Upload 5 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: internlm/internlm2-1_8b
+---
+
+# 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 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "internlm/internlm2-1_8b",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "wqkv",
+    "w1",
+    "w3",
+    "w2",
+    "wo"
+  ],
+  "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 sha256:4eb0b71e0344c866d9eb3ab045020448241ef87edee557161f0247ca7a3d7bd1
+size 31488776

trainer_state.json

@@ -0,0 +1,333 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2,
+  "eval_steps": 50,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 14.438831329345703,
+      "learning_rate": 0.00015,
+      "loss": 1.116,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 0.8588868975639343,
+      "eval_runtime": 680.2426,
+      "eval_samples_per_second": 8.601,
+      "eval_steps_per_second": 1.076,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.0438328981399536,
+      "learning_rate": 0.0003,
+      "loss": 0.723,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 0.8119707703590393,
+      "eval_runtime": 681.2671,
+      "eval_samples_per_second": 8.588,
+      "eval_steps_per_second": 1.074,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.8140527009963989,
+      "learning_rate": 0.0002833333333333333,
+      "loss": 0.6987,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.7736836075782776,
+      "eval_runtime": 681.2882,
+      "eval_samples_per_second": 8.588,
+      "eval_steps_per_second": 1.074,
+      "step": 150
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.7538554668426514,
+      "learning_rate": 0.0002666666666666666,
+      "loss": 0.6701,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.7494252324104309,
+      "eval_runtime": 681.1585,
+      "eval_samples_per_second": 8.59,
+      "eval_steps_per_second": 1.075,
+      "step": 200
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8082383871078491,
+      "learning_rate": 0.00025,
+      "loss": 0.6585,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 0.7359848022460938,
+      "eval_runtime": 681.3996,
+      "eval_samples_per_second": 8.587,
+      "eval_steps_per_second": 1.074,
+      "step": 250
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.7390263080596924,
+      "learning_rate": 0.0002333333333333333,
+      "loss": 0.6451,
+      "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.7315810322761536,
+      "eval_runtime": 680.7597,
+      "eval_samples_per_second": 8.595,
+      "eval_steps_per_second": 1.075,
+      "step": 300
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.719605565071106,
+      "learning_rate": 0.00021666666666666666,
+      "loss": 0.6382,
+      "step": 350
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.6773383617401123,
+      "eval_runtime": 680.8905,
+      "eval_samples_per_second": 8.593,
+      "eval_steps_per_second": 1.075,
+      "step": 350
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.8071795701980591,
+      "learning_rate": 0.00019999999999999998,
+      "loss": 0.6304,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 0.6790196299552917,
+      "eval_runtime": 680.4041,
+      "eval_samples_per_second": 8.599,
+      "eval_steps_per_second": 1.076,
+      "step": 400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6562775373458862,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 0.6236,
+      "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.667582631111145,
+      "eval_runtime": 680.9279,
+      "eval_samples_per_second": 8.593,
+      "eval_steps_per_second": 1.075,
+      "step": 450
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6858498454093933,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 0.6127,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.6611046195030212,
+      "eval_runtime": 681.3448,
+      "eval_samples_per_second": 8.587,
+      "eval_steps_per_second": 1.074,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.7050228714942932,
+      "learning_rate": 0.00015,
+      "loss": 0.6109,
+      "step": 550
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.6624142527580261,
+      "eval_runtime": 680.8132,
+      "eval_samples_per_second": 8.594,
+      "eval_steps_per_second": 1.075,
+      "step": 550
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.7099040746688843,
+      "learning_rate": 0.0001333333333333333,
+      "loss": 0.6074,
+      "step": 600
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.6503908634185791,
+      "eval_runtime": 680.9458,
+      "eval_samples_per_second": 8.592,
+      "eval_steps_per_second": 1.075,
+      "step": 600
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.7423191070556641,
+      "learning_rate": 0.00011666666666666665,
+      "loss": 0.5972,
+      "step": 650
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.6401746273040771,
+      "eval_runtime": 680.6123,
+      "eval_samples_per_second": 8.597,
+      "eval_steps_per_second": 1.076,
+      "step": 650
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.6712120175361633,
+      "learning_rate": 9.999999999999999e-05,
+      "loss": 0.5912,
+      "step": 700
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.6332426071166992,
+      "eval_runtime": 680.7596,
+      "eval_samples_per_second": 8.595,
+      "eval_steps_per_second": 1.075,
+      "step": 700
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.7194417715072632,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 0.5934,
+      "step": 750
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 0.6242749094963074,
+      "eval_runtime": 679.731,
+      "eval_samples_per_second": 8.608,
+      "eval_steps_per_second": 1.077,
+      "step": 750
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7845382690429688,
+      "learning_rate": 6.666666666666666e-05,
+      "loss": 0.5908,
+      "step": 800
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.6116130352020264,
+      "eval_runtime": 681.1204,
+      "eval_samples_per_second": 8.59,
+      "eval_steps_per_second": 1.075,
+      "step": 800
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.7342799305915833,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 0.5824,
+      "step": 850
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.6023569703102112,
+      "eval_runtime": 680.663,
+      "eval_samples_per_second": 8.596,
+      "eval_steps_per_second": 1.075,
+      "step": 850
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6745529174804688,
+      "learning_rate": 3.333333333333333e-05,
+      "loss": 0.5823,
+      "step": 900
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 0.5980194211006165,
+      "eval_runtime": 680.2295,
+      "eval_samples_per_second": 8.602,
+      "eval_steps_per_second": 1.076,
+      "step": 900
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.7388492226600647,
+      "learning_rate": 1.6666666666666664e-05,
+      "loss": 0.5876,
+      "step": 950
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 0.5954298973083496,
+      "eval_runtime": 680.8083,
+      "eval_samples_per_second": 8.594,
+      "eval_steps_per_second": 1.075,
+      "step": 950
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8207566738128662,
+      "learning_rate": 0.0,
+      "loss": 0.5748,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.5945320725440979,
+      "eval_runtime": 680.8349,
+      "eval_samples_per_second": 8.594,
+      "eval_steps_per_second": 1.075,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.187924717080576e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db9f452ec744555ae421f40234c5c68c6d5069b9866a96baae4ee6a12fef477
+size 5048