Initial commit

1K_Dataset_FineTuned_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b4eaba93f32b16fe247d5b1a36135d9d41f50b7502cd925cc9b2123017eff8
+size 533

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: vaiv/GeM2-Llamion-14B-Chat
+---
+
+# 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 0.11.1

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vaiv/GeM2-Llamion-14B-Chat",
+  "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": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_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 sha256:3ef69e51067889b87b8287b763e69a966c73a2109a482bab21a7c55422698319
+size 78675512

checkpoint-30/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: vaiv/GeM2-Llamion-14B-Chat
+---
+
+# 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 0.11.1

checkpoint-30/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vaiv/GeM2-Llamion-14B-Chat",
+  "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": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-30/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a084986c9be2a525cdc48f6137286f30632843cfc3be3968b62b24562543c0ad
+size 78675512

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e9f30e466dc7209fd2ec77da41e2361a950f83b37ea372acf17f82ed523c57
+size 157488261

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b348592609b97f528b85a8251f5c2a3aff9e2f20a4eda55d11cbcef4b440733d
+size 14575

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c52f1e1f7f8d03d4c41986fa678ad532b656201bd49d63369a405ab79d528bbf
+size 627

checkpoint-30/trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.960960960960961,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03203203203203203,
+      "grad_norm": 0.5500465035438538,
+      "learning_rate": 0.0002,
+      "loss": 1.9326,
+      "step": 1
+    },
+    {
+      "epoch": 0.06406406406406406,
+      "grad_norm": 0.3067496418952942,
+      "learning_rate": 0.0004,
+      "loss": 2.0123,
+      "step": 2
+    },
+    {
+      "epoch": 0.0960960960960961,
+      "grad_norm": 0.24163766205310822,
+      "learning_rate": 0.0003988275914308719,
+      "loss": 1.6857,
+      "step": 3
+    },
+    {
+      "epoch": 0.12812812812812813,
+      "grad_norm": 0.4033714830875397,
+      "learning_rate": 0.00039532411114201737,
+      "loss": 1.568,
+      "step": 4
+    },
+    {
+      "epoch": 0.16016016016016016,
+      "grad_norm": 0.40937018394470215,
+      "learning_rate": 0.00038953063423656053,
+      "loss": 1.2066,
+      "step": 5
+    },
+    {
+      "epoch": 0.1921921921921922,
+      "grad_norm": 0.303056001663208,
+      "learning_rate": 0.00038151508393419143,
+      "loss": 1.2382,
+      "step": 6
+    },
+    {
+      "epoch": 0.22422422422422422,
+      "grad_norm": 0.286432147026062,
+      "learning_rate": 0.00037137143523351785,
+      "loss": 0.9406,
+      "step": 7
+    },
+    {
+      "epoch": 0.25625625625625625,
+      "grad_norm": 0.354612797498703,
+      "learning_rate": 0.00035921861314112876,
+      "loss": 1.032,
+      "step": 8
+    },
+    {
+      "epoch": 0.2882882882882883,
+      "grad_norm": 0.3172045052051544,
+      "learning_rate": 0.0003451990983846262,
+      "loss": 1.1604,
+      "step": 9
+    },
+    {
+      "epoch": 0.3203203203203203,
+      "grad_norm": 0.35591357946395874,
+      "learning_rate": 0.00032947725695636553,
+      "loss": 1.2686,
+      "step": 10
+    },
+    {
+      "epoch": 0.35235235235235235,
+      "grad_norm": 0.45947980880737305,
+      "learning_rate": 0.0003122374130724765,
+      "loss": 1.4562,
+      "step": 11
+    },
+    {
+      "epoch": 0.3843843843843844,
+      "grad_norm": 0.381909042596817,
+      "learning_rate": 0.00029368168813995806,
+      "loss": 1.3231,
+      "step": 12
+    },
+    {
+      "epoch": 0.4164164164164164,
+      "grad_norm": 0.47724688053131104,
+      "learning_rate": 0.0002740276310679829,
+      "loss": 1.276,
+      "step": 13
+    },
+    {
+      "epoch": 0.44844844844844844,
+      "grad_norm": 0.3836033344268799,
+      "learning_rate": 0.00025350566770584423,
+      "loss": 1.5523,
+      "step": 14
+    },
+    {
+      "epoch": 0.4804804804804805,
+      "grad_norm": 0.3899593651294708,
+      "learning_rate": 0.000232356399310553,
+      "loss": 1.2293,
+      "step": 15
+    },
+    {
+      "epoch": 0.5125125125125125,
+      "grad_norm": 0.3470306992530823,
+      "learning_rate": 0.00021082778171708353,
+      "loss": 1.2625,
+      "step": 16
+    },
+    {
+      "epoch": 0.5445445445445446,
+      "grad_norm": 0.36498191952705383,
+      "learning_rate": 0.00018917221828291652,
+      "loss": 1.2286,
+      "step": 17
+    },
+    {
+      "epoch": 0.5765765765765766,
+      "grad_norm": 0.3170139193534851,
+      "learning_rate": 0.00016764360068944706,
+      "loss": 1.2458,
+      "step": 18
+    },
+    {
+      "epoch": 0.6086086086086087,
+      "grad_norm": 0.3011997938156128,
+      "learning_rate": 0.00014649433229415587,
+      "loss": 1.1672,
+      "step": 19
+    },
+    {
+      "epoch": 0.6406406406406406,
+      "grad_norm": 0.29357728362083435,
+      "learning_rate": 0.00012597236893201712,
+      "loss": 1.1728,
+      "step": 20
+    },
+    {
+      "epoch": 0.6726726726726727,
+      "grad_norm": 0.30459967255592346,
+      "learning_rate": 0.000106318311860042,
+      "loss": 1.1528,
+      "step": 21
+    },
+    {
+      "epoch": 0.7047047047047047,
+      "grad_norm": 0.23712120950222015,
+      "learning_rate": 8.776258692752355e-05,
+      "loss": 0.7205,
+      "step": 22
+    },
+    {
+      "epoch": 0.7367367367367368,
+      "grad_norm": 0.2815784215927124,
+      "learning_rate": 7.052274304363449e-05,
+      "loss": 0.7541,
+      "step": 23
+    },
+    {
+      "epoch": 0.7687687687687688,
+      "grad_norm": 0.3061799705028534,
+      "learning_rate": 5.4800901615373876e-05,
+      "loss": 1.4001,
+      "step": 24
+    },
+    {
+      "epoch": 0.8008008008008008,
+      "grad_norm": 0.32817238569259644,
+      "learning_rate": 4.078138685887125e-05,
+      "loss": 1.1528,
+      "step": 25
+    },
+    {
+      "epoch": 0.8328328328328328,
+      "grad_norm": 0.37422603368759155,
+      "learning_rate": 2.862856476648219e-05,
+      "loss": 1.3155,
+      "step": 26
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.3299436867237091,
+      "learning_rate": 1.8484916065808623e-05,
+      "loss": 1.1114,
+      "step": 27
+    },
+    {
+      "epoch": 0.8968968968968969,
+      "grad_norm": 0.32912251353263855,
+      "learning_rate": 1.0469365763439531e-05,
+      "loss": 1.0327,
+      "step": 28
+    },
+    {
+      "epoch": 0.928928928928929,
+      "grad_norm": 0.30801478028297424,
+      "learning_rate": 4.6758888579826685e-06,
+      "loss": 0.85,
+      "step": 29
+    },
+    {
+      "epoch": 0.960960960960961,
+      "grad_norm": 0.3802436292171478,
+      "learning_rate": 1.1724085691280805e-06,
+      "loss": 1.2445,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 31,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.01879310700544e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:514f71936a5f899993d94d34548bdd93baa947df9ea065c1e45431c6433d331c
+size 4667

runs/Jun17_12-17-24_main1/events.out.tfevents.1718626655.main1.193.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f091d706f292a5dd2d9f073c10b3b1143a04a0e608a3a1debabf316cbffaf68c
+size 12132

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "use_default_system_prompt": false
+}