-    "dataset_path": "gemma4_preencoded_dataset",
-    "training_input": [
-        "input_ids",
-        "attention_mask",
-        "pixel_values",
-        "other_precomputed_processor_features"
-    ],
-    "training_labels": "precomputed completion-only labels",
-    "raw_images_loaded_during_training": false,
-    "raw_text_loaded_during_training": false,
-    "processor_called_during_training": false,
-    "training_loss": 0.5774162989731849,
-    "training_metrics": {
-        "train_runtime": 403.7248,
-        "train_samples_per_second": 0.52,
-        "train_steps_per_second": 0.297,
-        "total_flos": 3325449084076032.0,
-        "train_loss": 0.5774162989731849,
-        "epoch": 30.0
-    },
-    "validation_metrics": {},
-    "training_seconds": 405.704416513443,
-    "training_seed": 1234,
-    "gpu_peak_allocated_gb": 11.1423978805542,
-    "gradient_health": {
-        "gradient_checks": 120,
-        "skipped_optimizer_steps": 0,
-        "skipped_step_indices": [],
-        "nonfinite_gradient_steps": [],
-        "nonfinite_gradient_tensors": 0,
-        "no_gradient_steps": [],
-        "gradient_norms": [
-            0.2999999967057757,
-            0.29999993283753906,
-            0.2999999882627466,
-            0.29999995549701025,
-            0.2999999056871044,
-            0.29999997674311024,
-            0.29999996019639635,
-            0.2999999331868226,
-            0.2999999190714327,
-            0.29999994453961754,
-            0.29999992767652045,
-            0.2999999171052898,
-            0.299999891168433,
-            0.2999999387562522,
-            0.2999998559474201,
-            0.2999998651608199,
-            0.29999989888361955,
-            0.299999860837114,
-            0.2999998637005364,
-            0.2999999487365302,
-            0.29999991210927746,
-            0.29999983302762295,
-            0.29999986467178447,
-            0.2999999246373012,
-            0.2999998710247092,
-            0.29999993885001613,
-            0.2999998562013249,
-            0.2999997898603423,
-            0.2999998988001732,
-            0.2999997968720858,
-            0.29999981960907923,
-            0.29999979953123646,
-            0.29999993062910396,
-            0.2999998143369396,
-            0.29999988013220563,
-            0.29999991627050243,
-            0.2999998549485208,
-            0.29999983698781824,
-            0.29999988739171235,
-            0.29999984926746825,
-            0.29999978238735703,
-            0.29999989584211356,
-            0.29999983784788814,
-            0.2999997514863681,
-            0.2999997904095978,
-            0.29999987607479484,
-            0.29999983808389075,
-            0.29999982376193984,
-            0.299999843238001,
-            0.2999997380879359,
-            0.29999984200200724,
-            0.2999998571695013,
-            0.29999993043955364,
-            0.2999998548770266,
-            0.29999998275241463,
-            0.2999998385367787,
-            0.29999985670904267,
-            0.2999998650251881,
-            0.29999990770273105,
-            0.2999997907082759,
-            0.29999975991044014,
-            0.2999998386237497,
-            0.29999976701075326,
-            0.2999996384655255,
-            0.2999998653212779,
-            0.29999942298684046,
-            0.29999983928156604,
-            0.2999998335974349,
-            0.2999997630936651,
-            0.29999957808098776,
-            0.2999993324745417,
-            0.29999964148031316,
-            0.2999993150217098,
-            0.2999994021040341,
-            0.29999970079639704,
-            0.2999996212821266,
-            0.29999923384458965,
-            0.2400580492521267,
-            0.2999991859568465,
-            0.29999952391317286,
-            0.29999943933173767,
-            0.23904489591558,
-            0.22082136702898114,
-            0.2999996496006251,
-            0.29999960097840744,
-            0.06084565240294252,
-            0.29999985714989785,
-            0.27001140019986175,
-            0.24196433419393892,
-            0.05825369805852839,
-            0.2999991469929516,
-            0.15705863171793738,
-            0.03828652322329344,
-            0.023200811595227796,
-            0.04129434956180859,
-            0.049138123368485935,
-            0.04487694375693962,
-            0.224603229033112,
-            0.03229273522786361,
-            0.032599237798871604,
-            0.022936590735817202,
-            0.02703242390409454,
-            0.04120622897715978,
-            0.08993883373234765,
-            0.017092950887663435,
-            0.0368967124461106,
-            0.032362015474763244,
-            0.020569942602627754,
-            0.033200306693477066,
-            0.030664452587451013,
-            0.01549019716854724,
-            0.06880451374310592,
-            0.1791207763483352,
-            0.035754383235644914,
-            0.0195178739292786,
-            0.021198802830342003,
-            0.0159683130342503,
-            0.03289778612980872,
-            0.03374332580161473,
-            0.026582601743105054
-        ],
-        "gradient_tensor_counts": [
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780,
-            780
-        ],
-        "grad_scaler_values": [
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0,
-            2048.0
-        ],
-        "loss_history": [
-            {
-                "global_step": 1,
-                "epoch": 0.25,
-                "loss": 3.0028076171875,
-                "learning_rate": 0.0,
-                "grad_norm": 5.735446453094482
-            },
-            {
-                "global_step": 2,
-                "epoch": 0.5,
-                "loss": 2.5738320350646973,
-                "learning_rate": 3.3333333333333335e-05,
-                "grad_norm": 4.246273517608643
-            },
-            {
-                "global_step": 3,
-                "epoch": 0.75,
-                "loss": 3.9848618507385254,
-                "learning_rate": 6.666666666666667e-05,
-                "grad_norm": 7.595849990844727
-            },
-            {
-                "global_step": 4,
-                "epoch": 1.0,
-                "loss": 2.5158143043518066,
-                "learning_rate": 0.0001,
-                "grad_norm": 4.926611423492432
-            },
-            {
-                "global_step": 5,
-                "epoch": 1.25,
-                "loss": 2.6317954063415527,
-                "learning_rate": 9.998197638354428e-05,
-                "grad_norm": 3.7285847663879395
-            },
-            {
-                "global_step": 6,
-                "epoch": 1.5,
-                "loss": 3.391207218170166,
-                "learning_rate": 9.992791852820709e-05,
-                "grad_norm": 6.960104465484619
-            },
-            {
-                "global_step": 7,
-                "epoch": 1.75,
-                "loss": 1.7886579036712646,
-                "learning_rate": 9.983786540671051e-05,
-                "grad_norm": 3.496877431869507
-            },
-            {
-                "global_step": 8,
-                "epoch": 2.0,
-                "loss": 1.9815987348556519,
-                "learning_rate": 9.97118819423714e-05,
-                "grad_norm": 2.860832691192627
-            },
-            {
-                "global_step": 9,
-                "epoch": 2.25,
-                "loss": 1.775098443031311,
-                "learning_rate": 9.955005896229543e-05,
-                "grad_norm": 3.4511520862579346
-            },
-            {
-                "global_step": 10,
-                "epoch": 2.5,
-                "loss": 1.6050281524658203,
-                "learning_rate": 9.935251313189564e-05,
-                "grad_norm": 3.639047384262085
-            },
-            {
-                "global_step": 11,
-                "epoch": 2.75,
-                "loss": 2.5201776027679443,
-                "learning_rate": 9.911938687078324e-05,
-                "grad_norm": 3.662109613418579
-            },
-            {
-                "global_step": 12,
-                "epoch": 3.0,
-                "loss": 1.7487728595733643,
-                "learning_rate": 9.885084825009086e-05,
-                "grad_norm": 2.736379384994507
-            },
-            {
-                "global_step": 13,
-                "epoch": 3.25,
-                "loss": 1.685441255569458,
-                "learning_rate": 9.85470908713026e-05,
-                "grad_norm": 2.4754011631011963
-            },
-            {
-                "global_step": 14,
-                "epoch": 3.5,
-                "loss": 2.0612027645111084,
-                "learning_rate": 9.820833372667812e-05,
-                "grad_norm": 2.888793468475342
-            },
-            {
-                "global_step": 15,
-                "epoch": 3.75,
-                "loss": 1.2462215423583984,
-                "learning_rate": 9.783482104137127e-05,
-                "grad_norm": 2.124307632446289
-            },
-            {
-                "global_step": 16,
-                "epoch": 4.0,
-                "loss": 1.5945758819580078,
-                "learning_rate": 9.742682209735727e-05,
-                "grad_norm": 2.0276503562927246
-            },
-            {
-                "global_step": 17,
-                "epoch": 4.25,
-                "loss": 1.8966870307922363,
-                "learning_rate": 9.698463103929542e-05,
-                "grad_norm": 2.2649166584014893
-            },
-            {
-                "global_step": 18,
-                "epoch": 4.5,
-                "loss": 1.220649242401123,
-                "learning_rate": 9.650856666246693e-05,
-                "grad_norm": 1.7242375612258911
-            },
-            {
-                "global_step": 19,
-                "epoch": 4.75,
-                "loss": 1.4429657459259033,
-                "learning_rate": 9.599897218294122e-05,
-                "grad_norm": 1.889949083328247
-            },
-            {
-                "global_step": 20,
-                "epoch": 5.0,
-                "loss": 1.791039228439331,
-                "learning_rate": 9.54562149901362e-05,
-                "grad_norm": 3.159863233566284
-            },
-            {
-                "global_step": 21,
-                "epoch": 5.25,
-                "loss": 1.2491681575775146,
-                "learning_rate": 9.48806863819507e-05,
-                "grad_norm": 2.510749340057373
-            },
-            {
-                "global_step": 22,
-                "epoch": 5.5,
-                "loss": 0.9549908638000488,
-                "learning_rate": 9.42728012826605e-05,
-                "grad_norm": 1.8189880847930908
-            },
-            {
-                "global_step": 23,
-                "epoch": 5.75,
-                "loss": 1.671364188194275,
-                "learning_rate": 9.363299794378073e-05,
-                "grad_norm": 1.8584535121917725
-            },
-            {
-                "global_step": 24,
-                "epoch": 6.0,
-                "loss": 1.1979198455810547,
-                "learning_rate": 9.296173762811085e-05,
-                "grad_norm": 2.8647730350494385
-            },
-            {
-                "global_step": 25,
-                "epoch": 6.25,
-                "loss": 1.0778791904449463,
-                "learning_rate": 9.225950427718975e-05,
-                "grad_norm": 2.2521347999572754
-            },
-            {
-                "global_step": 26,
-                "epoch": 6.5,
-                "loss": 0.9626718759536743,
-                "learning_rate": 9.152680416240059e-05,
-                "grad_norm": 2.9740376472473145
-            },
-            {
-                "global_step": 27,
-                "epoch": 6.75,
-                "loss": 1.4524807929992676,
-                "learning_rate": 9.076416551997721e-05,
-                "grad_norm": 1.8301929235458374
-            },
-            {
-                "global_step": 28,
-                "epoch": 7.0,
-                "loss": 0.9822371006011963,
-                "learning_rate": 8.997213817017507e-05,
-                "grad_norm": 1.515589952468872
-            },
-            {
-                "global_step": 29,
-                "epoch": 7.25,
-                "loss": 1.3678052425384521,
-                "learning_rate": 8.915129312088112e-05,
-                "grad_norm": 2.429225444793701
-            },
-            {
-                "global_step": 30,
-                "epoch": 7.5,
-                "loss": 0.7263110876083374,
-                "learning_rate": 8.83022221559489e-05,
-                "grad_norm": 1.299315333366394
-            },
-            {
-                "global_step": 31,
-                "epoch": 7.75,
-                "loss": 0.8736010789871216,
-                "learning_rate": 8.742553740855506e-05,
-                "grad_norm": 1.5025458335876465
-            },
-            {
-                "global_step": 32,
-                "epoch": 8.0,
-                "loss": 0.9786587357521057,
-                "learning_rate": 8.652187091988517e-05,
-                "grad_norm": 1.3604384660720825
-            },
-            {
-                "global_step": 33,
-                "epoch": 8.25,
-                "loss": 0.5913520455360413,
-                "learning_rate": 8.559187418346703e-05,
-                "grad_norm": 3.1408023834228516
-            },
-            {
-                "global_step": 34,
-                "epoch": 8.5,
-                "loss": 0.8007135391235352,
-                "learning_rate": 8.463621767547998e-05,
-                "grad_norm": 1.5192880630493164
-            },
-            {
-                "global_step": 35,
-                "epoch": 8.75,
-                "loss": 0.8744857311248779,
-                "learning_rate": 8.365559037137852e-05,
-                "grad_norm": 2.1710562705993652
-            },
-            {
-                "global_step": 36,
-                "epoch": 9.0,
-                "loss": 0.8190163373947144,
-                "learning_rate": 8.265069924917925e-05,
-                "grad_norm": 3.7557790279388428
-            },
-            {
-                "global_step": 37,
-                "epoch": 9.25,
-                "loss": 0.7986066341400146,
-                "learning_rate": 8.162226877976887e-05,
-                "grad_norm": 1.8751171827316284
-            },
-            {
-                "global_step": 38,
-                "epoch": 9.5,
-                "loss": 0.5472699403762817,
-                "learning_rate": 8.057104040460062e-05,
-                "grad_norm": 1.435860514640808
-            },
-            {
-                "global_step": 39,
-                "epoch": 9.75,
-                "loss": 0.728087306022644,
-                "learning_rate": 7.949777200115616e-05,
-                "grad_norm": 2.4945225715637207
-            },
-            {
-                "global_step": 40,
-                "epoch": 10.0,
-                "loss": 0.7109437584877014,
-                "learning_rate": 7.840323733655778e-05,
-                "grad_norm": 1.7653728723526
-            },
-            {
-                "global_step": 41,
-                "epoch": 10.25,
-                "loss": 0.4470646381378174,
-                "learning_rate": 7.728822550972523e-05,
-                "grad_norm": 1.2734816074371338
-            },
-            {
-                "global_step": 42,
-                "epoch": 10.5,
-                "loss": 0.7584569454193115,
-                "learning_rate": 7.615354038247888e-05,
-                "grad_norm": 2.3084428310394287
-            },
-            {
-                "global_step": 43,
-                "epoch": 10.75,
-                "loss": 0.46312659978866577,
-                "learning_rate": 7.500000000000001e-05,
-                "grad_norm": 1.7591501474380493
-            },
-            {
-                "global_step": 44,
-                "epoch": 11.0,
-                "loss": 0.45575660467147827,
-                "learning_rate": 7.38284360010654e-05,
-                "grad_norm": 1.154929518699646
-            },
-            {
-                "global_step": 45,
-                "epoch": 11.25,
-                "loss": 0.4252345860004425,
-                "learning_rate": 7.263969301848188e-05,
-                "grad_norm": 1.0464447736740112
-            },
-            {
-                "global_step": 46,
-                "epoch": 11.5,
-                "loss": 0.5287308692932129,
-                "learning_rate": 7.143462807015271e-05,
-                "grad_norm": 2.1150853633880615
-            },
-            {
-                "global_step": 47,
-                "epoch": 11.75,
-                "loss": 0.4766055643558502,
-                "learning_rate": 7.021410994121525e-05,
-                "grad_norm": 2.03830885887146
-            },
-            {
-                "global_step": 48,
-                "epoch": 12.0,
-                "loss": 0.23271411657333374,
-                "learning_rate": 6.897901855769483e-05,
-                "grad_norm": 1.4084392786026
-            },
-            {
-                "global_step": 49,
-                "epoch": 12.25,
-                "loss": 0.35807982087135315,
-                "learning_rate": 6.773024435212678e-05,
-                "grad_norm": 1.8897265195846558
-            },
-            {
-                "global_step": 50,
-                "epoch": 12.5,
-                "loss": 0.18392693996429443,
-                "learning_rate": 6.646868762160399e-05,
-                "grad_norm": 1.135053038597107
-            },
-            {
-                "global_step": 51,
-                "epoch": 12.75,
-                "loss": 0.4107872247695923,
-                "learning_rate": 6.519525787871235e-05,
-                "grad_norm": 1.7325575351715088
-            },
-            {
-                "global_step": 52,
-                "epoch": 13.0,
-                "loss": 0.295409232378006,
-                "learning_rate": 6.391087319582264e-05,
-                "grad_norm": 1.7553775310516357
-            },
-            {
-                "global_step": 53,
-                "epoch": 13.25,
-                "loss": 0.24841588735580444,
-                "learning_rate": 6.261645954321109e-05,
-                "grad_norm": 2.4505655765533447
-            },
-            {
-                "global_step": 54,
-                "epoch": 13.5,
-                "loss": 0.28180259466171265,
-                "learning_rate": 6.131295012148612e-05,
-                "grad_norm": 1.7769156694412231
-            },
-            {
-                "global_step": 55,
-                "epoch": 13.75,
-                "loss": 0.21721918880939484,
-                "learning_rate": 6.0001284688802226e-05,
-                "grad_norm": 8.174845695495605
-            },
-            {
-                "global_step": 56,
-                "epoch": 14.0,
-                "loss": 0.18195383250713348,
-                "learning_rate": 5.868240888334653e-05,
-                "grad_norm": 1.8216534852981567
-            },
-            {
-                "global_step": 57,
-                "epoch": 14.25,
-                "loss": 0.15293434262275696,
-                "learning_rate": 5.735727354158581e-05,
-                "grad_norm": 1.528199315071106
-            },
-            {
-                "global_step": 58,
-                "epoch": 14.5,
-                "loss": 0.18003931641578674,
-                "learning_rate": 5.602683401276615e-05,
-                "grad_norm": 1.7730704545974731
-            },
-            {
-                "global_step": 59,
-                "epoch": 14.75,
-                "loss": 0.16167467832565308,
-                "learning_rate": 5.469204947015897e-05,
-                "grad_norm": 2.5438311100006104
-            },
-            {
-                "global_step": 60,
-                "epoch": 15.0,
-                "loss": 0.06871137768030167,
-                "learning_rate": 5.335388221955012e-05,
-                "grad_norm": 1.244670033454895
-            },
-            {
-                "global_step": 61,
-                "epoch": 15.25,
-                "loss": 0.08273965865373611,
-                "learning_rate": 5.201329700547076e-05,
-                "grad_norm": 1.158942699432373
-            },
-            {
-                "global_step": 62,
-                "epoch": 15.5,
-                "loss": 0.1550861895084381,
-                "learning_rate": 5.0671260315669875e-05,
-                "grad_norm": 1.5921404361724854
-            },
-            {
-                "global_step": 63,
-                "epoch": 15.75,
-                "loss": 0.07742718607187271,
-                "learning_rate": 4.9328739684330137e-05,
-                "grad_norm": 1.2498779296875
-            },
-            {
-                "global_step": 64,
-                "epoch": 16.0,
-                "loss": 0.060180872678756714,
-                "learning_rate": 4.798670299452926e-05,
-                "grad_norm": 0.8160451650619507
-            },
-            {
-                "global_step": 65,
-                "epoch": 16.25,
-                "loss": 0.11217842251062393,
-                "learning_rate": 4.6646117780449876e-05,
-                "grad_norm": 2.351928472518921
-            },
-            {
-                "global_step": 66,
-                "epoch": 16.5,
-                "loss": 0.029149621725082397,
-                "learning_rate": 4.530795052984104e-05,
-                "grad_norm": 0.5133053064346313
-            },
-            {
-                "global_step": 67,
-                "epoch": 16.75,
-                "loss": 0.057295918464660645,
-                "learning_rate": 4.397316598723385e-05,
-                "grad_norm": 1.4209790229797363
-            },
-            {
-                "global_step": 68,
-                "epoch": 17.0,
-                "loss": 0.05391449108719826,
-                "learning_rate": 4.264272645841419e-05,
-                "grad_norm": 1.5596890449523926
-            },
-            {
-                "global_step": 69,
-                "epoch": 17.25,
-                "loss": 0.07454235851764679,
-                "learning_rate": 4.131759111665349e-05,
-                "grad_norm": 1.2337915897369385
-            },
-            {
-                "global_step": 70,
-                "epoch": 17.5,
-                "loss": 0.03401903435587883,
-                "learning_rate": 3.9998715311197785e-05,
-                "grad_norm": 0.718992292881012
-            },
-            {
-                "global_step": 71,
-                "epoch": 17.75,
-                "loss": 0.016408829018473625,
-                "learning_rate": 3.86870498785139e-05,
-                "grad_norm": 0.44305819272994995
-            },
-            {
-                "global_step": 72,
-                "epoch": 18.0,
-                "loss": 0.03439335897564888,
-                "learning_rate": 3.738354045678891e-05,
-                "grad_norm": 0.8151929974555969
-            },
-            {
-                "global_step": 73,
-                "epoch": 18.25,
-                "loss": 0.01341971568763256,
-                "learning_rate": 3.608912680417737e-05,
-                "grad_norm": 0.44037967920303345
-            },
-            {
-                "global_step": 74,
-                "epoch": 18.5,
-                "loss": 0.015053657814860344,
-                "learning_rate": 3.480474212128766e-05,
-                "grad_norm": 0.505387008190155
-            },
-            {
-                "global_step": 75,
-                "epoch": 18.75,
-                "loss": 0.020888736471533775,
-                "learning_rate": 3.3531312378396026e-05,
-                "grad_norm": 0.9699237942695618
-            },
-            {
-                "global_step": 76,
-                "epoch": 19.0,
-                "loss": 0.015053548850119114,
-                "learning_rate": 3.226975564787322e-05,
-                "grad_norm": 0.7767230868339539
-            },
-            {
-                "global_step": 77,
-                "epoch": 19.25,
-                "loss": 0.005396610591560602,
-                "learning_rate": 3.1020981442305184e-05,
-                "grad_norm": 0.40644827485084534
-            },
-            {
-                "global_step": 78,
-                "epoch": 19.5,
-                "loss": 0.004981599748134613,
-                "learning_rate": 2.978589005878476e-05,
-                "grad_norm": 0.2400580644607544
-            },
-            {
-                "global_step": 79,
-                "epoch": 19.75,
-                "loss": 0.004586038179695606,
-                "learning_rate": 2.8565371929847284e-05,
-                "grad_norm": 0.35911986231803894
-            },
-            {
-                "global_step": 80,
-                "epoch": 20.0,
-                "loss": 0.013846193440258503,
-                "learning_rate": 2.7360306981518146e-05,
-                "grad_norm": 0.644167959690094
-            },
-            {
-                "global_step": 81,
-                "epoch": 20.25,
-                "loss": 0.009072684682905674,
-                "learning_rate": 2.6171563998934605e-05,
-                "grad_norm": 0.559910237789154
-            },
-            {
-                "global_step": 82,
-                "epoch": 20.5,
-                "loss": 0.0030265708919614553,
-                "learning_rate": 2.500000000000001e-05,
-                "grad_norm": 0.2390448898077011
-            },
-            {
-                "global_step": 83,
-                "epoch": 20.75,
-                "loss": 0.0019349269568920135,
-                "learning_rate": 2.3846459617521128e-05,
-                "grad_norm": 0.220821350812912
-            },
-            {
-                "global_step": 84,
-                "epoch": 21.0,
-                "loss": 0.008226916193962097,
-                "learning_rate": 2.2711774490274766e-05,
-                "grad_norm": 0.8569097518920898
-            },
-            {
-                "global_step": 85,
-                "epoch": 21.25,
-                "loss": 0.007080879062414169,
-                "learning_rate": 2.1596762663442218e-05,
-                "grad_norm": 0.7534610629081726
-            },
-            {
-                "global_step": 86,
-                "epoch": 21.5,
-                "loss": 0.0010789937805384398,
-                "learning_rate": 2.050222799884387e-05,
-                "grad_norm": 0.06084565073251724
-            },
-            {
-                "global_step": 87,
-                "epoch": 21.75,
-                "loss": 0.0016643002163618803,
-                "learning_rate": 1.942895959539939e-05,
-                "grad_norm": 1.5307955741882324
-            },
-            {
-                "global_step": 88,
-                "epoch": 22.0,
-                "loss": 0.002636656863614917,
-                "learning_rate": 1.837773122023114e-05,
-                "grad_norm": 0.27001139521598816
-            },
-            {
-                "global_step": 89,
-                "epoch": 22.25,
-                "loss": 0.0008208074723370373,
-                "learning_rate": 1.734930075082076e-05,
-                "grad_norm": 0.24196434020996094
-            },
-            {
-                "global_step": 90,
-                "epoch": 22.5,
-                "loss": 0.001030398067086935,
-                "learning_rate": 1.6344409628621484e-05,
-                "grad_norm": 0.0582536980509758
-            },
-            {
-                "global_step": 91,
-                "epoch": 22.75,
-                "loss": 0.001805206760764122,
-                "learning_rate": 1.536378232452003e-05,
-                "grad_norm": 0.3588670790195465
-            },
-            {
-                "global_step": 92,
-                "epoch": 23.0,
-                "loss": 0.0013909051194787025,
-                "learning_rate": 1.440812581653298e-05,
-                "grad_norm": 0.15705862641334534
-            },
-            {
-                "global_step": 93,
-                "epoch": 23.25,
-                "loss": 0.0007190693868324161,
-                "learning_rate": 1.3478129080114848e-05,
-                "grad_norm": 0.03828652575612068
-            },
-            {
-                "global_step": 94,
-                "epoch": 23.5,
-                "loss": 0.00025069594266824424,
-                "learning_rate": 1.257446259144494e-05,
-                "grad_norm": 0.023200809955596924
-            },
-            {
-                "global_step": 95,
-                "epoch": 23.75,
-                "loss": 0.0011277927551418543,
-                "learning_rate": 1.1697777844051105e-05,
-                "grad_norm": 0.04129434749484062
-            },
-            {
-                "global_step": 96,
-                "epoch": 24.0,
-                "loss": 0.0009472159435972571,
-                "learning_rate": 1.0848706879118892e-05,
-                "grad_norm": 0.04913812503218651
-            },
-            {
-                "global_step": 97,
-                "epoch": 24.25,
-                "loss": 0.0007696544635109603,
-                "learning_rate": 1.0027861829824952e-05,
-                "grad_norm": 0.04487694054841995
-            },
-            {
-                "global_step": 98,
-                "epoch": 24.5,
-                "loss": 0.0009453248931095004,
-                "learning_rate": 9.235834480022787e-06,
-                "grad_norm": 0.22460322082042694
-            },
-            {
-                "global_step": 99,
-                "epoch": 24.75,
-                "loss": 0.000631998700555414,
-                "learning_rate": 8.473195837599418e-06,
-                "grad_norm": 0.03229273483157158
-            },
-            {
-                "global_step": 100,
-                "epoch": 25.0,
-                "loss": 0.0006901748711243272,
-                "learning_rate": 7.740495722810271e-06,
-                "grad_norm": 0.03259923681616783
-            },
-            {
-                "global_step": 101,
-                "epoch": 25.25,
-                "loss": 0.0003148592368233949,
-                "learning_rate": 7.038262371889159e-06,
-                "grad_norm": 0.022936590015888214
-            },
-            {
-                "global_step": 102,
-                "epoch": 25.5,
-                "loss": 0.0004651989438571036,
-                "learning_rate": 6.367002056219284e-06,
-                "grad_norm": 0.02703242376446724
-            },
-            {
-                "global_step": 103,
-                "epoch": 25.75,
-                "loss": 0.0010305196046829224,
-                "learning_rate": 5.727198717339511e-06,
-                "grad_norm": 0.041206229478120804
-            },
-            {
-                "global_step": 104,
-                "epoch": 26.0,
-                "loss": 0.000634815136436373,
-                "learning_rate": 5.1193136180493095e-06,
-                "grad_norm": 0.08993884176015854
-            },
-            {
-                "global_step": 105,
-                "epoch": 26.25,
-                "loss": 0.00019032439740840346,
-                "learning_rate": 4.54378500986381e-06,
-                "grad_norm": 0.017092950642108917
-            },
-            {
-                "global_step": 106,
-                "epoch": 26.5,
-                "loss": 0.0008260362083092332,
-                "learning_rate": 4.001027817058789e-06,
-                "grad_norm": 0.036896709352731705
-            },
-            {
-                "global_step": 107,
-                "epoch": 26.75,
-                "loss": 0.0005347628612071276,
-                "learning_rate": 3.4914333375330898e-06,
-                "grad_norm": 0.032362014055252075
-            },
-            {
-                "global_step": 108,
-                "epoch": 27.0,
-                "loss": 0.0005628281505778432,
-                "learning_rate": 3.0153689607045845e-06,
-                "grad_norm": 0.020569942891597748
-            },
-            {
-                "global_step": 109,
-                "epoch": 27.25,
-                "loss": 0.0006590321427211165,
-                "learning_rate": 2.573177902642726e-06,
-                "grad_norm": 0.033200304955244064
-            },
-            {
-                "global_step": 110,
-                "epoch": 27.5,
-                "loss": 0.0005788324633613229,
-                "learning_rate": 2.1651789586287442e-06,
-                "grad_norm": 0.03066444955766201
-            },
-            {
-                "global_step": 111,
-                "epoch": 27.75,
-                "loss": 0.0002574412210378796,
-                "learning_rate": 1.7916662733218847e-06,
-                "grad_norm": 0.015490197576582432
-            },
-            {
-                "global_step": 112,
-                "epoch": 28.0,
-                "loss": 0.0007605571881867945,
-                "learning_rate": 1.4529091286973995e-06,
-                "grad_norm": 0.06880451738834381
-            },
-            {
-                "global_step": 113,
-                "epoch": 28.25,
-                "loss": 0.0004236309032421559,
-                "learning_rate": 1.1491517499091498e-06,
-                "grad_norm": 0.17912079393863678
-            },
-            {
-                "global_step": 114,
-                "epoch": 28.5,
-                "loss": 0.0008066121954470873,
-                "learning_rate": 8.806131292167618e-07,
-                "grad_norm": 0.035754382610321045
-            },
-            {
-                "global_step": 115,
-                "epoch": 28.75,
-                "loss": 0.000279993808362633,
-                "learning_rate": 6.474868681043578e-07,
-                "grad_norm": 0.019517874345183372
-            },
-            {
-                "global_step": 116,
-                "epoch": 29.0,
-                "loss": 0.0005598465213552117,
-                "learning_rate": 4.4994103770457653e-07,
-                "grad_norm": 0.021198801696300507
-            },
-            {
-                "global_step": 117,
-                "epoch": 29.25,
-                "loss": 0.000262636283878237,
-                "learning_rate": 2.8811805762860576e-07,
-                "grad_norm": 0.015968313440680504
-            },
-            {
-                "global_step": 118,
-                "epoch": 29.5,
-                "loss": 0.000800407025963068,
-                "learning_rate": 1.6213459328950352e-07,
-                "grad_norm": 0.03289778530597687
-            },
-            {
-                "global_step": 119,
-                "epoch": 29.75,
-                "loss": 0.0005571640795096755,
-                "learning_rate": 7.208147179291192e-08,
-                "grad_norm": 0.033743325620889664
-            },
-            {
-                "global_step": 120,
-                "epoch": 30.0,
-                "loss": 0.00039453001227229834,
-                "learning_rate": 1.802361645573125e-08,
-                "grad_norm": 0.02658260241150856
-            },
-            {
-                "global_step": 120,
-                "epoch": 30.0,
-                "loss": null,
-                "learning_rate": null,
-                "grad_norm": null
-            }
-        ]
-    },
-    "gradient_health_passed": true,
-    "numerical_recovery_passed": true,
-    "post_training_audit_status": "passed",
-    "recoverable_fp16_overflows": 0,
-    "recoverable_overflow_indices": [],
-    "adapter_saved_before_health_audit": true,
-    "adapter_weights_finite": true,
-    "adapter_export_eligible": true,
-    "post_training_audit": {
-        "audit_version": 1,
-        "audit_timestamp_unix": 1793918763.25352,
-        "base_model": "coder3101/gemma-4-E2B-it-heretic",
-        "adapter_directory": "/kaggle/working/gemma4_lora/adapter",
-        "gradient_health_passed": true,
-        "numerical_recovery_passed": true,
-        "adapter_weights_finite": true,
-        "adapter_export_eligible": true,
-        "gradient_checks": 120,
-        "skipped_optimizer_steps": 0,
-        "skipped_step_indices": [],
-        "nonfinite_gradient_steps": [],
-        "nonfinite_gradient_tensors": 0,
-        "gradient_norm_statistics": {
-            "count": 120,
-            "minimum": 0.01549019716854724,
-            "median": 0.2999997905589369,
-            "maximum": 0.2999999967057757,
-            "mean": 0.23312759692201965
-        },
-        "grad_scaler_initial": 2048.0,
-        "grad_scaler_final": 2048.0,
-        "grad_scaler_minimum": 512.0,
-        "loss_history_entries": 121,
-        "adapter_tensor_count": 1050,
-        "adapter_parameter_count": 37920768,
-        "nonfinite_adapter_tensors": [],
-        "passed_checks": 22,
-        "failed_checks": 0,
-        "checks": [
-            {
-                "name": "Gradient monitoring executed",
-                "passed": true,
-                "detail": "120 optimizer attempts were monitored."
-            },
-            {
-                "name": "Gradient norm history length",
-                "passed": true,
-                "detail": "120 norms for 120 checks."
-            },
-            {
-                "name": "Gradient tensor-count history length",
-                "passed": true,
-                "detail": "120 entries for 120 checks."
-            },
-            {
-                "name": "GradScaler history length",
-                "passed": true,
-                "detail": "120 entries for 120 checks."
-            },
-            {
-                "name": "Skipped optimizer update limit",
-                "passed": true,
-                "detail": "0 skipped; maximum allowed is 2."
-            },
-            {
-                "name": "Skipped update indices are unique",
-                "passed": true,
-                "detail": "Indices: []"
-            },
-            {
-                "name": "Skipped update indices are in range",
-                "passed": true,
-                "detail": "Valid range: 0 to 119."
-            },
-            {
-                "name": "Non-finite gradient indices are unique",
-                "passed": true,
-                "detail": "Indices: []"
-            },
-            {
-                "name": "Non-finite gradient indices are in range",
-                "passed": true,
-                "detail": "Valid range: 0 to 119."
-            },
-            {
-                "name": "Overflow attempts match skipped optimizer attempts",
-                "passed": true,
-                "detail": "Skipped=[]; non-finite=[]."
-            },
-            {
-                "name": "Non-finite tensor count is consistent",
-                "passed": true,
-                "detail": "0 non-finite gradient tensors."
-            },
-            {
-                "name": "No optimizer attempt lacked all gradients",
-                "passed": true,
-                "detail": "No-gradient attempts: []."
-            },
-            {
-                "name": "No consecutive overflow attempts",
-                "passed": true,
-                "detail": "Overflow indices: []."
-            },
-            {
-                "name": "Final overflow has recovery window",
-                "passed": true,
-                "detail": "No overflow in the final two attempts."
-            },
-            {
-                "name": "Missing gradient norms match overflow attempts",
-                "passed": true,
-                "detail": "Missing norms=[]; overflow attempts=[]."
-            },
-            {
-                "name": "All recorded finite gradient norms are valid",
-                "passed": true,
-                "detail": "120 finite norms; invalid indices=[]."
-            },
-            {
-                "name": "GradScaler history is finite and positive",
-                "passed": true,
-                "detail": "120 recorded values."
-            },
-            {
-                "name": "Initial GradScaler value is valid",
-                "passed": true,
-                "detail": "Initial scale: 2048.0."
-            },
-            {
-                "name": "Final GradScaler value is valid",
-                "passed": true,
-                "detail": "Final scale: 2048.0."
-            },
-            {
-                "name": "Final GradScaler meets minimum",
-                "passed": true,
-                "detail": "Final=2048.0; minimum=512.0."
-            },
-            {
-                "name": "Recorded loss history contains valid values",
-                "passed": true,
-                "detail": "120 finite loss values; invalid entries=[]."
-            },
-            {
-                "name": "Adapter weights contain only finite values",
-                "passed": true,
-                "detail": "1050 tensors; 37,920,768 parameters; 0 non-finite tensors."
-            }
-        ]
-    }
-}