Initial commit of latest checkpoint files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: CohereForAI/aya-101
+---
+
+# 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 0.10.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/aya-101",
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cececb099b3e2b9d2e272b5d46bfe07566c5242d08397e4b859854434d3c3140
+size 18918496

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832db86ce0568dd67d71155967e4768687015a9b5556ece5e75f4f0e3b0b5244
+size 37990394

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ab3bca667cf29f3ea7c5e9867acbb2b3f66632e8425745ffc0e157fb4ac21a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3639a21adec6316397ddf46df39adb14bf2c1acdddc7615711b1520a3e25eb1e
+size 1064

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": 0.5068484544754028,
+  "best_model_checkpoint": "/mnt/beegfs/farid/mlora/outputs/xnli/aya-101/zh/rank4_lr5e-5/checkpoint-4000",
+  "epoch": 0.24445893089960888,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020371577574967405,
+      "grad_norm": 2.87671160697937,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.201,
+      "step": 500
+    },
+    {
+      "epoch": 0.020371577574967405,
+      "eval_accuracy": 0.3718875502008032,
+      "eval_f1": 0.3144388665500335,
+      "eval_loss": 1.0995594263076782,
+      "eval_runtime": 413.743,
+      "eval_samples_per_second": 6.018,
+      "eval_steps_per_second": 0.377,
+      "step": 500
+    },
+    {
+      "epoch": 0.04074315514993481,
+      "grad_norm": 9.780874252319336,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 1.0225,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04074315514993481,
+      "eval_accuracy": 0.6277108433734939,
+      "eval_f1": 0.6294051779002606,
+      "eval_loss": 0.9010089039802551,
+      "eval_runtime": 411.7026,
+      "eval_samples_per_second": 6.048,
+      "eval_steps_per_second": 0.379,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06111473272490222,
+      "grad_norm": 54.40706253051758,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.7434,
+      "step": 1500
+    },
+    {
+      "epoch": 0.06111473272490222,
+      "eval_accuracy": 0.748995983935743,
+      "eval_f1": 0.7514237869702255,
+      "eval_loss": 0.6406136155128479,
+      "eval_runtime": 411.3183,
+      "eval_samples_per_second": 6.054,
+      "eval_steps_per_second": 0.379,
+      "step": 1500
+    },
+    {
+      "epoch": 0.08148631029986962,
+      "grad_norm": 11.607203483581543,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.6288,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08148631029986962,
+      "eval_accuracy": 0.7738955823293173,
+      "eval_f1": 0.7758546821907705,
+      "eval_loss": 0.5777280926704407,
+      "eval_runtime": 411.4602,
+      "eval_samples_per_second": 6.052,
+      "eval_steps_per_second": 0.379,
+      "step": 2000
+    },
+    {
+      "epoch": 0.10185788787483703,
+      "grad_norm": 5.107800483703613,
+      "learning_rate": 3.240740740740741e-05,
+      "loss": 0.6186,
+      "step": 2500
+    },
+    {
+      "epoch": 0.10185788787483703,
+      "eval_accuracy": 0.7847389558232932,
+      "eval_f1": 0.7871483289805999,
+      "eval_loss": 0.5597745180130005,
+      "eval_runtime": 411.7146,
+      "eval_samples_per_second": 6.048,
+      "eval_steps_per_second": 0.379,
+      "step": 2500
+    },
+    {
+      "epoch": 0.12222946544980444,
+      "grad_norm": 7.775627136230469,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.5909,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12222946544980444,
+      "eval_accuracy": 0.7963855421686747,
+      "eval_f1": 0.7956904592219637,
+      "eval_loss": 0.5284361839294434,
+      "eval_runtime": 411.1781,
+      "eval_samples_per_second": 6.056,
+      "eval_steps_per_second": 0.379,
+      "step": 3000
+    },
+    {
+      "epoch": 0.14260104302477183,
+      "grad_norm": 18.797571182250977,
+      "learning_rate": 2.314814814814815e-05,
+      "loss": 0.58,
+      "step": 3500
+    },
+    {
+      "epoch": 0.14260104302477183,
+      "eval_accuracy": 0.7891566265060241,
+      "eval_f1": 0.7909172071907363,
+      "eval_loss": 0.5231069922447205,
+      "eval_runtime": 412.124,
+      "eval_samples_per_second": 6.042,
+      "eval_steps_per_second": 0.379,
+      "step": 3500
+    },
+    {
+      "epoch": 0.16297262059973924,
+      "grad_norm": 5.233774185180664,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.5752,
+      "step": 4000
+    },
+    {
+      "epoch": 0.16297262059973924,
+      "eval_accuracy": 0.8028112449799196,
+      "eval_f1": 0.8033343776283127,
+      "eval_loss": 0.5068484544754028,
+      "eval_runtime": 411.2741,
+      "eval_samples_per_second": 6.054,
+      "eval_steps_per_second": 0.379,
+      "step": 4000
+    },
+    {
+      "epoch": 0.18334419817470665,
+      "grad_norm": 5.612044334411621,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.5495,
+      "step": 4500
+    },
+    {
+      "epoch": 0.18334419817470665,
+      "eval_accuracy": 0.8016064257028113,
+      "eval_f1": 0.8027178095880526,
+      "eval_loss": 0.5132325887680054,
+      "eval_runtime": 411.4311,
+      "eval_samples_per_second": 6.052,
+      "eval_steps_per_second": 0.379,
+      "step": 4500
+    },
+    {
+      "epoch": 0.20371577574967406,
+      "grad_norm": 5.75107479095459,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.5594,
+      "step": 5000
+    },
+    {
+      "epoch": 0.20371577574967406,
+      "eval_accuracy": 0.8016064257028113,
+      "eval_f1": 0.802067784242174,
+      "eval_loss": 0.52597576379776,
+      "eval_runtime": 412.0059,
+      "eval_samples_per_second": 6.044,
+      "eval_steps_per_second": 0.379,
+      "step": 5000
+    },
+    {
+      "epoch": 0.22408735332464147,
+      "grad_norm": 4.854472637176514,
+      "learning_rate": 4.6296296296296296e-06,
+      "loss": 0.5561,
+      "step": 5500
+    },
+    {
+      "epoch": 0.22408735332464147,
+      "eval_accuracy": 0.8016064257028113,
+      "eval_f1": 0.8025734250007549,
+      "eval_loss": 0.5094338059425354,
+      "eval_runtime": 411.5334,
+      "eval_samples_per_second": 6.051,
+      "eval_steps_per_second": 0.379,
+      "step": 5500
+    },
+    {
+      "epoch": 0.24445893089960888,
+      "grad_norm": 6.345026016235352,
+      "learning_rate": 0.0,
+      "loss": 0.5454,
+      "step": 6000
+    },
+    {
+      "epoch": 0.24445893089960888,
+      "eval_accuracy": 0.804417670682731,
+      "eval_f1": 0.8051855538804084,
+      "eval_loss": 0.5121804475784302,
+      "eval_runtime": 411.4571,
+      "eval_samples_per_second": 6.052,
+      "eval_steps_per_second": 0.379,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 8.03166870528e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c103d55742ba673ae3b14f7d6f249482d41a4ce5bb9f8ae0c7bdb60ec1b3943f
+size 5048