Task: SequenceClassification

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: facebook/opt-6.7b
+---
+
+# 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 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-6.7b",
+  "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",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "fc2",
+    "k_proj",
+    "q_proj",
+    "out_proj",
+    "v_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 sha256:27242ced345b45768279c9e62dfaf41805467fbba343b86ede00c0984c7296f6
+size 37826552

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-fp16-QLORA-super_glue-cb-sequence_classification.json

@@ -0,0 +1,722 @@
+{
+  "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": 22.375,
+      "learning_rate": 2.5e-05,
+      "loss": 1.3311,
+      "step": 1
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.3548387096774194,
+      "eval_f1": 0.2145748987854251,
+      "eval_loss": 1.257245421409607,
+      "eval_runtime": 1.4238,
+      "eval_samples_per_second": 43.545,
+      "eval_steps_per_second": 2.809,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 23.125,
+      "learning_rate": 5e-05,
+      "loss": 1.3826,
+      "step": 2
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.3709677419354839,
+      "eval_f1": 0.18930041152263377,
+      "eval_loss": 1.2128275632858276,
+      "eval_runtime": 1.4194,
+      "eval_samples_per_second": 43.681,
+      "eval_steps_per_second": 2.818,
+      "step": 2
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 21.375,
+      "learning_rate": 4.868421052631579e-05,
+      "loss": 1.1411,
+      "step": 3
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.43548387096774194,
+      "eval_f1": 0.20689655172413793,
+      "eval_loss": 1.1111390590667725,
+      "eval_runtime": 1.3732,
+      "eval_samples_per_second": 45.15,
+      "eval_steps_per_second": 2.913,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 19.125,
+      "learning_rate": 4.736842105263158e-05,
+      "loss": 1.0967,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.45161290322580644,
+      "eval_f1": 0.20740740740740746,
+      "eval_loss": 1.0505292415618896,
+      "eval_runtime": 1.4197,
+      "eval_samples_per_second": 43.671,
+      "eval_steps_per_second": 2.817,
+      "step": 4
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 16.75,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 1.0499,
+      "step": 5
+    },
+    {
+      "epoch": 1.25,
+      "eval_accuracy": 0.46774193548387094,
+      "eval_f1": 0.23196004993757802,
+      "eval_loss": 1.023846983909607,
+      "eval_runtime": 1.4198,
+      "eval_samples_per_second": 43.669,
+      "eval_steps_per_second": 2.817,
+      "step": 5
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 13.25,
+      "learning_rate": 4.473684210526316e-05,
+      "loss": 0.9663,
+      "step": 6
+    },
+    {
+      "epoch": 1.5,
+      "eval_accuracy": 0.46774193548387094,
+      "eval_f1": 0.23196004993757802,
+      "eval_loss": 1.0119235515594482,
+      "eval_runtime": 1.4209,
+      "eval_samples_per_second": 43.633,
+      "eval_steps_per_second": 2.815,
+      "step": 6
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 14.625,
+      "learning_rate": 4.342105263157895e-05,
+      "loss": 1.0378,
+      "step": 7
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.46774193548387094,
+      "eval_f1": 0.21245421245421245,
+      "eval_loss": 1.0040794610977173,
+      "eval_runtime": 1.4206,
+      "eval_samples_per_second": 43.643,
+      "eval_steps_per_second": 2.816,
+      "step": 7
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 15.125,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.9995,
+      "step": 8
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.46774193548387094,
+      "eval_f1": 0.23196004993757802,
+      "eval_loss": 0.9963457584381104,
+      "eval_runtime": 1.4208,
+      "eval_samples_per_second": 43.638,
+      "eval_steps_per_second": 2.815,
+      "step": 8
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 6.09375,
+      "learning_rate": 4.078947368421053e-05,
+      "loss": 0.8568,
+      "step": 9
+    },
+    {
+      "epoch": 2.25,
+      "eval_accuracy": 0.46774193548387094,
+      "eval_f1": 0.21245421245421245,
+      "eval_loss": 0.9923135042190552,
+      "eval_runtime": 1.4203,
+      "eval_samples_per_second": 43.652,
+      "eval_steps_per_second": 2.816,
+      "step": 9
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 8.6875,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 0.9505,
+      "step": 10
+    },
+    {
+      "epoch": 2.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.25513196480938416,
+      "eval_loss": 0.9838079810142517,
+      "eval_runtime": 1.4208,
+      "eval_samples_per_second": 43.636,
+      "eval_steps_per_second": 2.815,
+      "step": 10
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 12.0,
+      "learning_rate": 3.815789473684211e-05,
+      "loss": 1.0523,
+      "step": 11
+    },
+    {
+      "epoch": 2.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.26990838618745594,
+      "eval_loss": 0.9715851545333862,
+      "eval_runtime": 1.4206,
+      "eval_samples_per_second": 43.644,
+      "eval_steps_per_second": 2.816,
+      "step": 11
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.25,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 0.8034,
+      "step": 12
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.3108974358974359,
+      "eval_loss": 0.9636703133583069,
+      "eval_runtime": 1.4203,
+      "eval_samples_per_second": 43.653,
+      "eval_steps_per_second": 2.816,
+      "step": 12
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 7.15625,
+      "learning_rate": 3.5526315789473684e-05,
+      "loss": 0.8381,
+      "step": 13
+    },
+    {
+      "epoch": 3.25,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.3108974358974359,
+      "eval_loss": 0.9614336490631104,
+      "eval_runtime": 1.4203,
+      "eval_samples_per_second": 43.652,
+      "eval_steps_per_second": 2.816,
+      "step": 13
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 5.65625,
+      "learning_rate": 3.421052631578947e-05,
+      "loss": 0.9831,
+      "step": 14
+    },
+    {
+      "epoch": 3.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9595750570297241,
+      "eval_runtime": 1.3701,
+      "eval_samples_per_second": 45.253,
+      "eval_steps_per_second": 2.92,
+      "step": 14
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 4.21875,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 0.7901,
+      "step": 15
+    },
+    {
+      "epoch": 3.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9619613289833069,
+      "eval_runtime": 1.4199,
+      "eval_samples_per_second": 43.667,
+      "eval_steps_per_second": 2.817,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.65625,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.7296,
+      "step": 16
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9658597111701965,
+      "eval_runtime": 1.4204,
+      "eval_samples_per_second": 43.65,
+      "eval_steps_per_second": 2.816,
+      "step": 16
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 8.25,
+      "learning_rate": 3.0263157894736844e-05,
+      "loss": 0.7682,
+      "step": 17
+    },
+    {
+      "epoch": 4.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9644736051559448,
+      "eval_runtime": 1.4189,
+      "eval_samples_per_second": 43.695,
+      "eval_steps_per_second": 2.819,
+      "step": 17
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 6.71875,
+      "learning_rate": 2.8947368421052634e-05,
+      "loss": 0.88,
+      "step": 18
+    },
+    {
+      "epoch": 4.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9645444750785828,
+      "eval_runtime": 1.419,
+      "eval_samples_per_second": 43.694,
+      "eval_steps_per_second": 2.819,
+      "step": 18
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 3.921875,
+      "learning_rate": 2.7631578947368426e-05,
+      "loss": 0.8078,
+      "step": 19
+    },
+    {
+      "epoch": 4.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.961181640625,
+      "eval_runtime": 1.4194,
+      "eval_samples_per_second": 43.679,
+      "eval_steps_per_second": 2.818,
+      "step": 19
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.7689,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9596459269523621,
+      "eval_runtime": 1.419,
+      "eval_samples_per_second": 43.692,
+      "eval_steps_per_second": 2.819,
+      "step": 20
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 10.0,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0543,
+      "step": 21
+    },
+    {
+      "epoch": 5.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9581180810928345,
+      "eval_runtime": 1.4191,
+      "eval_samples_per_second": 43.691,
+      "eval_steps_per_second": 2.819,
+      "step": 21
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 3.515625,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 0.7845,
+      "step": 22
+    },
+    {
+      "epoch": 5.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9573659300804138,
+      "eval_runtime": 1.4193,
+      "eval_samples_per_second": 43.684,
+      "eval_steps_per_second": 2.818,
+      "step": 22
+    },
+    {
+      "epoch": 5.75,
+      "grad_norm": 2.765625,
+      "learning_rate": 2.236842105263158e-05,
+      "loss": 0.7907,
+      "step": 23
+    },
+    {
+      "epoch": 5.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9584291577339172,
+      "eval_runtime": 1.4194,
+      "eval_samples_per_second": 43.681,
+      "eval_steps_per_second": 2.818,
+      "step": 23
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.15625,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.7345,
+      "step": 24
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9615005850791931,
+      "eval_runtime": 1.4194,
+      "eval_samples_per_second": 43.679,
+      "eval_steps_per_second": 2.818,
+      "step": 24
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 4.25,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 0.7753,
+      "step": 25
+    },
+    {
+      "epoch": 6.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.965796709060669,
+      "eval_runtime": 1.4191,
+      "eval_samples_per_second": 43.689,
+      "eval_steps_per_second": 2.819,
+      "step": 25
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 4.3125,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.7508,
+      "step": 26
+    },
+    {
+      "epoch": 6.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9699903726577759,
+      "eval_runtime": 1.4192,
+      "eval_samples_per_second": 43.688,
+      "eval_steps_per_second": 2.819,
+      "step": 26
+    },
+    {
+      "epoch": 6.75,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.7105263157894737e-05,
+      "loss": 0.7477,
+      "step": 27
+    },
+    {
+      "epoch": 6.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9734280705451965,
+      "eval_runtime": 1.4193,
+      "eval_samples_per_second": 43.684,
+      "eval_steps_per_second": 2.818,
+      "step": 27
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.71875,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 0.9474,
+      "step": 28
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9768341779708862,
+      "eval_runtime": 1.4192,
+      "eval_samples_per_second": 43.687,
+      "eval_steps_per_second": 2.819,
+      "step": 28
+    },
+    {
+      "epoch": 7.25,
+      "grad_norm": 5.125,
+      "learning_rate": 1.4473684210526317e-05,
+      "loss": 0.9033,
+      "step": 29
+    },
+    {
+      "epoch": 7.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9821304678916931,
+      "eval_runtime": 1.4191,
+      "eval_samples_per_second": 43.691,
+      "eval_steps_per_second": 2.819,
+      "step": 29
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 3.859375,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.7329,
+      "step": 30
+    },
+    {
+      "epoch": 7.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9849578142166138,
+      "eval_runtime": 1.4195,
+      "eval_samples_per_second": 43.677,
+      "eval_steps_per_second": 2.818,
+      "step": 30
+    },
+    {
+      "epoch": 7.75,
+      "grad_norm": 3.625,
+      "learning_rate": 1.1842105263157895e-05,
+      "loss": 0.7054,
+      "step": 31
+    },
+    {
+      "epoch": 7.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9871038794517517,
+      "eval_runtime": 1.4195,
+      "eval_samples_per_second": 43.677,
+      "eval_steps_per_second": 2.818,
+      "step": 31
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.9037,
+      "step": 32
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.986328125,
+      "eval_runtime": 1.3698,
+      "eval_samples_per_second": 45.261,
+      "eval_steps_per_second": 2.92,
+      "step": 32
+    },
+    {
+      "epoch": 8.25,
+      "grad_norm": 4.0,
+      "learning_rate": 9.210526315789474e-06,
+      "loss": 0.8046,
+      "step": 33
+    },
+    {
+      "epoch": 8.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9895294904708862,
+      "eval_runtime": 1.421,
+      "eval_samples_per_second": 43.632,
+      "eval_steps_per_second": 2.815,
+      "step": 33
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 2.359375,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 0.7161,
+      "step": 34
+    },
+    {
+      "epoch": 8.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9918173551559448,
+      "eval_runtime": 1.3694,
+      "eval_samples_per_second": 45.274,
+      "eval_steps_per_second": 2.921,
+      "step": 34
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 7.8125,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 0.8239,
+      "step": 35
+    },
+    {
+      "epoch": 8.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9916952848434448,
+      "eval_runtime": 1.4202,
+      "eval_samples_per_second": 43.657,
+      "eval_steps_per_second": 2.817,
+      "step": 35
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.375,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.8111,
+      "step": 36
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9914905428886414,
+      "eval_runtime": 1.4189,
+      "eval_samples_per_second": 43.695,
+      "eval_steps_per_second": 2.819,
+      "step": 36
+    },
+    {
+      "epoch": 9.25,
+      "grad_norm": 3.78125,
+      "learning_rate": 3.9473684210526315e-06,
+      "loss": 0.9011,
+      "step": 37
+    },
+    {
+      "epoch": 9.25,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9921599626541138,
+      "eval_runtime": 1.4188,
+      "eval_samples_per_second": 43.7,
+      "eval_steps_per_second": 2.819,
+      "step": 37
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 2.90625,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.8858,
+      "step": 38
+    },
+    {
+      "epoch": 9.5,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9920575618743896,
+      "eval_runtime": 1.4203,
+      "eval_samples_per_second": 43.653,
+      "eval_steps_per_second": 2.816,
+      "step": 38
+    },
+    {
+      "epoch": 9.75,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.822,
+      "step": 39
+    },
+    {
+      "epoch": 9.75,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9910297989845276,
+      "eval_runtime": 1.4201,
+      "eval_samples_per_second": 43.658,
+      "eval_steps_per_second": 2.817,
+      "step": 39
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.203125,
+      "learning_rate": 0.0,
+      "loss": 0.7812,
+      "step": 40
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.4838709677419355,
+      "eval_f1": 0.293480615118042,
+      "eval_loss": 0.9894664883613586,
+      "eval_runtime": 1.4198,
+      "eval_samples_per_second": 43.668,
+      "eval_steps_per_second": 2.817,
+      "step": 40
+    },
+    {
+      "epoch": 10.0,
+      "step": 40,
+      "total_flos": 1.4174270733156352e+16,
+      "train_loss": 0.8902546644210816,
+      "train_runtime": 176.2791,
+      "train_samples_per_second": 13.842,
+      "train_steps_per_second": 0.227
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4174270733156352e+16,
+  "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 sha256:02d7dfc1a5b8b4914415cbfd026790f7e606430bef215fdb07e0b937792ed753
+size 5112