Task: SequenceClassification

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: RMHalak/opt-6.7b-GPTQ-4bits-128g-wikitext2
+---
+
+# 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 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "RMHalak/opt-6.7b-GPTQ-4bits-128g-wikitext2",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "fc1",
+    "fc2",
+    "v_proj",
+    "k_proj",
+    "out_proj"
+  ],
+  "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 sha256:74f1c2744a9aa7c8c7639a6528db0b8d0bc10dba67a5fc9f59be2a7122520a23
+size 75575016

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

trainer_state-opt-gptq-QLORA-super_glue-cb-sequence_classification.json

@@ -0,0 +1,710 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 1,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 32.508975982666016,
+      "learning_rate": 2.5e-05,
+      "loss": 1.9242,
+      "step": 1
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.845262050628662,
+      "eval_runtime": 1.664,
+      "eval_samples_per_second": 37.261,
+      "eval_steps_per_second": 1.202,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 31.633163452148438,
+      "learning_rate": 5e-05,
+      "loss": 1.8427,
+      "step": 2
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.8311964273452759,
+      "eval_runtime": 1.6638,
+      "eval_samples_per_second": 37.264,
+      "eval_steps_per_second": 1.202,
+      "step": 2
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 32.75844192504883,
+      "learning_rate": 4.868421052631579e-05,
+      "loss": 1.811,
+      "step": 3
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.7797694206237793,
+      "eval_runtime": 1.6596,
+      "eval_samples_per_second": 37.359,
+      "eval_steps_per_second": 1.205,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 33.511817932128906,
+      "learning_rate": 4.736842105263158e-05,
+      "loss": 1.9235,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.7310200929641724,
+      "eval_runtime": 1.6611,
+      "eval_samples_per_second": 37.325,
+      "eval_steps_per_second": 1.204,
+      "step": 4
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 30.517168045043945,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 1.6903,
+      "step": 5
+    },
+    {
+      "epoch": 1.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.6759703159332275,
+      "eval_runtime": 1.6597,
+      "eval_samples_per_second": 37.357,
+      "eval_steps_per_second": 1.205,
+      "step": 5
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 29.271242141723633,
+      "learning_rate": 4.473684210526316e-05,
+      "loss": 1.6032,
+      "step": 6
+    },
+    {
+      "epoch": 1.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.620038390159607,
+      "eval_runtime": 1.6099,
+      "eval_samples_per_second": 38.511,
+      "eval_steps_per_second": 1.242,
+      "step": 6
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 31.15843963623047,
+      "learning_rate": 4.342105263157895e-05,
+      "loss": 1.7522,
+      "step": 7
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.5599325895309448,
+      "eval_runtime": 1.6096,
+      "eval_samples_per_second": 38.518,
+      "eval_steps_per_second": 1.243,
+      "step": 7
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 32.795101165771484,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 1.665,
+      "step": 8
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.5007245540618896,
+      "eval_runtime": 1.6593,
+      "eval_samples_per_second": 37.365,
+      "eval_steps_per_second": 1.205,
+      "step": 8
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 24.919414520263672,
+      "learning_rate": 4.078947368421053e-05,
+      "loss": 1.4334,
+      "step": 9
+    },
+    {
+      "epoch": 2.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.4376260042190552,
+      "eval_runtime": 1.6592,
+      "eval_samples_per_second": 37.367,
+      "eval_steps_per_second": 1.205,
+      "step": 9
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 26.314369201660156,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 1.4499,
+      "step": 10
+    },
+    {
+      "epoch": 2.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.3746062517166138,
+      "eval_runtime": 1.659,
+      "eval_samples_per_second": 37.372,
+      "eval_steps_per_second": 1.206,
+      "step": 10
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 29.581968307495117,
+      "learning_rate": 3.815789473684211e-05,
+      "loss": 1.4751,
+      "step": 11
+    },
+    {
+      "epoch": 2.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.3099955320358276,
+      "eval_runtime": 1.6591,
+      "eval_samples_per_second": 37.37,
+      "eval_steps_per_second": 1.205,
+      "step": 11
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 23.594392776489258,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.2184,
+      "step": 12
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.2490864992141724,
+      "eval_runtime": 1.6592,
+      "eval_samples_per_second": 37.368,
+      "eval_steps_per_second": 1.205,
+      "step": 12
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 21.464380264282227,
+      "learning_rate": 3.5526315789473684e-05,
+      "loss": 1.1918,
+      "step": 13
+    },
+    {
+      "epoch": 3.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.1868385076522827,
+      "eval_runtime": 1.6597,
+      "eval_samples_per_second": 37.355,
+      "eval_steps_per_second": 1.205,
+      "step": 13
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 23.22657585144043,
+      "learning_rate": 3.421052631578947e-05,
+      "loss": 1.2961,
+      "step": 14
+    },
+    {
+      "epoch": 3.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.1285125017166138,
+      "eval_runtime": 1.6596,
+      "eval_samples_per_second": 37.359,
+      "eval_steps_per_second": 1.205,
+      "step": 14
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 20.130626678466797,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 1.058,
+      "step": 15
+    },
+    {
+      "epoch": 3.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.0760616064071655,
+      "eval_runtime": 1.6629,
+      "eval_samples_per_second": 37.284,
+      "eval_steps_per_second": 1.203,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 19.751522064208984,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 1.0431,
+      "step": 16
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 1.027753233909607,
+      "eval_runtime": 1.6593,
+      "eval_samples_per_second": 37.365,
+      "eval_steps_per_second": 1.205,
+      "step": 16
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 21.63219451904297,
+      "learning_rate": 3.0263157894736844e-05,
+      "loss": 1.1025,
+      "step": 17
+    },
+    {
+      "epoch": 4.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 0.9908801913261414,
+      "eval_runtime": 1.6593,
+      "eval_samples_per_second": 37.364,
+      "eval_steps_per_second": 1.205,
+      "step": 17
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 10.896172523498535,
+      "learning_rate": 2.8947368421052634e-05,
+      "loss": 1.027,
+      "step": 18
+    },
+    {
+      "epoch": 4.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 0.9616305232048035,
+      "eval_runtime": 1.6609,
+      "eval_samples_per_second": 37.328,
+      "eval_steps_per_second": 1.204,
+      "step": 18
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 10.560508728027344,
+      "learning_rate": 2.7631578947368426e-05,
+      "loss": 0.9494,
+      "step": 19
+    },
+    {
+      "epoch": 4.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.26990838618745594,
+      "eval_loss": 0.9417527914047241,
+      "eval_runtime": 1.6591,
+      "eval_samples_per_second": 37.369,
+      "eval_steps_per_second": 1.205,
+      "step": 19
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.201696395874023,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.8845,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.532258064516129,
+      "eval_f1": 0.32762030323005936,
+      "eval_loss": 0.9292937517166138,
+      "eval_runtime": 1.6591,
+      "eval_samples_per_second": 37.371,
+      "eval_steps_per_second": 1.206,
+      "step": 20
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 3.4469192028045654,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0096,
+      "step": 21
+    },
+    {
+      "epoch": 5.25,
+      "eval_accuracy": 0.5967741935483871,
+      "eval_f1": 0.4066193853427896,
+      "eval_loss": 0.9209141731262207,
+      "eval_runtime": 1.6594,
+      "eval_samples_per_second": 37.363,
+      "eval_steps_per_second": 1.205,
+      "step": 21
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 5.117708683013916,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 0.8488,
+      "step": 22
+    },
+    {
+      "epoch": 5.5,
+      "eval_accuracy": 0.6290322580645161,
+      "eval_f1": 0.434640522875817,
+      "eval_loss": 0.9170079231262207,
+      "eval_runtime": 1.6597,
+      "eval_samples_per_second": 37.356,
+      "eval_steps_per_second": 1.205,
+      "step": 22
+    },
+    {
+      "epoch": 5.75,
+      "grad_norm": 4.267374515533447,
+      "learning_rate": 2.236842105263158e-05,
+      "loss": 0.847,
+      "step": 23
+    },
+    {
+      "epoch": 5.75,
+      "eval_accuracy": 0.6129032258064516,
+      "eval_f1": 0.41979655712050085,
+      "eval_loss": 0.9126449227333069,
+      "eval_runtime": 1.6593,
+      "eval_samples_per_second": 37.364,
+      "eval_steps_per_second": 1.205,
+      "step": 23
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.23488712310791,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.8127,
+      "step": 24
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.3648484848484848,
+      "eval_loss": 0.9107705354690552,
+      "eval_runtime": 1.6606,
+      "eval_samples_per_second": 37.337,
+      "eval_steps_per_second": 1.204,
+      "step": 24
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 6.90617561340332,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 0.8793,
+      "step": 25
+    },
+    {
+      "epoch": 6.25,
+      "eval_accuracy": 0.5161290322580645,
+      "eval_f1": 0.34080808080808084,
+      "eval_loss": 0.9092269539833069,
+      "eval_runtime": 1.6621,
+      "eval_samples_per_second": 37.302,
+      "eval_steps_per_second": 1.203,
+      "step": 25
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 3.975435733795166,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.8219,
+      "step": 26
+    },
+    {
+      "epoch": 6.5,
+      "eval_accuracy": 0.532258064516129,
+      "eval_f1": 0.35006119951040393,
+      "eval_loss": 0.9109280705451965,
+      "eval_runtime": 1.6614,
+      "eval_samples_per_second": 37.318,
+      "eval_steps_per_second": 1.204,
+      "step": 26
+    },
+    {
+      "epoch": 6.75,
+      "grad_norm": 4.9610748291015625,
+      "learning_rate": 1.7105263157894737e-05,
+      "loss": 0.8406,
+      "step": 27
+    },
+    {
+      "epoch": 6.75,
+      "eval_accuracy": 0.5161290322580645,
+      "eval_f1": 0.34080808080808084,
+      "eval_loss": 0.9092269539833069,
+      "eval_runtime": 1.6609,
+      "eval_samples_per_second": 37.33,
+      "eval_steps_per_second": 1.204,
+      "step": 27
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.729252815246582,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 0.9318,
+      "step": 28
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.532258064516129,
+      "eval_f1": 0.3553553553553554,
+      "eval_loss": 0.9079668521881104,
+      "eval_runtime": 1.6613,
+      "eval_samples_per_second": 37.321,
+      "eval_steps_per_second": 1.204,
+      "step": 28
+    },
+    {
+      "epoch": 7.25,
+      "grad_norm": 5.042109489440918,
+      "learning_rate": 1.4473684210526317e-05,
+      "loss": 0.9478,
+      "step": 29
+    },
+    {
+      "epoch": 7.25,
+      "eval_accuracy": 0.532258064516129,
+      "eval_f1": 0.3553553553553554,
+      "eval_loss": 0.9087701439857483,
+      "eval_runtime": 1.661,
+      "eval_samples_per_second": 37.327,
+      "eval_steps_per_second": 1.204,
+      "step": 29
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 4.453703880310059,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.8433,
+      "step": 30
+    },
+    {
+      "epoch": 7.5,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.36946595195552906,
+      "eval_loss": 0.9084787964820862,
+      "eval_runtime": 1.6611,
+      "eval_samples_per_second": 37.325,
+      "eval_steps_per_second": 1.204,
+      "step": 30
+    },
+    {
+      "epoch": 7.75,
+      "grad_norm": 3.1456220149993896,
+      "learning_rate": 1.1842105263157895e-05,
+      "loss": 0.794,
+      "step": 31
+    },
+    {
+      "epoch": 7.75,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.36946595195552906,
+      "eval_loss": 0.9089512825012207,
+      "eval_runtime": 1.6607,
+      "eval_samples_per_second": 37.334,
+      "eval_steps_per_second": 1.204,
+      "step": 31
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 12.549348831176758,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.9746,
+      "step": 32
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.36946595195552906,
+      "eval_loss": 0.9065335392951965,
+      "eval_runtime": 1.6609,
+      "eval_samples_per_second": 37.329,
+      "eval_steps_per_second": 1.204,
+      "step": 32
+    },
+    {
+      "epoch": 8.25,
+      "grad_norm": 4.388298511505127,
+      "learning_rate": 9.210526315789474e-06,
+      "loss": 0.9246,
+      "step": 33
+    },
+    {
+      "epoch": 8.25,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.36946595195552906,
+      "eval_loss": 0.9052813053131104,
+      "eval_runtime": 1.661,
+      "eval_samples_per_second": 37.326,
+      "eval_steps_per_second": 1.204,
+      "step": 33
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 2.7072877883911133,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 0.7426,
+      "step": 34
+    },
+    {
+      "epoch": 8.5,
+      "eval_accuracy": 0.5645161290322581,
+      "eval_f1": 0.3831757289204098,
+      "eval_loss": 0.9058404564857483,
+      "eval_runtime": 1.661,
+      "eval_samples_per_second": 37.328,
+      "eval_steps_per_second": 1.204,
+      "step": 34
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 12.431721687316895,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 0.8438,
+      "step": 35
+    },
+    {
+      "epoch": 8.75,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.3732394366197183,
+      "eval_loss": 0.9043520092964172,
+      "eval_runtime": 1.6608,
+      "eval_samples_per_second": 37.332,
+      "eval_steps_per_second": 1.204,
+      "step": 35
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.142194747924805,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.8591,
+      "step": 36
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.3732394366197183,
+      "eval_loss": 0.9042260050773621,
+      "eval_runtime": 1.6606,
+      "eval_samples_per_second": 37.336,
+      "eval_steps_per_second": 1.204,
+      "step": 36
+    },
+    {
+      "epoch": 9.25,
+      "grad_norm": 2.2469961643218994,
+      "learning_rate": 3.9473684210526315e-06,
+      "loss": 0.8005,
+      "step": 37
+    },
+    {
+      "epoch": 9.25,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.3732394366197183,
+      "eval_loss": 0.9043677449226379,
+      "eval_runtime": 1.6601,
+      "eval_samples_per_second": 37.347,
+      "eval_steps_per_second": 1.205,
+      "step": 37
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 2.831308126449585,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.8354,
+      "step": 38
+    },
+    {
+      "epoch": 9.5,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.3732394366197183,
+      "eval_loss": 0.9049898982048035,
+      "eval_runtime": 1.6604,
+      "eval_samples_per_second": 37.341,
+      "eval_steps_per_second": 1.205,
+      "step": 38
+    },
+    {
+      "epoch": 9.75,
+      "grad_norm": 4.90074348449707,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.8728,
+      "step": 39
+    },
+    {
+      "epoch": 9.75,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.3732394366197183,
+      "eval_loss": 0.9037298560142517,
+      "eval_runtime": 1.6599,
+      "eval_samples_per_second": 37.352,
+      "eval_steps_per_second": 1.205,
+      "step": 39
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.8960094451904297,
+      "learning_rate": 0.0,
+      "loss": 0.8464,
+      "step": 40
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5483870967741935,
+      "eval_f1": 0.3732394366197183,
+      "eval_loss": 0.9036431908607483,
+      "eval_runtime": 1.6603,
+      "eval_samples_per_second": 37.343,
+      "eval_steps_per_second": 1.205,
+      "step": 40
+    },
+    {
+      "epoch": 10.0,
+      "step": 40,
+      "total_flos": 50446463926272.0,
+      "train_loss": 1.1404520988464355,
+      "train_runtime": 238.9505,
+      "train_samples_per_second": 10.211,
+      "train_steps_per_second": 0.167
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 50446463926272.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8941be34e68fe9911829fa1e5ff870fac1609a57217ca2aed57220d8a39abb8d
+size 5048