Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
-base_model: TheBloke/Llama-2-7B-fp16
 library_name: peft
+base_model: TheBloke/Llama-2-7B-fp16
 ---
 
 # Model Card for Model ID

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
-    "q_proj",
     "o_proj",
-    "k_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06e781f63931f2a767880f6d4b91f140eb5043f4a642a1a68d8adbb81bbcae9d
+oid sha256:58a8f71955b57e8e1082d6f6f180646592764af968e225bda2b732733e64a34c
 size 67143296

checkpoint-10/README.md

@@ -1,6 +1,6 @@
 ---
-base_model: TheBloke/Llama-2-7B-fp16
 library_name: peft
+base_model: TheBloke/Llama-2-7B-fp16
 ---
 
 # Model Card for Model ID

checkpoint-10/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
-    "q_proj",
     "o_proj",
-    "k_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-10/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bdb12be1e8a3735b34051dd69cbe3689aa855355eecde29c57851904d81ecf
+oid sha256:232e478a97bd908880b31806be86d4debfd0492ee0eb83ba509e3293c6c3565a
 size 67143296

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7148ac4a39214d064ffce80fb50e3dd973562f331727ef157843d938bed4c7
+oid sha256:40afa20170f291b125eb81d0ffabecaf09477598d9e256ea01ff0b97e18e70a9
 size 134433530

checkpoint-10/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657ce80fb8c4abe8e223e56f6ece2f925cddc4720e917ac9a1e7ce94ab2749a8
+oid sha256:a35af14c8f81087292db706fc180cce03fb0f692ed151b0664293b217dd11fa5
 size 1064

checkpoint-10/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.769914984703064,
+  "best_metric": 1.733155369758606,
   "best_model_checkpoint": "/kaggle/working/checkpoint-10",
   "epoch": 1.1111111111111112,
   "eval_steps": 10,
@@ -10,24 +10,24 @@
   "log_history": [
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.022207504138350487,
-      "learning_rate": 0.00012592592592592592,
-      "loss": 2.058,
+      "grad_norm": 0.022282764315605164,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 2.0424,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "eval_loss": 1.769914984703064,
-      "eval_runtime": 34.8115,
-      "eval_samples_per_second": 1.034,
-      "eval_steps_per_second": 0.144,
+      "eval_loss": 1.733155369758606,
+      "eval_runtime": 34.5543,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
       "step": 10
     }
   ],
   "logging_steps": 10,
-  "max_steps": 27,
+  "max_steps": 135,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 15,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {

checkpoint-10/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6729829c35b3a85ce1b9965237f3a3b4ff249959cfad240042e0219e283812ed
+oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
 size 5112

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TheBloke/Llama-2-7B-fp16
+---
+
+# 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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-fp16",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_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:ac3b59826a91a331332b5850491ffec38f48afde058dead68205fb9903924aac
+size 67143296

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ff3c81928bee92eb73c79e2f6088612cc35f2fab427d0f73ba21269e3c8085
+size 134433530

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9fcf2e86ce0f113dac0c406c0b49ce72f5891aaa3942215cde240415672553
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67071c9831c7625e547eac0c0538006ee7fe06d1b1052844fd1cdb5172b8b9f
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_metric": 1.2115424871444702,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-90",
+  "epoch": 11.11111111111111,
+  "eval_steps": 10,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.022282764315605164,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 2.0424,
+      "step": 10
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "eval_loss": 1.733155369758606,
+      "eval_runtime": 34.5543,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 10
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.018981408327817917,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 1.6072,
+      "step": 20
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 1.5428930521011353,
+      "eval_runtime": 34.6485,
+      "eval_samples_per_second": 1.039,
+      "eval_steps_per_second": 0.144,
+      "step": 20
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.023157037794589996,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.4025,
+      "step": 30
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 1.4176721572875977,
+      "eval_runtime": 34.5433,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 30
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.021338749676942825,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 1.285,
+      "step": 40
+    },
+    {
+      "epoch": 4.444444444444445,
+      "eval_loss": 1.3449772596359253,
+      "eval_runtime": 34.5594,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 40
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 0.02489505708217621,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 1.1687,
+      "step": 50
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_loss": 1.2951068878173828,
+      "eval_runtime": 34.5896,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 50
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.028962766751646996,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.0521,
+      "step": 60
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 1.2674343585968018,
+      "eval_runtime": 34.5586,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 60
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 0.033917125314474106,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.9885,
+      "step": 70
+    },
+    {
+      "epoch": 7.777777777777778,
+      "eval_loss": 1.2424466609954834,
+      "eval_runtime": 34.5412,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 70
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.03393130004405975,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.8784,
+      "step": 80
+    },
+    {
+      "epoch": 8.88888888888889,
+      "eval_loss": 1.2252851724624634,
+      "eval_runtime": 34.58,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 80
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.04081139340996742,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8154,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2115424871444702,
+      "eval_runtime": 34.5784,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 90
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 0.04114004969596863,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.7376,
+      "step": 100
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_loss": 1.2147088050842285,
+      "eval_runtime": 34.595,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6718311886422016e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+size 5112

checkpoint-110/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TheBloke/Llama-2-7B-fp16
+---
+
+# 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-110/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-fp16",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-110/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7b95474c7a25c6961db7fe4913e88e0e78819b321a21a383b179782c22ef6c
+size 67143296

checkpoint-110/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567bf2cdba466fb3da7301567fc6eee0fd77e99808ab9402911468a94017eb0a
+size 134433530

checkpoint-110/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74e65bff4ecaf37ea6199e51bc5b668d4b069c4bc042e44eeac5d4c4ffef401
+size 14244

checkpoint-110/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7403172deaf546b51410d54cab636a5c53264be17aa6a439e5934523944587
+size 1064

checkpoint-110/trainer_state.json

@@ -0,0 +1,207 @@
+{
+  "best_metric": 1.2115424871444702,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-90",
+  "epoch": 12.222222222222221,
+  "eval_steps": 10,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.022282764315605164,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 2.0424,
+      "step": 10
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "eval_loss": 1.733155369758606,
+      "eval_runtime": 34.5543,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 10
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.018981408327817917,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 1.6072,
+      "step": 20
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 1.5428930521011353,
+      "eval_runtime": 34.6485,
+      "eval_samples_per_second": 1.039,
+      "eval_steps_per_second": 0.144,
+      "step": 20
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.023157037794589996,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.4025,
+      "step": 30
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 1.4176721572875977,
+      "eval_runtime": 34.5433,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 30
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.021338749676942825,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 1.285,
+      "step": 40
+    },
+    {
+      "epoch": 4.444444444444445,
+      "eval_loss": 1.3449772596359253,
+      "eval_runtime": 34.5594,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 40
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 0.02489505708217621,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 1.1687,
+      "step": 50
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_loss": 1.2951068878173828,
+      "eval_runtime": 34.5896,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 50
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.028962766751646996,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.0521,
+      "step": 60
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 1.2674343585968018,
+      "eval_runtime": 34.5586,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 60
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 0.033917125314474106,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.9885,
+      "step": 70
+    },
+    {
+      "epoch": 7.777777777777778,
+      "eval_loss": 1.2424466609954834,
+      "eval_runtime": 34.5412,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 70
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.03393130004405975,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.8784,
+      "step": 80
+    },
+    {
+      "epoch": 8.88888888888889,
+      "eval_loss": 1.2252851724624634,
+      "eval_runtime": 34.58,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 80
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.04081139340996742,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8154,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2115424871444702,
+      "eval_runtime": 34.5784,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 90
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 0.04114004969596863,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.7376,
+      "step": 100
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_loss": 1.2147088050842285,
+      "eval_runtime": 34.595,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 100
+    },
+    {
+      "epoch": 12.222222222222221,
+      "grad_norm": 0.04217207431793213,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.6642,
+      "step": 110
+    },
+    {
+      "epoch": 12.222222222222221,
+      "eval_loss": 1.2141155004501343,
+      "eval_runtime": 34.6053,
+      "eval_samples_per_second": 1.04,
+      "eval_steps_per_second": 0.144,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.93951986040832e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-110/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+size 5112

checkpoint-120/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TheBloke/Llama-2-7B-fp16
+---
+
+# 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-120/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-fp16",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-120/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1690155a5e4a4452a0e292d686003b08ac457e37c20099c948aae55ca8e453
+size 67143296

checkpoint-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14cc791678f8ce58b5f8b40f05113973aa7f94325c356b74d4df44ff8c1a956a
+size 134433530

checkpoint-120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:899181c47750d0177e5f1571bc0ad909b3a3ebab597f384c5023f1d8dcb8a73a
+size 14244

checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7846da062f26e398f1065295f9c7cbaf4768d3aa6b5518863ce89b7eb9d328e
+size 1064

checkpoint-120/trainer_state.json

@@ -0,0 +1,222 @@
+{
+  "best_metric": 1.20501708984375,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-120",
+  "epoch": 13.333333333333334,
+  "eval_steps": 10,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.022282764315605164,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 2.0424,
+      "step": 10
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "eval_loss": 1.733155369758606,
+      "eval_runtime": 34.5543,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 10
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.018981408327817917,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 1.6072,
+      "step": 20
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 1.5428930521011353,
+      "eval_runtime": 34.6485,
+      "eval_samples_per_second": 1.039,
+      "eval_steps_per_second": 0.144,
+      "step": 20
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.023157037794589996,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.4025,
+      "step": 30
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 1.4176721572875977,
+      "eval_runtime": 34.5433,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 30
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.021338749676942825,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 1.285,
+      "step": 40
+    },
+    {
+      "epoch": 4.444444444444445,
+      "eval_loss": 1.3449772596359253,
+      "eval_runtime": 34.5594,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 40
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 0.02489505708217621,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 1.1687,
+      "step": 50
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_loss": 1.2951068878173828,
+      "eval_runtime": 34.5896,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 50
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.028962766751646996,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.0521,
+      "step": 60
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 1.2674343585968018,
+      "eval_runtime": 34.5586,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 60
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 0.033917125314474106,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.9885,
+      "step": 70
+    },
+    {
+      "epoch": 7.777777777777778,
+      "eval_loss": 1.2424466609954834,
+      "eval_runtime": 34.5412,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 70
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.03393130004405975,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.8784,
+      "step": 80
+    },
+    {
+      "epoch": 8.88888888888889,
+      "eval_loss": 1.2252851724624634,
+      "eval_runtime": 34.58,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 80
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.04081139340996742,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8154,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2115424871444702,
+      "eval_runtime": 34.5784,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 90
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 0.04114004969596863,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.7376,
+      "step": 100
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_loss": 1.2147088050842285,
+      "eval_runtime": 34.595,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 100
+    },
+    {
+      "epoch": 12.222222222222221,
+      "grad_norm": 0.04217207431793213,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.6642,
+      "step": 110
+    },
+    {
+      "epoch": 12.222222222222221,
+      "eval_loss": 1.2141155004501343,
+      "eval_runtime": 34.6053,
+      "eval_samples_per_second": 1.04,
+      "eval_steps_per_second": 0.144,
+      "step": 110
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.04223904013633728,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.6353,
+      "step": 120
+    },
+    {
+      "epoch": 13.333333333333334,
+      "eval_loss": 1.20501708984375,
+      "eval_runtime": 34.6447,
+      "eval_samples_per_second": 1.039,
+      "eval_steps_per_second": 0.144,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.2063182503346176e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+size 5112

checkpoint-130/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TheBloke/Llama-2-7B-fp16
+---
+
+# 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-130/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-fp16",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-130/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a8f71955b57e8e1082d6f6f180646592764af968e225bda2b732733e64a34c
+size 67143296

checkpoint-130/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4daf30044a564bcf59ea2751408ea8dce0ec90f49d285e08583c20de07041a11
+size 134433530

checkpoint-130/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae41843bfbaf9bfb2da44e736c97098eebc3d8816f1d5ca8fbf5df92c5f45233
+size 14244

checkpoint-130/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b0d7953ae2a99e745d016a7542f93f08a2bf1f998ff2ee97a233ec022e1d0b
+size 1064

checkpoint-130/trainer_state.json

@@ -0,0 +1,237 @@
+{
+  "best_metric": 1.2035548686981201,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-130",
+  "epoch": 14.444444444444445,
+  "eval_steps": 10,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.022282764315605164,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 2.0424,
+      "step": 10
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "eval_loss": 1.733155369758606,
+      "eval_runtime": 34.5543,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 10
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.018981408327817917,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 1.6072,
+      "step": 20
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 1.5428930521011353,
+      "eval_runtime": 34.6485,
+      "eval_samples_per_second": 1.039,
+      "eval_steps_per_second": 0.144,
+      "step": 20
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.023157037794589996,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.4025,
+      "step": 30
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 1.4176721572875977,
+      "eval_runtime": 34.5433,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 30
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.021338749676942825,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 1.285,
+      "step": 40
+    },
+    {
+      "epoch": 4.444444444444445,
+      "eval_loss": 1.3449772596359253,
+      "eval_runtime": 34.5594,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 40
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 0.02489505708217621,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 1.1687,
+      "step": 50
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_loss": 1.2951068878173828,
+      "eval_runtime": 34.5896,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 50
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.028962766751646996,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.0521,
+      "step": 60
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 1.2674343585968018,
+      "eval_runtime": 34.5586,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 60
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 0.033917125314474106,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.9885,
+      "step": 70
+    },
+    {
+      "epoch": 7.777777777777778,
+      "eval_loss": 1.2424466609954834,
+      "eval_runtime": 34.5412,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
+      "step": 70
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.03393130004405975,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.8784,
+      "step": 80
+    },
+    {
+      "epoch": 8.88888888888889,
+      "eval_loss": 1.2252851724624634,
+      "eval_runtime": 34.58,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 80
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.04081139340996742,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8154,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2115424871444702,
+      "eval_runtime": 34.5784,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 90
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 0.04114004969596863,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.7376,
+      "step": 100
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_loss": 1.2147088050842285,
+      "eval_runtime": 34.595,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 100
+    },
+    {
+      "epoch": 12.222222222222221,
+      "grad_norm": 0.04217207431793213,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.6642,
+      "step": 110
+    },
+    {
+      "epoch": 12.222222222222221,
+      "eval_loss": 1.2141155004501343,
+      "eval_runtime": 34.6053,
+      "eval_samples_per_second": 1.04,
+      "eval_steps_per_second": 0.144,
+      "step": 110
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.04223904013633728,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.6353,
+      "step": 120
+    },
+    {
+      "epoch": 13.333333333333334,
+      "eval_loss": 1.20501708984375,
+      "eval_runtime": 34.6447,
+      "eval_samples_per_second": 1.039,
+      "eval_steps_per_second": 0.144,
+      "step": 120
+    },
+    {
+      "epoch": 14.444444444444445,
+      "grad_norm": 0.04531875252723694,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.5992,
+      "step": 130
+    },
+    {
+      "epoch": 14.444444444444445,
+      "eval_loss": 1.2035548686981201,
+      "eval_runtime": 34.5919,
+      "eval_samples_per_second": 1.041,
+      "eval_steps_per_second": 0.145,
+      "step": 130
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.474229492560691e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-130/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+size 5112

checkpoint-20/README.md

@@ -1,6 +1,6 @@
 ---
-base_model: TheBloke/Llama-2-7B-fp16
 library_name: peft
+base_model: TheBloke/Llama-2-7B-fp16
 ---
 
 # Model Card for Model ID

checkpoint-20/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
-    "q_proj",
     "o_proj",
-    "k_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-20/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06e781f63931f2a767880f6d4b91f140eb5043f4a642a1a68d8adbb81bbcae9d
+oid sha256:b330fca16a5ab17049bdd4e6e42df52bd8bd0ac1fbeb1577f683e7b1212f0d83
 size 67143296

checkpoint-20/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c2d558714cf4e61497566f22afcd3dd08e9e361ad958db0e013352981bfea11
+oid sha256:83e5faf17f41fc7dcd6907ecd97bc5e5b82bfa377a6683ddd9d25e9c5a4f3efd
 size 134433530

checkpoint-20/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebdc6c179af92eaaefe04390084f5c059665a54c6acce66616e26194c4f7008a
+oid sha256:18bf434d2955f164730aed9c7994cdd6c773ed80052fc3ef975fae4adef61283
 size 1064

checkpoint-20/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.6234142780303955,
+  "best_metric": 1.5428930521011353,
   "best_model_checkpoint": "/kaggle/working/checkpoint-20",
   "epoch": 2.2222222222222223,
   "eval_steps": 10,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.022207504138350487,
-      "learning_rate": 0.00012592592592592592,
-      "loss": 2.058,
+      "grad_norm": 0.022282764315605164,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 2.0424,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "eval_loss": 1.769914984703064,
-      "eval_runtime": 34.8115,
-      "eval_samples_per_second": 1.034,
-      "eval_steps_per_second": 0.144,
+      "eval_loss": 1.733155369758606,
+      "eval_runtime": 34.5543,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.145,
       "step": 10
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 0.022052476182579994,
-      "learning_rate": 5.185185185185185e-05,
-      "loss": 1.6674,
+      "grad_norm": 0.018981408327817917,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 1.6072,
       "step": 20
     },
     {
       "epoch": 2.2222222222222223,
-      "eval_loss": 1.6234142780303955,
-      "eval_runtime": 34.7607,
-      "eval_samples_per_second": 1.036,
+      "eval_loss": 1.5428930521011353,
+      "eval_runtime": 34.6485,
+      "eval_samples_per_second": 1.039,
       "eval_steps_per_second": 0.144,
       "step": 20
     }
   ],
   "logging_steps": 10,
-  "max_steps": 27,
+  "max_steps": 135,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 15,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {

checkpoint-20/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6729829c35b3a85ce1b9965237f3a3b4ff249959cfad240042e0219e283812ed
+oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
 size 5112

checkpoint-30/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TheBloke/Llama-2-7B-fp16
+---
+
+# 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