Upload folder using huggingface_hub

.gitattributes

@@ -63,3 +63,13 @@ max_seq_length_512_experiments/google/gemma_2b_scotus/checkpoint-300/tokenizer.j
 max_seq_length_512_experiments/google/gemma_2b_scotus/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 max_seq_length_512_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 max_seq_length_512_experiments/google/gemma_2b_twitter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt_default/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster_default/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.json filter=lfs diff=lfs merge=lfs -text

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/README.md

@@ -0,0 +1,78 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-7B
+metrics:
+- accuracy
+model-index:
+- name: amazon_attrprompt_default
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# amazon_attrprompt_default
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4968
+- Accuracy: 0.8597
+- F1 Macro: 0.8370
+- F1 Micro: 0.8597
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
+| 5.8578        | 0.26  | 50   | 5.5037          | 0.1252   | 0.0968   | 0.1252   |
+| 2.3145        | 0.53  | 100  | 1.9805          | 0.5283   | 0.4222   | 0.5283   |
+| 0.9115        | 0.79  | 150  | 0.9064          | 0.7721   | 0.7139   | 0.7721   |
+| 0.7251        | 1.05  | 200  | 0.7034          | 0.8090   | 0.7669   | 0.8090   |
+| 0.5086        | 1.32  | 250  | 0.6432          | 0.8267   | 0.7756   | 0.8267   |
+| 0.5473        | 1.58  | 300  | 0.5911          | 0.8353   | 0.7983   | 0.8353   |
+| 0.514         | 1.84  | 350  | 0.5454          | 0.8564   | 0.8329   | 0.8564   |
+| 0.4493        | 2.11  | 400  | 0.5437          | 0.8465   | 0.8172   | 0.8465   |
+| 0.516         | 2.37  | 450  | 0.5225          | 0.8531   | 0.8289   | 0.8531   |
+| 0.343         | 2.63  | 500  | 0.4982          | 0.8557   | 0.8339   | 0.8557   |
+| 0.4203        | 2.89  | 550  | 0.4968          | 0.8597   | 0.8370   | 0.8597   |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedc29f0e3c70b05d17a273bde6f9c121acca7eb499a20c583e76da75799cbfb
+size 1882260178

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8596837944664032,
+    "eval_f1_macro": 0.8369626014217448,
+    "eval_f1_micro": 0.8596837944664032,
+    "eval_loss": 0.4968219995498657,
+    "eval_runtime": 69.9894,
+    "eval_samples": 1518,
+    "eval_samples_per_second": 21.689,
+    "eval_steps_per_second": 0.343,
+    "test_accuracy": 0.8656126482213439,
+    "test_f1_macro": 0.8325216055106754,
+    "test_f1_micro": 0.8656126482213439,
+    "test_loss": 0.4752732813358307,
+    "test_runtime": 71.3407,
+    "test_samples_per_second": 21.278,
+    "test_steps_per_second": 0.336,
+    "train_loss": 1.5545654296875,
+    "train_runtime": 6735.4111,
+    "train_samples": 12144,
+    "train_samples_per_second": 5.409,
+    "train_steps_per_second": 0.085
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-7B
+---
+
+# 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 0.9.0

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedc29f0e3c70b05d17a273bde6f9c121acca7eb499a20c583e76da75799cbfb
+size 1882260178

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebaf6fa93d3430bc145598aa505e219ab667a5f938f820ac94c1169747e80395
+size 1919487472

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3397151de151c5dedad4dda7af68c85ab858df82dbf136614e81529bad333259
+size 1919487600

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7860285270e3c30292d40ae46c06834ae4b7394e3a03162fe85c73be54c8fb9f
+size 640146476

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/latest

@@ -0,0 +1 @@
+global_step550

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa878b9dab4c3723c4f5604b647f0a382b5b43b32ec9ed579e02f8f396f30f88
+size 14512

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a380ec5d7ef6434080f7e34913d8fb510f595347139628691d6320bcf76a7f
+size 14512

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:398f41e79c8fa897296b46d4295b47f9f97b941419fa2b04df7bf09aa5e5015d
+size 1064

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/trainer_state.json

@@ -0,0 +1,527 @@
+{
+  "best_metric": 0.4968219995498657,
+  "best_model_checkpoint": "../experiments_checkpoints/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550",
+  "epoch": 2.8947368421052633,
+  "eval_steps": 50,
+  "global_step": 550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 78.0635757446289,
+      "learning_rate": 4.912280701754386e-06,
+      "loss": 11.5813,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 72.21075439453125,
+      "learning_rate": 4.824561403508772e-06,
+      "loss": 9.4297,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 67.49365997314453,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 8.2891,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 66.80319213867188,
+      "learning_rate": 4.649122807017544e-06,
+      "loss": 6.8797,
+      "step": 40
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 65.08647155761719,
+      "learning_rate": 4.56140350877193e-06,
+      "loss": 5.8578,
+      "step": 50
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.1251646903820817,
+      "eval_f1_macro": 0.09680804168971274,
+      "eval_f1_micro": 0.1251646903820817,
+      "eval_loss": 5.503664493560791,
+      "eval_runtime": 70.8056,
+      "eval_samples_per_second": 21.439,
+      "eval_steps_per_second": 0.339,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 56.8034553527832,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 5.1516,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 48.72732925415039,
+      "learning_rate": 4.385964912280702e-06,
+      "loss": 4.1211,
+      "step": 70
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 52.9466667175293,
+      "learning_rate": 4.298245614035088e-06,
+      "loss": 3.4531,
+      "step": 80
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 52.9542350769043,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 2.9504,
+      "step": 90
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 49.08361053466797,
+      "learning_rate": 4.12280701754386e-06,
+      "loss": 2.3145,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.52832674571805,
+      "eval_f1_macro": 0.4222235273845894,
+      "eval_f1_micro": 0.52832674571805,
+      "eval_loss": 1.9804636240005493,
+      "eval_runtime": 70.8343,
+      "eval_samples_per_second": 21.43,
+      "eval_steps_per_second": 0.339,
+      "step": 100
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 38.720149993896484,
+      "learning_rate": 4.035087719298246e-06,
+      "loss": 1.6187,
+      "step": 110
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 51.675872802734375,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 1.4811,
+      "step": 120
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 33.777587890625,
+      "learning_rate": 3.859649122807018e-06,
+      "loss": 1.3875,
+      "step": 130
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 25.40624237060547,
+      "learning_rate": 3.7719298245614037e-06,
+      "loss": 1.1301,
+      "step": 140
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 30.72103500366211,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.9115,
+      "step": 150
+    },
+    {
+      "epoch": 0.79,
+      "eval_accuracy": 0.7720685111989459,
+      "eval_f1_macro": 0.7139330965236713,
+      "eval_f1_micro": 0.7720685111989459,
+      "eval_loss": 0.9063529372215271,
+      "eval_runtime": 70.8238,
+      "eval_samples_per_second": 21.433,
+      "eval_steps_per_second": 0.339,
+      "step": 150
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 47.277923583984375,
+      "learning_rate": 3.596491228070176e-06,
+      "loss": 0.8274,
+      "step": 160
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 34.87353515625,
+      "learning_rate": 3.5087719298245615e-06,
+      "loss": 0.9087,
+      "step": 170
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 33.74974060058594,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.8381,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 30.923776626586914,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8215,
+      "step": 190
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 30.552841186523438,
+      "learning_rate": 3.2456140350877197e-06,
+      "loss": 0.7251,
+      "step": 200
+    },
+    {
+      "epoch": 1.05,
+      "eval_accuracy": 0.8089591567852438,
+      "eval_f1_macro": 0.7669219918531099,
+      "eval_f1_micro": 0.8089591567852438,
+      "eval_loss": 0.7033617496490479,
+      "eval_runtime": 70.8095,
+      "eval_samples_per_second": 21.438,
+      "eval_steps_per_second": 0.339,
+      "step": 200
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 40.9909553527832,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.6617,
+      "step": 210
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 22.532026290893555,
+      "learning_rate": 3.0701754385964915e-06,
+      "loss": 0.6655,
+      "step": 220
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 22.03099250793457,
+      "learning_rate": 2.9824561403508774e-06,
+      "loss": 0.6155,
+      "step": 230
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 31.129398345947266,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.5786,
+      "step": 240
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 22.806337356567383,
+      "learning_rate": 2.8070175438596493e-06,
+      "loss": 0.5086,
+      "step": 250
+    },
+    {
+      "epoch": 1.32,
+      "eval_accuracy": 0.8267457180500659,
+      "eval_f1_macro": 0.7755720185959084,
+      "eval_f1_micro": 0.8267457180500659,
+      "eval_loss": 0.6432034373283386,
+      "eval_runtime": 70.864,
+      "eval_samples_per_second": 21.421,
+      "eval_steps_per_second": 0.339,
+      "step": 250
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 24.898916244506836,
+      "learning_rate": 2.7192982456140356e-06,
+      "loss": 0.537,
+      "step": 260
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 33.29705047607422,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.5357,
+      "step": 270
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 20.23432159423828,
+      "learning_rate": 2.5438596491228075e-06,
+      "loss": 0.5452,
+      "step": 280
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 26.38104820251465,
+      "learning_rate": 2.456140350877193e-06,
+      "loss": 0.5015,
+      "step": 290
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 23.257266998291016,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.5473,
+      "step": 300
+    },
+    {
+      "epoch": 1.58,
+      "eval_accuracy": 0.8353096179183136,
+      "eval_f1_macro": 0.7982776447477468,
+      "eval_f1_micro": 0.8353096179183136,
+      "eval_loss": 0.591135561466217,
+      "eval_runtime": 70.7822,
+      "eval_samples_per_second": 21.446,
+      "eval_steps_per_second": 0.339,
+      "step": 300
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 31.060453414916992,
+      "learning_rate": 2.280701754385965e-06,
+      "loss": 0.5914,
+      "step": 310
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 38.224273681640625,
+      "learning_rate": 2.192982456140351e-06,
+      "loss": 0.547,
+      "step": 320
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 24.825180053710938,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.5009,
+      "step": 330
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 33.94304656982422,
+      "learning_rate": 2.017543859649123e-06,
+      "loss": 0.607,
+      "step": 340
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 47.21768569946289,
+      "learning_rate": 1.929824561403509e-06,
+      "loss": 0.514,
+      "step": 350
+    },
+    {
+      "epoch": 1.84,
+      "eval_accuracy": 0.8563899868247694,
+      "eval_f1_macro": 0.8328616425942686,
+      "eval_f1_micro": 0.8563899868247694,
+      "eval_loss": 0.5453721880912781,
+      "eval_runtime": 70.8148,
+      "eval_samples_per_second": 21.436,
+      "eval_steps_per_second": 0.339,
+      "step": 350
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 22.25798797607422,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 0.4804,
+      "step": 360
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 25.627458572387695,
+      "learning_rate": 1.7543859649122807e-06,
+      "loss": 0.5387,
+      "step": 370
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 26.785030364990234,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.5375,
+      "step": 380
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 24.151248931884766,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.4375,
+      "step": 390
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 31.1235408782959,
+      "learning_rate": 1.4912280701754387e-06,
+      "loss": 0.4493,
+      "step": 400
+    },
+    {
+      "epoch": 2.11,
+      "eval_accuracy": 0.8465085638998683,
+      "eval_f1_macro": 0.817214362989291,
+      "eval_f1_micro": 0.8465085638998683,
+      "eval_loss": 0.5436841249465942,
+      "eval_runtime": 70.7986,
+      "eval_samples_per_second": 21.441,
+      "eval_steps_per_second": 0.339,
+      "step": 400
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 24.023176193237305,
+      "learning_rate": 1.4035087719298246e-06,
+      "loss": 0.4135,
+      "step": 410
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 29.59303092956543,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.4725,
+      "step": 420
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 26.1127872467041,
+      "learning_rate": 1.2280701754385965e-06,
+      "loss": 0.3891,
+      "step": 430
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 30.481605529785156,
+      "learning_rate": 1.1403508771929824e-06,
+      "loss": 0.4042,
+      "step": 440
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 22.664913177490234,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 0.516,
+      "step": 450
+    },
+    {
+      "epoch": 2.37,
+      "eval_accuracy": 0.8530961791831357,
+      "eval_f1_macro": 0.828913306836084,
+      "eval_f1_micro": 0.8530961791831357,
+      "eval_loss": 0.5225136876106262,
+      "eval_runtime": 70.8455,
+      "eval_samples_per_second": 21.427,
+      "eval_steps_per_second": 0.339,
+      "step": 450
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 27.753475189208984,
+      "learning_rate": 9.649122807017545e-07,
+      "loss": 0.3435,
+      "step": 460
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 28.056856155395508,
+      "learning_rate": 8.771929824561404e-07,
+      "loss": 0.4159,
+      "step": 470
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 28.235706329345703,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.44,
+      "step": 480
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 19.392196655273438,
+      "learning_rate": 7.017543859649123e-07,
+      "loss": 0.3991,
+      "step": 490
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 24.779186248779297,
+      "learning_rate": 6.140350877192982e-07,
+      "loss": 0.343,
+      "step": 500
+    },
+    {
+      "epoch": 2.63,
+      "eval_accuracy": 0.8557312252964426,
+      "eval_f1_macro": 0.8339166245745164,
+      "eval_f1_micro": 0.8557312252964426,
+      "eval_loss": 0.4982321560382843,
+      "eval_runtime": 70.8133,
+      "eval_samples_per_second": 21.437,
+      "eval_steps_per_second": 0.339,
+      "step": 500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 21.358295440673828,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 0.3543,
+      "step": 510
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 26.393150329589844,
+      "learning_rate": 4.385964912280702e-07,
+      "loss": 0.4026,
+      "step": 520
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 26.136310577392578,
+      "learning_rate": 3.5087719298245616e-07,
+      "loss": 0.3974,
+      "step": 530
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 20.45792579650879,
+      "learning_rate": 2.6315789473684213e-07,
+      "loss": 0.4142,
+      "step": 540
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 24.060897827148438,
+      "learning_rate": 1.7543859649122808e-07,
+      "loss": 0.4203,
+      "step": 550
+    },
+    {
+      "epoch": 2.89,
+      "eval_accuracy": 0.8596837944664032,
+      "eval_f1_macro": 0.8369626014217448,
+      "eval_f1_micro": 0.8596837944664032,
+      "eval_loss": 0.4968219995498657,
+      "eval_runtime": 70.7643,
+      "eval_samples_per_second": 21.452,
+      "eval_steps_per_second": 0.339,
+      "step": 550
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 570,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 7.34953687000023e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c352945f05514abeccc19c517e1b0f3bc31de7dfc5f7a93d0b302ba8e6938bcf
+size 6008

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8596837944664032,
+    "eval_f1_macro": 0.8369626014217448,
+    "eval_f1_micro": 0.8596837944664032,
+    "eval_loss": 0.4968219995498657,
+    "eval_runtime": 69.9894,
+    "eval_samples": 1518,
+    "eval_samples_per_second": 21.689,
+    "eval_steps_per_second": 0.343
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/run.log

@@ -0,0 +1,4 @@
+03/25/2024 02:21:11 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False
+03/25/2024 02:21:11 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: False
+03/25/2024 02:21:39 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
+03/25/2024 02:21:39 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/test_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "test_accuracy": 0.8656126482213439,
+    "test_f1_macro": 0.8325216055106754,
+    "test_f1_micro": 0.8656126482213439,
+    "test_loss": 0.4752732813358307,
+    "test_runtime": 71.3407,
+    "test_samples_per_second": 21.278,
+    "test_steps_per_second": 0.336
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.5545654296875,
+    "train_runtime": 6735.4111,
+    "train_samples": 12144,
+    "train_samples_per_second": 5.409,
+    "train_steps_per_second": 0.085
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/trainer_state.json

@@ -0,0 +1,550 @@
+{
+  "best_metric": 0.4968219995498657,
+  "best_model_checkpoint": "../experiments_checkpoints/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550",
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 570,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 78.0635757446289,
+      "learning_rate": 4.912280701754386e-06,
+      "loss": 11.5813,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 72.21075439453125,
+      "learning_rate": 4.824561403508772e-06,
+      "loss": 9.4297,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 67.49365997314453,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 8.2891,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 66.80319213867188,
+      "learning_rate": 4.649122807017544e-06,
+      "loss": 6.8797,
+      "step": 40
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 65.08647155761719,
+      "learning_rate": 4.56140350877193e-06,
+      "loss": 5.8578,
+      "step": 50
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.1251646903820817,
+      "eval_f1_macro": 0.09680804168971274,
+      "eval_f1_micro": 0.1251646903820817,
+      "eval_loss": 5.503664493560791,
+      "eval_runtime": 70.8056,
+      "eval_samples_per_second": 21.439,
+      "eval_steps_per_second": 0.339,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 56.8034553527832,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 5.1516,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 48.72732925415039,
+      "learning_rate": 4.385964912280702e-06,
+      "loss": 4.1211,
+      "step": 70
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 52.9466667175293,
+      "learning_rate": 4.298245614035088e-06,
+      "loss": 3.4531,
+      "step": 80
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 52.9542350769043,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 2.9504,
+      "step": 90
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 49.08361053466797,
+      "learning_rate": 4.12280701754386e-06,
+      "loss": 2.3145,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.52832674571805,
+      "eval_f1_macro": 0.4222235273845894,
+      "eval_f1_micro": 0.52832674571805,
+      "eval_loss": 1.9804636240005493,
+      "eval_runtime": 70.8343,
+      "eval_samples_per_second": 21.43,
+      "eval_steps_per_second": 0.339,
+      "step": 100
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 38.720149993896484,
+      "learning_rate": 4.035087719298246e-06,
+      "loss": 1.6187,
+      "step": 110
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 51.675872802734375,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 1.4811,
+      "step": 120
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 33.777587890625,
+      "learning_rate": 3.859649122807018e-06,
+      "loss": 1.3875,
+      "step": 130
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 25.40624237060547,
+      "learning_rate": 3.7719298245614037e-06,
+      "loss": 1.1301,
+      "step": 140
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 30.72103500366211,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.9115,
+      "step": 150
+    },
+    {
+      "epoch": 0.79,
+      "eval_accuracy": 0.7720685111989459,
+      "eval_f1_macro": 0.7139330965236713,
+      "eval_f1_micro": 0.7720685111989459,
+      "eval_loss": 0.9063529372215271,
+      "eval_runtime": 70.8238,
+      "eval_samples_per_second": 21.433,
+      "eval_steps_per_second": 0.339,
+      "step": 150
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 47.277923583984375,
+      "learning_rate": 3.596491228070176e-06,
+      "loss": 0.8274,
+      "step": 160
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 34.87353515625,
+      "learning_rate": 3.5087719298245615e-06,
+      "loss": 0.9087,
+      "step": 170
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 33.74974060058594,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.8381,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 30.923776626586914,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8215,
+      "step": 190
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 30.552841186523438,
+      "learning_rate": 3.2456140350877197e-06,
+      "loss": 0.7251,
+      "step": 200
+    },
+    {
+      "epoch": 1.05,
+      "eval_accuracy": 0.8089591567852438,
+      "eval_f1_macro": 0.7669219918531099,
+      "eval_f1_micro": 0.8089591567852438,
+      "eval_loss": 0.7033617496490479,
+      "eval_runtime": 70.8095,
+      "eval_samples_per_second": 21.438,
+      "eval_steps_per_second": 0.339,
+      "step": 200
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 40.9909553527832,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.6617,
+      "step": 210
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 22.532026290893555,
+      "learning_rate": 3.0701754385964915e-06,
+      "loss": 0.6655,
+      "step": 220
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 22.03099250793457,
+      "learning_rate": 2.9824561403508774e-06,
+      "loss": 0.6155,
+      "step": 230
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 31.129398345947266,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.5786,
+      "step": 240
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 22.806337356567383,
+      "learning_rate": 2.8070175438596493e-06,
+      "loss": 0.5086,
+      "step": 250
+    },
+    {
+      "epoch": 1.32,
+      "eval_accuracy": 0.8267457180500659,
+      "eval_f1_macro": 0.7755720185959084,
+      "eval_f1_micro": 0.8267457180500659,
+      "eval_loss": 0.6432034373283386,
+      "eval_runtime": 70.864,
+      "eval_samples_per_second": 21.421,
+      "eval_steps_per_second": 0.339,
+      "step": 250
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 24.898916244506836,
+      "learning_rate": 2.7192982456140356e-06,
+      "loss": 0.537,
+      "step": 260
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 33.29705047607422,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.5357,
+      "step": 270
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 20.23432159423828,
+      "learning_rate": 2.5438596491228075e-06,
+      "loss": 0.5452,
+      "step": 280
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 26.38104820251465,
+      "learning_rate": 2.456140350877193e-06,
+      "loss": 0.5015,
+      "step": 290
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 23.257266998291016,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.5473,
+      "step": 300
+    },
+    {
+      "epoch": 1.58,
+      "eval_accuracy": 0.8353096179183136,
+      "eval_f1_macro": 0.7982776447477468,
+      "eval_f1_micro": 0.8353096179183136,
+      "eval_loss": 0.591135561466217,
+      "eval_runtime": 70.7822,
+      "eval_samples_per_second": 21.446,
+      "eval_steps_per_second": 0.339,
+      "step": 300
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 31.060453414916992,
+      "learning_rate": 2.280701754385965e-06,
+      "loss": 0.5914,
+      "step": 310
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 38.224273681640625,
+      "learning_rate": 2.192982456140351e-06,
+      "loss": 0.547,
+      "step": 320
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 24.825180053710938,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.5009,
+      "step": 330
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 33.94304656982422,
+      "learning_rate": 2.017543859649123e-06,
+      "loss": 0.607,
+      "step": 340
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 47.21768569946289,
+      "learning_rate": 1.929824561403509e-06,
+      "loss": 0.514,
+      "step": 350
+    },
+    {
+      "epoch": 1.84,
+      "eval_accuracy": 0.8563899868247694,
+      "eval_f1_macro": 0.8328616425942686,
+      "eval_f1_micro": 0.8563899868247694,
+      "eval_loss": 0.5453721880912781,
+      "eval_runtime": 70.8148,
+      "eval_samples_per_second": 21.436,
+      "eval_steps_per_second": 0.339,
+      "step": 350
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 22.25798797607422,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 0.4804,
+      "step": 360
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 25.627458572387695,
+      "learning_rate": 1.7543859649122807e-06,
+      "loss": 0.5387,
+      "step": 370
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 26.785030364990234,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.5375,
+      "step": 380
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 24.151248931884766,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.4375,
+      "step": 390
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 31.1235408782959,
+      "learning_rate": 1.4912280701754387e-06,
+      "loss": 0.4493,
+      "step": 400
+    },
+    {
+      "epoch": 2.11,
+      "eval_accuracy": 0.8465085638998683,
+      "eval_f1_macro": 0.817214362989291,
+      "eval_f1_micro": 0.8465085638998683,
+      "eval_loss": 0.5436841249465942,
+      "eval_runtime": 70.7986,
+      "eval_samples_per_second": 21.441,
+      "eval_steps_per_second": 0.339,
+      "step": 400
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 24.023176193237305,
+      "learning_rate": 1.4035087719298246e-06,
+      "loss": 0.4135,
+      "step": 410
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 29.59303092956543,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.4725,
+      "step": 420
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 26.1127872467041,
+      "learning_rate": 1.2280701754385965e-06,
+      "loss": 0.3891,
+      "step": 430
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 30.481605529785156,
+      "learning_rate": 1.1403508771929824e-06,
+      "loss": 0.4042,
+      "step": 440
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 22.664913177490234,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 0.516,
+      "step": 450
+    },
+    {
+      "epoch": 2.37,
+      "eval_accuracy": 0.8530961791831357,
+      "eval_f1_macro": 0.828913306836084,
+      "eval_f1_micro": 0.8530961791831357,
+      "eval_loss": 0.5225136876106262,
+      "eval_runtime": 70.8455,
+      "eval_samples_per_second": 21.427,
+      "eval_steps_per_second": 0.339,
+      "step": 450
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 27.753475189208984,
+      "learning_rate": 9.649122807017545e-07,
+      "loss": 0.3435,
+      "step": 460
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 28.056856155395508,
+      "learning_rate": 8.771929824561404e-07,
+      "loss": 0.4159,
+      "step": 470
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 28.235706329345703,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.44,
+      "step": 480
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 19.392196655273438,
+      "learning_rate": 7.017543859649123e-07,
+      "loss": 0.3991,
+      "step": 490
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 24.779186248779297,
+      "learning_rate": 6.140350877192982e-07,
+      "loss": 0.343,
+      "step": 500
+    },
+    {
+      "epoch": 2.63,
+      "eval_accuracy": 0.8557312252964426,
+      "eval_f1_macro": 0.8339166245745164,
+      "eval_f1_micro": 0.8557312252964426,
+      "eval_loss": 0.4982321560382843,
+      "eval_runtime": 70.8133,
+      "eval_samples_per_second": 21.437,
+      "eval_steps_per_second": 0.339,
+      "step": 500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 21.358295440673828,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 0.3543,
+      "step": 510
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 26.393150329589844,
+      "learning_rate": 4.385964912280702e-07,
+      "loss": 0.4026,
+      "step": 520
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 26.136310577392578,
+      "learning_rate": 3.5087719298245616e-07,
+      "loss": 0.3974,
+      "step": 530
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 20.45792579650879,
+      "learning_rate": 2.6315789473684213e-07,
+      "loss": 0.4142,
+      "step": 540
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 24.060897827148438,
+      "learning_rate": 1.7543859649122808e-07,
+      "loss": 0.4203,
+      "step": 550
+    },
+    {
+      "epoch": 2.89,
+      "eval_accuracy": 0.8596837944664032,
+      "eval_f1_macro": 0.8369626014217448,
+      "eval_f1_micro": 0.8596837944664032,
+      "eval_loss": 0.4968219995498657,
+      "eval_runtime": 70.7643,
+      "eval_samples_per_second": 21.452,
+      "eval_steps_per_second": 0.339,
+      "step": 550
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 21.141916275024414,
+      "learning_rate": 8.771929824561404e-08,
+      "loss": 0.4682,
+      "step": 560
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 26.661828994750977,
+      "learning_rate": 0.0,
+      "loss": 0.4384,
+      "step": 570
+    },
+    {
+      "epoch": 3.0,
+      "step": 570,
+      "total_flos": 7.616792756182057e+17,
+      "train_loss": 1.5545654296875,
+      "train_runtime": 6735.4111,
+      "train_samples_per_second": 5.409,
+      "train_steps_per_second": 0.085
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 570,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "total_flos": 7.616792756182057e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c352945f05514abeccc19c517e1b0f3bc31de7dfc5f7a93d0b302ba8e6938bcf
+size 6008

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/README.md

@@ -0,0 +1,75 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-7B
+metrics:
+- accuracy
+model-index:
+- name: twitter_disaster_default
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# twitter_disaster_default
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7973
+- Accuracy: 0.7151
+- F1 Macro: 0.6612
+- F1 Micro: 0.7151
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
+| 1.0791        | 0.37  | 50   | 1.3147          | 0.6765   | 0.6068   | 0.6765   |
+| 0.8888        | 0.74  | 100  | 1.0283          | 0.6884   | 0.6494   | 0.6884   |
+| 0.6325        | 1.1   | 150  | 0.8961          | 0.6912   | 0.6240   | 0.6912   |
+| 0.7378        | 1.47  | 200  | 0.8683          | 0.7105   | 0.6437   | 0.7105   |
+| 0.5979        | 1.84  | 250  | 0.8460          | 0.7243   | 0.6393   | 0.7243   |
+| 0.4513        | 2.21  | 300  | 0.8070          | 0.7142   | 0.6592   | 0.7142   |
+| 0.5699        | 2.57  | 350  | 0.8001          | 0.7114   | 0.6636   | 0.7114   |
+| 0.4189        | 2.94  | 400  | 0.7973          | 0.7151   | 0.6612   | 0.7151   |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2597662e929c041bde6c94fcb1ef7b879f93c6a81c59504a0f9450cc504d3753
+size 1882088146

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7150735294117647,
+    "eval_f1_macro": 0.6611572572705318,
+    "eval_f1_micro": 0.7150735294117647,
+    "eval_loss": 0.7973345518112183,
+    "eval_runtime": 49.6177,
+    "eval_samples": 1088,
+    "eval_samples_per_second": 21.928,
+    "eval_steps_per_second": 0.343,
+    "test_accuracy": 0.7417279411764706,
+    "test_f1_macro": 0.6892802878238908,
+    "test_f1_micro": 0.7417279411764706,
+    "test_loss": 0.7253561615943909,
+    "test_runtime": 51.0672,
+    "test_samples_per_second": 21.305,
+    "test_steps_per_second": 0.333,
+    "train_loss": 0.7515426336550245,
+    "train_runtime": 4685.4738,
+    "train_samples": 8700,
+    "train_samples_per_second": 5.57,
+    "train_steps_per_second": 0.087
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-7B
+---
+
+# 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 0.9.0

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2597662e929c041bde6c94fcb1ef7b879f93c6a81c59504a0f9450cc504d3753
+size 1882088146

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31a3ada65c23868f51012d3b6043f0a51210668a988ebf13af85c5c8d071f98
+size 1918971376

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808d47ea51a83854ffa8c9308cfb08212c5e1f9fa8efe01304d240d6ef81555a
+size 1918971504

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f953adf8ae05c2c89096dc7d063d8b4b40f73ddc6c7dabc46c014ca9d2aee4
+size 639974444

max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/latest

@@ -0,0 +1 @@
+global_step400