Upload stage2 checkpoint (full/lora)

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1048/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2096/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3144/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,51 @@
+---
+language:
+- ar
+license: llama3
+base_model: meta-llama/Llama-3.1-8B
+tags:
+- arabic
+- medical
+- question-answering
+- fine-tuned
+- full
+---
+
+# Omaratef3221/llama-3.1-8b-s1-full-s2-lora-medarabench
+
+**Base model:** `meta-llama/Llama-3.1-8B`  
+**Training stage:** Stage 2 — Task Fine-tuning (MedAraBench)  
+**Stage 1 method:** full  
+**Stage 2 method:** lora  
+
+## Paper
+
+_LoRA vs. Full Fine-Tuning for Arabic Medical Question Answering: A Systematic Comparison Across General-Purpose and Arabic-Centric Large Language Models_
+
+## Training data
+
+| Stage | Dataset | Samples |
+|-------|---------|---------|
+| Stage 1 | AraMed (open-ended Arabic medical QA) | ~110K |
+| Stage 2 | MedAraBench (Arabic MCQ) | ~17.6K (cleaned) |
+
+## Evaluation
+
+Evaluated on MedAraBench test set (4,959 MCQ samples) using log-probability selection.
+Metrics: **Accuracy** and **Macro F1** across answer classes A–E.
+
+## Experiment metadata
+
+```json
+{
+  "model_name": "meta-llama/Llama-3.1-8B",
+  "stage1_method": "full",
+  "stage2_method": "lora",
+  "stage": "task_specific",
+  "num_epochs": 3,
+  "config_path": "/home/oelgendy/arabic-medical-llm/script/configs/lora.yaml",
+  "stage1_checkpoint": "outputs/exp04_llama_full_lora/stage1",
+  "train_samples": 16756,
+  "val_samples": 882
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "outputs/exp04_llama_full_lora/stage1",
+  "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": 0.05,
+  "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": [
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9312cbde2c4c3a9b7a3abc1b21eb38e782845a9779a795b248b7caf694a3f89e
+size 167832240

checkpoint-1048/README.md

@@ -0,0 +1,209 @@
+---
+base_model: outputs/exp04_llama_full_lora/stage1
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:outputs/exp04_llama_full_lora/stage1
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-1048/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "outputs/exp04_llama_full_lora/stage1",
+  "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": 0.05,
+  "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": [
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1048/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cbdcc0dc17b6c142eae447ec1b1bcd8cafec800e048868a7d191ff2d4ca8088
+size 167832240

checkpoint-1048/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37442db983991d61bbbe413f26907dde786f5798199633f5ca9a66f6a38cd484
+size 86128920

checkpoint-1048/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48852ab2d09f4e417e2e311aa546f11cc8e500f7ffd24e3c7010785a0ee97a60
+size 14244

checkpoint-1048/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:514642a74f9ab860eddeecf0df77df92eac84728bc4df60b477858ab09996687
+size 1064

checkpoint-1048/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-1048/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-1048/trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1048,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.9169489538669586,
+      "epoch": 0.0477326968973747,
+      "grad_norm": 0.4528772830963135,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 2.1467950439453123,
+      "mean_token_accuracy": 0.5774942764639854,
+      "num_tokens": 62415.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.7696015048027038,
+      "epoch": 0.0954653937947494,
+      "grad_norm": 0.559516429901123,
+      "learning_rate": 0.00019999915067429384,
+      "loss": 1.7887376403808595,
+      "mean_token_accuracy": 0.6264250260591507,
+      "num_tokens": 126004.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.693043473958969,
+      "epoch": 0.1431980906921241,
+      "grad_norm": 0.5153214931488037,
+      "learning_rate": 0.0001998452500999697,
+      "loss": 1.7081011962890624,
+      "mean_token_accuracy": 0.6385690844058991,
+      "num_tokens": 188614.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.6898816537857055,
+      "epoch": 0.1909307875894988,
+      "grad_norm": 0.5599738955497742,
+      "learning_rate": 0.00019942640420376765,
+      "loss": 1.7022125244140625,
+      "mean_token_accuracy": 0.6406848466396332,
+      "num_tokens": 251062.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.6405246889591216,
+      "epoch": 0.2386634844868735,
+      "grad_norm": 0.49600595235824585,
+      "learning_rate": 0.00019874372441823629,
+      "loss": 1.6459197998046875,
+      "mean_token_accuracy": 0.6479257130622864,
+      "num_tokens": 313957.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.6324861299991609,
+      "epoch": 0.2863961813842482,
+      "grad_norm": 0.5211499333381653,
+      "learning_rate": 0.00019779902227487397,
+      "loss": 1.6452156066894532,
+      "mean_token_accuracy": 0.6487298482656478,
+      "num_tokens": 376779.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.5829804718494416,
+      "epoch": 0.3341288782816229,
+      "grad_norm": 0.5337353348731995,
+      "learning_rate": 0.00019659480459712202,
+      "loss": 1.5916696166992188,
+      "mean_token_accuracy": 0.657093957066536,
+      "num_tokens": 439472.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.5584524583816528,
+      "epoch": 0.3818615751789976,
+      "grad_norm": 0.5614678263664246,
+      "learning_rate": 0.00019513426684835924,
+      "loss": 1.5665699768066406,
+      "mean_token_accuracy": 0.6622982215881348,
+      "num_tokens": 501279.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.5577264988422395,
+      "epoch": 0.4295942720763723,
+      "grad_norm": 0.5509770512580872,
+      "learning_rate": 0.00019342128465254943,
+      "loss": 1.5625930786132813,
+      "mean_token_accuracy": 0.6628634428977966,
+      "num_tokens": 564442.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.5444469928741456,
+      "epoch": 0.477326968973747,
+      "grad_norm": 0.5766333937644958,
+      "learning_rate": 0.00019146040351004223,
+      "loss": 1.5518899536132813,
+      "mean_token_accuracy": 0.6658952581882477,
+      "num_tokens": 627102.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.5157422959804534,
+      "epoch": 0.5250596658711217,
+      "grad_norm": 0.5064456462860107,
+      "learning_rate": 0.00018925682673581707,
+      "loss": 1.517430877685547,
+      "mean_token_accuracy": 0.6710657715797425,
+      "num_tokens": 689421.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.5208299958705902,
+      "epoch": 0.5727923627684964,
+      "grad_norm": 0.5480907559394836,
+      "learning_rate": 0.0001868164016521766,
+      "loss": 1.5297586059570312,
+      "mean_token_accuracy": 0.6690839475393295,
+      "num_tokens": 752388.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.4881639647483826,
+      "epoch": 0.6205250596658711,
+      "grad_norm": 0.5211111307144165,
+      "learning_rate": 0.0001841456040725287,
+      "loss": 1.4932846069335937,
+      "mean_token_accuracy": 0.6743283599615097,
+      "num_tokens": 815803.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.4972898173332214,
+      "epoch": 0.6682577565632458,
+      "grad_norm": 0.5176190137863159,
+      "learning_rate": 0.00018125152111742946,
+      "loss": 1.5032540893554687,
+      "mean_token_accuracy": 0.6734136432409287,
+      "num_tokens": 878686.0,
+      "step": 700
+    },
+    {
+      "entropy": 1.473973354101181,
+      "epoch": 0.7159904534606205,
+      "grad_norm": 0.5914217829704285,
+      "learning_rate": 0.00017814183240848634,
+      "loss": 1.4737196350097657,
+      "mean_token_accuracy": 0.6782503163814545,
+      "num_tokens": 940629.0,
+      "step": 750
+    },
+    {
+      "entropy": 1.4514920926094055,
+      "epoch": 0.7637231503579952,
+      "grad_norm": 0.578711211681366,
+      "learning_rate": 0.00017482478969002484,
+      "loss": 1.4571778869628906,
+      "mean_token_accuracy": 0.6808390617370605,
+      "num_tokens": 1002810.0,
+      "step": 800
+    },
+    {
+      "entropy": 1.445438961982727,
+      "epoch": 0.8114558472553699,
+      "grad_norm": 0.5754839181900024,
+      "learning_rate": 0.00017130919493259282,
+      "loss": 1.4394004821777344,
+      "mean_token_accuracy": 0.6844613349437714,
+      "num_tokens": 1067041.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.4248486053943634,
+      "epoch": 0.8591885441527446,
+      "grad_norm": 0.5281590819358826,
+      "learning_rate": 0.00016760437697640722,
+      "loss": 1.4258000183105468,
+      "mean_token_accuracy": 0.6896877753734588,
+      "num_tokens": 1130309.0,
+      "step": 900
+    },
+    {
+      "entropy": 1.435852448940277,
+      "epoch": 0.9069212410501193,
+      "grad_norm": 0.5507786870002747,
+      "learning_rate": 0.00016372016677672037,
+      "loss": 1.4390003967285157,
+      "mean_token_accuracy": 0.6855950307846069,
+      "num_tokens": 1192924.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.402035859823227,
+      "epoch": 0.954653937947494,
+      "grad_norm": 0.49761536717414856,
+      "learning_rate": 0.00015966687131679463,
+      "loss": 1.3975450134277343,
+      "mean_token_accuracy": 0.6939341032505035,
+      "num_tokens": 1254418.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 1.3806531386716026,
+      "eval_loss": 1.3620444536209106,
+      "eval_mean_token_accuracy": 0.6980640984176237,
+      "eval_num_tokens": 1314012.0,
+      "eval_runtime": 86.3192,
+      "eval_samples_per_second": 10.218,
+      "eval_steps_per_second": 10.218,
+      "step": 1048
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3144,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.126155436883968e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1048/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a92f47f215f6192c33d2a857fefbabc108b7e532a835fab7fa19809483c7a6f
+size 5304

checkpoint-2096/README.md

@@ -0,0 +1,209 @@
+---
+base_model: outputs/exp04_llama_full_lora/stage1
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:outputs/exp04_llama_full_lora/stage1
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-2096/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "outputs/exp04_llama_full_lora/stage1",
+  "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": 0.05,
+  "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": [
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2096/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:536953a0341226a27f17459aef42e1c3eaaa3a930173c278711b46f0af5b0a03
+size 167832240

checkpoint-2096/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1eb9d8aefa88386225d99c5fcb081cb04ef093e229d4ce7ca38aa9499ff3fe1
+size 86128920

checkpoint-2096/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1942ca16846370f11dc56d67000b0504ee5cc67f2daaaa4452c78e338e07012
+size 14244

checkpoint-2096/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d83869a47d0c4867636b032d40d8ebcad0d5ea84bd9f07a838676db92dbffd0
+size 1064

checkpoint-2096/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-2096/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-2096/trainer_state.json

@@ -0,0 +1,466 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2096,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.9169489538669586,
+      "epoch": 0.0477326968973747,
+      "grad_norm": 0.4528772830963135,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 2.1467950439453123,
+      "mean_token_accuracy": 0.5774942764639854,
+      "num_tokens": 62415.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.7696015048027038,
+      "epoch": 0.0954653937947494,
+      "grad_norm": 0.559516429901123,
+      "learning_rate": 0.00019999915067429384,
+      "loss": 1.7887376403808595,
+      "mean_token_accuracy": 0.6264250260591507,
+      "num_tokens": 126004.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.693043473958969,
+      "epoch": 0.1431980906921241,
+      "grad_norm": 0.5153214931488037,
+      "learning_rate": 0.0001998452500999697,
+      "loss": 1.7081011962890624,
+      "mean_token_accuracy": 0.6385690844058991,
+      "num_tokens": 188614.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.6898816537857055,
+      "epoch": 0.1909307875894988,
+      "grad_norm": 0.5599738955497742,
+      "learning_rate": 0.00019942640420376765,
+      "loss": 1.7022125244140625,
+      "mean_token_accuracy": 0.6406848466396332,
+      "num_tokens": 251062.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.6405246889591216,
+      "epoch": 0.2386634844868735,
+      "grad_norm": 0.49600595235824585,
+      "learning_rate": 0.00019874372441823629,
+      "loss": 1.6459197998046875,
+      "mean_token_accuracy": 0.6479257130622864,
+      "num_tokens": 313957.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.6324861299991609,
+      "epoch": 0.2863961813842482,
+      "grad_norm": 0.5211499333381653,
+      "learning_rate": 0.00019779902227487397,
+      "loss": 1.6452156066894532,
+      "mean_token_accuracy": 0.6487298482656478,
+      "num_tokens": 376779.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.5829804718494416,
+      "epoch": 0.3341288782816229,
+      "grad_norm": 0.5337353348731995,
+      "learning_rate": 0.00019659480459712202,
+      "loss": 1.5916696166992188,
+      "mean_token_accuracy": 0.657093957066536,
+      "num_tokens": 439472.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.5584524583816528,
+      "epoch": 0.3818615751789976,
+      "grad_norm": 0.5614678263664246,
+      "learning_rate": 0.00019513426684835924,
+      "loss": 1.5665699768066406,
+      "mean_token_accuracy": 0.6622982215881348,
+      "num_tokens": 501279.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.5577264988422395,
+      "epoch": 0.4295942720763723,
+      "grad_norm": 0.5509770512580872,
+      "learning_rate": 0.00019342128465254943,
+      "loss": 1.5625930786132813,
+      "mean_token_accuracy": 0.6628634428977966,
+      "num_tokens": 564442.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.5444469928741456,
+      "epoch": 0.477326968973747,
+      "grad_norm": 0.5766333937644958,
+      "learning_rate": 0.00019146040351004223,
+      "loss": 1.5518899536132813,
+      "mean_token_accuracy": 0.6658952581882477,
+      "num_tokens": 627102.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.5157422959804534,
+      "epoch": 0.5250596658711217,
+      "grad_norm": 0.5064456462860107,
+      "learning_rate": 0.00018925682673581707,
+      "loss": 1.517430877685547,
+      "mean_token_accuracy": 0.6710657715797425,
+      "num_tokens": 689421.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.5208299958705902,
+      "epoch": 0.5727923627684964,
+      "grad_norm": 0.5480907559394836,
+      "learning_rate": 0.0001868164016521766,
+      "loss": 1.5297586059570312,
+      "mean_token_accuracy": 0.6690839475393295,
+      "num_tokens": 752388.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.4881639647483826,
+      "epoch": 0.6205250596658711,
+      "grad_norm": 0.5211111307144165,
+      "learning_rate": 0.0001841456040725287,
+      "loss": 1.4932846069335937,
+      "mean_token_accuracy": 0.6743283599615097,
+      "num_tokens": 815803.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.4972898173332214,
+      "epoch": 0.6682577565632458,
+      "grad_norm": 0.5176190137863159,
+      "learning_rate": 0.00018125152111742946,
+      "loss": 1.5032540893554687,
+      "mean_token_accuracy": 0.6734136432409287,
+      "num_tokens": 878686.0,
+      "step": 700
+    },
+    {
+      "entropy": 1.473973354101181,
+      "epoch": 0.7159904534606205,
+      "grad_norm": 0.5914217829704285,
+      "learning_rate": 0.00017814183240848634,
+      "loss": 1.4737196350097657,
+      "mean_token_accuracy": 0.6782503163814545,
+      "num_tokens": 940629.0,
+      "step": 750
+    },
+    {
+      "entropy": 1.4514920926094055,
+      "epoch": 0.7637231503579952,
+      "grad_norm": 0.578711211681366,
+      "learning_rate": 0.00017482478969002484,
+      "loss": 1.4571778869628906,
+      "mean_token_accuracy": 0.6808390617370605,
+      "num_tokens": 1002810.0,
+      "step": 800
+    },
+    {
+      "entropy": 1.445438961982727,
+      "epoch": 0.8114558472553699,
+      "grad_norm": 0.5754839181900024,
+      "learning_rate": 0.00017130919493259282,
+      "loss": 1.4394004821777344,
+      "mean_token_accuracy": 0.6844613349437714,
+      "num_tokens": 1067041.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.4248486053943634,
+      "epoch": 0.8591885441527446,
+      "grad_norm": 0.5281590819358826,
+      "learning_rate": 0.00016760437697640722,
+      "loss": 1.4258000183105468,
+      "mean_token_accuracy": 0.6896877753734588,
+      "num_tokens": 1130309.0,
+      "step": 900
+    },
+    {
+      "entropy": 1.435852448940277,
+      "epoch": 0.9069212410501193,
+      "grad_norm": 0.5507786870002747,
+      "learning_rate": 0.00016372016677672037,
+      "loss": 1.4390003967285157,
+      "mean_token_accuracy": 0.6855950307846069,
+      "num_tokens": 1192924.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.402035859823227,
+      "epoch": 0.954653937947494,
+      "grad_norm": 0.49761536717414856,
+      "learning_rate": 0.00015966687131679463,
+      "loss": 1.3975450134277343,
+      "mean_token_accuracy": 0.6939341032505035,
+      "num_tokens": 1254418.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 1.3806531386716026,
+      "eval_loss": 1.3620444536209106,
+      "eval_mean_token_accuracy": 0.6980640984176237,
+      "eval_num_tokens": 1314012.0,
+      "eval_runtime": 86.3192,
+      "eval_samples_per_second": 10.218,
+      "eval_steps_per_second": 10.218,
+      "step": 1048
+    },
+    {
+      "entropy": 1.3871761247365162,
+      "epoch": 1.001909307875895,
+      "grad_norm": 0.5140528082847595,
+      "learning_rate": 0.0001554552462577077,
+      "loss": 1.3846685791015625,
+      "mean_token_accuracy": 0.6949169792310156,
+      "num_tokens": 1316679.0,
+      "step": 1050
+    },
+    {
+      "entropy": 1.1777105987071992,
+      "epoch": 1.0496420047732697,
+      "grad_norm": 0.5981715321540833,
+      "learning_rate": 0.0001510964673975651,
+      "loss": 1.1399847412109374,
+      "mean_token_accuracy": 0.737745595574379,
+      "num_tokens": 1379361.0,
+      "step": 1100
+    },
+    {
+      "entropy": 1.1736225724220275,
+      "epoch": 1.0973747016706443,
+      "grad_norm": 0.6831048727035522,
+      "learning_rate": 0.00014660210101585368,
+      "loss": 1.1506944274902344,
+      "mean_token_accuracy": 0.7348957419395447,
+      "num_tokens": 1442332.0,
+      "step": 1150
+    },
+    {
+      "entropy": 1.1798189544677735,
+      "epoch": 1.1451073985680191,
+      "grad_norm": 0.5928924083709717,
+      "learning_rate": 0.00014198407318162976,
+      "loss": 1.1495547485351563,
+      "mean_token_accuracy": 0.736353549361229,
+      "num_tokens": 1506048.0,
+      "step": 1200
+    },
+    {
+      "entropy": 1.1766791635751723,
+      "epoch": 1.1928400954653937,
+      "grad_norm": 0.6532445549964905,
+      "learning_rate": 0.00013725463810698417,
+      "loss": 1.1499956512451173,
+      "mean_token_accuracy": 0.7360061597824097,
+      "num_tokens": 1569529.0,
+      "step": 1250
+    },
+    {
+      "entropy": 1.1588226580619811,
+      "epoch": 1.2405727923627685,
+      "grad_norm": 0.6756422519683838,
+      "learning_rate": 0.0001324263456297599,
+      "loss": 1.1256829833984374,
+      "mean_token_accuracy": 0.741998724937439,
+      "num_tokens": 1632744.0,
+      "step": 1300
+    },
+    {
+      "entropy": 1.1586075723171234,
+      "epoch": 1.2883054892601433,
+      "grad_norm": 0.6124622225761414,
+      "learning_rate": 0.00012751200791180962,
+      "loss": 1.134525604248047,
+      "mean_token_accuracy": 0.740217564702034,
+      "num_tokens": 1695454.0,
+      "step": 1350
+    },
+    {
+      "entropy": 1.1286164861917496,
+      "epoch": 1.336038186157518,
+      "grad_norm": 0.6842568516731262,
+      "learning_rate": 0.00012252466544116048,
+      "loss": 1.1040880584716797,
+      "mean_token_accuracy": 0.7439208465814591,
+      "num_tokens": 1759868.0,
+      "step": 1400
+    },
+    {
+      "entropy": 1.1323925870656968,
+      "epoch": 1.3837708830548925,
+      "grad_norm": 0.7253908514976501,
+      "learning_rate": 0.00011747755242830202,
+      "loss": 1.1016536712646485,
+      "mean_token_accuracy": 0.7450394695997238,
+      "num_tokens": 1820879.0,
+      "step": 1450
+    },
+    {
+      "entropy": 1.121083972454071,
+      "epoch": 1.4315035799522673,
+      "grad_norm": 0.5749630928039551,
+      "learning_rate": 0.00011238406168841982,
+      "loss": 1.1001790618896485,
+      "mean_token_accuracy": 0.7459173601865768,
+      "num_tokens": 1883307.0,
+      "step": 1500
+    },
+    {
+      "entropy": 1.122628794312477,
+      "epoch": 1.479236276849642,
+      "grad_norm": 0.6206186413764954,
+      "learning_rate": 0.00010725770910276218,
+      "loss": 1.0909404754638672,
+      "mean_token_accuracy": 0.7463360679149628,
+      "num_tokens": 1946095.0,
+      "step": 1550
+    },
+    {
+      "entropy": 1.1350409585237502,
+      "epoch": 1.5269689737470167,
+      "grad_norm": 0.662372887134552,
+      "learning_rate": 0.00010211209775344377,
+      "loss": 1.1051890563964843,
+      "mean_token_accuracy": 0.747498095035553,
+      "num_tokens": 2009039.0,
+      "step": 1600
+    },
+    {
+      "entropy": 1.1150280052423478,
+      "epoch": 1.5747016706443913,
+      "grad_norm": 0.6651705503463745,
+      "learning_rate": 9.696088182685638e-05,
+      "loss": 1.09230224609375,
+      "mean_token_accuracy": 0.7472188991308212,
+      "num_tokens": 2070866.0,
+      "step": 1650
+    },
+    {
+      "entropy": 1.0846411114931107,
+      "epoch": 1.622434367541766,
+      "grad_norm": 0.7228969931602478,
+      "learning_rate": 9.181773038147168e-05,
+      "loss": 1.0646434020996094,
+      "mean_token_accuracy": 0.756052638888359,
+      "num_tokens": 2133531.0,
+      "step": 1700
+    },
+    {
+      "entropy": 1.1237550568580628,
+      "epoch": 1.6701670644391409,
+      "grad_norm": 0.6554394364356995,
+      "learning_rate": 8.66962910761798e-05,
+      "loss": 1.0866881561279298,
+      "mean_token_accuracy": 0.7495866256952286,
+      "num_tokens": 2196212.0,
+      "step": 1750
+    },
+    {
+      "entropy": 1.0998593443632125,
+      "epoch": 1.7178997613365157,
+      "grad_norm": 0.6516928672790527,
+      "learning_rate": 8.16101539554131e-05,
+      "loss": 1.072577590942383,
+      "mean_token_accuracy": 0.7526345264911651,
+      "num_tokens": 2259117.0,
+      "step": 1800
+    },
+    {
+      "entropy": 1.1008843111991882,
+      "epoch": 1.7656324582338903,
+      "grad_norm": 0.7132663726806641,
+      "learning_rate": 7.65728153871533e-05,
+      "loss": 1.0717825317382812,
+      "mean_token_accuracy": 0.7529473024606704,
+      "num_tokens": 2320595.0,
+      "step": 1850
+    },
+    {
+      "entropy": 1.091220656633377,
+      "epoch": 1.8133651551312648,
+      "grad_norm": 0.6660885810852051,
+      "learning_rate": 7.159764224951468e-05,
+      "loss": 1.060431900024414,
+      "mean_token_accuracy": 0.7562662494182587,
+      "num_tokens": 2384167.0,
+      "step": 1900
+    },
+    {
+      "entropy": 1.1030601847171784,
+      "epoch": 1.8610978520286396,
+      "grad_norm": 0.6854376196861267,
+      "learning_rate": 6.669783646093635e-05,
+      "loss": 1.0840390014648438,
+      "mean_token_accuracy": 0.7516759240627289,
+      "num_tokens": 2444983.0,
+      "step": 1950
+    },
+    {
+      "entropy": 1.0597282403707504,
+      "epoch": 1.9088305489260144,
+      "grad_norm": 0.6586617231369019,
+      "learning_rate": 6.188639994810476e-05,
+      "loss": 1.0197964477539063,
+      "mean_token_accuracy": 0.7626945042610168,
+      "num_tokens": 2508413.0,
+      "step": 2000
+    },
+    {
+      "entropy": 1.0780229181051255,
+      "epoch": 1.956563245823389,
+      "grad_norm": 0.6627408862113953,
+      "learning_rate": 5.7176100144566437e-05,
+      "loss": 1.053470458984375,
+      "mean_token_accuracy": 0.7603739106655121,
+      "num_tokens": 2570521.0,
+      "step": 2050
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 1.1270634393606866,
+      "eval_loss": 1.2241966724395752,
+      "eval_mean_token_accuracy": 0.7277251901337349,
+      "eval_num_tokens": 2628024.0,
+      "eval_runtime": 86.3772,
+      "eval_samples_per_second": 10.211,
+      "eval_steps_per_second": 10.211,
+      "step": 2096
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3144,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.822900010877911e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2096/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a92f47f215f6192c33d2a857fefbabc108b7e532a835fab7fa19809483c7a6f
+size 5304

checkpoint-3144/README.md

@@ -0,0 +1,209 @@
+---
+base_model: outputs/exp04_llama_full_lora/stage1
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:outputs/exp04_llama_full_lora/stage1
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-3144/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "outputs/exp04_llama_full_lora/stage1",
+  "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": 0.05,
+  "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": [
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-3144/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9312cbde2c4c3a9b7a3abc1b21eb38e782845a9779a795b248b7caf694a3f89e
+size 167832240

checkpoint-3144/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972510432a74d3667edb77dd99105a688ef7658f3f9256d463c10bcd925dd5f7
+size 86128920

checkpoint-3144/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5bd367049ed0fd697ff3d2e9a8f5c7c6d3895ba42c7508317ce576578c750ea
+size 14244

checkpoint-3144/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347fa92e207018e9a9f46566ad6c280b801685fc904993687f51943ee8f2a3f2
+size 1064

checkpoint-3144/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-3144/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-3144/trainer_state.json

@@ -0,0 +1,687 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.9169489538669586,
+      "epoch": 0.0477326968973747,
+      "grad_norm": 0.4528772830963135,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 2.1467950439453123,
+      "mean_token_accuracy": 0.5774942764639854,
+      "num_tokens": 62415.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.7696015048027038,
+      "epoch": 0.0954653937947494,
+      "grad_norm": 0.559516429901123,
+      "learning_rate": 0.00019999915067429384,
+      "loss": 1.7887376403808595,
+      "mean_token_accuracy": 0.6264250260591507,
+      "num_tokens": 126004.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.693043473958969,
+      "epoch": 0.1431980906921241,
+      "grad_norm": 0.5153214931488037,
+      "learning_rate": 0.0001998452500999697,
+      "loss": 1.7081011962890624,
+      "mean_token_accuracy": 0.6385690844058991,
+      "num_tokens": 188614.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.6898816537857055,
+      "epoch": 0.1909307875894988,
+      "grad_norm": 0.5599738955497742,
+      "learning_rate": 0.00019942640420376765,
+      "loss": 1.7022125244140625,
+      "mean_token_accuracy": 0.6406848466396332,
+      "num_tokens": 251062.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.6405246889591216,
+      "epoch": 0.2386634844868735,
+      "grad_norm": 0.49600595235824585,
+      "learning_rate": 0.00019874372441823629,
+      "loss": 1.6459197998046875,
+      "mean_token_accuracy": 0.6479257130622864,
+      "num_tokens": 313957.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.6324861299991609,
+      "epoch": 0.2863961813842482,
+      "grad_norm": 0.5211499333381653,
+      "learning_rate": 0.00019779902227487397,
+      "loss": 1.6452156066894532,
+      "mean_token_accuracy": 0.6487298482656478,
+      "num_tokens": 376779.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.5829804718494416,
+      "epoch": 0.3341288782816229,
+      "grad_norm": 0.5337353348731995,
+      "learning_rate": 0.00019659480459712202,
+      "loss": 1.5916696166992188,
+      "mean_token_accuracy": 0.657093957066536,
+      "num_tokens": 439472.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.5584524583816528,
+      "epoch": 0.3818615751789976,
+      "grad_norm": 0.5614678263664246,
+      "learning_rate": 0.00019513426684835924,
+      "loss": 1.5665699768066406,
+      "mean_token_accuracy": 0.6622982215881348,
+      "num_tokens": 501279.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.5577264988422395,
+      "epoch": 0.4295942720763723,
+      "grad_norm": 0.5509770512580872,
+      "learning_rate": 0.00019342128465254943,
+      "loss": 1.5625930786132813,
+      "mean_token_accuracy": 0.6628634428977966,
+      "num_tokens": 564442.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.5444469928741456,
+      "epoch": 0.477326968973747,
+      "grad_norm": 0.5766333937644958,
+      "learning_rate": 0.00019146040351004223,
+      "loss": 1.5518899536132813,
+      "mean_token_accuracy": 0.6658952581882477,
+      "num_tokens": 627102.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.5157422959804534,
+      "epoch": 0.5250596658711217,
+      "grad_norm": 0.5064456462860107,
+      "learning_rate": 0.00018925682673581707,
+      "loss": 1.517430877685547,
+      "mean_token_accuracy": 0.6710657715797425,
+      "num_tokens": 689421.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.5208299958705902,
+      "epoch": 0.5727923627684964,
+      "grad_norm": 0.5480907559394836,
+      "learning_rate": 0.0001868164016521766,
+      "loss": 1.5297586059570312,
+      "mean_token_accuracy": 0.6690839475393295,
+      "num_tokens": 752388.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.4881639647483826,
+      "epoch": 0.6205250596658711,
+      "grad_norm": 0.5211111307144165,
+      "learning_rate": 0.0001841456040725287,
+      "loss": 1.4932846069335937,
+      "mean_token_accuracy": 0.6743283599615097,
+      "num_tokens": 815803.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.4972898173332214,
+      "epoch": 0.6682577565632458,
+      "grad_norm": 0.5176190137863159,
+      "learning_rate": 0.00018125152111742946,
+      "loss": 1.5032540893554687,
+      "mean_token_accuracy": 0.6734136432409287,
+      "num_tokens": 878686.0,
+      "step": 700
+    },
+    {
+      "entropy": 1.473973354101181,
+      "epoch": 0.7159904534606205,
+      "grad_norm": 0.5914217829704285,
+      "learning_rate": 0.00017814183240848634,
+      "loss": 1.4737196350097657,
+      "mean_token_accuracy": 0.6782503163814545,
+      "num_tokens": 940629.0,
+      "step": 750
+    },
+    {
+      "entropy": 1.4514920926094055,
+      "epoch": 0.7637231503579952,
+      "grad_norm": 0.578711211681366,
+      "learning_rate": 0.00017482478969002484,
+      "loss": 1.4571778869628906,
+      "mean_token_accuracy": 0.6808390617370605,
+      "num_tokens": 1002810.0,
+      "step": 800
+    },
+    {
+      "entropy": 1.445438961982727,
+      "epoch": 0.8114558472553699,
+      "grad_norm": 0.5754839181900024,
+      "learning_rate": 0.00017130919493259282,
+      "loss": 1.4394004821777344,
+      "mean_token_accuracy": 0.6844613349437714,
+      "num_tokens": 1067041.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.4248486053943634,
+      "epoch": 0.8591885441527446,
+      "grad_norm": 0.5281590819358826,
+      "learning_rate": 0.00016760437697640722,
+      "loss": 1.4258000183105468,
+      "mean_token_accuracy": 0.6896877753734588,
+      "num_tokens": 1130309.0,
+      "step": 900
+    },
+    {
+      "entropy": 1.435852448940277,
+      "epoch": 0.9069212410501193,
+      "grad_norm": 0.5507786870002747,
+      "learning_rate": 0.00016372016677672037,
+      "loss": 1.4390003967285157,
+      "mean_token_accuracy": 0.6855950307846069,
+      "num_tokens": 1192924.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.402035859823227,
+      "epoch": 0.954653937947494,
+      "grad_norm": 0.49761536717414856,
+      "learning_rate": 0.00015966687131679463,
+      "loss": 1.3975450134277343,
+      "mean_token_accuracy": 0.6939341032505035,
+      "num_tokens": 1254418.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 1.3806531386716026,
+      "eval_loss": 1.3620444536209106,
+      "eval_mean_token_accuracy": 0.6980640984176237,
+      "eval_num_tokens": 1314012.0,
+      "eval_runtime": 86.3192,
+      "eval_samples_per_second": 10.218,
+      "eval_steps_per_second": 10.218,
+      "step": 1048
+    },
+    {
+      "entropy": 1.3871761247365162,
+      "epoch": 1.001909307875895,
+      "grad_norm": 0.5140528082847595,
+      "learning_rate": 0.0001554552462577077,
+      "loss": 1.3846685791015625,
+      "mean_token_accuracy": 0.6949169792310156,
+      "num_tokens": 1316679.0,
+      "step": 1050
+    },
+    {
+      "entropy": 1.1777105987071992,
+      "epoch": 1.0496420047732697,
+      "grad_norm": 0.5981715321540833,
+      "learning_rate": 0.0001510964673975651,
+      "loss": 1.1399847412109374,
+      "mean_token_accuracy": 0.737745595574379,
+      "num_tokens": 1379361.0,
+      "step": 1100
+    },
+    {
+      "entropy": 1.1736225724220275,
+      "epoch": 1.0973747016706443,
+      "grad_norm": 0.6831048727035522,
+      "learning_rate": 0.00014660210101585368,
+      "loss": 1.1506944274902344,
+      "mean_token_accuracy": 0.7348957419395447,
+      "num_tokens": 1442332.0,
+      "step": 1150
+    },
+    {
+      "entropy": 1.1798189544677735,
+      "epoch": 1.1451073985680191,
+      "grad_norm": 0.5928924083709717,
+      "learning_rate": 0.00014198407318162976,
+      "loss": 1.1495547485351563,
+      "mean_token_accuracy": 0.736353549361229,
+      "num_tokens": 1506048.0,
+      "step": 1200
+    },
+    {
+      "entropy": 1.1766791635751723,
+      "epoch": 1.1928400954653937,
+      "grad_norm": 0.6532445549964905,
+      "learning_rate": 0.00013725463810698417,
+      "loss": 1.1499956512451173,
+      "mean_token_accuracy": 0.7360061597824097,
+      "num_tokens": 1569529.0,
+      "step": 1250
+    },
+    {
+      "entropy": 1.1588226580619811,
+      "epoch": 1.2405727923627685,
+      "grad_norm": 0.6756422519683838,
+      "learning_rate": 0.0001324263456297599,
+      "loss": 1.1256829833984374,
+      "mean_token_accuracy": 0.741998724937439,
+      "num_tokens": 1632744.0,
+      "step": 1300
+    },
+    {
+      "entropy": 1.1586075723171234,
+      "epoch": 1.2883054892601433,
+      "grad_norm": 0.6124622225761414,
+      "learning_rate": 0.00012751200791180962,
+      "loss": 1.134525604248047,
+      "mean_token_accuracy": 0.740217564702034,
+      "num_tokens": 1695454.0,
+      "step": 1350
+    },
+    {
+      "entropy": 1.1286164861917496,
+      "epoch": 1.336038186157518,
+      "grad_norm": 0.6842568516731262,
+      "learning_rate": 0.00012252466544116048,
+      "loss": 1.1040880584716797,
+      "mean_token_accuracy": 0.7439208465814591,
+      "num_tokens": 1759868.0,
+      "step": 1400
+    },
+    {
+      "entropy": 1.1323925870656968,
+      "epoch": 1.3837708830548925,
+      "grad_norm": 0.7253908514976501,
+      "learning_rate": 0.00011747755242830202,
+      "loss": 1.1016536712646485,
+      "mean_token_accuracy": 0.7450394695997238,
+      "num_tokens": 1820879.0,
+      "step": 1450
+    },
+    {
+      "entropy": 1.121083972454071,
+      "epoch": 1.4315035799522673,
+      "grad_norm": 0.5749630928039551,
+      "learning_rate": 0.00011238406168841982,
+      "loss": 1.1001790618896485,
+      "mean_token_accuracy": 0.7459173601865768,
+      "num_tokens": 1883307.0,
+      "step": 1500
+    },
+    {
+      "entropy": 1.122628794312477,
+      "epoch": 1.479236276849642,
+      "grad_norm": 0.6206186413764954,
+      "learning_rate": 0.00010725770910276218,
+      "loss": 1.0909404754638672,
+      "mean_token_accuracy": 0.7463360679149628,
+      "num_tokens": 1946095.0,
+      "step": 1550
+    },
+    {
+      "entropy": 1.1350409585237502,
+      "epoch": 1.5269689737470167,
+      "grad_norm": 0.662372887134552,
+      "learning_rate": 0.00010211209775344377,
+      "loss": 1.1051890563964843,
+      "mean_token_accuracy": 0.747498095035553,
+      "num_tokens": 2009039.0,
+      "step": 1600
+    },
+    {
+      "entropy": 1.1150280052423478,
+      "epoch": 1.5747016706443913,
+      "grad_norm": 0.6651705503463745,
+      "learning_rate": 9.696088182685638e-05,
+      "loss": 1.09230224609375,
+      "mean_token_accuracy": 0.7472188991308212,
+      "num_tokens": 2070866.0,
+      "step": 1650
+    },
+    {
+      "entropy": 1.0846411114931107,
+      "epoch": 1.622434367541766,
+      "grad_norm": 0.7228969931602478,
+      "learning_rate": 9.181773038147168e-05,
+      "loss": 1.0646434020996094,
+      "mean_token_accuracy": 0.756052638888359,
+      "num_tokens": 2133531.0,
+      "step": 1700
+    },
+    {
+      "entropy": 1.1237550568580628,
+      "epoch": 1.6701670644391409,
+      "grad_norm": 0.6554394364356995,
+      "learning_rate": 8.66962910761798e-05,
+      "loss": 1.0866881561279298,
+      "mean_token_accuracy": 0.7495866256952286,
+      "num_tokens": 2196212.0,
+      "step": 1750
+    },
+    {
+      "entropy": 1.0998593443632125,
+      "epoch": 1.7178997613365157,
+      "grad_norm": 0.6516928672790527,
+      "learning_rate": 8.16101539554131e-05,
+      "loss": 1.072577590942383,
+      "mean_token_accuracy": 0.7526345264911651,
+      "num_tokens": 2259117.0,
+      "step": 1800
+    },
+    {
+      "entropy": 1.1008843111991882,
+      "epoch": 1.7656324582338903,
+      "grad_norm": 0.7132663726806641,
+      "learning_rate": 7.65728153871533e-05,
+      "loss": 1.0717825317382812,
+      "mean_token_accuracy": 0.7529473024606704,
+      "num_tokens": 2320595.0,
+      "step": 1850
+    },
+    {
+      "entropy": 1.091220656633377,
+      "epoch": 1.8133651551312648,
+      "grad_norm": 0.6660885810852051,
+      "learning_rate": 7.159764224951468e-05,
+      "loss": 1.060431900024414,
+      "mean_token_accuracy": 0.7562662494182587,
+      "num_tokens": 2384167.0,
+      "step": 1900
+    },
+    {
+      "entropy": 1.1030601847171784,
+      "epoch": 1.8610978520286396,
+      "grad_norm": 0.6854376196861267,
+      "learning_rate": 6.669783646093635e-05,
+      "loss": 1.0840390014648438,
+      "mean_token_accuracy": 0.7516759240627289,
+      "num_tokens": 2444983.0,
+      "step": 1950
+    },
+    {
+      "entropy": 1.0597282403707504,
+      "epoch": 1.9088305489260144,
+      "grad_norm": 0.6586617231369019,
+      "learning_rate": 6.188639994810476e-05,
+      "loss": 1.0197964477539063,
+      "mean_token_accuracy": 0.7626945042610168,
+      "num_tokens": 2508413.0,
+      "step": 2000
+    },
+    {
+      "entropy": 1.0780229181051255,
+      "epoch": 1.956563245823389,
+      "grad_norm": 0.6627408862113953,
+      "learning_rate": 5.7176100144566437e-05,
+      "loss": 1.053470458984375,
+      "mean_token_accuracy": 0.7603739106655121,
+      "num_tokens": 2570521.0,
+      "step": 2050
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 1.1270634393606866,
+      "eval_loss": 1.2241966724395752,
+      "eval_mean_token_accuracy": 0.7277251901337349,
+      "eval_num_tokens": 2628024.0,
+      "eval_runtime": 86.3772,
+      "eval_samples_per_second": 10.211,
+      "eval_steps_per_second": 10.211,
+      "step": 2096
+    },
+    {
+      "entropy": 1.0549406896937976,
+      "epoch": 2.00381861575179,
+      "grad_norm": 0.6006537675857544,
+      "learning_rate": 5.257943611158213e-05,
+      "loss": 1.0044329071044922,
+      "mean_token_accuracy": 0.7685194587466693,
+      "num_tokens": 2632866.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.8462848180532455,
+      "epoch": 2.0515513126491647,
+      "grad_norm": 0.738232433795929,
+      "learning_rate": 4.8108605371122664e-05,
+      "loss": 0.7164443969726563,
+      "mean_token_accuracy": 0.8271950417757035,
+      "num_tokens": 2695322.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.83010901927948,
+      "epoch": 2.0992840095465395,
+      "grad_norm": 0.8230165243148804,
+      "learning_rate": 4.377547153901771e-05,
+      "loss": 0.7212278747558594,
+      "mean_token_accuracy": 0.826329802274704,
+      "num_tokens": 2758736.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.8135236877202988,
+      "epoch": 2.147016706443914,
+      "grad_norm": 0.7282742857933044,
+      "learning_rate": 3.959153284414369e-05,
+      "loss": 0.6992168426513672,
+      "mean_token_accuracy": 0.8299387520551682,
+      "num_tokens": 2820842.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.8248880213499069,
+      "epoch": 2.1947494033412887,
+      "grad_norm": 0.7465704679489136,
+      "learning_rate": 3.5567891617188664e-05,
+      "loss": 0.7128165435791015,
+      "mean_token_accuracy": 0.8283046728372574,
+      "num_tokens": 2883956.0,
+      "step": 2300
+    },
+    {
+      "entropy": 0.8233794635534286,
+      "epoch": 2.2424821002386635,
+      "grad_norm": 0.7302447557449341,
+      "learning_rate": 3.1715224829955757e-05,
+      "loss": 0.7124533081054687,
+      "mean_token_accuracy": 0.8284728264808655,
+      "num_tokens": 2947262.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.7968180871009827,
+      "epoch": 2.2902147971360383,
+      "grad_norm": 0.7197865843772888,
+      "learning_rate": 2.8043755763382285e-05,
+      "loss": 0.6874373626708984,
+      "mean_token_accuracy": 0.8334536749124527,
+      "num_tokens": 3010412.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.8235478883981705,
+      "epoch": 2.337947494033413,
+      "grad_norm": 0.7800441980361938,
+      "learning_rate": 2.4563226879454594e-05,
+      "loss": 0.7153313446044922,
+      "mean_token_accuracy": 0.8293009757995605,
+      "num_tokens": 3073608.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.8219516462087632,
+      "epoch": 2.3856801909307874,
+      "grad_norm": 0.7577798366546631,
+      "learning_rate": 2.1282873969004237e-05,
+      "loss": 0.7069300079345703,
+      "mean_token_accuracy": 0.8292675828933715,
+      "num_tokens": 3135626.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.7990449127554894,
+      "epoch": 2.4334128878281622,
+      "grad_norm": 0.7231966853141785,
+      "learning_rate": 1.821140164398689e-05,
+      "loss": 0.6839562225341796,
+      "mean_token_accuracy": 0.8350012344121933,
+      "num_tokens": 3199381.0,
+      "step": 2550
+    },
+    {
+      "entropy": 0.8046583250164986,
+      "epoch": 2.481145584725537,
+      "grad_norm": 0.7514696717262268,
+      "learning_rate": 1.5356960239275586e-05,
+      "loss": 0.6949836730957031,
+      "mean_token_accuracy": 0.8329219031333923,
+      "num_tokens": 3261575.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.7942794787883759,
+      "epoch": 2.528878281622912,
+      "grad_norm": 0.7590946555137634,
+      "learning_rate": 1.2727124185261197e-05,
+      "loss": 0.6895380401611328,
+      "mean_token_accuracy": 0.832926099896431,
+      "num_tokens": 3323813.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.8118013942241669,
+      "epoch": 2.5766109785202866,
+      "grad_norm": 0.7059034109115601,
+      "learning_rate": 1.0328871908650328e-05,
+      "loss": 0.7040079498291015,
+      "mean_token_accuracy": 0.8309143006801605,
+      "num_tokens": 3386995.0,
+      "step": 2700
+    },
+    {
+      "entropy": 0.806537373661995,
+      "epoch": 2.624343675417661,
+      "grad_norm": 0.7431624531745911,
+      "learning_rate": 8.16856731479384e-06,
+      "loss": 0.688738021850586,
+      "mean_token_accuracy": 0.8332961136102677,
+      "num_tokens": 3449788.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.8005938905477524,
+      "epoch": 2.672076372315036,
+      "grad_norm": 0.8506917953491211,
+      "learning_rate": 6.251942900684804e-06,
+      "loss": 0.6902422332763671,
+      "mean_token_accuracy": 0.8328836613893509,
+      "num_tokens": 3511961.0,
+      "step": 2800
+    },
+    {
+      "entropy": 0.7861854726076126,
+      "epoch": 2.7198090692124106,
+      "grad_norm": 0.7526294589042664,
+      "learning_rate": 4.584084543436173e-06,
+      "loss": 0.6763236236572265,
+      "mean_token_accuracy": 0.8362268596887589,
+      "num_tokens": 3574785.0,
+      "step": 2850
+    },
+    {
+      "entropy": 0.7960345908999443,
+      "epoch": 2.767541766109785,
+      "grad_norm": 0.7011904120445251,
+      "learning_rate": 3.1694180046025646e-06,
+      "loss": 0.6868787384033204,
+      "mean_token_accuracy": 0.8327940762042999,
+      "num_tokens": 3636998.0,
+      "step": 2900
+    },
+    {
+      "entropy": 0.7944136542081833,
+      "epoch": 2.8152744630071598,
+      "grad_norm": 0.7616329193115234,
+      "learning_rate": 2.0116971861583565e-06,
+      "loss": 0.6847939300537109,
+      "mean_token_accuracy": 0.8341733467578888,
+      "num_tokens": 3700205.0,
+      "step": 2950
+    },
+    {
+      "entropy": 0.7962760901451111,
+      "epoch": 2.8630071599045346,
+      "grad_norm": 0.7714470624923706,
+      "learning_rate": 1.1139941692950074e-06,
+      "loss": 0.6834097290039063,
+      "mean_token_accuracy": 0.8354327756166459,
+      "num_tokens": 3763095.0,
+      "step": 3000
+    },
+    {
+      "entropy": 0.7855075746774673,
+      "epoch": 2.9107398568019094,
+      "grad_norm": 0.7710275053977966,
+      "learning_rate": 4.786910624704932e-07,
+      "loss": 0.6833212280273437,
+      "mean_token_accuracy": 0.8346857005357742,
+      "num_tokens": 3826241.0,
+      "step": 3050
+    },
+    {
+      "entropy": 0.7781499969959259,
+      "epoch": 2.958472553699284,
+      "grad_norm": 0.7958815693855286,
+      "learning_rate": 1.0747368034260686e-07,
+      "loss": 0.6754365539550782,
+      "mean_token_accuracy": 0.8352688610553741,
+      "num_tokens": 3887718.0,
+      "step": 3100
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.9699639558555588,
+      "eval_loss": 1.256901502609253,
+      "eval_mean_token_accuracy": 0.7340467933421773,
+      "eval_num_tokens": 3942036.0,
+      "eval_runtime": 86.059,
+      "eval_samples_per_second": 10.249,
+      "eval_steps_per_second": 10.249,
+      "step": 3144
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3144,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7336608363574067e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3144/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a92f47f215f6192c33d2a857fefbabc108b7e532a835fab7fa19809483c7a6f
+size 5304

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a92f47f215f6192c33d2a857fefbabc108b7e532a835fab7fa19809483c7a6f
+size 5304

training_args.json

@@ -0,0 +1,11 @@
+{
+  "model_name": "meta-llama/Llama-3.1-8B",
+  "stage1_method": "full",
+  "stage2_method": "lora",
+  "stage": "task_specific",
+  "num_epochs": 3,
+  "config_path": "/home/oelgendy/arabic-medical-llm/script/configs/lora.yaml",
+  "stage1_checkpoint": "outputs/exp04_llama_full_lora/stage1",
+  "train_samples": 16756,
+  "val_samples": 882
+}