hr-train

README.md

@@ -0,0 +1,51 @@
+---
+base_model: E:\lenv\llmmode\localdown\Meta-Llama-3.1-8B-Instruct
+library_name: peft
+tags:
+- generated_from_trainer
+model-index:
+- name: lama3_lora3
+  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. -->
+
+# lama3_lora3
+
+This model was trained from scratch on the None dataset.
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu124
+- Datasets 3.0.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "E:\\lenv\\llmmode\\localdown\\Meta-Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "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": 256,
+  "lora_dropout": 0.5,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09de19e4db5cd9a11f1ea04385c821eef5e4e7eacae08f3ba0ae96ee296dbf85
+size 1342238560

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: E:\lenv\llmmode\localdown\Meta-Llama-3.1-8B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "E:\\lenv\\llmmode\\localdown\\Meta-Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "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": 256,
+  "lora_dropout": 0.5,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7fccaa3a812d62a1bf7a6e0dc90b17b023d98ced7757090bef391e5f4cea79
+size 1342238560

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04231aaa96c6503bea0e9f8a4501b0e0a9af12bb9bc677caabd710ac957d095
+size 2684732882

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4608fe39c5d636fda6075e89d8c795c8d1602432e9ccf4b870b3679a66d4c401
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172bbc317a22af49648653c031b9b80dae00fe0bd40f2fa2909748ce7e72fc0f
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.451612903225806,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 1.17766535282135,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 2.5686,
+      "step": 10
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 1.074232816696167,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 2.2897,
+      "step": 20
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 1.3295201063156128,
+      "learning_rate": 9e-05,
+      "loss": 2.0286,
+      "step": 30
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 1.5712580680847168,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 1.6861,
+      "step": 40
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 2.046724319458008,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 1.5038,
+      "step": 50
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 2.154179334640503,
+      "learning_rate": 8e-05,
+      "loss": 1.1607,
+      "step": 60
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 1.9853581190109253,
+      "learning_rate": 7.666666666666667e-05,
+      "loss": 0.8446,
+      "step": 70
+    },
+    {
+      "epoch": 5.161290322580645,
+      "grad_norm": 1.9510444402694702,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.6355,
+      "step": 80
+    },
+    {
+      "epoch": 5.806451612903226,
+      "grad_norm": 2.4067842960357666,
+      "learning_rate": 7e-05,
+      "loss": 0.396,
+      "step": 90
+    },
+    {
+      "epoch": 6.451612903225806,
+      "grad_norm": 2.007054090499878,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.2548,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.89031048921088e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f684410c2baa0ec6e59caf223fb99687291c450479fc2f8246e737644deee0
+size 5176

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: E:\lenv\llmmode\localdown\Meta-Llama-3.1-8B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "E:\\lenv\\llmmode\\localdown\\Meta-Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "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": 256,
+  "lora_dropout": 0.5,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98279e84d31455cd7e5b9fa0b7463bc015bbb1a1840847a968ca35fe5726cfee
+size 1342238560

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3fd0927f9666893fccf2f4fbee996d0f0a36dda1b520b528ba3b96c175949c
+size 2684732882

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a3905cd12784728658ab9ea3a9109d0042a24a844f8c7de5a3190e002f7c15
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd5364ddb13584666ecd791c6d39855f64e77860e0e91a7911e5c04081f7d16e
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.903225806451612,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 1.17766535282135,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 2.5686,
+      "step": 10
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 1.074232816696167,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 2.2897,
+      "step": 20
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 1.3295201063156128,
+      "learning_rate": 9e-05,
+      "loss": 2.0286,
+      "step": 30
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 1.5712580680847168,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 1.6861,
+      "step": 40
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 2.046724319458008,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 1.5038,
+      "step": 50
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 2.154179334640503,
+      "learning_rate": 8e-05,
+      "loss": 1.1607,
+      "step": 60
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 1.9853581190109253,
+      "learning_rate": 7.666666666666667e-05,
+      "loss": 0.8446,
+      "step": 70
+    },
+    {
+      "epoch": 5.161290322580645,
+      "grad_norm": 1.9510444402694702,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.6355,
+      "step": 80
+    },
+    {
+      "epoch": 5.806451612903226,
+      "grad_norm": 2.4067842960357666,
+      "learning_rate": 7e-05,
+      "loss": 0.396,
+      "step": 90
+    },
+    {
+      "epoch": 6.451612903225806,
+      "grad_norm": 2.007054090499878,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.2548,
+      "step": 100
+    },
+    {
+      "epoch": 7.096774193548387,
+      "grad_norm": 1.1860252618789673,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 0.1762,
+      "step": 110
+    },
+    {
+      "epoch": 7.741935483870968,
+      "grad_norm": 1.3247166872024536,
+      "learning_rate": 6e-05,
+      "loss": 0.0907,
+      "step": 120
+    },
+    {
+      "epoch": 8.387096774193548,
+      "grad_norm": 1.0443822145462036,
+      "learning_rate": 5.666666666666667e-05,
+      "loss": 0.0663,
+      "step": 130
+    },
+    {
+      "epoch": 9.03225806451613,
+      "grad_norm": 0.96644127368927,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.0593,
+      "step": 140
+    },
+    {
+      "epoch": 9.67741935483871,
+      "grad_norm": 1.1865681409835815,
+      "learning_rate": 5e-05,
+      "loss": 0.0366,
+      "step": 150
+    },
+    {
+      "epoch": 10.32258064516129,
+      "grad_norm": 0.8162716031074524,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.0329,
+      "step": 160
+    },
+    {
+      "epoch": 10.967741935483872,
+      "grad_norm": 0.8599117398262024,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.0275,
+      "step": 170
+    },
+    {
+      "epoch": 11.612903225806452,
+      "grad_norm": 0.5749396681785583,
+      "learning_rate": 4e-05,
+      "loss": 0.0182,
+      "step": 180
+    },
+    {
+      "epoch": 12.258064516129032,
+      "grad_norm": 0.4733521044254303,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.0157,
+      "step": 190
+    },
+    {
+      "epoch": 12.903225806451612,
+      "grad_norm": 0.654066264629364,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0123,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.78062097842176e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f684410c2baa0ec6e59caf223fb99687291c450479fc2f8246e737644deee0
+size 5176

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: E:\lenv\llmmode\localdown\Meta-Llama-3.1-8B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "E:\\lenv\\llmmode\\localdown\\Meta-Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "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": 256,
+  "lora_dropout": 0.5,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256a38a4bfa48f7f4c1ed0578ab50e08a17ecb4f1965789c11a7b6db8786574a
+size 1342238560

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8263a423066e1381f86840437f60ae764739d0a82894453a2444c689daa9a134
+size 2684732882

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac23bd68b689c22c1c2cd6c70642737f482d0b93273a34cd6005a81048705e30
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7a30af751fa27f81dbf5d838c3d86fc6056c2936cb106ad6b76d1cd8bbcc7d
+size 1064

checkpoint-300/trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.35483870967742,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 1.17766535282135,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 2.5686,
+      "step": 10
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 1.074232816696167,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 2.2897,
+      "step": 20
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 1.3295201063156128,
+      "learning_rate": 9e-05,
+      "loss": 2.0286,
+      "step": 30
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 1.5712580680847168,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 1.6861,
+      "step": 40
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 2.046724319458008,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 1.5038,
+      "step": 50
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 2.154179334640503,
+      "learning_rate": 8e-05,
+      "loss": 1.1607,
+      "step": 60
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 1.9853581190109253,
+      "learning_rate": 7.666666666666667e-05,
+      "loss": 0.8446,
+      "step": 70
+    },
+    {
+      "epoch": 5.161290322580645,
+      "grad_norm": 1.9510444402694702,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.6355,
+      "step": 80
+    },
+    {
+      "epoch": 5.806451612903226,
+      "grad_norm": 2.4067842960357666,
+      "learning_rate": 7e-05,
+      "loss": 0.396,
+      "step": 90
+    },
+    {
+      "epoch": 6.451612903225806,
+      "grad_norm": 2.007054090499878,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.2548,
+      "step": 100
+    },
+    {
+      "epoch": 7.096774193548387,
+      "grad_norm": 1.1860252618789673,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 0.1762,
+      "step": 110
+    },
+    {
+      "epoch": 7.741935483870968,
+      "grad_norm": 1.3247166872024536,
+      "learning_rate": 6e-05,
+      "loss": 0.0907,
+      "step": 120
+    },
+    {
+      "epoch": 8.387096774193548,
+      "grad_norm": 1.0443822145462036,
+      "learning_rate": 5.666666666666667e-05,
+      "loss": 0.0663,
+      "step": 130
+    },
+    {
+      "epoch": 9.03225806451613,
+      "grad_norm": 0.96644127368927,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.0593,
+      "step": 140
+    },
+    {
+      "epoch": 9.67741935483871,
+      "grad_norm": 1.1865681409835815,
+      "learning_rate": 5e-05,
+      "loss": 0.0366,
+      "step": 150
+    },
+    {
+      "epoch": 10.32258064516129,
+      "grad_norm": 0.8162716031074524,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.0329,
+      "step": 160
+    },
+    {
+      "epoch": 10.967741935483872,
+      "grad_norm": 0.8599117398262024,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.0275,
+      "step": 170
+    },
+    {
+      "epoch": 11.612903225806452,
+      "grad_norm": 0.5749396681785583,
+      "learning_rate": 4e-05,
+      "loss": 0.0182,
+      "step": 180
+    },
+    {
+      "epoch": 12.258064516129032,
+      "grad_norm": 0.4733521044254303,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.0157,
+      "step": 190
+    },
+    {
+      "epoch": 12.903225806451612,
+      "grad_norm": 0.654066264629364,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0123,
+      "step": 200
+    },
+    {
+      "epoch": 13.548387096774194,
+      "grad_norm": 0.6262084245681763,
+      "learning_rate": 3e-05,
+      "loss": 0.0088,
+      "step": 210
+    },
+    {
+      "epoch": 14.193548387096774,
+      "grad_norm": 0.45759856700897217,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.0084,
+      "step": 220
+    },
+    {
+      "epoch": 14.838709677419354,
+      "grad_norm": 0.20262958109378815,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.0061,
+      "step": 230
+    },
+    {
+      "epoch": 15.483870967741936,
+      "grad_norm": 0.21387845277786255,
+      "learning_rate": 2e-05,
+      "loss": 0.0051,
+      "step": 240
+    },
+    {
+      "epoch": 16.129032258064516,
+      "grad_norm": 0.13789059221744537,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0049,
+      "step": 250
+    },
+    {
+      "epoch": 16.774193548387096,
+      "grad_norm": 0.08313337713479996,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.0039,
+      "step": 260
+    },
+    {
+      "epoch": 17.419354838709676,
+      "grad_norm": 0.10394257307052612,
+      "learning_rate": 1e-05,
+      "loss": 0.0041,
+      "step": 270
+    },
+    {
+      "epoch": 18.06451612903226,
+      "grad_norm": 0.10370919108390808,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0039,
+      "step": 280
+    },
+    {
+      "epoch": 18.70967741935484,
+      "grad_norm": 0.06597656011581421,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0035,
+      "step": 290
+    },
+    {
+      "epoch": 19.35483870967742,
+      "grad_norm": 0.11637765914201736,
+      "learning_rate": 0.0,
+      "loss": 0.0035,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.67093146763264e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f684410c2baa0ec6e59caf223fb99687291c450479fc2f8246e737644deee0
+size 5176

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62520cd7a435d2f9026a767dfbaeb1bf472db5c5192cb1958c46fbadc1aa9a5e
+size 5176