Upload SDG checkpoint

adapter_config.json

@@ -18,7 +18,7 @@
   "loftq_config": {},
   "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -29,12 +29,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o",
-    "wi",
     "q",
-    "v",
     "k",
-    "wo"
+    "wi",
+    "wo",
+    "o",
+    "v"
   ],
   "target_parameters": null,
   "task_type": "SEQ_2_SEQ_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50dfa5a795234be8995d30dd9b2cc806b4e7560a823d6a999642e201cd7e8b77
+oid sha256:d132234d93d10ab49e2abad26ef3a2438eda16c5c8f3a3be863b34dcda89f16f
 size 34675328

checkpoint-100/README.md

@@ -0,0 +1,206 @@
+---
+base_model: amazon/chronos-t5-small
+library_name: peft
+tags:
+- base_model:adapter:amazon/chronos-t5-small
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "amazon/chronos-t5-small",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v",
+    "k",
+    "wi",
+    "q",
+    "o",
+    "wo"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff89b5ebce1a9aed202867901606a36d5970e0f2832b8afc10066abf25beb201
+size 26024408

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad2bb16040ab03ce63eaf55269c74eed216dedcdcb63df4a222583ece453b71
+size 17457803

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f70f09d3cb910592b4d2344caae1568a9b5043377429849d732244fbeec9cb
+size 14391

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1154e599b40cad63e7c3e7593533c1b4a92dcb4ca99419a21971491c50b7b25
+size 1465

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_global_step": 100,
+  "best_metric": 4.469874858856201,
+  "best_model_checkpoint": "/Users/alexgrigoras/Library/Mobile Documents/com~apple~CloudDocs/[5] Software/github/dif-pi/artifacts/models/sdg_chronos_t5_small_dunnhumby/checkpoint-100",
+  "epoch": 0.027878449958182325,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006969612489545581,
+      "grad_norm": 0.2126408815383911,
+      "learning_rate": 2.2612712429686845e-05,
+      "loss": 47.1256640625,
+      "step": 25
+    },
+    {
+      "epoch": 0.006969612489545581,
+      "eval_loss": 4.553621292114258,
+      "eval_runtime": 92.4561,
+      "eval_samples_per_second": 137.947,
+      "eval_steps_per_second": 34.492,
+      "step": 25
+    },
+    {
+      "epoch": 0.013939224979091162,
+      "grad_norm": 0.2005404382944107,
+      "learning_rate": 1.394355796211983e-05,
+      "loss": 46.44048828125,
+      "step": 50
+    },
+    {
+      "epoch": 0.013939224979091162,
+      "eval_loss": 4.501615047454834,
+      "eval_runtime": 93.5682,
+      "eval_samples_per_second": 136.307,
+      "eval_steps_per_second": 34.082,
+      "step": 50
+    },
+    {
+      "epoch": 0.020908837468636744,
+      "grad_norm": 0.22218841314315796,
+      "learning_rate": 4.342677980947892e-06,
+      "loss": 46.2969970703125,
+      "step": 75
+    },
+    {
+      "epoch": 0.020908837468636744,
+      "eval_loss": 4.4744110107421875,
+      "eval_runtime": 92.9448,
+      "eval_samples_per_second": 137.221,
+      "eval_steps_per_second": 34.311,
+      "step": 75
+    },
+    {
+      "epoch": 0.027878449958182325,
+      "grad_norm": 0.22809632122516632,
+      "learning_rate": 6.8342832384243885e-09,
+      "loss": 46.36712890625,
+      "step": 100
+    },
+    {
+      "epoch": 0.027878449958182325,
+      "eval_loss": 4.469874858856201,
+      "eval_runtime": 92.8908,
+      "eval_samples_per_second": 137.301,
+      "eval_steps_per_second": 34.331,
+      "step": 100
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 146422628352000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ee0b43a815c9eaf0d8c72af13a117c88bb1009b80bc491fb3a9cbdd3bb1ef8
+size 5457

checkpoint-300/README.md

@@ -0,0 +1,206 @@
+---
+base_model: amazon/chronos-t5-small
+library_name: peft
+tags:
+- base_model:adapter:amazon/chronos-t5-small
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-300/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "amazon/chronos-t5-small",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "k",
+    "wi",
+    "wo",
+    "o",
+    "v"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d132234d93d10ab49e2abad26ef3a2438eda16c5c8f3a3be863b34dcda89f16f
+size 34675328

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5049a8d2f4f806a56d89530c4da05f252f9e18c9c0c9d0f2c59d1a2d5a51301d
+size 34759371

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f8fe56a72edfbc414d4b2de40ca33521959ba7ae7f211e3b88c911b03de69c
+size 14391

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c6773821ea9d3bef830d1d03869581ad60560d632621bbb6430b6bc17d445f
+size 1465

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_global_step": 300,
+  "best_metric": 4.177750110626221,
+  "best_model_checkpoint": "/Users/alexgrigoras/Library/Mobile Documents/com~apple~CloudDocs/[5] Software/github/dif-pi/artifacts/models/sdg_chronos_t5_small_dunnhumby/checkpoint-300",
+  "epoch": 0.04181840358244324,
+  "eval_steps": 25,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0034848669652036033,
+      "grad_norm": 0.2658565640449524,
+      "learning_rate": 2.4938536281812643e-05,
+      "loss": 50.4958984375,
+      "step": 25
+    },
+    {
+      "epoch": 0.0034848669652036033,
+      "eval_loss": 4.513997554779053,
+      "eval_runtime": 126.0711,
+      "eval_samples_per_second": 101.165,
+      "eval_steps_per_second": 50.583,
+      "step": 25
+    },
+    {
+      "epoch": 0.006969733930407207,
+      "grad_norm": 0.3027424216270447,
+      "learning_rate": 2.4132322535191482e-05,
+      "loss": 49.5675048828125,
+      "step": 50
+    },
+    {
+      "epoch": 0.006969733930407207,
+      "eval_loss": 4.422898769378662,
+      "eval_runtime": 135.5543,
+      "eval_samples_per_second": 94.088,
+      "eval_steps_per_second": 47.044,
+      "step": 50
+    },
+    {
+      "epoch": 0.01045460089561081,
+      "grad_norm": 0.34238171577453613,
+      "learning_rate": 2.2448287207969232e-05,
+      "loss": 48.3637109375,
+      "step": 75
+    },
+    {
+      "epoch": 0.01045460089561081,
+      "eval_loss": 4.359263896942139,
+      "eval_runtime": 138.5997,
+      "eval_samples_per_second": 92.02,
+      "eval_steps_per_second": 46.01,
+      "step": 75
+    },
+    {
+      "epoch": 0.013939467860814413,
+      "grad_norm": 0.3021143674850464,
+      "learning_rate": 2.0013514341037815e-05,
+      "loss": 47.3734521484375,
+      "step": 100
+    },
+    {
+      "epoch": 0.013939467860814413,
+      "eval_loss": 4.318150997161865,
+      "eval_runtime": 136.3222,
+      "eval_samples_per_second": 93.558,
+      "eval_steps_per_second": 46.779,
+      "step": 100
+    },
+    {
+      "epoch": 0.017424334826018018,
+      "grad_norm": 0.28853410482406616,
+      "learning_rate": 1.7011741632521437e-05,
+      "loss": 48.521357421875,
+      "step": 125
+    },
+    {
+      "epoch": 0.017424334826018018,
+      "eval_loss": 4.282954692840576,
+      "eval_runtime": 132.1879,
+      "eval_samples_per_second": 96.484,
+      "eval_steps_per_second": 48.242,
+      "step": 125
+    },
+    {
+      "epoch": 0.02090920179122162,
+      "grad_norm": 0.3650856614112854,
+      "learning_rate": 1.3669494856238973e-05,
+      "loss": 47.43091796875,
+      "step": 150
+    },
+    {
+      "epoch": 0.02090920179122162,
+      "eval_loss": 4.249988555908203,
+      "eval_runtime": 145.2659,
+      "eval_samples_per_second": 87.798,
+      "eval_steps_per_second": 43.899,
+      "step": 150
+    },
+    {
+      "epoch": 0.024394068756425222,
+      "grad_norm": 0.3505313992500305,
+      "learning_rate": 1.023899332084863e-05,
+      "loss": 46.525419921875,
+      "step": 175
+    },
+    {
+      "epoch": 0.024394068756425222,
+      "eval_loss": 4.218865871429443,
+      "eval_runtime": 137.0969,
+      "eval_samples_per_second": 93.029,
+      "eval_steps_per_second": 46.515,
+      "step": 175
+    },
+    {
+      "epoch": 0.027878935721628827,
+      "grad_norm": 0.3190622925758362,
+      "learning_rate": 6.979116392095325e-06,
+      "loss": 46.60708984375,
+      "step": 200
+    },
+    {
+      "epoch": 0.027878935721628827,
+      "eval_loss": 4.196957588195801,
+      "eval_runtime": 140.7578,
+      "eval_samples_per_second": 90.61,
+      "eval_steps_per_second": 45.305,
+      "step": 200
+    },
+    {
+      "epoch": 0.03136380268683243,
+      "grad_norm": 0.3062129318714142,
+      "learning_rate": 4.1358674205142765e-06,
+      "loss": 48.300791015625,
+      "step": 225
+    },
+    {
+      "epoch": 0.03136380268683243,
+      "eval_loss": 4.185319900512695,
+      "eval_runtime": 134.3944,
+      "eval_samples_per_second": 94.9,
+      "eval_steps_per_second": 47.45,
+      "step": 225
+    },
+    {
+      "epoch": 0.034848669652036035,
+      "grad_norm": 0.30869823694229126,
+      "learning_rate": 1.923809344738306e-06,
+      "loss": 47.4475341796875,
+      "step": 250
+    },
+    {
+      "epoch": 0.034848669652036035,
+      "eval_loss": 4.180154323577881,
+      "eval_runtime": 142.7493,
+      "eval_samples_per_second": 89.345,
+      "eval_steps_per_second": 44.673,
+      "step": 250
+    },
+    {
+      "epoch": 0.038333536617239636,
+      "grad_norm": 0.30447155237197876,
+      "learning_rate": 5.098729140296271e-07,
+      "loss": 47.397509765625,
+      "step": 275
+    },
+    {
+      "epoch": 0.038333536617239636,
+      "eval_loss": 4.1781206130981445,
+      "eval_runtime": 150.242,
+      "eval_samples_per_second": 84.89,
+      "eval_steps_per_second": 42.445,
+      "step": 275
+    },
+    {
+      "epoch": 0.04181840358244324,
+      "grad_norm": 0.3095584213733673,
+      "learning_rate": 7.594263207122421e-10,
+      "loss": 46.36583984375,
+      "step": 300
+    },
+    {
+      "epoch": 0.04181840358244324,
+      "eval_loss": 4.177750110626221,
+      "eval_runtime": 144.6681,
+      "eval_samples_per_second": 88.16,
+      "eval_steps_per_second": 44.08,
+      "step": 300
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 229911035904000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3cbde0e32fb05322d5f55e6154336171a3e6994fa4c5c61e7e2ad0be268c10
+size 5457

privacy_reference_bank.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b2a98c927eb38de4afe90ee0cf075290b30bf898e7ce8935a526d7f4a002f5
+size 240128

privacy_reference_stats.json

@@ -0,0 +1,6 @@
+{
+  "n_reference_windows": 2000,
+  "min_distance_threshold": 8.543635129928589,
+  "avg_real_nn_distance": 1678.3014648655792,
+  "distance_quantile": 0.25
+}

sdg_config.json

@@ -9,7 +9,7 @@
     5.0
   ],
   "learning_rate": 2.5e-05,
-  "train_steps": 1500,
+  "train_steps": 300,
   "lora_rank": 32,
   "lora_alpha": 64,
   "batch_size": 2,
@@ -18,13 +18,23 @@
   "max_target_length": 256,
   "random_state": 42,
   "task_prefix": "generate synthetic retail demand future from historical context",
-  "seasonality_strength": 0.75,
+  "seasonality_strength": 0.6,
   "seasonal_period": 7,
-  "seasonal_fallback_strength": 0.35,
+  "seasonal_fallback_strength": 0.25,
   "zero_threshold_for_sparsity": 0.6,
-  "prefer_backend": "qlora",
+  "prefer_backend": "lora",
   "use_special_tokens": true,
   "add_calendar_features": true,
   "warmup_ratio": 0.05,
-  "weight_decay": 0.01
+  "weight_decay": 0.01,
+  "privacy_reference_max_windows": 2000,
+  "privacy_min_distance_quantile": 0.25,
+  "privacy_distance_penalty": 4.0,
+  "privacy_noise_strength": 0.1,
+  "privacy_baseline_blend": 0.25,
+  "privacy_training_jitter_prob": 0.6,
+  "privacy_training_jitter_strength": 0.1,
+  "privacy_deduplicate_examples": true,
+  "privacy_filter_enabled": true,
+  "privacy_filter_max_retries": 6
 }

training_info.json

@@ -1,11 +1,20 @@
 {
   "train_examples": 114782,
   "eval_examples": 12754,
-  "train_steps": 1500,
+  "train_steps": 300,
   "learning_rate": 2.5e-05,
-  "train_runtime": 9612.5461,
-  "train_loss": 32.71766121419271,
+  "train_runtime": 1945.4336,
+  "train_loss": 47.86641886393229,
   "is_peft_model": true,
   "backend_name": "lora",
-  "added_special_tokens": 4131
+  "added_special_tokens": 4131,
+  "privacy_reference_windows": 2000,
+  "privacy_deduplicated_examples": 0,
+  "privacy_jittered_examples": 68730,
+  "privacy_reference_stats": {
+    "n_reference_windows": 2000,
+    "min_distance_threshold": 8.543635129928589,
+    "avg_real_nn_distance": 1678.3014648655792,
+    "distance_quantile": 0.25
+  }
 }