Upload 8 files

README.md

@@ -1,5 +1,202 @@
 ---
-license: mit
-base_model:
-- openai-community/gpt2
----
+base_model: openai-community/gpt2-medium
+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 0.13.2

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "GPT2LMHeadModel",
+    "parent_library": "transformers.models.gpt2.modeling_gpt2"
+  },
+  "base_model_name_or_path": "openai-community/gpt2-medium",
+  "bias": "none",
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "attn.q_attn",
+    "attn.c_attn",
+    "attn.v_attn"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6a471a964abee443c283fe8172901295c0c8a5c7d509c23096d677747e636f
+size 12589136

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb17e442f1d44a37ab1a94466c3e84deb361c7b61fe669d15f798a3f509659f
+size 25206586

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5620c430df1ca74939020d9c48d52aa3a8501e1734b6a1de0f0463acd1b4dff0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f03cd71de0821e87e0f5a6a6174c73a7a197df82a5553623705418216a4cb5c
+size 1064

trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28178,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10646603733409042,
+      "grad_norm": 0.10739253461360931,
+      "learning_rate": 4.81935110918419e-05,
+      "loss": 1.4731,
+      "step": 1500
+    },
+    {
+      "epoch": 0.21293207466818084,
+      "grad_norm": 0.12009046971797943,
+      "learning_rate": 4.548377772960474e-05,
+      "loss": 0.1519,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31939811200227125,
+      "grad_norm": 0.17752079665660858,
+      "learning_rate": 4.277404436736759e-05,
+      "loss": 0.1419,
+      "step": 4500
+    },
+    {
+      "epoch": 0.4258641493363617,
+      "grad_norm": 0.18882086873054504,
+      "learning_rate": 4.006431100513043e-05,
+      "loss": 0.1371,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5323301866704522,
+      "grad_norm": 0.13926886022090912,
+      "learning_rate": 3.735457764289327e-05,
+      "loss": 0.1348,
+      "step": 7500
+    },
+    {
+      "epoch": 0.6387962240045425,
+      "grad_norm": 0.13389110565185547,
+      "learning_rate": 3.464484428065612e-05,
+      "loss": 0.1324,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7452622613386329,
+      "grad_norm": 0.11937592923641205,
+      "learning_rate": 3.1935110918418966e-05,
+      "loss": 0.1295,
+      "step": 10500
+    },
+    {
+      "epoch": 0.8517282986727234,
+      "grad_norm": 0.09599358588457108,
+      "learning_rate": 2.9225377556181803e-05,
+      "loss": 0.1282,
+      "step": 12000
+    },
+    {
+      "epoch": 0.9581943360068138,
+      "grad_norm": 0.1334109604358673,
+      "learning_rate": 2.651564419394465e-05,
+      "loss": 0.1287,
+      "step": 13500
+    },
+    {
+      "epoch": 1.0646603733409044,
+      "grad_norm": 0.14946720004081726,
+      "learning_rate": 2.3805910831707495e-05,
+      "loss": 0.1282,
+      "step": 15000
+    },
+    {
+      "epoch": 1.1711264106749946,
+      "grad_norm": 0.12653611600399017,
+      "learning_rate": 2.109617746947034e-05,
+      "loss": 0.1256,
+      "step": 16500
+    },
+    {
+      "epoch": 1.2775924480090852,
+      "grad_norm": 0.19287967681884766,
+      "learning_rate": 1.8386444107233183e-05,
+      "loss": 0.127,
+      "step": 18000
+    },
+    {
+      "epoch": 1.3840584853431754,
+      "grad_norm": 0.16098152101039886,
+      "learning_rate": 1.5676710744996027e-05,
+      "loss": 0.1242,
+      "step": 19500
+    },
+    {
+      "epoch": 1.4905245226772659,
+      "grad_norm": 0.16886812448501587,
+      "learning_rate": 1.2966977382758871e-05,
+      "loss": 0.1236,
+      "step": 21000
+    },
+    {
+      "epoch": 1.5969905600113563,
+      "grad_norm": 0.14498655498027802,
+      "learning_rate": 1.0257244020521714e-05,
+      "loss": 0.124,
+      "step": 22500
+    },
+    {
+      "epoch": 1.703456597345447,
+      "grad_norm": 0.19877927005290985,
+      "learning_rate": 7.547510658284558e-06,
+      "loss": 0.1251,
+      "step": 24000
+    },
+    {
+      "epoch": 1.8099226346795372,
+      "grad_norm": 0.33909276127815247,
+      "learning_rate": 4.837777296047403e-06,
+      "loss": 0.1242,
+      "step": 25500
+    },
+    {
+      "epoch": 1.9163886720136276,
+      "grad_norm": 0.14188048243522644,
+      "learning_rate": 2.1280439338102465e-06,
+      "loss": 0.1222,
+      "step": 27000
+    }
+  ],
+  "logging_steps": 1500,
+  "max_steps": 28178,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0576304824909824e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cb965b572e952a0b06cdecba8d1e5a72039dd0258bb2eb0966c5def14b9a9e
+size 5176